From 37c53b3f40d7fdf2dbbf4b9062543a655449fb6e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ertu=C4=9Frul=20Erata?= Date: Fri, 28 Oct 2016 23:09:40 +0300 Subject: [PATCH] kernel-4.8.4 work 1 --- .../kernel/files/patches/linux/patch-4.8.4.xz | Bin 0 -> 39264 bytes ...-partitioning-for-multi-screen-cases.patch | 35 + ...ir-Fix-incorrect-task-group-load_avg.patch | 73 + .../files/patches/mageia/linux-BFQ-v8r4.patch | 9004 +++++++++++++++++ .../net-add-recursion-limit-to-GRO.patch | 213 + ...ession-caused-by-commit-d86e64768859.patch | 426 + .../files/patches/mageia/nvmepatch1-V4.patch | 111 + .../files/patches/mageia/nvmepatch2-V4.patch | 107 + .../files/patches/mageia/nvmepatch3-V4.patch | 264 + ...d_mode_in_SAGV_check_on_a7fac751ddba.patch | 110 + 10 files changed, 10343 insertions(+) create mode 100644 kernel/kernel/files/patches/linux/patch-4.8.4.xz create mode 100644 kernel/kernel/files/patches/mageia/drm-i915-gen9-fix-DDB-partitioning-for-multi-screen-cases.patch create mode 100644 kernel/kernel/files/patches/mageia/kernel-sched-fair-Fix-incorrect-task-group-load_avg.patch create mode 100644 kernel/kernel/files/patches/mageia/linux-BFQ-v8r4.patch create mode 100644 kernel/kernel/files/patches/mageia/net-add-recursion-limit-to-GRO.patch create mode 100644 kernel/kernel/files/patches/mageia/net-wireless-rtlwifi-Fix-regression-caused-by-commit-d86e64768859.patch create mode 100644 kernel/kernel/files/patches/mageia/nvmepatch1-V4.patch create mode 100644 kernel/kernel/files/patches/mageia/nvmepatch2-V4.patch create mode 100644 kernel/kernel/files/patches/mageia/nvmepatch3-V4.patch create mode 100644 kernel/kernel/files/patches/mageia/skl_uncondition_memory_bandwitdth_WA_n_adjusted_mode_in_SAGV_check_on_a7fac751ddba.patch diff --git a/kernel/kernel/files/patches/linux/patch-4.8.4.xz b/kernel/kernel/files/patches/linux/patch-4.8.4.xz new file mode 100644 index 0000000000000000000000000000000000000000..6d7f4fa56a567e6f527265dc03a5d2f2fef432c5 GIT binary patch literal 39264 zcmV(hK={A?H+ooF000E$*0e?f03iV!0000G&sfajQ2&`AT>vr~NeROI5q(hJ3QtGS z!4;|pXZW)T&B<2$p4?5Uykz&~I{{irkN`}*xpLlc{IG_OPQ?9WZKmmJAmg*vZ^3jU zKVPb;%6}J&Tqm}LNk0p*a3IeKCci}K^RR?ERF5VkxcjV(ly*NgR#J!yC@)@v#pbn8 zswfK<-0x%-T**Wxw(M}TM`>TnbBS3fX|B5)Y=p+}{PXQpycQl}z*N<9gVf6*X0k{c|E$*@)*vlmLM*c!9PV;49PH>+_)_k#F!#FW&MV z<2<`s9keo&s%*8t{ay+98`sPc^^>?I(R^cBLey# zcOT2UH`FD-688_rR@|aNUef55m_Q-v=9-W^u>UXP`)aSU0PR)E?O@6kX<$)bsBXq)EJ7kDGc?*(dMt zW6RA!zpaWOQ}T;*IkUndaZu+us8JVbI-ovA7deqAXFsr$$(P`QY65bV0DFg(ZP`2H z+NSIpP_$XeuG8s1ywir|dH(u3{x)i|7ckTIMv#;OK^=8GDi_ zOlc!))efQNjJDIYjGVy0;7y?5!~^I}KNmNftsK8o}89T*^WC=fj z4Q!+gBv71z%ki*E!KL%5Vx(%IGQfDtiH@vScCyBryRG)|jg=5n)Doz@OZ1I*oJP|y z2Y9n}_>)4foRt!s$9Ngth13hgU~H|ZsEi0YiSKFo_qDXUEb=mHio0cU0JWz+sbE~o z>%@K+p)Us?F4*M#~H_ZO`*i#|1ss01Yi635$Wl>e>Zum()N1)E4k(jn{2|C0#X>R zWAgJ$euqrzaUZG;Bpm}A572Z-2K|_eQf-h9(V0%aInM>bUDwg%O(?N68yDA(1PJEDZw>!bD%@ZJMa$UmU-&hPDrGvz@;#0149J2m z&sY7fuIs#t33o5?YL2O5~8u&|4h&xY9&J0%pp(VS#xdp{a4Lk*OpKU~*C{I5i zjFY=o5XjQqETR{T7_q`@FAy5LaHANZ#UN(gNpR|t5t%nwAaVHWOk&(Y*-MeYkfyL7 zng^b4UKr4Me4JA58VJW`mW{SIF>%-68r;KCC) zgX&#Kt8?z7447$lTR-8FB}=>`CC90QYFOt}x#;ha2X3Ey_%>SBWL8r*@l^rMjiXnT z#Irr-jg35SCzCi-@Fh;_buv4jIvG8Hc^DoeXb|S3)elF@ zb9#B})@DXmQklgoTi-#_*sl<=jkUD2cOhF;$Use}APuG5cO6$wws3x*NkPF1Gz?@S zqKVj|h+cd9Y}ZB?@19omArQ!UaSW0w=4#{zY|i3`05ma3zRy;LHKykOc!&8@CazD4 z)ROsI}=cYe(a|AOQ0l zcs8mAb@0OB$eJ3D_vxIKV7Iiz{h-E0W`A|0PPr3@F23{?a{ zs%@i&$Wz}fp@L!gXBT>|znX0+>R&CN8#ffVh8oO0Bz13O6CSB0BDWc=O<%iQQ~EjW z<=@?=XFxyT*t2q6&p|VY15>HEY&O#SDvTc^ej1n^@bjq-eHF~KQE?z^QWkUyWy5dbT#uWRoxk_O)jVb72!0j}YZb5g%cmc^Wfw{W%x z*i+#QVNvrUv!x_fP&cCbQDh?^N~M$yARxY(QC(IP7Vwc_OIn|v+=a}fQ= z1!zDn3Dxb&bb>VB%1v`vQq_Qz^MMWv2Qy+oI-paZ7I=03Nlw;BWFI_v09{-^DSR%d zZ3((*ZKkOHf1(gn4ac&F-#WouQ(!v`Y#HiI@LG@keNyUR29z-S-GPM!sq^O> zip-J)@{5NyUy*ftAHXH9G=ic67F2wP92tMocBP6#f!2VNPdfi)$Ds5UYBZ3Y3KI^b z$@dI2YXCk`6aSf2Z9=79!!6iRjm5T##HMl%3y08f{y=PHPZzCBHh?NWP*fQezfZpj zfxiTZ+JO(I1bUpkN(b|QmQEo~-`!NRM9)1zaawn3R7b0zGRI$G>4nnxs@wsNs1A;# zBCXS*dc3O`eda1oE`lK>^@*eQp&CVALI(c2KPy|%c(be;YOtU(n%}eAHaQ-)a8oM_ z0(EGo%0;Kk0uK!)4kvT0&oR_0cU^@13u0?wDUGX}kR=+U%GslQm!|-@ZUO@pmii5P z^s$&T_0kb$1(RmtfTST9Kx(=Hf`gOM|43(Z1Lu`~CPwmmA86{r7=Ds`WJO%VE`jg{ zM}tL}b_)VqT6?LFI*%#G0}nVn?&?;ite$a4dEd|127A`N)+3J1;1Yr6mb(e_A@-AL ze30P`NqATWnmgX=$!xE|qiy*97CfDi^buM#G$@uM^NflpgbPrM?B`g__gz@?rS$g2 z4I@&S>Z}f=mjLJwc*A03!1J=F~GpQ06V z-Mz&Wekq%`O-=L|4n)j`yCi$8-*2=dFUiF!x7AuQ{Jxn5FWC;-Q9bBce$Y|G_Zf}X z=f566dM`E0uf{k9pe*IPm%pgjDwFJ0Qtgv($|I)Djxe4)_DK5A$jYaMLS6KGIhwg3 zrhJpVdFd-ss``D4*rh7X-8yGJm|Y;xhg(7(NnBcUIZ$6&;BVg7ssXM@;7cvx1{Jk@4wCQp zId-qof%@7!%YelTlbAS?z0Q{jJ=H*kLDG>G_k;`DUx-7ElETDY=XdtVh2nnEiC+@( zmLUAqTYrN2&xxefkf_EIg&o80@?!WHTK1c@{N*Nln1{8wR1|hSHhBp21_pXmpmi_e zpeh^{jD?o=S-pGMrYT5595tp>w zX73RlDGz2gvU9R1(&`>jNe7O&nFTikVX`t-$9Gq#v)$lx7o8go`yPzp@l|u@0cI(* zYa7hA_2U$*C-@UEj1}VbtRFs1Fw9VaEVvWAY?>Wie#zo{Bf6VgGksk@;TJ!AgX%R=88{?6l+v8$ z?5+bbERGX=nah(-8Ga6TW<#83nRaneu-F$;cv$D)HlE|Q$Ct04*o`m;YNn; zNo5FiL)7~?qT=9?>{3DW+pxk^1uBBp;qH@psp-2IbPY#TsAWRnm)7W-@C#Vd++qmA zbfx$Va@eurx1|YPnQUuEwfhUHW7ov{kc;HD##x#IeI>?HH$z*Ta3`7z4d+<<7*d9) z^o*PBoz#7=fk-jB3vi0R zew4g`8DTLDhwE*!HnpaC?0Taq2u7hEwE(y`@Pv8HCvO1nM`2$ab)mC6;|gcf?6I>jNe;0*`9wv630=mR8J8jeio25)3a}3G4|o zd)1TCm)FM2dow&Kh)s+bVhg5D>A;ICFjPGJ3zz>M+@SWX~&?MRS2ZZ6~=z=g}M zaHnD~uC@l|%%~;)1oBk}Upu@X7A$N^)^%Iv7aZwOF4wM$^9GNie4ki^n>YMUu8e1F za}u2EL2bMW|EJ!s4uThx5Y`>3RmMt{bQ{FL8Vwm-0T=O2EMi3*)3k)fvA}FmGY(U_(JHs2CT|O7ANwi^)X#(1V-O6KEfkrI1k)iv-BHcT3khHTUkc<$MWF_%^5Spd7v)SkBKv<3;Ef% z^$&4U%4vLM`v=?#@`A-VTE&R$&e#~N>5h=ASW=CiU@e$DfPlKLx4$A1H=33Yz_+(b z37}-){g9am-Q16I0L6@dS2(f%*?FeHAtiPXUsJmZPV*k-$6(vY3xx4cZwVHLBs_{E>hs+GBQi8_Jt1ad zaM`l)b%?Om8O@OU})lwhhkSgcc2R2)1ingHwd;r3aSlei=d z>AZY1vq3SjHPcy<_f?38h(K*xPQ z_koTE=)Xfb#3jrvuDCQ|3fMw~uutu(G;BDX$eWI5PrW#g`89`Mw3p~DwbP=1!yPq+ zR07FxV;IFX2Fy~DwNgS=mI=g@9$abjE(CR+eU~xKkH|m>B%=D|Fg4~!7acJ8cKT)} z8dWk}V%aD#FuLJlG+TLl&HmMN6?Ns)hT<**Wgfl<9gUPw1E35XtD;t50XQ+T*yGi2 z_wVH!6i>4~xoaShEU(5%%3;piv+kdC(uF;fK%eX@97Lc1AYau#3gn8H_4kjBe}&9W zcqfee42m^=xfa{qf>^?HX3+>3yR7!`GxHMU8R0BUJK;O0mUx*RsvHz@D9HHsv&F%R zB0x^a;)^S$rJ7nFyzbOHj6dM);h(8uwH4ce1Ax0BKR81 zAq8dJkZMb--&?zQC)t!h?CR2fcMo=#E>XiSZTi0kE0sEXCxRR`wzfZrzL}GDk8ih7 zF*t6J)#9`b0F8iDy~^1X==$gJ{oNOwNk%bUxKZW@h>9i;Dp8XOo*TZD@di0{zt0H% z2{9gQIbSKo$@yG>KYNza=u^DoT#T2lHqpE;j(P*8oYV0Ri%TYy;J0wNMP<&s z@7nbsRH!IibW7wZ>)LmBAXtG2+chJEBh0D{Ni~)FX5-EwIfMYVQnXXm17JOQrBMb& z!W0VJKe~Y_WX4r^GCxcys-O1Kryy1xWtjLwU>{QXX1f1}yyz#zOcYXFYs!1vz5-S)PXGz-LxvFZ3IZ#{Ze{kBs{mo>#HC-u}jlp(1OEwmBo4myv z3dYN=z)sosT~Q4Gr-8+&{@ac7NQCiMIkB$z`kJ-UYRXct++t>R!L8jUy|h)Ac0YB(ASM@eL}$t z&Bkuco0Jp}YWNlF@A22nFF50Xvg=D8Ye;?|ulK#8X~2Gq21xMAf~OO~+9 z1tR#r;&MSb)p7)`a6oP_e#6M;P`q6P6j?*F6gtq* zIAr1zYZ4gc$4US+vgZ2J)y2r#+4rQn6R+r`K8{F>#1&S-K!)uAr9SJ&z_j89X zh)~xSRG))CK&~UjANeD=v(+({>Fm)-guZQ*lzBdOhfZ|bAnTkI)Ils2QDw?6FU651 zgz!jW)xouQUe)9_!V7vTCam5t)rFZ$X6;N3m2LNKN>PM6ZNA5-T#o$|d`Q=JsJJd~ zw*5*R#aLUGFftd4O1kUUR$^BoqZN~H*CNULs?#(y`MZGhO)h`UaAU@UjRc)xYUd1A zqhLIGx!%P^wA~$To%{mj0?Y;XTsKgEHQ;C6D#BC`{OKFEvD7MI;uPz0_|?$tibMLDnEj^ zkt@ab^$HDN+Thv_nc5-Kge=GA6$x4wV&#;jX5~bVOO>6S>?dVqx+T5g0-k<5#5J1N zPn7Tnw~TyeG=F~7`~^yk%>BFVY35+2TcRcBZEsT1)95unvzb$F*7r~R#TE#=xsmi2Kw!A`HcB<@WG-VX*aj*RlmXd= zaKr+($JbIV^{V*J^1s%SB3X7##dnSSFLg5CHLa=!ove~ylCR9W1v+mwZp*4)-f=21 zm>vZ@^vVp3T4fY0z)lBdM^Wn2lsSJ_-Q3*f8+hDRG$W%E*`sk`$}vxZSX&H`;$fVB z+rb?ZH@sLr;wtNg;!5hT2O1nh0?~>&X4TkQu5sn*yWh!tKddH{WmuKm$_-6DS7UiK z|0RQr#q4fl(u-(FPQ>kn6b}X7l=r00f^ob4G3TpmG%|jTlLa<30p}Q)gz9R+9eb27ADV#Yt2dq42? zv|{}{j!R^Hi=pka0|PR?LVr>*2$~8VhaYRQakMH;VxNw^BLrUfzGvo3HMH6&*_whF z{d|O)17nT_j-31!`4WF^BP$?Wb~&P?j5Uhl*Janq_gxK-9luslOGc z0|&d>gq?|7n~kyn?Cu=^wsILa80RgyCs&$*`!x_RHjV&t_nrV8BS83!Zz6;&5yupT zuCPFTF0W#8q(6XR?XweM$NIYO-Mbd~OhkmlidcpTv!@#E&Z-@CYnxR=F}IexRSYZP zQk}9SqFSCF4z?SIf3RzPvU_v2W9fnkYqKg}xA*cD*2`~Yd=GK|;owYE8IJ4mCda#> zVqX2}NuGmQbiYS&*UF8dy-A7ILV?SG+@-R;TDJh1y%=(e=t*HcjE-X}u85qvawLN{%_hw&PKYHU#;?=Y18n1Fou9W)lM=Zh0-Q_y z7j1wBSQGxq<#z)P2O)bpnrU%V5>1r>4)a#xOCeMWeH#E&Qt-VapLF+6qN7gQHexF; z4lv836&7!k(P>qSL?=$4L2aW{ z-@UN^#I_si@jB3)n(Kw>vq~wK8sPfR@MluMJOGE^tsi(e&(2k@#^Rth*G7WfU(~5U z=nRc5q0zKLA?YjTA@0Buj95-xNjLfLcKQ0YQQ$p|c@*6|yG*66J-^aEF0&mEz)?1& zcs02vfp<#N3KOMR*RTvi#I2XfTZ$nzd-?iaZXIGmHno#1Vqe=Vf43xAVg2s`!zmId zNNkyyDA99*o6<8DbNLzg*rZbnxJ#~l77=;*C>x+&cvSU-V-a}Odt%Z+shc?wx9`fY zPZPYB7Y*D1Jg>UT&f2qz$l8aLm`uzl^*-^)Aln%3WdhKmORcPJC(Gwz#LwWe+@vB^dx4ajl6J(`F?mNXnf!hK~ZeO0YYsx4O z@ucN>v~L48==NM8T==8q~KZj=z0EAZ1Jb=F76nNTgj=c3b zxg0fUDcS-yiEo>lBC6|6Iz4x21i7gAgaK7mN2~@JJtTyN*OGGC4>@BtI1thxtw=|chNQ{0;+50#R-8EW-~n8x4>dAS@7!vi((Jpc#v zFdD%0$SsK8*vYHEmAG4_GtrU6KEbCH)PFMkII zA$8Mo(a)u*HNDSoBH`XNMoT(4o$5d(^t|?vZ0T=junB3}3Go>VY)CBWK3!i^j41ss z#5v|q#kj^ri5UeR=za#(95d@>Y1!FC7=4rH@@m*U7$jCU)IRsApl`jetfo_e0%bVJ zG{)V^8-I1EBA9XCN%sz4m7lpV7J6*F8J)xhLN5dB2ecIBP$FeLgINY(sUA2yRLbk$ z`5T5YlwwE7^j=284Dk0~r=|{LZq3nSCT@DH;{i4uH9o0tNH_Nv<%9fGWr6|91n&ZT zIpsmeVB{f0$q-RRk6tXA-RcWA#u(gdzleCOf0$-tbAUq17xxhpr4<*N74Mj?gmTa@ z4Q@Lcp!l4t`aqHRLl_i&jtA%Zx*4`5tZvCCEINmFt3kPD_dr->Xgp&)(^w5=-A6Hs zjB7_OhUtWRRrhBS-qx3OzEKg}cFpXR2moW~*~sB3QIEqSDWvE(uw&m|Nm-)#NaYHy zzkn$dd27Ro$8_05uAc)*QtgRfW)=?rlmMN+?>Pv8gHf-7-3>YL>jRU|6GbG{a#=$~ zhxO|eV0km*p`|O_pP76xjVNNLX}-w^U6bYSbwwsSX@0dTrGY$ZlW1i)h6JS7N-xzC zC&lnt9#V+6GSgKZ+Q49VUS_Fct+I)fG=s)PC)475_R5v@=~K!emBX&+`E3A{(>*T4 z?8i=#xl+4lT)s6{P+MTy4og*QJgYX{E!?p`ZS{^{Ky5sY;^XvP=zx6wD@0$(4U61) zRLK_XUE~Sd_qMw%#@u*1vj8(_4I(hR4S9nhsU(=Zffe5_a!@^#jOBo=v3tehpL!xB zHboz46Vj5eM*|8?&TygJJawwH9lj3J@=*9DN#?!r)~6bomW13eJ319cHdHL?#9vdB z%F*g76-l77AWg6&_S#zv32Wy0VF7|_Og`~jaCE6L;*m zmA!Q-EZA(Rxg2C6DZ_70s`Ukp-%9R6?K6EcO7EjzXQjTu@q-Um-#th>v^UUI0sIfw zVu^|fi-8oe+m`3}&?A)iAJtGY(5a`myIQtViVRsG5d%plWn^c?KhwyCQ3)RKl?uca z7Q@m@6<%E+PO24;!#okUJjb_Iw(stFP;T%;%)5YYxm}+UHY6UtV#K`gUP&^np^V?) zn0vo>EG~!lflU>duB+hoRX@EkOo?raDz@!PPIvXpSy8`+^Ay|I)l6pd82piyF(A}_0xXo zXRV9MYeH2gL7AmILD{d_I0Q0E^Dvg0xX{V&&=8MUHY49y)e@Y ziCR`bob`ZMHdwQwDwaRu>4|u5+z19fyZ(rZMKh5Gn?89yO|&dXIq)r~firF?;ic^5 zG(@^zFm11>xC~8!FCmPGS!YlRiKKs8KCoV;IRXnGS4JLojTxABK64UIuPvpKPlFc= zm~<~ukK-T0_Ln`Ph(}O;{x~gfQ<=Z zo?`I7gH6%-1l$L<$=u-5qj}{l2n#z1RRkqxi$2OZ^G#=;LQi-~$WFNPdb|&q3)`$M zalxpkhyoOYe`!}qd+HTh44>!NEj532=qZm{yHoVpios92mpYE~=!yV^%T!sH zzz+@4tUu958~gSdBpG)+e1$D-_Y-cuPjn(L0^xk{hQ36}77IUMEeQv79_GJld9gfsDXv#Rb#AZ&VP zK=6{Bx?I|tC8zYhN>*YwV@}(pv?9Y%fCfE6QyRROPt(mY<$*d)H;oAs+jV4MDWPPz zcBHw80!EhBlDLI79w23XHzEiVgn;!!R3!`btR2&>r4VP-zQnqjA zr}J5Ntx0Z;)8YD5*TvrC%+b`a2oJ~n>Q51&RCwp`Z>(B}eVe%$NWTfEE3d<@g7hQ! zIE|51JBuL{uk_MPrbS~F)`_moQT2BL*J8ICOy7ft%5vxr#of|sE;%Zs|V8eF;fsTLYg z2MT%Q@1RZyu{JVuo62v~_jm(7LKDg0^Q8r`eBnV-F1_MD7qQ=`a|0x%_&NP16>aQa zet|D1|A{F48;R?SKqc$S+VxOUZA^1A_Wm5v8!m7a48R(y+?ir>t*IgN^#dT%{|CC> zYi)Z-uc8pR*{#>PD*k#BIkorT6dhWW7ad8tc4#OCY8-4FtHaAs?#hclC|s2u%0=veYpZr!JX8saox^9{>+&CJLpP-u>h)_o%OYy zlKIlT3A+TScnB0*mMB}W`2X+)J@#3RfC4giTaoVr2wWn_iX?hQ+Z<|& zsFiM8^FlSaIKTrwWuVdzl+k?ug555~l1qjp@Ikp6bjq&-QD+H@pPq^N)J!XgLOXvD zn6WcQ-mGKkN0mj&*r3v3RPt)^bw+s9_3qTBo-dETn1?&Yfumfng`k9#6@Wfeh7)eq z5*ND;Ma|?XJ)*$84d)~a9j{Z!%)r&Zq;3B*@<`Eki-LX#PnW>~QbOwz4*^d8g#|q| z=-3+#A}m3qPaUUXyf*(JXG=a?rEzT@Tt}yAiiCqCpuhyAq#OpxRYsU!#^}Sm^T2z$ z^)8n;&%Mc>$Y*Et0~(Ea@?nDl6}2ZhUZ~s09@xutz@oq;@k)Jk)FVN}L3R`;S^}HU zgJasz%tl|_gVxg&=+f7p7&tXI$#GX0H^aI=AtdEAO2t$SwbEhT4c61bK_&sQO}lfy z4|6J%KP$kv<~K2o%>JcRXjGZX>MPe#?ax@#RZYjg;uvAvInj*ps?-tI3Ohs8&AUbb zIv!quq9AP{^C3SOfT&(TqF0qfJctMM%m$terZ4J(0UgDo<@M;x|rneMrf zF!JSZ23LMSqE$)W86_OWZ22RWMTn57y+TOR-{%QTmYol5k1^5pg@l{?qyF)XSOPaZ zBJ_p9Phg5VFEW?DKK;Wbky@yk5}u}OOe@O0B!skyOR9MM?Q;IfUo2NKbHJCv)f{@m zSEnW>@PWxP&{?-?R{|i?{a@FSLw@}Ds3uA6Jqg#_J8l2@;?o`6UO9%*@h9(r4@6Cw zcafR5=Bdc%uPJTtR*6Qa@%Vl+P?Q6EWHd_|b&vS;NCaNO*UqVxYXIs%K^~DzOX|ILIJka{9oEMy*$zdNp z3)Ig*&m{2!RBpOj=YqsBD@XPY^0!l~N+>vG?RUyKnEdvMT?k3AQMz54R8XH^NKRT0 zf2;%fDL6|cUc%pTw3>63z2*STNlaPLB7YPLy})sJ0tqy8GSflB=Ypwx*a}>Oa0ZT7bOTVuHYlS!$X_i! zNi6#YZO`*;0+{}?>fD(iqRlA~n>@VDrz1}_I*tNcDn6=RL9UKHL0Md_c)-8lLL9v( z%s|mNVF#P8Rm3eSs{B1j>*+PKD&ec@KP)IqQ_;7;aKfpl;*i+YqMWZY?_D>=@2xUNAjJSv1X}IZ&~yOdN^x8Kt{k+b@||A*$p% zNw-w+>wIIG{|y>_P-}4&QGlJFCHHDX-03%{ryl%G7`@b$Lx?tkDYEk`k!PA9hkBa7 zDq17ud%67efk1#yBEzQ7Y>u<0?ych0X@2?8yW_dv9MZBCg}yXY0r~x7J2_1LU=v@0 z+84VMK46t6N5N6kP@SK&k!5iMQW~#6;!J}%_Wx^S1>1yYlC?R=ZSg>281=~dUKh*~ z7ISd7qQQ^msMC34eZCE5eW4|4KCrjsegXr|d@*ifi7ddDzGZeJHuPjvTkwe&xfy|w zv4A&smM*Z`B(BN|XD#nLfFhN-1nt^pBjkCKN*4*FI|WFxg$z<$60UP2GVst9ubO5W zfm6O>7M?%Fv5Sj>{rT`SiwfizS3IXWqw$CK!WQY?m0hNer{paJ&FWqqKY&0e&^l`S zdeEVQ?Znv+S?RWo04iOeUL&E9oKwXJ6Y3oF6~Vf$ljZv=Vs*Ok_(#(m+7Mp6cOQHC zuBT^firp|E-tJ)G6TdxkPYz~ekN4LIwVYhxPyiWkauW=IL$3^=AbmlZ%=9NbIlpI5 z9H8EC`!~{587lYvbO(%+l8>JO^1n4j*Q%-V9q`xwsBxO8wCmkUkrv znk>C6JXk#2X&a8(y}8Hc2OL)_#|7JoTTefFCLm0AXmNH)+K-^DeA9qc^c^~Y z3mY#&k{Xtaft6MVw*>BrJSM~;C-oA|74cG7(7Ip z!69ZRPu#m)C9|>+T2o!ENV|n2xvf2n5Q>*Q%wY@-lay{^Qi((5&5m^%3}kCc`w~(4 z^g;f9xNffaHPb4;D6$jR$(+ht` zumBIAXdQP&Ng3lCPd-zph}$dO9zwi5q+r;5@iPs~HPv(#>z`40}#{fHkvd1=f8i>Zk10%}& z+s?pJO~Agro~d%EudyMj^SE{u<$Y`c02YnNBR>+~)povcNjN9&RvlnTKx&*SfjkRk zo)(C+NHc@Z#pv8e3~%yQM-X()s;3cgCP#8M{3WLocc({%jj(P1UqAW?-Gb1ElzlZn z%k&iAdq|ufVG38e%dU>)O?iDR6LfC8~sj_)Bt1pOC-7~crzvh*_v0QBXWW+*% zXZ`^>>HS+i7r$a7tjmEN76wa+yqXiP6CY!5!3tPTHW)J0wj?2w@I`-ym3z3aB1M28 zs(uN_=?j)$6&Uso6p6JMTbgM_K~ASbj=r2VBF=ZIgWR3?z5APeP2pxoGg@x3sM^n4 z{~th!kcrkW9K1wd2q`AA5Zg`Tz0}L)~S!+5omg~O*ZL;-YT!j)x7ieCHcm+ zHf5h;*GTiL|6dG57n8P-9Gq6)*XC}+;1$ZTs^a!zJThO$mJYXMAOlOhKv+l{gHjpl zx3e~*e{iJO*`tj93`ZKv7oUcg^8z;R9y^VHR6%Q_L5?sM*!5)nt~$);w- zG?kLEo=q|+h@_bZ*@x`h;sgp|CP_48z+L4L?4cp$X_5(ccu{H=595UUD}zl>3Bqd>mE&}yo>U$8&kj5Z$wXf*2tjloj7 z@&2>D)fOVQ1K~cyK^bb0Iu0oom$afeRGm0vTAGiroRZfHx65HFl2oWz6`I;8W$L^@ zap+gZA-^k65m@x=cmO*RH@n2SNkdIrD z_3}}Sq=V`JEE{#~QKhxq;B>}U>wU6n6y7@=L}4F@`h5$MOgH|CK5gj*Bp7Cso!c74 za1#+KD&cN^A={L5?vQ8*b6aNDZngXFxCY14vI#h4*n=l5ASn8-QW3 zAbLT0>0md=J^=djcQrGC&1GItK0&2OuT^(AC?7mDZ!E}Qq^6toGYcT9=!UT8{XF`^ z@1^?JHMpgt!2Zi62xb@XYYa7j?P+qM0Yzp+$g&HE@&13CVJyNA|6q&@b(%y!!?lo)6sYO+8{@gDiAr#fx+1okcO zg0QBS4-~uK5iWDsc^{}R=!kH$DGYC9 z3dLa)YF$7w479$BNc!wb3LCMJc+N_lNVZZ{znL^mOw zAX{)cf;L^PI(TKH3{0x|FS_*?AFozx|7}WJqxxpJf4 zcmvy1`v(+4oO|-$Dlqx_69x{5D#Y|GAsC}e(*sd=sjC8>Hq8VvY7438w^|hI?=^6l zd@LAz)b}Riqnj%-0?)T7k$0Bxymg4B?gE20&=KXf8GU}*|n;u73^1gtkPsG zX-iM2;NWRLrxh_Zn4g8AH2ZzJpNZM#(_RkX@;!os#=p!k>%~PWAN2bpc8)sfy6|1g z=~%r&{Ib2Jm^KFmg5nIMnK{z3PMc6{0hx0fn%#mF4o@x{koajNf5J!S>Yb{bB_>cE zw5#rqHzka^F+VXd9|<;kczDwnOU+8V6bII&O|ELl8zVZ6_{O|DIP(^f!5^`?&f z3^dxm^yJ!VVmW_k8)so3?q9nhXsUO<`c?e!>iu*|JRRjWP+aU1TS*|m{JHBxXX9V7hfGDZfi%@({#Qr46q!}Z}vbu*u0{PH^+lhjzRZH@I2Gz zIokDq3QZqfy51bi)3qo}WD`l2?HXVH!|uI#gj)VAoLABg_#uP@>PdPw&K|Y3Je-qj zR3)e1-x9hmCUj^m8*v3uB}NyoCaX~EgEl0fxzYw8Bo|_+9RzjW%|w}V`s$7Y{`L~$ zW^otUkxoi9=Wq2?%tfBOPbEQ_Kr)mq{hd3h)DS(hQ-;7k(R+aut^#yfA5ABl~PK0z~)!9XIp=b7g+uhwv#Z$n)8@QLNDHy|`0YmLc<_^)S@V8M6}hDI3#_ok#j!Jls`{8`+^`Ytn5EEk7e5qHhrU zqIFH@Z+-6DLJUmO@sG=3(QYg2NC2#xmvLd3i>lXdyN#7Asx)(V8ZE+(F~V?|F-V}! z7$=8|+dh&hRF|uF@J#2UhS}gt(}Ix`hAC}Bq5s{~;k)Ks^g-cRgJTUK5@Fql3kEC0 zo^;@RTbHWN1x}sNIPoZ@`PZlaF8>Iek9}RV=yv)!w|SW4vVm$Qn$@?~-pO>9XoKzn z{pOc91xt(V8m;%;bDD(lq0y)16b0^|&hh;|pNOytOxqU)WUY$S>|ouCxm^7@r-KJj zn#NtypK7F6gC|vCX>{M;biSIJz=#i6cpSXmt~~Cw=FTyG!q>yYO(OE2ASPCS=)&ZW zfjs^OeC@C|xtHao!`f~}))U%~Q@#8^FS>YH0dzGZD%WGyR0!lJ`B|er)+li18%ec?@`$$jqnq=3 z6CBJ-sSWFt2oVJht%&87_~hPe4;LnAN}T`&Vt~}|e5Thcc(puuEBrz2CDNO1v8S8a zsUJ?vFy>fk*Nl^ch7!MVF_3^o^#IS>gaor>9)~F2fqSh??n&y^l?|F?FQIM!7skL6 zhDrbOZE-F&N30p8Ch&U_EULqM>71N6%_d#uD?177wNG7tBnxJ`xUE<5*5xG3e|cQq zsNnLUzhS;4g84Qj^Rb8!%(0?>~EDO$d`Y z)KSYxq}lV*ZO}69Fn@lt2i;jP5x@Fe)~A^7AqLca6L7j1)$Ye&1ngF=;QSh}^oOF1 zam3B883}O)&ElBY$^CkUT>jXsBfj9CiE(J=88GPS{%K^RR#sx>s9;JBB7xX8*i;++$$(5O_)?!XE7qk}jBui|| zEdvvMn5S@4**M<6zs)Cr38uu37c;JNmT+P=*jE!$SoH z-Z@+?$CqEY!1Aq#O75suY!i7r-HH&+TxL5lC};6l{?)*#ip7G!-2IU`_bXA>xD-M{ zz+%0+J%TxG_m34#pYWQQ8543y;jnaCi)Plk+HIKqoy0wg(C7eC)7w^8Bx?VWI8}VI z=^d&aCU^E|C}AR8E4bn5kyJX*0$X6^xv?qTf}G7pE?FX_sbdkhevRZ8`Qcjc26Kjq za{bIWuw!6r;CRY>tP7&Q5XPM~Irhs14(MP$CpY*qn0dv$JpC0QzB>y@lOhzeY%N~(Uw}V}hAYg~84jp6Zp02gCq<-)d5nyTfis-^R+sardKr9A@5sH#{2+Ul+tDviMUD0tp(x(){(uuH{G zn=fcm7^fqz83&1048Oy~4;TRkb_t9xF{dQ@iVaK*IynAsWuxW*4w>ZHLe=)7gD!l= z&QC!h@6Lmp9JDM)h?2H89r;yGaK?Wh6IKB-PF^It*3K_=lFwP9trp2TeR*Kvsz-`) zP7wt-bVbXcw5Gmx<YWkq4SqnOo-)Z6gZRJmLK6kt zFRC`Luci;;a>p4-JWV~WksnF!0$JDB$|txw@x#BXha+NikJ>+LAW@RRm4}{Yv&KG> z@v==DU2f;f;mIh3Z1)d>UhXx^Do$b6c4_9Wu9fbE90hZ z3VtAS={2ckjX6%PQayNP4j&;`jn% zU73i-Y3MOa1sN}VsK+wb0L*Ud)Uy>iWlF0+apZsh67NdG4BlfT*sn6~wb0tLtW>9R*j5bzu$*<1P`F(^fE<}$Oo1x`zM^a<|J zWc&QuhTY=^Ef-gfJlvJKTm;esiLpi5+fs`qtL6lO2Ru);k57vVU)8L#|7}-Ay<=HSpOCG!m?TP1`Rg%J4A?zgA2~o=m|)5o3L`a9 zmlmtxFTyLy_`dSwb*7vC9H*TD6UByb!QdRJgQ;g7;ou*{1hS-w%W9ZfZBTk21?iq# zUYhLGTcK zojH-tUGhgF2OGDL07EGcud@Ok*HHy*ElJ_n*lkw;qJ6MS!^+P?bFB=` zsZWGf-!GD>!~LX)y}lvLH5ZyyFADOubE_|1KH9y4?F15yqDeLQQ(h7CR!||{>!=}X_N+G zeYwg^k5PYZDTdV^MlVeK5LKe(0|EOiJ}A@d%daqh%8W;%VBb8>*-U7 z-#pUE_x-s_)z53PXu+#TxJxy0*g(hvM6i;x7K|c&*F7X8OLtUKA<<60^~=D<)l>i0 zs79xcaBA$KI?9pUwBNDXy!jZv2^Mit+&~!t{H}+x){i%1689o7Vk2bfJ@5*nmoB;u2;=NWKw&~EJ$kwWBbGXQ12|bvuJKw+O z2C!pBT~1Nkfl|xwRZR09z_m_KBD*H25T11SCAUh?dIHv;&_O{o$9?1;Pg%Q?5iM*p z>#)8$z~Ojd59)__oWu1rDDU1dw|XLsR_V zCU0w0Oi)AnJ>i4Z(7#M1S}3V zML9W0(!v8O(6xN$>8;HT=_C2vOVj>%8W4~Wt!@8xxqluwmp4f~bEDk9#%*RQLMeo2Vf@CH8jF|SoANkNGmS<4(b;T@|k(D zQSHA7VQ3SvT!{mIZR=S;Y5-#}PmR8M?K=2RUEzlW+(6J95}nDJVD&2U#?_MjgQW&e zb@~buXa7cx;?DZ2H`XTgDq2=pb_IOMFe`O>-zOi*)@Vj5My_uC#Q9NSo15o*?{0h67=Xq=Hs21KTsO7Qol0z%r+k`X7S_=rvI8 zkB&L4Xo5&7tf5e_;uCy0C)gi>4fX&A{iXS+Y~tPFJgd>0kp z7!+5W)gF!-K25;A50S+q=+lU$5i0!%uII+-pOxJMa%mAdP%pCIGIGmxrilnFr3#=q z`oDYZYVRJkBP3$MSUH9>Z!Kh%O`^tN!))Yt6tk|)OYcKxgmzX$S0L!|@ zIY(C&4S(?}iOk~k6Q?vdb536NG~`GOo+*4%ii>mgJzRwTRwg~e8dE&Zos1G8?Rz1> zb^{$-wA^ma3#|i&d@Zc7oxkY#O)GK`2AB6|px29gvC^N1U67C?1qY5HNs~35E!mR- zgc3?2oTz5mbDR%!brSEe(8#4~Jt2f@!uh#r1tG2}rp;)iT-IS4qH$Hwdv>W=A2yAr zw|l+7oF6YJmaBg{7c|&5c6|GKRH5YiS=zlqPz>pHBIBl#Y>jC)?SDpG+MZjef9}&8 zT6trnkPB*ir_oG&(W4+)nj(DYiIYM;!?!=1l$UGE&6P;cH5kHyF>Ihy{1pKQ$J-m1 zfm%7C9wF7YSw(Xr>$7Gx4o}DEWwr<+{;)<4{Yr*8>tm^cLU|srb36G>WVft4y=C`X zxMO)t@?_6$b&<#a>^;BbSf__PPve*^A~>BeA77jeoaBYEmVI|s_34^_2VX~0rIupu zl8E>xC*>FG%feTn$NenVFmq5SQIo?yJ_>)(4!s>KxqfKJM;WUP zlAdm5su1`PpF@#(QN`<@BWNZRHub9_A=T6GXv@pC)(GcZU=KTk6UsnXHxOTPWSA>M zAHvEhil!z&`0tH_9;dFU8n5$^k%hftX9nveT;HHF2uWRS$G4u{1M zA$enEfh;efR!f!#HL8(@6LQ)x%g8-9e*s4VPGTDi?n{HhdtGtEq_H=cniAv!#(6z* zKJ5S4< z$u^*Gqfx{CZoL|nWID!sT=PAZvaNkZT&qaw6ZmNO;jY~<*BhfT^*Sn^%+HtJZLmiB#~LvZGyP3IsO@*V z_)ijmecUQGBJYK$W$iT=-l2H2+a-Z#i|W(*-Y2X^s;$^bxN1151y>TvWN9~NTYy+T zm@!T8!_ze(Rt7nU2A)HuU5Ox1a70_>gbgwo2q zlsQ0Zabo+*Ih{0;XkvD|Ia@r>XyU7{4R+-MSQ^8#Q^~`^m<&DyWf#a(Rf2bMMt4t4 z#z-s))jpri=2dcD zz`_#fNItl_Xl26Izf>K!eQ?x$xr!bp!``ljp&P=n%lOhOBrSUcR03@`JYDcd73`q7 zsGG2+(@{|{-&{mFEN@-grK%e}UZy4~Q}49%6k|$E*53b8D-UZnR!dV3t~ZQ*$$sHt zAC~g?;xI*Lk)F-R{aAfGBM*J+@?0|QR5t!iN{B}~I*g{K(yLL>AI?+nm(ZW;WK*Ql zosp_&HydwXuS#(gEPb3~yjq!DCYK=T$*2({`}Wc_wV9_9inv<7kkY6ve<7Uoay*p< z;vpmUOUsKGyLs4jAIp4%8Qc8SIT|ZzQM-WcWMuzXF1K68`rt;hU{#zBU-VgP6W$d^ zIKG`F!A9$rFBQyF&K>XO49t|BsCqB4bA@&NPd>gCSn4Tm@glJIaA}l}D&`ld6clH` zD7+U#wf)v!;9GP48v_P+ClVH(wmnldikQt5&W%F3^o_rdDO@BiC?1c8IWQn`xFI^~w(*4Sred?5I?PChWGU zcF{%#!}aBj3UvUkRJxRfftu+u{Q8EQMaF@wgCVO`nz%W@P)&@ut)_yPYX(yd=dc7Q zFuYrAnpjB;=5knI`!aefZ)jnMGt>}HViC3%-Dmaq?D>x zD+L)#hkvvWQZ)4{9IycMZ2UF3nB9UG!F_Grp%MeJbdAi2Cd=A|LWHr7ran;IxOz@sVv&QrqmE6AfN9)(LjC4G^ z=}5KNh_xd6jU((Zt>f$W-GK0v2C}q$9)K%j`fQmd`6E!nTYmRA>Zkc;b!P{ zS)Y~@;E>-HXN$!d?Ejhw zkUMZa?eWcz7P5#(x5xDbxvHYb%w}&O(x!jRf$P%-sL4K+*IP$;fOocS3lt@Xys>7+ zWWBl*mu=@PQ$-|A>6wf%)k+m|txQbZw+E(U6CmMp@9%FDv}1FotlCR@Kruy@`u{+4 zy$)`GKv*=+*Gc^*VMrISb=*7}bf}@~ZaU5RYMv6OSDF5%p`Sf%FQ%P?%kK99)t@JI z$&P7~AY!rLNc(2~+sCT1poN>|JSrw4q z5RDB_*L}@Y!TI+@>NFIL3fo|XZ!Dmi9{WqtOyzm+4Khaaz-}$oV5^3d zh2x*`w|(NP8T$ERTjy_7cNk>`gRC2Jd7`2p>nnZIP-vXYy6dT0&G@jeLm{CE>Cx2> z7zF(ibVCfycDZRO(B08?zOEq5f;4bw(i~uNfhjDKISXohAVqAC4wj7U8cimGP`y({ zval{b?h#+>zA4?CgYeXDIZ6KO3nha^sXjD6nEgp~;qG!aMLi59;E!1iHb%A@6&~cJ z$oCm&;kJ#w5VwxjFy@yEwdas={!1zzkM?*^@=wO_WzZno(EvsZ}??{`h{g0mi|boM7UE2 z&d4s5loe~aC!+SPXV!Hr9~c`ardmVdJhpN>zjRrVbPp)MdV%PDS|J+R`A=Wr$^&-ZOwvVgxBevz| zai*IYsAH}`(UdU&-}oW{4{Mslz*rh@d1W`y{20s}gwCuAtFduYp`<3E4YyAPZ|iaB z{tHqVj%9*bvDQg3v5hp|^D7XlQu*+{3my3O4Hk(Q>h_t6H9S*Ea?YL+?K7DY@4;q7 zY_Owxvv>dAr|n77Ruex2igL^*C(8!vV6St=C{@l-j)|aNr){G6U#_($q!dQf2j_vU z=huKMJUtD`y6*xiAL~x-vHz745~`H&72gN&>yK(H)a&U$%t1Yx9FkgDTe(EO?&{LI zR&d0u2dZSAM$3jp|NQ@Y6_UAANG%o~-&T;c>lzK97up)UB+&#A2!KslCF@2#G7FRB zh!9^Kt$$LN1+DoXP&TJ;`NSNpZ*&keA~6)_yHuw0%iv&s7W;t-0xjXwiyryax=B$@ zyQ0iWKAA1l!ISqVLRUG#rs)8#2*T(dU23ZwfQ?1-bPe1kBU3TZ_H+6*H4IaB<(CJs zJy~A}G!k?Z><1bOdjt=`^#h@ZC}Do_Z8@-@C9hZTj7V z`;SJ|N}6e4blJV;h*Q8uigh46Bjp+rj!fr2uD~B0Jie6P#taB%6J$laE==gS2aAu^ z;@aDemy^m>)2HM}C`yWhKlV4EhjS!?Uh~E`GPrBp)OFUaDdA+4dqmqU{?dG1(3FMT zPDSvB$U6tvm~G~+a$3UD*_PEdKYztUW;%k8N@8|s_I zse8slI;V?);_dg=Ir>CoVhucw3bnsvvK#K!na=DV$G&->B+$LQKg6c!@vF48H zk?Q)-b<$U{&n2Z-l)H<03Dmua!T&g=f;S(?+Cn%Cs(q*UE(B@gFkSYZMJph@FMo38 zq(ySRgW#wlTU*;E4GB#W8z}KX3mP7( zFxSM|a|G(oWJ_=FOa^wimg2~{3hCsaxyZcmp>v+4yE+)W3BaLz?4bSieq}Qw?-dO4 z$c}H9vw&oSVf14#WOl`U(iw>ReH#DbVdlclUGxINTl4c;kXpw=CS!OUFHZY}@1sI1 zEiMCl%$aM8z%7@5!<@XFj(nWp%1BjSbqHLVTTyZ!Hcp?{Uec^1XTh()0pqzkeO&05 zG-S@+4L886Q-=+OA?@Iey@~^xI_=Cv%8n}^94#zW!qR6Smoi;@d${9w;eTQ<_3?O{ zM*xUkXY3KKc$IIY`7H%d7VtyGT|7c@1Hpbe{u`fJ)F;$}h*+-VymQ2* zT}%&VEv@EXYk~c1BNid8%)hS2bv%4e07Rz-?YwwJ(k!Ce1NE%F!^{~UUXKXIWol3-uX(qbi1VAfq5Npd$ZrmSLH zaPIWJSmo&^QLKt4VF+}}Oo}C)DK-h&Tdz*?{B#_){b)yNFQX~(EP?SOw@lo)^HB*W z8;I1{MOpG>;Z;4!J|C>jIMAO)@BP8fdiRfkE=NfyVR{6CyuM&YQA5FC&CYdZO2uV#gN#6QL@Lgd<0}w{LB45WRev zxh?f5z7$HDS*#KwgOtjlgysR>TtP<@wYX6kV;1kpvIQ3c-++9Iwgzpo6zpIB-f%0q zpv=j}st0%!tlMo-XYOh*6^?^A7$W;>@^qdbjs;J>TsiztFT5a3^db7L+nQdE!lU^! z2M;I8WcOkHiIcyg5%uE%^g z2E{G_!D3x=WybSasCm>^o(tcTb*+Wl7o*syWmdT~KQBqkMv3(=5O?zy;c`jPXs>w2 zE#&y64}ifs`E9_3bBxZ7=>8pv$vNE>$j4_l?y$Ov54Q^2a$nZ@+3d!G?thp9>~g>+ z%CGTPV_)J#=5zK0;OwMhr5eP-%!bSy!Pfx~eBd70cE`JgbtM^3|7(A(mf5%r_E;h*kY`U!jG=Ge{wRqr>-ImnoxObu}i0n#M@Sq6u;mKsAn4uC0yV z9U_p@#n%U67)U`LQQO*xC+8*ct|oN z+9JF^)`jhZZgh_ZRvv7b9uqPXRm@9(MAIEb{5iOP1}- zUy7%`^}VB~Qt9hEwTJFvYyNP&-?qPg@Em89{r7t;p>|(0z0z)!J2SQrnXE#vwN+N} z1$)Q)nXS)qe#0H&?%trwS-^pAZ0LYmz?8PeMBq?!RO{6|Sjis(V9q6gxF0K-qitC_ zgP-+;dMCR;#mVx*AQZ9+VerRm(d1TWAUga_!U!_q2%U}eGf+j&A#QFZe<0JxCelBo zZX>f3VRwRle{&V7j?(ATy3ED)@9R$v{Qvz_kOsJHqF=gOn&<;&&R+8~~xIeWJV z;rv^{;uG;KRvZUbR?<$1&9Dd=V_Ww{qwNDXX8n6(G!X&TjIl?vpYGG&*oVICEjihE z@~0Hl1V0dFU}Q*Bl!f!JL7P9vq?Kpx%kX$+!$Aer!IaD(`IR zflH#8CLh*b2v1&f;_)4pGkTix%rsCremiKs=C75pA zaool~t8+4bC%P0!G}lu7A?3u)#)J19AEx?YLSaY)EOUFu9_lU7!^6H0*dythgx6Wu z1!Y8*9Pk`-iX)SC5p@n;3DGw4U&r8mCG!}O;{qQGlIn>8{_R^+-46^M5Mw=&p#(v- zl!crZULs25=OLwGVo=bAbai1Z)DM>)yD%7E1eGTGP~q`!jh3=ICMTunnu4BeSBXI?=6$3+>G9d zNo+hw4pU9ofb~uOjaBY&kx`sj8;pLZ=VFUpL9elYWl>OQ679MkHLUf^_t%(jVo(&*_fIRD{LKqeCnijj z({+G#70T1sx^HZMm>Pd}%eKfGUkm`)5#xwQcx#{+(f%1n3|$qakvE%}J{k zFpS`*6=ZdOtp^wYUNSJAXqh=XNI6xFkz!j@;hM%rYm6$xDEl_yNOM-19 zpwwfXcU1>#4n@@PS5~2sRdpik z+w3#EZl=Ji{}(F5Gz1hzP$L^#BPWSx4k`{Gm%7i9*_aTfZ+EE__X?g`z-_?}&ZfiT zV}*)jZCg;Q%$$b`Q})31?n`tyM~Ub`WwT(M;-x%nL)&_%iIviQ9kQ(Zrg}Pj#ae1? zkn1f5`F^c}@V)lvsyOqM^wum<_xU3JntK`*siuJ^vszeXUn#RP`*mULb!$kpN+$x~ zVkq4LaEpq#D<9By`x0^H8{w$I5FLubo@Tj@Kfj&!6Dc`a5#gGpKN!CM4lfLl4s(~9 zwIilT3lTRct^Z}4|H_$^RNd1^-~LXLZ!s#ud`_VJ5|Iq!a&xv~@|#ZQ=U0QcE%R?l zW_4f+apj#dR!{J#mG$IpN>~+iirvJ`HvA9xFIr`b-d)}<1$GDtwkKivvP_o)F^gOG zY}?*Ar-@au4MWvj8oI;h2fHgqt0))+#3i37N-0Cl&-YAOqfa_RyRC^;4-1_W>E0;I zu!+d#GoPxTvoBLE{i)fmJfdClEvvnkpaO||a){twhpZeBJvKqCEyI`j$8G2QP%Tm` zgr1<-C$Gji3?c5dD$z(&;ngo|a~CO8QnB6XGF6mIHyPzAyy#* zcpAoGH_}XrMQ#j)q~8G(Q1d9mfOP=w1$X|Xn!ODV6XiK`W>D0(MwG{u7w*{c8E0T& z_-vjBQ}elDt$3Lz2A|o1o3-!~kNMV^K=!r9hGGIscbuZcPZM@UQfMj&P4gz*+b2f1 zG$O``(-I(mOG`Nn-yiZc8lH)G!DaY`KLBKHlA#ztJ($DZ*G>24Ju3Y9R`g`Rvm^-Y zY^5nlSv!m=;B3TSq+ZDo=ckJbmn%M@RiL!->d7ln!Q-;FLQ^d&@_K{4gvgUvcFlYF zGtLby{O_sw@)DblVbgS%r+M!Plrr*u^}E1zS6!PU{-CsavGWgWO~qC*_FZnv=9vMr z;z^!sJ;r`m{cC_i=lwYD>=$i8UhyNWY(}#-#nNgsA88(7tsKdk-dC z={llb>uFriukMRt42mzW5Q+0n?kpa;Ph-CQP-*oR0H}|R_)uCohq`0(Pcx(b;-|6| zGzf<~T0TV#a>|qUux>O+cW_?}zG2m;8Pc(ws}{r@OYZ>&dc3*2T7x;e*Ff3dly4R`hkv4t5HxvvJbDM427_Wgy>wsAUv^?ADhHD=uSf{o(v z4}Foo-91ClW;yrhkr8mL9zETZgW_|(J?DP-P}PSco`TBptd`UmAfu$ zP*it86q^h0tr3|{C+GxW7}`(AQHlIwA$-4{oa*0>lJ&XKj_9pu({wQLSE}(>aWhp8Z`q*e^vDuna%XuM$&_zO}GybHR>>4dJt5_(%S|G+@M``aaD zYwfR2_oDZ=-mQuK38CZ3@zMc-e|il~Pf~BR@kYK%FzOYUcER;#vZC+$ky1)K0v=u> z_N5EbMWtejC=*(LN&L}wQyDrl{dExpO}hX>+AtE5KHBNxZ3FD#hL6QBGJ!M4R2Yte z{pc3OwiY2`lO9PhdMmi(Zv=B#7k+B=SH1Q5;9*f3x{hc-#U?3;+}G(rI+L=4H;#U( z83ZbebcmEQ3b;gs1}d$E%}Wh_OVFx9O51XhC6eFi^l0h@!+bgbhc3C!xNozns5jf% zPeN0q&FHT;sqF^bFH)VdXilU5LuBDfq~hn4(7Lgo{%IPkq@VzOyI9+@h_;O|vBnCqquvk5cAaB;V5)>UY1p018eo$fz zPme(cPYNj;iXhBbpybr$*;rRRStodaaF|SC{hC>S@xOjJk|A#ZG|y)ssdnTUI%&)y zaBaBD_HumnW6=o}4W@yfCfWyh9cq4D36d{s*q>nby@;>6!8wIhDGDCi;P^@-ZbY*& z*0N#}^gb&MY}53#mHr^U3zyV=1{2&bP(ZsF@tgV{tuaQiB+@$jkGPh@4O4N3E?s1s zP|Iyna8*O{HL9q1pq_Od1}+byEDHIbxIAHh^j#NAuO6K{Q{FO^_|3Vm2Y{O>70p(m zGd|VT+*dywcKdlYwF576xm_DS*}Ut&gLZAT-`1-ZlA728{#|OOSX|K@;PuS|&V3yp zKV$oeOnY4mFf~#9V)SmpvN{*ycGwNUNHb#!q!3mcWaTkgh=}O_TbKS{C!nR4j$@kl zVM7As)&OtVw8%HDH#=gWfHiu&c*C9n0JRtmy=z+xE zFeq~25(Rli8eLgdMPgQYT&o1LGK~Dhj_foTkcF9Hd@`@?CyOe*vx1J;ox{7Cdl@eO z2Dr=ffJ`NE#h=v7CzE8}W*rb5H;KJh%5C@n_&F|?Wey&6DF2@+=7xQ0gSi~Ch5(sU zaG+olw;f!JHkW1zlfNX>{3qz`6y6>-84-PiL%h!~h8RrY?00XSc(rk$fI!7nfJ&!VJcjFUj4ASN(nEG?GFJ1tC;~TBY9Ko- zowit}ttCSCzYju0{?8=UUtksa5e4yy0-fo|D{F4z-H1ByhYVBX?u{}R9L?}jbwnbU zbjV+!sv4Yioa%}`s6O8p0@yFbLRIIq6*^`ShjtG*A9V4y?@9~p#4G!|E*H!>)URj+ z)AB)=C9B}sI~!gHm6~W*0o_U^1%ZlBF6C_Bf!R}KMANn0?JA;`DuhlUP=cndCKdAUf)4*C@ z);M#&31Z<6=TGhMxZ0md+07LM9K=Cqoh?zuBDP$|x|@`2vm%*;sJ&;w$fXEP3#zp^ zP9VgwWT?SnbSl(tVanfg5Or`Pm6ZH+cRJ}0Yj?7TrIK>{{V@FNE4fB}V!((y0I&t^ zQA^lvBi;P+{t;Z{M!9e}Tk6!WeHX6KDNNu#j{KK{OOHucruoW2bT1(v2Tr}{wx2E> zXmZ)$4QxPeeMR`!(EFk~?DyJ9#`3dkHfaDlXzPNqwM%GLnYBmcq(3Rmkl3hX*#Mf} zAz|J;?tlhIA6+@?8N9R_I$L5ruc)wo{_bibw2xCJE%$vZ6~lDF;DNu(?kC$g`)7Sf zo{aFH9-!?s_45xc;>YDg=9Tf;hbh1KIiURx-@4xB=_`1SKD za+)BFu_ML*52D8eH;Dj!M!r(KFI$g#97nIR=?9iH?c4LZSry()^u9_*BQ1ZUX1x@7 zJ)`x^r$O>x+ShI<48%Bp8&M|*vB3&jV&C*&akdM%@wqWW2; zarCxxKQ}ie4UWL$^5)@m@SAzrY0m9}l6JouHJ4}gj6@JNy}{p~~zWQZtXe>#SrZ+UqIooR%TT-oEp zukTG5f!V}+BV3JHl za}AFwi_ejpvd5~)JSMNNyCbDDeT%m0hp{>Z4~O0a8CkF48>GvN)>9Dp)u?C5O@i_5 z9f;e*+?SHJ7_AJ1zO~*KqqLee!Hc-Q`qqcx_R9_eQMcJ<-yL*I%EfX}M*Cpi zRDk_&0LVeWua9ofL-_}u+Q^=7+%3;{B7BUeZh+;x>59$cM-AYQfw7=GrE!#*EwF(! z`)rhhi81IMbD7SEzswAZ;Hdo%jpcTA=WgJs{6J-z z2JBX!)tI9}n}xqEV0Y#W!Wg&@u|E@w-k>JjPAmeS zKqIByf+`qoKh=6T8Ebkc`bCnr3%$IS9a~v%p&8oJxnys4o(;o|M{l`3JSl{Dujst8c_dq0s-( z@&dDz6qIL_!*I_-EEC!NIk>0B^)jcZ4!%m#0uD&md~GVJolE_c=?1E8Du>$c7-mY_ zea{M5>E-MP{2&9fS6mz36|Fg{r@u_Am8TBAWcD1+llGeOtlr^#va>Kf(yk8qjyHuzjMWw9|E`R%X3RuY=%#P9bS9&tz;So1}H@PH_Rtek_q8WSr4=OfP0b+#n%;){br++K@MacOAGkIri)*#;?6r z$h%Or?Ct~7UsB-M=L96c47$FgP5n!4K4FZO30dRA(C;0v>^zE+NF5X8gV}PS%&+~9 z&E1{O<2h8Grqp&+F{l>x1)9ep`dq((Fv#d*PC3liJ>3kzJ1chAn$48>ntllUI6`Ou z_Q4J^x#+#!dGt!!x_+6;frFU`tY%87y(GpJB{2y24!qYN6zQV>Se+#ttWfpZ-l(#g zOg_^jr3iOYn3#3pP@6jC$dET1uONZa_&rdL zF0#GhSql9T`P-`ojQnYl=-Ezo6fKJGg3GYC-Qbwoe|!5@RY+igk7pnk^Z%1o{a|KC zB@Bg;a5q1+kMU8aJmk3N*%K}Taz+W_hU@$PYRQ-H9}`IgQoZFP?yDU zgH^t4M9B^oco;i;C|`=BmTa}`e14xDovCq}0OF8x_0WBJKuL98MP9)OaX&I4j@{q! zEfXgYLO)aDKl*+%ySSOYGkd@$t_nJG^ca@>LqCxx>WE7VVHv;(>dyZcdOz2 ze$JfTx=Afq(6gA^-pDC6^Ql9rUgRYG3#`p z$0DFjz8@gE-b#mUT3AGPAeL9Akwa9ingarN2)3o`cC?DOTIVi7p*}rr<-p=9+}c|V z{*d4x2Y2w@GyOs5kEA-|6c-NaYZLNou3pqes1m`tAT)*XfNV)bSSEDPSR^s<0MYqLo4qo0|2~fEpGa4cZ?K=p8v37+b$BXd ztBtY=bG;EI3)Rx5vWg?86$^$Urw2Q;a&0Ws`r1s#A-`P(w zgpT)W$eBX3f&kNZvOheO^Q+G)?%z-qV7imNo9mpnsNrafANJf&ypDv)OG-Zd2ojsK zHYal4{}U4UIombCX&OpmX}8LwRcel5OV=*@{x7-^3y5yUFEXXsIf(bR28!R*>2SOP zipYY0hGW!xJRLc0fvrZVGix#9UB0akIMZ%6(FGIXIwpuz_t<=nSE+#Cfo&qEK7E#7 z1K2%8bH)NfOca~tb0kKGxd~dGQ8?%2Ff#@ z`?>fZVKKx`kqU{g6)tFxcZ7Bf%SfX#nHe>^2Iv(}|Jc>*-s{NQ-9#As>&&i;0)hz1DKp=b|zqX(mMFERUtHkc4*TTP09z?79kv!K~8M{X)=&-0@L z{(>O=MY@57tr(!f z3Fcu^{~ZR9)>%G=`(KAoPfW?Ttzwyd@MSbi^Ij^v50F^!tq zsHtXeZ-o=Po0tK%3_{13zTY7|h`O*;AN>#1_WcfX4EX>=(}iR@(r$`n#{ZQezOQR&jgAwFP{I~A7cj%hA4>nD0 zKk`k0qcfqxwm;#Ok17^fATU3 zWXM{#6CsvR%zI>Lw{0$#!P!~UHekze(BB?QBK9mojlL4A>~HVa-1{Uc{Y#v&`Sfuo z{c&;=1OkzMcld;=I>f_K&hLF@kpkR@t)LA2yl(O^is{L zx>+CC{x@z;k_+NV`yXwwdgX2yP}!#x&sdtc!UkJzzQ%V02GbVW@HGYEbQ!cQ(TR8*ppia@QkDU5r$Ro%K^=$=TJT*e@IWbZ=QA#ZCo1 zT?BN|fDGPPOyD1vic_IlSA#7;DpJ@rmyN%~dbK?drs)MPDC-isG!;LKHEIwwr|u3} z-WS8<>$&xg2#bHJvQLX9&!9K+3z)AqR$3yLs#(Hmk->FHCRM^;+m)@2WRvk48!zTc zfix906T8_4b_lsK95^v6-=jdAPLr%eud+=3OBf6ML^6+Rss|!!i*i^xmru9NqYKJS(urdB zo2%beW*d-b~IQt%b>UfHHP)a2yKxLSQ zvx0OwB1@!SVF#}FE^T?q-Mg#@RB+(}G`D9d2sFJna-^xHR;R8yDPke;k55tvr;iXYJ-m8?2Zp$J+Zx z`}=J_Wi{s?(owLKZyS7RDTL4fJ!qGNf?=qMZ}o8oB55Sv zuc)wZzx>!;zM3uBpiXLE=Dk@c@G=;E&Xg!A^JRJ4^aVY#G}9Cw!jy7-GrDhc-+*%O{g}#eocx zNGMZnt_)bEP}i4}Qh>mk?djP^K=ZB0UT__GLc%O6J3IVxEm(<^MYQ$F-X<=!X*P3zyzTfW-PTBPw+JuG`pU8J_ z4NRNH`>A9-$w{M0z2{kF!=FmEwQ2Q2U;AvQtkrvPCoJ~RGc;gZp1x;VV}59v3TlW* zMXf*`uu}C<4qk@iLQW>|>HAy%xB3f;y!xY4(~;CH(C2c{c+P?I<)c~m_D?lE10$G1 zv10(M9C5^3HYBRonw&%W!xnD@oI*++w~oQREJJ!6hC z2HYx?MCkA`I6#V&Jb$JhtH;*}+dc$5Uq24w71x3g3KF3`(%Y0`pE>|fQ$qkrwU>GT-_67TCh6x)c?_ynN)YkM zkx-Ln&*yV&VU9nFE0|<-kXf+nb#5W{?Z2sM zr=L%arF?k=zQ>w1{o`*9#@s)6-p<29h$0c&bONG=Pa^`Uz%BcqM?iw3zRlZH#u}DD z8VGOv7aOgB_}Vih4RrgfCEF^`2h@b~dn%%YdHypZsiSxvts_uh&{ z$JF#%2eyIFjafr#|G1~S5I2U;Bnhh8d@UAeGS#^Dt*0*qcSaozuxTWjV7S6Mvb6)PmTcS&A=9_W8k^z1AloWhQ3%`R2^Q@QO4qR=2$MeUma^+3u9E&Gimev($FBVoKdg3@#TRD$bCpPA8$mb}Y7}++ zWk<_cFj=t02(#^hK|(w9q~oBVT1q81))rU2okaw-5g%zyt=>S&b9_$#R z2L<&S9kw^ttGYB#Bx_>nxnaZ?EEYQfeAqeoOI&U)n`rd#b@&=o82Wl-2s(1Vhm*WJ zcy8HVIv@8^H?_~BY3HcHBv_zu(0TDtUC@KdL?MtZN*u%!f1WoD=p)rQMV{~t?$k%v zcjmArcUO}*H^(@l$%2dE1Dl$>wkSa;J9}Jod7~DEqLqr3tBP$%4aEb&fRwPuj@(*! zVl?rW4eVZ(T_>TJ!kqvs;%IJ;DDei8k z^pq0cGe&eog>5f)snvtvSAEdW?C3@ll1Alu<5P4#BgNHD4mV5@nN{XA3cXXx1!zHR zy{8w$aEBUz$_wV@me%RsdAmvk3*J(vyrA~%)fFZDN*69`pWZi4c@b6TvD}n_M!z|Y z^&))h-m{ixLp->FTu@~pD46FuXNgamH7@Gv+?^P?{RNRQveaG zUifiwGEM*^=1z688io*_JPal@0EN8fCu!W1rOSq25nC*_=*j2Qo{&&%rnnXa7#Bdh zrDx<|(T|os?|x1nQc7i70fPYb7_f}R>)b%CV9KWs0`}HvIaA|qWK)BPtD)V@<*7|o!sK4AG)S~r$uthtgNj01%wV8 zLWAa9uX+Tr7^tlP`YRTb^Wq?Nl@)LU_Ur0X7q_ADTR9oNMACg%GCvxLRY3E0auFnI z#`cIFV$0xJ*AbXE3ch}`O+%I93H)$rfBhWqu*%{~LF^1cVL$8*dB&T!6!2P^2Y;~d z-M^krcp~)kBx>_Eh$SN;)z~WUC&@Crh8MW!SLzuaOA=Cud|qvH7vHMb%23Cp9~MUp z`Pd$&5aBc{|1a?R>8P71uy`j&h1;sSOR2&Z*?~FAJo>Uv)Yj%px19A%F6pK(F|N?% zHWDPjW6ly-Ugzvmkk*~44FtvelP_j(*NrZR7HWLiaXtDooz%Xk&}5ClTM%oxE8Ev) z$YAjAn8XaD*IDOqv&ha7vSb{bu`;aX$ZygdyE0=iw;z_i`a=+f>BC{u>Bq|FTC$MY ze-Vx^UWlczFS?J8PF_RF2ZO?GP_zE>yBJNTWzs}pw(^r`t)=4v3QxnbHKbMqcM3QJ zyl+TvphM~ZAXlaF`2j4cY#%zz$wC_%sluM^f;z9lI%-MD8(I_;E8%|(YQFvEOhb)7U!yYdE%dYT6B z$u>I~7I?3kreDQA;M^}B+efk_^8S6vOWX%=mBQ9U)}d@+a@bvAtllEWGxa+%uvD-r zUayJHZyDi@7}?)w`ZfI`uD)J1m)TbK75I`PHC;HKh~O7ra#XNcH?VKn1Lclg=*pAD z)Cwr6DFngie;6z?8Vr_YeWeHqY34c5SxBe6CWr5V(!ik~mRa!90^-|M(EOBM{eC8GOAm6{B`B0E{Uo{>-ZoC;70 zdOy~n3}eR&e1MQ9$&Cu6m#GK95V0*M?{j?u~Gay_eP(MyRXz^+-rPWY~GN+f+PsI)UtxV7)Au4QsW&qaX*5} zs$c**m$@&JkMEWaf&n$wqb1u{r0IAnl4E)1oO0TIgeq$r!GwQaH1&Z|=rO|A*KQxa z>HJg>;CNl=4QPlgN>rBse3Rd!OEe3UGlxGp%7iv3r3@>yPpOg{}9?DujR@(4?bs2-C(~4x@x5ar;Ir3$1v30d* zX*Ughnt1o8uyoR{Ds>Itx17i{A|=UUkBF9%vv;`W`Ebk4F}`GqY6+9!QBLM9l{O;O9a0YRk(_{A5h~%& z8BCnK!blnq4X)b_IMp)a*sL1(XT4FdLl`_T_#ZKms)wQ7t^soQbqY(9A^sJZp%VlW zBCY3aJS!MNpRcZ`6pV5U%R=z>?%ox|;C|Q>jyaE+D9VIXRTxNfjt_9$)3ujA5icyV z$=)a);5aRntRP=6ga{VO*$&awEHGEL(w$}plane[pipe], 0, sizeof(ddb->plane[pipe])); ++ memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe])); ++ + if (WARN_ON(!state)) + return 0; + + if (!cstate->base.active) { + ddb->pipe[pipe].start = ddb->pipe[pipe].end = 0; +- memset(ddb->plane[pipe], 0, sizeof(ddb->plane[pipe])); +- memset(ddb->y_plane[pipe], 0, sizeof(ddb->y_plane[pipe])); + return 0; + } + +@@ -4054,6 +4056,12 @@ skl_compute_ddb(struct drm_atomic_state *state) + intel_state->wm_results.dirty_pipes = ~0; + } + ++ /* ++ * We're not recomputing for the pipes not included in the commit, so ++ * make sure we start with the current state. ++ */ ++ memcpy(ddb, &dev_priv->wm.skl_hw.ddb, sizeof(*ddb)); ++ + for_each_intel_crtc_mask(dev, intel_crtc, realloc_pipes) { + struct intel_crtc_state *cstate; + diff --git a/kernel/kernel/files/patches/mageia/kernel-sched-fair-Fix-incorrect-task-group-load_avg.patch b/kernel/kernel/files/patches/mageia/kernel-sched-fair-Fix-incorrect-task-group-load_avg.patch new file mode 100644 index 00000000..3c7c7279 --- /dev/null +++ b/kernel/kernel/files/patches/mageia/kernel-sched-fair-Fix-incorrect-task-group-load_avg.patch @@ -0,0 +1,73 @@ +From b5a9b340789b2b24c6896bcf7a065c31a4db671c Mon Sep 17 00:00:00 2001 +From: Vincent Guittot +Date: Wed, 19 Oct 2016 14:45:23 +0200 +Subject: [PATCH] sched/fair: Fix incorrect task group ->load_avg + +A scheduler performance regression has been reported by Joseph Salisbury, +which he bisected back to: + + 3d30544f0212 ("sched/fair: Apply more PELT fixes) + +The regression triggers when several levels of task groups are involved +(read: SystemD) and cpu_possible_mask != cpu_present_mask. + +The root cause is that group entity's load (tg_child->se[i]->avg.load_avg) +is initialized to scale_load_down(se->load.weight). During the creation of +a child task group, its group entities on possible CPUs are attached to +parent's cfs_rq (tg_parent) and their loads are added to the parent's load +(tg_parent->load_avg) with update_tg_load_avg(). + +But only the load on online CPUs will then be updated to reflect real load, +whereas load on other CPUs will stay at the initial value. + +The result is a tg_parent->load_avg that is higher than the real load, the +weight of group entities (tg_parent->se[i]->load.weight) on online CPUs is +smaller than it should be, and the task group gets a less running time than +what it could expect. + +( This situation can be detected with /proc/sched_debug. The ".tg_load_avg" + of the task group will be much higher than sum of ".tg_load_avg_contrib" + of online cfs_rqs of the task group. ) + +The load of group entities don't have to be intialized to something else +than 0 because their load will increase when an entity is attached. + +Reported-by: Joseph Salisbury +Tested-by: Dietmar Eggemann +Signed-off-by: Vincent Guittot +Acked-by: Peter Zijlstra +Cc: # 4.8.x +Cc: Linus Torvalds +Cc: Peter Zijlstra +Cc: Thomas Gleixner +Cc: joonwoop@codeaurora.org +Fixes: 3d30544f0212 ("sched/fair: Apply more PELT fixes) +Link: http://lkml.kernel.org/r/1476881123-10159-1-git-send-email-vincent.guittot@linaro.org +Signed-off-by: Ingo Molnar +--- + kernel/sched/fair.c | 9 ++++++++- + 1 file changed, 8 insertions(+), 1 deletion(-) + +diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c +index 76ee7de..d941c97 100644 +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -690,7 +690,14 @@ void init_entity_runnable_average(struct sched_entity *se) + * will definitely be update (after enqueue). + */ + sa->period_contrib = 1023; +- sa->load_avg = scale_load_down(se->load.weight); ++ /* ++ * Tasks are intialized with full load to be seen as heavy tasks until ++ * they get a chance to stabilize to their real load level. ++ * Group entities are intialized with zero load to reflect the fact that ++ * nothing has been attached to the task group yet. ++ */ ++ if (entity_is_task(se)) ++ sa->load_avg = scale_load_down(se->load.weight); + sa->load_sum = sa->load_avg * LOAD_AVG_MAX; + /* + * At this point, util_avg won't be used in select_task_rq_fair anyway +-- +2.10.1 + diff --git a/kernel/kernel/files/patches/mageia/linux-BFQ-v8r4.patch b/kernel/kernel/files/patches/mageia/linux-BFQ-v8r4.patch new file mode 100644 index 00000000..abb33847 --- /dev/null +++ b/kernel/kernel/files/patches/mageia/linux-BFQ-v8r4.patch @@ -0,0 +1,9004 @@ +diff -w -uNr '--exclude=.git' linux-4.8/block/bfq-cgroup.c linux-4.8-bfq/block/bfq-cgroup.c +--- linux-4.8/block/bfq-cgroup.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.8-bfq/block/bfq-cgroup.c 2016-10-18 12:57:57.691164881 +0200 +@@ -0,0 +1,1196 @@ ++/* ++ * BFQ: CGROUPS support. ++ * ++ * Based on ideas and code from CFQ: ++ * Copyright (C) 2003 Jens Axboe ++ * ++ * Copyright (C) 2008 Fabio Checconi ++ * Paolo Valente ++ * ++ * Copyright (C) 2015 Paolo Valente ++ * ++ * Copyright (C) 2016 Paolo Valente ++ * ++ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ ++ * file. ++ */ ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ ++/* bfqg stats flags */ ++enum bfqg_stats_flags { ++ BFQG_stats_waiting = 0, ++ BFQG_stats_idling, ++ BFQG_stats_empty, ++}; ++ ++#define BFQG_FLAG_FNS(name) \ ++static void bfqg_stats_mark_##name(struct bfqg_stats *stats) \ ++{ \ ++ stats->flags |= (1 << BFQG_stats_##name); \ ++} \ ++static void bfqg_stats_clear_##name(struct bfqg_stats *stats) \ ++{ \ ++ stats->flags &= ~(1 << BFQG_stats_##name); \ ++} \ ++static int bfqg_stats_##name(struct bfqg_stats *stats) \ ++{ \ ++ return (stats->flags & (1 << BFQG_stats_##name)) != 0; \ ++} \ ++ ++BFQG_FLAG_FNS(waiting) ++BFQG_FLAG_FNS(idling) ++BFQG_FLAG_FNS(empty) ++#undef BFQG_FLAG_FNS ++ ++/* This should be called with the queue_lock held. */ ++static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats) ++{ ++ unsigned long long now; ++ ++ if (!bfqg_stats_waiting(stats)) ++ return; ++ ++ now = sched_clock(); ++ if (time_after64(now, stats->start_group_wait_time)) ++ blkg_stat_add(&stats->group_wait_time, ++ now - stats->start_group_wait_time); ++ bfqg_stats_clear_waiting(stats); ++} ++ ++/* This should be called with the queue_lock held. */ ++static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg, ++ struct bfq_group *curr_bfqg) ++{ ++ struct bfqg_stats *stats = &bfqg->stats; ++ ++ if (bfqg_stats_waiting(stats)) ++ return; ++ if (bfqg == curr_bfqg) ++ return; ++ stats->start_group_wait_time = sched_clock(); ++ bfqg_stats_mark_waiting(stats); ++} ++ ++/* This should be called with the queue_lock held. */ ++static void bfqg_stats_end_empty_time(struct bfqg_stats *stats) ++{ ++ unsigned long long now; ++ ++ if (!bfqg_stats_empty(stats)) ++ return; ++ ++ now = sched_clock(); ++ if (time_after64(now, stats->start_empty_time)) ++ blkg_stat_add(&stats->empty_time, ++ now - stats->start_empty_time); ++ bfqg_stats_clear_empty(stats); ++} ++ ++static void bfqg_stats_update_dequeue(struct bfq_group *bfqg) ++{ ++ blkg_stat_add(&bfqg->stats.dequeue, 1); ++} ++ ++static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) ++{ ++ struct bfqg_stats *stats = &bfqg->stats; ++ ++ if (blkg_rwstat_total(&stats->queued)) ++ return; ++ ++ /* ++ * group is already marked empty. This can happen if bfqq got new ++ * request in parent group and moved to this group while being added ++ * to service tree. Just ignore the event and move on. ++ */ ++ if (bfqg_stats_empty(stats)) ++ return; ++ ++ stats->start_empty_time = sched_clock(); ++ bfqg_stats_mark_empty(stats); ++} ++ ++static void bfqg_stats_update_idle_time(struct bfq_group *bfqg) ++{ ++ struct bfqg_stats *stats = &bfqg->stats; ++ ++ if (bfqg_stats_idling(stats)) { ++ unsigned long long now = sched_clock(); ++ ++ if (time_after64(now, stats->start_idle_time)) ++ blkg_stat_add(&stats->idle_time, ++ now - stats->start_idle_time); ++ bfqg_stats_clear_idling(stats); ++ } ++} ++ ++static void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) ++{ ++ struct bfqg_stats *stats = &bfqg->stats; ++ ++ stats->start_idle_time = sched_clock(); ++ bfqg_stats_mark_idling(stats); ++} ++ ++static void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) ++{ ++ struct bfqg_stats *stats = &bfqg->stats; ++ ++ blkg_stat_add(&stats->avg_queue_size_sum, ++ blkg_rwstat_total(&stats->queued)); ++ blkg_stat_add(&stats->avg_queue_size_samples, 1); ++ bfqg_stats_update_group_wait_time(stats); ++} ++ ++static struct blkcg_policy blkcg_policy_bfq; ++ ++/* ++ * blk-cgroup policy-related handlers ++ * The following functions help in converting between blk-cgroup ++ * internal structures and BFQ-specific structures. ++ */ ++ ++static struct bfq_group *pd_to_bfqg(struct blkg_policy_data *pd) ++{ ++ return pd ? container_of(pd, struct bfq_group, pd) : NULL; ++} ++ ++static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg) ++{ ++ return pd_to_blkg(&bfqg->pd); ++} ++ ++static struct bfq_group *blkg_to_bfqg(struct blkcg_gq *blkg) ++{ ++ struct blkg_policy_data *pd = blkg_to_pd(blkg, &blkcg_policy_bfq); ++ ++ return pd_to_bfqg(pd); ++} ++ ++/* ++ * bfq_group handlers ++ * The following functions help in navigating the bfq_group hierarchy ++ * by allowing to find the parent of a bfq_group or the bfq_group ++ * associated to a bfq_queue. ++ */ ++ ++static struct bfq_group *bfqg_parent(struct bfq_group *bfqg) ++{ ++ struct blkcg_gq *pblkg = bfqg_to_blkg(bfqg)->parent; ++ ++ return pblkg ? blkg_to_bfqg(pblkg) : NULL; ++} ++ ++static struct bfq_group *bfqq_group(struct bfq_queue *bfqq) ++{ ++ struct bfq_entity *group_entity = bfqq->entity.parent; ++ ++ return group_entity ? container_of(group_entity, struct bfq_group, ++ entity) : ++ bfqq->bfqd->root_group; ++} ++ ++/* ++ * The following two functions handle get and put of a bfq_group by ++ * wrapping the related blk-cgroup hooks. ++ */ ++ ++static void bfqg_get(struct bfq_group *bfqg) ++{ ++ return blkg_get(bfqg_to_blkg(bfqg)); ++} ++ ++static void bfqg_put(struct bfq_group *bfqg) ++{ ++ return blkg_put(bfqg_to_blkg(bfqg)); ++} ++ ++static void bfqg_stats_update_io_add(struct bfq_group *bfqg, ++ struct bfq_queue *bfqq, ++ int op, int op_flags) ++{ ++ blkg_rwstat_add(&bfqg->stats.queued, op, op_flags, 1); ++ bfqg_stats_end_empty_time(&bfqg->stats); ++ if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue)) ++ bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq)); ++} ++ ++static void bfqg_stats_update_io_remove(struct bfq_group *bfqg, int op, ++ int op_flags) ++{ ++ blkg_rwstat_add(&bfqg->stats.queued, op, op_flags, -1); ++} ++ ++static void bfqg_stats_update_io_merged(struct bfq_group *bfqg, int op, ++ int op_flags) ++{ ++ blkg_rwstat_add(&bfqg->stats.merged, op, op_flags, 1); ++} ++ ++static void bfqg_stats_update_completion(struct bfq_group *bfqg, ++ uint64_t start_time, uint64_t io_start_time, int op, ++ int op_flags) ++{ ++ struct bfqg_stats *stats = &bfqg->stats; ++ unsigned long long now = sched_clock(); ++ ++ if (time_after64(now, io_start_time)) ++ blkg_rwstat_add(&stats->service_time, op, op_flags, ++ now - io_start_time); ++ if (time_after64(io_start_time, start_time)) ++ blkg_rwstat_add(&stats->wait_time, op, op_flags, ++ io_start_time - start_time); ++} ++ ++/* @stats = 0 */ ++static void bfqg_stats_reset(struct bfqg_stats *stats) ++{ ++ /* queued stats shouldn't be cleared */ ++ blkg_rwstat_reset(&stats->merged); ++ blkg_rwstat_reset(&stats->service_time); ++ blkg_rwstat_reset(&stats->wait_time); ++ blkg_stat_reset(&stats->time); ++ blkg_stat_reset(&stats->avg_queue_size_sum); ++ blkg_stat_reset(&stats->avg_queue_size_samples); ++ blkg_stat_reset(&stats->dequeue); ++ blkg_stat_reset(&stats->group_wait_time); ++ blkg_stat_reset(&stats->idle_time); ++ blkg_stat_reset(&stats->empty_time); ++} ++ ++/* @to += @from */ ++static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from) ++{ ++ if (!to || !from) ++ return; ++ ++ /* queued stats shouldn't be cleared */ ++ blkg_rwstat_add_aux(&to->merged, &from->merged); ++ blkg_rwstat_add_aux(&to->service_time, &from->service_time); ++ blkg_rwstat_add_aux(&to->wait_time, &from->wait_time); ++ blkg_stat_add_aux(&from->time, &from->time); ++ blkg_stat_add_aux(&to->avg_queue_size_sum, &from->avg_queue_size_sum); ++ blkg_stat_add_aux(&to->avg_queue_size_samples, ++ &from->avg_queue_size_samples); ++ blkg_stat_add_aux(&to->dequeue, &from->dequeue); ++ blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time); ++ blkg_stat_add_aux(&to->idle_time, &from->idle_time); ++ blkg_stat_add_aux(&to->empty_time, &from->empty_time); ++} ++ ++/* ++ * Transfer @bfqg's stats to its parent's dead_stats so that the ancestors' ++ * recursive stats can still account for the amount used by this bfqg after ++ * it's gone. ++ */ ++static void bfqg_stats_xfer_dead(struct bfq_group *bfqg) ++{ ++ struct bfq_group *parent; ++ ++ if (!bfqg) /* root_group */ ++ return; ++ ++ parent = bfqg_parent(bfqg); ++ ++ lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock); ++ ++ if (unlikely(!parent)) ++ return; ++ ++ bfqg_stats_add_aux(&parent->stats, &bfqg->stats); ++ bfqg_stats_reset(&bfqg->stats); ++} ++ ++static void bfq_init_entity(struct bfq_entity *entity, ++ struct bfq_group *bfqg) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ ++ entity->weight = entity->new_weight; ++ entity->orig_weight = entity->new_weight; ++ if (bfqq) { ++ bfqq->ioprio = bfqq->new_ioprio; ++ bfqq->ioprio_class = bfqq->new_ioprio_class; ++ bfqg_get(bfqg); ++ } ++ entity->parent = bfqg->my_entity; ++ entity->sched_data = &bfqg->sched_data; ++} ++ ++static void bfqg_stats_exit(struct bfqg_stats *stats) ++{ ++ blkg_rwstat_exit(&stats->merged); ++ blkg_rwstat_exit(&stats->service_time); ++ blkg_rwstat_exit(&stats->wait_time); ++ blkg_rwstat_exit(&stats->queued); ++ blkg_stat_exit(&stats->time); ++ blkg_stat_exit(&stats->avg_queue_size_sum); ++ blkg_stat_exit(&stats->avg_queue_size_samples); ++ blkg_stat_exit(&stats->dequeue); ++ blkg_stat_exit(&stats->group_wait_time); ++ blkg_stat_exit(&stats->idle_time); ++ blkg_stat_exit(&stats->empty_time); ++} ++ ++static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp) ++{ ++ if (blkg_rwstat_init(&stats->merged, gfp) || ++ blkg_rwstat_init(&stats->service_time, gfp) || ++ blkg_rwstat_init(&stats->wait_time, gfp) || ++ blkg_rwstat_init(&stats->queued, gfp) || ++ blkg_stat_init(&stats->time, gfp) || ++ blkg_stat_init(&stats->avg_queue_size_sum, gfp) || ++ blkg_stat_init(&stats->avg_queue_size_samples, gfp) || ++ blkg_stat_init(&stats->dequeue, gfp) || ++ blkg_stat_init(&stats->group_wait_time, gfp) || ++ blkg_stat_init(&stats->idle_time, gfp) || ++ blkg_stat_init(&stats->empty_time, gfp)) { ++ bfqg_stats_exit(stats); ++ return -ENOMEM; ++ } ++ ++ return 0; ++} ++ ++static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd) ++{ ++ return cpd ? container_of(cpd, struct bfq_group_data, pd) : NULL; ++} ++ ++static struct bfq_group_data *blkcg_to_bfqgd(struct blkcg *blkcg) ++{ ++ return cpd_to_bfqgd(blkcg_to_cpd(blkcg, &blkcg_policy_bfq)); ++} ++ ++static struct blkcg_policy_data *bfq_cpd_alloc(gfp_t gfp) ++{ ++ struct bfq_group_data *bgd; ++ ++ bgd = kzalloc(sizeof(*bgd), GFP_KERNEL); ++ if (!bgd) ++ return NULL; ++ return &bgd->pd; ++} ++ ++static void bfq_cpd_init(struct blkcg_policy_data *cpd) ++{ ++ struct bfq_group_data *d = cpd_to_bfqgd(cpd); ++ ++ d->weight = cgroup_subsys_on_dfl(io_cgrp_subsys) ? ++ CGROUP_WEIGHT_DFL : BFQ_WEIGHT_LEGACY_DFL; ++} ++ ++static void bfq_cpd_free(struct blkcg_policy_data *cpd) ++{ ++ kfree(cpd_to_bfqgd(cpd)); ++} ++ ++static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, int node) ++{ ++ struct bfq_group *bfqg; ++ ++ bfqg = kzalloc_node(sizeof(*bfqg), gfp, node); ++ if (!bfqg) ++ return NULL; ++ ++ if (bfqg_stats_init(&bfqg->stats, gfp)) { ++ kfree(bfqg); ++ return NULL; ++ } ++ ++ return &bfqg->pd; ++} ++ ++static void bfq_pd_init(struct blkg_policy_data *pd) ++{ ++ struct blkcg_gq *blkg; ++ struct bfq_group *bfqg; ++ struct bfq_data *bfqd; ++ struct bfq_entity *entity; ++ struct bfq_group_data *d; ++ ++ blkg = pd_to_blkg(pd); ++ BUG_ON(!blkg); ++ bfqg = blkg_to_bfqg(blkg); ++ bfqd = blkg->q->elevator->elevator_data; ++ entity = &bfqg->entity; ++ d = blkcg_to_bfqgd(blkg->blkcg); ++ ++ entity->orig_weight = entity->weight = entity->new_weight = d->weight; ++ entity->my_sched_data = &bfqg->sched_data; ++ bfqg->my_entity = entity; /* ++ * the root_group's will be set to NULL ++ * in bfq_init_queue() ++ */ ++ bfqg->bfqd = bfqd; ++ bfqg->active_entities = 0; ++ bfqg->rq_pos_tree = RB_ROOT; ++} ++ ++static void bfq_pd_free(struct blkg_policy_data *pd) ++{ ++ struct bfq_group *bfqg = pd_to_bfqg(pd); ++ ++ bfqg_stats_exit(&bfqg->stats); ++ return kfree(bfqg); ++} ++ ++static void bfq_pd_reset_stats(struct blkg_policy_data *pd) ++{ ++ struct bfq_group *bfqg = pd_to_bfqg(pd); ++ ++ bfqg_stats_reset(&bfqg->stats); ++} ++ ++static void bfq_group_set_parent(struct bfq_group *bfqg, ++ struct bfq_group *parent) ++{ ++ struct bfq_entity *entity; ++ ++ BUG_ON(!parent); ++ BUG_ON(!bfqg); ++ BUG_ON(bfqg == parent); ++ ++ entity = &bfqg->entity; ++ entity->parent = parent->my_entity; ++ entity->sched_data = &parent->sched_data; ++} ++ ++static struct bfq_group *bfq_lookup_bfqg(struct bfq_data *bfqd, ++ struct blkcg *blkcg) ++{ ++ struct blkcg_gq *blkg; ++ ++ blkg = blkg_lookup(blkcg, bfqd->queue); ++ if (likely(blkg)) ++ return blkg_to_bfqg(blkg); ++ return NULL; ++} ++ ++static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, ++ struct blkcg *blkcg) ++{ ++ struct bfq_group *bfqg, *parent; ++ struct bfq_entity *entity; ++ ++ assert_spin_locked(bfqd->queue->queue_lock); ++ ++ bfqg = bfq_lookup_bfqg(bfqd, blkcg); ++ ++ if (unlikely(!bfqg)) ++ return NULL; ++ ++ /* ++ * Update chain of bfq_groups as we might be handling a leaf group ++ * which, along with some of its relatives, has not been hooked yet ++ * to the private hierarchy of BFQ. ++ */ ++ entity = &bfqg->entity; ++ for_each_entity(entity) { ++ bfqg = container_of(entity, struct bfq_group, entity); ++ BUG_ON(!bfqg); ++ if (bfqg != bfqd->root_group) { ++ parent = bfqg_parent(bfqg); ++ if (!parent) ++ parent = bfqd->root_group; ++ BUG_ON(!parent); ++ bfq_group_set_parent(bfqg, parent); ++ } ++ } ++ ++ return bfqg; ++} ++ ++static void bfq_pos_tree_add_move(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq); ++ ++static void bfq_bfqq_expire(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ bool compensate, ++ enum bfqq_expiration reason); ++ ++/** ++ * bfq_bfqq_move - migrate @bfqq to @bfqg. ++ * @bfqd: queue descriptor. ++ * @bfqq: the queue to move. ++ * @bfqg: the group to move to. ++ * ++ * Move @bfqq to @bfqg, deactivating it from its old group and reactivating ++ * it on the new one. Avoid putting the entity on the old group idle tree. ++ * ++ * Must be called under the queue lock; the cgroup owning @bfqg must ++ * not disappear (by now this just means that we are called under ++ * rcu_read_lock()). ++ */ ++static void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ struct bfq_group *bfqg) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ ++ BUG_ON(!bfq_bfqq_busy(bfqq) && !RB_EMPTY_ROOT(&bfqq->sort_list)); ++ BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list) && !entity->on_st); ++ BUG_ON(bfq_bfqq_busy(bfqq) && RB_EMPTY_ROOT(&bfqq->sort_list) ++ && entity->on_st && ++ bfqq != bfqd->in_service_queue); ++ BUG_ON(!bfq_bfqq_busy(bfqq) && bfqq == bfqd->in_service_queue); ++ ++ /* If bfqq is empty, then bfq_bfqq_expire also invokes ++ * bfq_del_bfqq_busy, thereby removing bfqq and its entity ++ * from data structures related to current group. Otherwise we ++ * need to remove bfqq explicitly with bfq_deactivate_bfqq, as ++ * we do below. ++ */ ++ if (bfqq == bfqd->in_service_queue) ++ bfq_bfqq_expire(bfqd, bfqd->in_service_queue, ++ false, BFQ_BFQQ_PREEMPTED); ++ ++ BUG_ON(entity->on_st && !bfq_bfqq_busy(bfqq) ++ && &bfq_entity_service_tree(entity)->idle != ++ entity->tree); ++ ++ BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_busy(bfqq)); ++ ++ if (bfq_bfqq_busy(bfqq)) ++ bfq_deactivate_bfqq(bfqd, bfqq, 0); ++ else if (entity->on_st) { ++ BUG_ON(&bfq_entity_service_tree(entity)->idle != ++ entity->tree); ++ bfq_put_idle_entity(bfq_entity_service_tree(entity), entity); ++ } ++ bfqg_put(bfqq_group(bfqq)); ++ ++ /* ++ * Here we use a reference to bfqg. We don't need a refcounter ++ * as the cgroup reference will not be dropped, so that its ++ * destroy() callback will not be invoked. ++ */ ++ entity->parent = bfqg->my_entity; ++ entity->sched_data = &bfqg->sched_data; ++ bfqg_get(bfqg); ++ ++ BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_busy(bfqq)); ++ if (bfq_bfqq_busy(bfqq)) { ++ bfq_pos_tree_add_move(bfqd, bfqq); ++ bfq_activate_bfqq(bfqd, bfqq); ++ } ++ ++ if (!bfqd->in_service_queue && !bfqd->rq_in_driver) ++ bfq_schedule_dispatch(bfqd); ++ BUG_ON(entity->on_st && !bfq_bfqq_busy(bfqq) ++ && &bfq_entity_service_tree(entity)->idle != ++ entity->tree); ++} ++ ++/** ++ * __bfq_bic_change_cgroup - move @bic to @cgroup. ++ * @bfqd: the queue descriptor. ++ * @bic: the bic to move. ++ * @blkcg: the blk-cgroup to move to. ++ * ++ * Move bic to blkcg, assuming that bfqd->queue is locked; the caller ++ * has to make sure that the reference to cgroup is valid across the call. ++ * ++ * NOTE: an alternative approach might have been to store the current ++ * cgroup in bfqq and getting a reference to it, reducing the lookup ++ * time here, at the price of slightly more complex code. ++ */ ++static struct bfq_group *__bfq_bic_change_cgroup(struct bfq_data *bfqd, ++ struct bfq_io_cq *bic, ++ struct blkcg *blkcg) ++{ ++ struct bfq_queue *async_bfqq = bic_to_bfqq(bic, 0); ++ struct bfq_queue *sync_bfqq = bic_to_bfqq(bic, 1); ++ struct bfq_group *bfqg; ++ struct bfq_entity *entity; ++ ++ lockdep_assert_held(bfqd->queue->queue_lock); ++ ++ bfqg = bfq_find_set_group(bfqd, blkcg); ++ ++ if (unlikely(!bfqg)) ++ bfqg = bfqd->root_group; ++ ++ if (async_bfqq) { ++ entity = &async_bfqq->entity; ++ ++ if (entity->sched_data != &bfqg->sched_data) { ++ bic_set_bfqq(bic, NULL, 0); ++ bfq_log_bfqq(bfqd, async_bfqq, ++ "bic_change_group: %p %d", ++ async_bfqq, ++ async_bfqq->ref); ++ bfq_put_queue(async_bfqq); ++ } ++ } ++ ++ if (sync_bfqq) { ++ entity = &sync_bfqq->entity; ++ if (entity->sched_data != &bfqg->sched_data) ++ bfq_bfqq_move(bfqd, sync_bfqq, bfqg); ++ } ++ ++ return bfqg; ++} ++ ++static void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) ++{ ++ struct bfq_data *bfqd = bic_to_bfqd(bic); ++ struct bfq_group *bfqg = NULL; ++ uint64_t serial_nr; ++ ++ rcu_read_lock(); ++ serial_nr = bio_blkcg(bio)->css.serial_nr; ++ ++ /* ++ * Check whether blkcg has changed. The condition may trigger ++ * spuriously on a newly created cic but there's no harm. ++ */ ++ if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) ++ goto out; ++ ++ bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio)); ++ bic->blkcg_serial_nr = serial_nr; ++out: ++ rcu_read_unlock(); ++} ++ ++/** ++ * bfq_flush_idle_tree - deactivate any entity on the idle tree of @st. ++ * @st: the service tree being flushed. ++ */ ++static void bfq_flush_idle_tree(struct bfq_service_tree *st) ++{ ++ struct bfq_entity *entity = st->first_idle; ++ ++ for (; entity ; entity = st->first_idle) ++ __bfq_deactivate_entity(entity, 0); ++} ++ ++/** ++ * bfq_reparent_leaf_entity - move leaf entity to the root_group. ++ * @bfqd: the device data structure with the root group. ++ * @entity: the entity to move. ++ */ ++static void bfq_reparent_leaf_entity(struct bfq_data *bfqd, ++ struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ ++ BUG_ON(!bfqq); ++ bfq_bfqq_move(bfqd, bfqq, bfqd->root_group); ++} ++ ++/** ++ * bfq_reparent_active_entities - move to the root group all active ++ * entities. ++ * @bfqd: the device data structure with the root group. ++ * @bfqg: the group to move from. ++ * @st: the service tree with the entities. ++ * ++ * Needs queue_lock to be taken and reference to be valid over the call. ++ */ ++static void bfq_reparent_active_entities(struct bfq_data *bfqd, ++ struct bfq_group *bfqg, ++ struct bfq_service_tree *st) ++{ ++ struct rb_root *active = &st->active; ++ struct bfq_entity *entity = NULL; ++ ++ if (!RB_EMPTY_ROOT(&st->active)) ++ entity = bfq_entity_of(rb_first(active)); ++ ++ for (; entity ; entity = bfq_entity_of(rb_first(active))) ++ bfq_reparent_leaf_entity(bfqd, entity); ++ ++ if (bfqg->sched_data.in_service_entity) ++ bfq_reparent_leaf_entity(bfqd, ++ bfqg->sched_data.in_service_entity); ++} ++ ++/** ++ * bfq_pd_offline - deactivate the entity associated with @pd, ++ * and reparent its children entities. ++ * @pd: descriptor of the policy going offline. ++ * ++ * blkio already grabs the queue_lock for us, so no need to use ++ * RCU-based magic ++ */ ++static void bfq_pd_offline(struct blkg_policy_data *pd) ++{ ++ struct bfq_service_tree *st; ++ struct bfq_group *bfqg; ++ struct bfq_data *bfqd; ++ struct bfq_entity *entity; ++ int i; ++ ++ BUG_ON(!pd); ++ bfqg = pd_to_bfqg(pd); ++ BUG_ON(!bfqg); ++ bfqd = bfqg->bfqd; ++ BUG_ON(bfqd && !bfqd->root_group); ++ ++ entity = bfqg->my_entity; ++ ++ if (!entity) /* root group */ ++ return; ++ ++ /* ++ * Empty all service_trees belonging to this group before ++ * deactivating the group itself. ++ */ ++ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) { ++ BUG_ON(!bfqg->sched_data.service_tree); ++ st = bfqg->sched_data.service_tree + i; ++ /* ++ * The idle tree may still contain bfq_queues belonging ++ * to exited task because they never migrated to a different ++ * cgroup from the one being destroyed now. No one else ++ * can access them so it's safe to act without any lock. ++ */ ++ bfq_flush_idle_tree(st); ++ ++ /* ++ * It may happen that some queues are still active ++ * (busy) upon group destruction (if the corresponding ++ * processes have been forced to terminate). We move ++ * all the leaf entities corresponding to these queues ++ * to the root_group. ++ * Also, it may happen that the group has an entity ++ * in service, which is disconnected from the active ++ * tree: it must be moved, too. ++ * There is no need to put the sync queues, as the ++ * scheduler has taken no reference. ++ */ ++ bfq_reparent_active_entities(bfqd, bfqg, st); ++ BUG_ON(!RB_EMPTY_ROOT(&st->active)); ++ BUG_ON(!RB_EMPTY_ROOT(&st->idle)); ++ } ++ BUG_ON(bfqg->sched_data.next_in_service); ++ BUG_ON(bfqg->sched_data.in_service_entity); ++ ++ __bfq_deactivate_entity(entity, 0); ++ bfq_put_async_queues(bfqd, bfqg); ++ BUG_ON(entity->tree); ++ ++ /* ++ * @blkg is going offline and will be ignored by ++ * blkg_[rw]stat_recursive_sum(). Transfer stats to the parent so ++ * that they don't get lost. If IOs complete after this point, the ++ * stats for them will be lost. Oh well... ++ */ ++ bfqg_stats_xfer_dead(bfqg); ++} ++ ++static void bfq_end_wr_async(struct bfq_data *bfqd) ++{ ++ struct blkcg_gq *blkg; ++ ++ list_for_each_entry(blkg, &bfqd->queue->blkg_list, q_node) { ++ struct bfq_group *bfqg = blkg_to_bfqg(blkg); ++ BUG_ON(!bfqg); ++ ++ bfq_end_wr_async_queues(bfqd, bfqg); ++ } ++ bfq_end_wr_async_queues(bfqd, bfqd->root_group); ++} ++ ++static int bfq_io_show_weight(struct seq_file *sf, void *v) ++{ ++ struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); ++ struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); ++ unsigned int val = 0; ++ ++ if (bfqgd) ++ val = bfqgd->weight; ++ ++ seq_printf(sf, "%u\n", val); ++ ++ return 0; ++} ++ ++static int bfq_io_set_weight_legacy(struct cgroup_subsys_state *css, ++ struct cftype *cftype, ++ u64 val) ++{ ++ struct blkcg *blkcg = css_to_blkcg(css); ++ struct bfq_group_data *bfqgd = blkcg_to_bfqgd(blkcg); ++ struct blkcg_gq *blkg; ++ int ret = -ERANGE; ++ ++ if (val < BFQ_MIN_WEIGHT || val > BFQ_MAX_WEIGHT) ++ return ret; ++ ++ ret = 0; ++ spin_lock_irq(&blkcg->lock); ++ bfqgd->weight = (unsigned short)val; ++ hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { ++ struct bfq_group *bfqg = blkg_to_bfqg(blkg); ++ ++ if (!bfqg) ++ continue; ++ /* ++ * Setting the prio_changed flag of the entity ++ * to 1 with new_weight == weight would re-set ++ * the value of the weight to its ioprio mapping. ++ * Set the flag only if necessary. ++ */ ++ if ((unsigned short)val != bfqg->entity.new_weight) { ++ bfqg->entity.new_weight = (unsigned short)val; ++ /* ++ * Make sure that the above new value has been ++ * stored in bfqg->entity.new_weight before ++ * setting the prio_changed flag. In fact, ++ * this flag may be read asynchronously (in ++ * critical sections protected by a different ++ * lock than that held here), and finding this ++ * flag set may cause the execution of the code ++ * for updating parameters whose value may ++ * depend also on bfqg->entity.new_weight (in ++ * __bfq_entity_update_weight_prio). ++ * This barrier makes sure that the new value ++ * of bfqg->entity.new_weight is correctly ++ * seen in that code. ++ */ ++ smp_wmb(); ++ bfqg->entity.prio_changed = 1; ++ } ++ } ++ spin_unlock_irq(&blkcg->lock); ++ ++ return ret; ++} ++ ++static ssize_t bfq_io_set_weight(struct kernfs_open_file *of, ++ char *buf, size_t nbytes, ++ loff_t off) ++{ ++ u64 weight; ++ /* First unsigned long found in the file is used */ ++ int ret = kstrtoull(strim(buf), 0, &weight); ++ ++ if (ret) ++ return ret; ++ ++ return bfq_io_set_weight_legacy(of_css(of), NULL, weight); ++} ++ ++static int bfqg_print_stat(struct seq_file *sf, void *v) ++{ ++ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat, ++ &blkcg_policy_bfq, seq_cft(sf)->private, false); ++ return 0; ++} ++ ++static int bfqg_print_rwstat(struct seq_file *sf, void *v) ++{ ++ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_rwstat, ++ &blkcg_policy_bfq, seq_cft(sf)->private, true); ++ return 0; ++} ++ ++static u64 bfqg_prfill_stat_recursive(struct seq_file *sf, ++ struct blkg_policy_data *pd, int off) ++{ ++ u64 sum = blkg_stat_recursive_sum(pd_to_blkg(pd), ++ &blkcg_policy_bfq, off); ++ return __blkg_prfill_u64(sf, pd, sum); ++} ++ ++static u64 bfqg_prfill_rwstat_recursive(struct seq_file *sf, ++ struct blkg_policy_data *pd, int off) ++{ ++ struct blkg_rwstat sum = blkg_rwstat_recursive_sum(pd_to_blkg(pd), ++ &blkcg_policy_bfq, ++ off); ++ return __blkg_prfill_rwstat(sf, pd, &sum); ++} ++ ++static int bfqg_print_stat_recursive(struct seq_file *sf, void *v) ++{ ++ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), ++ bfqg_prfill_stat_recursive, &blkcg_policy_bfq, ++ seq_cft(sf)->private, false); ++ return 0; ++} ++ ++static int bfqg_print_rwstat_recursive(struct seq_file *sf, void *v) ++{ ++ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), ++ bfqg_prfill_rwstat_recursive, &blkcg_policy_bfq, ++ seq_cft(sf)->private, true); ++ return 0; ++} ++ ++static u64 bfqg_prfill_sectors(struct seq_file *sf, struct blkg_policy_data *pd, ++ int off) ++{ ++ u64 sum = blkg_rwstat_total(&pd->blkg->stat_bytes); ++ ++ return __blkg_prfill_u64(sf, pd, sum >> 9); ++} ++ ++static int bfqg_print_stat_sectors(struct seq_file *sf, void *v) ++{ ++ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), ++ bfqg_prfill_sectors, &blkcg_policy_bfq, 0, false); ++ return 0; ++} ++ ++static u64 bfqg_prfill_sectors_recursive(struct seq_file *sf, ++ struct blkg_policy_data *pd, int off) ++{ ++ struct blkg_rwstat tmp = blkg_rwstat_recursive_sum(pd->blkg, NULL, ++ offsetof(struct blkcg_gq, stat_bytes)); ++ u64 sum = atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_READ]) + ++ atomic64_read(&tmp.aux_cnt[BLKG_RWSTAT_WRITE]); ++ ++ return __blkg_prfill_u64(sf, pd, sum >> 9); ++} ++ ++static int bfqg_print_stat_sectors_recursive(struct seq_file *sf, void *v) ++{ ++ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), ++ bfqg_prfill_sectors_recursive, &blkcg_policy_bfq, 0, ++ false); ++ return 0; ++} ++ ++ ++static u64 bfqg_prfill_avg_queue_size(struct seq_file *sf, ++ struct blkg_policy_data *pd, int off) ++{ ++ struct bfq_group *bfqg = pd_to_bfqg(pd); ++ u64 samples = blkg_stat_read(&bfqg->stats.avg_queue_size_samples); ++ u64 v = 0; ++ ++ if (samples) { ++ v = blkg_stat_read(&bfqg->stats.avg_queue_size_sum); ++ v = div64_u64(v, samples); ++ } ++ __blkg_prfill_u64(sf, pd, v); ++ return 0; ++} ++ ++/* print avg_queue_size */ ++static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v) ++{ ++ blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), ++ bfqg_prfill_avg_queue_size, &blkcg_policy_bfq, ++ 0, false); ++ return 0; ++} ++ ++static struct bfq_group * ++bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) ++{ ++ int ret; ++ ++ ret = blkcg_activate_policy(bfqd->queue, &blkcg_policy_bfq); ++ if (ret) ++ return NULL; ++ ++ return blkg_to_bfqg(bfqd->queue->root_blkg); ++} ++ ++static struct cftype bfq_blkcg_legacy_files[] = { ++ { ++ .name = "bfq.weight", ++ .flags = CFTYPE_NOT_ON_ROOT, ++ .seq_show = bfq_io_show_weight, ++ .write_u64 = bfq_io_set_weight_legacy, ++ }, ++ ++ /* statistics, covers only the tasks in the bfqg */ ++ { ++ .name = "bfq.time", ++ .private = offsetof(struct bfq_group, stats.time), ++ .seq_show = bfqg_print_stat, ++ }, ++ { ++ .name = "bfq.sectors", ++ .seq_show = bfqg_print_stat_sectors, ++ }, ++ { ++ .name = "bfq.io_service_bytes", ++ .private = (unsigned long)&blkcg_policy_bfq, ++ .seq_show = blkg_print_stat_bytes, ++ }, ++ { ++ .name = "bfq.io_serviced", ++ .private = (unsigned long)&blkcg_policy_bfq, ++ .seq_show = blkg_print_stat_ios, ++ }, ++ { ++ .name = "bfq.io_service_time", ++ .private = offsetof(struct bfq_group, stats.service_time), ++ .seq_show = bfqg_print_rwstat, ++ }, ++ { ++ .name = "bfq.io_wait_time", ++ .private = offsetof(struct bfq_group, stats.wait_time), ++ .seq_show = bfqg_print_rwstat, ++ }, ++ { ++ .name = "bfq.io_merged", ++ .private = offsetof(struct bfq_group, stats.merged), ++ .seq_show = bfqg_print_rwstat, ++ }, ++ { ++ .name = "bfq.io_queued", ++ .private = offsetof(struct bfq_group, stats.queued), ++ .seq_show = bfqg_print_rwstat, ++ }, ++ ++ /* the same statictics which cover the bfqg and its descendants */ ++ { ++ .name = "bfq.time_recursive", ++ .private = offsetof(struct bfq_group, stats.time), ++ .seq_show = bfqg_print_stat_recursive, ++ }, ++ { ++ .name = "bfq.sectors_recursive", ++ .seq_show = bfqg_print_stat_sectors_recursive, ++ }, ++ { ++ .name = "bfq.io_service_bytes_recursive", ++ .private = (unsigned long)&blkcg_policy_bfq, ++ .seq_show = blkg_print_stat_bytes_recursive, ++ }, ++ { ++ .name = "bfq.io_serviced_recursive", ++ .private = (unsigned long)&blkcg_policy_bfq, ++ .seq_show = blkg_print_stat_ios_recursive, ++ }, ++ { ++ .name = "bfq.io_service_time_recursive", ++ .private = offsetof(struct bfq_group, stats.service_time), ++ .seq_show = bfqg_print_rwstat_recursive, ++ }, ++ { ++ .name = "bfq.io_wait_time_recursive", ++ .private = offsetof(struct bfq_group, stats.wait_time), ++ .seq_show = bfqg_print_rwstat_recursive, ++ }, ++ { ++ .name = "bfq.io_merged_recursive", ++ .private = offsetof(struct bfq_group, stats.merged), ++ .seq_show = bfqg_print_rwstat_recursive, ++ }, ++ { ++ .name = "bfq.io_queued_recursive", ++ .private = offsetof(struct bfq_group, stats.queued), ++ .seq_show = bfqg_print_rwstat_recursive, ++ }, ++ { ++ .name = "bfq.avg_queue_size", ++ .seq_show = bfqg_print_avg_queue_size, ++ }, ++ { ++ .name = "bfq.group_wait_time", ++ .private = offsetof(struct bfq_group, stats.group_wait_time), ++ .seq_show = bfqg_print_stat, ++ }, ++ { ++ .name = "bfq.idle_time", ++ .private = offsetof(struct bfq_group, stats.idle_time), ++ .seq_show = bfqg_print_stat, ++ }, ++ { ++ .name = "bfq.empty_time", ++ .private = offsetof(struct bfq_group, stats.empty_time), ++ .seq_show = bfqg_print_stat, ++ }, ++ { ++ .name = "bfq.dequeue", ++ .private = offsetof(struct bfq_group, stats.dequeue), ++ .seq_show = bfqg_print_stat, ++ }, ++ { } /* terminate */ ++}; ++ ++static struct cftype bfq_blkg_files[] = { ++ { ++ .name = "bfq.weight", ++ .flags = CFTYPE_NOT_ON_ROOT, ++ .seq_show = bfq_io_show_weight, ++ .write = bfq_io_set_weight, ++ }, ++ {} /* terminate */ ++}; ++ ++#else /* CONFIG_BFQ_GROUP_IOSCHED */ ++ ++static inline void bfqg_stats_update_io_add(struct bfq_group *bfqg, ++ struct bfq_queue *bfqq, int op, int op_flags) { } ++static inline void ++bfqg_stats_update_io_remove(struct bfq_group *bfqg, int op, int op_flags) { } ++static inline void ++bfqg_stats_update_io_merged(struct bfq_group *bfqg, int op, int op_flags) { } ++static inline void bfqg_stats_update_completion(struct bfq_group *bfqg, ++ uint64_t start_time, uint64_t io_start_time, int op, ++ int op_flags) { } ++static inline void ++bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg, ++ struct bfq_group *curr_bfqg) { } ++static inline void bfqg_stats_end_empty_time(struct bfqg_stats *stats) { } ++static inline void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { } ++static inline void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { } ++static inline void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { } ++static inline void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { } ++static inline void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { } ++ ++static void bfq_init_entity(struct bfq_entity *entity, ++ struct bfq_group *bfqg) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ ++ entity->weight = entity->new_weight; ++ entity->orig_weight = entity->new_weight; ++ if (bfqq) { ++ bfqq->ioprio = bfqq->new_ioprio; ++ bfqq->ioprio_class = bfqq->new_ioprio_class; ++ } ++ entity->sched_data = &bfqg->sched_data; ++} ++ ++static struct bfq_group * ++bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) ++{ ++ struct bfq_data *bfqd = bic_to_bfqd(bic); ++ ++ return bfqd->root_group; ++} ++ ++static void bfq_end_wr_async(struct bfq_data *bfqd) ++{ ++ bfq_end_wr_async_queues(bfqd, bfqd->root_group); ++} ++ ++static struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd, ++ struct blkcg *blkcg) ++{ ++ return bfqd->root_group; ++} ++ ++static struct bfq_group *bfqq_group(struct bfq_queue *bfqq) ++{ ++ return bfqq->bfqd->root_group; ++} ++ ++static struct bfq_group * ++bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) ++{ ++ struct bfq_group *bfqg; ++ int i; ++ ++ bfqg = kmalloc_node(sizeof(*bfqg), GFP_KERNEL | __GFP_ZERO, node); ++ if (!bfqg) ++ return NULL; ++ ++ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) ++ bfqg->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; ++ ++ return bfqg; ++} ++#endif +diff -w -uNr '--exclude=.git' linux-4.8/block/bfq.h linux-4.8-bfq/block/bfq.h +--- linux-4.8/block/bfq.h 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.8-bfq/block/bfq.h 2016-10-18 12:57:57.691164881 +0200 +@@ -0,0 +1,886 @@ ++/* ++ * BFQ-v8r4 for 4.8.0: data structures and common functions prototypes. ++ * ++ * Based on ideas and code from CFQ: ++ * Copyright (C) 2003 Jens Axboe ++ * ++ * Copyright (C) 2008 Fabio Checconi ++ * Paolo Valente ++ * ++ * Copyright (C) 2015 Paolo Valente ++ * ++ * Copyright (C) 2016 Paolo Valente ++ */ ++ ++#ifndef _BFQ_H ++#define _BFQ_H ++ ++#include ++#include ++#include ++#include ++#include ++ ++#define BFQ_IOPRIO_CLASSES 3 ++#define BFQ_CL_IDLE_TIMEOUT (HZ/5) ++ ++#define BFQ_MIN_WEIGHT 1 ++#define BFQ_MAX_WEIGHT 1000 ++#define BFQ_WEIGHT_CONVERSION_COEFF 10 ++ ++#define BFQ_DEFAULT_QUEUE_IOPRIO 4 ++ ++#define BFQ_WEIGHT_LEGACY_DFL 100 ++#define BFQ_DEFAULT_GRP_IOPRIO 0 ++#define BFQ_DEFAULT_GRP_CLASS IOPRIO_CLASS_BE ++ ++/* ++ * Soft real-time applications are extremely more latency sensitive ++ * than interactive ones. Over-raise the weight of the former to ++ * privilege them against the latter. ++ */ ++#define BFQ_SOFTRT_WEIGHT_FACTOR 100 ++ ++struct bfq_entity; ++ ++/** ++ * struct bfq_service_tree - per ioprio_class service tree. ++ * ++ * Each service tree represents a B-WF2Q+ scheduler on its own. Each ++ * ioprio_class has its own independent scheduler, and so its own ++ * bfq_service_tree. All the fields are protected by the queue lock ++ * of the containing bfqd. ++ */ ++struct bfq_service_tree { ++ /* tree for active entities (i.e., those backlogged) */ ++ struct rb_root active; ++ /* tree for idle entities (i.e., not backlogged, with V <= F_i)*/ ++ struct rb_root idle; ++ ++ struct bfq_entity *first_idle; /* idle entity with minimum F_i */ ++ struct bfq_entity *last_idle; /* idle entity with maximum F_i */ ++ ++ u64 vtime; /* scheduler virtual time */ ++ /* scheduler weight sum; active and idle entities contribute to it */ ++ unsigned long wsum; ++}; ++ ++/** ++ * struct bfq_sched_data - multi-class scheduler. ++ * ++ * bfq_sched_data is the basic scheduler queue. It supports three ++ * ioprio_classes, and can be used either as a toplevel queue or as an ++ * intermediate queue on a hierarchical setup. @next_in_service ++ * points to the active entity of the sched_data service trees that ++ * will be scheduled next. It is used to reduce the number of steps ++ * needed for each hierarchical-schedule update. ++ * ++ * The supported ioprio_classes are the same as in CFQ, in descending ++ * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE. ++ * Requests from higher priority queues are served before all the ++ * requests from lower priority queues; among requests of the same ++ * queue requests are served according to B-WF2Q+. ++ * All the fields are protected by the queue lock of the containing bfqd. ++ */ ++struct bfq_sched_data { ++ struct bfq_entity *in_service_entity; /* entity in service */ ++ /* head-of-the-line entity in the scheduler (see comments above) */ ++ struct bfq_entity *next_in_service; ++ /* array of service trees, one per ioprio_class */ ++ struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES]; ++}; ++ ++/** ++ * struct bfq_weight_counter - counter of the number of all active entities ++ * with a given weight. ++ */ ++struct bfq_weight_counter { ++ unsigned int weight; /* weight of the entities this counter refers to */ ++ unsigned int num_active; /* nr of active entities with this weight */ ++ /* ++ * Weights tree member (see bfq_data's @queue_weights_tree and ++ * @group_weights_tree) ++ */ ++ struct rb_node weights_node; ++}; ++ ++/** ++ * struct bfq_entity - schedulable entity. ++ * ++ * A bfq_entity is used to represent either a bfq_queue (leaf node in the ++ * cgroup hierarchy) or a bfq_group into the upper level scheduler. Each ++ * entity belongs to the sched_data of the parent group in the cgroup ++ * hierarchy. Non-leaf entities have also their own sched_data, stored ++ * in @my_sched_data. ++ * ++ * Each entity stores independently its priority values; this would ++ * allow different weights on different devices, but this ++ * functionality is not exported to userspace by now. Priorities and ++ * weights are updated lazily, first storing the new values into the ++ * new_* fields, then setting the @prio_changed flag. As soon as ++ * there is a transition in the entity state that allows the priority ++ * update to take place the effective and the requested priority ++ * values are synchronized. ++ * ++ * Unless cgroups are used, the weight value is calculated from the ++ * ioprio to export the same interface as CFQ. When dealing with ++ * ``well-behaved'' queues (i.e., queues that do not spend too much ++ * time to consume their budget and have true sequential behavior, and ++ * when there are no external factors breaking anticipation) the ++ * relative weights at each level of the cgroups hierarchy should be ++ * guaranteed. All the fields are protected by the queue lock of the ++ * containing bfqd. ++ */ ++struct bfq_entity { ++ struct rb_node rb_node; /* service_tree member */ ++ /* pointer to the weight counter associated with this entity */ ++ struct bfq_weight_counter *weight_counter; ++ ++ /* ++ * flag, true if the entity is on a tree (either the active or ++ * the idle one of its service_tree). ++ */ ++ int on_st; ++ ++ u64 finish; /* B-WF2Q+ finish timestamp (aka F_i) */ ++ u64 start; /* B-WF2Q+ start timestamp (aka S_i) */ ++ ++ /* tree the entity is enqueued into; %NULL if not on a tree */ ++ struct rb_root *tree; ++ ++ /* ++ * minimum start time of the (active) subtree rooted at this ++ * entity; used for O(log N) lookups into active trees ++ */ ++ u64 min_start; ++ ++ /* amount of service received during the last service slot */ ++ int service; ++ ++ /* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */ ++ int budget; ++ ++ unsigned int weight; /* weight of the queue */ ++ unsigned int new_weight; /* next weight if a change is in progress */ ++ ++ /* original weight, used to implement weight boosting */ ++ unsigned int orig_weight; ++ ++ /* parent entity, for hierarchical scheduling */ ++ struct bfq_entity *parent; ++ ++ /* ++ * For non-leaf nodes in the hierarchy, the associated ++ * scheduler queue, %NULL on leaf nodes. ++ */ ++ struct bfq_sched_data *my_sched_data; ++ /* the scheduler queue this entity belongs to */ ++ struct bfq_sched_data *sched_data; ++ ++ /* flag, set to request a weight, ioprio or ioprio_class change */ ++ int prio_changed; ++}; ++ ++struct bfq_group; ++ ++/** ++ * struct bfq_queue - leaf schedulable entity. ++ * ++ * A bfq_queue is a leaf request queue; it can be associated with an ++ * io_context or more, if it is async or shared between cooperating ++ * processes. @cgroup holds a reference to the cgroup, to be sure that it ++ * does not disappear while a bfqq still references it (mostly to avoid ++ * races between request issuing and task migration followed by cgroup ++ * destruction). ++ * All the fields are protected by the queue lock of the containing bfqd. ++ */ ++struct bfq_queue { ++ /* reference counter */ ++ int ref; ++ /* parent bfq_data */ ++ struct bfq_data *bfqd; ++ ++ /* current ioprio and ioprio class */ ++ unsigned short ioprio, ioprio_class; ++ /* next ioprio and ioprio class if a change is in progress */ ++ unsigned short new_ioprio, new_ioprio_class; ++ ++ /* ++ * Shared bfq_queue if queue is cooperating with one or more ++ * other queues. ++ */ ++ struct bfq_queue *new_bfqq; ++ /* request-position tree member (see bfq_group's @rq_pos_tree) */ ++ struct rb_node pos_node; ++ /* request-position tree root (see bfq_group's @rq_pos_tree) */ ++ struct rb_root *pos_root; ++ ++ /* sorted list of pending requests */ ++ struct rb_root sort_list; ++ /* if fifo isn't expired, next request to serve */ ++ struct request *next_rq; ++ /* number of sync and async requests queued */ ++ int queued[2]; ++ /* number of sync and async requests currently allocated */ ++ int allocated[2]; ++ /* number of pending metadata requests */ ++ int meta_pending; ++ /* fifo list of requests in sort_list */ ++ struct list_head fifo; ++ ++ /* entity representing this queue in the scheduler */ ++ struct bfq_entity entity; ++ ++ /* maximum budget allowed from the feedback mechanism */ ++ int max_budget; ++ /* budget expiration (in jiffies) */ ++ unsigned long budget_timeout; ++ ++ /* number of requests on the dispatch list or inside driver */ ++ int dispatched; ++ ++ unsigned int flags; /* status flags.*/ ++ ++ /* node for active/idle bfqq list inside parent bfqd */ ++ struct list_head bfqq_list; ++ ++ /* bit vector: a 1 for each seeky requests in history */ ++ u32 seek_history; ++ ++ /* node for the device's burst list */ ++ struct hlist_node burst_list_node; ++ ++ /* position of the last request enqueued */ ++ sector_t last_request_pos; ++ ++ /* Number of consecutive pairs of request completion and ++ * arrival, such that the queue becomes idle after the ++ * completion, but the next request arrives within an idle ++ * time slice; used only if the queue's IO_bound flag has been ++ * cleared. ++ */ ++ unsigned int requests_within_timer; ++ ++ /* pid of the process owning the queue, used for logging purposes */ ++ pid_t pid; ++ ++ /* ++ * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL ++ * if the queue is shared. ++ */ ++ struct bfq_io_cq *bic; ++ ++ /* current maximum weight-raising time for this queue */ ++ unsigned long wr_cur_max_time; ++ /* ++ * Minimum time instant such that, only if a new request is ++ * enqueued after this time instant in an idle @bfq_queue with ++ * no outstanding requests, then the task associated with the ++ * queue it is deemed as soft real-time (see the comments on ++ * the function bfq_bfqq_softrt_next_start()) ++ */ ++ unsigned long soft_rt_next_start; ++ /* ++ * Start time of the current weight-raising period if ++ * the @bfq-queue is being weight-raised, otherwise ++ * finish time of the last weight-raising period. ++ */ ++ unsigned long last_wr_start_finish; ++ /* factor by which the weight of this queue is multiplied */ ++ unsigned int wr_coeff; ++ /* ++ * Time of the last transition of the @bfq_queue from idle to ++ * backlogged. ++ */ ++ unsigned long last_idle_bklogged; ++ /* ++ * Cumulative service received from the @bfq_queue since the ++ * last transition from idle to backlogged. ++ */ ++ unsigned long service_from_backlogged; ++ /* ++ * Value of wr start time when switching to soft rt ++ */ ++ unsigned long wr_start_at_switch_to_srt; ++ ++ unsigned long split_time; /* time of last split */ ++}; ++ ++/** ++ * struct bfq_ttime - per process thinktime stats. ++ */ ++struct bfq_ttime { ++ u64 last_end_request; /* completion time of last request */ ++ ++ u64 ttime_total; /* total process thinktime */ ++ unsigned long ttime_samples; /* number of thinktime samples */ ++ u64 ttime_mean; /* average process thinktime */ ++ ++}; ++ ++/** ++ * struct bfq_io_cq - per (request_queue, io_context) structure. ++ */ ++struct bfq_io_cq { ++ /* associated io_cq structure */ ++ struct io_cq icq; /* must be the first member */ ++ /* array of two process queues, the sync and the async */ ++ struct bfq_queue *bfqq[2]; ++ /* associated @bfq_ttime struct */ ++ struct bfq_ttime ttime; ++ /* per (request_queue, blkcg) ioprio */ ++ int ioprio; ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ uint64_t blkcg_serial_nr; /* the current blkcg serial */ ++#endif ++ ++ /* ++ * Snapshot of the idle window before merging; taken to ++ * remember this value while the queue is merged, so as to be ++ * able to restore it in case of split. ++ */ ++ bool saved_idle_window; ++ /* ++ * Same purpose as the previous two fields for the I/O bound ++ * classification of a queue. ++ */ ++ bool saved_IO_bound; ++ ++ /* ++ * Same purpose as the previous fields for the value of the ++ * field keeping the queue's belonging to a large burst ++ */ ++ bool saved_in_large_burst; ++ /* ++ * True if the queue belonged to a burst list before its merge ++ * with another cooperating queue. ++ */ ++ bool was_in_burst_list; ++ ++ /* ++ * Similar to previous fields: save wr information. ++ */ ++ unsigned long saved_wr_coeff; ++ unsigned long saved_last_wr_start_finish; ++ unsigned long saved_wr_start_at_switch_to_srt; ++}; ++ ++enum bfq_device_speed { ++ BFQ_BFQD_FAST, ++ BFQ_BFQD_SLOW, ++}; ++ ++/** ++ * struct bfq_data - per-device data structure. ++ * ++ * All the fields are protected by the @queue lock. ++ */ ++struct bfq_data { ++ /* request queue for the device */ ++ struct request_queue *queue; ++ ++ /* root bfq_group for the device */ ++ struct bfq_group *root_group; ++ ++ /* ++ * rbtree of weight counters of @bfq_queues, sorted by ++ * weight. Used to keep track of whether all @bfq_queues have ++ * the same weight. The tree contains one counter for each ++ * distinct weight associated to some active and not ++ * weight-raised @bfq_queue (see the comments to the functions ++ * bfq_weights_tree_[add|remove] for further details). ++ */ ++ struct rb_root queue_weights_tree; ++ /* ++ * rbtree of non-queue @bfq_entity weight counters, sorted by ++ * weight. Used to keep track of whether all @bfq_groups have ++ * the same weight. The tree contains one counter for each ++ * distinct weight associated to some active @bfq_group (see ++ * the comments to the functions bfq_weights_tree_[add|remove] ++ * for further details). ++ */ ++ struct rb_root group_weights_tree; ++ ++ /* ++ * Number of bfq_queues containing requests (including the ++ * queue in service, even if it is idling). ++ */ ++ int busy_queues; ++ /* number of weight-raised busy @bfq_queues */ ++ int wr_busy_queues; ++ /* number of queued requests */ ++ int queued; ++ /* number of requests dispatched and waiting for completion */ ++ int rq_in_driver; ++ ++ /* ++ * Maximum number of requests in driver in the last ++ * @hw_tag_samples completed requests. ++ */ ++ int max_rq_in_driver; ++ /* number of samples used to calculate hw_tag */ ++ int hw_tag_samples; ++ /* flag set to one if the driver is showing a queueing behavior */ ++ int hw_tag; ++ ++ /* number of budgets assigned */ ++ int budgets_assigned; ++ ++ /* ++ * Timer set when idling (waiting) for the next request from ++ * the queue in service. ++ */ ++ struct hrtimer idle_slice_timer; ++ /* delayed work to restart dispatching on the request queue */ ++ struct work_struct unplug_work; ++ ++ /* bfq_queue in service */ ++ struct bfq_queue *in_service_queue; ++ /* bfq_io_cq (bic) associated with the @in_service_queue */ ++ struct bfq_io_cq *in_service_bic; ++ ++ /* on-disk position of the last served request */ ++ sector_t last_position; ++ ++ /* time of last request completion (ns) */ ++ u64 last_completion; ++ ++ /* time of first rq dispatch in current observation interval (ns) */ ++ u64 first_dispatch; ++ /* time of last rq dispatch in current observation interval (ns) */ ++ u64 last_dispatch; ++ ++ /* beginning of the last budget */ ++ ktime_t last_budget_start; ++ /* beginning of the last idle slice */ ++ ktime_t last_idling_start; ++ ++ /* number of samples in current observation interval */ ++ int peak_rate_samples; ++ /* num of samples of seq dispatches in current observation interval */ ++ u32 sequential_samples; ++ /* total num of sectors transferred in current observation interval */ ++ u64 tot_sectors_dispatched; ++ /* max rq size seen during current observation interval (sectors) */ ++ u32 last_rq_max_size; ++ /* time elapsed from first dispatch in current observ. interval (us) */ ++ u64 delta_from_first; ++ /* current estimate of device peak rate */ ++ u32 peak_rate; ++ ++ /* maximum budget allotted to a bfq_queue before rescheduling */ ++ int bfq_max_budget; ++ ++ /* list of all the bfq_queues active on the device */ ++ struct list_head active_list; ++ /* list of all the bfq_queues idle on the device */ ++ struct list_head idle_list; ++ ++ /* ++ * Timeout for async/sync requests; when it fires, requests ++ * are served in fifo order. ++ */ ++ u64 bfq_fifo_expire[2]; ++ /* weight of backward seeks wrt forward ones */ ++ unsigned int bfq_back_penalty; ++ /* maximum allowed backward seek */ ++ unsigned int bfq_back_max; ++ /* maximum idling time */ ++ u32 bfq_slice_idle; ++ /* last time CLASS_IDLE was served */ ++ u64 bfq_class_idle_last_service; ++ ++ /* user-configured max budget value (0 for auto-tuning) */ ++ int bfq_user_max_budget; ++ /* ++ * Timeout for bfq_queues to consume their budget; used to ++ * prevent seeky queues from imposing long latencies to ++ * sequential or quasi-sequential ones (this also implies that ++ * seeky queues cannot receive guarantees in the service ++ * domain; after a timeout they are charged for the time they ++ * have been in service, to preserve fairness among them, but ++ * without service-domain guarantees). ++ */ ++ unsigned int bfq_timeout; ++ ++ /* ++ * Number of consecutive requests that must be issued within ++ * the idle time slice to set again idling to a queue which ++ * was marked as non-I/O-bound (see the definition of the ++ * IO_bound flag for further details). ++ */ ++ unsigned int bfq_requests_within_timer; ++ ++ /* ++ * Force device idling whenever needed to provide accurate ++ * service guarantees, without caring about throughput ++ * issues. CAVEAT: this may even increase latencies, in case ++ * of useless idling for processes that did stop doing I/O. ++ */ ++ bool strict_guarantees; ++ ++ /* ++ * Last time at which a queue entered the current burst of ++ * queues being activated shortly after each other; for more ++ * details about this and the following parameters related to ++ * a burst of activations, see the comments on the function ++ * bfq_handle_burst. ++ */ ++ unsigned long last_ins_in_burst; ++ /* ++ * Reference time interval used to decide whether a queue has ++ * been activated shortly after @last_ins_in_burst. ++ */ ++ unsigned long bfq_burst_interval; ++ /* number of queues in the current burst of queue activations */ ++ int burst_size; ++ ++ /* common parent entity for the queues in the burst */ ++ struct bfq_entity *burst_parent_entity; ++ /* Maximum burst size above which the current queue-activation ++ * burst is deemed as 'large'. ++ */ ++ unsigned long bfq_large_burst_thresh; ++ /* true if a large queue-activation burst is in progress */ ++ bool large_burst; ++ /* ++ * Head of the burst list (as for the above fields, more ++ * details in the comments on the function bfq_handle_burst). ++ */ ++ struct hlist_head burst_list; ++ ++ /* if set to true, low-latency heuristics are enabled */ ++ bool low_latency; ++ /* ++ * Maximum factor by which the weight of a weight-raised queue ++ * is multiplied. ++ */ ++ unsigned int bfq_wr_coeff; ++ /* maximum duration of a weight-raising period (jiffies) */ ++ unsigned int bfq_wr_max_time; ++ ++ /* Maximum weight-raising duration for soft real-time processes */ ++ unsigned int bfq_wr_rt_max_time; ++ /* ++ * Minimum idle period after which weight-raising may be ++ * reactivated for a queue (in jiffies). ++ */ ++ unsigned int bfq_wr_min_idle_time; ++ /* ++ * Minimum period between request arrivals after which ++ * weight-raising may be reactivated for an already busy async ++ * queue (in jiffies). ++ */ ++ unsigned long bfq_wr_min_inter_arr_async; ++ ++ /* Max service-rate for a soft real-time queue, in sectors/sec */ ++ unsigned int bfq_wr_max_softrt_rate; ++ /* ++ * Cached value of the product R*T, used for computing the ++ * maximum duration of weight raising automatically. ++ */ ++ u64 RT_prod; ++ /* device-speed class for the low-latency heuristic */ ++ enum bfq_device_speed device_speed; ++ ++ /* fallback dummy bfqq for extreme OOM conditions */ ++ struct bfq_queue oom_bfqq; ++}; ++ ++enum bfqq_state_flags { ++ BFQ_BFQQ_FLAG_just_created = 0, /* queue just allocated */ ++ BFQ_BFQQ_FLAG_busy, /* has requests or is in service */ ++ BFQ_BFQQ_FLAG_wait_request, /* waiting for a request */ ++ BFQ_BFQQ_FLAG_non_blocking_wait_rq, /* ++ * waiting for a request ++ * without idling the device ++ */ ++ BFQ_BFQQ_FLAG_must_alloc, /* must be allowed rq alloc */ ++ BFQ_BFQQ_FLAG_fifo_expire, /* FIFO checked in this slice */ ++ BFQ_BFQQ_FLAG_idle_window, /* slice idling enabled */ ++ BFQ_BFQQ_FLAG_sync, /* synchronous queue */ ++ BFQ_BFQQ_FLAG_IO_bound, /* ++ * bfqq has timed-out at least once ++ * having consumed at most 2/10 of ++ * its budget ++ */ ++ BFQ_BFQQ_FLAG_in_large_burst, /* ++ * bfqq activated in a large burst, ++ * see comments to bfq_handle_burst. ++ */ ++ BFQ_BFQQ_FLAG_softrt_update, /* ++ * may need softrt-next-start ++ * update ++ */ ++ BFQ_BFQQ_FLAG_coop, /* bfqq is shared */ ++ BFQ_BFQQ_FLAG_split_coop /* shared bfqq will be split */ ++}; ++ ++#define BFQ_BFQQ_FNS(name) \ ++static void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \ ++{ \ ++ (bfqq)->flags |= (1 << BFQ_BFQQ_FLAG_##name); \ ++} \ ++static void bfq_clear_bfqq_##name(struct bfq_queue *bfqq) \ ++{ \ ++ (bfqq)->flags &= ~(1 << BFQ_BFQQ_FLAG_##name); \ ++} \ ++static int bfq_bfqq_##name(const struct bfq_queue *bfqq) \ ++{ \ ++ return ((bfqq)->flags & (1 << BFQ_BFQQ_FLAG_##name)) != 0; \ ++} ++ ++BFQ_BFQQ_FNS(just_created); ++BFQ_BFQQ_FNS(busy); ++BFQ_BFQQ_FNS(wait_request); ++BFQ_BFQQ_FNS(non_blocking_wait_rq); ++BFQ_BFQQ_FNS(must_alloc); ++BFQ_BFQQ_FNS(fifo_expire); ++BFQ_BFQQ_FNS(idle_window); ++BFQ_BFQQ_FNS(sync); ++BFQ_BFQQ_FNS(IO_bound); ++BFQ_BFQQ_FNS(in_large_burst); ++BFQ_BFQQ_FNS(coop); ++BFQ_BFQQ_FNS(split_coop); ++BFQ_BFQQ_FNS(softrt_update); ++#undef BFQ_BFQQ_FNS ++ ++/* Logging facilities. */ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++static struct bfq_group *bfqq_group(struct bfq_queue *bfqq); ++static struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg); ++ ++#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) do { \ ++ char __pbuf[128]; \ ++ \ ++ assert_spin_locked((bfqd)->queue->queue_lock); \ ++ blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \ ++ blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, \ ++ (bfqq)->pid, \ ++ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ ++ __pbuf, ##args); \ ++} while (0) ++ ++#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do { \ ++ char __pbuf[128]; \ ++ \ ++ blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf)); \ ++ blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args); \ ++} while (0) ++ ++#else /* CONFIG_BFQ_GROUP_IOSCHED */ ++ ++#define bfq_log_bfqq(bfqd, bfqq, fmt, args...) \ ++ blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid, \ ++ bfq_bfqq_sync((bfqq)) ? 'S' : 'A', \ ++ ##args) ++#define bfq_log_bfqg(bfqd, bfqg, fmt, args...) do {} while (0) ++ ++#endif /* CONFIG_BFQ_GROUP_IOSCHED */ ++ ++#define bfq_log(bfqd, fmt, args...) \ ++ blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args) ++ ++/* Expiration reasons. */ ++enum bfqq_expiration { ++ BFQ_BFQQ_TOO_IDLE = 0, /* ++ * queue has been idling for ++ * too long ++ */ ++ BFQ_BFQQ_BUDGET_TIMEOUT, /* budget took too long to be used */ ++ BFQ_BFQQ_BUDGET_EXHAUSTED, /* budget consumed */ ++ BFQ_BFQQ_NO_MORE_REQUESTS, /* the queue has no more requests */ ++ BFQ_BFQQ_PREEMPTED /* preemption in progress */ ++}; ++ ++ ++struct bfqg_stats { ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ /* number of ios merged */ ++ struct blkg_rwstat merged; ++ /* total time spent on device in ns, may not be accurate w/ queueing */ ++ struct blkg_rwstat service_time; ++ /* total time spent waiting in scheduler queue in ns */ ++ struct blkg_rwstat wait_time; ++ /* number of IOs queued up */ ++ struct blkg_rwstat queued; ++ /* total disk time and nr sectors dispatched by this group */ ++ struct blkg_stat time; ++ /* sum of number of ios queued across all samples */ ++ struct blkg_stat avg_queue_size_sum; ++ /* count of samples taken for average */ ++ struct blkg_stat avg_queue_size_samples; ++ /* how many times this group has been removed from service tree */ ++ struct blkg_stat dequeue; ++ /* total time spent waiting for it to be assigned a timeslice. */ ++ struct blkg_stat group_wait_time; ++ /* time spent idling for this blkcg_gq */ ++ struct blkg_stat idle_time; ++ /* total time with empty current active q with other requests queued */ ++ struct blkg_stat empty_time; ++ /* fields after this shouldn't be cleared on stat reset */ ++ uint64_t start_group_wait_time; ++ uint64_t start_idle_time; ++ uint64_t start_empty_time; ++ uint16_t flags; ++#endif ++}; ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++/* ++ * struct bfq_group_data - per-blkcg storage for the blkio subsystem. ++ * ++ * @ps: @blkcg_policy_storage that this structure inherits ++ * @weight: weight of the bfq_group ++ */ ++struct bfq_group_data { ++ /* must be the first member */ ++ struct blkcg_policy_data pd; ++ ++ unsigned int weight; ++}; ++ ++/** ++ * struct bfq_group - per (device, cgroup) data structure. ++ * @entity: schedulable entity to insert into the parent group sched_data. ++ * @sched_data: own sched_data, to contain child entities (they may be ++ * both bfq_queues and bfq_groups). ++ * @bfqd: the bfq_data for the device this group acts upon. ++ * @async_bfqq: array of async queues for all the tasks belonging to ++ * the group, one queue per ioprio value per ioprio_class, ++ * except for the idle class that has only one queue. ++ * @async_idle_bfqq: async queue for the idle class (ioprio is ignored). ++ * @my_entity: pointer to @entity, %NULL for the toplevel group; used ++ * to avoid too many special cases during group creation/ ++ * migration. ++ * @active_entities: number of active entities belonging to the group; ++ * unused for the root group. Used to know whether there ++ * are groups with more than one active @bfq_entity ++ * (see the comments to the function ++ * bfq_bfqq_may_idle()). ++ * @rq_pos_tree: rbtree sorted by next_request position, used when ++ * determining if two or more queues have interleaving ++ * requests (see bfq_find_close_cooperator()). ++ * ++ * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup ++ * there is a set of bfq_groups, each one collecting the lower-level ++ * entities belonging to the group that are acting on the same device. ++ * ++ * Locking works as follows: ++ * o @bfqd is protected by the queue lock, RCU is used to access it ++ * from the readers. ++ * o All the other fields are protected by the @bfqd queue lock. ++ */ ++struct bfq_group { ++ /* must be the first member */ ++ struct blkg_policy_data pd; ++ ++ struct bfq_entity entity; ++ struct bfq_sched_data sched_data; ++ ++ void *bfqd; ++ ++ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR]; ++ struct bfq_queue *async_idle_bfqq; ++ ++ struct bfq_entity *my_entity; ++ ++ int active_entities; ++ ++ struct rb_root rq_pos_tree; ++ ++ struct bfqg_stats stats; ++}; ++ ++#else ++struct bfq_group { ++ struct bfq_sched_data sched_data; ++ ++ struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR]; ++ struct bfq_queue *async_idle_bfqq; ++ ++ struct rb_root rq_pos_tree; ++}; ++#endif ++ ++static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity); ++ ++static struct bfq_service_tree * ++bfq_entity_service_tree(struct bfq_entity *entity) ++{ ++ struct bfq_sched_data *sched_data = entity->sched_data; ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ unsigned int idx = bfqq ? bfqq->ioprio_class - 1 : ++ BFQ_DEFAULT_GRP_CLASS - 1; ++ ++ BUG_ON(idx >= BFQ_IOPRIO_CLASSES); ++ BUG_ON(sched_data == NULL); ++ ++ if (bfqq) ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "entity_service_tree %p %d", ++ sched_data->service_tree + idx, idx); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "entity_service_tree %p %d", ++ sched_data->service_tree + idx, idx); ++ } ++#endif ++ return sched_data->service_tree + idx; ++} ++ ++static struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync) ++{ ++ return bic->bfqq[is_sync]; ++} ++ ++static void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, ++ bool is_sync) ++{ ++ bic->bfqq[is_sync] = bfqq; ++} ++ ++static struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic) ++{ ++ return bic->icq.q->elevator->elevator_data; ++} ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ ++static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq) ++{ ++ struct bfq_entity *group_entity = bfqq->entity.parent; ++ ++ if (!group_entity) ++ group_entity = &bfqq->bfqd->root_group->entity; ++ ++ return container_of(group_entity, struct bfq_group, entity); ++} ++ ++#else ++ ++static struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq) ++{ ++ return bfqq->bfqd->root_group; ++} ++ ++#endif ++ ++static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio); ++static void bfq_put_queue(struct bfq_queue *bfqq); ++static void bfq_dispatch_insert(struct request_queue *q, struct request *rq); ++static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, ++ struct bio *bio, bool is_sync, ++ struct bfq_io_cq *bic); ++static void bfq_end_wr_async_queues(struct bfq_data *bfqd, ++ struct bfq_group *bfqg); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); ++#endif ++static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq); ++ ++#endif /* _BFQ_H */ +diff -w -uNr '--exclude=.git' linux-4.8/block/bfq-ioc.c linux-4.8-bfq/block/bfq-ioc.c +--- linux-4.8/block/bfq-ioc.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.8-bfq/block/bfq-ioc.c 2016-10-18 12:57:57.691164881 +0200 +@@ -0,0 +1,36 @@ ++/* ++ * BFQ: I/O context handling. ++ * ++ * Based on ideas and code from CFQ: ++ * Copyright (C) 2003 Jens Axboe ++ * ++ * Copyright (C) 2008 Fabio Checconi ++ * Paolo Valente ++ * ++ * Copyright (C) 2010 Paolo Valente ++ */ ++ ++/** ++ * icq_to_bic - convert iocontext queue structure to bfq_io_cq. ++ * @icq: the iocontext queue. ++ */ ++static struct bfq_io_cq *icq_to_bic(struct io_cq *icq) ++{ ++ /* bic->icq is the first member, %NULL will convert to %NULL */ ++ return container_of(icq, struct bfq_io_cq, icq); ++} ++ ++/** ++ * bfq_bic_lookup - search into @ioc a bic associated to @bfqd. ++ * @bfqd: the lookup key. ++ * @ioc: the io_context of the process doing I/O. ++ * ++ * Queue lock must be held. ++ */ ++static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd, ++ struct io_context *ioc) ++{ ++ if (ioc) ++ return icq_to_bic(ioc_lookup_icq(ioc, bfqd->queue)); ++ return NULL; ++} +diff -w -uNr '--exclude=.git' linux-4.8/block/bfq-iosched.c linux-4.8-bfq/block/bfq-iosched.c +--- linux-4.8/block/bfq-iosched.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.8-bfq/block/bfq-iosched.c 2016-10-18 12:57:57.691164881 +0200 +@@ -0,0 +1,5288 @@ ++/* ++ * Budget Fair Queueing (BFQ) disk scheduler. ++ * ++ * Based on ideas and code from CFQ: ++ * Copyright (C) 2003 Jens Axboe ++ * ++ * Copyright (C) 2008 Fabio Checconi ++ * Paolo Valente ++ * ++ * Copyright (C) 2015 Paolo Valente ++ * ++ * Copyright (C) 2016 Paolo Valente ++ * ++ * Licensed under the GPL-2 as detailed in the accompanying COPYING.BFQ ++ * file. ++ * ++ * BFQ is a proportional-share storage-I/O scheduling algorithm based ++ * on the slice-by-slice service scheme of CFQ. But BFQ assigns ++ * budgets, measured in number of sectors, to processes instead of ++ * time slices. The device is not granted to the in-service process ++ * for a given time slice, but until it has exhausted its assigned ++ * budget. This change from the time to the service domain enables BFQ ++ * to distribute the device throughput among processes as desired, ++ * without any distortion due to throughput fluctuations, or to device ++ * internal queueing. BFQ uses an ad hoc internal scheduler, called ++ * B-WF2Q+, to schedule processes according to their budgets. More ++ * precisely, BFQ schedules queues associated with processes. Thanks to ++ * the accurate policy of B-WF2Q+, BFQ can afford to assign high ++ * budgets to I/O-bound processes issuing sequential requests (to ++ * boost the throughput), and yet guarantee a low latency to ++ * interactive and soft real-time applications. ++ * ++ * BFQ is described in [1], where also a reference to the initial, more ++ * theoretical paper on BFQ can be found. The interested reader can find ++ * in the latter paper full details on the main algorithm, as well as ++ * formulas of the guarantees and formal proofs of all the properties. ++ * With respect to the version of BFQ presented in these papers, this ++ * implementation adds a few more heuristics, such as the one that ++ * guarantees a low latency to soft real-time applications, and a ++ * hierarchical extension based on H-WF2Q+. ++ * ++ * B-WF2Q+ is based on WF2Q+, that is described in [2], together with ++ * H-WF2Q+, while the augmented tree used to implement B-WF2Q+ with O(log N) ++ * complexity derives from the one introduced with EEVDF in [3]. ++ * ++ * [1] P. Valente and M. Andreolini, ``Improving Application Responsiveness ++ * with the BFQ Disk I/O Scheduler'', ++ * Proceedings of the 5th Annual International Systems and Storage ++ * Conference (SYSTOR '12), June 2012. ++ * ++ * http://algogroup.unimo.it/people/paolo/disk_sched/bf1-v1-suite-results.pdf ++ * ++ * [2] Jon C.R. Bennett and H. Zhang, ``Hierarchical Packet Fair Queueing ++ * Algorithms,'' IEEE/ACM Transactions on Networking, 5(5):675-689, ++ * Oct 1997. ++ * ++ * http://www.cs.cmu.edu/~hzhang/papers/TON-97-Oct.ps.gz ++ * ++ * [3] I. Stoica and H. Abdel-Wahab, ``Earliest Eligible Virtual Deadline ++ * First: A Flexible and Accurate Mechanism for Proportional Share ++ * Resource Allocation,'' technical report. ++ * ++ * http://www.cs.berkeley.edu/~istoica/papers/eevdf-tr-95.pdf ++ */ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include "bfq.h" ++#include "blk.h" ++ ++/* Expiration time of sync (0) and async (1) requests, in ns. */ ++static const u64 bfq_fifo_expire[2] = { NSEC_PER_SEC / 4, NSEC_PER_SEC / 8 }; ++ ++/* Maximum backwards seek, in KiB. */ ++static const int bfq_back_max = 16 * 1024; ++ ++/* Penalty of a backwards seek, in number of sectors. */ ++static const int bfq_back_penalty = 2; ++ ++/* Idling period duration, in ns. */ ++static u32 bfq_slice_idle = NSEC_PER_SEC / 125; ++ ++/* Minimum number of assigned budgets for which stats are safe to compute. */ ++static const int bfq_stats_min_budgets = 194; ++ ++/* Default maximum budget values, in sectors and number of requests. */ ++static const int bfq_default_max_budget = 16 * 1024; ++ ++/* ++ * Async to sync throughput distribution is controlled as follows: ++ * when an async request is served, the entity is charged the number ++ * of sectors of the request, multiplied by the factor below ++ */ ++static const int bfq_async_charge_factor = 10; ++ ++/* Default timeout values, in jiffies, approximating CFQ defaults. */ ++static const int bfq_timeout = HZ / 8; ++ ++struct kmem_cache *bfq_pool; ++ ++/* Below this threshold (in ns), we consider thinktime immediate. */ ++#define BFQ_MIN_TT (2 * NSEC_PER_MSEC) ++ ++/* hw_tag detection: parallel requests threshold and min samples needed. */ ++#define BFQ_HW_QUEUE_THRESHOLD 4 ++#define BFQ_HW_QUEUE_SAMPLES 32 ++ ++#define BFQQ_SEEK_THR (sector_t)(8 * 100) ++#define BFQQ_CLOSE_THR (sector_t)(8 * 1024) ++#define BFQQ_SEEKY(bfqq) (hweight32(bfqq->seek_history) > 32/8) ++ ++/* Min number of samples required to perform peak-rate update */ ++#define BFQ_RATE_MIN_SAMPLES 32 ++/* Min observation time interval required to perform a peak-rate update (ns) */ ++#define BFQ_RATE_MIN_INTERVAL 300*NSEC_PER_MSEC ++/* Target observation time interval for a peak-rate update (ns) */ ++#define BFQ_RATE_REF_INTERVAL NSEC_PER_SEC ++ ++/* Shift used for peak rate fixed precision calculations. */ ++#define BFQ_RATE_SHIFT 16 ++ ++/* ++ * By default, BFQ computes the duration of the weight raising for ++ * interactive applications automatically, using the following formula: ++ * duration = (R / r) * T, where r is the peak rate of the device, and ++ * R and T are two reference parameters. ++ * In particular, R is the peak rate of the reference device (see below), ++ * and T is a reference time: given the systems that are likely to be ++ * installed on the reference device according to its speed class, T is ++ * about the maximum time needed, under BFQ and while reading two files in ++ * parallel, to load typical large applications on these systems. ++ * In practice, the slower/faster the device at hand is, the more/less it ++ * takes to load applications with respect to the reference device. ++ * Accordingly, the longer/shorter BFQ grants weight raising to interactive ++ * applications. ++ * ++ * BFQ uses four different reference pairs (R, T), depending on: ++ * . whether the device is rotational or non-rotational; ++ * . whether the device is slow, such as old or portable HDDs, as well as ++ * SD cards, or fast, such as newer HDDs and SSDs. ++ * ++ * The device's speed class is dynamically (re)detected in ++ * bfq_update_peak_rate() every time the estimated peak rate is updated. ++ * ++ * In the following definitions, R_slow[0]/R_fast[0] and ++ * T_slow[0]/T_fast[0] are the reference values for a slow/fast ++ * rotational device, whereas R_slow[1]/R_fast[1] and ++ * T_slow[1]/T_fast[1] are the reference values for a slow/fast ++ * non-rotational device. Finally, device_speed_thresh are the ++ * thresholds used to switch between speed classes. The reference ++ * rates are not the actual peak rates of the devices used as a ++ * reference, but slightly lower values. The reason for using these ++ * slightly lower values is that the peak-rate estimator tends to ++ * yield slightly lower values than the actual peak rate (it can yield ++ * the actual peak rate only if there is only one process doing I/O, ++ * and the process does sequential I/O). ++ * ++ * Both the reference peak rates and the thresholds are measured in ++ * sectors/usec, left-shifted by BFQ_RATE_SHIFT. ++ */ ++static int R_slow[2] = {1000, 10700}; ++static int R_fast[2] = {14000, 33000}; ++/* ++ * To improve readability, a conversion function is used to initialize the ++ * following arrays, which entails that they can be initialized only in a ++ * function. ++ */ ++static int T_slow[2]; ++static int T_fast[2]; ++static int device_speed_thresh[2]; ++ ++#define BFQ_SERVICE_TREE_INIT ((struct bfq_service_tree) \ ++ { RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 }) ++ ++#define RQ_BIC(rq) ((struct bfq_io_cq *) (rq)->elv.priv[0]) ++#define RQ_BFQQ(rq) ((rq)->elv.priv[1]) ++ ++static void bfq_schedule_dispatch(struct bfq_data *bfqd); ++ ++#include "bfq-ioc.c" ++#include "bfq-sched.c" ++#include "bfq-cgroup.c" ++ ++#define bfq_class_idle(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_IDLE) ++#define bfq_class_rt(bfqq) ((bfqq)->ioprio_class == IOPRIO_CLASS_RT) ++ ++#define bfq_sample_valid(samples) ((samples) > 80) ++ ++/* ++ * We regard a request as SYNC, if either it's a read or has the SYNC bit ++ * set (in which case it could also be a direct WRITE). ++ */ ++static int bfq_bio_sync(struct bio *bio) ++{ ++ return bio_data_dir(bio) == READ || (bio->bi_opf & REQ_SYNC); ++} ++ ++/* ++ * Scheduler run of queue, if there are requests pending and no one in the ++ * driver that will restart queueing. ++ */ ++static void bfq_schedule_dispatch(struct bfq_data *bfqd) ++{ ++ if (bfqd->queued != 0) { ++ bfq_log(bfqd, "schedule dispatch"); ++ kblockd_schedule_work(&bfqd->unplug_work); ++ } ++} ++ ++/* ++ * Lifted from AS - choose which of rq1 and rq2 that is best served now. ++ * We choose the request that is closesr to the head right now. Distance ++ * behind the head is penalized and only allowed to a certain extent. ++ */ ++static struct request *bfq_choose_req(struct bfq_data *bfqd, ++ struct request *rq1, ++ struct request *rq2, ++ sector_t last) ++{ ++ sector_t s1, s2, d1 = 0, d2 = 0; ++ unsigned long back_max; ++#define BFQ_RQ1_WRAP 0x01 /* request 1 wraps */ ++#define BFQ_RQ2_WRAP 0x02 /* request 2 wraps */ ++ unsigned int wrap = 0; /* bit mask: requests behind the disk head? */ ++ ++ if (!rq1 || rq1 == rq2) ++ return rq2; ++ if (!rq2) ++ return rq1; ++ ++ if (rq_is_sync(rq1) && !rq_is_sync(rq2)) ++ return rq1; ++ else if (rq_is_sync(rq2) && !rq_is_sync(rq1)) ++ return rq2; ++ if ((rq1->cmd_flags & REQ_META) && !(rq2->cmd_flags & REQ_META)) ++ return rq1; ++ else if ((rq2->cmd_flags & REQ_META) && !(rq1->cmd_flags & REQ_META)) ++ return rq2; ++ ++ s1 = blk_rq_pos(rq1); ++ s2 = blk_rq_pos(rq2); ++ ++ /* ++ * By definition, 1KiB is 2 sectors. ++ */ ++ back_max = bfqd->bfq_back_max * 2; ++ ++ /* ++ * Strict one way elevator _except_ in the case where we allow ++ * short backward seeks which are biased as twice the cost of a ++ * similar forward seek. ++ */ ++ if (s1 >= last) ++ d1 = s1 - last; ++ else if (s1 + back_max >= last) ++ d1 = (last - s1) * bfqd->bfq_back_penalty; ++ else ++ wrap |= BFQ_RQ1_WRAP; ++ ++ if (s2 >= last) ++ d2 = s2 - last; ++ else if (s2 + back_max >= last) ++ d2 = (last - s2) * bfqd->bfq_back_penalty; ++ else ++ wrap |= BFQ_RQ2_WRAP; ++ ++ /* Found required data */ ++ ++ /* ++ * By doing switch() on the bit mask "wrap" we avoid having to ++ * check two variables for all permutations: --> faster! ++ */ ++ switch (wrap) { ++ case 0: /* common case for CFQ: rq1 and rq2 not wrapped */ ++ if (d1 < d2) ++ return rq1; ++ else if (d2 < d1) ++ return rq2; ++ ++ if (s1 >= s2) ++ return rq1; ++ else ++ return rq2; ++ ++ case BFQ_RQ2_WRAP: ++ return rq1; ++ case BFQ_RQ1_WRAP: ++ return rq2; ++ case (BFQ_RQ1_WRAP|BFQ_RQ2_WRAP): /* both rqs wrapped */ ++ default: ++ /* ++ * Since both rqs are wrapped, ++ * start with the one that's further behind head ++ * (--> only *one* back seek required), ++ * since back seek takes more time than forward. ++ */ ++ if (s1 <= s2) ++ return rq1; ++ else ++ return rq2; ++ } ++} ++ ++static struct bfq_queue * ++bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root, ++ sector_t sector, struct rb_node **ret_parent, ++ struct rb_node ***rb_link) ++{ ++ struct rb_node **p, *parent; ++ struct bfq_queue *bfqq = NULL; ++ ++ parent = NULL; ++ p = &root->rb_node; ++ while (*p) { ++ struct rb_node **n; ++ ++ parent = *p; ++ bfqq = rb_entry(parent, struct bfq_queue, pos_node); ++ ++ /* ++ * Sort strictly based on sector. Smallest to the left, ++ * largest to the right. ++ */ ++ if (sector > blk_rq_pos(bfqq->next_rq)) ++ n = &(*p)->rb_right; ++ else if (sector < blk_rq_pos(bfqq->next_rq)) ++ n = &(*p)->rb_left; ++ else ++ break; ++ p = n; ++ bfqq = NULL; ++ } ++ ++ *ret_parent = parent; ++ if (rb_link) ++ *rb_link = p; ++ ++ bfq_log(bfqd, "rq_pos_tree_lookup %llu: returning %d", ++ (unsigned long long) sector, ++ bfqq ? bfqq->pid : 0); ++ ++ return bfqq; ++} ++ ++static void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ struct rb_node **p, *parent; ++ struct bfq_queue *__bfqq; ++ ++ if (bfqq->pos_root) { ++ rb_erase(&bfqq->pos_node, bfqq->pos_root); ++ bfqq->pos_root = NULL; ++ } ++ ++ if (bfq_class_idle(bfqq)) ++ return; ++ if (!bfqq->next_rq) ++ return; ++ ++ bfqq->pos_root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; ++ __bfqq = bfq_rq_pos_tree_lookup(bfqd, bfqq->pos_root, ++ blk_rq_pos(bfqq->next_rq), &parent, &p); ++ if (!__bfqq) { ++ rb_link_node(&bfqq->pos_node, parent, p); ++ rb_insert_color(&bfqq->pos_node, bfqq->pos_root); ++ } else ++ bfqq->pos_root = NULL; ++} ++ ++/* ++ * Tell whether there are active queues or groups with differentiated weights. ++ */ ++static bool bfq_differentiated_weights(struct bfq_data *bfqd) ++{ ++ /* ++ * For weights to differ, at least one of the trees must contain ++ * at least two nodes. ++ */ ++ return (!RB_EMPTY_ROOT(&bfqd->queue_weights_tree) && ++ (bfqd->queue_weights_tree.rb_node->rb_left || ++ bfqd->queue_weights_tree.rb_node->rb_right) ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ ) || ++ (!RB_EMPTY_ROOT(&bfqd->group_weights_tree) && ++ (bfqd->group_weights_tree.rb_node->rb_left || ++ bfqd->group_weights_tree.rb_node->rb_right) ++#endif ++ ); ++} ++ ++/* ++ * The following function returns true if every queue must receive the ++ * same share of the throughput (this condition is used when deciding ++ * whether idling may be disabled, see the comments in the function ++ * bfq_bfqq_may_idle()). ++ * ++ * Such a scenario occurs when: ++ * 1) all active queues have the same weight, ++ * 2) all active groups at the same level in the groups tree have the same ++ * weight, ++ * 3) all active groups at the same level in the groups tree have the same ++ * number of children. ++ * ++ * Unfortunately, keeping the necessary state for evaluating exactly the ++ * above symmetry conditions would be quite complex and time-consuming. ++ * Therefore this function evaluates, instead, the following stronger ++ * sub-conditions, for which it is much easier to maintain the needed ++ * state: ++ * 1) all active queues have the same weight, ++ * 2) all active groups have the same weight, ++ * 3) all active groups have at most one active child each. ++ * In particular, the last two conditions are always true if hierarchical ++ * support and the cgroups interface are not enabled, thus no state needs ++ * to be maintained in this case. ++ */ ++static bool bfq_symmetric_scenario(struct bfq_data *bfqd) ++{ ++ return !bfq_differentiated_weights(bfqd); ++} ++ ++/* ++ * If the weight-counter tree passed as input contains no counter for ++ * the weight of the input entity, then add that counter; otherwise just ++ * increment the existing counter. ++ * ++ * Note that weight-counter trees contain few nodes in mostly symmetric ++ * scenarios. For example, if all queues have the same weight, then the ++ * weight-counter tree for the queues may contain at most one node. ++ * This holds even if low_latency is on, because weight-raised queues ++ * are not inserted in the tree. ++ * In most scenarios, the rate at which nodes are created/destroyed ++ * should be low too. ++ */ ++static void bfq_weights_tree_add(struct bfq_data *bfqd, ++ struct bfq_entity *entity, ++ struct rb_root *root) ++{ ++ struct rb_node **new = &(root->rb_node), *parent = NULL; ++ ++ /* ++ * Do not insert if the entity is already associated with a ++ * counter, which happens if: ++ * 1) the entity is associated with a queue, ++ * 2) a request arrival has caused the queue to become both ++ * non-weight-raised, and hence change its weight, and ++ * backlogged; in this respect, each of the two events ++ * causes an invocation of this function, ++ * 3) this is the invocation of this function caused by the ++ * second event. This second invocation is actually useless, ++ * and we handle this fact by exiting immediately. More ++ * efficient or clearer solutions might possibly be adopted. ++ */ ++ if (entity->weight_counter) ++ return; ++ ++ while (*new) { ++ struct bfq_weight_counter *__counter = container_of(*new, ++ struct bfq_weight_counter, ++ weights_node); ++ parent = *new; ++ ++ if (entity->weight == __counter->weight) { ++ entity->weight_counter = __counter; ++ goto inc_counter; ++ } ++ if (entity->weight < __counter->weight) ++ new = &((*new)->rb_left); ++ else ++ new = &((*new)->rb_right); ++ } ++ ++ entity->weight_counter = kzalloc(sizeof(struct bfq_weight_counter), ++ GFP_ATOMIC); ++ entity->weight_counter->weight = entity->weight; ++ rb_link_node(&entity->weight_counter->weights_node, parent, new); ++ rb_insert_color(&entity->weight_counter->weights_node, root); ++ ++inc_counter: ++ entity->weight_counter->num_active++; ++} ++ ++/* ++ * Decrement the weight counter associated with the entity, and, if the ++ * counter reaches 0, remove the counter from the tree. ++ * See the comments to the function bfq_weights_tree_add() for considerations ++ * about overhead. ++ */ ++static void bfq_weights_tree_remove(struct bfq_data *bfqd, ++ struct bfq_entity *entity, ++ struct rb_root *root) ++{ ++ if (!entity->weight_counter) ++ return; ++ ++ BUG_ON(RB_EMPTY_ROOT(root)); ++ BUG_ON(entity->weight_counter->weight != entity->weight); ++ ++ BUG_ON(!entity->weight_counter->num_active); ++ entity->weight_counter->num_active--; ++ if (entity->weight_counter->num_active > 0) ++ goto reset_entity_pointer; ++ ++ rb_erase(&entity->weight_counter->weights_node, root); ++ kfree(entity->weight_counter); ++ ++reset_entity_pointer: ++ entity->weight_counter = NULL; ++} ++ ++static struct request *bfq_find_next_rq(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ struct request *last) ++{ ++ struct rb_node *rbnext = rb_next(&last->rb_node); ++ struct rb_node *rbprev = rb_prev(&last->rb_node); ++ struct request *next = NULL, *prev = NULL; ++ ++ BUG_ON(RB_EMPTY_NODE(&last->rb_node)); ++ ++ if (rbprev) ++ prev = rb_entry_rq(rbprev); ++ ++ if (rbnext) ++ next = rb_entry_rq(rbnext); ++ else { ++ rbnext = rb_first(&bfqq->sort_list); ++ if (rbnext && rbnext != &last->rb_node) ++ next = rb_entry_rq(rbnext); ++ } ++ ++ return bfq_choose_req(bfqd, next, prev, blk_rq_pos(last)); ++} ++ ++/* see the definition of bfq_async_charge_factor for details */ ++static unsigned long bfq_serv_to_charge(struct request *rq, ++ struct bfq_queue *bfqq) ++{ ++ if (bfq_bfqq_sync(bfqq) || bfqq->wr_coeff > 1) ++ return blk_rq_sectors(rq); ++ ++ /* ++ * If there are no weight-raised queues, then amplify service ++ * by just the async charge factor; otherwise amplify service ++ * by twice the async charge factor, to further reduce latency ++ * for weight-raised queues. ++ */ ++ if (bfqq->bfqd->wr_busy_queues == 0) ++ return blk_rq_sectors(rq) * bfq_async_charge_factor; ++ ++ return blk_rq_sectors(rq) * 2 * bfq_async_charge_factor; ++} ++ ++/** ++ * bfq_updated_next_req - update the queue after a new next_rq selection. ++ * @bfqd: the device data the queue belongs to. ++ * @bfqq: the queue to update. ++ * ++ * If the first request of a queue changes we make sure that the queue ++ * has enough budget to serve at least its first request (if the ++ * request has grown). We do this because if the queue has not enough ++ * budget for its first request, it has to go through two dispatch ++ * rounds to actually get it dispatched. ++ */ ++static void bfq_updated_next_req(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ struct bfq_service_tree *st = bfq_entity_service_tree(entity); ++ struct request *next_rq = bfqq->next_rq; ++ unsigned long new_budget; ++ ++ if (!next_rq) ++ return; ++ ++ if (bfqq == bfqd->in_service_queue) ++ /* ++ * In order not to break guarantees, budgets cannot be ++ * changed after an entity has been selected. ++ */ ++ return; ++ ++ BUG_ON(entity->tree != &st->active); ++ BUG_ON(entity == entity->sched_data->in_service_entity); ++ ++ new_budget = max_t(unsigned long, bfqq->max_budget, ++ bfq_serv_to_charge(next_rq, bfqq)); ++ if (entity->budget != new_budget) { ++ entity->budget = new_budget; ++ bfq_log_bfqq(bfqd, bfqq, "updated next rq: new budget %lu", ++ new_budget); ++ bfq_activate_bfqq(bfqd, bfqq); ++ } ++} ++ ++static unsigned int bfq_wr_duration(struct bfq_data *bfqd) ++{ ++ u64 dur; ++ ++ if (bfqd->bfq_wr_max_time > 0) ++ return bfqd->bfq_wr_max_time; ++ ++ dur = bfqd->RT_prod; ++ do_div(dur, bfqd->peak_rate); ++ ++ /* ++ * Limit duration between 3 and 13 seconds. Tests show that ++ * higher values than 13 seconds often yield the opposite of ++ * the desired result, i.e., worsen responsiveness by letting ++ * non-interactive and non-soft-real-time applications ++ * preserve weight raising for a too long time interval. ++ * ++ * On the other end, lower values than 3 seconds make it ++ * difficult for most interactive tasks to complete their jobs ++ * before weight-raising finishes. ++ */ ++ if (dur > msecs_to_jiffies(13000)) ++ dur = msecs_to_jiffies(13000); ++ else if (dur < msecs_to_jiffies(3000)) ++ dur = msecs_to_jiffies(3000); ++ ++ return dur; ++} ++ ++static void ++bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic) ++{ ++ if (bic->saved_idle_window) ++ bfq_mark_bfqq_idle_window(bfqq); ++ else ++ bfq_clear_bfqq_idle_window(bfqq); ++ ++ if (bic->saved_IO_bound) ++ bfq_mark_bfqq_IO_bound(bfqq); ++ else ++ bfq_clear_bfqq_IO_bound(bfqq); ++ ++ bfqq->wr_coeff = bic->saved_wr_coeff; ++ bfqq->wr_start_at_switch_to_srt = bic->saved_wr_start_at_switch_to_srt; ++ BUG_ON(time_is_after_jiffies(bfqq->wr_start_at_switch_to_srt)); ++ bfqq->last_wr_start_finish = bic->saved_last_wr_start_finish; ++ BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); ++ ++ if (bfqq->wr_coeff > 1 && (bfq_bfqq_in_large_burst(bfqq) || ++ time_is_before_jiffies(bfqq->last_wr_start_finish + ++ bfqq->wr_cur_max_time))) { ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "resume state: switching off wr"); ++ ++ bfqq->wr_coeff = 1; ++ } ++ /* make sure weight will be updated, however we got here */ ++ bfqq->entity.prio_changed = 1; ++} ++ ++static int bfqq_process_refs(struct bfq_queue *bfqq) ++{ ++ int process_refs, io_refs; ++ ++ lockdep_assert_held(bfqq->bfqd->queue->queue_lock); ++ ++ io_refs = bfqq->allocated[READ] + bfqq->allocated[WRITE]; ++ process_refs = bfqq->ref - io_refs - bfqq->entity.on_st; ++ BUG_ON(process_refs < 0); ++ return process_refs; ++} ++ ++/* Empty burst list and add just bfqq (see comments to bfq_handle_burst) */ ++static void bfq_reset_burst_list(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ struct bfq_queue *item; ++ struct hlist_node *n; ++ ++ hlist_for_each_entry_safe(item, n, &bfqd->burst_list, burst_list_node) ++ hlist_del_init(&item->burst_list_node); ++ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list); ++ bfqd->burst_size = 1; ++ bfqd->burst_parent_entity = bfqq->entity.parent; ++} ++ ++/* Add bfqq to the list of queues in current burst (see bfq_handle_burst) */ ++static void bfq_add_to_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ /* Increment burst size to take into account also bfqq */ ++ bfqd->burst_size++; ++ ++ bfq_log_bfqq(bfqd, bfqq, "add_to_burst %d", bfqd->burst_size); ++ ++ BUG_ON(bfqd->burst_size > bfqd->bfq_large_burst_thresh); ++ ++ if (bfqd->burst_size == bfqd->bfq_large_burst_thresh) { ++ struct bfq_queue *pos, *bfqq_item; ++ struct hlist_node *n; ++ ++ /* ++ * Enough queues have been activated shortly after each ++ * other to consider this burst as large. ++ */ ++ bfqd->large_burst = true; ++ bfq_log_bfqq(bfqd, bfqq, "add_to_burst: large burst started"); ++ ++ /* ++ * We can now mark all queues in the burst list as ++ * belonging to a large burst. ++ */ ++ hlist_for_each_entry(bfqq_item, &bfqd->burst_list, ++ burst_list_node) { ++ bfq_mark_bfqq_in_large_burst(bfqq_item); ++ bfq_log_bfqq(bfqd, bfqq_item, "marked in large burst"); ++ } ++ bfq_mark_bfqq_in_large_burst(bfqq); ++ bfq_log_bfqq(bfqd, bfqq, "marked in large burst"); ++ ++ /* ++ * From now on, and until the current burst finishes, any ++ * new queue being activated shortly after the last queue ++ * was inserted in the burst can be immediately marked as ++ * belonging to a large burst. So the burst list is not ++ * needed any more. Remove it. ++ */ ++ hlist_for_each_entry_safe(pos, n, &bfqd->burst_list, ++ burst_list_node) ++ hlist_del_init(&pos->burst_list_node); ++ } else /* ++ * Burst not yet large: add bfqq to the burst list. Do ++ * not increment the ref counter for bfqq, because bfqq ++ * is removed from the burst list before freeing bfqq ++ * in put_queue. ++ */ ++ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list); ++} ++ ++/* ++ * If many queues belonging to the same group happen to be created ++ * shortly after each other, then the processes associated with these ++ * queues have typically a common goal. In particular, bursts of queue ++ * creations are usually caused by services or applications that spawn ++ * many parallel threads/processes. Examples are systemd during boot, ++ * or git grep. To help these processes get their job done as soon as ++ * possible, it is usually better to not grant either weight-raising ++ * or device idling to their queues. ++ * ++ * In this comment we describe, firstly, the reasons why this fact ++ * holds, and, secondly, the next function, which implements the main ++ * steps needed to properly mark these queues so that they can then be ++ * treated in a different way. ++ * ++ * The above services or applications benefit mostly from a high ++ * throughput: the quicker the requests of the activated queues are ++ * cumulatively served, the sooner the target job of these queues gets ++ * completed. As a consequence, weight-raising any of these queues, ++ * which also implies idling the device for it, is almost always ++ * counterproductive. In most cases it just lowers throughput. ++ * ++ * On the other hand, a burst of queue creations may be caused also by ++ * the start of an application that does not consist of a lot of ++ * parallel I/O-bound threads. In fact, with a complex application, ++ * several short processes may need to be executed to start-up the ++ * application. In this respect, to start an application as quickly as ++ * possible, the best thing to do is in any case to privilege the I/O ++ * related to the application with respect to all other ++ * I/O. Therefore, the best strategy to start as quickly as possible ++ * an application that causes a burst of queue creations is to ++ * weight-raise all the queues created during the burst. This is the ++ * exact opposite of the best strategy for the other type of bursts. ++ * ++ * In the end, to take the best action for each of the two cases, the ++ * two types of bursts need to be distinguished. Fortunately, this ++ * seems relatively easy, by looking at the sizes of the bursts. In ++ * particular, we found a threshold such that only bursts with a ++ * larger size than that threshold are apparently caused by ++ * services or commands such as systemd or git grep. For brevity, ++ * hereafter we call just 'large' these bursts. BFQ *does not* ++ * weight-raise queues whose creation occurs in a large burst. In ++ * addition, for each of these queues BFQ performs or does not perform ++ * idling depending on which choice boosts the throughput more. The ++ * exact choice depends on the device and request pattern at ++ * hand. ++ * ++ * Unfortunately, false positives may occur while an interactive task ++ * is starting (e.g., an application is being started). The ++ * consequence is that the queues associated with the task do not ++ * enjoy weight raising as expected. Fortunately these false positives ++ * are very rare. They typically occur if some service happens to ++ * start doing I/O exactly when the interactive task starts. ++ * ++ * Turning back to the next function, it implements all the steps ++ * needed to detect the occurrence of a large burst and to properly ++ * mark all the queues belonging to it (so that they can then be ++ * treated in a different way). This goal is achieved by maintaining a ++ * "burst list" that holds, temporarily, the queues that belong to the ++ * burst in progress. The list is then used to mark these queues as ++ * belonging to a large burst if the burst does become large. The main ++ * steps are the following. ++ * ++ * . when the very first queue is created, the queue is inserted into the ++ * list (as it could be the first queue in a possible burst) ++ * ++ * . if the current burst has not yet become large, and a queue Q that does ++ * not yet belong to the burst is activated shortly after the last time ++ * at which a new queue entered the burst list, then the function appends ++ * Q to the burst list ++ * ++ * . if, as a consequence of the previous step, the burst size reaches ++ * the large-burst threshold, then ++ * ++ * . all the queues in the burst list are marked as belonging to a ++ * large burst ++ * ++ * . the burst list is deleted; in fact, the burst list already served ++ * its purpose (keeping temporarily track of the queues in a burst, ++ * so as to be able to mark them as belonging to a large burst in the ++ * previous sub-step), and now is not needed any more ++ * ++ * . the device enters a large-burst mode ++ * ++ * . if a queue Q that does not belong to the burst is created while ++ * the device is in large-burst mode and shortly after the last time ++ * at which a queue either entered the burst list or was marked as ++ * belonging to the current large burst, then Q is immediately marked ++ * as belonging to a large burst. ++ * ++ * . if a queue Q that does not belong to the burst is created a while ++ * later, i.e., not shortly after, than the last time at which a queue ++ * either entered the burst list or was marked as belonging to the ++ * current large burst, then the current burst is deemed as finished and: ++ * ++ * . the large-burst mode is reset if set ++ * ++ * . the burst list is emptied ++ * ++ * . Q is inserted in the burst list, as Q may be the first queue ++ * in a possible new burst (then the burst list contains just Q ++ * after this step). ++ */ ++static void bfq_handle_burst(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ /* ++ * If bfqq is already in the burst list or is part of a large ++ * burst, or finally has just been split, then there is ++ * nothing else to do. ++ */ ++ if (!hlist_unhashed(&bfqq->burst_list_node) || ++ bfq_bfqq_in_large_burst(bfqq) || ++ time_is_after_eq_jiffies(bfqq->split_time + ++ msecs_to_jiffies(10))) ++ return; ++ ++ /* ++ * If bfqq's creation happens late enough, or bfqq belongs to ++ * a different group than the burst group, then the current ++ * burst is finished, and related data structures must be ++ * reset. ++ * ++ * In this respect, consider the special case where bfqq is ++ * the very first queue created after BFQ is selected for this ++ * device. In this case, last_ins_in_burst and ++ * burst_parent_entity are not yet significant when we get ++ * here. But it is easy to verify that, whether or not the ++ * following condition is true, bfqq will end up being ++ * inserted into the burst list. In particular the list will ++ * happen to contain only bfqq. And this is exactly what has ++ * to happen, as bfqq may be the first queue of the first ++ * burst. ++ */ ++ if (time_is_before_jiffies(bfqd->last_ins_in_burst + ++ bfqd->bfq_burst_interval) || ++ bfqq->entity.parent != bfqd->burst_parent_entity) { ++ bfqd->large_burst = false; ++ bfq_reset_burst_list(bfqd, bfqq); ++ bfq_log_bfqq(bfqd, bfqq, ++ "handle_burst: late activation or different group"); ++ goto end; ++ } ++ ++ /* ++ * If we get here, then bfqq is being activated shortly after the ++ * last queue. So, if the current burst is also large, we can mark ++ * bfqq as belonging to this large burst immediately. ++ */ ++ if (bfqd->large_burst) { ++ bfq_log_bfqq(bfqd, bfqq, "handle_burst: marked in burst"); ++ bfq_mark_bfqq_in_large_burst(bfqq); ++ goto end; ++ } ++ ++ /* ++ * If we get here, then a large-burst state has not yet been ++ * reached, but bfqq is being activated shortly after the last ++ * queue. Then we add bfqq to the burst. ++ */ ++ bfq_add_to_burst(bfqd, bfqq); ++end: ++ /* ++ * At this point, bfqq either has been added to the current ++ * burst or has caused the current burst to terminate and a ++ * possible new burst to start. In particular, in the second ++ * case, bfqq has become the first queue in the possible new ++ * burst. In both cases last_ins_in_burst needs to be moved ++ * forward. ++ */ ++ bfqd->last_ins_in_burst = jiffies; ++ ++} ++ ++static int bfq_bfqq_budget_left(struct bfq_queue *bfqq) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ ++ return entity->budget - entity->service; ++} ++ ++/* ++ * If enough samples have been computed, return the current max budget ++ * stored in bfqd, which is dynamically updated according to the ++ * estimated disk peak rate; otherwise return the default max budget ++ */ ++static int bfq_max_budget(struct bfq_data *bfqd) ++{ ++ if (bfqd->budgets_assigned < bfq_stats_min_budgets) ++ return bfq_default_max_budget; ++ else ++ return bfqd->bfq_max_budget; ++} ++ ++/* ++ * Return min budget, which is a fraction of the current or default ++ * max budget (trying with 1/32) ++ */ ++static int bfq_min_budget(struct bfq_data *bfqd) ++{ ++ if (bfqd->budgets_assigned < bfq_stats_min_budgets) ++ return bfq_default_max_budget / 32; ++ else ++ return bfqd->bfq_max_budget / 32; ++} ++ ++static void bfq_bfqq_expire(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ bool compensate, ++ enum bfqq_expiration reason); ++ ++/* ++ * The next function, invoked after the input queue bfqq switches from ++ * idle to busy, updates the budget of bfqq. The function also tells ++ * whether the in-service queue should be expired, by returning ++ * true. The purpose of expiring the in-service queue is to give bfqq ++ * the chance to possibly preempt the in-service queue, and the reason ++ * for preempting the in-service queue is to achieve one of the two ++ * goals below. ++ * ++ * 1. Guarantee to bfqq its reserved bandwidth even if bfqq has ++ * expired because it has remained idle. In particular, bfqq may have ++ * expired for one of the following two reasons: ++ * ++ * - BFQ_BFQQ_NO_MORE_REQUEST bfqq did not enjoy any device idling and ++ * did not make it to issue a new request before its last request ++ * was served; ++ * ++ * - BFQ_BFQQ_TOO_IDLE bfqq did enjoy device idling, but did not issue ++ * a new request before the expiration of the idling-time. ++ * ++ * Even if bfqq has expired for one of the above reasons, the process ++ * associated with the queue may be however issuing requests greedily, ++ * and thus be sensitive to the bandwidth it receives (bfqq may have ++ * remained idle for other reasons: CPU high load, bfqq not enjoying ++ * idling, I/O throttling somewhere in the path from the process to ++ * the I/O scheduler, ...). But if, after every expiration for one of ++ * the above two reasons, bfqq has to wait for the service of at least ++ * one full budget of another queue before being served again, then ++ * bfqq is likely to get a much lower bandwidth or resource time than ++ * its reserved ones. To address this issue, two countermeasures need ++ * to be taken. ++ * ++ * First, the budget and the timestamps of bfqq need to be updated in ++ * a special way on bfqq reactivation: they need to be updated as if ++ * bfqq did not remain idle and did not expire. In fact, if they are ++ * computed as if bfqq expired and remained idle until reactivation, ++ * then the process associated with bfqq is treated as if, instead of ++ * being greedy, it stopped issuing requests when bfqq remained idle, ++ * and restarts issuing requests only on this reactivation. In other ++ * words, the scheduler does not help the process recover the "service ++ * hole" between bfqq expiration and reactivation. As a consequence, ++ * the process receives a lower bandwidth than its reserved one. In ++ * contrast, to recover this hole, the budget must be updated as if ++ * bfqq was not expired at all before this reactivation, i.e., it must ++ * be set to the value of the remaining budget when bfqq was ++ * expired. Along the same line, timestamps need to be assigned the ++ * value they had the last time bfqq was selected for service, i.e., ++ * before last expiration. Thus timestamps need to be back-shifted ++ * with respect to their normal computation (see [1] for more details ++ * on this tricky aspect). ++ * ++ * Secondly, to allow the process to recover the hole, the in-service ++ * queue must be expired too, to give bfqq the chance to preempt it ++ * immediately. In fact, if bfqq has to wait for a full budget of the ++ * in-service queue to be completed, then it may become impossible to ++ * let the process recover the hole, even if the back-shifted ++ * timestamps of bfqq are lower than those of the in-service queue. If ++ * this happens for most or all of the holes, then the process may not ++ * receive its reserved bandwidth. In this respect, it is worth noting ++ * that, being the service of outstanding requests unpreemptible, a ++ * little fraction of the holes may however be unrecoverable, thereby ++ * causing a little loss of bandwidth. ++ * ++ * The last important point is detecting whether bfqq does need this ++ * bandwidth recovery. In this respect, the next function deems the ++ * process associated with bfqq greedy, and thus allows it to recover ++ * the hole, if: 1) the process is waiting for the arrival of a new ++ * request (which implies that bfqq expired for one of the above two ++ * reasons), and 2) such a request has arrived soon. The first ++ * condition is controlled through the flag non_blocking_wait_rq, ++ * while the second through the flag arrived_in_time. If both ++ * conditions hold, then the function computes the budget in the ++ * above-described special way, and signals that the in-service queue ++ * should be expired. Timestamp back-shifting is done later in ++ * __bfq_activate_entity. ++ * ++ * 2. Reduce latency. Even if timestamps are not backshifted to let ++ * the process associated with bfqq recover a service hole, bfqq may ++ * however happen to have, after being (re)activated, a lower finish ++ * timestamp than the in-service queue. That is, the next budget of ++ * bfqq may have to be completed before the one of the in-service ++ * queue. If this is the case, then preempting the in-service queue ++ * allows this goal to be achieved, apart from the unpreemptible, ++ * outstanding requests mentioned above. ++ * ++ * Unfortunately, regardless of which of the above two goals one wants ++ * to achieve, service trees need first to be updated to know whether ++ * the in-service queue must be preempted. To have service trees ++ * correctly updated, the in-service queue must be expired and ++ * rescheduled, and bfqq must be scheduled too. This is one of the ++ * most costly operations (in future versions, the scheduling ++ * mechanism may be re-designed in such a way to make it possible to ++ * know whether preemption is needed without needing to update service ++ * trees). In addition, queue preemptions almost always cause random ++ * I/O, and thus loss of throughput. Because of these facts, the next ++ * function adopts the following simple scheme to avoid both costly ++ * operations and too frequent preemptions: it requests the expiration ++ * of the in-service queue (unconditionally) only for queues that need ++ * to recover a hole, or that either are weight-raised or deserve to ++ * be weight-raised. ++ */ ++static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ bool arrived_in_time, ++ bool wr_or_deserves_wr) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ ++ if (bfq_bfqq_non_blocking_wait_rq(bfqq) && arrived_in_time) { ++ /* ++ * We do not clear the flag non_blocking_wait_rq here, as ++ * the latter is used in bfq_activate_bfqq to signal ++ * that timestamps need to be back-shifted (and is ++ * cleared right after). ++ */ ++ ++ /* ++ * In next assignment we rely on that either ++ * entity->service or entity->budget are not updated ++ * on expiration if bfqq is empty (see ++ * __bfq_bfqq_recalc_budget). Thus both quantities ++ * remain unchanged after such an expiration, and the ++ * following statement therefore assigns to ++ * entity->budget the remaining budget on such an ++ * expiration. For clarity, entity->service is not ++ * updated on expiration in any case, and, in normal ++ * operation, is reset only when bfqq is selected for ++ * service (see bfq_get_next_queue). ++ */ ++ BUG_ON(bfqq->max_budget < 0); ++ entity->budget = min_t(unsigned long, ++ bfq_bfqq_budget_left(bfqq), ++ bfqq->max_budget); ++ ++ BUG_ON(entity->budget < 0); ++ return true; ++ } ++ ++ BUG_ON(bfqq->max_budget < 0); ++ entity->budget = max_t(unsigned long, bfqq->max_budget, ++ bfq_serv_to_charge(bfqq->next_rq, bfqq)); ++ BUG_ON(entity->budget < 0); ++ ++ bfq_clear_bfqq_non_blocking_wait_rq(bfqq); ++ return wr_or_deserves_wr; ++} ++ ++static void bfq_update_bfqq_wr_on_rq_arrival(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ unsigned int old_wr_coeff, ++ bool wr_or_deserves_wr, ++ bool interactive, ++ bool in_burst, ++ bool soft_rt) ++{ ++ if (old_wr_coeff == 1 && wr_or_deserves_wr) { ++ /* start a weight-raising period */ ++ if (interactive) { ++ bfqq->wr_coeff = bfqd->bfq_wr_coeff; ++ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); ++ } else { ++ bfqq->wr_start_at_switch_to_srt = jiffies; ++ bfqq->wr_coeff = bfqd->bfq_wr_coeff * ++ BFQ_SOFTRT_WEIGHT_FACTOR; ++ bfqq->wr_cur_max_time = ++ bfqd->bfq_wr_rt_max_time; ++ } ++ /* ++ * If needed, further reduce budget to make sure it is ++ * close to bfqq's backlog, so as to reduce the ++ * scheduling-error component due to a too large ++ * budget. Do not care about throughput consequences, ++ * but only about latency. Finally, do not assign a ++ * too small budget either, to avoid increasing ++ * latency by causing too frequent expirations. ++ */ ++ bfqq->entity.budget = min_t(unsigned long, ++ bfqq->entity.budget, ++ 2 * bfq_min_budget(bfqd)); ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "wrais starting at %lu, rais_max_time %u", ++ jiffies, ++ jiffies_to_msecs(bfqq->wr_cur_max_time)); ++ } else if (old_wr_coeff > 1) { ++ if (interactive) { /* update wr coeff and duration */ ++ bfqq->wr_coeff = bfqd->bfq_wr_coeff; ++ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); ++ } else if (in_burst) { ++ bfqq->wr_coeff = 1; ++ bfq_log_bfqq(bfqd, bfqq, ++ "wrais ending at %lu, rais_max_time %u", ++ jiffies, ++ jiffies_to_msecs(bfqq-> ++ wr_cur_max_time)); ++ } else if (soft_rt) { ++ /* ++ * The application is now or still meeting the ++ * requirements for being deemed soft rt. We ++ * can then correctly and safely (re)charge ++ * the weight-raising duration for the ++ * application with the weight-raising ++ * duration for soft rt applications. ++ * ++ * In particular, doing this recharge now, i.e., ++ * before the weight-raising period for the ++ * application finishes, reduces the probability ++ * of the following negative scenario: ++ * 1) the weight of a soft rt application is ++ * raised at startup (as for any newly ++ * created application), ++ * 2) since the application is not interactive, ++ * at a certain time weight-raising is ++ * stopped for the application, ++ * 3) at that time the application happens to ++ * still have pending requests, and hence ++ * is destined to not have a chance to be ++ * deemed soft rt before these requests are ++ * completed (see the comments to the ++ * function bfq_bfqq_softrt_next_start() ++ * for details on soft rt detection), ++ * 4) these pending requests experience a high ++ * latency because the application is not ++ * weight-raised while they are pending. ++ */ ++ if (bfqq->wr_cur_max_time != ++ bfqd->bfq_wr_rt_max_time) { ++ bfqq->wr_start_at_switch_to_srt = ++ bfqq->last_wr_start_finish; ++ BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); ++ ++ bfqq->wr_cur_max_time = ++ bfqd->bfq_wr_rt_max_time; ++ bfqq->wr_coeff = bfqd->bfq_wr_coeff * ++ BFQ_SOFTRT_WEIGHT_FACTOR; ++ bfq_log_bfqq(bfqd, bfqq, ++ "switching to soft_rt wr"); ++ } else ++ bfq_log_bfqq(bfqd, bfqq, ++ "moving forward soft_rt wr duration"); ++ bfqq->last_wr_start_finish = jiffies; ++ } ++ } ++} ++ ++static bool bfq_bfqq_idle_for_long_time(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq) ++{ ++ return bfqq->dispatched == 0 && ++ time_is_before_jiffies( ++ bfqq->budget_timeout + ++ bfqd->bfq_wr_min_idle_time); ++} ++ ++static void bfq_bfqq_handle_idle_busy_switch(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ int old_wr_coeff, ++ struct request *rq, ++ bool *interactive) ++{ ++ bool soft_rt, in_burst, wr_or_deserves_wr, ++ bfqq_wants_to_preempt, ++ idle_for_long_time = bfq_bfqq_idle_for_long_time(bfqd, bfqq), ++ /* ++ * See the comments on ++ * bfq_bfqq_update_budg_for_activation for ++ * details on the usage of the next variable. ++ */ ++ arrived_in_time = ktime_get_ns() <= ++ RQ_BIC(rq)->ttime.last_end_request + ++ bfqd->bfq_slice_idle * 3; ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "bfq_add_request non-busy: " ++ "jiffies %lu, in_time %d, idle_long %d busyw %d " ++ "wr_coeff %u", ++ jiffies, arrived_in_time, ++ idle_for_long_time, ++ bfq_bfqq_non_blocking_wait_rq(bfqq), ++ old_wr_coeff); ++ ++ BUG_ON(bfqq->entity.budget < bfqq->entity.service); ++ ++ BUG_ON(bfqq == bfqd->in_service_queue); ++ bfqg_stats_update_io_add(bfqq_group(RQ_BFQQ(rq)), bfqq, ++ req_op(rq), rq->cmd_flags); ++ ++ /* ++ * bfqq deserves to be weight-raised if: ++ * - it is sync, ++ * - it does not belong to a large burst, ++ * - it has been idle for enough time or is soft real-time, ++ * - is linked to a bfq_io_cq (it is not shared in any sense) ++ */ ++ in_burst = bfq_bfqq_in_large_burst(bfqq); ++ soft_rt = bfqd->bfq_wr_max_softrt_rate > 0 && ++ !in_burst && ++ time_is_before_jiffies(bfqq->soft_rt_next_start); ++ *interactive = ++ !in_burst && ++ idle_for_long_time; ++ wr_or_deserves_wr = bfqd->low_latency && ++ (bfqq->wr_coeff > 1 || ++ (bfq_bfqq_sync(bfqq) && ++ bfqq->bic && (*interactive || soft_rt))); ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "bfq_add_request: " ++ "in_burst %d, " ++ "soft_rt %d (next %lu), inter %d, bic %p", ++ bfq_bfqq_in_large_burst(bfqq), soft_rt, ++ bfqq->soft_rt_next_start, ++ *interactive, ++ bfqq->bic); ++ ++ /* ++ * Using the last flag, update budget and check whether bfqq ++ * may want to preempt the in-service queue. ++ */ ++ bfqq_wants_to_preempt = ++ bfq_bfqq_update_budg_for_activation(bfqd, bfqq, ++ arrived_in_time, ++ wr_or_deserves_wr); ++ ++ /* ++ * If bfqq happened to be activated in a burst, but has been ++ * idle for much more than an interactive queue, then we ++ * assume that, in the overall I/O initiated in the burst, the ++ * I/O associated with bfqq is finished. So bfqq does not need ++ * to be treated as a queue belonging to a burst ++ * anymore. Accordingly, we reset bfqq's in_large_burst flag ++ * if set, and remove bfqq from the burst list if it's ++ * there. We do not decrement burst_size, because the fact ++ * that bfqq does not need to belong to the burst list any ++ * more does not invalidate the fact that bfqq was created in ++ * a burst. ++ */ ++ if (likely(!bfq_bfqq_just_created(bfqq)) && ++ idle_for_long_time && ++ time_is_before_jiffies( ++ bfqq->budget_timeout + ++ msecs_to_jiffies(10000))) { ++ hlist_del_init(&bfqq->burst_list_node); ++ bfq_clear_bfqq_in_large_burst(bfqq); ++ } ++ ++ bfq_clear_bfqq_just_created(bfqq); ++ ++ if (!bfq_bfqq_IO_bound(bfqq)) { ++ if (arrived_in_time) { ++ bfqq->requests_within_timer++; ++ if (bfqq->requests_within_timer >= ++ bfqd->bfq_requests_within_timer) ++ bfq_mark_bfqq_IO_bound(bfqq); ++ } else ++ bfqq->requests_within_timer = 0; ++ bfq_log_bfqq(bfqd, bfqq, "requests in time %d", ++ bfqq->requests_within_timer); ++ } ++ ++ if (bfqd->low_latency) { ++ if (unlikely(time_is_after_jiffies(bfqq->split_time))) ++ /* wraparound */ ++ bfqq->split_time = ++ jiffies - bfqd->bfq_wr_min_idle_time - 1; ++ ++ if (time_is_before_jiffies(bfqq->split_time + ++ bfqd->bfq_wr_min_idle_time)) { ++ bfq_update_bfqq_wr_on_rq_arrival(bfqd, bfqq, ++ old_wr_coeff, ++ wr_or_deserves_wr, ++ *interactive, ++ in_burst, ++ soft_rt); ++ ++ if (old_wr_coeff != bfqq->wr_coeff) ++ bfqq->entity.prio_changed = 1; ++ } ++ } ++ ++ bfqq->last_idle_bklogged = jiffies; ++ bfqq->service_from_backlogged = 0; ++ bfq_clear_bfqq_softrt_update(bfqq); ++ ++ bfq_add_bfqq_busy(bfqd, bfqq); ++ ++ /* ++ * Expire in-service queue only if preemption may be needed ++ * for guarantees. In this respect, the function ++ * next_queue_may_preempt just checks a simple, necessary ++ * condition, and not a sufficient condition based on ++ * timestamps. In fact, for the latter condition to be ++ * evaluated, timestamps would need first to be updated, and ++ * this operation is quite costly (see the comments on the ++ * function bfq_bfqq_update_budg_for_activation). ++ */ ++ if (bfqd->in_service_queue && bfqq_wants_to_preempt && ++ bfqd->in_service_queue->wr_coeff < bfqq->wr_coeff && ++ next_queue_may_preempt(bfqd)) { ++ struct bfq_queue *in_serv = ++ bfqd->in_service_queue; ++ BUG_ON(in_serv == bfqq); ++ ++ bfq_bfqq_expire(bfqd, bfqd->in_service_queue, ++ false, BFQ_BFQQ_PREEMPTED); ++ BUG_ON(in_serv->entity.budget < 0); ++ } ++} ++ ++static void bfq_add_request(struct request *rq) ++{ ++ struct bfq_queue *bfqq = RQ_BFQQ(rq); ++ struct bfq_data *bfqd = bfqq->bfqd; ++ struct request *next_rq, *prev; ++ unsigned int old_wr_coeff = bfqq->wr_coeff; ++ bool interactive = false; ++ ++ bfq_log_bfqq(bfqd, bfqq, "add_request: size %u %s", ++ blk_rq_sectors(rq), rq_is_sync(rq) ? "S" : "A"); ++ ++ if (bfqq->wr_coeff > 1) /* queue is being weight-raised */ ++ bfq_log_bfqq(bfqd, bfqq, ++ "raising period dur %u/%u msec, old coeff %u, w %d(%d)", ++ jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), ++ jiffies_to_msecs(bfqq->wr_cur_max_time), ++ bfqq->wr_coeff, ++ bfqq->entity.weight, bfqq->entity.orig_weight); ++ ++ bfqq->queued[rq_is_sync(rq)]++; ++ bfqd->queued++; ++ ++ elv_rb_add(&bfqq->sort_list, rq); ++ ++ /* ++ * Check if this request is a better next-to-serve candidate. ++ */ ++ prev = bfqq->next_rq; ++ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, rq, bfqd->last_position); ++ BUG_ON(!next_rq); ++ bfqq->next_rq = next_rq; ++ ++ /* ++ * Adjust priority tree position, if next_rq changes. ++ */ ++ if (prev != bfqq->next_rq) ++ bfq_pos_tree_add_move(bfqd, bfqq); ++ ++ if (!bfq_bfqq_busy(bfqq)) /* switching to busy ... */ ++ bfq_bfqq_handle_idle_busy_switch(bfqd, bfqq, old_wr_coeff, ++ rq, &interactive); ++ else { ++ if (bfqd->low_latency && old_wr_coeff == 1 && !rq_is_sync(rq) && ++ time_is_before_jiffies( ++ bfqq->last_wr_start_finish + ++ bfqd->bfq_wr_min_inter_arr_async)) { ++ bfqq->wr_coeff = bfqd->bfq_wr_coeff; ++ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); ++ ++ bfqd->wr_busy_queues++; ++ bfqq->entity.prio_changed = 1; ++ bfq_log_bfqq(bfqd, bfqq, ++ "non-idle wrais starting, " ++ "wr_max_time %u wr_busy %d", ++ jiffies_to_msecs(bfqq->wr_cur_max_time), ++ bfqd->wr_busy_queues); ++ } ++ if (prev != bfqq->next_rq) ++ bfq_updated_next_req(bfqd, bfqq); ++ } ++ ++ /* ++ * Assign jiffies to last_wr_start_finish in the following ++ * cases: ++ * ++ * . if bfqq is not going to be weight-raised, because, for ++ * non weight-raised queues, last_wr_start_finish stores the ++ * arrival time of the last request; as of now, this piece ++ * of information is used only for deciding whether to ++ * weight-raise async queues ++ * ++ * . if bfqq is not weight-raised, because, if bfqq is now ++ * switching to weight-raised, then last_wr_start_finish ++ * stores the time when weight-raising starts ++ * ++ * . if bfqq is interactive, because, regardless of whether ++ * bfqq is currently weight-raised, the weight-raising ++ * period must start or restart (this case is considered ++ * separately because it is not detected by the above ++ * conditions, if bfqq is already weight-raised) ++ * ++ * last_wr_start_finish has to be updated also if bfqq is soft ++ * real-time, because the weight-raising period is constantly ++ * restarted on idle-to-busy transitions for these queues, but ++ * this is already done in bfq_bfqq_handle_idle_busy_switch if ++ * needed. ++ */ ++ if (bfqd->low_latency && ++ (old_wr_coeff == 1 || bfqq->wr_coeff == 1 || interactive)) ++ bfqq->last_wr_start_finish = jiffies; ++} ++ ++static struct request *bfq_find_rq_fmerge(struct bfq_data *bfqd, ++ struct bio *bio) ++{ ++ struct task_struct *tsk = current; ++ struct bfq_io_cq *bic; ++ struct bfq_queue *bfqq; ++ ++ bic = bfq_bic_lookup(bfqd, tsk->io_context); ++ if (!bic) ++ return NULL; ++ ++ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); ++ if (bfqq) ++ return elv_rb_find(&bfqq->sort_list, bio_end_sector(bio)); ++ ++ return NULL; ++} ++ ++static sector_t get_sdist(sector_t last_pos, struct request *rq) ++{ ++ sector_t sdist = 0; ++ ++ if (last_pos) { ++ if (last_pos < blk_rq_pos(rq)) ++ sdist = blk_rq_pos(rq) - last_pos; ++ else ++ sdist = last_pos - blk_rq_pos(rq); ++ } ++ ++ return sdist; ++} ++ ++static void bfq_activate_request(struct request_queue *q, struct request *rq) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ bfqd->rq_in_driver++; ++} ++ ++static void bfq_deactivate_request(struct request_queue *q, struct request *rq) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ ++ BUG_ON(bfqd->rq_in_driver == 0); ++ bfqd->rq_in_driver--; ++} ++ ++static void bfq_remove_request(struct request *rq) ++{ ++ struct bfq_queue *bfqq = RQ_BFQQ(rq); ++ struct bfq_data *bfqd = bfqq->bfqd; ++ const int sync = rq_is_sync(rq); ++ ++ BUG_ON(bfqq->entity.service > bfqq->entity.budget && ++ bfqq == bfqd->in_service_queue); ++ ++ if (bfqq->next_rq == rq) { ++ bfqq->next_rq = bfq_find_next_rq(bfqd, bfqq, rq); ++ bfq_updated_next_req(bfqd, bfqq); ++ } ++ ++ if (rq->queuelist.prev != &rq->queuelist) ++ list_del_init(&rq->queuelist); ++ BUG_ON(bfqq->queued[sync] == 0); ++ bfqq->queued[sync]--; ++ bfqd->queued--; ++ elv_rb_del(&bfqq->sort_list, rq); ++ ++ if (RB_EMPTY_ROOT(&bfqq->sort_list)) { ++ BUG_ON(bfqq->entity.budget < 0); ++ ++ if (bfq_bfqq_busy(bfqq) && bfqq != bfqd->in_service_queue) { ++ bfq_del_bfqq_busy(bfqd, bfqq, 1); ++ ++ /* bfqq emptied. In normal operation, when ++ * bfqq is empty, bfqq->entity.service and ++ * bfqq->entity.budget must contain, ++ * respectively, the service received and the ++ * budget used last time bfqq emptied. These ++ * facts do not hold in this case, as at least ++ * this last removal occurred while bfqq is ++ * not in service. To avoid inconsistencies, ++ * reset both bfqq->entity.service and ++ * bfqq->entity.budget. ++ */ ++ bfqq->entity.budget = bfqq->entity.service = 0; ++ } ++ ++ /* ++ * Remove queue from request-position tree as it is empty. ++ */ ++ if (bfqq->pos_root) { ++ rb_erase(&bfqq->pos_node, bfqq->pos_root); ++ bfqq->pos_root = NULL; ++ } ++ } ++ ++ if (rq->cmd_flags & REQ_META) { ++ BUG_ON(bfqq->meta_pending == 0); ++ bfqq->meta_pending--; ++ } ++ bfqg_stats_update_io_remove(bfqq_group(bfqq), req_op(rq), ++ rq->cmd_flags); ++} ++ ++static int bfq_merge(struct request_queue *q, struct request **req, ++ struct bio *bio) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ struct request *__rq; ++ ++ __rq = bfq_find_rq_fmerge(bfqd, bio); ++ if (__rq && elv_bio_merge_ok(__rq, bio)) { ++ *req = __rq; ++ return ELEVATOR_FRONT_MERGE; ++ } ++ ++ return ELEVATOR_NO_MERGE; ++} ++ ++static void bfq_merged_request(struct request_queue *q, struct request *req, ++ int type) ++{ ++ if (type == ELEVATOR_FRONT_MERGE && ++ rb_prev(&req->rb_node) && ++ blk_rq_pos(req) < ++ blk_rq_pos(container_of(rb_prev(&req->rb_node), ++ struct request, rb_node))) { ++ struct bfq_queue *bfqq = RQ_BFQQ(req); ++ struct bfq_data *bfqd = bfqq->bfqd; ++ struct request *prev, *next_rq; ++ ++ /* Reposition request in its sort_list */ ++ elv_rb_del(&bfqq->sort_list, req); ++ elv_rb_add(&bfqq->sort_list, req); ++ /* Choose next request to be served for bfqq */ ++ prev = bfqq->next_rq; ++ next_rq = bfq_choose_req(bfqd, bfqq->next_rq, req, ++ bfqd->last_position); ++ BUG_ON(!next_rq); ++ bfqq->next_rq = next_rq; ++ /* ++ * If next_rq changes, update both the queue's budget to ++ * fit the new request and the queue's position in its ++ * rq_pos_tree. ++ */ ++ if (prev != bfqq->next_rq) { ++ bfq_updated_next_req(bfqd, bfqq); ++ bfq_pos_tree_add_move(bfqd, bfqq); ++ } ++ } ++} ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++static void bfq_bio_merged(struct request_queue *q, struct request *req, ++ struct bio *bio) ++{ ++ bfqg_stats_update_io_merged(bfqq_group(RQ_BFQQ(req)), bio_op(bio), ++ bio->bi_opf); ++} ++#endif ++ ++static void bfq_merged_requests(struct request_queue *q, struct request *rq, ++ struct request *next) ++{ ++ struct bfq_queue *bfqq = RQ_BFQQ(rq), *next_bfqq = RQ_BFQQ(next); ++ ++ /* ++ * If next and rq belong to the same bfq_queue and next is older ++ * than rq, then reposition rq in the fifo (by substituting next ++ * with rq). Otherwise, if next and rq belong to different ++ * bfq_queues, never reposition rq: in fact, we would have to ++ * reposition it with respect to next's position in its own fifo, ++ * which would most certainly be too expensive with respect to ++ * the benefits. ++ */ ++ if (bfqq == next_bfqq && ++ !list_empty(&rq->queuelist) && !list_empty(&next->queuelist) && ++ next->fifo_time < rq->fifo_time) { ++ list_del_init(&rq->queuelist); ++ list_replace_init(&next->queuelist, &rq->queuelist); ++ rq->fifo_time = next->fifo_time; ++ } ++ ++ if (bfqq->next_rq == next) ++ bfqq->next_rq = rq; ++ ++ bfq_remove_request(next); ++ bfqg_stats_update_io_merged(bfqq_group(bfqq), req_op(next), ++ next->cmd_flags); ++} ++ ++/* Must be called with bfqq != NULL */ ++static void bfq_bfqq_end_wr(struct bfq_queue *bfqq) ++{ ++ BUG_ON(!bfqq); ++ ++ if (bfq_bfqq_busy(bfqq)) ++ bfqq->bfqd->wr_busy_queues--; ++ bfqq->wr_coeff = 1; ++ bfqq->wr_cur_max_time = 0; ++ bfqq->last_wr_start_finish = jiffies; ++ /* ++ * Trigger a weight change on the next invocation of ++ * __bfq_entity_update_weight_prio. ++ */ ++ bfqq->entity.prio_changed = 1; ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "end_wr: wrais ending at %lu, rais_max_time %u", ++ bfqq->last_wr_start_finish, ++ jiffies_to_msecs(bfqq->wr_cur_max_time)); ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "end_wr: wr_busy %d", ++ bfqq->bfqd->wr_busy_queues); ++} ++ ++static void bfq_end_wr_async_queues(struct bfq_data *bfqd, ++ struct bfq_group *bfqg) ++{ ++ int i, j; ++ ++ for (i = 0; i < 2; i++) ++ for (j = 0; j < IOPRIO_BE_NR; j++) ++ if (bfqg->async_bfqq[i][j]) ++ bfq_bfqq_end_wr(bfqg->async_bfqq[i][j]); ++ if (bfqg->async_idle_bfqq) ++ bfq_bfqq_end_wr(bfqg->async_idle_bfqq); ++} ++ ++static void bfq_end_wr(struct bfq_data *bfqd) ++{ ++ struct bfq_queue *bfqq; ++ ++ spin_lock_irq(bfqd->queue->queue_lock); ++ ++ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) ++ bfq_bfqq_end_wr(bfqq); ++ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) ++ bfq_bfqq_end_wr(bfqq); ++ bfq_end_wr_async(bfqd); ++ ++ spin_unlock_irq(bfqd->queue->queue_lock); ++} ++ ++static sector_t bfq_io_struct_pos(void *io_struct, bool request) ++{ ++ if (request) ++ return blk_rq_pos(io_struct); ++ else ++ return ((struct bio *)io_struct)->bi_iter.bi_sector; ++} ++ ++static int bfq_rq_close_to_sector(void *io_struct, bool request, ++ sector_t sector) ++{ ++ return abs(bfq_io_struct_pos(io_struct, request) - sector) <= ++ BFQQ_CLOSE_THR; ++} ++ ++static struct bfq_queue *bfqq_find_close(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ sector_t sector) ++{ ++ struct rb_root *root = &bfq_bfqq_to_bfqg(bfqq)->rq_pos_tree; ++ struct rb_node *parent, *node; ++ struct bfq_queue *__bfqq; ++ ++ if (RB_EMPTY_ROOT(root)) ++ return NULL; ++ ++ /* ++ * First, if we find a request starting at the end of the last ++ * request, choose it. ++ */ ++ __bfqq = bfq_rq_pos_tree_lookup(bfqd, root, sector, &parent, NULL); ++ if (__bfqq) ++ return __bfqq; ++ ++ /* ++ * If the exact sector wasn't found, the parent of the NULL leaf ++ * will contain the closest sector (rq_pos_tree sorted by ++ * next_request position). ++ */ ++ __bfqq = rb_entry(parent, struct bfq_queue, pos_node); ++ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) ++ return __bfqq; ++ ++ if (blk_rq_pos(__bfqq->next_rq) < sector) ++ node = rb_next(&__bfqq->pos_node); ++ else ++ node = rb_prev(&__bfqq->pos_node); ++ if (!node) ++ return NULL; ++ ++ __bfqq = rb_entry(node, struct bfq_queue, pos_node); ++ if (bfq_rq_close_to_sector(__bfqq->next_rq, true, sector)) ++ return __bfqq; ++ ++ return NULL; ++} ++ ++static struct bfq_queue *bfq_find_close_cooperator(struct bfq_data *bfqd, ++ struct bfq_queue *cur_bfqq, ++ sector_t sector) ++{ ++ struct bfq_queue *bfqq; ++ ++ /* ++ * We shall notice if some of the queues are cooperating, ++ * e.g., working closely on the same area of the device. In ++ * that case, we can group them together and: 1) don't waste ++ * time idling, and 2) serve the union of their requests in ++ * the best possible order for throughput. ++ */ ++ bfqq = bfqq_find_close(bfqd, cur_bfqq, sector); ++ if (!bfqq || bfqq == cur_bfqq) ++ return NULL; ++ ++ return bfqq; ++} ++ ++static struct bfq_queue * ++bfq_setup_merge(struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) ++{ ++ int process_refs, new_process_refs; ++ struct bfq_queue *__bfqq; ++ ++ /* ++ * If there are no process references on the new_bfqq, then it is ++ * unsafe to follow the ->new_bfqq chain as other bfqq's in the chain ++ * may have dropped their last reference (not just their last process ++ * reference). ++ */ ++ if (!bfqq_process_refs(new_bfqq)) ++ return NULL; ++ ++ /* Avoid a circular list and skip interim queue merges. */ ++ while ((__bfqq = new_bfqq->new_bfqq)) { ++ if (__bfqq == bfqq) ++ return NULL; ++ new_bfqq = __bfqq; ++ } ++ ++ process_refs = bfqq_process_refs(bfqq); ++ new_process_refs = bfqq_process_refs(new_bfqq); ++ /* ++ * If the process for the bfqq has gone away, there is no ++ * sense in merging the queues. ++ */ ++ if (process_refs == 0 || new_process_refs == 0) ++ return NULL; ++ ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "scheduling merge with queue %d", ++ new_bfqq->pid); ++ ++ /* ++ * Merging is just a redirection: the requests of the process ++ * owning one of the two queues are redirected to the other queue. ++ * The latter queue, in its turn, is set as shared if this is the ++ * first time that the requests of some process are redirected to ++ * it. ++ * ++ * We redirect bfqq to new_bfqq and not the opposite, because we ++ * are in the context of the process owning bfqq, hence we have ++ * the io_cq of this process. So we can immediately configure this ++ * io_cq to redirect the requests of the process to new_bfqq. ++ * ++ * NOTE, even if new_bfqq coincides with the in-service queue, the ++ * io_cq of new_bfqq is not available, because, if the in-service ++ * queue is shared, bfqd->in_service_bic may not point to the ++ * io_cq of the in-service queue. ++ * Redirecting the requests of the process owning bfqq to the ++ * currently in-service queue is in any case the best option, as ++ * we feed the in-service queue with new requests close to the ++ * last request served and, by doing so, hopefully increase the ++ * throughput. ++ */ ++ bfqq->new_bfqq = new_bfqq; ++ new_bfqq->ref += process_refs; ++ return new_bfqq; ++} ++ ++static bool bfq_may_be_close_cooperator(struct bfq_queue *bfqq, ++ struct bfq_queue *new_bfqq) ++{ ++ if (bfq_class_idle(bfqq) || bfq_class_idle(new_bfqq) || ++ (bfqq->ioprio_class != new_bfqq->ioprio_class)) ++ return false; ++ ++ /* ++ * If either of the queues has already been detected as seeky, ++ * then merging it with the other queue is unlikely to lead to ++ * sequential I/O. ++ */ ++ if (BFQQ_SEEKY(bfqq) || BFQQ_SEEKY(new_bfqq)) ++ return false; ++ ++ /* ++ * Interleaved I/O is known to be done by (some) applications ++ * only for reads, so it does not make sense to merge async ++ * queues. ++ */ ++ if (!bfq_bfqq_sync(bfqq) || !bfq_bfqq_sync(new_bfqq)) ++ return false; ++ ++ return true; ++} ++ ++/* ++ * If this function returns true, then bfqq cannot be merged. The idea ++ * is that true cooperation happens very early after processes start ++ * to do I/O. Usually, late cooperations are just accidental false ++ * positives. In case bfqq is weight-raised, such false positives ++ * would evidently degrade latency guarantees for bfqq. ++ */ ++bool wr_from_too_long(struct bfq_queue *bfqq) ++{ ++ return bfqq->wr_coeff > 1 && ++ time_is_before_jiffies(bfqq->last_wr_start_finish + ++ msecs_to_jiffies(100)); ++} ++ ++/* ++ * Attempt to schedule a merge of bfqq with the currently in-service ++ * queue or with a close queue among the scheduled queues. Return ++ * NULL if no merge was scheduled, a pointer to the shared bfq_queue ++ * structure otherwise. ++ * ++ * The OOM queue is not allowed to participate to cooperation: in fact, since ++ * the requests temporarily redirected to the OOM queue could be redirected ++ * again to dedicated queues at any time, the state needed to correctly ++ * handle merging with the OOM queue would be quite complex and expensive ++ * to maintain. Besides, in such a critical condition as an out of memory, ++ * the benefits of queue merging may be little relevant, or even negligible. ++ * ++ * Weight-raised queues can be merged only if their weight-raising ++ * period has just started. In fact cooperating processes are usually ++ * started together. Thus, with this filter we avoid false positives ++ * that would jeopardize low-latency guarantees. ++ * ++ * WARNING: queue merging may impair fairness among non-weight raised ++ * queues, for at least two reasons: 1) the original weight of a ++ * merged queue may change during the merged state, 2) even being the ++ * weight the same, a merged queue may be bloated with many more ++ * requests than the ones produced by its originally-associated ++ * process. ++ */ ++static struct bfq_queue * ++bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ void *io_struct, bool request) ++{ ++ struct bfq_queue *in_service_bfqq, *new_bfqq; ++ ++ if (bfqq->new_bfqq) ++ return bfqq->new_bfqq; ++ ++ if (io_struct && wr_from_too_long(bfqq) && ++ likely(bfqq != &bfqd->oom_bfqq)) ++ bfq_log_bfqq(bfqd, bfqq, ++ "would have looked for coop, but bfq%d wr", ++ bfqq->pid); ++ ++ if (!io_struct || ++ wr_from_too_long(bfqq) || ++ unlikely(bfqq == &bfqd->oom_bfqq)) ++ return NULL; ++ ++ /* If there is only one backlogged queue, don't search. */ ++ if (bfqd->busy_queues == 1) ++ return NULL; ++ ++ in_service_bfqq = bfqd->in_service_queue; ++ ++ if (in_service_bfqq && in_service_bfqq != bfqq && ++ bfqd->in_service_bic && wr_from_too_long(in_service_bfqq) ++ && likely(in_service_bfqq == &bfqd->oom_bfqq)) ++ bfq_log_bfqq(bfqd, bfqq, ++ "would have tried merge with in-service-queue, but wr"); ++ ++ if (!in_service_bfqq || in_service_bfqq == bfqq || ++ !bfqd->in_service_bic || wr_from_too_long(in_service_bfqq) || ++ unlikely(in_service_bfqq == &bfqd->oom_bfqq)) ++ goto check_scheduled; ++ ++ if (bfq_rq_close_to_sector(io_struct, request, bfqd->last_position) && ++ bfqq->entity.parent == in_service_bfqq->entity.parent && ++ bfq_may_be_close_cooperator(bfqq, in_service_bfqq)) { ++ new_bfqq = bfq_setup_merge(bfqq, in_service_bfqq); ++ if (new_bfqq) ++ return new_bfqq; ++ } ++ /* ++ * Check whether there is a cooperator among currently scheduled ++ * queues. The only thing we need is that the bio/request is not ++ * NULL, as we need it to establish whether a cooperator exists. ++ */ ++check_scheduled: ++ new_bfqq = bfq_find_close_cooperator(bfqd, bfqq, ++ bfq_io_struct_pos(io_struct, request)); ++ ++ BUG_ON(new_bfqq && bfqq->entity.parent != new_bfqq->entity.parent); ++ ++ if (new_bfqq && wr_from_too_long(new_bfqq) && ++ likely(new_bfqq != &bfqd->oom_bfqq) && ++ bfq_may_be_close_cooperator(bfqq, new_bfqq)) ++ bfq_log_bfqq(bfqd, bfqq, ++ "would have merged with bfq%d, but wr", ++ new_bfqq->pid); ++ ++ if (new_bfqq && !wr_from_too_long(new_bfqq) && ++ likely(new_bfqq != &bfqd->oom_bfqq) && ++ bfq_may_be_close_cooperator(bfqq, new_bfqq)) ++ return bfq_setup_merge(bfqq, new_bfqq); ++ ++ return NULL; ++} ++ ++static void bfq_bfqq_save_state(struct bfq_queue *bfqq) ++{ ++ struct bfq_io_cq *bic = bfqq->bic; ++ ++ /* ++ * If !bfqq->bic, the queue is already shared or its requests ++ * have already been redirected to a shared queue; both idle window ++ * and weight raising state have already been saved. Do nothing. ++ */ ++ if (!bic) ++ return; ++ ++ bic->saved_idle_window = bfq_bfqq_idle_window(bfqq); ++ bic->saved_IO_bound = bfq_bfqq_IO_bound(bfqq); ++ bic->saved_in_large_burst = bfq_bfqq_in_large_burst(bfqq); ++ bic->was_in_burst_list = !hlist_unhashed(&bfqq->burst_list_node); ++ bic->saved_wr_coeff = bfqq->wr_coeff; ++ bic->saved_wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt; ++ bic->saved_last_wr_start_finish = bfqq->last_wr_start_finish; ++ BUG_ON(time_is_after_jiffies(bfqq->last_wr_start_finish)); ++} ++ ++static void bfq_get_bic_reference(struct bfq_queue *bfqq) ++{ ++ /* ++ * If bfqq->bic has a non-NULL value, the bic to which it belongs ++ * is about to begin using a shared bfq_queue. ++ */ ++ if (bfqq->bic) ++ atomic_long_inc(&bfqq->bic->icq.ioc->refcount); ++} ++ ++static void ++bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, ++ struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) ++{ ++ bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", ++ (unsigned long) new_bfqq->pid); ++ /* Save weight raising and idle window of the merged queues */ ++ bfq_bfqq_save_state(bfqq); ++ bfq_bfqq_save_state(new_bfqq); ++ if (bfq_bfqq_IO_bound(bfqq)) ++ bfq_mark_bfqq_IO_bound(new_bfqq); ++ bfq_clear_bfqq_IO_bound(bfqq); ++ ++ /* ++ * If bfqq is weight-raised, then let new_bfqq inherit ++ * weight-raising. To reduce false positives, neglect the case ++ * where bfqq has just been created, but has not yet made it ++ * to be weight-raised (which may happen because EQM may merge ++ * bfqq even before bfq_add_request is executed for the first ++ * time for bfqq). Handling this case would however be very ++ * easy, thanks to the flag just_created. ++ */ ++ if (new_bfqq->wr_coeff == 1 && bfqq->wr_coeff > 1) { ++ new_bfqq->wr_coeff = bfqq->wr_coeff; ++ new_bfqq->wr_cur_max_time = bfqq->wr_cur_max_time; ++ new_bfqq->last_wr_start_finish = bfqq->last_wr_start_finish; ++ new_bfqq->wr_start_at_switch_to_srt = bfqq->wr_start_at_switch_to_srt; ++ if (bfq_bfqq_busy(new_bfqq)) ++ bfqd->wr_busy_queues++; ++ new_bfqq->entity.prio_changed = 1; ++ bfq_log_bfqq(bfqd, new_bfqq, ++ "wr start after merge with %d, rais_max_time %u", ++ bfqq->pid, ++ jiffies_to_msecs(bfqq->wr_cur_max_time)); ++ } ++ ++ if (bfqq->wr_coeff > 1) { /* bfqq has given its wr to new_bfqq */ ++ bfqq->wr_coeff = 1; ++ bfqq->entity.prio_changed = 1; ++ if (bfq_bfqq_busy(bfqq)) ++ bfqd->wr_busy_queues--; ++ } ++ ++ bfq_log_bfqq(bfqd, new_bfqq, "merge_bfqqs: wr_busy %d", ++ bfqd->wr_busy_queues); ++ ++ /* ++ * Grab a reference to the bic, to prevent it from being destroyed ++ * before being possibly touched by a bfq_split_bfqq(). ++ */ ++ bfq_get_bic_reference(bfqq); ++ bfq_get_bic_reference(new_bfqq); ++ /* ++ * Merge queues (that is, let bic redirect its requests to new_bfqq) ++ */ ++ bic_set_bfqq(bic, new_bfqq, 1); ++ bfq_mark_bfqq_coop(new_bfqq); ++ /* ++ * new_bfqq now belongs to at least two bics (it is a shared queue): ++ * set new_bfqq->bic to NULL. bfqq either: ++ * - does not belong to any bic any more, and hence bfqq->bic must ++ * be set to NULL, or ++ * - is a queue whose owning bics have already been redirected to a ++ * different queue, hence the queue is destined to not belong to ++ * any bic soon and bfqq->bic is already NULL (therefore the next ++ * assignment causes no harm). ++ */ ++ new_bfqq->bic = NULL; ++ bfqq->bic = NULL; ++ bfq_put_queue(bfqq); ++} ++ ++static int bfq_allow_bio_merge(struct request_queue *q, struct request *rq, ++ struct bio *bio) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ struct bfq_io_cq *bic; ++ struct bfq_queue *bfqq, *new_bfqq; ++ ++ /* ++ * Disallow merge of a sync bio into an async request. ++ */ ++ if (bfq_bio_sync(bio) && !rq_is_sync(rq)) ++ return false; ++ ++ /* ++ * Lookup the bfqq that this bio will be queued with. Allow ++ * merge only if rq is queued there. ++ * Queue lock is held here. ++ */ ++ bic = bfq_bic_lookup(bfqd, current->io_context); ++ if (!bic) ++ return false; ++ ++ bfqq = bic_to_bfqq(bic, bfq_bio_sync(bio)); ++ /* ++ * We take advantage of this function to perform an early merge ++ * of the queues of possible cooperating processes. ++ */ ++ if (bfqq) { ++ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, bio, false); ++ if (new_bfqq) { ++ bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq); ++ /* ++ * If we get here, the bio will be queued in the ++ * shared queue, i.e., new_bfqq, so use new_bfqq ++ * to decide whether bio and rq can be merged. ++ */ ++ bfqq = new_bfqq; ++ } ++ } ++ ++ return bfqq == RQ_BFQQ(rq); ++} ++ ++static int bfq_allow_rq_merge(struct request_queue *q, struct request *rq, ++ struct request *next) ++{ ++ return RQ_BFQQ(rq) == RQ_BFQQ(next); ++} ++ ++/* ++ * Set the maximum time for the in-service queue to consume its ++ * budget. This prevents seeky processes from lowering the throughput. ++ * In practice, a time-slice service scheme is used with seeky ++ * processes. ++ */ ++static void bfq_set_budget_timeout(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq) ++{ ++ unsigned int timeout_coeff; ++ ++ if (bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time) ++ timeout_coeff = 1; ++ else ++ timeout_coeff = bfqq->entity.weight / bfqq->entity.orig_weight; ++ ++ bfqd->last_budget_start = ktime_get(); ++ ++ bfqq->budget_timeout = jiffies + ++ bfqd->bfq_timeout * timeout_coeff; ++ ++ bfq_log_bfqq(bfqd, bfqq, "set budget_timeout %u", ++ jiffies_to_msecs(bfqd->bfq_timeout * timeout_coeff)); ++} ++ ++static void __bfq_set_in_service_queue(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq) ++{ ++ if (bfqq) { ++ bfqg_stats_update_avg_queue_size(bfqq_group(bfqq)); ++ bfq_mark_bfqq_must_alloc(bfqq); ++ bfq_clear_bfqq_fifo_expire(bfqq); ++ ++ bfqd->budgets_assigned = (bfqd->budgets_assigned*7 + 256) / 8; ++ ++ BUG_ON(bfqq == bfqd->in_service_queue); ++ BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); ++ ++ if (time_is_before_jiffies(bfqq->last_wr_start_finish) && ++ bfqq->wr_coeff > 1 && ++ bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && ++ time_is_before_jiffies(bfqq->budget_timeout)) { ++ /* ++ * For soft real-time queues, move the start ++ * of the weight-raising period forward by the ++ * time the queue has not received any ++ * service. Otherwise, a relatively long ++ * service delay is likely to cause the ++ * weight-raising period of the queue to end, ++ * because of the short duration of the ++ * weight-raising period of a soft real-time ++ * queue. It is worth noting that this move ++ * is not so dangerous for the other queues, ++ * because soft real-time queues are not ++ * greedy. ++ * ++ * To not add a further variable, we use the ++ * overloaded field budget_timeout to ++ * determine for how long the queue has not ++ * received service, i.e., how much time has ++ * elapsed since the queue expired. However, ++ * this is a little imprecise, because ++ * budget_timeout is set to jiffies if bfqq ++ * not only expires, but also remains with no ++ * request. ++ */ ++ bfqq->last_wr_start_finish += jiffies - ++ max_t(unsigned long, bfqq->last_wr_start_finish, ++ bfqq->budget_timeout); ++ if (time_is_after_jiffies(bfqq->last_wr_start_finish)) { ++ pr_crit( ++ "BFQ WARNING:last %lu budget %lu jiffies %lu", ++ bfqq->last_wr_start_finish, ++ bfqq->budget_timeout, ++ jiffies); ++ pr_crit("diff %lu", jiffies - ++ max_t(unsigned long, ++ bfqq->last_wr_start_finish, ++ bfqq->budget_timeout)); ++ bfqq->last_wr_start_finish = jiffies; ++ } ++ } ++ ++ bfq_set_budget_timeout(bfqd, bfqq); ++ bfq_log_bfqq(bfqd, bfqq, ++ "set_in_service_queue, cur-budget = %d", ++ bfqq->entity.budget); ++ } else ++ bfq_log(bfqd, "set_in_service_queue: NULL"); ++ ++ bfqd->in_service_queue = bfqq; ++} ++ ++/* ++ * Get and set a new queue for service. ++ */ ++static struct bfq_queue *bfq_set_in_service_queue(struct bfq_data *bfqd) ++{ ++ struct bfq_queue *bfqq = bfq_get_next_queue(bfqd); ++ ++ __bfq_set_in_service_queue(bfqd, bfqq); ++ return bfqq; ++} ++ ++static void bfq_arm_slice_timer(struct bfq_data *bfqd) ++{ ++ struct bfq_queue *bfqq = bfqd->in_service_queue; ++ struct bfq_io_cq *bic; ++ u32 sl; ++ ++ BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); ++ ++ /* Processes have exited, don't wait. */ ++ bic = bfqd->in_service_bic; ++ if (!bic || atomic_read(&bic->icq.ioc->active_ref) == 0) ++ return; ++ ++ bfq_mark_bfqq_wait_request(bfqq); ++ ++ /* ++ * We don't want to idle for seeks, but we do want to allow ++ * fair distribution of slice time for a process doing back-to-back ++ * seeks. So allow a little bit of time for him to submit a new rq. ++ * ++ * To prevent processes with (partly) seeky workloads from ++ * being too ill-treated, grant them a small fraction of the ++ * assigned budget before reducing the waiting time to ++ * BFQ_MIN_TT. This happened to help reduce latency. ++ */ ++ sl = bfqd->bfq_slice_idle; ++ /* ++ * Unless the queue is being weight-raised or the scenario is ++ * asymmetric, grant only minimum idle time if the queue ++ * is seeky. A long idling is preserved for a weight-raised ++ * queue, or, more in general, in an asymemtric scenario, ++ * because a long idling is needed for guaranteeing to a queue ++ * its reserved share of the throughput (in particular, it is ++ * needed if the queue has a higher weight than some other ++ * queue). ++ */ ++ if (BFQQ_SEEKY(bfqq) && bfqq->wr_coeff == 1 && ++ bfq_symmetric_scenario(bfqd)) ++ sl = min_t(u32, sl, BFQ_MIN_TT); ++ ++ bfqd->last_idling_start = ktime_get(); ++ hrtimer_start(&bfqd->idle_slice_timer, ns_to_ktime(sl), ++ HRTIMER_MODE_REL); ++ bfqg_stats_set_start_idle_time(bfqq_group(bfqq)); ++ bfq_log(bfqd, "arm idle: %ld/%ld ms", ++ sl / NSEC_PER_MSEC, bfqd->bfq_slice_idle / NSEC_PER_MSEC); ++} ++ ++/* ++ * In autotuning mode, max_budget is dynamically recomputed as the ++ * amount of sectors transferred in timeout at the estimated peak ++ * rate. This enables BFQ to utilize a full timeslice with a full ++ * budget, even if the in-service queue is served at peak rate. And ++ * this maximises throughput with sequential workloads. ++ */ ++static unsigned long bfq_calc_max_budget(struct bfq_data *bfqd) ++{ ++ return (u64)bfqd->peak_rate * USEC_PER_MSEC * ++ jiffies_to_msecs(bfqd->bfq_timeout)>>BFQ_RATE_SHIFT; ++} ++ ++/* ++ * Update parameters related to throughput and responsiveness, as a ++ * function of the estimated peak rate. See comments on ++ * bfq_calc_max_budget(), and on T_slow and T_fast arrays. ++ */ ++void update_thr_responsiveness_params(struct bfq_data *bfqd) ++{ ++ int dev_type = blk_queue_nonrot(bfqd->queue); ++ ++ if (bfqd->bfq_user_max_budget == 0) { ++ bfqd->bfq_max_budget = ++ bfq_calc_max_budget(bfqd); ++ BUG_ON(bfqd->bfq_max_budget < 0); ++ bfq_log(bfqd, "new max_budget = %d", ++ bfqd->bfq_max_budget); ++ } ++ ++ if (bfqd->device_speed == BFQ_BFQD_FAST && ++ bfqd->peak_rate < device_speed_thresh[dev_type]) { ++ bfqd->device_speed = BFQ_BFQD_SLOW; ++ bfqd->RT_prod = R_slow[dev_type] * ++ T_slow[dev_type]; ++ } else if (bfqd->device_speed == BFQ_BFQD_SLOW && ++ bfqd->peak_rate > device_speed_thresh[dev_type]) { ++ bfqd->device_speed = BFQ_BFQD_FAST; ++ bfqd->RT_prod = R_fast[dev_type] * ++ T_fast[dev_type]; ++ } ++ ++ bfq_log(bfqd, ++"dev_type %s dev_speed_class = %s (%llu sects/sec), thresh %llu setcs/sec", ++ dev_type == 0 ? "ROT" : "NONROT", ++ bfqd->device_speed == BFQ_BFQD_FAST ? "FAST" : "SLOW", ++ bfqd->device_speed == BFQ_BFQD_FAST ? ++ (USEC_PER_SEC*(u64)R_fast[dev_type])>>BFQ_RATE_SHIFT : ++ (USEC_PER_SEC*(u64)R_slow[dev_type])>>BFQ_RATE_SHIFT, ++ (USEC_PER_SEC*(u64)device_speed_thresh[dev_type])>> ++ BFQ_RATE_SHIFT); ++} ++ ++void bfq_reset_rate_computation(struct bfq_data *bfqd, struct request *rq) ++{ ++ if (rq != NULL) { /* new rq dispatch now, reset accordingly */ ++ bfqd->last_dispatch = bfqd->first_dispatch = ktime_get_ns() ; ++ bfqd->peak_rate_samples = 1; ++ bfqd->sequential_samples = 0; ++ bfqd->tot_sectors_dispatched = bfqd->last_rq_max_size = ++ blk_rq_sectors(rq); ++ } else /* no new rq dispatched, just reset the number of samples */ ++ bfqd->peak_rate_samples = 0; /* full re-init on next disp. */ ++ ++ bfq_log(bfqd, ++ "reset_rate_computation at end, sample %u/%u tot_sects %llu", ++ bfqd->peak_rate_samples, bfqd->sequential_samples, ++ bfqd->tot_sectors_dispatched); ++} ++ ++void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq) ++{ ++ u32 rate, weight, divisor; ++ ++ /* ++ * For the convergence property to hold (see comments on ++ * bfq_update_peak_rate()) and for the assessment to be ++ * reliable, a minimum number of samples must be present, and ++ * a minimum amount of time must have elapsed. If not so, do ++ * not compute new rate. Just reset parameters, to get ready ++ * for a new evaluation attempt. ++ */ ++ if (bfqd->peak_rate_samples < BFQ_RATE_MIN_SAMPLES || ++ bfqd->delta_from_first < BFQ_RATE_MIN_INTERVAL) { ++ bfq_log(bfqd, ++ "update_rate_reset: only resetting, delta_first %lluus samples %d", ++ bfqd->delta_from_first>>10, bfqd->peak_rate_samples); ++ goto reset_computation; ++ } ++ ++ /* ++ * If a new request completion has occurred after last ++ * dispatch, then, to approximate the rate at which requests ++ * have been served by the device, it is more precise to ++ * extend the observation interval to the last completion. ++ */ ++ bfqd->delta_from_first = ++ max_t(u64, bfqd->delta_from_first, ++ bfqd->last_completion - bfqd->first_dispatch); ++ ++ BUG_ON(bfqd->delta_from_first == 0); ++ /* ++ * Rate computed in sects/usec, and not sects/nsec, for ++ * precision issues. ++ */ ++ rate = div64_ul(bfqd->tot_sectors_dispatched<delta_from_first, NSEC_PER_USEC)); ++ ++ bfq_log(bfqd, ++"update_rate_reset: tot_sects %llu delta_first %lluus rate %llu sects/s (%d)", ++ bfqd->tot_sectors_dispatched, bfqd->delta_from_first>>10, ++ ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), ++ rate > 20< 20M sectors/sec) ++ */ ++ if ((bfqd->peak_rate_samples > (3 * bfqd->sequential_samples)>>2 && ++ rate <= bfqd->peak_rate) || ++ rate > 20<peak_rate_samples, bfqd->sequential_samples, ++ ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), ++ ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); ++ goto reset_computation; ++ } else { ++ bfq_log(bfqd, ++ "update_rate_reset: do update, samples %u/%u rate/peak %llu/%llu", ++ bfqd->peak_rate_samples, bfqd->sequential_samples, ++ ((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT), ++ ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); ++ } ++ ++ /* ++ * We have to update the peak rate, at last! To this purpose, ++ * we use a low-pass filter. We compute the smoothing constant ++ * of the filter as a function of the 'weight' of the new ++ * measured rate. ++ * ++ * As can be seen in next formulas, we define this weight as a ++ * quantity proportional to how sequential the workload is, ++ * and to how long the observation time interval is. ++ * ++ * The weight runs from 0 to 8. The maximum value of the ++ * weight, 8, yields the minimum value for the smoothing ++ * constant. At this minimum value for the smoothing constant, ++ * the measured rate contributes for half of the next value of ++ * the estimated peak rate. ++ * ++ * So, the first step is to compute the weight as a function ++ * of how sequential the workload is. Note that the weight ++ * cannot reach 9, because bfqd->sequential_samples cannot ++ * become equal to bfqd->peak_rate_samples, which, in its ++ * turn, holds true because bfqd->sequential_samples is not ++ * incremented for the first sample. ++ */ ++ weight = (9 * bfqd->sequential_samples) / bfqd->peak_rate_samples; ++ ++ /* ++ * Second step: further refine the weight as a function of the ++ * duration of the observation interval. ++ */ ++ weight = min_t(u32, 8, ++ div_u64(weight * bfqd->delta_from_first, ++ BFQ_RATE_REF_INTERVAL)); ++ ++ /* ++ * Divisor ranging from 10, for minimum weight, to 2, for ++ * maximum weight. ++ */ ++ divisor = 10 - weight; ++ BUG_ON(divisor == 0); ++ ++ /* ++ * Finally, update peak rate: ++ * ++ * peak_rate = peak_rate * (divisor-1) / divisor + rate / divisor ++ */ ++ bfqd->peak_rate *= divisor-1; ++ bfqd->peak_rate /= divisor; ++ rate /= divisor; /* smoothing constant alpha = 1/divisor */ ++ ++ bfq_log(bfqd, ++ "update_rate_reset: divisor %d tmp_peak_rate %llu tmp_rate %u", ++ divisor, ++ ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT), ++ (u32)((USEC_PER_SEC*(u64)rate)>>BFQ_RATE_SHIFT)); ++ ++ BUG_ON(bfqd->peak_rate == 0); ++ BUG_ON(bfqd->peak_rate > 20<peak_rate += rate; ++ update_thr_responsiveness_params(bfqd); ++ BUG_ON(bfqd->peak_rate > 20<peak_rate_samples == 0) { /* first dispatch */ ++ bfq_log(bfqd, ++ "update_peak_rate: goto reset, samples %d", ++ bfqd->peak_rate_samples) ; ++ bfq_reset_rate_computation(bfqd, rq); ++ goto update_last_values; /* will add one sample */ ++ } ++ ++ /* ++ * Device idle for very long: the observation interval lasting ++ * up to this dispatch cannot be a valid observation interval ++ * for computing a new peak rate (similarly to the late- ++ * completion event in bfq_completed_request()). Go to ++ * update_rate_and_reset to have the following three steps ++ * taken: ++ * - close the observation interval at the last (previous) ++ * request dispatch or completion ++ * - compute rate, if possible, for that observation interval ++ * - start a new observation interval with this dispatch ++ */ ++ if (now_ns - bfqd->last_dispatch > 100*NSEC_PER_MSEC && ++ bfqd->rq_in_driver == 0) { ++ bfq_log(bfqd, ++"update_peak_rate: jumping to updating&resetting delta_last %lluus samples %d", ++ (now_ns - bfqd->last_dispatch)>>10, ++ bfqd->peak_rate_samples) ; ++ goto update_rate_and_reset; ++ } ++ ++ /* Update sampling information */ ++ bfqd->peak_rate_samples++; ++ ++ if ((bfqd->rq_in_driver > 0 || ++ now_ns - bfqd->last_completion < BFQ_MIN_TT) ++ && get_sdist(bfqd->last_position, rq) < BFQQ_SEEK_THR) ++ bfqd->sequential_samples++; ++ ++ bfqd->tot_sectors_dispatched += blk_rq_sectors(rq); ++ ++ /* Reset max observed rq size every 32 dispatches */ ++ if (likely(bfqd->peak_rate_samples % 32)) ++ bfqd->last_rq_max_size = ++ max_t(u32, blk_rq_sectors(rq), bfqd->last_rq_max_size); ++ else ++ bfqd->last_rq_max_size = blk_rq_sectors(rq); ++ ++ bfqd->delta_from_first = now_ns - bfqd->first_dispatch; ++ ++ bfq_log(bfqd, ++ "update_peak_rate: added samples %u/%u tot_sects %llu delta_first %lluus", ++ bfqd->peak_rate_samples, bfqd->sequential_samples, ++ bfqd->tot_sectors_dispatched, ++ bfqd->delta_from_first>>10); ++ ++ /* Target observation interval not yet reached, go on sampling */ ++ if (bfqd->delta_from_first < BFQ_RATE_REF_INTERVAL) ++ goto update_last_values; ++ ++update_rate_and_reset: ++ bfq_update_rate_reset(bfqd, rq); ++update_last_values: ++ bfqd->last_position = blk_rq_pos(rq) + blk_rq_sectors(rq); ++ bfqd->last_dispatch = now_ns; ++ ++ bfq_log(bfqd, ++ "update_peak_rate: delta_first %lluus last_pos %llu peak_rate %llu", ++ (now_ns - bfqd->first_dispatch)>>10, ++ (unsigned long long) bfqd->last_position, ++ ((USEC_PER_SEC*(u64)bfqd->peak_rate)>>BFQ_RATE_SHIFT)); ++ bfq_log(bfqd, ++ "update_peak_rate: samples at end %d", bfqd->peak_rate_samples); ++} ++ ++/* ++ * Move request from internal lists to the dispatch list of the request queue ++ */ ++static void bfq_dispatch_insert(struct request_queue *q, struct request *rq) ++{ ++ struct bfq_queue *bfqq = RQ_BFQQ(rq); ++ ++ /* ++ * For consistency, the next instruction should have been executed ++ * after removing the request from the queue and dispatching it. ++ * We execute instead this instruction before bfq_remove_request() ++ * (and hence introduce a temporary inconsistency), for efficiency. ++ * In fact, in a forced_dispatch, this prevents two counters related ++ * to bfqq->dispatched to risk to be uselessly decremented if bfqq ++ * is not in service, and then to be incremented again after ++ * incrementing bfqq->dispatched. ++ */ ++ bfqq->dispatched++; ++ bfq_update_peak_rate(q->elevator->elevator_data, rq); ++ ++ bfq_remove_request(rq); ++ elv_dispatch_sort(q, rq); ++} ++ ++/* ++ * Return expired entry, or NULL to just start from scratch in rbtree. ++ */ ++static struct request *bfq_check_fifo(struct bfq_queue *bfqq) ++{ ++ struct request *rq = NULL; ++ ++ if (bfq_bfqq_fifo_expire(bfqq)) ++ return NULL; ++ ++ bfq_mark_bfqq_fifo_expire(bfqq); ++ ++ if (list_empty(&bfqq->fifo)) ++ return NULL; ++ ++ rq = rq_entry_fifo(bfqq->fifo.next); ++ ++ if (ktime_get_ns() < rq->fifo_time) ++ return NULL; ++ ++ return rq; ++} ++ ++static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ BUG_ON(bfqq != bfqd->in_service_queue); ++ ++ __bfq_bfqd_reset_in_service(bfqd); ++ ++ /* ++ * If this bfqq is shared between multiple processes, check ++ * to make sure that those processes are still issuing I/Os ++ * within the mean seek distance. If not, it may be time to ++ * break the queues apart again. ++ */ ++ if (bfq_bfqq_coop(bfqq) && BFQQ_SEEKY(bfqq)) ++ bfq_mark_bfqq_split_coop(bfqq); ++ ++ if (RB_EMPTY_ROOT(&bfqq->sort_list)) { ++ if (bfqq->dispatched == 0) ++ /* ++ * Overloading budget_timeout field to store ++ * the time at which the queue remains with no ++ * backlog and no outstanding request; used by ++ * the weight-raising mechanism. ++ */ ++ bfqq->budget_timeout = jiffies; ++ ++ bfq_del_bfqq_busy(bfqd, bfqq, 1); ++ } else { ++ bfq_activate_bfqq(bfqd, bfqq); ++ /* ++ * Resort priority tree of potential close cooperators. ++ */ ++ bfq_pos_tree_add_move(bfqd, bfqq); ++ } ++} ++ ++/** ++ * __bfq_bfqq_recalc_budget - try to adapt the budget to the @bfqq behavior. ++ * @bfqd: device data. ++ * @bfqq: queue to update. ++ * @reason: reason for expiration. ++ * ++ * Handle the feedback on @bfqq budget at queue expiration. ++ * See the body for detailed comments. ++ */ ++static void __bfq_bfqq_recalc_budget(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ enum bfqq_expiration reason) ++{ ++ struct request *next_rq; ++ int budget, min_budget; ++ ++ BUG_ON(bfqq != bfqd->in_service_queue); ++ ++ min_budget = bfq_min_budget(bfqd); ++ ++ if (bfqq->wr_coeff == 1) ++ budget = bfqq->max_budget; ++ else /* ++ * Use a constant, low budget for weight-raised queues, ++ * to help achieve a low latency. Keep it slightly higher ++ * than the minimum possible budget, to cause a little ++ * bit fewer expirations. ++ */ ++ budget = 2 * min_budget; ++ ++ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last budg %d, budg left %d", ++ bfqq->entity.budget, bfq_bfqq_budget_left(bfqq)); ++ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: last max_budg %d, min budg %d", ++ budget, bfq_min_budget(bfqd)); ++ bfq_log_bfqq(bfqd, bfqq, "recalc_budg: sync %d, seeky %d", ++ bfq_bfqq_sync(bfqq), BFQQ_SEEKY(bfqd->in_service_queue)); ++ ++ if (bfq_bfqq_sync(bfqq) && bfqq->wr_coeff == 1) { ++ switch (reason) { ++ /* ++ * Caveat: in all the following cases we trade latency ++ * for throughput. ++ */ ++ case BFQ_BFQQ_TOO_IDLE: ++ /* ++ * This is the only case where we may reduce ++ * the budget: if there is no request of the ++ * process still waiting for completion, then ++ * we assume (tentatively) that the timer has ++ * expired because the batch of requests of ++ * the process could have been served with a ++ * smaller budget. Hence, betting that ++ * process will behave in the same way when it ++ * becomes backlogged again, we reduce its ++ * next budget. As long as we guess right, ++ * this budget cut reduces the latency ++ * experienced by the process. ++ * ++ * However, if there are still outstanding ++ * requests, then the process may have not yet ++ * issued its next request just because it is ++ * still waiting for the completion of some of ++ * the still outstanding ones. So in this ++ * subcase we do not reduce its budget, on the ++ * contrary we increase it to possibly boost ++ * the throughput, as discussed in the ++ * comments to the BUDGET_TIMEOUT case. ++ */ ++ if (bfqq->dispatched > 0) /* still outstanding reqs */ ++ budget = min(budget * 2, bfqd->bfq_max_budget); ++ else { ++ if (budget > 5 * min_budget) ++ budget -= 4 * min_budget; ++ else ++ budget = min_budget; ++ } ++ break; ++ case BFQ_BFQQ_BUDGET_TIMEOUT: ++ /* ++ * We double the budget here because it gives ++ * the chance to boost the throughput if this ++ * is not a seeky process (and has bumped into ++ * this timeout because of, e.g., ZBR). ++ */ ++ budget = min(budget * 2, bfqd->bfq_max_budget); ++ break; ++ case BFQ_BFQQ_BUDGET_EXHAUSTED: ++ /* ++ * The process still has backlog, and did not ++ * let either the budget timeout or the disk ++ * idling timeout expire. Hence it is not ++ * seeky, has a short thinktime and may be ++ * happy with a higher budget too. So ++ * definitely increase the budget of this good ++ * candidate to boost the disk throughput. ++ */ ++ budget = min(budget * 4, bfqd->bfq_max_budget); ++ break; ++ case BFQ_BFQQ_NO_MORE_REQUESTS: ++ /* ++ * For queues that expire for this reason, it ++ * is particularly important to keep the ++ * budget close to the actual service they ++ * need. Doing so reduces the timestamp ++ * misalignment problem described in the ++ * comments in the body of ++ * __bfq_activate_entity. In fact, suppose ++ * that a queue systematically expires for ++ * BFQ_BFQQ_NO_MORE_REQUESTS and presents a ++ * new request in time to enjoy timestamp ++ * back-shifting. The larger the budget of the ++ * queue is with respect to the service the ++ * queue actually requests in each service ++ * slot, the more times the queue can be ++ * reactivated with the same virtual finish ++ * time. It follows that, even if this finish ++ * time is pushed to the system virtual time ++ * to reduce the consequent timestamp ++ * misalignment, the queue unjustly enjoys for ++ * many re-activations a lower finish time ++ * than all newly activated queues. ++ * ++ * The service needed by bfqq is measured ++ * quite precisely by bfqq->entity.service. ++ * Since bfqq does not enjoy device idling, ++ * bfqq->entity.service is equal to the number ++ * of sectors that the process associated with ++ * bfqq requested to read/write before waiting ++ * for request completions, or blocking for ++ * other reasons. ++ */ ++ budget = max_t(int, bfqq->entity.service, min_budget); ++ break; ++ default: ++ return; ++ } ++ } else if (!bfq_bfqq_sync(bfqq)) ++ /* ++ * Async queues get always the maximum possible ++ * budget, as for them we do not care about latency ++ * (in addition, their ability to dispatch is limited ++ * by the charging factor). ++ */ ++ budget = bfqd->bfq_max_budget; ++ ++ bfqq->max_budget = budget; ++ ++ if (bfqd->budgets_assigned >= bfq_stats_min_budgets && ++ !bfqd->bfq_user_max_budget) ++ bfqq->max_budget = min(bfqq->max_budget, bfqd->bfq_max_budget); ++ ++ /* ++ * If there is still backlog, then assign a new budget, making ++ * sure that it is large enough for the next request. Since ++ * the finish time of bfqq must be kept in sync with the ++ * budget, be sure to call __bfq_bfqq_expire() *after* this ++ * update. ++ * ++ * If there is no backlog, then no need to update the budget; ++ * it will be updated on the arrival of a new request. ++ */ ++ next_rq = bfqq->next_rq; ++ if (next_rq) { ++ BUG_ON(reason == BFQ_BFQQ_TOO_IDLE || ++ reason == BFQ_BFQQ_NO_MORE_REQUESTS); ++ bfqq->entity.budget = max_t(unsigned long, bfqq->max_budget, ++ bfq_serv_to_charge(next_rq, bfqq)); ++ BUG_ON(!bfq_bfqq_busy(bfqq)); ++ BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); ++ } ++ ++ bfq_log_bfqq(bfqd, bfqq, "head sect: %u, new budget %d", ++ next_rq ? blk_rq_sectors(next_rq) : 0, ++ bfqq->entity.budget); ++} ++ ++/* ++ * Return true if the process associated with bfqq is "slow". The slow ++ * flag is used, in addition to the budget timeout, to reduce the ++ * amount of service provided to seeky processes, and thus reduce ++ * their chances to lower the throughput. More details in the comments ++ * on the function bfq_bfqq_expire(). ++ * ++ * An important observation is in order: as discussed in the comments ++ * on the function bfq_update_peak_rate(), with devices with internal ++ * queues, it is hard if ever possible to know when and for how long ++ * an I/O request is processed by the device (apart from the trivial ++ * I/O pattern where a new request is dispatched only after the ++ * previous one has been completed). This makes it hard to evaluate ++ * the real rate at which the I/O requests of each bfq_queue are ++ * served. In fact, for an I/O scheduler like BFQ, serving a ++ * bfq_queue means just dispatching its requests during its service ++ * slot (i.e., until the budget of the queue is exhausted, or the ++ * queue remains idle, or, finally, a timeout fires). But, during the ++ * service slot of a bfq_queue, around 100 ms at most, the device may ++ * be even still processing requests of bfq_queues served in previous ++ * service slots. On the opposite end, the requests of the in-service ++ * bfq_queue may be completed after the service slot of the queue ++ * finishes. ++ * ++ * Anyway, unless more sophisticated solutions are used ++ * (where possible), the sum of the sizes of the requests dispatched ++ * during the service slot of a bfq_queue is probably the only ++ * approximation available for the service received by the bfq_queue ++ * during its service slot. And this sum is the quantity used in this ++ * function to evaluate the I/O speed of a process. ++ */ ++static bool bfq_bfqq_is_slow(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ bool compensate, enum bfqq_expiration reason, ++ unsigned long *delta_ms) ++{ ++ ktime_t delta_ktime; ++ u32 delta_usecs; ++ bool slow = BFQQ_SEEKY(bfqq); /* if delta too short, use seekyness */ ++ ++ if (!bfq_bfqq_sync(bfqq)) ++ return false; ++ ++ if (compensate) ++ delta_ktime = bfqd->last_idling_start; ++ else ++ delta_ktime = ktime_get(); ++ delta_ktime = ktime_sub(delta_ktime, bfqd->last_budget_start); ++ delta_usecs = ktime_to_us(delta_ktime); ++ ++ /* don't trust short/unrealistic values. */ ++ if (delta_usecs < 1000 || delta_usecs >= LONG_MAX) { ++ if (blk_queue_nonrot(bfqd->queue)) ++ /* ++ * give same worst-case guarantees as idling ++ * for seeky ++ */ ++ *delta_ms = BFQ_MIN_TT / NSEC_PER_MSEC; ++ else /* charge at least one seek */ ++ *delta_ms = bfq_slice_idle / NSEC_PER_MSEC; ++ ++ bfq_log(bfqd, "bfq_bfqq_is_slow: unrealistic %u", delta_usecs); ++ ++ return slow; ++ } ++ ++ *delta_ms = delta_usecs / USEC_PER_MSEC; ++ ++ /* ++ * Use only long (> 20ms) intervals to filter out excessive ++ * spikes in service rate estimation. ++ */ ++ if (delta_usecs > 20000) { ++ /* ++ * Caveat for rotational devices: processes doing I/O ++ * in the slower disk zones tend to be slow(er) even ++ * if not seeky. In this respect, the estimated peak ++ * rate is likely to be an average over the disk ++ * surface. Accordingly, to not be too harsh with ++ * unlucky processes, a process is deemed slow only if ++ * its rate has been lower than half of the estimated ++ * peak rate. ++ */ ++ slow = bfqq->entity.service < bfqd->bfq_max_budget / 2; ++ bfq_log(bfqd, "bfq_bfqq_is_slow: relative rate %d/%d", ++ bfqq->entity.service, bfqd->bfq_max_budget); ++ } ++ ++ bfq_log_bfqq(bfqd, bfqq, "bfq_bfqq_is_slow: slow %d", slow); ++ ++ return slow; ++} ++ ++/* ++ * To be deemed as soft real-time, an application must meet two ++ * requirements. First, the application must not require an average ++ * bandwidth higher than the approximate bandwidth required to playback or ++ * record a compressed high-definition video. ++ * The next function is invoked on the completion of the last request of a ++ * batch, to compute the next-start time instant, soft_rt_next_start, such ++ * that, if the next request of the application does not arrive before ++ * soft_rt_next_start, then the above requirement on the bandwidth is met. ++ * ++ * The second requirement is that the request pattern of the application is ++ * isochronous, i.e., that, after issuing a request or a batch of requests, ++ * the application stops issuing new requests until all its pending requests ++ * have been completed. After that, the application may issue a new batch, ++ * and so on. ++ * For this reason the next function is invoked to compute ++ * soft_rt_next_start only for applications that meet this requirement, ++ * whereas soft_rt_next_start is set to infinity for applications that do ++ * not. ++ * ++ * Unfortunately, even a greedy application may happen to behave in an ++ * isochronous way if the CPU load is high. In fact, the application may ++ * stop issuing requests while the CPUs are busy serving other processes, ++ * then restart, then stop again for a while, and so on. In addition, if ++ * the disk achieves a low enough throughput with the request pattern ++ * issued by the application (e.g., because the request pattern is random ++ * and/or the device is slow), then the application may meet the above ++ * bandwidth requirement too. To prevent such a greedy application to be ++ * deemed as soft real-time, a further rule is used in the computation of ++ * soft_rt_next_start: soft_rt_next_start must be higher than the current ++ * time plus the maximum time for which the arrival of a request is waited ++ * for when a sync queue becomes idle, namely bfqd->bfq_slice_idle. ++ * This filters out greedy applications, as the latter issue instead their ++ * next request as soon as possible after the last one has been completed ++ * (in contrast, when a batch of requests is completed, a soft real-time ++ * application spends some time processing data). ++ * ++ * Unfortunately, the last filter may easily generate false positives if ++ * only bfqd->bfq_slice_idle is used as a reference time interval and one ++ * or both the following cases occur: ++ * 1) HZ is so low that the duration of a jiffy is comparable to or higher ++ * than bfqd->bfq_slice_idle. This happens, e.g., on slow devices with ++ * HZ=100. ++ * 2) jiffies, instead of increasing at a constant rate, may stop increasing ++ * for a while, then suddenly 'jump' by several units to recover the lost ++ * increments. This seems to happen, e.g., inside virtual machines. ++ * To address this issue, we do not use as a reference time interval just ++ * bfqd->bfq_slice_idle, but bfqd->bfq_slice_idle plus a few jiffies. In ++ * particular we add the minimum number of jiffies for which the filter ++ * seems to be quite precise also in embedded systems and KVM/QEMU virtual ++ * machines. ++ */ ++static unsigned long bfq_bfqq_softrt_next_start(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq) ++{ ++ bfq_log_bfqq(bfqd, bfqq, ++"softrt_next_start: service_blkg %lu soft_rate %u sects/sec interval %u", ++ bfqq->service_from_backlogged, ++ bfqd->bfq_wr_max_softrt_rate, ++ jiffies_to_msecs(HZ * bfqq->service_from_backlogged / ++ bfqd->bfq_wr_max_softrt_rate)); ++ ++ return max(bfqq->last_idle_bklogged + ++ HZ * bfqq->service_from_backlogged / ++ bfqd->bfq_wr_max_softrt_rate, ++ jiffies + nsecs_to_jiffies(bfqq->bfqd->bfq_slice_idle) + 4); ++} ++ ++/* ++ * Return the farthest future time instant according to jiffies ++ * macros. ++ */ ++static unsigned long bfq_greatest_from_now(void) ++{ ++ return jiffies + MAX_JIFFY_OFFSET; ++} ++ ++/* ++ * Return the farthest past time instant according to jiffies ++ * macros. ++ */ ++static unsigned long bfq_smallest_from_now(void) ++{ ++ return jiffies - MAX_JIFFY_OFFSET; ++} ++ ++/** ++ * bfq_bfqq_expire - expire a queue. ++ * @bfqd: device owning the queue. ++ * @bfqq: the queue to expire. ++ * @compensate: if true, compensate for the time spent idling. ++ * @reason: the reason causing the expiration. ++ * ++ * If the process associated with bfqq does slow I/O (e.g., because it ++ * issues random requests), we charge bfqq with the time it has been ++ * in service instead of the service it has received (see ++ * bfq_bfqq_charge_time for details on how this goal is achieved). As ++ * a consequence, bfqq will typically get higher timestamps upon ++ * reactivation, and hence it will be rescheduled as if it had ++ * received more service than what it has actually received. In the ++ * end, bfqq receives less service in proportion to how slowly its ++ * associated process consumes its budgets (and hence how seriously it ++ * tends to lower the throughput). In addition, this time-charging ++ * strategy guarantees time fairness among slow processes. In ++ * contrast, if the process associated with bfqq is not slow, we ++ * charge bfqq exactly with the service it has received. ++ * ++ * Charging time to the first type of queues and the exact service to ++ * the other has the effect of using the WF2Q+ policy to schedule the ++ * former on a timeslice basis, without violating service domain ++ * guarantees among the latter. ++ */ ++static void bfq_bfqq_expire(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ bool compensate, ++ enum bfqq_expiration reason) ++{ ++ bool slow; ++ unsigned long delta = 0; ++ struct bfq_entity *entity = &bfqq->entity; ++ ++ BUG_ON(bfqq != bfqd->in_service_queue); ++ ++ /* ++ * Check whether the process is slow (see bfq_bfqq_is_slow). ++ */ ++ slow = bfq_bfqq_is_slow(bfqd, bfqq, compensate, reason, &delta); ++ ++ /* ++ * Increase service_from_backlogged before next statement, ++ * because the possible next invocation of ++ * bfq_bfqq_charge_time would likely inflate ++ * entity->service. In contrast, service_from_backlogged must ++ * contain real service, to enable the soft real-time ++ * heuristic to correctly compute the bandwidth consumed by ++ * bfqq. ++ */ ++ bfqq->service_from_backlogged += entity->service; ++ ++ /* ++ * As above explained, charge slow (typically seeky) and ++ * timed-out queues with the time and not the service ++ * received, to favor sequential workloads. ++ * ++ * Processes doing I/O in the slower disk zones will tend to ++ * be slow(er) even if not seeky. Therefore, since the ++ * estimated peak rate is actually an average over the disk ++ * surface, these processes may timeout just for bad luck. To ++ * avoid punishing them, do not charge time to processes that ++ * succeeded in consuming at least 2/3 of their budget. This ++ * allows BFQ to preserve enough elasticity to still perform ++ * bandwidth, and not time, distribution with little unlucky ++ * or quasi-sequential processes. ++ */ ++ if (bfqq->wr_coeff == 1 && ++ (slow || ++ (reason == BFQ_BFQQ_BUDGET_TIMEOUT && ++ bfq_bfqq_budget_left(bfqq) >= entity->budget / 3))) ++ bfq_bfqq_charge_time(bfqd, bfqq, delta); ++ ++ BUG_ON(bfqq->entity.budget < bfqq->entity.service); ++ ++ if (reason == BFQ_BFQQ_TOO_IDLE && ++ entity->service <= 2 * entity->budget / 10) ++ bfq_clear_bfqq_IO_bound(bfqq); ++ ++ if (bfqd->low_latency && bfqq->wr_coeff == 1) ++ bfqq->last_wr_start_finish = jiffies; ++ ++ if (bfqd->low_latency && bfqd->bfq_wr_max_softrt_rate > 0 && ++ RB_EMPTY_ROOT(&bfqq->sort_list)) { ++ /* ++ * If we get here, and there are no outstanding ++ * requests, then the request pattern is isochronous ++ * (see the comments on the function ++ * bfq_bfqq_softrt_next_start()). Thus we can compute ++ * soft_rt_next_start. If, instead, the queue still ++ * has outstanding requests, then we have to wait for ++ * the completion of all the outstanding requests to ++ * discover whether the request pattern is actually ++ * isochronous. ++ */ ++ BUG_ON(bfqd->busy_queues < 1); ++ if (bfqq->dispatched == 0) { ++ bfqq->soft_rt_next_start = ++ bfq_bfqq_softrt_next_start(bfqd, bfqq); ++ bfq_log_bfqq(bfqd, bfqq, "new soft_rt_next %lu", ++ bfqq->soft_rt_next_start); ++ } else { ++ /* ++ * The application is still waiting for the ++ * completion of one or more requests: ++ * prevent it from possibly being incorrectly ++ * deemed as soft real-time by setting its ++ * soft_rt_next_start to infinity. In fact, ++ * without this assignment, the application ++ * would be incorrectly deemed as soft ++ * real-time if: ++ * 1) it issued a new request before the ++ * completion of all its in-flight ++ * requests, and ++ * 2) at that time, its soft_rt_next_start ++ * happened to be in the past. ++ */ ++ bfqq->soft_rt_next_start = ++ bfq_greatest_from_now(); ++ /* ++ * Schedule an update of soft_rt_next_start to when ++ * the task may be discovered to be isochronous. ++ */ ++ bfq_mark_bfqq_softrt_update(bfqq); ++ } ++ } ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "expire (%d, slow %d, num_disp %d, idle_win %d, weight %d)", ++ reason, slow, bfqq->dispatched, ++ bfq_bfqq_idle_window(bfqq), entity->weight); ++ ++ /* ++ * Increase, decrease or leave budget unchanged according to ++ * reason. ++ */ ++ BUG_ON(bfqq->entity.budget < bfqq->entity.service); ++ __bfq_bfqq_recalc_budget(bfqd, bfqq, reason); ++ BUG_ON(bfqq->next_rq == NULL && ++ bfqq->entity.budget < bfqq->entity.service); ++ __bfq_bfqq_expire(bfqd, bfqq); ++ ++ BUG_ON(!bfq_bfqq_busy(bfqq) && reason == BFQ_BFQQ_BUDGET_EXHAUSTED && ++ !bfq_class_idle(bfqq)); ++ ++ if (!bfq_bfqq_busy(bfqq) && ++ reason != BFQ_BFQQ_BUDGET_TIMEOUT && ++ reason != BFQ_BFQQ_BUDGET_EXHAUSTED) ++ bfq_mark_bfqq_non_blocking_wait_rq(bfqq); ++} ++ ++/* ++ * Budget timeout is not implemented through a dedicated timer, but ++ * just checked on request arrivals and completions, as well as on ++ * idle timer expirations. ++ */ ++static bool bfq_bfqq_budget_timeout(struct bfq_queue *bfqq) ++{ ++ return time_is_before_eq_jiffies(bfqq->budget_timeout); ++} ++ ++/* ++ * If we expire a queue that is actively waiting (i.e., with the ++ * device idled) for the arrival of a new request, then we may incur ++ * the timestamp misalignment problem described in the body of the ++ * function __bfq_activate_entity. Hence we return true only if this ++ * condition does not hold, or if the queue is slow enough to deserve ++ * only to be kicked off for preserving a high throughput. ++ */ ++static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq) ++{ ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "may_budget_timeout: wait_request %d left %d timeout %d", ++ bfq_bfqq_wait_request(bfqq), ++ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3, ++ bfq_bfqq_budget_timeout(bfqq)); ++ ++ return (!bfq_bfqq_wait_request(bfqq) || ++ bfq_bfqq_budget_left(bfqq) >= bfqq->entity.budget / 3) ++ && ++ bfq_bfqq_budget_timeout(bfqq); ++} ++ ++/* ++ * For a queue that becomes empty, device idling is allowed only if ++ * this function returns true for that queue. As a consequence, since ++ * device idling plays a critical role for both throughput boosting ++ * and service guarantees, the return value of this function plays a ++ * critical role as well. ++ * ++ * In a nutshell, this function returns true only if idling is ++ * beneficial for throughput or, even if detrimental for throughput, ++ * idling is however necessary to preserve service guarantees (low ++ * latency, desired throughput distribution, ...). In particular, on ++ * NCQ-capable devices, this function tries to return false, so as to ++ * help keep the drives' internal queues full, whenever this helps the ++ * device boost the throughput without causing any service-guarantee ++ * issue. ++ * ++ * In more detail, the return value of this function is obtained by, ++ * first, computing a number of boolean variables that take into ++ * account throughput and service-guarantee issues, and, then, ++ * combining these variables in a logical expression. Most of the ++ * issues taken into account are not trivial. We discuss these issues ++ * while introducing the variables. ++ */ ++static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq) ++{ ++ struct bfq_data *bfqd = bfqq->bfqd; ++ bool idling_boosts_thr, idling_boosts_thr_without_issues, ++ idling_needed_for_service_guarantees, ++ asymmetric_scenario; ++ ++ if (bfqd->strict_guarantees) ++ return true; ++ ++ /* ++ * The next variable takes into account the cases where idling ++ * boosts the throughput. ++ * ++ * The value of the variable is computed considering, first, that ++ * idling is virtually always beneficial for the throughput if: ++ * (a) the device is not NCQ-capable, or ++ * (b) regardless of the presence of NCQ, the device is rotational ++ * and the request pattern for bfqq is I/O-bound and sequential. ++ * ++ * Secondly, and in contrast to the above item (b), idling an ++ * NCQ-capable flash-based device would not boost the ++ * throughput even with sequential I/O; rather it would lower ++ * the throughput in proportion to how fast the device ++ * is. Accordingly, the next variable is true if any of the ++ * above conditions (a) and (b) is true, and, in particular, ++ * happens to be false if bfqd is an NCQ-capable flash-based ++ * device. ++ */ ++ idling_boosts_thr = !bfqd->hw_tag || ++ (!blk_queue_nonrot(bfqd->queue) && bfq_bfqq_IO_bound(bfqq) && ++ bfq_bfqq_idle_window(bfqq)); ++ ++ /* ++ * The value of the next variable, ++ * idling_boosts_thr_without_issues, is equal to that of ++ * idling_boosts_thr, unless a special case holds. In this ++ * special case, described below, idling may cause problems to ++ * weight-raised queues. ++ * ++ * When the request pool is saturated (e.g., in the presence ++ * of write hogs), if the processes associated with ++ * non-weight-raised queues ask for requests at a lower rate, ++ * then processes associated with weight-raised queues have a ++ * higher probability to get a request from the pool ++ * immediately (or at least soon) when they need one. Thus ++ * they have a higher probability to actually get a fraction ++ * of the device throughput proportional to their high ++ * weight. This is especially true with NCQ-capable drives, ++ * which enqueue several requests in advance, and further ++ * reorder internally-queued requests. ++ * ++ * For this reason, we force to false the value of ++ * idling_boosts_thr_without_issues if there are weight-raised ++ * busy queues. In this case, and if bfqq is not weight-raised, ++ * this guarantees that the device is not idled for bfqq (if, ++ * instead, bfqq is weight-raised, then idling will be ++ * guaranteed by another variable, see below). Combined with ++ * the timestamping rules of BFQ (see [1] for details), this ++ * behavior causes bfqq, and hence any sync non-weight-raised ++ * queue, to get a lower number of requests served, and thus ++ * to ask for a lower number of requests from the request ++ * pool, before the busy weight-raised queues get served ++ * again. This often mitigates starvation problems in the ++ * presence of heavy write workloads and NCQ, thereby ++ * guaranteeing a higher application and system responsiveness ++ * in these hostile scenarios. ++ */ ++ idling_boosts_thr_without_issues = idling_boosts_thr && ++ bfqd->wr_busy_queues == 0; ++ ++ /* ++ * There is then a case where idling must be performed not ++ * for throughput concerns, but to preserve service ++ * guarantees. ++ * ++ * To introduce this case, we can note that allowing the drive ++ * to enqueue more than one request at a time, and hence ++ * delegating de facto final scheduling decisions to the ++ * drive's internal scheduler, entails loss of control on the ++ * actual request service order. In particular, the critical ++ * situation is when requests from different processes happen ++ * to be present, at the same time, in the internal queue(s) ++ * of the drive. In such a situation, the drive, by deciding ++ * the service order of the internally-queued requests, does ++ * determine also the actual throughput distribution among ++ * these processes. But the drive typically has no notion or ++ * concern about per-process throughput distribution, and ++ * makes its decisions only on a per-request basis. Therefore, ++ * the service distribution enforced by the drive's internal ++ * scheduler is likely to coincide with the desired ++ * device-throughput distribution only in a completely ++ * symmetric scenario where: ++ * (i) each of these processes must get the same throughput as ++ * the others; ++ * (ii) all these processes have the same I/O pattern ++ * (either sequential or random). ++ * In fact, in such a scenario, the drive will tend to treat ++ * the requests of each of these processes in about the same ++ * way as the requests of the others, and thus to provide ++ * each of these processes with about the same throughput ++ * (which is exactly the desired throughput distribution). In ++ * contrast, in any asymmetric scenario, device idling is ++ * certainly needed to guarantee that bfqq receives its ++ * assigned fraction of the device throughput (see [1] for ++ * details). ++ * ++ * We address this issue by controlling, actually, only the ++ * symmetry sub-condition (i), i.e., provided that ++ * sub-condition (i) holds, idling is not performed, ++ * regardless of whether sub-condition (ii) holds. In other ++ * words, only if sub-condition (i) holds, then idling is ++ * allowed, and the device tends to be prevented from queueing ++ * many requests, possibly of several processes. The reason ++ * for not controlling also sub-condition (ii) is that we ++ * exploit preemption to preserve guarantees in case of ++ * symmetric scenarios, even if (ii) does not hold, as ++ * explained in the next two paragraphs. ++ * ++ * Even if a queue, say Q, is expired when it remains idle, Q ++ * can still preempt the new in-service queue if the next ++ * request of Q arrives soon (see the comments on ++ * bfq_bfqq_update_budg_for_activation). If all queues and ++ * groups have the same weight, this form of preemption, ++ * combined with the hole-recovery heuristic described in the ++ * comments on function bfq_bfqq_update_budg_for_activation, ++ * are enough to preserve a correct bandwidth distribution in ++ * the mid term, even without idling. In fact, even if not ++ * idling allows the internal queues of the device to contain ++ * many requests, and thus to reorder requests, we can rather ++ * safely assume that the internal scheduler still preserves a ++ * minimum of mid-term fairness. The motivation for using ++ * preemption instead of idling is that, by not idling, ++ * service guarantees are preserved without minimally ++ * sacrificing throughput. In other words, both a high ++ * throughput and its desired distribution are obtained. ++ * ++ * More precisely, this preemption-based, idleless approach ++ * provides fairness in terms of IOPS, and not sectors per ++ * second. This can be seen with a simple example. Suppose ++ * that there are two queues with the same weight, but that ++ * the first queue receives requests of 8 sectors, while the ++ * second queue receives requests of 1024 sectors. In ++ * addition, suppose that each of the two queues contains at ++ * most one request at a time, which implies that each queue ++ * always remains idle after it is served. Finally, after ++ * remaining idle, each queue receives very quickly a new ++ * request. It follows that the two queues are served ++ * alternatively, preempting each other if needed. This ++ * implies that, although both queues have the same weight, ++ * the queue with large requests receives a service that is ++ * 1024/8 times as high as the service received by the other ++ * queue. ++ * ++ * On the other hand, device idling is performed, and thus ++ * pure sector-domain guarantees are provided, for the ++ * following queues, which are likely to need stronger ++ * throughput guarantees: weight-raised queues, and queues ++ * with a higher weight than other queues. When such queues ++ * are active, sub-condition (i) is false, which triggers ++ * device idling. ++ * ++ * According to the above considerations, the next variable is ++ * true (only) if sub-condition (i) holds. To compute the ++ * value of this variable, we not only use the return value of ++ * the function bfq_symmetric_scenario(), but also check ++ * whether bfqq is being weight-raised, because ++ * bfq_symmetric_scenario() does not take into account also ++ * weight-raised queues (see comments on ++ * bfq_weights_tree_add()). ++ * ++ * As a side note, it is worth considering that the above ++ * device-idling countermeasures may however fail in the ++ * following unlucky scenario: if idling is (correctly) ++ * disabled in a time period during which all symmetry ++ * sub-conditions hold, and hence the device is allowed to ++ * enqueue many requests, but at some later point in time some ++ * sub-condition stops to hold, then it may become impossible ++ * to let requests be served in the desired order until all ++ * the requests already queued in the device have been served. ++ */ ++ asymmetric_scenario = bfqq->wr_coeff > 1 || ++ !bfq_symmetric_scenario(bfqd); ++ ++ /* ++ * Finally, there is a case where maximizing throughput is the ++ * best choice even if it may cause unfairness toward ++ * bfqq. Such a case is when bfqq became active in a burst of ++ * queue activations. Queues that became active during a large ++ * burst benefit only from throughput, as discussed in the ++ * comments on bfq_handle_burst. Thus, if bfqq became active ++ * in a burst and not idling the device maximizes throughput, ++ * then the device must no be idled, because not idling the ++ * device provides bfqq and all other queues in the burst with ++ * maximum benefit. Combining this and the above case, we can ++ * now establish when idling is actually needed to preserve ++ * service guarantees. ++ */ ++ idling_needed_for_service_guarantees = ++ asymmetric_scenario && !bfq_bfqq_in_large_burst(bfqq); ++ ++ /* ++ * We have now all the components we need to compute the return ++ * value of the function, which is true only if both the following ++ * conditions hold: ++ * 1) bfqq is sync, because idling make sense only for sync queues; ++ * 2) idling either boosts the throughput (without issues), or ++ * is necessary to preserve service guarantees. ++ */ ++ bfq_log_bfqq(bfqd, bfqq, "may_idle: sync %d idling_boosts_thr %d", ++ bfq_bfqq_sync(bfqq), idling_boosts_thr); ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "may_idle: wr_busy %d boosts %d IO-bound %d guar %d", ++ bfqd->wr_busy_queues, ++ idling_boosts_thr_without_issues, ++ bfq_bfqq_IO_bound(bfqq), ++ idling_needed_for_service_guarantees); ++ ++ return bfq_bfqq_sync(bfqq) && ++ (idling_boosts_thr_without_issues || ++ idling_needed_for_service_guarantees); ++} ++ ++/* ++ * If the in-service queue is empty but the function bfq_bfqq_may_idle ++ * returns true, then: ++ * 1) the queue must remain in service and cannot be expired, and ++ * 2) the device must be idled to wait for the possible arrival of a new ++ * request for the queue. ++ * See the comments on the function bfq_bfqq_may_idle for the reasons ++ * why performing device idling is the best choice to boost the throughput ++ * and preserve service guarantees when bfq_bfqq_may_idle itself ++ * returns true. ++ */ ++static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq) ++{ ++ struct bfq_data *bfqd = bfqq->bfqd; ++ ++ return RB_EMPTY_ROOT(&bfqq->sort_list) && bfqd->bfq_slice_idle != 0 && ++ bfq_bfqq_may_idle(bfqq); ++} ++ ++/* ++ * Select a queue for service. If we have a current queue in service, ++ * check whether to continue servicing it, or retrieve and set a new one. ++ */ ++static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd) ++{ ++ struct bfq_queue *bfqq; ++ struct request *next_rq; ++ enum bfqq_expiration reason = BFQ_BFQQ_BUDGET_TIMEOUT; ++ ++ bfqq = bfqd->in_service_queue; ++ if (!bfqq) ++ goto new_queue; ++ ++ bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue"); ++ ++ if (bfq_may_expire_for_budg_timeout(bfqq) && ++ !hrtimer_active(&bfqd->idle_slice_timer) && ++ !bfq_bfqq_must_idle(bfqq)) ++ goto expire; ++ ++ next_rq = bfqq->next_rq; ++ /* ++ * If bfqq has requests queued and it has enough budget left to ++ * serve them, keep the queue, otherwise expire it. ++ */ ++ if (next_rq) { ++ if (bfq_serv_to_charge(next_rq, bfqq) > ++ bfq_bfqq_budget_left(bfqq)) { ++ reason = BFQ_BFQQ_BUDGET_EXHAUSTED; ++ goto expire; ++ } else { ++ /* ++ * The idle timer may be pending because we may ++ * not disable disk idling even when a new request ++ * arrives. ++ */ ++ if (bfq_bfqq_wait_request(bfqq)) { ++ BUG_ON(!hrtimer_active(&bfqd->idle_slice_timer)); ++ /* ++ * If we get here: 1) at least a new request ++ * has arrived but we have not disabled the ++ * timer because the request was too small, ++ * 2) then the block layer has unplugged ++ * the device, causing the dispatch to be ++ * invoked. ++ * ++ * Since the device is unplugged, now the ++ * requests are probably large enough to ++ * provide a reasonable throughput. ++ * So we disable idling. ++ */ ++ bfq_clear_bfqq_wait_request(bfqq); ++ hrtimer_try_to_cancel(&bfqd->idle_slice_timer); ++ bfqg_stats_update_idle_time(bfqq_group(bfqq)); ++ } ++ goto keep_queue; ++ } ++ } ++ ++ /* ++ * No requests pending. However, if the in-service queue is idling ++ * for a new request, or has requests waiting for a completion and ++ * may idle after their completion, then keep it anyway. ++ */ ++ if (hrtimer_active(&bfqd->idle_slice_timer) || ++ (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) { ++ bfqq = NULL; ++ goto keep_queue; ++ } ++ ++ reason = BFQ_BFQQ_NO_MORE_REQUESTS; ++expire: ++ bfq_bfqq_expire(bfqd, bfqq, false, reason); ++new_queue: ++ bfqq = bfq_set_in_service_queue(bfqd); ++ bfq_log(bfqd, "select_queue: new queue %d returned", ++ bfqq ? bfqq->pid : 0); ++keep_queue: ++ return bfqq; ++} ++ ++static void bfq_update_wr_data(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ ++ if (bfqq->wr_coeff > 1) { /* queue is being weight-raised */ ++ BUG_ON(bfqq->wr_cur_max_time == bfqd->bfq_wr_rt_max_time && ++ time_is_after_jiffies(bfqq->last_wr_start_finish)); ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "raising period dur %u/%u msec, old coeff %u, w %d(%d)", ++ jiffies_to_msecs(jiffies - bfqq->last_wr_start_finish), ++ jiffies_to_msecs(bfqq->wr_cur_max_time), ++ bfqq->wr_coeff, ++ bfqq->entity.weight, bfqq->entity.orig_weight); ++ ++ BUG_ON(bfqq != bfqd->in_service_queue && entity->weight != ++ entity->orig_weight * bfqq->wr_coeff); ++ if (entity->prio_changed) ++ bfq_log_bfqq(bfqd, bfqq, "WARN: pending prio change"); ++ ++ /* ++ * If the queue was activated in a burst, or too much ++ * time has elapsed from the beginning of this ++ * weight-raising period, then end weight raising. ++ */ ++ if (bfq_bfqq_in_large_burst(bfqq)) ++ bfq_bfqq_end_wr(bfqq); ++ else if (time_is_before_jiffies(bfqq->last_wr_start_finish + ++ bfqq->wr_cur_max_time)) { ++ if (bfqq->wr_cur_max_time != bfqd->bfq_wr_rt_max_time || ++ time_is_before_jiffies(bfqq->wr_start_at_switch_to_srt + ++ bfq_wr_duration(bfqd))) ++ bfq_bfqq_end_wr(bfqq); ++ else { ++ /* switch back to interactive wr */ ++ bfqq->wr_coeff = bfqd->bfq_wr_coeff; ++ bfqq->wr_cur_max_time = bfq_wr_duration(bfqd); ++ bfqq->last_wr_start_finish = ++ bfqq->wr_start_at_switch_to_srt; ++ BUG_ON(time_is_after_jiffies( ++ bfqq->last_wr_start_finish)); ++ bfqq->entity.prio_changed = 1; ++ bfq_log_bfqq(bfqd, bfqq, ++ "back to interactive wr"); ++ } ++ } ++ } ++ /* Update weight both if it must be raised and if it must be lowered */ ++ if ((entity->weight > entity->orig_weight) != (bfqq->wr_coeff > 1)) ++ __bfq_entity_update_weight_prio( ++ bfq_entity_service_tree(entity), ++ entity); ++} ++ ++/* ++ * Dispatch one request from bfqq, moving it to the request queue ++ * dispatch list. ++ */ ++static int bfq_dispatch_request(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq) ++{ ++ int dispatched = 0; ++ struct request *rq; ++ unsigned long service_to_charge; ++ ++ BUG_ON(RB_EMPTY_ROOT(&bfqq->sort_list)); ++ ++ /* Follow expired path, else get first next available. */ ++ rq = bfq_check_fifo(bfqq); ++ if (!rq) ++ rq = bfqq->next_rq; ++ service_to_charge = bfq_serv_to_charge(rq, bfqq); ++ ++ if (service_to_charge > bfq_bfqq_budget_left(bfqq)) { ++ /* ++ * This may happen if the next rq is chosen in fifo order ++ * instead of sector order. The budget is properly ++ * dimensioned to be always sufficient to serve the next ++ * request only if it is chosen in sector order. The reason ++ * is that it would be quite inefficient and little useful ++ * to always make sure that the budget is large enough to ++ * serve even the possible next rq in fifo order. ++ * In fact, requests are seldom served in fifo order. ++ * ++ * Expire the queue for budget exhaustion, and make sure ++ * that the next act_budget is enough to serve the next ++ * request, even if it comes from the fifo expired path. ++ */ ++ bfqq->next_rq = rq; ++ /* ++ * Since this dispatch is failed, make sure that ++ * a new one will be performed ++ */ ++ if (!bfqd->rq_in_driver) ++ bfq_schedule_dispatch(bfqd); ++ BUG_ON(bfqq->entity.budget < bfqq->entity.service); ++ goto expire; ++ } ++ ++ BUG_ON(bfqq->entity.budget < bfqq->entity.service); ++ /* Finally, insert request into driver dispatch list. */ ++ bfq_bfqq_served(bfqq, service_to_charge); ++ ++ BUG_ON(bfqq->entity.budget < bfqq->entity.service); ++ ++ bfq_dispatch_insert(bfqd->queue, rq); ++ ++ /* ++ * If weight raising has to terminate for bfqq, then next ++ * function causes an immediate update of bfqq's weight, ++ * without waiting for next activation. As a consequence, on ++ * expiration, bfqq will be timestamped as if has never been ++ * weight-raised during this service slot, even if it has ++ * received part or even most of the service as a ++ * weight-raised queue. This inflates bfqq's timestamps, which ++ * is beneficial, as bfqq is then more willing to leave the ++ * device immediately to possible other weight-raised queues. ++ */ ++ bfq_update_wr_data(bfqd, bfqq); ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "dispatched %u sec req (%llu), budg left %d", ++ blk_rq_sectors(rq), ++ (unsigned long long) blk_rq_pos(rq), ++ bfq_bfqq_budget_left(bfqq)); ++ ++ dispatched++; ++ ++ if (!bfqd->in_service_bic) { ++ atomic_long_inc(&RQ_BIC(rq)->icq.ioc->refcount); ++ bfqd->in_service_bic = RQ_BIC(rq); ++ } ++ ++ if (bfqd->busy_queues > 1 && bfq_class_idle(bfqq)) ++ goto expire; ++ ++ return dispatched; ++ ++expire: ++ bfq_bfqq_expire(bfqd, bfqq, false, BFQ_BFQQ_BUDGET_EXHAUSTED); ++ return dispatched; ++} ++ ++static int __bfq_forced_dispatch_bfqq(struct bfq_queue *bfqq) ++{ ++ int dispatched = 0; ++ ++ while (bfqq->next_rq) { ++ bfq_dispatch_insert(bfqq->bfqd->queue, bfqq->next_rq); ++ dispatched++; ++ } ++ ++ BUG_ON(!list_empty(&bfqq->fifo)); ++ return dispatched; ++} ++ ++/* ++ * Drain our current requests. ++ * Used for barriers and when switching io schedulers on-the-fly. ++ */ ++static int bfq_forced_dispatch(struct bfq_data *bfqd) ++{ ++ struct bfq_queue *bfqq, *n; ++ struct bfq_service_tree *st; ++ int dispatched = 0; ++ ++ bfqq = bfqd->in_service_queue; ++ if (bfqq) ++ __bfq_bfqq_expire(bfqd, bfqq); ++ ++ /* ++ * Loop through classes, and be careful to leave the scheduler ++ * in a consistent state, as feedback mechanisms and vtime ++ * updates cannot be disabled during the process. ++ */ ++ list_for_each_entry_safe(bfqq, n, &bfqd->active_list, bfqq_list) { ++ st = bfq_entity_service_tree(&bfqq->entity); ++ ++ dispatched += __bfq_forced_dispatch_bfqq(bfqq); ++ ++ bfqq->max_budget = bfq_max_budget(bfqd); ++ bfq_forget_idle(st); ++ } ++ ++ BUG_ON(bfqd->busy_queues != 0); ++ ++ return dispatched; ++} ++ ++static int bfq_dispatch_requests(struct request_queue *q, int force) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ struct bfq_queue *bfqq; ++ ++ bfq_log(bfqd, "dispatch requests: %d busy queues", bfqd->busy_queues); ++ ++ if (bfqd->busy_queues == 0) ++ return 0; ++ ++ if (unlikely(force)) ++ return bfq_forced_dispatch(bfqd); ++ ++ /* ++ * Force device to serve one request at a time if ++ * strict_guarantees is true. Forcing this service scheme is ++ * currently the ONLY way to guarantee that the request ++ * service order enforced by the scheduler is respected by a ++ * queueing device. Otherwise the device is free even to make ++ * some unlucky request wait for as long as the device ++ * wishes. ++ * ++ * Of course, serving one request at at time may cause loss of ++ * throughput. ++ */ ++ if (bfqd->strict_guarantees && bfqd->rq_in_driver > 0) ++ return 0; ++ ++ bfqq = bfq_select_queue(bfqd); ++ if (!bfqq) ++ return 0; ++ ++ BUG_ON(bfqq->entity.budget < bfqq->entity.service); ++ ++ BUG_ON(bfq_bfqq_wait_request(bfqq)); ++ ++ if (!bfq_dispatch_request(bfqd, bfqq)) ++ return 0; ++ ++ bfq_log_bfqq(bfqd, bfqq, "dispatched %s request", ++ bfq_bfqq_sync(bfqq) ? "sync" : "async"); ++ ++ BUG_ON(bfqq->next_rq == NULL && ++ bfqq->entity.budget < bfqq->entity.service); ++ return 1; ++} ++ ++/* ++ * Task holds one reference to the queue, dropped when task exits. Each rq ++ * in-flight on this queue also holds a reference, dropped when rq is freed. ++ * ++ * Queue lock must be held here. ++ */ ++static void bfq_put_queue(struct bfq_queue *bfqq) ++{ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ struct bfq_group *bfqg = bfqq_group(bfqq); ++#endif ++ ++ BUG_ON(bfqq->ref <= 0); ++ ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p %d", bfqq, bfqq->ref); ++ bfqq->ref--; ++ if (bfqq->ref) ++ return; ++ ++ BUG_ON(rb_first(&bfqq->sort_list)); ++ BUG_ON(bfqq->allocated[READ] + bfqq->allocated[WRITE] != 0); ++ BUG_ON(bfqq->entity.tree); ++ BUG_ON(bfq_bfqq_busy(bfqq)); ++ BUG_ON(bfqq->bfqd->in_service_queue == bfqq); ++ ++ if (bfq_bfqq_sync(bfqq)) ++ /* ++ * The fact that this queue is being destroyed does not ++ * invalidate the fact that this queue may have been ++ * activated during the current burst. As a consequence, ++ * although the queue does not exist anymore, and hence ++ * needs to be removed from the burst list if there, ++ * the burst size has not to be decremented. ++ */ ++ hlist_del_init(&bfqq->burst_list_node); ++ ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_queue: %p freed", bfqq); ++ ++ kmem_cache_free(bfq_pool, bfqq); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ bfqg_put(bfqg); ++#endif ++} ++ ++static void bfq_put_cooperator(struct bfq_queue *bfqq) ++{ ++ struct bfq_queue *__bfqq, *next; ++ ++ /* ++ * If this queue was scheduled to merge with another queue, be ++ * sure to drop the reference taken on that queue (and others in ++ * the merge chain). See bfq_setup_merge and bfq_merge_bfqqs. ++ */ ++ __bfqq = bfqq->new_bfqq; ++ while (__bfqq) { ++ if (__bfqq == bfqq) ++ break; ++ next = __bfqq->new_bfqq; ++ bfq_put_queue(__bfqq); ++ __bfqq = next; ++ } ++} ++ ++static void bfq_exit_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ if (bfqq == bfqd->in_service_queue) { ++ __bfq_bfqq_expire(bfqd, bfqq); ++ bfq_schedule_dispatch(bfqd); ++ } ++ ++ bfq_log_bfqq(bfqd, bfqq, "exit_bfqq: %p, %d", bfqq, bfqq->ref); ++ ++ bfq_put_cooperator(bfqq); ++ ++ bfq_put_queue(bfqq); ++} ++ ++static void bfq_init_icq(struct io_cq *icq) ++{ ++ icq_to_bic(icq)->ttime.last_end_request = ktime_get_ns() - (1ULL<<32); ++} ++ ++static void bfq_exit_icq(struct io_cq *icq) ++{ ++ struct bfq_io_cq *bic = icq_to_bic(icq); ++ struct bfq_data *bfqd = bic_to_bfqd(bic); ++ ++ if (bic_to_bfqq(bic, false)) { ++ bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, false)); ++ bic_set_bfqq(bic, NULL, false); ++ } ++ ++ if (bic_to_bfqq(bic, true)) { ++ /* ++ * If the bic is using a shared queue, put the reference ++ * taken on the io_context when the bic started using a ++ * shared bfq_queue. ++ */ ++ if (bfq_bfqq_coop(bic_to_bfqq(bic, true))) ++ put_io_context(icq->ioc); ++ bfq_exit_bfqq(bfqd, bic_to_bfqq(bic, true)); ++ bic_set_bfqq(bic, NULL, true); ++ } ++} ++ ++/* ++ * Update the entity prio values; note that the new values will not ++ * be used until the next (re)activation. ++ */ ++static void bfq_set_next_ioprio_data(struct bfq_queue *bfqq, ++ struct bfq_io_cq *bic) ++{ ++ struct task_struct *tsk = current; ++ int ioprio_class; ++ ++ ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); ++ switch (ioprio_class) { ++ default: ++ dev_err(bfqq->bfqd->queue->backing_dev_info.dev, ++ "bfq: bad prio class %d\n", ioprio_class); ++ case IOPRIO_CLASS_NONE: ++ /* ++ * No prio set, inherit CPU scheduling settings. ++ */ ++ bfqq->new_ioprio = task_nice_ioprio(tsk); ++ bfqq->new_ioprio_class = task_nice_ioclass(tsk); ++ break; ++ case IOPRIO_CLASS_RT: ++ bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); ++ bfqq->new_ioprio_class = IOPRIO_CLASS_RT; ++ break; ++ case IOPRIO_CLASS_BE: ++ bfqq->new_ioprio = IOPRIO_PRIO_DATA(bic->ioprio); ++ bfqq->new_ioprio_class = IOPRIO_CLASS_BE; ++ break; ++ case IOPRIO_CLASS_IDLE: ++ bfqq->new_ioprio_class = IOPRIO_CLASS_IDLE; ++ bfqq->new_ioprio = 7; ++ bfq_clear_bfqq_idle_window(bfqq); ++ break; ++ } ++ ++ if (bfqq->new_ioprio >= IOPRIO_BE_NR) { ++ pr_crit("bfq_set_next_ioprio_data: new_ioprio %d\n", ++ bfqq->new_ioprio); ++ BUG(); ++ } ++ ++ bfqq->entity.new_weight = bfq_ioprio_to_weight(bfqq->new_ioprio); ++ bfqq->entity.prio_changed = 1; ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "set_next_ioprio_data: bic_class %d prio %d class %d", ++ ioprio_class, bfqq->new_ioprio, bfqq->new_ioprio_class); ++} ++ ++static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) ++{ ++ struct bfq_data *bfqd = bic_to_bfqd(bic); ++ struct bfq_queue *bfqq; ++ unsigned long uninitialized_var(flags); ++ int ioprio = bic->icq.ioc->ioprio; ++ ++ /* ++ * This condition may trigger on a newly created bic, be sure to ++ * drop the lock before returning. ++ */ ++ if (unlikely(!bfqd) || likely(bic->ioprio == ioprio)) ++ return; ++ ++ bic->ioprio = ioprio; ++ ++ bfqq = bic_to_bfqq(bic, false); ++ if (bfqq) { ++ bfq_put_queue(bfqq); ++ bfqq = bfq_get_queue(bfqd, bio, BLK_RW_ASYNC, bic); ++ bic_set_bfqq(bic, bfqq, false); ++ bfq_log_bfqq(bfqd, bfqq, ++ "check_ioprio_change: bfqq %p %d", ++ bfqq, bfqq->ref); ++ } ++ ++ bfqq = bic_to_bfqq(bic, true); ++ if (bfqq) ++ bfq_set_next_ioprio_data(bfqq, bic); ++} ++ ++static void bfq_init_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ struct bfq_io_cq *bic, pid_t pid, int is_sync) ++{ ++ RB_CLEAR_NODE(&bfqq->entity.rb_node); ++ INIT_LIST_HEAD(&bfqq->fifo); ++ INIT_HLIST_NODE(&bfqq->burst_list_node); ++ BUG_ON(!hlist_unhashed(&bfqq->burst_list_node)); ++ ++ bfqq->ref = 0; ++ bfqq->bfqd = bfqd; ++ ++ if (bic) ++ bfq_set_next_ioprio_data(bfqq, bic); ++ ++ if (is_sync) { ++ if (!bfq_class_idle(bfqq)) ++ bfq_mark_bfqq_idle_window(bfqq); ++ bfq_mark_bfqq_sync(bfqq); ++ bfq_mark_bfqq_just_created(bfqq); ++ } else ++ bfq_clear_bfqq_sync(bfqq); ++ bfq_mark_bfqq_IO_bound(bfqq); ++ ++ /* Tentative initial value to trade off between thr and lat */ ++ bfqq->max_budget = (2 * bfq_max_budget(bfqd)) / 3; ++ bfqq->pid = pid; ++ ++ bfqq->wr_coeff = 1; ++ bfqq->last_wr_start_finish = jiffies; ++ bfqq->wr_start_at_switch_to_srt = bfq_smallest_from_now(); ++ bfqq->budget_timeout = bfq_smallest_from_now(); ++ bfqq->split_time = bfq_smallest_from_now(); ++ ++ /* ++ * Set to the value for which bfqq will not be deemed as ++ * soft rt when it becomes backlogged. ++ */ ++ bfqq->soft_rt_next_start = bfq_greatest_from_now(); ++ ++ /* first request is almost certainly seeky */ ++ bfqq->seek_history = 1; ++} ++ ++static struct bfq_queue **bfq_async_queue_prio(struct bfq_data *bfqd, ++ struct bfq_group *bfqg, ++ int ioprio_class, int ioprio) ++{ ++ switch (ioprio_class) { ++ case IOPRIO_CLASS_RT: ++ return &bfqg->async_bfqq[0][ioprio]; ++ case IOPRIO_CLASS_NONE: ++ ioprio = IOPRIO_NORM; ++ /* fall through */ ++ case IOPRIO_CLASS_BE: ++ return &bfqg->async_bfqq[1][ioprio]; ++ case IOPRIO_CLASS_IDLE: ++ return &bfqg->async_idle_bfqq; ++ default: ++ BUG(); ++ } ++} ++ ++static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, ++ struct bio *bio, bool is_sync, ++ struct bfq_io_cq *bic) ++{ ++ const int ioprio = IOPRIO_PRIO_DATA(bic->ioprio); ++ const int ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); ++ struct bfq_queue **async_bfqq = NULL; ++ struct bfq_queue *bfqq; ++ struct bfq_group *bfqg; ++ ++ rcu_read_lock(); ++ ++ bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio)); ++ if (!bfqg) { ++ bfqq = &bfqd->oom_bfqq; ++ goto out; ++ } ++ ++ if (!is_sync) { ++ async_bfqq = bfq_async_queue_prio(bfqd, bfqg, ioprio_class, ++ ioprio); ++ bfqq = *async_bfqq; ++ if (bfqq) ++ goto out; ++ } ++ ++ bfqq = kmem_cache_alloc_node(bfq_pool, GFP_NOWAIT | __GFP_ZERO, ++ bfqd->queue->node); ++ ++ if (bfqq) { ++ bfq_init_bfqq(bfqd, bfqq, bic, current->pid, ++ is_sync); ++ bfq_init_entity(&bfqq->entity, bfqg); ++ bfq_log_bfqq(bfqd, bfqq, "allocated"); ++ } else { ++ bfqq = &bfqd->oom_bfqq; ++ bfq_log_bfqq(bfqd, bfqq, "using oom bfqq"); ++ goto out; ++ } ++ ++ /* ++ * Pin the queue now that it's allocated, scheduler exit will ++ * prune it. ++ */ ++ if (async_bfqq) { ++ bfqq->ref++; ++ bfq_log_bfqq(bfqd, bfqq, "get_queue, bfqq not in async: %p, %d", ++ bfqq, bfqq->ref); ++ *async_bfqq = bfqq; ++ } ++ ++out: ++ bfqq->ref++; ++ bfq_log_bfqq(bfqd, bfqq, "get_queue, at end: %p, %d", bfqq, bfqq->ref); ++ rcu_read_unlock(); ++ return bfqq; ++} ++ ++static void bfq_update_io_thinktime(struct bfq_data *bfqd, ++ struct bfq_io_cq *bic) ++{ ++ struct bfq_ttime *ttime = &bic->ttime; ++ u64 elapsed = ktime_get_ns() - bic->ttime.last_end_request; ++ ++ elapsed = min_t(u64, elapsed, 2 * bfqd->bfq_slice_idle); ++ ++ ttime->ttime_samples = (7*bic->ttime.ttime_samples + 256) / 8; ++ ttime->ttime_total = div_u64(7*ttime->ttime_total + 256*elapsed, 8); ++ ttime->ttime_mean = div64_ul(ttime->ttime_total + 128, ++ ttime->ttime_samples); ++} ++ ++static void ++bfq_update_io_seektime(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ struct request *rq) ++{ ++ bfqq->seek_history <<= 1; ++ bfqq->seek_history |= ++ get_sdist(bfqq->last_request_pos, rq) > BFQQ_SEEK_THR; ++} ++ ++/* ++ * Disable idle window if the process thinks too long or seeks so much that ++ * it doesn't matter. ++ */ ++static void bfq_update_idle_window(struct bfq_data *bfqd, ++ struct bfq_queue *bfqq, ++ struct bfq_io_cq *bic) ++{ ++ int enable_idle; ++ ++ /* Don't idle for async or idle io prio class. */ ++ if (!bfq_bfqq_sync(bfqq) || bfq_class_idle(bfqq)) ++ return; ++ ++ /* Idle window just restored, statistics are meaningless. */ ++ if (time_is_after_eq_jiffies(bfqq->split_time + ++ bfqd->bfq_wr_min_idle_time)) ++ return; ++ ++ enable_idle = bfq_bfqq_idle_window(bfqq); ++ ++ if (atomic_read(&bic->icq.ioc->active_ref) == 0 || ++ bfqd->bfq_slice_idle == 0 || ++ (bfqd->hw_tag && BFQQ_SEEKY(bfqq) && ++ bfqq->wr_coeff == 1)) ++ enable_idle = 0; ++ else if (bfq_sample_valid(bic->ttime.ttime_samples)) { ++ if (bic->ttime.ttime_mean > bfqd->bfq_slice_idle && ++ bfqq->wr_coeff == 1) ++ enable_idle = 0; ++ else ++ enable_idle = 1; ++ } ++ bfq_log_bfqq(bfqd, bfqq, "update_idle_window: enable_idle %d", ++ enable_idle); ++ ++ if (enable_idle) ++ bfq_mark_bfqq_idle_window(bfqq); ++ else ++ bfq_clear_bfqq_idle_window(bfqq); ++} ++ ++/* ++ * Called when a new fs request (rq) is added to bfqq. Check if there's ++ * something we should do about it. ++ */ ++static void bfq_rq_enqueued(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ struct request *rq) ++{ ++ struct bfq_io_cq *bic = RQ_BIC(rq); ++ ++ if (rq->cmd_flags & REQ_META) ++ bfqq->meta_pending++; ++ ++ bfq_update_io_thinktime(bfqd, bic); ++ bfq_update_io_seektime(bfqd, bfqq, rq); ++ if (bfqq->entity.service > bfq_max_budget(bfqd) / 8 || ++ !BFQQ_SEEKY(bfqq)) ++ bfq_update_idle_window(bfqd, bfqq, bic); ++ ++ bfq_log_bfqq(bfqd, bfqq, ++ "rq_enqueued: idle_window=%d (seeky %d)", ++ bfq_bfqq_idle_window(bfqq), BFQQ_SEEKY(bfqq)); ++ ++ bfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq); ++ ++ if (bfqq == bfqd->in_service_queue && bfq_bfqq_wait_request(bfqq)) { ++ bool small_req = bfqq->queued[rq_is_sync(rq)] == 1 && ++ blk_rq_sectors(rq) < 32; ++ bool budget_timeout = bfq_bfqq_budget_timeout(bfqq); ++ ++ /* ++ * There is just this request queued: if the request ++ * is small and the queue is not to be expired, then ++ * just exit. ++ * ++ * In this way, if the device is being idled to wait ++ * for a new request from the in-service queue, we ++ * avoid unplugging the device and committing the ++ * device to serve just a small request. On the ++ * contrary, we wait for the block layer to decide ++ * when to unplug the device: hopefully, new requests ++ * will be merged to this one quickly, then the device ++ * will be unplugged and larger requests will be ++ * dispatched. ++ */ ++ if (small_req && !budget_timeout) ++ return; ++ ++ /* ++ * A large enough request arrived, or the queue is to ++ * be expired: in both cases disk idling is to be ++ * stopped, so clear wait_request flag and reset ++ * timer. ++ */ ++ bfq_clear_bfqq_wait_request(bfqq); ++ hrtimer_try_to_cancel(&bfqd->idle_slice_timer); ++ bfqg_stats_update_idle_time(bfqq_group(bfqq)); ++ ++ /* ++ * The queue is not empty, because a new request just ++ * arrived. Hence we can safely expire the queue, in ++ * case of budget timeout, without risking that the ++ * timestamps of the queue are not updated correctly. ++ * See [1] for more details. ++ */ ++ if (budget_timeout) ++ bfq_bfqq_expire(bfqd, bfqq, false, ++ BFQ_BFQQ_BUDGET_TIMEOUT); ++ ++ /* ++ * Let the request rip immediately, or let a new queue be ++ * selected if bfqq has just been expired. ++ */ ++ __blk_run_queue(bfqd->queue); ++ } ++} ++ ++static void bfq_insert_request(struct request_queue *q, struct request *rq) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ struct bfq_queue *bfqq = RQ_BFQQ(rq), *new_bfqq; ++ ++ assert_spin_locked(bfqd->queue->queue_lock); ++ ++ /* ++ * An unplug may trigger a requeue of a request from the device ++ * driver: make sure we are in process context while trying to ++ * merge two bfq_queues. ++ */ ++ if (!in_interrupt()) { ++ new_bfqq = bfq_setup_cooperator(bfqd, bfqq, rq, true); ++ if (new_bfqq) { ++ if (bic_to_bfqq(RQ_BIC(rq), 1) != bfqq) ++ new_bfqq = bic_to_bfqq(RQ_BIC(rq), 1); ++ /* ++ * Release the request's reference to the old bfqq ++ * and make sure one is taken to the shared queue. ++ */ ++ new_bfqq->allocated[rq_data_dir(rq)]++; ++ bfqq->allocated[rq_data_dir(rq)]--; ++ new_bfqq->ref++; ++ bfq_clear_bfqq_just_created(bfqq); ++ bfq_put_queue(bfqq); ++ if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) ++ bfq_merge_bfqqs(bfqd, RQ_BIC(rq), ++ bfqq, new_bfqq); ++ rq->elv.priv[1] = new_bfqq; ++ bfqq = new_bfqq; ++ } ++ } ++ ++ bfq_add_request(rq); ++ ++ rq->fifo_time = ktime_get_ns() + ++ jiffies_to_nsecs(bfqd->bfq_fifo_expire[rq_is_sync(rq)]); ++ list_add_tail(&rq->queuelist, &bfqq->fifo); ++ ++ bfq_rq_enqueued(bfqd, bfqq, rq); ++} ++ ++static void bfq_update_hw_tag(struct bfq_data *bfqd) ++{ ++ bfqd->max_rq_in_driver = max_t(int, bfqd->max_rq_in_driver, ++ bfqd->rq_in_driver); ++ ++ if (bfqd->hw_tag == 1) ++ return; ++ ++ /* ++ * This sample is valid if the number of outstanding requests ++ * is large enough to allow a queueing behavior. Note that the ++ * sum is not exact, as it's not taking into account deactivated ++ * requests. ++ */ ++ if (bfqd->rq_in_driver + bfqd->queued < BFQ_HW_QUEUE_THRESHOLD) ++ return; ++ ++ if (bfqd->hw_tag_samples++ < BFQ_HW_QUEUE_SAMPLES) ++ return; ++ ++ bfqd->hw_tag = bfqd->max_rq_in_driver > BFQ_HW_QUEUE_THRESHOLD; ++ bfqd->max_rq_in_driver = 0; ++ bfqd->hw_tag_samples = 0; ++} ++ ++static void bfq_completed_request(struct request_queue *q, struct request *rq) ++{ ++ struct bfq_queue *bfqq = RQ_BFQQ(rq); ++ struct bfq_data *bfqd = bfqq->bfqd; ++ u64 now_ns; ++ u32 delta_us; ++ ++ bfq_log_bfqq(bfqd, bfqq, "completed one req with %u sects left", ++ blk_rq_sectors(rq)); ++ ++ assert_spin_locked(bfqd->queue->queue_lock); ++ bfq_update_hw_tag(bfqd); ++ ++ BUG_ON(!bfqd->rq_in_driver); ++ BUG_ON(!bfqq->dispatched); ++ bfqd->rq_in_driver--; ++ bfqq->dispatched--; ++ bfqg_stats_update_completion(bfqq_group(bfqq), ++ rq_start_time_ns(rq), ++ rq_io_start_time_ns(rq), req_op(rq), ++ rq->cmd_flags); ++ ++ if (!bfqq->dispatched && !bfq_bfqq_busy(bfqq)) { ++ BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); ++ /* ++ * Set budget_timeout (which we overload to store the ++ * time at which the queue remains with no backlog and ++ * no outstanding request; used by the weight-raising ++ * mechanism). ++ */ ++ bfqq->budget_timeout = jiffies; ++ ++ bfq_weights_tree_remove(bfqd, &bfqq->entity, ++ &bfqd->queue_weights_tree); ++ } ++ ++ now_ns = ktime_get_ns(); ++ ++ RQ_BIC(rq)->ttime.last_end_request = now_ns; ++ ++ /* ++ * Using us instead of ns, to get a reasonable precision in ++ * computing rate in next check. ++ */ ++ delta_us = div_u64(now_ns - bfqd->last_completion, NSEC_PER_USEC); ++ ++ bfq_log(bfqd, "rq_completed: delta %uus/%luus max_size %u rate %llu/%llu", ++ delta_us, BFQ_MIN_TT/NSEC_PER_USEC, bfqd->last_rq_max_size, ++ (USEC_PER_SEC* ++ (u64)((bfqd->last_rq_max_size<>BFQ_RATE_SHIFT, ++ (USEC_PER_SEC*(u64)(1UL<<(BFQ_RATE_SHIFT-10)))>>BFQ_RATE_SHIFT); ++ ++ /* ++ * If the request took rather long to complete, and, according ++ * to the maximum request size recorded, this completion latency ++ * implies that the request was certainly served at a very low ++ * rate (less than 1M sectors/sec), then the whole observation ++ * interval that lasts up to this time instant cannot be a ++ * valid time interval for computing a new peak rate. Invoke ++ * bfq_update_rate_reset to have the following three steps ++ * taken: ++ * - close the observation interval at the last (previous) ++ * request dispatch or completion ++ * - compute rate, if possible, for that observation interval ++ * - reset to zero samples, which will trigger a proper ++ * re-initialization of the observation interval on next ++ * dispatch ++ */ ++ if (delta_us > BFQ_MIN_TT/NSEC_PER_USEC && ++ (bfqd->last_rq_max_size<last_completion = now_ns; ++ ++ /* ++ * If we are waiting to discover whether the request pattern ++ * of the task associated with the queue is actually ++ * isochronous, and both requisites for this condition to hold ++ * are now satisfied, then compute soft_rt_next_start (see the ++ * comments on the function bfq_bfqq_softrt_next_start()). We ++ * schedule this delayed check when bfqq expires, if it still ++ * has in-flight requests. ++ */ ++ if (bfq_bfqq_softrt_update(bfqq) && bfqq->dispatched == 0 && ++ RB_EMPTY_ROOT(&bfqq->sort_list)) ++ bfqq->soft_rt_next_start = ++ bfq_bfqq_softrt_next_start(bfqd, bfqq); ++ ++ /* ++ * If this is the in-service queue, check if it needs to be expired, ++ * or if we want to idle in case it has no pending requests. ++ */ ++ if (bfqd->in_service_queue == bfqq) { ++ if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) { ++ bfq_arm_slice_timer(bfqd); ++ goto out; ++ } else if (bfq_may_expire_for_budg_timeout(bfqq)) ++ bfq_bfqq_expire(bfqd, bfqq, false, ++ BFQ_BFQQ_BUDGET_TIMEOUT); ++ else if (RB_EMPTY_ROOT(&bfqq->sort_list) && ++ (bfqq->dispatched == 0 || ++ !bfq_bfqq_may_idle(bfqq))) ++ bfq_bfqq_expire(bfqd, bfqq, false, ++ BFQ_BFQQ_NO_MORE_REQUESTS); ++ } ++ ++ if (!bfqd->rq_in_driver) ++ bfq_schedule_dispatch(bfqd); ++ ++out: ++ return; ++} ++ ++static int __bfq_may_queue(struct bfq_queue *bfqq) ++{ ++ if (bfq_bfqq_wait_request(bfqq) && bfq_bfqq_must_alloc(bfqq)) { ++ bfq_clear_bfqq_must_alloc(bfqq); ++ return ELV_MQUEUE_MUST; ++ } ++ ++ return ELV_MQUEUE_MAY; ++} ++ ++static int bfq_may_queue(struct request_queue *q, int op, int op_flags) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ struct task_struct *tsk = current; ++ struct bfq_io_cq *bic; ++ struct bfq_queue *bfqq; ++ ++ /* ++ * Don't force setup of a queue from here, as a call to may_queue ++ * does not necessarily imply that a request actually will be ++ * queued. So just lookup a possibly existing queue, or return ++ * 'may queue' if that fails. ++ */ ++ bic = bfq_bic_lookup(bfqd, tsk->io_context); ++ if (!bic) ++ return ELV_MQUEUE_MAY; ++ ++ bfqq = bic_to_bfqq(bic, rw_is_sync(op, op_flags)); ++ if (bfqq) ++ return __bfq_may_queue(bfqq); ++ ++ return ELV_MQUEUE_MAY; ++} ++ ++/* ++ * Queue lock held here. ++ */ ++static void bfq_put_request(struct request *rq) ++{ ++ struct bfq_queue *bfqq = RQ_BFQQ(rq); ++ ++ if (bfqq) { ++ const int rw = rq_data_dir(rq); ++ ++ BUG_ON(!bfqq->allocated[rw]); ++ bfqq->allocated[rw]--; ++ ++ rq->elv.priv[0] = NULL; ++ rq->elv.priv[1] = NULL; ++ ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "put_request %p, %d", ++ bfqq, bfqq->ref); ++ bfq_put_queue(bfqq); ++ } ++} ++ ++/* ++ * Returns NULL if a new bfqq should be allocated, or the old bfqq if this ++ * was the last process referring to that bfqq. ++ */ ++static struct bfq_queue * ++bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) ++{ ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); ++ ++ put_io_context(bic->icq.ioc); ++ ++ if (bfqq_process_refs(bfqq) == 1) { ++ bfqq->pid = current->pid; ++ bfq_clear_bfqq_coop(bfqq); ++ bfq_clear_bfqq_split_coop(bfqq); ++ return bfqq; ++ } ++ ++ bic_set_bfqq(bic, NULL, 1); ++ ++ bfq_put_cooperator(bfqq); ++ ++ bfq_put_queue(bfqq); ++ return NULL; ++} ++ ++/* ++ * Allocate bfq data structures associated with this request. ++ */ ++static int bfq_set_request(struct request_queue *q, struct request *rq, ++ struct bio *bio, gfp_t gfp_mask) ++{ ++ struct bfq_data *bfqd = q->elevator->elevator_data; ++ struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq); ++ const int rw = rq_data_dir(rq); ++ const int is_sync = rq_is_sync(rq); ++ struct bfq_queue *bfqq; ++ unsigned long flags; ++ bool split = false; ++ ++ spin_lock_irqsave(q->queue_lock, flags); ++ bfq_check_ioprio_change(bic, bio); ++ ++ if (!bic) ++ goto queue_fail; ++ ++ bfq_bic_update_cgroup(bic, bio); ++ ++new_queue: ++ bfqq = bic_to_bfqq(bic, is_sync); ++ if (!bfqq || bfqq == &bfqd->oom_bfqq) { ++ if (bfqq) ++ bfq_put_queue(bfqq); ++ bfqq = bfq_get_queue(bfqd, bio, is_sync, bic); ++ BUG_ON(!hlist_unhashed(&bfqq->burst_list_node)); ++ ++ bic_set_bfqq(bic, bfqq, is_sync); ++ if (split && is_sync) { ++ bfq_log_bfqq(bfqd, bfqq, ++ "set_request: was_in_list %d " ++ "was_in_large_burst %d " ++ "large burst in progress %d", ++ bic->was_in_burst_list, ++ bic->saved_in_large_burst, ++ bfqd->large_burst); ++ ++ if ((bic->was_in_burst_list && bfqd->large_burst) || ++ bic->saved_in_large_burst) { ++ bfq_log_bfqq(bfqd, bfqq, ++ "set_request: marking in " ++ "large burst"); ++ bfq_mark_bfqq_in_large_burst(bfqq); ++ } else { ++ bfq_log_bfqq(bfqd, bfqq, ++ "set_request: clearing in " ++ "large burst"); ++ bfq_clear_bfqq_in_large_burst(bfqq); ++ if (bic->was_in_burst_list) ++ hlist_add_head(&bfqq->burst_list_node, ++ &bfqd->burst_list); ++ } ++ bfqq->split_time = jiffies; ++ } ++ } else { ++ /* If the queue was seeky for too long, break it apart. */ ++ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq)) { ++ bfq_log_bfqq(bfqd, bfqq, "breaking apart bfqq"); ++ ++ /* Update bic before losing reference to bfqq */ ++ if (bfq_bfqq_in_large_burst(bfqq)) ++ bic->saved_in_large_burst = true; ++ ++ bfqq = bfq_split_bfqq(bic, bfqq); ++ split = true; ++ if (!bfqq) ++ goto new_queue; ++ } ++ } ++ ++ bfqq->allocated[rw]++; ++ bfqq->ref++; ++ bfq_log_bfqq(bfqd, bfqq, "set_request: bfqq %p, %d", bfqq, bfqq->ref); ++ ++ rq->elv.priv[0] = bic; ++ rq->elv.priv[1] = bfqq; ++ ++ /* ++ * If a bfq_queue has only one process reference, it is owned ++ * by only one bfq_io_cq: we can set the bic field of the ++ * bfq_queue to the address of that structure. Also, if the ++ * queue has just been split, mark a flag so that the ++ * information is available to the other scheduler hooks. ++ */ ++ if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { ++ bfqq->bic = bic; ++ if (split) { ++ /* ++ * If the queue has just been split from a shared ++ * queue, restore the idle window and the possible ++ * weight raising period. ++ */ ++ bfq_bfqq_resume_state(bfqq, bic); ++ } ++ } ++ ++ if (unlikely(bfq_bfqq_just_created(bfqq))) ++ bfq_handle_burst(bfqd, bfqq); ++ ++ spin_unlock_irqrestore(q->queue_lock, flags); ++ ++ return 0; ++ ++queue_fail: ++ bfq_schedule_dispatch(bfqd); ++ spin_unlock_irqrestore(q->queue_lock, flags); ++ ++ return 1; ++} ++ ++static void bfq_kick_queue(struct work_struct *work) ++{ ++ struct bfq_data *bfqd = ++ container_of(work, struct bfq_data, unplug_work); ++ struct request_queue *q = bfqd->queue; ++ ++ spin_lock_irq(q->queue_lock); ++ __blk_run_queue(q); ++ spin_unlock_irq(q->queue_lock); ++} ++ ++/* ++ * Handler of the expiration of the timer running if the in-service queue ++ * is idling inside its time slice. ++ */ ++static enum hrtimer_restart bfq_idle_slice_timer(struct hrtimer *timer) ++{ ++ struct bfq_data *bfqd = container_of(timer, struct bfq_data, ++ idle_slice_timer); ++ struct bfq_queue *bfqq; ++ unsigned long flags; ++ enum bfqq_expiration reason; ++ ++ spin_lock_irqsave(bfqd->queue->queue_lock, flags); ++ ++ bfqq = bfqd->in_service_queue; ++ /* ++ * Theoretical race here: the in-service queue can be NULL or ++ * different from the queue that was idling if the timer handler ++ * spins on the queue_lock and a new request arrives for the ++ * current queue and there is a full dispatch cycle that changes ++ * the in-service queue. This can hardly happen, but in the worst ++ * case we just expire a queue too early. ++ */ ++ if (bfqq) { ++ bfq_log_bfqq(bfqd, bfqq, "slice_timer expired"); ++ bfq_clear_bfqq_wait_request(bfqq); ++ ++ if (bfq_bfqq_budget_timeout(bfqq)) ++ /* ++ * Also here the queue can be safely expired ++ * for budget timeout without wasting ++ * guarantees ++ */ ++ reason = BFQ_BFQQ_BUDGET_TIMEOUT; ++ else if (bfqq->queued[0] == 0 && bfqq->queued[1] == 0) ++ /* ++ * The queue may not be empty upon timer expiration, ++ * because we may not disable the timer when the ++ * first request of the in-service queue arrives ++ * during disk idling. ++ */ ++ reason = BFQ_BFQQ_TOO_IDLE; ++ else ++ goto schedule_dispatch; ++ ++ bfq_bfqq_expire(bfqd, bfqq, true, reason); ++ } ++ ++schedule_dispatch: ++ bfq_schedule_dispatch(bfqd); ++ ++ spin_unlock_irqrestore(bfqd->queue->queue_lock, flags); ++ return HRTIMER_NORESTART; ++} ++ ++static void bfq_shutdown_timer_wq(struct bfq_data *bfqd) ++{ ++ hrtimer_cancel(&bfqd->idle_slice_timer); ++ cancel_work_sync(&bfqd->unplug_work); ++} ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++static void __bfq_put_async_bfqq(struct bfq_data *bfqd, ++ struct bfq_queue **bfqq_ptr) ++{ ++ struct bfq_group *root_group = bfqd->root_group; ++ struct bfq_queue *bfqq = *bfqq_ptr; ++ ++ bfq_log(bfqd, "put_async_bfqq: %p", bfqq); ++ if (bfqq) { ++ bfq_bfqq_move(bfqd, bfqq, root_group); ++ bfq_log_bfqq(bfqd, bfqq, "put_async_bfqq: putting %p, %d", ++ bfqq, bfqq->ref); ++ bfq_put_queue(bfqq); ++ *bfqq_ptr = NULL; ++ } ++} ++ ++/* ++ * Release all the bfqg references to its async queues. If we are ++ * deallocating the group these queues may still contain requests, so ++ * we reparent them to the root cgroup (i.e., the only one that will ++ * exist for sure until all the requests on a device are gone). ++ */ ++static void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg) ++{ ++ int i, j; ++ ++ for (i = 0; i < 2; i++) ++ for (j = 0; j < IOPRIO_BE_NR; j++) ++ __bfq_put_async_bfqq(bfqd, &bfqg->async_bfqq[i][j]); ++ ++ __bfq_put_async_bfqq(bfqd, &bfqg->async_idle_bfqq); ++} ++#endif ++ ++static void bfq_exit_queue(struct elevator_queue *e) ++{ ++ struct bfq_data *bfqd = e->elevator_data; ++ struct request_queue *q = bfqd->queue; ++ struct bfq_queue *bfqq, *n; ++ ++ bfq_shutdown_timer_wq(bfqd); ++ ++ spin_lock_irq(q->queue_lock); ++ ++ BUG_ON(bfqd->in_service_queue); ++ list_for_each_entry_safe(bfqq, n, &bfqd->idle_list, bfqq_list) ++ bfq_deactivate_bfqq(bfqd, bfqq, 0); ++ ++ spin_unlock_irq(q->queue_lock); ++ ++ bfq_shutdown_timer_wq(bfqd); ++ ++ BUG_ON(hrtimer_active(&bfqd->idle_slice_timer)); ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ blkcg_deactivate_policy(q, &blkcg_policy_bfq); ++#else ++ kfree(bfqd->root_group); ++#endif ++ ++ kfree(bfqd); ++} ++ ++static void bfq_init_root_group(struct bfq_group *root_group, ++ struct bfq_data *bfqd) ++{ ++ int i; ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ root_group->entity.parent = NULL; ++ root_group->my_entity = NULL; ++ root_group->bfqd = bfqd; ++#endif ++ root_group->rq_pos_tree = RB_ROOT; ++ for (i = 0; i < BFQ_IOPRIO_CLASSES; i++) ++ root_group->sched_data.service_tree[i] = BFQ_SERVICE_TREE_INIT; ++} ++ ++static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) ++{ ++ struct bfq_data *bfqd; ++ struct elevator_queue *eq; ++ ++ eq = elevator_alloc(q, e); ++ if (!eq) ++ return -ENOMEM; ++ ++ bfqd = kzalloc_node(sizeof(*bfqd), GFP_KERNEL, q->node); ++ if (!bfqd) { ++ kobject_put(&eq->kobj); ++ return -ENOMEM; ++ } ++ eq->elevator_data = bfqd; ++ ++ /* ++ * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues. ++ * Grab a permanent reference to it, so that the normal code flow ++ * will not attempt to free it. ++ */ ++ bfq_init_bfqq(bfqd, &bfqd->oom_bfqq, NULL, 1, 0); ++ bfqd->oom_bfqq.ref++; ++ bfqd->oom_bfqq.new_ioprio = BFQ_DEFAULT_QUEUE_IOPRIO; ++ bfqd->oom_bfqq.new_ioprio_class = IOPRIO_CLASS_BE; ++ bfqd->oom_bfqq.entity.new_weight = ++ bfq_ioprio_to_weight(bfqd->oom_bfqq.new_ioprio); ++ ++ /* oom_bfqq does not participate to bursts */ ++ bfq_clear_bfqq_just_created(&bfqd->oom_bfqq); ++ /* ++ * Trigger weight initialization, according to ioprio, at the ++ * oom_bfqq's first activation. The oom_bfqq's ioprio and ioprio ++ * class won't be changed any more. ++ */ ++ bfqd->oom_bfqq.entity.prio_changed = 1; ++ ++ bfqd->queue = q; ++ ++ spin_lock_irq(q->queue_lock); ++ q->elevator = eq; ++ spin_unlock_irq(q->queue_lock); ++ ++ bfqd->root_group = bfq_create_group_hierarchy(bfqd, q->node); ++ if (!bfqd->root_group) ++ goto out_free; ++ bfq_init_root_group(bfqd->root_group, bfqd); ++ bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group); ++ ++ hrtimer_init(&bfqd->idle_slice_timer, CLOCK_MONOTONIC, ++ HRTIMER_MODE_REL); ++ bfqd->idle_slice_timer.function = bfq_idle_slice_timer; ++ ++ bfqd->queue_weights_tree = RB_ROOT; ++ bfqd->group_weights_tree = RB_ROOT; ++ ++ INIT_WORK(&bfqd->unplug_work, bfq_kick_queue); ++ ++ INIT_LIST_HEAD(&bfqd->active_list); ++ INIT_LIST_HEAD(&bfqd->idle_list); ++ INIT_HLIST_HEAD(&bfqd->burst_list); ++ ++ bfqd->hw_tag = -1; ++ ++ bfqd->bfq_max_budget = bfq_default_max_budget; ++ ++ bfqd->bfq_fifo_expire[0] = bfq_fifo_expire[0]; ++ bfqd->bfq_fifo_expire[1] = bfq_fifo_expire[1]; ++ bfqd->bfq_back_max = bfq_back_max; ++ bfqd->bfq_back_penalty = bfq_back_penalty; ++ bfqd->bfq_slice_idle = bfq_slice_idle; ++ bfqd->bfq_class_idle_last_service = 0; ++ bfqd->bfq_timeout = bfq_timeout; ++ ++ bfqd->bfq_requests_within_timer = 120; ++ ++ bfqd->bfq_large_burst_thresh = 8; ++ bfqd->bfq_burst_interval = msecs_to_jiffies(180); ++ ++ bfqd->low_latency = true; ++ ++ /* ++ * Trade-off between responsiveness and fairness. ++ */ ++ bfqd->bfq_wr_coeff = 30; ++ bfqd->bfq_wr_rt_max_time = msecs_to_jiffies(300); ++ bfqd->bfq_wr_max_time = 0; ++ bfqd->bfq_wr_min_idle_time = msecs_to_jiffies(2000); ++ bfqd->bfq_wr_min_inter_arr_async = msecs_to_jiffies(500); ++ bfqd->bfq_wr_max_softrt_rate = 7000; /* ++ * Approximate rate required ++ * to playback or record a ++ * high-definition compressed ++ * video. ++ */ ++ bfqd->wr_busy_queues = 0; ++ ++ /* ++ * Begin by assuming, optimistically, that the device is a ++ * high-speed one, and that its peak rate is equal to 2/3 of ++ * the highest reference rate. ++ */ ++ bfqd->RT_prod = R_fast[blk_queue_nonrot(bfqd->queue)] * ++ T_fast[blk_queue_nonrot(bfqd->queue)]; ++ bfqd->peak_rate = R_fast[blk_queue_nonrot(bfqd->queue)] * 2 / 3; ++ bfqd->device_speed = BFQ_BFQD_FAST; ++ ++ return 0; ++ ++out_free: ++ kfree(bfqd); ++ kobject_put(&eq->kobj); ++ return -ENOMEM; ++} ++ ++static void bfq_slab_kill(void) ++{ ++ kmem_cache_destroy(bfq_pool); ++} ++ ++static int __init bfq_slab_setup(void) ++{ ++ bfq_pool = KMEM_CACHE(bfq_queue, 0); ++ if (!bfq_pool) ++ return -ENOMEM; ++ return 0; ++} ++ ++static ssize_t bfq_var_show(unsigned int var, char *page) ++{ ++ return sprintf(page, "%u\n", var); ++} ++ ++static ssize_t bfq_var_store(unsigned long *var, const char *page, ++ size_t count) ++{ ++ unsigned long new_val; ++ int ret = kstrtoul(page, 10, &new_val); ++ ++ if (ret == 0) ++ *var = new_val; ++ ++ return count; ++} ++ ++static ssize_t bfq_wr_max_time_show(struct elevator_queue *e, char *page) ++{ ++ struct bfq_data *bfqd = e->elevator_data; ++ ++ return sprintf(page, "%d\n", bfqd->bfq_wr_max_time > 0 ? ++ jiffies_to_msecs(bfqd->bfq_wr_max_time) : ++ jiffies_to_msecs(bfq_wr_duration(bfqd))); ++} ++ ++static ssize_t bfq_weights_show(struct elevator_queue *e, char *page) ++{ ++ struct bfq_queue *bfqq; ++ struct bfq_data *bfqd = e->elevator_data; ++ ssize_t num_char = 0; ++ ++ num_char += sprintf(page + num_char, "Tot reqs queued %d\n\n", ++ bfqd->queued); ++ ++ spin_lock_irq(bfqd->queue->queue_lock); ++ ++ num_char += sprintf(page + num_char, "Active:\n"); ++ list_for_each_entry(bfqq, &bfqd->active_list, bfqq_list) { ++ num_char += sprintf(page + num_char, ++ "pid%d: weight %hu, nr_queued %d %d, ", ++ bfqq->pid, ++ bfqq->entity.weight, ++ bfqq->queued[0], ++ bfqq->queued[1]); ++ num_char += sprintf(page + num_char, ++ "dur %d/%u\n", ++ jiffies_to_msecs( ++ jiffies - ++ bfqq->last_wr_start_finish), ++ jiffies_to_msecs(bfqq->wr_cur_max_time)); ++ } ++ ++ num_char += sprintf(page + num_char, "Idle:\n"); ++ list_for_each_entry(bfqq, &bfqd->idle_list, bfqq_list) { ++ num_char += sprintf(page + num_char, ++ "pid%d: weight %hu, dur %d/%u\n", ++ bfqq->pid, ++ bfqq->entity.weight, ++ jiffies_to_msecs(jiffies - ++ bfqq->last_wr_start_finish), ++ jiffies_to_msecs(bfqq->wr_cur_max_time)); ++ } ++ ++ spin_unlock_irq(bfqd->queue->queue_lock); ++ ++ return num_char; ++} ++ ++#define SHOW_FUNCTION(__FUNC, __VAR, __CONV) \ ++static ssize_t __FUNC(struct elevator_queue *e, char *page) \ ++{ \ ++ struct bfq_data *bfqd = e->elevator_data; \ ++ u64 __data = __VAR; \ ++ if (__CONV == 1) \ ++ __data = jiffies_to_msecs(__data); \ ++ else if (__CONV == 2) \ ++ __data = div_u64(__data, NSEC_PER_MSEC); \ ++ return bfq_var_show(__data, (page)); \ ++} ++SHOW_FUNCTION(bfq_fifo_expire_sync_show, bfqd->bfq_fifo_expire[1], 2); ++SHOW_FUNCTION(bfq_fifo_expire_async_show, bfqd->bfq_fifo_expire[0], 2); ++SHOW_FUNCTION(bfq_back_seek_max_show, bfqd->bfq_back_max, 0); ++SHOW_FUNCTION(bfq_back_seek_penalty_show, bfqd->bfq_back_penalty, 0); ++SHOW_FUNCTION(bfq_slice_idle_show, bfqd->bfq_slice_idle, 2); ++SHOW_FUNCTION(bfq_max_budget_show, bfqd->bfq_user_max_budget, 0); ++SHOW_FUNCTION(bfq_timeout_sync_show, bfqd->bfq_timeout, 1); ++SHOW_FUNCTION(bfq_strict_guarantees_show, bfqd->strict_guarantees, 0); ++SHOW_FUNCTION(bfq_low_latency_show, bfqd->low_latency, 0); ++SHOW_FUNCTION(bfq_wr_coeff_show, bfqd->bfq_wr_coeff, 0); ++SHOW_FUNCTION(bfq_wr_rt_max_time_show, bfqd->bfq_wr_rt_max_time, 1); ++SHOW_FUNCTION(bfq_wr_min_idle_time_show, bfqd->bfq_wr_min_idle_time, 1); ++SHOW_FUNCTION(bfq_wr_min_inter_arr_async_show, bfqd->bfq_wr_min_inter_arr_async, ++ 1); ++SHOW_FUNCTION(bfq_wr_max_softrt_rate_show, bfqd->bfq_wr_max_softrt_rate, 0); ++#undef SHOW_FUNCTION ++ ++#define USEC_SHOW_FUNCTION(__FUNC, __VAR) \ ++static ssize_t __FUNC(struct elevator_queue *e, char *page) \ ++{ \ ++ struct bfq_data *bfqd = e->elevator_data; \ ++ u64 __data = __VAR; \ ++ __data = div_u64(__data, NSEC_PER_USEC); \ ++ return bfq_var_show(__data, (page)); \ ++} ++USEC_SHOW_FUNCTION(bfq_slice_idle_us_show, bfqd->bfq_slice_idle); ++#undef USEC_SHOW_FUNCTION ++ ++#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ ++static ssize_t \ ++__FUNC(struct elevator_queue *e, const char *page, size_t count) \ ++{ \ ++ struct bfq_data *bfqd = e->elevator_data; \ ++ unsigned long uninitialized_var(__data); \ ++ int ret = bfq_var_store(&__data, (page), count); \ ++ if (__data < (MIN)) \ ++ __data = (MIN); \ ++ else if (__data > (MAX)) \ ++ __data = (MAX); \ ++ if (__CONV == 1) \ ++ *(__PTR) = msecs_to_jiffies(__data); \ ++ else if (__CONV == 2) \ ++ *(__PTR) = (u64)__data * NSEC_PER_MSEC; \ ++ else \ ++ *(__PTR) = __data; \ ++ return ret; \ ++} ++STORE_FUNCTION(bfq_fifo_expire_sync_store, &bfqd->bfq_fifo_expire[1], 1, ++ INT_MAX, 2); ++STORE_FUNCTION(bfq_fifo_expire_async_store, &bfqd->bfq_fifo_expire[0], 1, ++ INT_MAX, 2); ++STORE_FUNCTION(bfq_back_seek_max_store, &bfqd->bfq_back_max, 0, INT_MAX, 0); ++STORE_FUNCTION(bfq_back_seek_penalty_store, &bfqd->bfq_back_penalty, 1, ++ INT_MAX, 0); ++STORE_FUNCTION(bfq_slice_idle_store, &bfqd->bfq_slice_idle, 0, INT_MAX, 2); ++STORE_FUNCTION(bfq_wr_coeff_store, &bfqd->bfq_wr_coeff, 1, INT_MAX, 0); ++STORE_FUNCTION(bfq_wr_max_time_store, &bfqd->bfq_wr_max_time, 0, INT_MAX, 1); ++STORE_FUNCTION(bfq_wr_rt_max_time_store, &bfqd->bfq_wr_rt_max_time, 0, INT_MAX, ++ 1); ++STORE_FUNCTION(bfq_wr_min_idle_time_store, &bfqd->bfq_wr_min_idle_time, 0, ++ INT_MAX, 1); ++STORE_FUNCTION(bfq_wr_min_inter_arr_async_store, ++ &bfqd->bfq_wr_min_inter_arr_async, 0, INT_MAX, 1); ++STORE_FUNCTION(bfq_wr_max_softrt_rate_store, &bfqd->bfq_wr_max_softrt_rate, 0, ++ INT_MAX, 0); ++#undef STORE_FUNCTION ++ ++#define USEC_STORE_FUNCTION(__FUNC, __PTR, MIN, MAX) \ ++static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)\ ++{ \ ++ struct bfq_data *bfqd = e->elevator_data; \ ++ unsigned long __data; \ ++ int ret = bfq_var_store(&__data, (page), count); \ ++ if (__data < (MIN)) \ ++ __data = (MIN); \ ++ else if (__data > (MAX)) \ ++ __data = (MAX); \ ++ *(__PTR) = (u64)__data * NSEC_PER_USEC; \ ++ return ret; \ ++} ++USEC_STORE_FUNCTION(bfq_slice_idle_us_store, &bfqd->bfq_slice_idle, 0, ++ UINT_MAX); ++#undef USEC_STORE_FUNCTION ++ ++/* do nothing for the moment */ ++static ssize_t bfq_weights_store(struct elevator_queue *e, ++ const char *page, size_t count) ++{ ++ return count; ++} ++ ++static ssize_t bfq_max_budget_store(struct elevator_queue *e, ++ const char *page, size_t count) ++{ ++ struct bfq_data *bfqd = e->elevator_data; ++ unsigned long uninitialized_var(__data); ++ int ret = bfq_var_store(&__data, (page), count); ++ ++ if (__data == 0) ++ bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd); ++ else { ++ if (__data > INT_MAX) ++ __data = INT_MAX; ++ bfqd->bfq_max_budget = __data; ++ } ++ ++ bfqd->bfq_user_max_budget = __data; ++ ++ return ret; ++} ++ ++/* ++ * Leaving this name to preserve name compatibility with cfq ++ * parameters, but this timeout is used for both sync and async. ++ */ ++static ssize_t bfq_timeout_sync_store(struct elevator_queue *e, ++ const char *page, size_t count) ++{ ++ struct bfq_data *bfqd = e->elevator_data; ++ unsigned long uninitialized_var(__data); ++ int ret = bfq_var_store(&__data, (page), count); ++ ++ if (__data < 1) ++ __data = 1; ++ else if (__data > INT_MAX) ++ __data = INT_MAX; ++ ++ bfqd->bfq_timeout = msecs_to_jiffies(__data); ++ if (bfqd->bfq_user_max_budget == 0) ++ bfqd->bfq_max_budget = bfq_calc_max_budget(bfqd); ++ ++ return ret; ++} ++ ++static ssize_t bfq_strict_guarantees_store(struct elevator_queue *e, ++ const char *page, size_t count) ++{ ++ struct bfq_data *bfqd = e->elevator_data; ++ unsigned long uninitialized_var(__data); ++ int ret = bfq_var_store(&__data, (page), count); ++ ++ if (__data > 1) ++ __data = 1; ++ if (!bfqd->strict_guarantees && __data == 1 ++ && bfqd->bfq_slice_idle < 8 * NSEC_PER_MSEC) ++ bfqd->bfq_slice_idle = 8 * NSEC_PER_MSEC; ++ ++ bfqd->strict_guarantees = __data; ++ ++ return ret; ++} ++ ++static ssize_t bfq_low_latency_store(struct elevator_queue *e, ++ const char *page, size_t count) ++{ ++ struct bfq_data *bfqd = e->elevator_data; ++ unsigned long uninitialized_var(__data); ++ int ret = bfq_var_store(&__data, (page), count); ++ ++ if (__data > 1) ++ __data = 1; ++ if (__data == 0 && bfqd->low_latency != 0) ++ bfq_end_wr(bfqd); ++ bfqd->low_latency = __data; ++ ++ return ret; ++} ++ ++#define BFQ_ATTR(name) \ ++ __ATTR(name, S_IRUGO|S_IWUSR, bfq_##name##_show, bfq_##name##_store) ++ ++static struct elv_fs_entry bfq_attrs[] = { ++ BFQ_ATTR(fifo_expire_sync), ++ BFQ_ATTR(fifo_expire_async), ++ BFQ_ATTR(back_seek_max), ++ BFQ_ATTR(back_seek_penalty), ++ BFQ_ATTR(slice_idle), ++ BFQ_ATTR(slice_idle_us), ++ BFQ_ATTR(max_budget), ++ BFQ_ATTR(timeout_sync), ++ BFQ_ATTR(strict_guarantees), ++ BFQ_ATTR(low_latency), ++ BFQ_ATTR(wr_coeff), ++ BFQ_ATTR(wr_max_time), ++ BFQ_ATTR(wr_rt_max_time), ++ BFQ_ATTR(wr_min_idle_time), ++ BFQ_ATTR(wr_min_inter_arr_async), ++ BFQ_ATTR(wr_max_softrt_rate), ++ BFQ_ATTR(weights), ++ __ATTR_NULL ++}; ++ ++static struct elevator_type iosched_bfq = { ++ .ops = { ++ .elevator_merge_fn = bfq_merge, ++ .elevator_merged_fn = bfq_merged_request, ++ .elevator_merge_req_fn = bfq_merged_requests, ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ .elevator_bio_merged_fn = bfq_bio_merged, ++#endif ++ .elevator_allow_bio_merge_fn = bfq_allow_bio_merge, ++ .elevator_allow_rq_merge_fn = bfq_allow_rq_merge, ++ .elevator_dispatch_fn = bfq_dispatch_requests, ++ .elevator_add_req_fn = bfq_insert_request, ++ .elevator_activate_req_fn = bfq_activate_request, ++ .elevator_deactivate_req_fn = bfq_deactivate_request, ++ .elevator_completed_req_fn = bfq_completed_request, ++ .elevator_former_req_fn = elv_rb_former_request, ++ .elevator_latter_req_fn = elv_rb_latter_request, ++ .elevator_init_icq_fn = bfq_init_icq, ++ .elevator_exit_icq_fn = bfq_exit_icq, ++ .elevator_set_req_fn = bfq_set_request, ++ .elevator_put_req_fn = bfq_put_request, ++ .elevator_may_queue_fn = bfq_may_queue, ++ .elevator_init_fn = bfq_init_queue, ++ .elevator_exit_fn = bfq_exit_queue, ++ }, ++ .icq_size = sizeof(struct bfq_io_cq), ++ .icq_align = __alignof__(struct bfq_io_cq), ++ .elevator_attrs = bfq_attrs, ++ .elevator_name = "bfq", ++ .elevator_owner = THIS_MODULE, ++}; ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++static struct blkcg_policy blkcg_policy_bfq = { ++ .dfl_cftypes = bfq_blkg_files, ++ .legacy_cftypes = bfq_blkcg_legacy_files, ++ ++ .cpd_alloc_fn = bfq_cpd_alloc, ++ .cpd_init_fn = bfq_cpd_init, ++ .cpd_bind_fn = bfq_cpd_init, ++ .cpd_free_fn = bfq_cpd_free, ++ ++ .pd_alloc_fn = bfq_pd_alloc, ++ .pd_init_fn = bfq_pd_init, ++ .pd_offline_fn = bfq_pd_offline, ++ .pd_free_fn = bfq_pd_free, ++ .pd_reset_stats_fn = bfq_pd_reset_stats, ++}; ++#endif ++ ++static int __init bfq_init(void) ++{ ++ int ret; ++ char msg[50] = "BFQ I/O-scheduler: v8r4"; ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ ret = blkcg_policy_register(&blkcg_policy_bfq); ++ if (ret) ++ return ret; ++#endif ++ ++ ret = -ENOMEM; ++ if (bfq_slab_setup()) ++ goto err_pol_unreg; ++ ++ /* ++ * Times to load large popular applications for the typical ++ * systems installed on the reference devices (see the ++ * comments before the definitions of the next two ++ * arrays). Actually, we use slightly slower values, as the ++ * estimated peak rate tends to be smaller than the actual ++ * peak rate. The reason for this last fact is that estimates ++ * are computed over much shorter time intervals than the long ++ * intervals typically used for benchmarking. Why? First, to ++ * adapt more quickly to variations. Second, because an I/O ++ * scheduler cannot rely on a peak-rate-evaluation workload to ++ * be run for a long time. ++ */ ++ T_slow[0] = msecs_to_jiffies(3500); /* actually 4 sec */ ++ T_slow[1] = msecs_to_jiffies(1000); /* actually 1.5 sec */ ++ T_fast[0] = msecs_to_jiffies(7000); /* actually 8 sec */ ++ T_fast[1] = msecs_to_jiffies(2500); /* actually 3 sec */ ++ ++ /* ++ * Thresholds that determine the switch between speed classes ++ * (see the comments before the definition of the array ++ * device_speed_thresh). These thresholds are biased towards ++ * transitions to the fast class. This is safer than the ++ * opposite bias. In fact, a wrong transition to the slow ++ * class results in short weight-raising periods, because the ++ * speed of the device then tends to be higher that the ++ * reference peak rate. On the opposite end, a wrong ++ * transition to the fast class tends to increase ++ * weight-raising periods, because of the opposite reason. ++ */ ++ device_speed_thresh[0] = (4 * R_slow[0]) / 3; ++ device_speed_thresh[1] = (4 * R_slow[1]) / 3; ++ ++ ret = elv_register(&iosched_bfq); ++ if (ret) ++ goto err_pol_unreg; ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ strcat(msg, " (with cgroups support)"); ++#endif ++ pr_info("%s", msg); ++ ++ return 0; ++ ++err_pol_unreg: ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ blkcg_policy_unregister(&blkcg_policy_bfq); ++#endif ++ return ret; ++} ++ ++static void __exit bfq_exit(void) ++{ ++ elv_unregister(&iosched_bfq); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ blkcg_policy_unregister(&blkcg_policy_bfq); ++#endif ++ bfq_slab_kill(); ++} ++ ++module_init(bfq_init); ++module_exit(bfq_exit); ++ ++MODULE_AUTHOR("Arianna Avanzini, Fabio Checconi, Paolo Valente"); ++MODULE_LICENSE("GPL"); +diff -w -uNr '--exclude=.git' linux-4.8/block/bfq-sched.c linux-4.8-bfq/block/bfq-sched.c +--- linux-4.8/block/bfq-sched.c 1970-01-01 01:00:00.000000000 +0100 ++++ linux-4.8-bfq/block/bfq-sched.c 2016-10-18 12:57:57.691164881 +0200 +@@ -0,0 +1,1501 @@ ++/* ++ * BFQ: Hierarchical B-WF2Q+ scheduler. ++ * ++ * Based on ideas and code from CFQ: ++ * Copyright (C) 2003 Jens Axboe ++ * ++ * Copyright (C) 2008 Fabio Checconi ++ * Paolo Valente ++ * ++ * Copyright (C) 2015 Paolo Valente ++ * ++ * Copyright (C) 2016 Paolo Valente ++ */ ++ ++static struct bfq_group *bfqq_group(struct bfq_queue *bfqq); ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++#define for_each_entity(entity) \ ++ for (; entity ; entity = entity->parent) ++ ++#define for_each_entity_safe(entity, parent) \ ++ for (; entity && ({ parent = entity->parent; 1; }); entity = parent) ++ ++ ++static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd, ++ int extract, ++ struct bfq_data *bfqd); ++ ++static void bfq_update_budget(struct bfq_entity *next_in_service) ++{ ++ struct bfq_entity *bfqg_entity; ++ struct bfq_group *bfqg; ++ struct bfq_sched_data *group_sd; ++ ++ BUG_ON(!next_in_service); ++ ++ group_sd = next_in_service->sched_data; ++ ++ bfqg = container_of(group_sd, struct bfq_group, sched_data); ++ /* ++ * bfq_group's my_entity field is not NULL only if the group ++ * is not the root group. We must not touch the root entity ++ * as it must never become an in-service entity. ++ */ ++ bfqg_entity = bfqg->my_entity; ++ if (bfqg_entity) ++ bfqg_entity->budget = next_in_service->budget; ++} ++ ++static int bfq_update_next_in_service(struct bfq_sched_data *sd) ++{ ++ struct bfq_entity *next_in_service; ++ struct bfq_queue *bfqq; ++ ++ if (sd->in_service_entity) ++ /* will update/requeue at the end of service */ ++ return 0; ++ ++ /* ++ * NOTE: this can be improved in many ways, such as returning ++ * 1 (and thus propagating upwards the update) only when the ++ * budget changes, or caching the bfqq that will be scheduled ++ * next from this subtree. By now we worry more about ++ * correctness than about performance... ++ */ ++ next_in_service = bfq_lookup_next_entity(sd, 0, NULL); ++ sd->next_in_service = next_in_service; ++ ++ if (next_in_service) ++ bfq_update_budget(next_in_service); ++ else ++ goto exit; ++ ++ bfqq = bfq_entity_to_bfqq(next_in_service); ++ if (bfqq) ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "update_next_in_service: chosen this queue"); ++ else { ++ struct bfq_group *bfqg = ++ container_of(next_in_service, ++ struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "update_next_in_service: chosen this entity"); ++ } ++exit: ++ return 1; ++} ++ ++static void bfq_check_next_in_service(struct bfq_sched_data *sd, ++ struct bfq_entity *entity) ++{ ++ WARN_ON(sd->next_in_service != entity); ++} ++#else ++#define for_each_entity(entity) \ ++ for (; entity ; entity = NULL) ++ ++#define for_each_entity_safe(entity, parent) \ ++ for (parent = NULL; entity ; entity = parent) ++ ++static int bfq_update_next_in_service(struct bfq_sched_data *sd) ++{ ++ return 0; ++} ++ ++static void bfq_check_next_in_service(struct bfq_sched_data *sd, ++ struct bfq_entity *entity) ++{ ++} ++ ++static void bfq_update_budget(struct bfq_entity *next_in_service) ++{ ++} ++#endif ++ ++/* ++ * Shift for timestamp calculations. This actually limits the maximum ++ * service allowed in one timestamp delta (small shift values increase it), ++ * the maximum total weight that can be used for the queues in the system ++ * (big shift values increase it), and the period of virtual time ++ * wraparounds. ++ */ ++#define WFQ_SERVICE_SHIFT 22 ++ ++/** ++ * bfq_gt - compare two timestamps. ++ * @a: first ts. ++ * @b: second ts. ++ * ++ * Return @a > @b, dealing with wrapping correctly. ++ */ ++static int bfq_gt(u64 a, u64 b) ++{ ++ return (s64)(a - b) > 0; ++} ++ ++static struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = NULL; ++ ++ BUG_ON(!entity); ++ ++ if (!entity->my_sched_data) ++ bfqq = container_of(entity, struct bfq_queue, entity); ++ ++ return bfqq; ++} ++ ++ ++/** ++ * bfq_delta - map service into the virtual time domain. ++ * @service: amount of service. ++ * @weight: scale factor (weight of an entity or weight sum). ++ */ ++static u64 bfq_delta(unsigned long service, unsigned long weight) ++{ ++ u64 d = (u64)service << WFQ_SERVICE_SHIFT; ++ ++ do_div(d, weight); ++ return d; ++} ++ ++/** ++ * bfq_calc_finish - assign the finish time to an entity. ++ * @entity: the entity to act upon. ++ * @service: the service to be charged to the entity. ++ */ ++static void bfq_calc_finish(struct bfq_entity *entity, unsigned long service) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ unsigned long long start, finish, delta; ++ ++ BUG_ON(entity->weight == 0); ++ ++ entity->finish = entity->start + ++ bfq_delta(service, entity->weight); ++ ++ start = ((entity->start>>10)*1000)>>12; ++ finish = ((entity->finish>>10)*1000)>>12; ++ delta = ((bfq_delta(service, entity->weight)>>10)*1000)>>12; ++ ++ if (bfqq) { ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "calc_finish: serv %lu, w %d", ++ service, entity->weight); ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "calc_finish: start %llu, finish %llu, delta %llu", ++ start, finish, delta); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ } else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "calc_finish group: serv %lu, w %d", ++ service, entity->weight); ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "calc_finish group: start %llu, finish %llu, delta %llu", ++ start, finish, delta); ++#endif ++ } ++} ++ ++/** ++ * bfq_entity_of - get an entity from a node. ++ * @node: the node field of the entity. ++ * ++ * Convert a node pointer to the relative entity. This is used only ++ * to simplify the logic of some functions and not as the generic ++ * conversion mechanism because, e.g., in the tree walking functions, ++ * the check for a %NULL value would be redundant. ++ */ ++static struct bfq_entity *bfq_entity_of(struct rb_node *node) ++{ ++ struct bfq_entity *entity = NULL; ++ ++ if (node) ++ entity = rb_entry(node, struct bfq_entity, rb_node); ++ ++ return entity; ++} ++ ++/** ++ * bfq_extract - remove an entity from a tree. ++ * @root: the tree root. ++ * @entity: the entity to remove. ++ */ ++static void bfq_extract(struct rb_root *root, struct bfq_entity *entity) ++{ ++ BUG_ON(entity->tree != root); ++ ++ entity->tree = NULL; ++ rb_erase(&entity->rb_node, root); ++} ++ ++/** ++ * bfq_idle_extract - extract an entity from the idle tree. ++ * @st: the service tree of the owning @entity. ++ * @entity: the entity being removed. ++ */ ++static void bfq_idle_extract(struct bfq_service_tree *st, ++ struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ struct rb_node *next; ++ ++ BUG_ON(entity->tree != &st->idle); ++ ++ if (entity == st->first_idle) { ++ next = rb_next(&entity->rb_node); ++ st->first_idle = bfq_entity_of(next); ++ } ++ ++ if (entity == st->last_idle) { ++ next = rb_prev(&entity->rb_node); ++ st->last_idle = bfq_entity_of(next); ++ } ++ ++ bfq_extract(&st->idle, entity); ++ ++ if (bfqq) ++ list_del(&bfqq->bfqq_list); ++} ++ ++/** ++ * bfq_insert - generic tree insertion. ++ * @root: tree root. ++ * @entity: entity to insert. ++ * ++ * This is used for the idle and the active tree, since they are both ++ * ordered by finish time. ++ */ ++static void bfq_insert(struct rb_root *root, struct bfq_entity *entity) ++{ ++ struct bfq_entity *entry; ++ struct rb_node **node = &root->rb_node; ++ struct rb_node *parent = NULL; ++ ++ BUG_ON(entity->tree); ++ ++ while (*node) { ++ parent = *node; ++ entry = rb_entry(parent, struct bfq_entity, rb_node); ++ ++ if (bfq_gt(entry->finish, entity->finish)) ++ node = &parent->rb_left; ++ else ++ node = &parent->rb_right; ++ } ++ ++ rb_link_node(&entity->rb_node, parent, node); ++ rb_insert_color(&entity->rb_node, root); ++ ++ entity->tree = root; ++} ++ ++/** ++ * bfq_update_min - update the min_start field of a entity. ++ * @entity: the entity to update. ++ * @node: one of its children. ++ * ++ * This function is called when @entity may store an invalid value for ++ * min_start due to updates to the active tree. The function assumes ++ * that the subtree rooted at @node (which may be its left or its right ++ * child) has a valid min_start value. ++ */ ++static void bfq_update_min(struct bfq_entity *entity, struct rb_node *node) ++{ ++ struct bfq_entity *child; ++ ++ if (node) { ++ child = rb_entry(node, struct bfq_entity, rb_node); ++ if (bfq_gt(entity->min_start, child->min_start)) ++ entity->min_start = child->min_start; ++ } ++} ++ ++/** ++ * bfq_update_active_node - recalculate min_start. ++ * @node: the node to update. ++ * ++ * @node may have changed position or one of its children may have moved, ++ * this function updates its min_start value. The left and right subtrees ++ * are assumed to hold a correct min_start value. ++ */ ++static void bfq_update_active_node(struct rb_node *node) ++{ ++ struct bfq_entity *entity = rb_entry(node, struct bfq_entity, rb_node); ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ ++ entity->min_start = entity->start; ++ bfq_update_min(entity, node->rb_right); ++ bfq_update_min(entity, node->rb_left); ++ ++ if (bfqq) { ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "update_active_node: new min_start %llu", ++ ((entity->min_start>>10)*1000)>>12); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ } else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "update_active_node: new min_start %llu", ++ ((entity->min_start>>10)*1000)>>12); ++#endif ++ } ++} ++ ++/** ++ * bfq_update_active_tree - update min_start for the whole active tree. ++ * @node: the starting node. ++ * ++ * @node must be the deepest modified node after an update. This function ++ * updates its min_start using the values held by its children, assuming ++ * that they did not change, and then updates all the nodes that may have ++ * changed in the path to the root. The only nodes that may have changed ++ * are the ones in the path or their siblings. ++ */ ++static void bfq_update_active_tree(struct rb_node *node) ++{ ++ struct rb_node *parent; ++ ++up: ++ bfq_update_active_node(node); ++ ++ parent = rb_parent(node); ++ if (!parent) ++ return; ++ ++ if (node == parent->rb_left && parent->rb_right) ++ bfq_update_active_node(parent->rb_right); ++ else if (parent->rb_left) ++ bfq_update_active_node(parent->rb_left); ++ ++ node = parent; ++ goto up; ++} ++ ++static void bfq_weights_tree_add(struct bfq_data *bfqd, ++ struct bfq_entity *entity, ++ struct rb_root *root); ++ ++static void bfq_weights_tree_remove(struct bfq_data *bfqd, ++ struct bfq_entity *entity, ++ struct rb_root *root); ++ ++ ++/** ++ * bfq_active_insert - insert an entity in the active tree of its ++ * group/device. ++ * @st: the service tree of the entity. ++ * @entity: the entity being inserted. ++ * ++ * The active tree is ordered by finish time, but an extra key is kept ++ * per each node, containing the minimum value for the start times of ++ * its children (and the node itself), so it's possible to search for ++ * the eligible node with the lowest finish time in logarithmic time. ++ */ ++static void bfq_active_insert(struct bfq_service_tree *st, ++ struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ struct rb_node *node = &entity->rb_node; ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ struct bfq_sched_data *sd = NULL; ++ struct bfq_group *bfqg = NULL; ++ struct bfq_data *bfqd = NULL; ++#endif ++ ++ bfq_insert(&st->active, entity); ++ ++ if (node->rb_left) ++ node = node->rb_left; ++ else if (node->rb_right) ++ node = node->rb_right; ++ ++ bfq_update_active_tree(node); ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ sd = entity->sched_data; ++ bfqg = container_of(sd, struct bfq_group, sched_data); ++ BUG_ON(!bfqg); ++ bfqd = (struct bfq_data *)bfqg->bfqd; ++#endif ++ if (bfqq) ++ list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { /* bfq_group */ ++ BUG_ON(!bfqd); ++ bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree); ++ } ++ if (bfqg != bfqd->root_group) { ++ BUG_ON(!bfqg); ++ BUG_ON(!bfqd); ++ bfqg->active_entities++; ++ } ++#endif ++} ++ ++/** ++ * bfq_ioprio_to_weight - calc a weight from an ioprio. ++ * @ioprio: the ioprio value to convert. ++ */ ++static unsigned short bfq_ioprio_to_weight(int ioprio) ++{ ++ BUG_ON(ioprio < 0 || ioprio >= IOPRIO_BE_NR); ++ return (IOPRIO_BE_NR - ioprio) * BFQ_WEIGHT_CONVERSION_COEFF; ++} ++ ++/** ++ * bfq_weight_to_ioprio - calc an ioprio from a weight. ++ * @weight: the weight value to convert. ++ * ++ * To preserve as much as possible the old only-ioprio user interface, ++ * 0 is used as an escape ioprio value for weights (numerically) equal or ++ * larger than IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF. ++ */ ++static unsigned short bfq_weight_to_ioprio(int weight) ++{ ++ BUG_ON(weight < BFQ_MIN_WEIGHT || weight > BFQ_MAX_WEIGHT); ++ return IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight < 0 ? ++ 0 : IOPRIO_BE_NR * BFQ_WEIGHT_CONVERSION_COEFF - weight; ++} ++ ++static void bfq_get_entity(struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ ++ if (bfqq) { ++ bfqq->ref++; ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "get_entity: %p %d", ++ bfqq, bfqq->ref); ++ } ++} ++ ++/** ++ * bfq_find_deepest - find the deepest node that an extraction can modify. ++ * @node: the node being removed. ++ * ++ * Do the first step of an extraction in an rb tree, looking for the ++ * node that will replace @node, and returning the deepest node that ++ * the following modifications to the tree can touch. If @node is the ++ * last node in the tree return %NULL. ++ */ ++static struct rb_node *bfq_find_deepest(struct rb_node *node) ++{ ++ struct rb_node *deepest; ++ ++ if (!node->rb_right && !node->rb_left) ++ deepest = rb_parent(node); ++ else if (!node->rb_right) ++ deepest = node->rb_left; ++ else if (!node->rb_left) ++ deepest = node->rb_right; ++ else { ++ deepest = rb_next(node); ++ if (deepest->rb_right) ++ deepest = deepest->rb_right; ++ else if (rb_parent(deepest) != node) ++ deepest = rb_parent(deepest); ++ } ++ ++ return deepest; ++} ++ ++/** ++ * bfq_active_extract - remove an entity from the active tree. ++ * @st: the service_tree containing the tree. ++ * @entity: the entity being removed. ++ */ ++static void bfq_active_extract(struct bfq_service_tree *st, ++ struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ struct rb_node *node; ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ struct bfq_sched_data *sd = NULL; ++ struct bfq_group *bfqg = NULL; ++ struct bfq_data *bfqd = NULL; ++#endif ++ ++ node = bfq_find_deepest(&entity->rb_node); ++ bfq_extract(&st->active, entity); ++ ++ if (node) ++ bfq_update_active_tree(node); ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ sd = entity->sched_data; ++ bfqg = container_of(sd, struct bfq_group, sched_data); ++ BUG_ON(!bfqg); ++ bfqd = (struct bfq_data *)bfqg->bfqd; ++#endif ++ if (bfqq) ++ list_del(&bfqq->bfqq_list); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { /* bfq_group */ ++ BUG_ON(!bfqd); ++ bfq_weights_tree_remove(bfqd, entity, ++ &bfqd->group_weights_tree); ++ } ++ if (bfqg != bfqd->root_group) { ++ BUG_ON(!bfqg); ++ BUG_ON(!bfqd); ++ BUG_ON(!bfqg->active_entities); ++ bfqg->active_entities--; ++ } ++#endif ++} ++ ++/** ++ * bfq_idle_insert - insert an entity into the idle tree. ++ * @st: the service tree containing the tree. ++ * @entity: the entity to insert. ++ */ ++static void bfq_idle_insert(struct bfq_service_tree *st, ++ struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ struct bfq_entity *first_idle = st->first_idle; ++ struct bfq_entity *last_idle = st->last_idle; ++ ++ if (!first_idle || bfq_gt(first_idle->finish, entity->finish)) ++ st->first_idle = entity; ++ if (!last_idle || bfq_gt(entity->finish, last_idle->finish)) ++ st->last_idle = entity; ++ ++ bfq_insert(&st->idle, entity); ++ ++ if (bfqq) ++ list_add(&bfqq->bfqq_list, &bfqq->bfqd->idle_list); ++} ++ ++/** ++ * bfq_forget_entity - remove an entity from the wfq trees. ++ * @st: the service tree. ++ * @entity: the entity being removed. ++ * ++ * Update the device status and forget everything about @entity, putting ++ * the device reference to it, if it is a queue. Entities belonging to ++ * groups are not refcounted. ++ */ ++static void bfq_forget_entity(struct bfq_service_tree *st, ++ struct bfq_entity *entity) ++{ ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ struct bfq_sched_data *sd; ++ ++ BUG_ON(!entity->on_st); ++ ++ entity->on_st = 0; ++ st->wsum -= entity->weight; ++ if (bfqq) { ++ sd = entity->sched_data; ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "forget_entity: %p %d", ++ bfqq, bfqq->ref); ++ bfq_put_queue(bfqq); ++ } ++} ++ ++/** ++ * bfq_put_idle_entity - release the idle tree ref of an entity. ++ * @st: service tree for the entity. ++ * @entity: the entity being released. ++ */ ++static void bfq_put_idle_entity(struct bfq_service_tree *st, ++ struct bfq_entity *entity) ++{ ++ bfq_idle_extract(st, entity); ++ bfq_forget_entity(st, entity); ++} ++ ++/** ++ * bfq_forget_idle - update the idle tree if necessary. ++ * @st: the service tree to act upon. ++ * ++ * To preserve the global O(log N) complexity we only remove one entry here; ++ * as the idle tree will not grow indefinitely this can be done safely. ++ */ ++static void bfq_forget_idle(struct bfq_service_tree *st) ++{ ++ struct bfq_entity *first_idle = st->first_idle; ++ struct bfq_entity *last_idle = st->last_idle; ++ ++ if (RB_EMPTY_ROOT(&st->active) && last_idle && ++ !bfq_gt(last_idle->finish, st->vtime)) { ++ /* ++ * Forget the whole idle tree, increasing the vtime past ++ * the last finish time of idle entities. ++ */ ++ st->vtime = last_idle->finish; ++ } ++ ++ if (first_idle && !bfq_gt(first_idle->finish, st->vtime)) ++ bfq_put_idle_entity(st, first_idle); ++} ++ ++static struct bfq_service_tree * ++__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st, ++ struct bfq_entity *entity) ++{ ++ struct bfq_service_tree *new_st = old_st; ++ ++ if (entity->prio_changed) { ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ unsigned int prev_weight, new_weight; ++ struct bfq_data *bfqd = NULL; ++ struct rb_root *root; ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ struct bfq_sched_data *sd; ++ struct bfq_group *bfqg; ++#endif ++ ++ if (bfqq) ++ bfqd = bfqq->bfqd; ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ sd = entity->my_sched_data; ++ bfqg = container_of(sd, struct bfq_group, sched_data); ++ BUG_ON(!bfqg); ++ bfqd = (struct bfq_data *)bfqg->bfqd; ++ BUG_ON(!bfqd); ++ } ++#endif ++ ++ BUG_ON(old_st->wsum < entity->weight); ++ old_st->wsum -= entity->weight; ++ ++ if (entity->new_weight != entity->orig_weight) { ++ if (entity->new_weight < BFQ_MIN_WEIGHT || ++ entity->new_weight > BFQ_MAX_WEIGHT) { ++ pr_crit("update_weight_prio: new_weight %d\n", ++ entity->new_weight); ++ if (entity->new_weight < BFQ_MIN_WEIGHT) ++ entity->new_weight = BFQ_MIN_WEIGHT; ++ else ++ entity->new_weight = BFQ_MAX_WEIGHT; ++ } ++ entity->orig_weight = entity->new_weight; ++ if (bfqq) ++ bfqq->ioprio = ++ bfq_weight_to_ioprio(entity->orig_weight); ++ } ++ ++ if (bfqq) ++ bfqq->ioprio_class = bfqq->new_ioprio_class; ++ entity->prio_changed = 0; ++ ++ /* ++ * NOTE: here we may be changing the weight too early, ++ * this will cause unfairness. The correct approach ++ * would have required additional complexity to defer ++ * weight changes to the proper time instants (i.e., ++ * when entity->finish <= old_st->vtime). ++ */ ++ new_st = bfq_entity_service_tree(entity); ++ ++ prev_weight = entity->weight; ++ new_weight = entity->orig_weight * ++ (bfqq ? bfqq->wr_coeff : 1); ++ /* ++ * If the weight of the entity changes, remove the entity ++ * from its old weight counter (if there is a counter ++ * associated with the entity), and add it to the counter ++ * associated with its new weight. ++ */ ++ if (prev_weight != new_weight) { ++ if (bfqq) ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "weight changed %d %d(%d %d)", ++ prev_weight, new_weight, ++ entity->orig_weight, ++ bfqq->wr_coeff); ++ ++ root = bfqq ? &bfqd->queue_weights_tree : ++ &bfqd->group_weights_tree; ++ bfq_weights_tree_remove(bfqd, entity, root); ++ } ++ entity->weight = new_weight; ++ /* ++ * Add the entity to its weights tree only if it is ++ * not associated with a weight-raised queue. ++ */ ++ if (prev_weight != new_weight && ++ (bfqq ? bfqq->wr_coeff == 1 : 1)) ++ /* If we get here, root has been initialized. */ ++ bfq_weights_tree_add(bfqd, entity, root); ++ ++ new_st->wsum += entity->weight; ++ ++ if (new_st != old_st) ++ entity->start = new_st->vtime; ++ } ++ ++ return new_st; ++} ++ ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++static void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg); ++#endif ++ ++/** ++ * bfq_bfqq_served - update the scheduler status after selection for ++ * service. ++ * @bfqq: the queue being served. ++ * @served: bytes to transfer. ++ * ++ * NOTE: this can be optimized, as the timestamps of upper level entities ++ * are synchronized every time a new bfqq is selected for service. By now, ++ * we keep it to better check consistency. ++ */ ++static void bfq_bfqq_served(struct bfq_queue *bfqq, int served) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ struct bfq_service_tree *st; ++ ++ for_each_entity(entity) { ++ st = bfq_entity_service_tree(entity); ++ ++ entity->service += served; ++ ++ BUG_ON(st->wsum == 0); ++ ++ st->vtime += bfq_delta(served, st->wsum); ++ bfq_forget_idle(st); ++ } ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ bfqg_stats_set_start_empty_time(bfqq_group(bfqq)); ++#endif ++ st = bfq_entity_service_tree(&bfqq->entity); ++ bfq_log_bfqq(bfqq->bfqd, bfqq, "bfqq_served %d secs, vtime %llu on %p", ++ served, ((st->vtime>>10)*1000)>>12, st); ++} ++ ++/** ++ * bfq_bfqq_charge_time - charge an amount of service equivalent to the length ++ * of the time interval during which bfqq has been in ++ * service. ++ * @bfqd: the device ++ * @bfqq: the queue that needs a service update. ++ * @time_ms: the amount of time during which the queue has received service ++ * ++ * If a queue does not consume its budget fast enough, then providing ++ * the queue with service fairness may impair throughput, more or less ++ * severely. For this reason, queues that consume their budget slowly ++ * are provided with time fairness instead of service fairness. This ++ * goal is achieved through the BFQ scheduling engine, even if such an ++ * engine works in the service, and not in the time domain. The trick ++ * is charging these queues with an inflated amount of service, equal ++ * to the amount of service that they would have received during their ++ * service slot if they had been fast, i.e., if their requests had ++ * been dispatched at a rate equal to the estimated peak rate. ++ * ++ * It is worth noting that time fairness can cause important ++ * distortions in terms of bandwidth distribution, on devices with ++ * internal queueing. The reason is that I/O requests dispatched ++ * during the service slot of a queue may be served after that service ++ * slot is finished, and may have a total processing time loosely ++ * correlated with the duration of the service slot. This is ++ * especially true for short service slots. ++ */ ++static void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ unsigned long time_ms) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ int tot_serv_to_charge = entity->service; ++ unsigned int timeout_ms = jiffies_to_msecs(bfq_timeout); ++ ++ if (time_ms > 0 && time_ms < timeout_ms) ++ tot_serv_to_charge = ++ (bfqd->bfq_max_budget * time_ms) / timeout_ms; ++ ++ if (tot_serv_to_charge < entity->service) ++ tot_serv_to_charge = entity->service; ++ ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "charge_time: %lu/%u ms, %d/%d/%d sectors", ++ time_ms, timeout_ms, entity->service, ++ tot_serv_to_charge, entity->budget); ++ ++ /* Increase budget to avoid inconsistencies */ ++ if (tot_serv_to_charge > entity->budget) ++ entity->budget = tot_serv_to_charge; ++ ++ bfq_bfqq_served(bfqq, ++ max_t(int, 0, tot_serv_to_charge - entity->service)); ++} ++ ++/** ++ * __bfq_activate_entity - activate an entity. ++ * @entity: the entity being activated. ++ * @non_blocking_wait_rq: true if this entity was waiting for a request ++ * ++ * Called whenever an entity is activated, i.e., it is not active and one ++ * of its children receives a new request, or has to be reactivated due to ++ * budget exhaustion. It uses the current budget of the entity (and the ++ * service received if @entity is active) of the queue to calculate its ++ * timestamps. ++ */ ++static void __bfq_activate_entity(struct bfq_entity *entity, ++ bool non_blocking_wait_rq) ++{ ++ struct bfq_sched_data *sd = entity->sched_data; ++ struct bfq_service_tree *st = bfq_entity_service_tree(entity); ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ bool backshifted = false; ++ ++ BUG_ON(!sd); ++ BUG_ON(!st); ++ if (entity == sd->in_service_entity) { ++ BUG_ON(entity->tree); ++ /* ++ * If we are requeueing the current entity we have ++ * to take care of not charging to it service it has ++ * not received. ++ */ ++ bfq_calc_finish(entity, entity->service); ++ entity->start = entity->finish; ++ sd->in_service_entity = NULL; ++ } else if (entity->tree == &st->active) { ++ /* ++ * Requeueing an entity due to a change of some ++ * next_in_service entity below it. We reuse the ++ * old start time. ++ */ ++ bfq_active_extract(st, entity); ++ } else { ++ unsigned long long min_vstart; ++ ++ /* See comments on bfq_fqq_update_budg_for_activation */ ++ if (non_blocking_wait_rq && bfq_gt(st->vtime, entity->finish)) { ++ backshifted = true; ++ min_vstart = entity->finish; ++ } else ++ min_vstart = st->vtime; ++ ++ if (entity->tree == &st->idle) { ++ /* ++ * Must be on the idle tree, bfq_idle_extract() will ++ * check for that. ++ */ ++ bfq_idle_extract(st, entity); ++ entity->start = bfq_gt(min_vstart, entity->finish) ? ++ min_vstart : entity->finish; ++ } else { ++ /* ++ * The finish time of the entity may be invalid, and ++ * it is in the past for sure, otherwise the queue ++ * would have been on the idle tree. ++ */ ++ entity->start = min_vstart; ++ st->wsum += entity->weight; ++ bfq_get_entity(entity); ++ ++ BUG_ON(entity->on_st); ++ entity->on_st = 1; ++ } ++ } ++ ++ st = __bfq_entity_update_weight_prio(st, entity); ++ bfq_calc_finish(entity, entity->budget); ++ ++ /* ++ * If some queues enjoy backshifting for a while, then their ++ * (virtual) finish timestamps may happen to become lower and ++ * lower than the system virtual time. In particular, if ++ * these queues often happen to be idle for short time ++ * periods, and during such time periods other queues with ++ * higher timestamps happen to be busy, then the backshifted ++ * timestamps of the former queues can become much lower than ++ * the system virtual time. In fact, to serve the queues with ++ * higher timestamps while the ones with lower timestamps are ++ * idle, the system virtual time may be pushed-up to much ++ * higher values than the finish timestamps of the idle ++ * queues. As a consequence, the finish timestamps of all new ++ * or newly activated queues may end up being much larger than ++ * those of lucky queues with backshifted timestamps. The ++ * latter queues may then monopolize the device for a lot of ++ * time. This would simply break service guarantees. ++ * ++ * To reduce this problem, push up a little bit the ++ * backshifted timestamps of the queue associated with this ++ * entity (only a queue can happen to have the backshifted ++ * flag set): just enough to let the finish timestamp of the ++ * queue be equal to the current value of the system virtual ++ * time. This may introduce a little unfairness among queues ++ * with backshifted timestamps, but it does not break ++ * worst-case fairness guarantees. ++ * ++ * As a special case, if bfqq is weight-raised, push up ++ * timestamps much less, to keep very low the probability that ++ * this push up causes the backshifted finish timestamps of ++ * weight-raised queues to become higher than the backshifted ++ * finish timestamps of non weight-raised queues. ++ */ ++ if (backshifted && bfq_gt(st->vtime, entity->finish)) { ++ unsigned long delta = st->vtime - entity->finish; ++ ++ if (bfqq) ++ delta /= bfqq->wr_coeff; ++ ++ entity->start += delta; ++ entity->finish += delta; ++ ++ if (bfqq) { ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "__activate_entity: new queue finish %llu", ++ ((entity->finish>>10)*1000)>>12); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ } else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "__activate_entity: new group finish %llu", ++ ((entity->finish>>10)*1000)>>12); ++#endif ++ } ++ } ++ ++ bfq_active_insert(st, entity); ++ ++ if (bfqq) { ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "__activate_entity: queue %seligible in st %p", ++ entity->start <= st->vtime ? "" : "non ", st); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ } else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "__activate_entity: group %seligible in st %p", ++ entity->start <= st->vtime ? "" : "non ", st); ++#endif ++ } ++} ++ ++/** ++ * bfq_activate_entity - activate an entity and its ancestors if necessary. ++ * @entity: the entity to activate. ++ * @non_blocking_wait_rq: true if this entity was waiting for a request ++ * ++ * Activate @entity and all the entities on the path from it to the root. ++ */ ++static void bfq_activate_entity(struct bfq_entity *entity, ++ bool non_blocking_wait_rq) ++{ ++ struct bfq_sched_data *sd; ++ ++ for_each_entity(entity) { ++ BUG_ON(!entity); ++ __bfq_activate_entity(entity, non_blocking_wait_rq); ++ ++ sd = entity->sched_data; ++ if (!bfq_update_next_in_service(sd)) ++ /* ++ * No need to propagate the activation to the ++ * upper entities, as they will be updated when ++ * the in-service entity is rescheduled. ++ */ ++ break; ++ } ++} ++ ++/** ++ * __bfq_deactivate_entity - deactivate an entity from its service tree. ++ * @entity: the entity to deactivate. ++ * @requeue: if false, the entity will not be put into the idle tree. ++ * ++ * Deactivate an entity, independently from its previous state. If the ++ * entity was not on a service tree just return, otherwise if it is on ++ * any scheduler tree, extract it from that tree, and if necessary ++ * and if the caller did not specify @requeue, put it on the idle tree. ++ * ++ * Return %1 if the caller should update the entity hierarchy, i.e., ++ * if the entity was in service or if it was the next_in_service for ++ * its sched_data; return %0 otherwise. ++ */ ++static int __bfq_deactivate_entity(struct bfq_entity *entity, int requeue) ++{ ++ struct bfq_sched_data *sd = entity->sched_data; ++ struct bfq_service_tree *st; ++ int was_in_service; ++ int ret = 0; ++ ++ if (sd == NULL || !entity->on_st) /* never activated, or inactive */ ++ return 0; ++ ++ st = bfq_entity_service_tree(entity); ++ was_in_service = entity == sd->in_service_entity; ++ ++ BUG_ON(was_in_service && entity->tree); ++ ++ if (was_in_service) { ++ bfq_calc_finish(entity, entity->service); ++ sd->in_service_entity = NULL; ++ } else if (entity->tree == &st->active) ++ bfq_active_extract(st, entity); ++ else if (entity->tree == &st->idle) ++ bfq_idle_extract(st, entity); ++ else if (entity->tree) ++ BUG(); ++ ++ if (was_in_service || sd->next_in_service == entity) ++ ret = bfq_update_next_in_service(sd); ++ ++ if (!requeue || !bfq_gt(entity->finish, st->vtime)) ++ bfq_forget_entity(st, entity); ++ else ++ bfq_idle_insert(st, entity); ++ ++ BUG_ON(sd->in_service_entity == entity); ++ BUG_ON(sd->next_in_service == entity); ++ ++ return ret; ++} ++ ++/** ++ * bfq_deactivate_entity - deactivate an entity. ++ * @entity: the entity to deactivate. ++ * @requeue: true if the entity can be put on the idle tree ++ */ ++static void bfq_deactivate_entity(struct bfq_entity *entity, int requeue) ++{ ++ struct bfq_sched_data *sd; ++ struct bfq_entity *parent; ++ ++ for_each_entity_safe(entity, parent) { ++ sd = entity->sched_data; ++ ++ if (!__bfq_deactivate_entity(entity, requeue)) ++ /* ++ * next_in_service has not been changed, so ++ * no upwards update is needed ++ */ ++ break; ++ ++ if (sd->next_in_service) ++ /* ++ * The parent entity is still backlogged, ++ * because next_in_service is not NULL, and ++ * next_in_service has been updated (see ++ * comment on the body of the above if): ++ * upwards update of the schedule is needed. ++ */ ++ goto update; ++ ++ /* ++ * If we get here, then the parent is no more backlogged and ++ * we want to propagate the deactivation upwards. ++ */ ++ requeue = 1; ++ } ++ ++ return; ++ ++update: ++ entity = parent; ++ for_each_entity(entity) { ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ __bfq_activate_entity(entity, false); ++ ++ sd = entity->sched_data; ++ if (bfqq) ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "invoking udpdate_next for this queue"); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ struct bfq_group *bfqg = ++ container_of(entity, ++ struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "invoking udpdate_next for this entity"); ++ } ++#endif ++ if (!bfq_update_next_in_service(sd)) ++ break; ++ } ++} ++ ++/** ++ * bfq_update_vtime - update vtime if necessary. ++ * @st: the service tree to act upon. ++ * ++ * If necessary update the service tree vtime to have at least one ++ * eligible entity, skipping to its start time. Assumes that the ++ * active tree of the device is not empty. ++ * ++ * NOTE: this hierarchical implementation updates vtimes quite often, ++ * we may end up with reactivated processes getting timestamps after a ++ * vtime skip done because we needed a ->first_active entity on some ++ * intermediate node. ++ */ ++static void bfq_update_vtime(struct bfq_service_tree *st) ++{ ++ struct bfq_entity *entry; ++ struct rb_node *node = st->active.rb_node; ++ ++ entry = rb_entry(node, struct bfq_entity, rb_node); ++ if (bfq_gt(entry->min_start, st->vtime)) { ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entry); ++ st->vtime = entry->min_start; ++ ++ if (bfqq) ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "update_vtime: new vtime %llu %p", ++ ((st->vtime>>10)*1000)>>12, st); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ struct bfq_group *bfqg = ++ container_of(entry, struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "update_vtime: new vtime %llu %p", ++ ((st->vtime>>10)*1000)>>12, st); ++ } ++#endif ++ bfq_forget_idle(st); ++ } ++} ++ ++/** ++ * bfq_first_active_entity - find the eligible entity with ++ * the smallest finish time ++ * @st: the service tree to select from. ++ * ++ * This function searches the first schedulable entity, starting from the ++ * root of the tree and going on the left every time on this side there is ++ * a subtree with at least one eligible (start >= vtime) entity. The path on ++ * the right is followed only if a) the left subtree contains no eligible ++ * entities and b) no eligible entity has been found yet. ++ */ ++static struct bfq_entity *bfq_first_active_entity(struct bfq_service_tree *st) ++{ ++ struct bfq_entity *entry, *first = NULL; ++ struct rb_node *node = st->active.rb_node; ++ ++ while (node) { ++ entry = rb_entry(node, struct bfq_entity, rb_node); ++left: ++ if (!bfq_gt(entry->start, st->vtime)) ++ first = entry; ++ ++ BUG_ON(bfq_gt(entry->min_start, st->vtime)); ++ ++ if (node->rb_left) { ++ entry = rb_entry(node->rb_left, ++ struct bfq_entity, rb_node); ++ if (!bfq_gt(entry->min_start, st->vtime)) { ++ node = node->rb_left; ++ goto left; ++ } ++ } ++ if (first) ++ break; ++ node = node->rb_right; ++ } ++ ++ BUG_ON(!first && !RB_EMPTY_ROOT(&st->active)); ++ return first; ++} ++ ++/** ++ * __bfq_lookup_next_entity - return the first eligible entity in @st. ++ * @st: the service tree. ++ * ++ * Update the virtual time in @st and return the first eligible entity ++ * it contains. ++ */ ++static struct bfq_entity * ++__bfq_lookup_next_entity(struct bfq_service_tree *st, bool force) ++{ ++ struct bfq_entity *entity, *new_next_in_service = NULL; ++ struct bfq_queue *bfqq; ++ ++ if (RB_EMPTY_ROOT(&st->active)) ++ return NULL; ++ ++ bfq_update_vtime(st); ++ entity = bfq_first_active_entity(st); ++ BUG_ON(bfq_gt(entity->start, st->vtime)); ++ ++ bfqq = bfq_entity_to_bfqq(entity); ++ if (bfqq) ++ bfq_log_bfqq(bfqq->bfqd, bfqq, ++ "__lookup_next: start %llu vtime %llu st %p", ++ ((entity->start>>10)*1000)>>12, ++ ((st->vtime>>10)*1000)>>12, st); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg((struct bfq_data *)bfqg->bfqd, bfqg, ++ "__lookup_next: start %llu vtime %llu st %p", ++ ((entity->start>>10)*1000)>>12, ++ ((st->vtime>>10)*1000)>>12, st); ++ } ++#endif ++ ++ /* ++ * If the chosen entity does not match with the sched_data's ++ * next_in_service and we are forcedly serving the IDLE priority ++ * class tree, bubble up budget update. ++ */ ++ if (unlikely(force && entity != entity->sched_data->next_in_service)) { ++ new_next_in_service = entity; ++ for_each_entity(new_next_in_service) ++ bfq_update_budget(new_next_in_service); ++ } ++ ++ return entity; ++} ++ ++/** ++ * bfq_lookup_next_entity - return the first eligible entity in @sd. ++ * @sd: the sched_data. ++ * @extract: if true the returned entity will be also extracted from @sd. ++ * ++ * NOTE: since we cache the next_in_service entity at each level of the ++ * hierarchy, the complexity of the lookup can be decreased with ++ * absolutely no effort just returning the cached next_in_service value; ++ * we prefer to do full lookups to test the consistency of * the data ++ * structures. ++ */ ++static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd, ++ int extract, ++ struct bfq_data *bfqd) ++{ ++ struct bfq_service_tree *st = sd->service_tree; ++ struct bfq_entity *entity; ++ int i = 0; ++ ++ BUG_ON(sd->in_service_entity); ++ ++ /* ++ * Choose from idle class, if needed to guarantee a minimum ++ * bandwidth to this class. This should also mitigate ++ * priority-inversion problems in case a low priority task is ++ * holding file system resources. ++ */ ++ if (bfqd && ++ jiffies - bfqd->bfq_class_idle_last_service > ++ BFQ_CL_IDLE_TIMEOUT) { ++ entity = __bfq_lookup_next_entity(st + BFQ_IOPRIO_CLASSES - 1, ++ true); ++ if (entity) { ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ ++ if (bfqq) ++ bfq_log_bfqq(bfqd, bfqq, ++ "idle chosen from st %p %d", ++ st + BFQ_IOPRIO_CLASSES - 1, ++ BFQ_IOPRIO_CLASSES - 1); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg(bfqd, bfqg, ++ "idle chosen from st %p %d", ++ st + BFQ_IOPRIO_CLASSES - 1, ++ BFQ_IOPRIO_CLASSES - 1); ++ } ++#endif ++ i = BFQ_IOPRIO_CLASSES - 1; ++ bfqd->bfq_class_idle_last_service = jiffies; ++ sd->next_in_service = entity; ++ } ++ } ++ for (; i < BFQ_IOPRIO_CLASSES; i++) { ++ entity = __bfq_lookup_next_entity(st + i, false); ++ if (entity) { ++ if (bfqd != NULL) { ++ struct bfq_queue *bfqq = bfq_entity_to_bfqq(entity); ++ ++ if (bfqq) ++ bfq_log_bfqq(bfqd, bfqq, ++ "chosen from st %p %d", ++ st + i, i); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg(bfqd, bfqg, ++ "chosen from st %p %d", ++ st + i, i); ++ } ++#endif ++ } ++ ++ if (extract) { ++ bfq_check_next_in_service(sd, entity); ++ bfq_active_extract(st + i, entity); ++ sd->in_service_entity = entity; ++ sd->next_in_service = NULL; ++ } ++ break; ++ } ++ } ++ ++ return entity; ++} ++ ++static bool next_queue_may_preempt(struct bfq_data *bfqd) ++{ ++ struct bfq_sched_data *sd = &bfqd->root_group->sched_data; ++ ++ return sd->next_in_service != sd->in_service_entity; ++} ++ ++/* ++ * Get next queue for service. ++ */ ++static struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd) ++{ ++ struct bfq_entity *entity = NULL; ++ struct bfq_sched_data *sd; ++ struct bfq_queue *bfqq; ++ ++ BUG_ON(bfqd->in_service_queue); ++ ++ if (bfqd->busy_queues == 0) ++ return NULL; ++ ++ sd = &bfqd->root_group->sched_data; ++ for (; sd ; sd = entity->my_sched_data) { ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ if (entity) { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg(bfqd, bfqg, ++ "get_next_queue: lookup in this group"); ++ } else ++ bfq_log_bfqg(bfqd, bfqd->root_group, ++ "get_next_queue: lookup in root group"); ++#endif ++ ++ entity = bfq_lookup_next_entity(sd, 1, bfqd); ++ ++ bfqq = bfq_entity_to_bfqq(entity); ++ if (bfqq) ++ bfq_log_bfqq(bfqd, bfqq, ++ "get_next_queue: this queue, finish %llu", ++ (((entity->finish>>10)*1000)>>10)>>2); ++#ifdef CONFIG_BFQ_GROUP_IOSCHED ++ else { ++ struct bfq_group *bfqg = ++ container_of(entity, struct bfq_group, entity); ++ ++ bfq_log_bfqg(bfqd, bfqg, ++ "get_next_queue: this entity, finish %llu", ++ (((entity->finish>>10)*1000)>>10)>>2); ++ } ++#endif ++ ++ BUG_ON(!entity); ++ entity->service = 0; ++ } ++ ++ bfqq = bfq_entity_to_bfqq(entity); ++ BUG_ON(!bfqq); ++ ++ return bfqq; ++} ++ ++static void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd) ++{ ++ if (bfqd->in_service_bic) { ++ put_io_context(bfqd->in_service_bic->icq.ioc); ++ bfqd->in_service_bic = NULL; ++ } ++ ++ bfq_clear_bfqq_wait_request(bfqd->in_service_queue); ++ hrtimer_try_to_cancel(&bfqd->idle_slice_timer); ++ bfqd->in_service_queue = NULL; ++} ++ ++static void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ int requeue) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ ++ BUG_ON(bfqq == bfqd->in_service_queue); ++ bfq_deactivate_entity(entity, requeue); ++} ++ ++static void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ struct bfq_entity *entity = &bfqq->entity; ++ ++ bfq_activate_entity(entity, bfq_bfqq_non_blocking_wait_rq(bfqq)); ++ bfq_clear_bfqq_non_blocking_wait_rq(bfqq); ++} ++ ++static void bfqg_stats_update_dequeue(struct bfq_group *bfqg); ++ ++/* ++ * Called when the bfqq no longer has requests pending, remove it from ++ * the service tree. ++ */ ++static void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq, ++ int requeue) ++{ ++ BUG_ON(!bfq_bfqq_busy(bfqq)); ++ BUG_ON(!RB_EMPTY_ROOT(&bfqq->sort_list)); ++ BUG_ON(bfqq == bfqd->in_service_queue); ++ ++ bfq_log_bfqq(bfqd, bfqq, "del from busy"); ++ ++ bfq_clear_bfqq_busy(bfqq); ++ ++ BUG_ON(bfqd->busy_queues == 0); ++ bfqd->busy_queues--; ++ ++ if (!bfqq->dispatched) ++ bfq_weights_tree_remove(bfqd, &bfqq->entity, ++ &bfqd->queue_weights_tree); ++ ++ if (bfqq->wr_coeff > 1) ++ bfqd->wr_busy_queues--; ++ ++ bfqg_stats_update_dequeue(bfqq_group(bfqq)); ++ ++ BUG_ON(bfqq->entity.budget < 0); ++ ++ bfq_deactivate_bfqq(bfqd, bfqq, requeue); ++ ++ BUG_ON(bfqq->entity.budget < 0); ++} ++ ++/* ++ * Called when an inactive queue receives a new request. ++ */ ++static void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq) ++{ ++ BUG_ON(bfq_bfqq_busy(bfqq)); ++ BUG_ON(bfqq == bfqd->in_service_queue); ++ ++ bfq_log_bfqq(bfqd, bfqq, "add to busy"); ++ ++ bfq_activate_bfqq(bfqd, bfqq); ++ ++ bfq_mark_bfqq_busy(bfqq); ++ bfqd->busy_queues++; ++ ++ if (!bfqq->dispatched) ++ if (bfqq->wr_coeff == 1) ++ bfq_weights_tree_add(bfqd, &bfqq->entity, ++ &bfqd->queue_weights_tree); ++ ++ if (bfqq->wr_coeff > 1) ++ bfqd->wr_busy_queues++; ++} +diff -w -uNr '--exclude=.git' linux-4.8/block/Kconfig.iosched linux-4.8-bfq/block/Kconfig.iosched +--- linux-4.8/block/Kconfig.iosched 2016-10-03 01:24:33.000000000 +0200 ++++ linux-4.8-bfq/block/Kconfig.iosched 2016-10-18 12:57:57.691164881 +0200 +@@ -39,6 +39,25 @@ + ---help--- + Enable group IO scheduling in CFQ. + ++config IOSCHED_BFQ ++ tristate "BFQ I/O scheduler" ++ default n ++ ---help--- ++ The BFQ I/O scheduler tries to distribute bandwidth among ++ all processes according to their weights. ++ It aims at distributing the bandwidth as desired, independently of ++ the disk parameters and with any workload. It also tries to ++ guarantee low latency to interactive and soft real-time ++ applications. If compiled built-in (saying Y here), BFQ can ++ be configured to support hierarchical scheduling. ++ ++config BFQ_GROUP_IOSCHED ++ bool "BFQ hierarchical scheduling support" ++ depends on IOSCHED_BFQ && BLK_CGROUP ++ default n ++ ---help--- ++ Enable hierarchical scheduling in BFQ, using the blkio controller. ++ + choice + prompt "Default I/O scheduler" + default DEFAULT_CFQ +@@ -52,6 +71,16 @@ + config DEFAULT_CFQ + bool "CFQ" if IOSCHED_CFQ=y + ++ config DEFAULT_BFQ ++ bool "BFQ" if IOSCHED_BFQ=y ++ help ++ Selects BFQ as the default I/O scheduler which will be ++ used by default for all block devices. ++ The BFQ I/O scheduler aims at distributing the bandwidth ++ as desired, independently of the disk parameters and with ++ any workload. It also tries to guarantee low latency to ++ interactive and soft real-time applications. ++ + config DEFAULT_NOOP + bool "No-op" + +@@ -61,6 +90,7 @@ + string + default "deadline" if DEFAULT_DEADLINE + default "cfq" if DEFAULT_CFQ ++ default "bfq" if DEFAULT_BFQ + default "noop" if DEFAULT_NOOP + + endmenu +diff -w -uNr '--exclude=.git' linux-4.8/block/Makefile linux-4.8-bfq/block/Makefile +--- linux-4.8/block/Makefile 2016-10-03 01:24:33.000000000 +0200 ++++ linux-4.8-bfq/block/Makefile 2016-10-18 12:57:57.691164881 +0200 +@@ -18,6 +18,7 @@ + obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o + obj-$(CONFIG_IOSCHED_DEADLINE) += deadline-iosched.o + obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o ++obj-$(CONFIG_IOSCHED_BFQ) += bfq-iosched.o + + obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o + obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o +diff -w -uNr '--exclude=.git' linux-4.8/include/linux/blkdev.h linux-4.8-bfq/include/linux/blkdev.h +--- linux-4.8/include/linux/blkdev.h 2016-10-03 01:24:33.000000000 +0200 ++++ linux-4.8-bfq/include/linux/blkdev.h 2016-10-18 12:57:59.951179412 +0200 +@@ -45,7 +45,7 @@ + * Maximum number of blkcg policies allowed to be registered concurrently. + * Defined here to simplify include dependency. + */ +-#define BLKCG_MAX_POLS 2 ++#define BLKCG_MAX_POLS 3 + + typedef void (rq_end_io_fn)(struct request *, int); + diff --git a/kernel/kernel/files/patches/mageia/net-add-recursion-limit-to-GRO.patch b/kernel/kernel/files/patches/mageia/net-add-recursion-limit-to-GRO.patch new file mode 100644 index 00000000..cece1d9f --- /dev/null +++ b/kernel/kernel/files/patches/mageia/net-add-recursion-limit-to-GRO.patch @@ -0,0 +1,213 @@ + +From: Sabrina Dubroca + +https://bugzilla.redhat.com/show_bug.cgi?id=1375944 +https://patchwork.ozlabs.org/patch/680412/ + + +Currently, GRO can do unlimited recursion through the gro_receive +handlers. This was fixed for tunneling protocols by limiting tunnel GRO +to one level with encap_mark, but both VLAN and TEB still have this +problem. Thus, the kernel is vulnerable to a stack overflow, if we +receive a packet composed entirely of VLAN headers. + +This patch adds a recursion counter to the GRO layer to prevent stack +overflow. When a gro_receive function hits the recursion limit, GRO is +aborted for this skb and it is processed normally. + +Thanks to Vladimír Beneš for the initial bug report. + +Fixes: CVE-2016-7039 +Fixes: 9b174d88c257 ("net: Add Transparent Ethernet Bridging GRO support.") +Fixes: 66e5133f19e9 ("vlan: Add GRO support for non hardware accelerated vlan") +Signed-off-by: Sabrina Dubroca +Reviewed-by: Jiri Benc +Acked-by: Hannes Frederic Sowa + + +diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c +index 3c20e87bb761..16af1ce99233 100644 +--- a/drivers/net/geneve.c ++++ b/drivers/net/geneve.c +@@ -453,7 +453,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk, + + skb_gro_pull(skb, gh_len); + skb_gro_postpull_rcsum(skb, gh, gh_len); +- pp = ptype->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); + flush = 0; + + out_unlock: +diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c +index e7d16687538b..c1639a3e95a4 100644 +--- a/drivers/net/vxlan.c ++++ b/drivers/net/vxlan.c +@@ -583,7 +583,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk, + } + } + +- pp = eth_gro_receive(head, skb); ++ pp = call_gro_receive(eth_gro_receive, head, skb); + flush = 0; + + out: +diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h +index 136ae6bbe81e..11a7218c3661 100644 +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -2169,7 +2169,10 @@ struct napi_gro_cb { + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; + +- /* 5 bit hole */ ++ /* Number of gro_receive callbacks this packet already went through */ ++ u8 recursion_counter:4; ++ ++ /* 1 bit hole */ + + /* used to support CHECKSUM_COMPLETE for tunneling protocols */ + __wsum csum; +@@ -2180,6 +2183,25 @@ struct napi_gro_cb { + + #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) + ++#define GRO_RECURSION_LIMIT 15 ++static inline int gro_recursion_inc_test(struct sk_buff *skb) ++{ ++ return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; ++} ++ ++typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *); ++static inline struct sk_buff **call_gro_receive(gro_receive_t cb, ++ struct sk_buff **head, ++ struct sk_buff *skb) ++{ ++ if (gro_recursion_inc_test(skb)) { ++ NAPI_GRO_CB(skb)->flush |= 1; ++ return NULL; ++ } ++ ++ return cb(head, skb); ++} ++ + struct packet_type { + __be16 type; /* This is really htons(ether_type). */ + struct net_device *dev; /* NULL is wildcarded here */ +diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c +index 8de138d3306b..f2531ad66b68 100644 +--- a/net/8021q/vlan.c ++++ b/net/8021q/vlan.c +@@ -664,7 +664,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, + + skb_gro_pull(skb, sizeof(*vhdr)); + skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr)); +- pp = ptype->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); + + out_unlock: + rcu_read_unlock(); +diff --git a/net/core/dev.c b/net/core/dev.c +index f1fe26f66458..f7cd4b8b035d 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -4511,6 +4511,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff + NAPI_GRO_CB(skb)->flush = 0; + NAPI_GRO_CB(skb)->free = 0; + NAPI_GRO_CB(skb)->encap_mark = 0; ++ NAPI_GRO_CB(skb)->recursion_counter = 0; + NAPI_GRO_CB(skb)->is_fou = 0; + NAPI_GRO_CB(skb)->is_atomic = 1; + NAPI_GRO_CB(skb)->gro_remcsum_start = 0; +diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c +index 66dff5e3d772..02acfff36028 100644 +--- a/net/ethernet/eth.c ++++ b/net/ethernet/eth.c +@@ -439,7 +439,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head, + + skb_gro_pull(skb, sizeof(*eh)); + skb_gro_postpull_rcsum(skb, eh, sizeof(*eh)); +- pp = ptype->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); + + out_unlock: + rcu_read_unlock(); +diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c +index 1effc986739e..9648c97e541f 100644 +--- a/net/ipv4/af_inet.c ++++ b/net/ipv4/af_inet.c +@@ -1391,7 +1391,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb) + skb_gro_pull(skb, sizeof(*iph)); + skb_set_transport_header(skb, skb_gro_offset(skb)); + +- pp = ops->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); + + out_unlock: + rcu_read_unlock(); +diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c +index cf50f7e2b012..030d1531e897 100644 +--- a/net/ipv4/fou.c ++++ b/net/ipv4/fou.c +@@ -249,7 +249,7 @@ static struct sk_buff **fou_gro_receive(struct sock *sk, + if (!ops || !ops->callbacks.gro_receive) + goto out_unlock; + +- pp = ops->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); + + out_unlock: + rcu_read_unlock(); +@@ -441,7 +441,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk, + if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) + goto out_unlock; + +- pp = ops->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); + flush = 0; + + out_unlock: +diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c +index 96e0efecefa6..d5cac99170b1 100644 +--- a/net/ipv4/gre_offload.c ++++ b/net/ipv4/gre_offload.c +@@ -229,7 +229,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, + /* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/ + skb_gro_postpull_rcsum(skb, greh, grehlen); + +- pp = ptype->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); + flush = 0; + + out_unlock: +diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c +index f9333c963607..7b5879bcd08b 100644 +--- a/net/ipv4/udp_offload.c ++++ b/net/ipv4/udp_offload.c +@@ -295,7 +295,13 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, + + skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */ + skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); +- pp = udp_sk(sk)->gro_receive(sk, head, skb); ++ ++ if (gro_recursion_inc_test(skb)) { ++ flush = 1; ++ pp = NULL; ++ } else { ++ pp = udp_sk(sk)->gro_receive(sk, head, skb); ++ } + + out_unlock: + rcu_read_unlock(); +diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c +index e7bfd55899a3..1fcf61f1cbc3 100644 +--- a/net/ipv6/ip6_offload.c ++++ b/net/ipv6/ip6_offload.c +@@ -246,7 +246,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head, + + skb_gro_postpull_rcsum(skb, iph, nlen); + +- pp = ops->callbacks.gro_receive(head, skb); ++ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); + + out_unlock: + rcu_read_unlock(); diff --git a/kernel/kernel/files/patches/mageia/net-wireless-rtlwifi-Fix-regression-caused-by-commit-d86e64768859.patch b/kernel/kernel/files/patches/mageia/net-wireless-rtlwifi-Fix-regression-caused-by-commit-d86e64768859.patch new file mode 100644 index 00000000..536fce2e --- /dev/null +++ b/kernel/kernel/files/patches/mageia/net-wireless-rtlwifi-Fix-regression-caused-by-commit-d86e64768859.patch @@ -0,0 +1,426 @@ + +From: Larry Finger + +In commit d86e64768859 ("rtlwifi: rtl818x: constify local structures"), +the configuration struct for most of the drivers was changed to be +constant. The problem is that five of the modified drivers need to be +able to update the firmware name based on the exact model of the card. +As the file names were stored in one of the members of that struct, +these drivers would fail with a kernel BUG splat when they tried to +update the firmware name. + +Rather than reverting the previous commit, I used a suggestion by +Johannes Berg and made the firmware file name pointers be local to +the routines that update the software variables. + +The configuration struct of rtl8192cu, which was not touched in the +previous patch, is now constantfied. + +Fixes: d86e64768859 ("rtlwifi: rtl818x: constify local structures") +Suggested-by: Johannes Berg +Signed-off-by: Larry Finger +Cc: Stable +Cc: Julia Lawall +--- + +V2 - Fix warnings that were generated for some compiler versions. +--- + drivers/net/wireless/realtek/rtlwifi/core.c | 2 +- + drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c | 8 ++++---- + drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c | 13 +++++-------- + drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c | 12 ++++++------ + drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c | 6 +++--- + drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c | 8 ++++---- + drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c | 9 +++++---- + drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c | 12 +++++------- + drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c | 6 +++--- + drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c | 18 +++++++++--------- + drivers/net/wireless/realtek/rtlwifi/wifi.h | 2 -- + 11 files changed, 45 insertions(+), 51 deletions(-) + +diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c +index f95760c..8e7f23c 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/core.c ++++ b/drivers/net/wireless/realtek/rtlwifi/core.c +@@ -111,7 +111,7 @@ static void rtl_fw_do_work(const struct firmware *firmware, void *context, + if (!err) + goto found_alt; + } +- pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name); ++ pr_err("Selected firmware is not available\n"); + rtlpriv->max_fw_size = 0; + return; + } +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c +index e7b11b4..f361808 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8188ee/sw.c +@@ -86,6 +86,7 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw) + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + u8 tid; ++ char *fw_name; + + rtl8188ee_bt_reg_init(hw); + rtlpriv->dm.dm_initialgain_enable = 1; +@@ -169,10 +170,10 @@ int rtl88e_init_sw_vars(struct ieee80211_hw *hw) + return 1; + } + +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8188efw.bin"; ++ fw_name = "rtlwifi/rtl8188efw.bin"; + rtlpriv->max_fw_size = 0x8000; +- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name); +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ pr_info("Using firmware %s\n", fw_name); ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_fw_cb); + if (err) { +@@ -284,7 +285,6 @@ static const struct rtl_hal_cfg rtl88ee_hal_cfg = { + .bar_id = 2, + .write_readback = true, + .name = "rtl88e_pci", +- .fw_name = "rtlwifi/rtl8188efw.bin", + .ops = &rtl8188ee_hal_ops, + .mod_params = &rtl88ee_mod_params, + +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c +index 5c46a98..691ddef 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ce/sw.c +@@ -92,6 +92,7 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw) + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); ++ char *fw_name = "rtlwifi/rtl8192cfwU.bin"; + + rtl8192ce_bt_reg_init(hw); + +@@ -163,15 +164,12 @@ int rtl92c_init_sw_vars(struct ieee80211_hw *hw) + } + + /* request fw */ +- if (IS_VENDOR_UMC_A_CUT(rtlhal->version) && +- !IS_92C_SERIAL(rtlhal->version)) +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU.bin"; +- else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version)) +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cfwU_B.bin"; ++ if (IS_81XXC_VENDOR_UMC_B_CUT(rtlhal->version)) ++ fw_name = "rtlwifi/rtl8192cfwU_B.bin"; + + rtlpriv->max_fw_size = 0x4000; +- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name); +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ pr_info("Using firmware %s\n", fw_name); ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_fw_cb); + if (err) { +@@ -258,7 +256,6 @@ static const struct rtl_hal_cfg rtl92ce_hal_cfg = { + .bar_id = 2, + .write_readback = true, + .name = "rtl92c_pci", +- .fw_name = "rtlwifi/rtl8192cfw.bin", + .ops = &rtl8192ce_hal_ops, + .mod_params = &rtl92ce_mod_params, + +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c +index 92588e0..b84e13a 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192cu/sw.c +@@ -55,6 +55,7 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw) + { + struct rtl_priv *rtlpriv = rtl_priv(hw); + int err; ++ char *fw_name; + + rtlpriv->dm.dm_initialgain_enable = true; + rtlpriv->dm.dm_flag = 0; +@@ -73,18 +74,18 @@ static int rtl92cu_init_sw_vars(struct ieee80211_hw *hw) + } + if (IS_VENDOR_UMC_A_CUT(rtlpriv->rtlhal.version) && + !IS_92C_SERIAL(rtlpriv->rtlhal.version)) { +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_A.bin"; ++ fw_name = "rtlwifi/rtl8192cufw_A.bin"; + } else if (IS_81XXC_VENDOR_UMC_B_CUT(rtlpriv->rtlhal.version)) { +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_B.bin"; ++ fw_name = "rtlwifi/rtl8192cufw_B.bin"; + } else { +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192cufw_TMSC.bin"; ++ fw_name = "rtlwifi/rtl8192cufw_TMSC.bin"; + } + /* provide name of alternative file */ + rtlpriv->cfg->alt_fw_name = "rtlwifi/rtl8192cufw.bin"; +- pr_info("Loading firmware %s\n", rtlpriv->cfg->fw_name); ++ pr_info("Loading firmware %s\n", fw_name); + rtlpriv->max_fw_size = 0x4000; + err = request_firmware_nowait(THIS_MODULE, 1, +- rtlpriv->cfg->fw_name, rtlpriv->io.dev, ++ fw_name, rtlpriv->io.dev, + GFP_KERNEL, hw, rtl_fw_cb); + return err; + } +@@ -183,7 +184,6 @@ static struct rtl_hal_usbint_cfg rtl92cu_interface_cfg = { + + static struct rtl_hal_cfg rtl92cu_hal_cfg = { + .name = "rtl92c_usb", +- .fw_name = "rtlwifi/rtl8192cufw.bin", + .ops = &rtl8192cu_hal_ops, + .mod_params = &rtl92cu_mod_params, + .usb_interface_cfg = &rtl92cu_interface_cfg, +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c +index a9c39eb..2d65e40 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/sw.c +@@ -88,6 +88,7 @@ static int rtl92d_init_sw_vars(struct ieee80211_hw *hw) + u8 tid; + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); ++ char *fw_name = "rtlwifi/rtl8192defw.bin"; + + rtlpriv->dm.dm_initialgain_enable = true; + rtlpriv->dm.dm_flag = 0; +@@ -177,10 +178,10 @@ static int rtl92d_init_sw_vars(struct ieee80211_hw *hw) + + rtlpriv->max_fw_size = 0x8000; + pr_info("Driver for Realtek RTL8192DE WLAN interface\n"); +- pr_info("Loading firmware file %s\n", rtlpriv->cfg->fw_name); ++ pr_info("Loading firmware file %s\n", fw_name); + + /* request fw */ +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_fw_cb); + if (err) { +@@ -262,7 +263,6 @@ static const struct rtl_hal_cfg rtl92de_hal_cfg = { + .bar_id = 2, + .write_readback = true, + .name = "rtl8192de", +- .fw_name = "rtlwifi/rtl8192defw.bin", + .ops = &rtl8192de_hal_ops, + .mod_params = &rtl92de_mod_params, + +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c +index ac299cb..46b605de3 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192ee/sw.c +@@ -91,6 +91,7 @@ int rtl92ee_init_sw_vars(struct ieee80211_hw *hw) + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + int err = 0; ++ char *fw_name; + + rtl92ee_bt_reg_init(hw); + rtlpci->msi_support = rtlpriv->cfg->mod_params->msi_support; +@@ -170,11 +171,11 @@ int rtl92ee_init_sw_vars(struct ieee80211_hw *hw) + } + + /* request fw */ +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8192eefw.bin"; ++ fw_name = "rtlwifi/rtl8192eefw.bin"; + + rtlpriv->max_fw_size = 0x8000; +- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name); +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ pr_info("Using firmware %s\n", fw_name); ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_fw_cb); + if (err) { +@@ -266,7 +267,6 @@ static const struct rtl_hal_cfg rtl92ee_hal_cfg = { + .bar_id = 2, + .write_readback = true, + .name = "rtl92ee_pci", +- .fw_name = "rtlwifi/rtl8192eefw.bin", + .ops = &rtl8192ee_hal_ops, + .mod_params = &rtl92ee_mod_params, + +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c +index a652d45..998cefb 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192se/sw.c +@@ -85,12 +85,13 @@ static void rtl92se_fw_cb(const struct firmware *firmware, void *context) + struct ieee80211_hw *hw = context; + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rt_firmware *pfirmware = NULL; ++ char *fw_name = "rtlwifi/rtl8192sefw.bin"; + + RT_TRACE(rtlpriv, COMP_ERR, DBG_LOUD, + "Firmware callback routine entered!\n"); + complete(&rtlpriv->firmware_loading_complete); + if (!firmware) { +- pr_err("Firmware %s not available\n", rtlpriv->cfg->fw_name); ++ pr_err("Firmware %s not available\n", fw_name); + rtlpriv->max_fw_size = 0; + return; + } +@@ -113,6 +114,7 @@ static int rtl92s_init_sw_vars(struct ieee80211_hw *hw) + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + int err = 0; + u16 earlyrxthreshold = 7; ++ char *fw_name = "rtlwifi/rtl8192sefw.bin"; + + rtlpriv->dm.dm_initialgain_enable = true; + rtlpriv->dm.dm_flag = 0; +@@ -210,9 +212,9 @@ static int rtl92s_init_sw_vars(struct ieee80211_hw *hw) + rtlpriv->max_fw_size = RTL8190_MAX_FIRMWARE_CODE_SIZE*2 + + sizeof(struct fw_hdr); + pr_info("Driver for Realtek RTL8192SE/RTL8191SE\n" +- "Loading firmware %s\n", rtlpriv->cfg->fw_name); ++ "Loading firmware %s\n", fw_name); + /* request fw */ +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl92se_fw_cb); + if (err) { +@@ -306,7 +308,6 @@ static const struct rtl_hal_cfg rtl92se_hal_cfg = { + .bar_id = 1, + .write_readback = false, + .name = "rtl92s_pci", +- .fw_name = "rtlwifi/rtl8192sefw.bin", + .ops = &rtl8192se_hal_ops, + .mod_params = &rtl92se_mod_params, + +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c +index 89c828a..c51a9e8 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c +@@ -94,6 +94,7 @@ int rtl8723e_init_sw_vars(struct ieee80211_hw *hw) + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); + int err = 0; ++ char *fw_name = "rtlwifi/rtl8723fw.bin"; + + rtl8723e_bt_reg_init(hw); + +@@ -176,14 +177,12 @@ int rtl8723e_init_sw_vars(struct ieee80211_hw *hw) + return 1; + } + +- if (IS_VENDOR_8723_A_CUT(rtlhal->version)) +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8723fw.bin"; +- else if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version)) +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8723fw_B.bin"; ++ if (IS_81xxC_VENDOR_UMC_B_CUT(rtlhal->version)) ++ fw_name = "rtlwifi/rtl8723fw_B.bin"; + + rtlpriv->max_fw_size = 0x6000; +- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name); +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ pr_info("Using firmware %s\n", fw_name); ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_fw_cb); + if (err) { +@@ -280,7 +279,6 @@ static const struct rtl_hal_cfg rtl8723e_hal_cfg = { + .bar_id = 2, + .write_readback = true, + .name = "rtl8723e_pci", +- .fw_name = "rtlwifi/rtl8723efw.bin", + .ops = &rtl8723e_hal_ops, + .mod_params = &rtl8723e_mod_params, + .maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL, +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c +index 20b53f0..847644d 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/sw.c +@@ -91,6 +91,7 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw) + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); ++ char *fw_name = "rtlwifi/rtl8723befw.bin"; + + rtl8723be_bt_reg_init(hw); + rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer(); +@@ -184,8 +185,8 @@ int rtl8723be_init_sw_vars(struct ieee80211_hw *hw) + } + + rtlpriv->max_fw_size = 0x8000; +- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name); +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ pr_info("Using firmware %s\n", fw_name); ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_fw_cb); + if (err) { +@@ -280,7 +281,6 @@ static const struct rtl_hal_cfg rtl8723be_hal_cfg = { + .bar_id = 2, + .write_readback = true, + .name = "rtl8723be_pci", +- .fw_name = "rtlwifi/rtl8723befw.bin", + .ops = &rtl8723be_hal_ops, + .mod_params = &rtl8723be_mod_params, + .maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL, +diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c +index 22f687b1..297938e 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c ++++ b/drivers/net/wireless/realtek/rtlwifi/rtl8821ae/sw.c +@@ -93,6 +93,7 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) + struct rtl_pci *rtlpci = rtl_pcidev(rtl_pcipriv(hw)); + struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); + struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); ++ char *fw_name, *wowlan_fw_name; + + rtl8821ae_bt_reg_init(hw); + rtlpriv->btcoexist.btc_ops = rtl_btc_get_ops_pointer(); +@@ -203,17 +204,17 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) + } + + if (rtlhal->hw_type == HARDWARE_TYPE_RTL8812AE) { +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8812aefw.bin"; +- rtlpriv->cfg->wowlan_fw_name = "rtlwifi/rtl8812aefw_wowlan.bin"; ++ fw_name = "rtlwifi/rtl8812aefw.bin"; ++ wowlan_fw_name = "rtlwifi/rtl8812aefw_wowlan.bin"; + } else { +- rtlpriv->cfg->fw_name = "rtlwifi/rtl8821aefw.bin"; +- rtlpriv->cfg->wowlan_fw_name = "rtlwifi/rtl8821aefw_wowlan.bin"; ++ fw_name = "rtlwifi/rtl8821aefw.bin"; ++ wowlan_fw_name = "rtlwifi/rtl8821aefw_wowlan.bin"; + } + + rtlpriv->max_fw_size = 0x8000; + /*load normal firmware*/ +- pr_info("Using firmware %s\n", rtlpriv->cfg->fw_name); +- err = request_firmware_nowait(THIS_MODULE, 1, rtlpriv->cfg->fw_name, ++ pr_info("Using firmware %s\n", fw_name); ++ err = request_firmware_nowait(THIS_MODULE, 1, fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_fw_cb); + if (err) { +@@ -222,9 +223,9 @@ int rtl8821ae_init_sw_vars(struct ieee80211_hw *hw) + return 1; + } + /*load wowlan firmware*/ +- pr_info("Using firmware %s\n", rtlpriv->cfg->wowlan_fw_name); ++ pr_info("Using firmware %s\n", wowlan_fw_name); + err = request_firmware_nowait(THIS_MODULE, 1, +- rtlpriv->cfg->wowlan_fw_name, ++ wowlan_fw_name, + rtlpriv->io.dev, GFP_KERNEL, hw, + rtl_wowlan_fw_cb); + if (err) { +@@ -320,7 +321,6 @@ static const struct rtl_hal_cfg rtl8821ae_hal_cfg = { + .bar_id = 2, + .write_readback = true, + .name = "rtl8821ae_pci", +- .fw_name = "rtlwifi/rtl8821aefw.bin", + .ops = &rtl8821ae_hal_ops, + .mod_params = &rtl8821ae_mod_params, + .maps[SYS_ISO_CTRL] = REG_SYS_ISO_CTRL, +diff --git a/drivers/net/wireless/realtek/rtlwifi/wifi.h b/drivers/net/wireless/realtek/rtlwifi/wifi.h +index 595f7d5..dafe486 100644 +--- a/drivers/net/wireless/realtek/rtlwifi/wifi.h ++++ b/drivers/net/wireless/realtek/rtlwifi/wifi.h +@@ -2278,9 +2278,7 @@ struct rtl_hal_cfg { + u8 bar_id; + bool write_readback; + char *name; +- char *fw_name; + char *alt_fw_name; +- char *wowlan_fw_name; + struct rtl_hal_ops *ops; + struct rtl_mod_params *mod_params; + struct rtl_hal_usbint_cfg *usb_interface_cfg; diff --git a/kernel/kernel/files/patches/mageia/nvmepatch1-V4.patch b/kernel/kernel/files/patches/mageia/nvmepatch1-V4.patch new file mode 100644 index 00000000..9bcefef0 --- /dev/null +++ b/kernel/kernel/files/patches/mageia/nvmepatch1-V4.patch @@ -0,0 +1,111 @@ +diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c +index e947e298a737..44009105f8c8 100644 +--- a/drivers/nvme/host/scsi.c ++++ b/drivers/nvme/host/scsi.c +@@ -72,15 +72,6 @@ static int sg_version_num = 30534; /* 2 digits for each component */ + #define ALL_LUNS_RETURNED 0x02 + #define ALL_WELL_KNOWN_LUNS_RETURNED 0x01 + #define RESTRICTED_LUNS_RETURNED 0x00 +-#define NVME_POWER_STATE_START_VALID 0x00 +-#define NVME_POWER_STATE_ACTIVE 0x01 +-#define NVME_POWER_STATE_IDLE 0x02 +-#define NVME_POWER_STATE_STANDBY 0x03 +-#define NVME_POWER_STATE_LU_CONTROL 0x07 +-#define POWER_STATE_0 0 +-#define POWER_STATE_1 1 +-#define POWER_STATE_2 2 +-#define POWER_STATE_3 3 + #define DOWNLOAD_SAVE_ACTIVATE 0x05 + #define DOWNLOAD_SAVE_DEFER_ACTIVATE 0x0E + #define ACTIVATE_DEFERRED_MICROCODE 0x0F +@@ -1229,64 +1220,6 @@ static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns *id_ns, + + /* Start Stop Unit Helper Functions */ + +-static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr, +- u8 pc, u8 pcmod, u8 start) +-{ +- int res; +- int nvme_sc; +- struct nvme_id_ctrl *id_ctrl; +- int lowest_pow_st; /* max npss = lowest power consumption */ +- unsigned ps_desired = 0; +- +- nvme_sc = nvme_identify_ctrl(ns->ctrl, &id_ctrl); +- res = nvme_trans_status_code(hdr, nvme_sc); +- if (res) +- return res; +- +- lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1)); +- kfree(id_ctrl); +- +- switch (pc) { +- case NVME_POWER_STATE_START_VALID: +- /* Action unspecified if POWER CONDITION MODIFIER != 0 */ +- if (pcmod == 0 && start == 0x1) +- ps_desired = POWER_STATE_0; +- if (pcmod == 0 && start == 0x0) +- ps_desired = lowest_pow_st; +- break; +- case NVME_POWER_STATE_ACTIVE: +- /* Action unspecified if POWER CONDITION MODIFIER != 0 */ +- if (pcmod == 0) +- ps_desired = POWER_STATE_0; +- break; +- case NVME_POWER_STATE_IDLE: +- /* Action unspecified if POWER CONDITION MODIFIER != [0,1,2] */ +- if (pcmod == 0x0) +- ps_desired = POWER_STATE_1; +- else if (pcmod == 0x1) +- ps_desired = POWER_STATE_2; +- else if (pcmod == 0x2) +- ps_desired = POWER_STATE_3; +- break; +- case NVME_POWER_STATE_STANDBY: +- /* Action unspecified if POWER CONDITION MODIFIER != [0,1] */ +- if (pcmod == 0x0) +- ps_desired = max(POWER_STATE_0, (lowest_pow_st - 2)); +- else if (pcmod == 0x1) +- ps_desired = max(POWER_STATE_0, (lowest_pow_st - 1)); +- break; +- case NVME_POWER_STATE_LU_CONTROL: +- default: +- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION, +- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB, +- SCSI_ASCQ_CAUSE_NOT_REPORTABLE); +- break; +- } +- nvme_sc = nvme_set_features(ns->ctrl, NVME_FEAT_POWER_MGMT, ps_desired, 0, +- NULL); +- return nvme_trans_status_code(hdr, nvme_sc); +-} +- + static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr, + u8 buffer_id) + { +@@ -2235,11 +2168,10 @@ static int nvme_trans_synchronize_cache(struct nvme_ns *ns, + static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr, + u8 *cmd) + { +- u8 immed, pcmod, pc, no_flush, start; ++ u8 immed, pcmod, no_flush, start; + + immed = cmd[1] & 0x01; + pcmod = cmd[3] & 0x0f; +- pc = (cmd[4] & 0xf0) >> 4; + no_flush = cmd[4] & 0x04; + start = cmd[4] & 0x01; + +@@ -2254,8 +2186,8 @@ static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr, + if (res) + return res; + } +- /* Setup the expected power state transition */ +- return nvme_trans_power_state(ns, hdr, pc, pcmod, start); ++ ++ return 0; + } + } + +-- +2.7.4 diff --git a/kernel/kernel/files/patches/mageia/nvmepatch2-V4.patch b/kernel/kernel/files/patches/mageia/nvmepatch2-V4.patch new file mode 100644 index 00000000..454cb4a5 --- /dev/null +++ b/kernel/kernel/files/patches/mageia/nvmepatch2-V4.patch @@ -0,0 +1,107 @@ +diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c +index 2feacc70bf61..b92a7f767bfc 100644 +--- a/drivers/nvme/host/core.c ++++ b/drivers/nvme/host/core.c +@@ -597,7 +597,7 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, + } + + int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, +- dma_addr_t dma_addr, u32 *result) ++ void *buffer, size_t buflen, u32 *result) + { + struct nvme_command c; + struct nvme_completion cqe; +@@ -606,10 +606,9 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, + memset(&c, 0, sizeof(c)); + c.features.opcode = nvme_admin_get_features; + c.features.nsid = cpu_to_le32(nsid); +- c.features.dptr.prp1 = cpu_to_le64(dma_addr); + c.features.fid = cpu_to_le32(fid); + +- ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, ++ ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, buffer, buflen, 0, + NVME_QID_ANY, 0, 0); + if (ret >= 0 && result) + *result = le32_to_cpu(cqe.result); +@@ -617,7 +616,7 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, + } + + int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, +- dma_addr_t dma_addr, u32 *result) ++ void *buffer, size_t buflen, u32 *result) + { + struct nvme_command c; + struct nvme_completion cqe; +@@ -625,12 +624,11 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, + + memset(&c, 0, sizeof(c)); + c.features.opcode = nvme_admin_set_features; +- c.features.dptr.prp1 = cpu_to_le64(dma_addr); + c.features.fid = cpu_to_le32(fid); + c.features.dword11 = cpu_to_le32(dword11); + +- ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, +- NVME_QID_ANY, 0, 0); ++ ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, ++ buffer, buflen, 0, NVME_QID_ANY, 0, 0); + if (ret >= 0 && result) + *result = le32_to_cpu(cqe.result); + return ret; +@@ -664,7 +662,7 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count) + u32 result; + int status, nr_io_queues; + +- status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, 0, ++ status = nvme_set_features(ctrl, NVME_FEAT_NUM_QUEUES, q_count, NULL, 0, + &result); + if (status < 0) + return status; +diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h +index ab18b78102bf..c2151761ec5f 100644 +--- a/drivers/nvme/host/nvme.h ++++ b/drivers/nvme/host/nvme.h +@@ -292,9 +292,9 @@ int nvme_identify_ns(struct nvme_ctrl *dev, unsigned nsid, + struct nvme_id_ns **id); + int nvme_get_log_page(struct nvme_ctrl *dev, struct nvme_smart_log **log); + int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, +- dma_addr_t dma_addr, u32 *result); ++ void *buffer, size_t buflen, u32 *result); + int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, +- dma_addr_t dma_addr, u32 *result); ++ void *buffer, size_t buflen, u32 *result); + int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count); + void nvme_start_keep_alive(struct nvme_ctrl *ctrl); + void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); +diff --git a/drivers/nvme/host/scsi.c b/drivers/nvme/host/scsi.c +index 44009105f8c8..c2a0a1c7d05d 100644 +--- a/drivers/nvme/host/scsi.c ++++ b/drivers/nvme/host/scsi.c +@@ -906,7 +906,7 @@ static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr, + kfree(smart_log); + + /* Get Features for Temp Threshold */ +- res = nvme_get_features(ns->ctrl, NVME_FEAT_TEMP_THRESH, 0, 0, ++ res = nvme_get_features(ns->ctrl, NVME_FEAT_TEMP_THRESH, 0, NULL, 0, + &feature_resp); + if (res != NVME_SC_SUCCESS) + temp_c_thresh = LOG_TEMP_UNKNOWN; +@@ -1039,7 +1039,7 @@ static int nvme_trans_fill_caching_page(struct nvme_ns *ns, + if (len < MODE_PAGE_CACHING_LEN) + return -EINVAL; + +- nvme_sc = nvme_get_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, 0, 0, ++ nvme_sc = nvme_get_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, 0, NULL, 0, + &feature_resp); + res = nvme_trans_status_code(hdr, nvme_sc); + if (res) +@@ -1328,7 +1328,7 @@ static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr, + case MODE_PAGE_CACHING: + dword11 = ((mode_page[2] & CACHING_MODE_PAGE_WCE_MASK) ? 1 : 0); + nvme_sc = nvme_set_features(ns->ctrl, NVME_FEAT_VOLATILE_WC, +- dword11, 0, NULL); ++ dword11, NULL, 0, NULL); + res = nvme_trans_status_code(hdr, nvme_sc); + break; + case MODE_PAGE_CONTROL: +-- +2.7.4 diff --git a/kernel/kernel/files/patches/mageia/nvmepatch3-V4.patch b/kernel/kernel/files/patches/mageia/nvmepatch3-V4.patch new file mode 100644 index 00000000..797c4681 --- /dev/null +++ b/kernel/kernel/files/patches/mageia/nvmepatch3-V4.patch @@ -0,0 +1,264 @@ +diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c +index b92a7f767bfc..a143c72c3d0d 100644 +--- a/drivers/nvme/host/core.c ++++ b/drivers/nvme/host/core.c +@@ -56,6 +56,11 @@ EXPORT_SYMBOL_GPL(nvme_max_retries); + static int nvme_char_major; + module_param(nvme_char_major, int, 0); + ++static unsigned long default_ps_max_latency_us = 25000; ++module_param(default_ps_max_latency_us, ulong, 0644); ++MODULE_PARM_DESC(ps_max_latency_us, ++ "default max power saving latency; overridden per device in sysfs"); ++ + static LIST_HEAD(nvme_ctrl_list); + static DEFINE_SPINLOCK(dev_list_lock); + +@@ -1205,6 +1210,98 @@ static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, + blk_queue_write_cache(q, vwc, vwc); + } + ++static void nvme_configure_apst(struct nvme_ctrl *ctrl) ++{ ++ /* ++ * APST (Autonomous Power State Transition) lets us program a ++ * table of power state transitions that the controller will ++ * perform automatically. We configure it with a simple ++ * heuristic: we are willing to spend at most 2% of the time ++ * transitioning between power states. Therefore, when running ++ * in any given state, we will enter the next lower-power ++ * non-operational state after waiting 100 * (enlat + exlat) ++ * microseconds, as long as that state's total latency is under ++ * the requested maximum latency. ++ * ++ * We will not autonomously enter any non-operational state for ++ * which the total latency exceeds ps_max_latency_us. Users ++ * can set ps_max_latency_us to zero to turn off APST. ++ */ ++ ++ unsigned apste; ++ struct nvme_feat_auto_pst *table; ++ int ret; ++ ++ if (!ctrl->apsta) ++ return; /* APST isn't supported. */ ++ ++ if (ctrl->npss > 31) { ++ dev_warn(ctrl->device, "NPSS is invalid; not using APST\n"); ++ return; ++ } ++ ++ table = kzalloc(sizeof(*table), GFP_KERNEL); ++ if (!table) ++ return; ++ ++ if (ctrl->ps_max_latency_us == 0) { ++ /* Turn off APST. */ ++ apste = 0; ++ } else { ++ __le64 target = cpu_to_le64(0); ++ int state; ++ ++ /* ++ * Walk through all states from lowest- to highest-power. ++ * According to the spec, lower-numbered states use more ++ * power. NPSS, despite the name, is the index of the ++ * lowest-power state, not the number of states. ++ */ ++ for (state = (int)ctrl->npss; state >= 0; state--) { ++ u64 total_latency_us, transition_ms; ++ ++ if (target) ++ table->entries[state] = target; ++ ++ /* ++ * Is this state a useful non-operational state for ++ * higher-power states to autonomously transition to? ++ */ ++ if (!(ctrl->psd[state].flags & 2)) ++ continue; /* It's an operational state. */ ++ ++ total_latency_us = ++ (u64)cpu_to_le32(ctrl->psd[state].entry_lat) + ++ + cpu_to_le32(ctrl->psd[state].exit_lat); ++ if (total_latency_us > ctrl->ps_max_latency_us) ++ continue; ++ ++ /* ++ * This state is good. Use it as the APST idle ++ * target for higher power states. ++ */ ++ transition_ms = total_latency_us + 19; ++ do_div(transition_ms, 20); ++ if (transition_ms >= (1 << 24)) ++ transition_ms = (1 << 24); ++ ++ target = cpu_to_le64((state << 3) | ++ (transition_ms << 8)); ++ } ++ ++ apste = 1; ++ } ++ ++ ret = nvme_set_features(ctrl, NVME_FEAT_AUTO_PST, apste, ++ table, sizeof(*table), NULL); ++ if (ret) ++ dev_err(ctrl->device, "failed to set APST feature (%d)\n", ret); ++ ++ kfree(table); ++} ++ ++static struct attribute_group nvme_dev_dynamic_attrs_group; ++ + /* + * Initialize the cached copies of the Identify data and various controller + * register in our nvme_ctrl structure. This should be called as soon as +@@ -1271,6 +1368,10 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) + ctrl->sgls = le32_to_cpu(id->sgls); + ctrl->kas = le16_to_cpu(id->kas); + ++ ctrl->npss = id->npss; ++ ctrl->apsta = id->apsta; ++ memcpy(ctrl->psd, id->psd, sizeof(ctrl->psd)); ++ + if (ctrl->ops->is_fabrics) { + ctrl->icdoff = le16_to_cpu(id->icdoff); + ctrl->ioccsz = le32_to_cpu(id->ioccsz); +@@ -1294,6 +1395,10 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) + } + + kfree(id); ++ ++ nvme_configure_apst(ctrl); ++ ++ sysfs_update_group(&ctrl->device->kobj, &nvme_dev_dynamic_attrs_group); + return ret; + } + EXPORT_SYMBOL_GPL(nvme_init_identify); +@@ -1564,6 +1669,41 @@ static ssize_t nvme_sysfs_show_address(struct device *dev, + } + static DEVICE_ATTR(address, S_IRUGO, nvme_sysfs_show_address, NULL); + ++static ssize_t nvme_sysfs_show_ps_max_latency_us( ++ struct device *dev, ++ struct device_attribute *attr, ++ char *buf) ++{ ++ struct nvme_ctrl *ctrl = dev_get_drvdata(dev); ++ ++ return snprintf(buf, PAGE_SIZE, "%llu\n", ctrl->ps_max_latency_us); ++} ++ ++static ssize_t nvme_sysfs_store_ps_max_latency_us( ++ struct device *dev, ++ struct device_attribute *attr, ++ const char *buf, size_t size) ++{ ++ struct nvme_ctrl *ctrl = dev_get_drvdata(dev); ++ int ret; ++ u64 val; ++ ++ ret = kstrtoull(buf, 10, &val); ++ if (ret) ++ return ret; ++ ++ if (ctrl->ps_max_latency_us != val) { ++ ctrl->ps_max_latency_us = val; ++ nvme_configure_apst(ctrl); ++ } ++ ++ return size; ++} ++ ++static DEVICE_ATTR(ps_max_latency_us, 0644, ++ nvme_sysfs_show_ps_max_latency_us, ++ nvme_sysfs_store_ps_max_latency_us); ++ + static struct attribute *nvme_dev_attrs[] = { + &dev_attr_reset_controller.attr, + &dev_attr_rescan_controller.attr, +@@ -1605,8 +1745,33 @@ static struct attribute_group nvme_dev_attrs_group = { + .is_visible = nvme_dev_attrs_are_visible, + }; + ++static struct attribute *nvme_dev_dynamic_attrs[] = { ++ &dev_attr_ps_max_latency_us.attr, ++ NULL ++}; ++ ++static umode_t nvme_dev_dynamic_attrs_are_visible(struct kobject *kobj, ++ struct attribute *a, int n) ++{ ++ struct device *dev = container_of(kobj, struct device, kobj); ++ struct nvme_ctrl *ctrl = dev_get_drvdata(dev); ++ ++ if (a == &dev_attr_ps_max_latency_us.attr) { ++ if (!ctrl->apsta) ++ return 0; ++ } ++ ++ return a->mode; ++} ++ ++static struct attribute_group nvme_dev_dynamic_attrs_group = { ++ .attrs = nvme_dev_dynamic_attrs, ++ .is_visible = nvme_dev_dynamic_attrs_are_visible, ++}; ++ + static const struct attribute_group *nvme_dev_attr_groups[] = { + &nvme_dev_attrs_group, ++ &nvme_dev_dynamic_attrs_group, + NULL, + }; + +@@ -1991,6 +2156,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, + ctrl->quirks = quirks; + INIT_WORK(&ctrl->scan_work, nvme_scan_work); + INIT_WORK(&ctrl->async_event_work, nvme_async_event_work); ++ ctrl->ps_max_latency_us = default_ps_max_latency_us; + + ret = nvme_set_instance(ctrl); + if (ret) +diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h +index c2151761ec5f..16d51006afc0 100644 +--- a/drivers/nvme/host/nvme.h ++++ b/drivers/nvme/host/nvme.h +@@ -129,13 +129,19 @@ struct nvme_ctrl { + u32 vs; + u32 sgls; + u16 kas; ++ u8 npss; ++ u8 apsta; + unsigned int kato; + bool subsystem; + unsigned long quirks; ++ struct nvme_id_power_state psd[32]; + struct work_struct scan_work; + struct work_struct async_event_work; + struct delayed_work ka_work; + ++ /* Power saving configuration */ ++ u64 ps_max_latency_us; ++ + /* Fabrics only */ + u16 sqsize; + u32 ioccsz; +diff --git a/include/linux/nvme.h b/include/linux/nvme.h +index d8b37bab2887..a76237dac4b0 100644 +--- a/include/linux/nvme.h ++++ b/include/linux/nvme.h +@@ -543,6 +543,12 @@ struct nvme_dsm_range { + __le64 slba; + }; + ++/* Features */ ++ ++struct nvme_feat_auto_pst { ++ __le64 entries[32]; ++}; ++ + /* Admin commands */ + + enum nvme_admin_opcode { +-- +2.7.4 diff --git a/kernel/kernel/files/patches/mageia/skl_uncondition_memory_bandwitdth_WA_n_adjusted_mode_in_SAGV_check_on_a7fac751ddba.patch b/kernel/kernel/files/patches/mageia/skl_uncondition_memory_bandwitdth_WA_n_adjusted_mode_in_SAGV_check_on_a7fac751ddba.patch new file mode 100644 index 00000000..1b819dea --- /dev/null +++ b/kernel/kernel/files/patches/mageia/skl_uncondition_memory_bandwitdth_WA_n_adjusted_mode_in_SAGV_check_on_a7fac751ddba.patch @@ -0,0 +1,110 @@ +diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c +index 2d24813..498ded6 100644 +--- a/drivers/gpu/drm/i915/intel_pm.c ++++ b/drivers/gpu/drm/i915/intel_pm.c +@@ -2877,6 +2877,21 @@ skl_wm_plane_id(const struct intel_plane *plane) + } + + /* ++ * FIXME: We still don't have the proper code detect if we need to apply the WA, ++ * so assume we'll always need it in order to avoid underruns. ++ */ ++static bool skl_needs_memory_bw_wa(struct intel_atomic_state *state) ++{ ++ struct drm_i915_private *dev_priv = to_i915(state->base.dev); ++ ++ if (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv) || ++ IS_KABYLAKE(dev_priv)) ++ return true; ++ ++ return false; ++} ++ ++/* + * SAGV dynamically adjusts the system agent voltage and clock frequencies + * depending on power and performance requirements. The display engine access + * to system memory is blocked during the adjustment time. Because of the +@@ -2979,9 +2994,10 @@ bool skl_can_enable_sagv(struct drm_atomic_state *state) + struct drm_device *dev = state->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); +- struct drm_crtc *crtc; ++ struct intel_crtc *crtc; ++ struct intel_plane *plane; + enum pipe pipe; +- int level, plane; ++ int level, id, latency; + + /* + * SKL workaround: bspec recommends we disable the SAGV when we have +@@ -2996,27 +3012,35 @@ bool skl_can_enable_sagv(struct drm_atomic_state *state) + + /* Since we're now guaranteed to only have one active CRTC... */ + pipe = ffs(intel_state->active_crtcs) - 1; +- crtc = dev_priv->pipe_to_crtc_mapping[pipe]; ++ crtc = to_intel_crtc(dev_priv->pipe_to_crtc_mapping[pipe]); + +- if (crtc->state->mode.flags & DRM_MODE_FLAG_INTERLACE) ++ if (crtc->base.state->adjusted_mode.flags & DRM_MODE_FLAG_INTERLACE) + return false; ++ for_each_intel_plane_on_crtc(dev, crtc, plane) { ++ id = skl_wm_plane_id(plane); + +- for_each_plane(dev_priv, pipe, plane) { + /* Skip this plane if it's not enabled */ +- if (intel_state->wm_results.plane[pipe][plane][0] == 0) ++ if (intel_state->wm_results.plane[pipe][id][0] == 0) + continue; + + /* Find the highest enabled wm level for this plane */ + for (level = ilk_wm_max_level(dev); +- intel_state->wm_results.plane[pipe][plane][level] == 0; --level) ++ intel_state->wm_results.plane[pipe][id][level] == 0; --level) + { } + ++ latency = dev_priv->wm.skl_latency[level]; ++ ++ if (skl_needs_memory_bw_wa(intel_state) && ++ plane->base.state->fb->modifier[0] == ++ I915_FORMAT_MOD_X_TILED) ++ latency += 15; ++ + /* + * If any of the planes on this pipe don't enable wm levels + * that incur memory latencies higher then 30µs we can't enable + * the SAGV + */ +- if (dev_priv->wm.skl_latency[level] < SKL_SAGV_BLOCK_TIME) ++ if (latency < SKL_SAGV_BLOCK_TIME) + return false; + } + +@@ -3546,12 +3570,18 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, + uint8_t cpp; + uint32_t width = 0, height = 0; + uint32_t plane_pixel_rate; ++ struct intel_atomic_state *state = ++ to_intel_atomic_state(cstate->base.state); ++ bool apply_memory_bw_wa = skl_needs_memory_bw_wa(state); + + if (latency == 0 || !cstate->base.active || !intel_pstate->visible) { + *enabled = false; + return 0; + } + ++ if (apply_memory_bw_wa && fb->modifier[0] == I915_FORMAT_MOD_X_TILED) ++ latency += 15; ++ + width = drm_rect_width(&intel_pstate->src) >> 16; + height = drm_rect_height(&intel_pstate->src) >> 16; + +@@ -3593,6 +3623,9 @@ static int skl_compute_plane_wm(const struct drm_i915_private *dev_priv, + } + } + y_tile_minimum = plane_blocks_per_line * min_scanlines; ++ if (apply_memory_bw_wa) ++ y_tile_minimum *= 2; ++ + selected_result = max(method2, y_tile_minimum); + } else { + if ((ddb_allocation / plane_blocks_per_line) >= 1)