diff options
349 files changed, 4118 insertions, 2182 deletions
@@ -15,30 +15,31 @@ Aaron Durbin <adurbin@google.com> Adam Oldham <oldhamca@gmail.com> Adam Radford <aradford@gmail.com> -Adrian Bunk <bunk@stusta.de> Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com> +Adrian Bunk <bunk@stusta.de> Alan Cox <alan@lxorguk.ukuu.org.uk> Alan Cox <root@hraefn.swansea.linux.org.uk> -Aleksey Gorelov <aleksey_gorelov@phoenix.com> Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com> -Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com> -Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org> +Aleksey Gorelov <aleksey_gorelov@phoenix.com> Alexander Lobakin <alobakin@pm.me> <alobakin@dlink.ru> Alexander Lobakin <alobakin@pm.me> <alobakin@marvell.com> Alexander Lobakin <alobakin@pm.me> <bloodyreaper@yandex.ru> Alexandre Belloni <alexandre.belloni@bootlin.com> <alexandre.belloni@free-electrons.com> -Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com> Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com> Alexei Starovoitov <ast@kernel.org> <ast@fb.com> +Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com> +Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@intel.com> +Alex Shi <alex.shi@linux.alibaba.com> <alex.shi@linaro.org> Al Viro <viro@ftp.linux.org.uk> Al Viro <viro@zenIV.linux.org.uk> +Andi Kleen <ak@linux.intel.com> <ak@suse.de> Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com> Andreas Herrmann <aherrman@de.ibm.com> -Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andrew Morton <akpm@linux-foundation.org> -Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com> Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk> +Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com> Andrew Vasquez <andrew.vasquez@qlogic.com> +Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andy Adamson <andros@citi.umich.edu> Antoine Tenart <antoine.tenart@free-electrons.com> Antonio Ospite <ao2@ao2.it> <ao2@amarulasolutions.com> @@ -48,40 +49,42 @@ Arnaud Patard <arnaud.patard@rtp-net.org> Arnd Bergmann <arnd@arndb.de> Axel Dyks <xl@xlsigned.net> Axel Lin <axel.lin@gmail.com> -Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com> Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com> +Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com> Ben Gardner <bgardner@wabtec.com> Ben M Cahill <ben.m.cahill@intel.com> Björn Steinbrink <B.Steinbrink@gmx.de> -Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com> -Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com> Boris Brezillon <bbrezillon@kernel.org> <b.brezillon.dev@gmail.com> Boris Brezillon <bbrezillon@kernel.org> <b.brezillon@overkiz.com> +Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@bootlin.com> +Boris Brezillon <bbrezillon@kernel.org> <boris.brezillon@free-electrons.com> Brian Avery <b.avery@hp.com> Brian King <brking@us.ibm.com> +Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> +Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> Chao Yu <chao@kernel.org> <chao2.yu@samsung.com> Chao Yu <chao@kernel.org> <yuchao0@huawei.com> -Christoph Hellwig <hch@lst.de> Christophe Ricard <christophe.ricard@gmail.com> +Christoph Hellwig <hch@lst.de> Corey Minyard <minyard@acm.org> Damian Hobson-Garcia <dhobsong@igel.co.jp> -Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> -Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> +Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com> Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net> Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch> -Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com> +Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> +Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com> David Brownell <david-b@pacbell.net> David Woodhouse <dwmw2@shinybook.infradead.org> -Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> -Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> Dengcheng Zhu <dzhu@wavecomp.com> <dczhu@mips.com> Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com> +Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com> +Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com> <dev.kurt@vandijck-laurijssen.be> <kurt.van.dijck@eia.be> Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> -Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> -Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com> +Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com> +Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com> Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> Ed L. Cashin <ecashin@coraid.com> @@ -92,20 +95,22 @@ Felix Kuhling <fxkuehl@gmx.de> Felix Moeller <felix@derklecks.de> Filipe Lautert <filipe@icewall.org> Franck Bui-Huu <vagabon.xyz@gmail.com> -Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com> Frank Rowand <frowand.list@gmail.com> <frank.rowand@am.sony.com> Frank Rowand <frowand.list@gmail.com> <frank.rowand@sonymobile.com> +Frank Rowand <frowand.list@gmail.com> <frowand@mvista.com> Frank Zago <fzago@systemfabricworks.com> Gao Xiang <xiang@kernel.org> <gaoxiang25@huawei.com> Gao Xiang <xiang@kernel.org> <hsiangkao@aol.com> -Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com> Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@de.ibm.com> +Gerald Schaefer <gerald.schaefer@linux.ibm.com> <gerald.schaefer@de.ibm.com> Gerald Schaefer <gerald.schaefer@linux.ibm.com> <geraldsc@linux.vnet.ibm.com> Greg Kroah-Hartman <greg@echidna.(none)> Greg Kroah-Hartman <gregkh@suse.de> Greg Kroah-Hartman <greg@kroah.com> Greg Kurz <groug@kaod.org> <gkurz@linux.vnet.ibm.com> Gregory CLEMENT <gregory.clement@bootlin.com> <gregory.clement@free-electrons.com> +Gustavo Padovan <gustavo@las.ic.unicamp.br> +Gustavo Padovan <padovan@profusion.mobi> Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org> Heiko Carstens <hca@linux.ibm.com> <h.carstens@de.ibm.com> Heiko Carstens <hca@linux.ibm.com> <heiko.carstens@de.ibm.com> @@ -115,32 +120,33 @@ Henrik Rydberg <rydberg@bitmath.org> Herbert Xu <herbert@gondor.apana.org.au> Jacob Shin <Jacob.Shin@amd.com> Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@google.com> -Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com> Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk.kim@samsung.com> +Jaegeuk Kim <jaegeuk@kernel.org> <jaegeuk@motorola.com> Jakub Kicinski <kuba@kernel.org> <jakub.kicinski@netronome.com> James Bottomley <jejb@mulgrave.(none)> James Bottomley <jejb@titanic.il.steeleye.com> James E Wilson <wilson@specifix.com> -James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> James Hogan <jhogan@kernel.org> <james@albanarts.com> +James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> James Ketrenos <jketreno@io.(none)> Jan Glauber <jan.glauber@gmail.com> <jang@de.ibm.com> Jan Glauber <jan.glauber@gmail.com> <jang@linux.vnet.ibm.com> Jan Glauber <jan.glauber@gmail.com> <jglauber@cavium.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> +Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> -Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> <javier@osg.samsung.com> <javier.martinez@collabora.co.uk> +Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com> Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com> Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com> Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com> -Jean Tourrilhes <jt@hpl.hp.com> <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com> +Jean Tourrilhes <jt@hpl.hp.com> Jeff Garzik <jgarzik@pretzel.yyz.us> -Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net> Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com> +Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com> Jens Axboe <axboe@suse.de> Jens Osterkamp <Jens.Osterkamp@de.ibm.com> Jiri Slaby <jirislaby@kernel.org> <jirislaby@gmail.com> @@ -164,30 +170,31 @@ Julien Thierry <julien.thierry.kdev@gmail.com> <julien.thierry@arm.com> Kamil Konieczny <k.konieczny@samsung.com> <k.konieczny@partner.samsung.com> Kay Sievers <kay.sievers@vrfy.org> Kenneth W Chen <kenneth.w.chen@intel.com> -Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> Konstantin Khlebnikov <koct9i@gmail.com> <khlebnikov@yandex-team.ru> +Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com> Koushik <raghavendra.koushik@neterion.com> -Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com> Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com> +Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com> Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> -Leon Romanovsky <leon@kernel.org> <leon@leon.nu> -Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com> Leonardo Bras <leobras.c@gmail.com> <leonardo@linux.ibm.com> Leonid I Ananiev <leonid.i.ananiev@intel.com> +Leon Romanovsky <leon@kernel.org> <leon@leon.nu> +Leon Romanovsky <leon@kernel.org> <leonro@mellanox.com> +Leon Romanovsky <leon@kernel.org> <leonro@nvidia.com> Linas Vepstas <linas@austin.ibm.com> -Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de> Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@ascom.ch> -Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> +Linus Lüssing <linus.luessing@c0d3.blue> <linus.luessing@web.de> Li Yang <leoyang.li@nxp.com> <leoli@freescale.com> +Li Yang <leoyang.li@nxp.com> <leo@zh-kernel.org> Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com> Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com> -Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com> Marcin Nowakowski <marcin.nowakowski@mips.com> <marcin.nowakowski@imgtec.com> +Marc Zyngier <maz@kernel.org> <marc.zyngier@arm.com> Mark Brown <broonie@sirena.org.uk> Mark Yao <markyao0591@gmail.com> <mark.yao@rock-chips.com> -Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@ginzinger.com> Martin Kepplinger <martink@posteo.de> <martin.kepplinger@puri.sm> +Martin Kepplinger <martink@posteo.de> <martin.kepplinger@theobroma-systems.com> Mathieu Othacehe <m.othacehe@gmail.com> Matthew Wilcox <willy@infradead.org> <matthew.r.wilcox@intel.com> Matthew Wilcox <willy@infradead.org> <matthew@wil.cx> @@ -197,17 +204,17 @@ Matthew Wilcox <willy@infradead.org> <willy@debian.org> Matthew Wilcox <willy@infradead.org> <willy@linux.intel.com> Matthew Wilcox <willy@infradead.org> <willy@parisc-linux.org> Matthieu CASTET <castet.matthieu@free.fr> -Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br> +Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting> +Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com> +Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com> +Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com> Mauro Carvalho Chehab <mchehab@kernel.org> <maurochehab@gmail.com> +Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@brturbo.com.br> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@infradead.org> +Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@redhat.com> Mauro Carvalho Chehab <mchehab@kernel.org> <m.chehab@samsung.com> -Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@osg.samsung.com> Mauro Carvalho Chehab <mchehab@kernel.org> <mchehab@s-opensource.com> -Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com> -Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com> -Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting> -Matt Redfearn <matt.redfearn@mips.com> <matt.redfearn@imgtec.com> Maxime Ripard <mripard@kernel.org> <maxime.ripard@bootlin.com> Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com> Mayuresh Janorkar <mayur@ti.com> @@ -239,13 +246,13 @@ Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Patrick Mochel <mochel@digitalimplant.org> Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com> Paul Burton <paulburton@kernel.org> <paul.burton@mips.com> +Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org> Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.ibm.com> Paul E. McKenney <paulmck@kernel.org> <paulmck@linux.vnet.ibm.com> -Paul E. McKenney <paulmck@kernel.org> <paul.mckenney@linaro.org> Paul E. McKenney <paulmck@kernel.org> <paulmck@us.ibm.com> Peter A Jonsson <pj@ludd.ltu.se> -Peter Oruba <peter@oruba.de> Peter Oruba <peter.oruba@amd.com> +Peter Oruba <peter@oruba.de> Pratyush Anand <pratyush.anand@gmail.com> <pratyush.anand@st.com> Praveen BP <praveenbp@ti.com> Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com> @@ -258,23 +265,23 @@ Ralf Baechle <ralf@linux-mips.org> Ralf Wildenhues <Ralf.Wildenhues@gmx.de> Randy Dunlap <rdunlap@infradead.org> <rdunlap@xenotime.net> Rémi Denis-Courmont <rdenis@simphalempin.com> -Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com> Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com> Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org> +Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com> Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com> Rudolf Marek <R.Marek@sh.cvut.cz> Rui Saraiva <rmps@joel.ist.utl.pt> Sachin P Sant <ssant@in.ibm.com> -Sarangdhar Joshi <spjoshi@codeaurora.org> +Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi> Sam Ravnborg <sam@mars.ravnborg.org> -Santosh Shilimkar <ssantosh@kernel.org> Santosh Shilimkar <santosh.shilimkar@oracle.org> +Santosh Shilimkar <ssantosh@kernel.org> +Sarangdhar Joshi <spjoshi@codeaurora.org> Sascha Hauer <s.hauer@pengutronix.de> S.ÇaÄŸlar Onur <caglar@pardus.org.tr> -Sakari Ailus <sakari.ailus@linux.intel.com> <sakari.ailus@iki.fi> Sean Nyekjaer <sean@geanix.com> <sean.nyekjaer@prevas.dk> -Sebastian Reichel <sre@kernel.org> <sre@debian.org> Sebastian Reichel <sre@kernel.org> <sebastian.reichel@collabora.co.uk> +Sebastian Reichel <sre@kernel.org> <sre@debian.org> Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de> Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com> Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> @@ -285,18 +292,21 @@ Simon Arlott <simon@octiron.net> <simon@fire.lp0.eu> Simon Kelley <simon@thekelleys.org.uk> Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr> Stephen Hemminger <shemminger@osdl.org> +Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com> +Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com> Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> Subhash Jadavani <subhashj@codeaurora.org> Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com> Sumit Semwal <sumit.semwal@ti.com> +Takashi YOSHII <takashi.yoshii.zj@renesas.com> Tejun Heo <htejun@gmail.com> Thomas Graf <tgraf@suug.ch> Thomas Pedersen <twp@codeaurora.org> Tiezhu Yang <yangtiezhu@loongson.cn> <kernelpatch@126.com> Todor Tomov <todor.too@gmail.com> <todor.tomov@linaro.org> Tony Luck <tony.luck@intel.com> -TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn> TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org> +TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn> Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> Uwe Kleine-König <ukl@pengutronix.de> @@ -305,22 +315,16 @@ Valdis Kletnieks <Valdis.Kletnieks@vt.edu> Vinod Koul <vkoul@kernel.org> <vinod.koul@intel.com> Vinod Koul <vkoul@kernel.org> <vinod.koul@linux.intel.com> Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> +Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com> Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com> Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com> -Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com> Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com> Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com> -Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com> -Takashi YOSHII <takashi.yoshii.zj@renesas.com> +Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> +WeiXiong Liao <gmpy.liaowx@gmail.com> <liaoweixiong@allwinnertech.com> Will Deacon <will@kernel.org> <will.deacon@arm.com> -Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Wolfram Sang <wsa@kernel.org> <w.sang@pengutronix.de> +Wolfram Sang <wsa@kernel.org> <wsa@the-dreams.de> Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com> Yusuke Goda <goda.yusuke@renesas.com> -Gustavo Padovan <gustavo@las.ic.unicamp.br> -Gustavo Padovan <padovan@profusion.mobi> -Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> -Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> -Steve Wise <larrystevenwise@gmail.com> <swise@chelsio.com> -Steve Wise <larrystevenwise@gmail.com> <swise@opengridcomputing.com> diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst index a683976fad6d..d2795ca6821e 100644 --- a/Documentation/admin-guide/ext4.rst +++ b/Documentation/admin-guide/ext4.rst @@ -489,6 +489,9 @@ Files in /sys/fs/ext4/<devname>: multiple of this tuning parameter if the stripe size is not set in the ext4 superblock + mb_max_inode_prealloc + The maximum length of per-inode ext4_prealloc_space list. + mb_max_to_scan The maximum number of extents the multiblock allocator will search to find the best extent. @@ -529,21 +532,21 @@ Files in /sys/fs/ext4/<devname>: Ioctls ====== -There is some Ext4 specific functionality which can be accessed by applications -through the system call interfaces. The list of all Ext4 specific ioctls are -shown in the table below. +Ext4 implements various ioctls which can be used by applications to access +ext4-specific functionality. An incomplete list of these ioctls is shown in the +table below. This list includes truly ext4-specific ioctls (``EXT4_IOC_*``) as +well as ioctls that may have been ext4-specific originally but are now supported +by some other filesystem(s) too (``FS_IOC_*``). -Table of Ext4 specific ioctls +Table of Ext4 ioctls - EXT4_IOC_GETFLAGS + FS_IOC_GETFLAGS Get additional attributes associated with inode. The ioctl argument is - an integer bitfield, with bit values described in ext4.h. This ioctl is - an alias for FS_IOC_GETFLAGS. + an integer bitfield, with bit values described in ext4.h. - EXT4_IOC_SETFLAGS + FS_IOC_SETFLAGS Set additional attributes associated with inode. The ioctl argument is - an integer bitfield, with bit values described in ext4.h. This ioctl is - an alias for FS_IOC_SETFLAGS. + an integer bitfield, with bit values described in ext4.h. EXT4_IOC_GETVERSION, EXT4_IOC_GETVERSION_OLD Get the inode i_generation number stored for each inode. The diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index bdc1f33fd3d1..a1068742a6df 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -1233,8 +1233,7 @@ efi= [EFI] Format: { "debug", "disable_early_pci_dma", "nochunk", "noruntime", "nosoftreserve", - "novamap", "no_disable_early_pci_dma", - "old_map" } + "novamap", "no_disable_early_pci_dma" } debug: enable misc debug output. disable_early_pci_dma: disable the busmaster bit on all PCI bridges while in the EFI boot stub. @@ -1251,8 +1250,6 @@ novamap: do not call SetVirtualAddressMap(). no_disable_early_pci_dma: Leave the busmaster bit set on all PCI bridges while in the EFI boot stub - old_map [X86-64]: switch to the old ioremap-based EFI - runtime services mapping. [Needs CONFIG_X86_UV=y] efi_no_storage_paranoia [EFI; X86] Using this parameter you can use more than 50% of diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index d46429be334e..7df2465fd108 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -36,6 +36,12 @@ Two sets of Questions and Answers (Q&A) are maintained. bpf_devel_QA +Helper functions +================ + +* `bpf-helpers(7)`_ maintains a list of helpers available to eBPF programs. + + Program types ============= @@ -79,4 +85,5 @@ Other .. _networking-filter: ../networking/filter.rst .. _man-pages: https://www.kernel.org/doc/man-pages/ .. _bpf(2): https://man7.org/linux/man-pages/man2/bpf.2.html +.. _bpf-helpers(7): https://man7.org/linux/man-pages/man7/bpf-helpers.7.html .. _BPF and XDP Reference Guide: https://docs.cilium.io/en/latest/bpf/ diff --git a/Documentation/devicetree/bindings/clock/imx23-clock.yaml b/Documentation/devicetree/bindings/clock/imx23-clock.yaml index 66cb238a1040..ad21899981af 100644 --- a/Documentation/devicetree/bindings/clock/imx23-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx23-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX23 maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/clock/imx28-clock.yaml b/Documentation/devicetree/bindings/clock/imx28-clock.yaml index 72328d5ca09a..f1af1108129e 100644 --- a/Documentation/devicetree/bindings/clock/imx28-clock.yaml +++ b/Documentation/devicetree/bindings/clock/imx28-clock.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Clock bindings for Freescale i.MX28 maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> description: | The clock consumer should specify the desired clock by having the clock diff --git a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml index ccf5b50e798b..dfa1133f8c5e 100644 --- a/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml +++ b/Documentation/devicetree/bindings/gpio/gpio-mxs.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS GPIO controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> - Anson Huang <Anson.Huang@nxp.com> description: | diff --git a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml index d3134ed775fa..21ae7bce038e 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-mxs.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS Inter IC (I2C) Controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml index 75dc1168d717..10b45966f1b8 100644 --- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml +++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale Enhanced Secure Digital Host Controller (eSDHC) for i.MX maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> allOf: - $ref: "mmc-controller.yaml" diff --git a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml index 1cccc0478d49..bec8f8c71ff2 100644 --- a/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml +++ b/Documentation/devicetree/bindings/mmc/mxs-mmc.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS MMC controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> description: | The Freescale MXS Synchronous Serial Ports (SSP) can act as a MMC controller diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 1c4474036d46..fa2baca8c726 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -54,7 +54,8 @@ properties: phy-connection-type: description: - Operation mode of the PHY interface + Specifies interface type between the Ethernet device and a physical + layer (PHY) device. enum: # There is not a standard bus between the MAC and the PHY, # something proprietary is being used to embed the PHY in the diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 08678af5ed93..8ce5ed8a58dd 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -59,9 +59,15 @@ properties: clocks: maxItems: 1 - pinctrl-0: true + power-domains: + maxItems: 1 + + resets: + maxItems: 1 - pinctrl-names: true + phy-mode: true + + phy-handle: true renesas,no-ether-link: type: boolean @@ -74,6 +80,11 @@ properties: specify when the Ether LINK signal is active-low instead of normal active-high +patternProperties: + "^ethernet-phy@[0-9a-f]$": + type: object + $ref: ethernet-phy.yaml# + required: - compatible - reg @@ -83,7 +94,8 @@ required: - '#address-cells' - '#size-cells' - clocks - - pinctrl-0 + +additionalProperties: false examples: # Lager board @@ -99,8 +111,6 @@ examples: clocks = <&mstp8_clks R8A7790_CLK_ETHER>; phy-mode = "rmii"; phy-handle = <&phy1>; - pinctrl-0 = <ðer_pins>; - pinctrl-names = "default"; renesas,ether-link-active-low; #address-cells = <1>; #size-cells = <0>; @@ -109,7 +119,5 @@ examples: reg = <1>; interrupt-parent = <&irqc0>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>; - pinctrl-0 = <&phy1_pins>; - pinctrl-names = "default"; }; }; diff --git a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml index 64b2c64ca806..a1e2be737eec 100644 --- a/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml +++ b/Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml @@ -9,6 +9,14 @@ title: PCIe RC controller on Intel Gateway SoCs maintainers: - Dilip Kota <eswara.kota@linux.intel.com> +select: + properties: + compatible: + contains: + const: intel,lgm-pcie + required: + - compatible + properties: compatible: items: diff --git a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml index da68f4a25dd9..8740e076061e 100644 --- a/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/mxs-pwm.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale MXS PWM controller maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> - Anson Huang <anson.huang@nxp.com> properties: diff --git a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml index 1b50cedbfb3e..50df1a40bbe3 100644 --- a/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml +++ b/Documentation/devicetree/bindings/spi/fsl-imx-cspi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale (Enhanced) Configurable Serial Peripheral Interface (CSPI/eCSPI) for i.MX maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> allOf: - $ref: "/schemas/spi/spi-controller.yaml#" diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml index 22882e769e26..312d8fee9dbb 100644 --- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml +++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml @@ -39,6 +39,7 @@ properties: spi common code does not support use of CS signals discontinuously. i.MX8DXL-EVK board only uses CS1 without using CS0. Therefore, add this property to re-config the chipselect value in the LPSPI driver. + type: boolean required: - compatible diff --git a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml index aedac1669998..16b57f57d103 100644 --- a/Documentation/devicetree/bindings/thermal/imx-thermal.yaml +++ b/Documentation/devicetree/bindings/thermal/imx-thermal.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: NXP i.MX Thermal Binding maintainers: - - Shawn Guo <shawn.guo@linaro.org> + - Shawn Guo <shawnguo@kernel.org> - Anson Huang <Anson.Huang@nxp.com> properties: diff --git a/Documentation/devicetree/bindings/timer/sifive,clint.yaml b/Documentation/devicetree/bindings/timer/sifive,clint.yaml new file mode 100644 index 000000000000..2a0e9cd9fbcf --- /dev/null +++ b/Documentation/devicetree/bindings/timer/sifive,clint.yaml @@ -0,0 +1,60 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/timer/sifive,clint.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: SiFive Core Local Interruptor + +maintainers: + - Palmer Dabbelt <palmer@dabbelt.com> + - Anup Patel <anup.patel@wdc.com> + +description: + SiFive (and other RISC-V) SOCs include an implementation of the SiFive + Core Local Interruptor (CLINT) for M-mode timer and M-mode inter-processor + interrupts. It directly connects to the timer and inter-processor interrupt + lines of various HARTs (or CPUs) so RISC-V per-HART (or per-CPU) local + interrupt controller is the parent interrupt controller for CLINT device. + The clock frequency of CLINT is specified via "timebase-frequency" DT + property of "/cpus" DT node. The "timebase-frequency" DT property is + described in Documentation/devicetree/bindings/riscv/cpus.yaml + +properties: + compatible: + items: + - const: sifive,fu540-c000-clint + - const: sifive,clint0 + + description: + Should be "sifive,<chip>-clint" and "sifive,clint<version>". + Supported compatible strings are - + "sifive,fu540-c000-clint" for the SiFive CLINT v0 as integrated + onto the SiFive FU540 chip, and "sifive,clint0" for the SiFive + CLINT v0 IP block with no chip integration tweaks. + Please refer to sifive-blocks-ip-versioning.txt for details + + reg: + maxItems: 1 + + interrupts-extended: + minItems: 1 + +additionalProperties: false + +required: + - compatible + - reg + - interrupts-extended + +examples: + - | + timer@2000000 { + compatible = "sifive,fu540-c000-clint", "sifive,clint0"; + interrupts-extended = <&cpu1intc 3 &cpu1intc 7 + &cpu2intc 3 &cpu2intc 7 + &cpu3intc 3 &cpu3intc 7 + &cpu4intc 3 &cpu4intc 7>; + reg = <0x2000000 0x10000>; + }; +... diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 2baee2c817c1..63996ab03521 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -993,7 +993,7 @@ patternProperties: "^sst,.*": description: Silicon Storage Technology, Inc. "^sstar,.*": - description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. + description: Xiamen Xingchen(SigmaStar) Technology Co., Ltd. (formerly part of MStar Semiconductor, Inc.) "^st,.*": description: STMicroelectronics diff --git a/Documentation/devicetree/writing-schema.rst b/Documentation/devicetree/writing-schema.rst index 8c74a99f95e2..16f21e182ff6 100644 --- a/Documentation/devicetree/writing-schema.rst +++ b/Documentation/devicetree/writing-schema.rst @@ -5,7 +5,7 @@ Writing DeviceTree Bindings in json-schema Devicetree bindings are written using json-schema vocabulary. Schema files are written in a JSON compatible subset of YAML. YAML is used instead of JSON as it -considered more human readable and has some advantages such as allowing +is considered more human readable and has some advantages such as allowing comments (Prefixed with '#'). Schema Contents @@ -19,7 +19,7 @@ $id A json-schema unique identifier string. The string must be a valid URI typically containing the binding's filename and path. For DT schema, it must begin with "http://devicetree.org/schemas/". The URL is used in constructing - references to other files specified in schema "$ref" properties. A $ref values + references to other files specified in schema "$ref" properties. A $ref value with a leading '/' will have the hostname prepended. A $ref value a relative path or filename only will be prepended with the hostname and path components of the current schema file's '$id' value. A URL is used even for local files, diff --git a/Documentation/filesystems/ext4/about.rst b/Documentation/filesystems/ext4/about.rst index 0aadba052264..cc76b577d2f4 100644 --- a/Documentation/filesystems/ext4/about.rst +++ b/Documentation/filesystems/ext4/about.rst @@ -39,6 +39,6 @@ entry. Other References ---------------- -Also see http://www.nongnu.org/ext2-doc/ for quite a collection of +Also see https://www.nongnu.org/ext2-doc/ for quite a collection of information about ext2/3. Here's another old reference: http://wiki.osdev.org/Ext2 diff --git a/Documentation/networking/bonding.rst b/Documentation/networking/bonding.rst index 24168b0d16bd..adc314639085 100644 --- a/Documentation/networking/bonding.rst +++ b/Documentation/networking/bonding.rst @@ -2860,17 +2860,6 @@ version of the linux kernel, found on http://kernel.org The latest version of this document can be found in the latest kernel source (named Documentation/networking/bonding.rst). -Discussions regarding the usage of the bonding driver take place on the -bonding-devel mailing list, hosted at sourceforge.net. If you have questions or -problems, post them to the list. The list address is: - -bonding-devel@lists.sourceforge.net - -The administrative interface (to subscribe or unsubscribe) can -be found at: - -https://lists.sourceforge.net/lists/listinfo/bonding-devel - Discussions regarding the development of the bonding driver take place on the main Linux network mailing list, hosted at vger.kernel.org. The list address is: @@ -2881,10 +2870,3 @@ The administrative interface (to subscribe or unsubscribe) can be found at: http://vger.kernel.org/vger-lists.html#netdev - -Donald Becker's Ethernet Drivers and diag programs may be found at : - - - http://web.archive.org/web/%2E/http://www.scyld.com/network/ - -You will also find a lot of information regarding Ethernet, NWay, MII, -etc. at www.scyld.com. diff --git a/MAINTAINERS b/MAINTAINERS index deaafb617361..f0068bceeb61 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5050,7 +5050,7 @@ F: include/linux/dm-*.h F: include/uapi/linux/dm-*.h DEVLINK -M: Jiri Pirko <jiri@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> L: netdev@vger.kernel.org S: Supported F: Documentation/networking/devlink @@ -6081,7 +6081,7 @@ F: include/linux/dynamic_debug.h F: lib/dynamic_debug.c DYNAMIC INTERRUPT MODERATION -M: Tal Gilboa <talgi@mellanox.com> +M: Tal Gilboa <talgi@nvidia.com> S: Maintained F: Documentation/networking/net_dim.rst F: include/linux/dim.h @@ -6161,7 +6161,7 @@ F: Documentation/devicetree/bindings/edac/aspeed-sdram-edac.txt F: drivers/edac/aspeed_edac.c EDAC-BLUEFIELD -M: Shravan Kumar Ramani <sramani@mellanox.com> +M: Shravan Kumar Ramani <sramani@nvidia.com> S: Supported F: drivers/edac/bluefield_edac.c @@ -6483,8 +6483,8 @@ S: Odd Fixes F: drivers/net/ethernet/agere/ ETHERNET BRIDGE -M: Roopa Prabhu <roopa@cumulusnetworks.com> -M: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> +M: Roopa Prabhu <roopa@nvidia.com> +M: Nikolay Aleksandrov <nikolay@nvidia.com> L: bridge@lists.linux-foundation.org (moderated for non-subscribers) L: netdev@vger.kernel.org S: Maintained @@ -6599,7 +6599,7 @@ F: drivers/iommu/exynos-iommu.c EZchip NPS platform support M: Vineet Gupta <vgupta@synopsys.com> -M: Ofer Levi <oferle@mellanox.com> +M: Ofer Levi <oferle@nvidia.com> S: Supported F: arch/arc/boot/dts/eznps.dts F: arch/arc/plat-eznps @@ -8563,7 +8563,7 @@ F: drivers/iio/pressure/dps310.c INFINIBAND SUBSYSTEM M: Doug Ledford <dledford@redhat.com> -M: Jason Gunthorpe <jgg@mellanox.com> +M: Jason Gunthorpe <jgg@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/linux-rdma/rdma-core @@ -9226,7 +9226,7 @@ F: drivers/firmware/iscsi_ibft* ISCSI EXTENSIONS FOR RDMA (ISER) INITIATOR M: Sagi Grimberg <sagi@grimberg.me> -M: Max Gurtovoy <maxg@mellanox.com> +M: Max Gurtovoy <maxg@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: http://www.openfabrics.org @@ -11072,7 +11072,7 @@ F: Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt F: drivers/input/touchscreen/melfas_mip4.c MELLANOX ETHERNET DRIVER (mlx4_en) -M: Tariq Toukan <tariqt@mellanox.com> +M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11080,7 +11080,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx4/en_* MELLANOX ETHERNET DRIVER (mlx5e) -M: Saeed Mahameed <saeedm@mellanox.com> +M: Saeed Mahameed <saeedm@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11088,7 +11088,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* MELLANOX ETHERNET INNOVA DRIVERS -R: Boris Pismenny <borisp@mellanox.com> +R: Boris Pismenny <borisp@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11099,8 +11099,8 @@ F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* F: include/linux/mlx5/mlx5_ifc_fpga.h MELLANOX ETHERNET SWITCH DRIVERS -M: Jiri Pirko <jiri@mellanox.com> -M: Ido Schimmel <idosch@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> +M: Ido Schimmel <idosch@nvidia.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11109,7 +11109,7 @@ F: drivers/net/ethernet/mellanox/mlxsw/ F: tools/testing/selftests/drivers/net/mlxsw/ MELLANOX FIRMWARE FLASH LIBRARY (mlxfw) -M: mlxsw@mellanox.com +M: mlxsw@nvidia.com L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11119,7 +11119,7 @@ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT M: Andy Shevchenko <andy@infradead.org> M: Darren Hart <dvhart@infradead.org> -M: Vadim Pasternak <vadimp@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> L: platform-driver-x86@vger.kernel.org S: Supported F: Documentation/ABI/testing/sysfs-platform-mellanox-bootctl @@ -11127,7 +11127,7 @@ F: drivers/platform/mellanox/ F: include/linux/platform_data/mlxreg.h MELLANOX MLX4 core VPI driver -M: Tariq Toukan <tariqt@mellanox.com> +M: Tariq Toukan <tariqt@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported @@ -11137,7 +11137,7 @@ F: drivers/net/ethernet/mellanox/mlx4/ F: include/linux/mlx4/ MELLANOX MLX4 IB driver -M: Yishai Hadas <yishaih@mellanox.com> +M: Yishai Hadas <yishaih@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11147,8 +11147,8 @@ F: include/linux/mlx4/ F: include/uapi/rdma/mlx4-abi.h MELLANOX MLX5 core VPI driver -M: Saeed Mahameed <saeedm@mellanox.com> -M: Leon Romanovsky <leonro@mellanox.com> +M: Saeed Mahameed <saeedm@nvidia.com> +M: Leon Romanovsky <leonro@nvidia.com> L: netdev@vger.kernel.org L: linux-rdma@vger.kernel.org S: Supported @@ -11159,7 +11159,7 @@ F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ MELLANOX MLX5 IB driver -M: Leon Romanovsky <leonro@mellanox.com> +M: Leon Romanovsky <leonro@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported W: http://www.mellanox.com @@ -11169,8 +11169,8 @@ F: include/linux/mlx5/ F: include/uapi/rdma/mlx5-abi.h MELLANOX MLXCPLD I2C AND MUX DRIVER -M: Vadim Pasternak <vadimp@mellanox.com> -M: Michael Shych <michaelsh@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> +M: Michael Shych <michaelsh@nvidia.com> L: linux-i2c@vger.kernel.org S: Supported F: Documentation/i2c/busses/i2c-mlxcpld.rst @@ -11178,7 +11178,7 @@ F: drivers/i2c/busses/i2c-mlxcpld.c F: drivers/i2c/muxes/i2c-mux-mlxcpld.c MELLANOX MLXCPLD LED DRIVER -M: Vadim Pasternak <vadimp@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> L: linux-leds@vger.kernel.org S: Supported F: Documentation/leds/leds-mlxcpld.rst @@ -11186,7 +11186,7 @@ F: drivers/leds/leds-mlxcpld.c F: drivers/leds/leds-mlxreg.c MELLANOX PLATFORM DRIVER -M: Vadim Pasternak <vadimp@mellanox.com> +M: Vadim Pasternak <vadimp@nvidia.com> L: platform-driver-x86@vger.kernel.org S: Supported F: drivers/platform/x86/mlx-platform.c @@ -12167,8 +12167,8 @@ F: net/ipv6/syncookies.c F: net/ipv6/tcp*.c NETWORKING [TLS] -M: Boris Pismenny <borisp@mellanox.com> -M: Aviad Yehezkel <aviadye@mellanox.com> +M: Boris Pismenny <borisp@nvidia.com> +M: Aviad Yehezkel <aviadye@nvidia.com> M: John Fastabend <john.fastabend@gmail.com> M: Daniel Borkmann <daniel@iogearbox.net> M: Jakub Kicinski <kuba@kernel.org> @@ -12468,7 +12468,7 @@ S: Supported F: drivers/nfc/nxp-nci OBJAGG -M: Jiri Pirko <jiri@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> L: netdev@vger.kernel.org S: Supported F: include/linux/objagg.h @@ -13110,7 +13110,7 @@ F: drivers/video/logo/logo_parisc* F: include/linux/hp_sdc.h PARMAN -M: Jiri Pirko <jiri@mellanox.com> +M: Jiri Pirko <jiri@nvidia.com> L: netdev@vger.kernel.org S: Supported F: include/linux/parman.h @@ -16034,7 +16034,7 @@ F: drivers/infiniband/sw/siw/ F: include/uapi/rdma/siw-abi.h SOFT-ROCE DRIVER (rxe) -M: Zhu Yanjun <yanjunz@mellanox.com> +M: Zhu Yanjun <yanjunz@nvidia.com> L: linux-rdma@vger.kernel.org S: Supported F: drivers/infiniband/sw/rxe/ @@ -265,8 +265,7 @@ no-dot-config-targets := $(clean-targets) \ $(version_h) headers headers_% archheaders archscripts \ %asm-generic kernelversion %src-pkg dt_binding_check \ outputmakefile -no-sync-config-targets := $(no-dot-config-targets) install %install \ - kernelrelease +no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/ config-build := @@ -292,7 +291,7 @@ ifneq ($(KBUILD_EXTMOD),) endif ifeq ($(KBUILD_EXTMOD),) - ifneq ($(filter config %config,$(MAKECMDGOALS)),) + ifneq ($(filter %config,$(MAKECMDGOALS)),) config-build := 1 ifneq ($(words $(MAKECMDGOALS)),1) mixed-build := 1 diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 55bc8546d9c7..b45f0124cc16 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -165,6 +165,7 @@ zinstall install: PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ + $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@ # We use MRPROPER_FILES and CLEAN_FILES now archclean: diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 65568b23868a..e52c927aade5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -473,7 +473,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6bd1d3ad037a..c332d49780dc 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -910,6 +910,8 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM erratum 1418040", .capability = ARM64_WORKAROUND_1418040, ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), + .type = (ARM64_CPUCAP_SCOPE_LOCAL_CPU | + ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU), }, #endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2646178c8329..55af8b504b65 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -170,19 +170,6 @@ alternative_cb_end stp x28, x29, [sp, #16 * 14] .if \el == 0 - .if \regsize == 32 - /* - * If we're returning from a 32-bit task on a system affected by - * 1418040 then re-enable userspace access to the virtual counter. - */ -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - orr x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - .endif clear_gp_regs mrs x21, sp_el0 ldr_this_cpu tsk, __entry_task, x20 @@ -294,14 +281,6 @@ alternative_else_nop_endif tst x22, #PSR_MODE32_BIT // native task? b.eq 3f -#ifdef CONFIG_ARM64_ERRATUM_1418040 -alternative_if ARM64_WORKAROUND_1418040 - mrs x0, cntkctl_el1 - bic x0, x0, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN - msr cntkctl_el1, x0 -alternative_else_nop_endif -#endif - #ifdef CONFIG_ARM64_ERRATUM_845719 alternative_if ARM64_WORKAROUND_845719 #ifdef CONFIG_PID_IN_CONTEXTIDR diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 84ec630b8ab5..b63ce4c54cfe 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -516,6 +516,39 @@ static void entry_task_switch(struct task_struct *next) } /* + * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT. + * Assuming the virtual counter is enabled at the beginning of times: + * + * - disable access when switching from a 64bit task to a 32bit task + * - enable access when switching from a 32bit task to a 64bit task + */ +static void erratum_1418040_thread_switch(struct task_struct *prev, + struct task_struct *next) +{ + bool prev32, next32; + u64 val; + + if (!(IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) && + cpus_have_const_cap(ARM64_WORKAROUND_1418040))) + return; + + prev32 = is_compat_thread(task_thread_info(prev)); + next32 = is_compat_thread(task_thread_info(next)); + + if (prev32 == next32) + return; + + val = read_sysreg(cntkctl_el1); + + if (!next32) + val |= ARCH_TIMER_USR_VCT_ACCESS_EN; + else + val &= ~ARCH_TIMER_USR_VCT_ACCESS_EN; + + write_sysreg(val, cntkctl_el1); +} + +/* * Thread switching. */ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, @@ -530,6 +563,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, entry_task_switch(next); uao_thread_switch(next); ssbs_thread_switch(next); + erratum_1418040_thread_switch(prev, next); /* * Complete any pending TLB or cache maintenance on this CPU in case diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 5139a5f19256..d6adb4677c25 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -208,7 +208,7 @@ quiet_cmd_vdsosym = VDSOSYM $@ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ # Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ +quiet_cmd_vdso_install = INSTALL32 $@ cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so vdso.so: $(obj)/vdso.so.dbg diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 691d21e4c717..46dc3d75cf13 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1640,6 +1640,10 @@ int kvm_arch_init(void *opaque) return -ENODEV; } + if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)) + kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \ + "Only trusted guests should be used on this system.\n"); + for_each_online_cpu(cpu) { smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1); if (ret < 0) { diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 0121ef2c7c8d..ba00bcc0c884 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -343,7 +343,8 @@ static void unmap_stage2_p4ds(struct kvm_s2_mmu *mmu, pgd_t *pgd, * destroying the VM), otherwise another faulting VCPU may come in and mess * with things behind our backs. */ -static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +static void __unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size, + bool may_block) { struct kvm *kvm = mmu->kvm; pgd_t *pgd; @@ -369,11 +370,16 @@ static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 si * If the range is too large, release the kvm->mmu_lock * to prevent starvation and lockup detector warnings. */ - if (next != end) + if (may_block && next != end) cond_resched_lock(&kvm->mmu_lock); } while (pgd++, addr = next, addr != end); } +static void unmap_stage2_range(struct kvm_s2_mmu *mmu, phys_addr_t start, u64 size) +{ + __unmap_stage2_range(mmu, start, size, true); +} + static void stage2_flush_ptes(struct kvm_s2_mmu *mmu, pmd_t *pmd, phys_addr_t addr, phys_addr_t end) { @@ -2208,18 +2214,21 @@ static int handle_hva_to_gpa(struct kvm *kvm, static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data) { - unmap_stage2_range(&kvm->arch.mmu, gpa, size); + unsigned flags = *(unsigned *)data; + bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE; + + __unmap_stage2_range(&kvm->arch.mmu, gpa, size, may_block); return 0; } int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long end, unsigned flags) { if (!kvm->arch.mmu.pgd) return 0; trace_kvm_unmap_hva_range(start, end); - handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); + handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags); return 0; } diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 10850897a91c..779b6972aa84 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -366,6 +366,15 @@ pgd_index (unsigned long address) } #define pgd_index pgd_index +/* + * In the kernel's mapped region we know everything is in region number 5, so + * as an optimisation its PGD already points to the area for that region. + * However, this also means that we cannot use pgd_index() and we must + * never add the region here. + */ +#define pgd_offset_k(addr) \ + (init_mm.pgd + (((addr) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))) + /* Look up a pgd entry in the gate area. On IA-64, the gate-area resides in the kernel-mapped segment, hence we use pgd_offset_k() here. */ diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index d35eaed1668f..825d337a505a 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -969,7 +969,7 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, #define KVM_ARCH_WANT_MMU_NOTIFIER int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, unsigned flags); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 87fa8d8a1031..28c366d307e7 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -486,7 +486,8 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e020d269416d..10ded83414de 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -58,7 +58,8 @@ #define KVM_ARCH_WANT_MMU_NOTIFIER extern int kvm_unmap_hva_range(struct kvm *kvm, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, + unsigned flags); extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 41fedec69ac3..49db50d1db04 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -834,7 +834,8 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm, kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end); } diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index d6c1069e9954..ed0c9c43d0cf 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -734,7 +734,8 @@ static int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) return 0; } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { /* kvm_unmap_hva flushes everything anyways */ kvm_unmap_hva(kvm, start); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 7b5905529146..df18372861d8 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -81,7 +81,7 @@ config RISCV select PCI_DOMAINS_GENERIC if PCI select PCI_MSI if PCI select RISCV_INTC - select RISCV_TIMER + select RISCV_TIMER if RISCV_SBI select SPARSEMEM_STATIC if 32BIT select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6c88148f1b9b..8a55f6156661 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -12,6 +12,7 @@ config SOC_SIFIVE config SOC_VIRT bool "QEMU Virt Machine" + select CLINT_TIMER if RISCV_M_MODE select POWER_RESET select POWER_RESET_SYSCON select POWER_RESET_SYSCON_POWEROFF @@ -24,6 +25,7 @@ config SOC_VIRT config SOC_KENDRYTE bool "Kendryte K210 SoC" depends on !MMU + select CLINT_TIMER if RISCV_M_MODE select SERIAL_SIFIVE if TTY select SERIAL_SIFIVE_CONSOLE if TTY select SIFIVE_PLIC diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig index f27596e9663e..e046a0babde4 100644 --- a/arch/riscv/configs/nommu_virt_defconfig +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -26,6 +26,7 @@ CONFIG_EXPERT=y CONFIG_SLOB=y # CONFIG_SLAB_MERGE_DEFAULT is not set # CONFIG_MMU is not set +CONFIG_SOC_VIRT=y CONFIG_MAXPHYSMEM_2GB=y CONFIG_SMP=y CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0" @@ -49,7 +50,6 @@ CONFIG_VIRTIO_BLK=y # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set # CONFIG_LDISC_AUTOLOAD is not set -# CONFIG_DEVMEM is not set CONFIG_SERIAL_8250=y # CONFIG_SERIAL_8250_DEPRECATED_OPTIONS is not set CONFIG_SERIAL_8250_CONSOLE=y @@ -57,16 +57,13 @@ CONFIG_SERIAL_8250_NR_UARTS=1 CONFIG_SERIAL_8250_RUNTIME_UARTS=1 CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set # CONFIG_HWMON is not set -# CONFIG_LCD_CLASS_DEVICE is not set -# CONFIG_BACKLIGHT_CLASS_DEVICE is not set # CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set CONFIG_VIRTIO_MMIO=y CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y -CONFIG_SIFIVE_PLIC=y -# CONFIG_VALIDATE_FS_PARSER is not set CONFIG_EXT2_FS=y # CONFIG_DNOTIFY is not set # CONFIG_INOTIFY_USER is not set diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig index 3a55f0e00d6c..2c2cda6cc1c5 100644 --- a/arch/riscv/configs/rv32_defconfig +++ b/arch/riscv/configs/rv32_defconfig @@ -14,6 +14,7 @@ CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y +CONFIG_SOC_SIFIVE=y CONFIG_SOC_VIRT=y CONFIG_ARCH_RV32I=y CONFIG_SMP=y @@ -62,6 +63,8 @@ CONFIG_HVC_RISCV_SBI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_SPI=y +CONFIG_SPI_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y @@ -77,6 +80,8 @@ CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y +CONFIG_MMC=y +CONFIG_MMC_SPI=y CONFIG_RTC_CLASS=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h deleted file mode 100644 index a279b17a6aad..000000000000 --- a/arch/riscv/include/asm/clint.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_RISCV_CLINT_H -#define _ASM_RISCV_CLINT_H 1 - -#include <linux/io.h> -#include <linux/smp.h> - -#ifdef CONFIG_RISCV_M_MODE -extern u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void); - -static inline void clint_send_ipi_single(unsigned long hartid) -{ - writel(1, clint_ipi_base + hartid); -} - -static inline void clint_send_ipi_mask(const struct cpumask *mask) -{ - int cpu; - - for_each_cpu(cpu, mask) - clint_send_ipi_single(cpuid_to_hartid_map(cpu)); -} - -static inline void clint_clear_ipi(unsigned long hartid) -{ - writel(0, clint_ipi_base + hartid); -} -#else /* CONFIG_RISCV_M_MODE */ -#define clint_init_boot_cpu() do { } while (0) - -/* stubs to for code is only reachable under IS_ENABLED(CONFIG_RISCV_M_MODE): */ -void clint_send_ipi_single(unsigned long hartid); -void clint_send_ipi_mask(const struct cpumask *hartid_mask); -void clint_clear_ipi(unsigned long hartid); -#endif /* CONFIG_RISCV_M_MODE */ - -#endif /* _ASM_RISCV_CLINT_H */ diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h index 6dfd2a1446d5..df1f7c4cd433 100644 --- a/arch/riscv/include/asm/smp.h +++ b/arch/riscv/include/asm/smp.h @@ -15,6 +15,11 @@ struct seq_file; extern unsigned long boot_cpu_hartid; +struct riscv_ipi_ops { + void (*ipi_inject)(const struct cpumask *target); + void (*ipi_clear)(void); +}; + #ifdef CONFIG_SMP /* * Mapping between linux logical cpu index and hartid. @@ -40,6 +45,12 @@ void arch_send_call_function_single_ipi(int cpu); int riscv_hartid_to_cpuid(int hartid); void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out); +/* Set custom IPI operations */ +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops); + +/* Clear IPI for current CPU */ +void riscv_clear_ipi(void); + /* Secondary hart entry */ asmlinkage void smp_callin(void); @@ -81,6 +92,14 @@ static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in, cpumask_set_cpu(boot_cpu_hartid, out); } +static inline void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ +} + +static inline void riscv_clear_ipi(void) +{ +} + #endif /* CONFIG_SMP */ #if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP) diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index bad2a7c2cda5..a3fb85d505d4 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -7,41 +7,27 @@ #define _ASM_RISCV_TIMEX_H #include <asm/csr.h> -#include <asm/mmio.h> typedef unsigned long cycles_t; -extern u64 __iomem *riscv_time_val; -extern u64 __iomem *riscv_time_cmp; - -#ifdef CONFIG_64BIT -#define mmio_get_cycles() readq_relaxed(riscv_time_val) -#else -#define mmio_get_cycles() readl_relaxed(riscv_time_val) -#define mmio_get_cycles_hi() readl_relaxed(((u32 *)riscv_time_val) + 1) -#endif - static inline cycles_t get_cycles(void) { - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIME); - return mmio_get_cycles(); + return csr_read(CSR_TIME); } #define get_cycles get_cycles +static inline u32 get_cycles_hi(void) +{ + return csr_read(CSR_TIMEH); +} +#define get_cycles_hi get_cycles_hi + #ifdef CONFIG_64BIT static inline u64 get_cycles64(void) { return get_cycles(); } #else /* CONFIG_64BIT */ -static inline u32 get_cycles_hi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - return csr_read(CSR_TIMEH); - return mmio_get_cycles_hi(); -} - static inline u64 get_cycles64(void) { u32 hi, lo; diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index a5287ab9f7f2..dc93710f0b2f 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -31,7 +31,7 @@ obj-y += cacheinfo.o obj-y += patch.o obj-$(CONFIG_MMU) += vdso.o vdso/ -obj-$(CONFIG_RISCV_M_MODE) += clint.o traps_misaligned.o +obj-$(CONFIG_RISCV_M_MODE) += traps_misaligned.o obj-$(CONFIG_FPU) += fpu.o obj-$(CONFIG_SMP) += smpboot.o obj-$(CONFIG_SMP) += smp.o diff --git a/arch/riscv/kernel/clint.c b/arch/riscv/kernel/clint.c deleted file mode 100644 index 3647980d14c3..000000000000 --- a/arch/riscv/kernel/clint.c +++ /dev/null @@ -1,44 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2019 Christoph Hellwig. - */ - -#include <linux/io.h> -#include <linux/of_address.h> -#include <linux/types.h> -#include <asm/clint.h> -#include <asm/csr.h> -#include <asm/timex.h> -#include <asm/smp.h> - -/* - * This is the layout used by the SiFive clint, which is also shared by the qemu - * virt platform, and the Kendryte KD210 at least. - */ -#define CLINT_IPI_OFF 0 -#define CLINT_TIME_CMP_OFF 0x4000 -#define CLINT_TIME_VAL_OFF 0xbff8 - -u32 __iomem *clint_ipi_base; - -void clint_init_boot_cpu(void) -{ - struct device_node *np; - void __iomem *base; - - np = of_find_compatible_node(NULL, NULL, "riscv,clint0"); - if (!np) { - panic("clint not found"); - return; - } - - base = of_iomap(np, 0); - if (!base) - panic("could not map CLINT"); - - clint_ipi_base = base + CLINT_IPI_OFF; - riscv_time_cmp = base + CLINT_TIME_CMP_OFF; - riscv_time_val = base + CLINT_TIME_VAL_OFF; - - clint_clear_ipi(boot_cpu_hartid); -} diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c index f383ef5672b2..226ccce0f9e0 100644 --- a/arch/riscv/kernel/sbi.c +++ b/arch/riscv/kernel/sbi.c @@ -547,6 +547,18 @@ static inline long sbi_get_firmware_version(void) return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); } +static void sbi_send_cpumask_ipi(const struct cpumask *target) +{ + struct cpumask hartid_mask; + + riscv_cpuid_to_hartid_mask(target, &hartid_mask); + + sbi_send_ipi(cpumask_bits(&hartid_mask)); +} + +static struct riscv_ipi_ops sbi_ipi_ops = { + .ipi_inject = sbi_send_cpumask_ipi +}; int __init sbi_init(void) { @@ -587,5 +599,7 @@ int __init sbi_init(void) __sbi_rfence = __sbi_rfence_v01; } + riscv_set_ipi_ops(&sbi_ipi_ops); + return 0; } diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index f04373be54a6..2c6dd329312b 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -18,7 +18,6 @@ #include <linux/swiotlb.h> #include <linux/smp.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/setup.h> #include <asm/sections.h> @@ -79,7 +78,6 @@ void __init setup_arch(char **cmdline_p) #else unflatten_device_tree(); #endif - clint_init_boot_cpu(); #ifdef CONFIG_SWIOTLB swiotlb_init(1); diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index 554b0fb47060..ea028d9e0d24 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -18,7 +18,6 @@ #include <linux/delay.h> #include <linux/irq_work.h> -#include <asm/clint.h> #include <asm/sbi.h> #include <asm/tlbflush.h> #include <asm/cacheflush.h> @@ -86,9 +85,25 @@ static void ipi_stop(void) wait_for_interrupt(); } +static struct riscv_ipi_ops *ipi_ops; + +void riscv_set_ipi_ops(struct riscv_ipi_ops *ops) +{ + ipi_ops = ops; +} +EXPORT_SYMBOL_GPL(riscv_set_ipi_ops); + +void riscv_clear_ipi(void) +{ + if (ipi_ops && ipi_ops->ipi_clear) + ipi_ops->ipi_clear(); + + csr_clear(CSR_IP, IE_SIE); +} +EXPORT_SYMBOL_GPL(riscv_clear_ipi); + static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) { - struct cpumask hartid_mask; int cpu; smp_mb__before_atomic(); @@ -96,33 +111,22 @@ static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - riscv_cpuid_to_hartid_mask(mask, &hartid_mask); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(&hartid_mask)); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(mask); else - clint_send_ipi_mask(mask); + pr_warn("SMP: IPI inject method not available\n"); } static void send_ipi_single(int cpu, enum ipi_message_type op) { - int hartid = cpuid_to_hartid_map(cpu); - smp_mb__before_atomic(); set_bit(op, &ipi_data[cpu].bits); smp_mb__after_atomic(); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_send_ipi(cpumask_bits(cpumask_of(hartid))); - else - clint_send_ipi_single(hartid); -} - -static inline void clear_ipi(void) -{ - if (IS_ENABLED(CONFIG_RISCV_SBI)) - csr_clear(CSR_IP, IE_SIE); + if (ipi_ops && ipi_ops->ipi_inject) + ipi_ops->ipi_inject(cpumask_of(cpu)); else - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + pr_warn("SMP: IPI inject method not available\n"); } #ifdef CONFIG_IRQ_WORK @@ -140,7 +144,7 @@ void handle_IPI(struct pt_regs *regs) irq_enter(); - clear_ipi(); + riscv_clear_ipi(); while (true) { unsigned long ops; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 356825a57551..96167d55ed98 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -24,7 +24,6 @@ #include <linux/of.h> #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> -#include <asm/clint.h> #include <asm/cpu_ops.h> #include <asm/irq.h> #include <asm/mmu_context.h> @@ -147,8 +146,7 @@ asmlinkage __visible void smp_callin(void) struct mm_struct *mm = &init_mm; unsigned int curr_cpuid = smp_processor_id(); - if (!IS_ENABLED(CONFIG_RISCV_SBI)) - clint_clear_ipi(cpuid_to_hartid_map(smp_processor_id())); + riscv_clear_ipi(); /* All kernel threads share the same mm context. */ mmgrab(mm); diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index 11d2f7d05f91..a76dd27fb2e8 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -1268,7 +1268,6 @@ static bool is_ri_cb_valid(struct runtime_instr_cb *cb) cb->pc == 1 && cb->qc == 0 && cb->reserved2 == 0 && - cb->key == PAGE_DEFAULT_KEY && cb->reserved3 == 0 && cb->reserved4 == 0 && cb->reserved5 == 0 && @@ -1330,7 +1329,11 @@ static int s390_runtime_instr_set(struct task_struct *target, kfree(data); return -EINVAL; } - + /* + * Override access key in any case, since user space should + * not be able to set it, nor should it care about it. + */ + ri_cb.key = PAGE_DEFAULT_KEY >> 4; preempt_disable(); if (!target->thread.ri_cb) target->thread.ri_cb = data; diff --git a/arch/s390/kernel/runtime_instr.c b/arch/s390/kernel/runtime_instr.c index 125c7f6e8715..1788a5454b6f 100644 --- a/arch/s390/kernel/runtime_instr.c +++ b/arch/s390/kernel/runtime_instr.c @@ -57,7 +57,7 @@ static void init_runtime_instr_cb(struct runtime_instr_cb *cb) cb->k = 1; cb->ps = 1; cb->pc = 1; - cb->key = PAGE_DEFAULT_KEY; + cb->key = PAGE_DEFAULT_KEY >> 4; cb->v = 1; } diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index 3902c9f6f2d6..4b62d6b55024 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -672,6 +672,19 @@ int zpci_disable_device(struct zpci_dev *zdev) } EXPORT_SYMBOL_GPL(zpci_disable_device); +void zpci_remove_device(struct zpci_dev *zdev) +{ + struct zpci_bus *zbus = zdev->zbus; + struct pci_dev *pdev; + + pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (pdev) { + if (pdev->is_virtfn) + return zpci_remove_virtfn(pdev, zdev->vfn); + pci_stop_and_remove_bus_device_locked(pdev); + } +} + int zpci_create_device(struct zpci_dev *zdev) { int rc; @@ -716,13 +729,8 @@ void zpci_release_device(struct kref *kref) { struct zpci_dev *zdev = container_of(kref, struct zpci_dev, kref); - if (zdev->zbus->bus) { - struct pci_dev *pdev; - - pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); - if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); - } + if (zdev->zbus->bus) + zpci_remove_device(zdev); switch (zdev->state) { case ZPCI_FN_STATE_ONLINE: diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 642a99384688..5967f3014156 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -132,13 +132,14 @@ static int zpci_bus_link_virtfn(struct pci_dev *pdev, { int rc; - virtfn->physfn = pci_dev_get(pdev); rc = pci_iov_sysfs_link(pdev, virtfn, vfid); - if (rc) { - pci_dev_put(pdev); - virtfn->physfn = NULL; + if (rc) return rc; - } + + virtfn->is_virtfn = 1; + virtfn->multifunction = 0; + virtfn->physfn = pci_dev_get(pdev); + return 0; } @@ -151,9 +152,9 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, int vfid = vfn - 1; /* Linux' vfid's start at 0 vfn at 1*/ int rc = 0; - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; - WARN_ON(vfid < 0); + if (!zbus->multifunction) + return 0; + /* If the parent PF for the given VF is also configured in the * instance, it must be on the same zbus. * We can then identify the parent PF by checking what @@ -165,11 +166,17 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, zdev = zbus->function[i]; if (zdev && zdev->is_physfn) { pdev = pci_get_slot(zbus->bus, zdev->devfn); + if (!pdev) + continue; cand_devfn = pci_iov_virtfn_devfn(pdev, vfid); if (cand_devfn == virtfn->devfn) { rc = zpci_bus_link_virtfn(pdev, virtfn, vfid); + /* balance pci_get_slot() */ + pci_dev_put(pdev); break; } + /* balance pci_get_slot() */ + pci_dev_put(pdev); } } return rc; @@ -178,12 +185,23 @@ static int zpci_bus_setup_virtfn(struct zpci_bus *zbus, static inline int zpci_bus_setup_virtfn(struct zpci_bus *zbus, struct pci_dev *virtfn, int vfn) { - virtfn->is_virtfn = 1; - virtfn->multifunction = 0; return 0; } #endif +void pcibios_bus_add_device(struct pci_dev *pdev) +{ + struct zpci_dev *zdev = to_zpci(pdev); + + /* + * With pdev->no_vf_scan the common PCI probing code does not + * perform PF/VF linking. + */ + if (zdev->vfn) + zpci_bus_setup_virtfn(zdev->zbus, pdev, zdev->vfn); + +} + static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) { struct pci_bus *bus; @@ -214,20 +232,10 @@ static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev) } pdev = pci_scan_single_device(bus, zdev->devfn); - if (pdev) { - if (!zdev->is_physfn) { - rc = zpci_bus_setup_virtfn(zbus, pdev, zdev->vfn); - if (rc) - goto failed_with_pdev; - } + if (pdev) pci_bus_add_device(pdev); - } - return 0; -failed_with_pdev: - pci_stop_and_remove_bus_device(pdev); - pci_dev_put(pdev); - return rc; + return 0; } static void zpci_bus_add_devices(struct zpci_bus *zbus) diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index 89be3c354b7b..4972433df458 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -29,3 +29,16 @@ static inline struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus, return (devfn >= ZPCI_FUNCTIONS_PER_BUS) ? NULL : zbus->function[devfn]; } + +#ifdef CONFIG_PCI_IOV +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) +{ + + pci_lock_rescan_remove(); + /* Linux' vfid's start at 0 vfn at 1 */ + pci_iov_remove_virtfn(pdev->physfn, vfn - 1); + pci_unlock_rescan_remove(); +} +#else /* CONFIG_PCI_IOV */ +static inline void zpci_remove_virtfn(struct pci_dev *pdev, int vfn) {} +#endif /* CONFIG_PCI_IOV */ diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index fdebd286f402..9a3a291cad43 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -92,6 +92,9 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) ret = clp_add_pci_device(ccdf->fid, ccdf->fh, 1); break; } + /* the configuration request may be stale */ + if (zdev->state != ZPCI_FN_STATE_STANDBY) + break; zdev->fh = ccdf->fh; zdev->state = ZPCI_FN_STATE_CONFIGURED; ret = zpci_enable_device(zdev); @@ -118,7 +121,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) if (!zdev) break; if (pdev) - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); ret = zpci_disable_device(zdev); if (ret) @@ -137,7 +140,7 @@ static void __zpci_event_availability(struct zpci_ccdf_avail *ccdf) /* Give the driver a hint that the function is * already unusable. */ pdev->error_state = pci_channel_io_perm_failure; - pci_stop_and_remove_bus_device_locked(pdev); + zpci_remove_device(zdev); } zdev->state = ZPCI_FN_STATE_STANDBY; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 39e592d0e0b4..e478e40fbe5a 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -30,12 +30,9 @@ #define STATIC static /* - * Use normal definitions of mem*() from string.c. There are already - * included header files which expect a definition of memset() and by - * the time we define memset macro, it is too late. + * Provide definitions of memzero and memmove as some of the decompressors will + * try to define their own functions if these are not defined as macros. */ -#undef memcpy -#undef memset #define memzero(s, n) memset((s), 0, (n)) #define memmove memmove diff --git a/arch/x86/boot/string.h b/arch/x86/boot/string.h index 995f7b7ad512..a232da487cd2 100644 --- a/arch/x86/boot/string.h +++ b/arch/x86/boot/string.h @@ -11,10 +11,7 @@ void *memcpy(void *dst, const void *src, size_t len); void *memset(void *dst, int c, size_t len); int memcmp(const void *s1, const void *s2, size_t len); -/* - * Access builtin version by default. If one needs to use optimized version, - * do "undef memcpy" in .c file and link against right string.c - */ +/* Access builtin version by default. */ #define memcpy(d,s,l) __builtin_memcpy(d,s,l) #define memset(d,c,l) __builtin_memset(d,c,l) #define memcmp __builtin_memcmp diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 98e4d8886f11..ae9b0d4615b3 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -374,12 +374,14 @@ For 32-bit we have the following conventions - kernel is built with * Fetch the per-CPU GSBASE value for this processor and put it in @reg. * We normally use %gs for accessing per-CPU data, but we are setting up * %gs here and obviously can not use %gs itself to access per-CPU data. + * + * Do not use RDPID, because KVM loads guest's TSC_AUX on vm-entry and + * may not restore the host's value until the CPU returns to userspace. + * Thus the kernel would consume a guest's TSC_AUX if an NMI arrives + * while running KVM's run loop. */ .macro GET_PERCPU_BASE reg:req - ALTERNATIVE \ - "LOAD_CPU_AND_NODE_SEG_LIMIT \reg", \ - "RDPID \reg", \ - X86_FEATURE_RDPID + LOAD_CPU_AND_NODE_SEG_LIMIT \reg andq $VDSO_CPUNODE_MASK, \reg movq __per_cpu_offset(, \reg, 8), \reg .endm diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index cb94ba86efd2..6a4ca27b2c9e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -390,6 +390,18 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"), INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(gt_requests, "event=0x03"), + INTEL_UNCORE_EVENT_DESC(gt_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(gt_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(ia_requests, "event=0x04"), + INTEL_UNCORE_EVENT_DESC(ia_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(ia_requests.unit, "MiB"), + + INTEL_UNCORE_EVENT_DESC(io_requests, "event=0x05"), + INTEL_UNCORE_EVENT_DESC(io_requests.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(io_requests.unit, "MiB"), + { /* end: all zeroes */ }, }; @@ -405,13 +417,35 @@ static struct uncore_event_desc snb_uncore_imc_events[] = { #define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE 0x5054 #define SNB_UNCORE_PCI_IMC_CTR_BASE SNB_UNCORE_PCI_IMC_DATA_READS_BASE +/* BW break down- legacy counters */ +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS 0x3 +#define SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE 0x5040 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS 0x4 +#define SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE 0x5044 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS 0x5 +#define SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE 0x5048 + enum perf_snb_uncore_imc_freerunning_types { - SNB_PCI_UNCORE_IMC_DATA = 0, + SNB_PCI_UNCORE_IMC_DATA_READS = 0, + SNB_PCI_UNCORE_IMC_DATA_WRITES, + SNB_PCI_UNCORE_IMC_GT_REQUESTS, + SNB_PCI_UNCORE_IMC_IA_REQUESTS, + SNB_PCI_UNCORE_IMC_IO_REQUESTS, + SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, }; static struct freerunning_counters snb_uncore_imc_freerunning[] = { - [SNB_PCI_UNCORE_IMC_DATA] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, 0x4, 0x0, 2, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_READS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_DATA_READS] = { SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_GT_REQUESTS] = { SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IA_REQUESTS] = { SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, + [SNB_PCI_UNCORE_IMC_IO_REQUESTS] = { SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE, + 0x0, 0x0, 1, 32 }, }; static struct attribute *snb_uncore_imc_formats_attr[] = { @@ -525,6 +559,18 @@ static int snb_uncore_imc_event_init(struct perf_event *event) base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE; idx = UNCORE_PMC_IDX_FREERUNNING; break; + case SNB_UNCORE_PCI_IMC_GT_REQUESTS: + base = SNB_UNCORE_PCI_IMC_GT_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IA_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IA_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; + case SNB_UNCORE_PCI_IMC_IO_REQUESTS: + base = SNB_UNCORE_PCI_IMC_IO_REQUESTS_BASE; + idx = UNCORE_PMC_IDX_FREERUNNING; + break; default: return -EINVAL; } @@ -598,7 +644,7 @@ static struct intel_uncore_ops snb_uncore_imc_ops = { static struct intel_uncore_type snb_uncore_imc = { .name = "imc", - .num_counters = 2, + .num_counters = 5, .num_boxes = 1, .num_freerunning_types = SNB_PCI_UNCORE_IMC_FREERUNNING_TYPE_MAX, .mmio_map_size = SNB_UNCORE_PCI_IMC_MAP_SIZE, diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index b9c2667ac46c..bc9758ef292e 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -81,11 +81,8 @@ extern unsigned long efi_fw_vendor, efi_config_table; kernel_fpu_end(); \ }) - #define arch_efi_call_virt(p, f, args...) p->f(args) -#define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) - #else /* !CONFIG_X86_32 */ #define EFI_LOADER_SIGNATURE "EL64" @@ -125,9 +122,6 @@ struct efi_scratch { kernel_fpu_end(); \ }) -extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, - u32 type, u64 attribute); - #ifdef CONFIG_KASAN /* * CONFIG_KASAN may redefine memset to __memset. __memset function is present @@ -143,17 +137,13 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern struct efi_scratch efi_scratch; -extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable); extern int __init efi_memblock_x86_reserve_range(void); extern void __init efi_print_memmap(void); -extern void __init efi_memory_uc(u64 addr, unsigned long size); extern void __init efi_map_region(efi_memory_desc_t *md); extern void __init efi_map_region_fixed(efi_memory_desc_t *md); extern void efi_sync_low_kernel_mappings(void); extern int __init efi_alloc_page_tables(void); extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); -extern void __init old_map_region(efi_memory_desc_t *md); -extern void __init runtime_code_page_mkexec(void); extern void __init efi_runtime_update_mappings(void); extern void __init efi_dump_pagetable(void); extern void __init efi_apply_memmap_quirks(void); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5ab3af7275d8..5303dbc5c9bc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1596,7 +1596,8 @@ asmlinkage void kvm_spurious_fault(void); _ASM_EXTABLE(666b, 667b) #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4e03841f053d..a5d0207e7189 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1916,7 +1916,8 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) +int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, + unsigned flags) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 599d73206299..33945283fe07 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,7 +975,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE; + X86_CR4_SMEP; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -10751,9 +10751,11 @@ EXPORT_SYMBOL_GPL(kvm_spec_ctrl_test_value); void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code) { struct x86_exception fault; + u32 access = error_code & + (PFERR_WRITE_MASK | PFERR_FETCH_MASK | PFERR_USER_MASK); if (!(error_code & PFERR_PRESENT_MASK) || - vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, error_code, &fault) != UNMAPPED_GVA) { + vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, &fault) != UNMAPPED_GVA) { /* * If vcpu->arch.walk_mmu->gva_to_gpa succeeded, the page * tables probably do not match the TLB. Just proceed diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 9f9aad42ccff..89395a5049bb 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -26,6 +26,7 @@ #include <asm/xen/pci.h> #include <asm/xen/cpuid.h> #include <asm/apic.h> +#include <asm/acpi.h> #include <asm/i8259.h> static int xen_pcifront_enable_irq(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index f6ea8f1a9d57..d37ebe6e70d7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -49,7 +49,6 @@ #include <asm/efi.h> #include <asm/e820/api.h> #include <asm/time.h> -#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> #include <asm/uv/uv.h> @@ -496,74 +495,6 @@ void __init efi_init(void) efi_print_memmap(); } -#if defined(CONFIG_X86_32) - -void __init efi_set_executable(efi_memory_desc_t *md, bool executable) -{ - u64 addr, npages; - - addr = md->virt_addr; - npages = md->num_pages; - - memrange_efi_to_native(&addr, &npages); - - if (executable) - set_memory_x(addr, npages); - else - set_memory_nx(addr, npages); -} - -void __init runtime_code_page_mkexec(void) -{ - efi_memory_desc_t *md; - - /* Make EFI runtime service code area executable */ - for_each_efi_memory_desc(md) { - if (md->type != EFI_RUNTIME_SERVICES_CODE) - continue; - - efi_set_executable(md, true); - } -} - -void __init efi_memory_uc(u64 addr, unsigned long size) -{ - unsigned long page_shift = 1UL << EFI_PAGE_SHIFT; - u64 npages; - - npages = round_up(size, page_shift) / page_shift; - memrange_efi_to_native(&addr, &npages); - set_memory_uc(addr, npages); -} - -void __init old_map_region(efi_memory_desc_t *md) -{ - u64 start_pfn, end_pfn, end; - unsigned long size; - void *va; - - start_pfn = PFN_DOWN(md->phys_addr); - size = md->num_pages << PAGE_SHIFT; - end = md->phys_addr + size; - end_pfn = PFN_UP(end); - - if (pfn_range_is_mapped(start_pfn, end_pfn)) { - va = __va(md->phys_addr); - - if (!(md->attribute & EFI_MEMORY_WB)) - efi_memory_uc((u64)(unsigned long)va, size); - } else - va = efi_ioremap(md->phys_addr, size, - md->type, md->attribute); - - md->virt_addr = (u64) (unsigned long) va; - if (!va) - pr_err("ioremap of 0x%llX failed!\n", - (unsigned long long)md->phys_addr); -} - -#endif - /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 826ead67753d..e06a199423c0 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -29,9 +29,35 @@ #include <asm/io.h> #include <asm/desc.h> #include <asm/page.h> +#include <asm/set_memory.h> #include <asm/tlbflush.h> #include <asm/efi.h> +void __init efi_map_region(efi_memory_desc_t *md) +{ + u64 start_pfn, end_pfn, end; + unsigned long size; + void *va; + + start_pfn = PFN_DOWN(md->phys_addr); + size = md->num_pages << PAGE_SHIFT; + end = md->phys_addr + size; + end_pfn = PFN_UP(end); + + if (pfn_range_is_mapped(start_pfn, end_pfn)) { + va = __va(md->phys_addr); + + if (!(md->attribute & EFI_MEMORY_WB)) + set_memory_uc((unsigned long)va, md->num_pages); + } else { + va = ioremap_cache(md->phys_addr, size); + } + + md->virt_addr = (unsigned long)va; + if (!va) + pr_err("ioremap of 0x%llX failed!\n", md->phys_addr); +} + /* * To make EFI call EFI runtime service in physical addressing mode we need * prolog/epilog before/after the invocation to claim the EFI runtime service @@ -58,11 +84,6 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) return 0; } -void __init efi_map_region(efi_memory_desc_t *md) -{ - old_map_region(md); -} - void __init efi_map_region_fixed(efi_memory_desc_t *md) {} void __init parse_efi_setup(u64 phys_addr, u32 data_len) {} @@ -107,6 +128,15 @@ efi_status_t __init efi_set_virtual_address_map(unsigned long memory_map_size, void __init efi_runtime_update_mappings(void) { - if (__supported_pte_mask & _PAGE_NX) - runtime_code_page_mkexec(); + if (__supported_pte_mask & _PAGE_NX) { + efi_memory_desc_t *md; + + /* Make EFI runtime service code area executable */ + for_each_efi_memory_desc(md) { + if (md->type != EFI_RUNTIME_SERVICES_CODE) + continue; + + set_memory_x(md->virt_addr, md->num_pages); + } + } } diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 413583f904a6..6af4da1149ba 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -259,6 +259,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) npages = (__end_rodata - __start_rodata) >> PAGE_SHIFT; rodata = __pa(__start_rodata); pfn = rodata >> PAGE_SHIFT; + + pf = _PAGE_NX | _PAGE_ENC; if (kernel_map_pages_in_pgd(pgd, pfn, rodata, npages, pf)) { pr_err("Failed to map kernel rodata 1:1\n"); return 1; diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index 3576ad7bd380..68b087bff59c 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -653,9 +653,8 @@ config ATCPIT100_TIMER This option enables support for the Andestech ATCPIT100 timers. config RISCV_TIMER - bool "Timer for the RISC-V platform" + bool "Timer for the RISC-V platform" if COMPILE_TEST depends on GENERIC_SCHED_CLOCK && RISCV - default y select TIMER_PROBE select TIMER_OF help @@ -663,6 +662,15 @@ config RISCV_TIMER is accessed via both the SBI and the rdcycle instruction. This is required for all RISC-V systems. +config CLINT_TIMER + bool "CLINT Timer for the RISC-V platform" if COMPILE_TEST + depends on GENERIC_SCHED_CLOCK && RISCV + select TIMER_PROBE + select TIMER_OF + help + This option enables the CLINT timer for RISC-V systems. The CLINT + driver is usually used for NoMMU RISC-V systems. + config CSKY_MP_TIMER bool "SMP Timer for the C-SKY platform" if COMPILE_TEST depends on CSKY diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile index eaedb7240ae7..1c444cc3bb44 100644 --- a/drivers/clocksource/Makefile +++ b/drivers/clocksource/Makefile @@ -89,6 +89,7 @@ obj-$(CONFIG_CLKSRC_ST_LPC) += clksrc_st_lpc.o obj-$(CONFIG_X86_NUMACHIP) += numachip.o obj-$(CONFIG_ATCPIT100_TIMER) += timer-atcpit100.o obj-$(CONFIG_RISCV_TIMER) += timer-riscv.o +obj-$(CONFIG_CLINT_TIMER) += timer-clint.o obj-$(CONFIG_CSKY_MP_TIMER) += timer-mp-csky.o obj-$(CONFIG_GX6605S_TIMER) += timer-gx6605s.o obj-$(CONFIG_HYPERV_TIMER) += hyperv_timer.o diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c new file mode 100644 index 000000000000..8eeafa82c03d --- /dev/null +++ b/drivers/clocksource/timer-clint.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * + * Most of the M-mode (i.e. NoMMU) RISC-V systems usually have a + * CLINT MMIO timer device. + */ + +#define pr_fmt(fmt) "clint: " fmt +#include <linux/bitops.h> +#include <linux/clocksource.h> +#include <linux/clockchips.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/sched_clock.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include <linux/interrupt.h> +#include <linux/of_irq.h> +#include <linux/smp.h> + +#define CLINT_IPI_OFF 0 +#define CLINT_TIMER_CMP_OFF 0x4000 +#define CLINT_TIMER_VAL_OFF 0xbff8 + +/* CLINT manages IPI and Timer for RISC-V M-mode */ +static u32 __iomem *clint_ipi_base; +static u64 __iomem *clint_timer_cmp; +static u64 __iomem *clint_timer_val; +static unsigned long clint_timer_freq; +static unsigned int clint_timer_irq; + +static void clint_send_ipi(const struct cpumask *target) +{ + unsigned int cpu; + + for_each_cpu(cpu, target) + writel(1, clint_ipi_base + cpuid_to_hartid_map(cpu)); +} + +static void clint_clear_ipi(void) +{ + writel(0, clint_ipi_base + cpuid_to_hartid_map(smp_processor_id())); +} + +static struct riscv_ipi_ops clint_ipi_ops = { + .ipi_inject = clint_send_ipi, + .ipi_clear = clint_clear_ipi, +}; + +#ifdef CONFIG_64BIT +#define clint_get_cycles() readq_relaxed(clint_timer_val) +#else +#define clint_get_cycles() readl_relaxed(clint_timer_val) +#define clint_get_cycles_hi() readl_relaxed(((u32 *)clint_timer_val) + 1) +#endif + +#ifdef CONFIG_64BIT +static u64 notrace clint_get_cycles64(void) +{ + return clint_get_cycles(); +} +#else /* CONFIG_64BIT */ +static u64 notrace clint_get_cycles64(void) +{ + u32 hi, lo; + + do { + hi = clint_get_cycles_hi(); + lo = clint_get_cycles(); + } while (hi != clint_get_cycles_hi()); + + return ((u64)hi << 32) | lo; +} +#endif /* CONFIG_64BIT */ + +static u64 clint_rdtime(struct clocksource *cs) +{ + return clint_get_cycles64(); +} + +static struct clocksource clint_clocksource = { + .name = "clint_clocksource", + .rating = 300, + .mask = CLOCKSOURCE_MASK(64), + .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .read = clint_rdtime, +}; + +static int clint_clock_next_event(unsigned long delta, + struct clock_event_device *ce) +{ + void __iomem *r = clint_timer_cmp + + cpuid_to_hartid_map(smp_processor_id()); + + csr_set(CSR_IE, IE_TIE); + writeq_relaxed(clint_get_cycles64() + delta, r); + return 0; +} + +static DEFINE_PER_CPU(struct clock_event_device, clint_clock_event) = { + .name = "clint_clockevent", + .features = CLOCK_EVT_FEAT_ONESHOT, + .rating = 100, + .set_next_event = clint_clock_next_event, +}; + +static int clint_timer_starting_cpu(unsigned int cpu) +{ + struct clock_event_device *ce = per_cpu_ptr(&clint_clock_event, cpu); + + ce->cpumask = cpumask_of(cpu); + clockevents_config_and_register(ce, clint_timer_freq, 100, 0x7fffffff); + + enable_percpu_irq(clint_timer_irq, + irq_get_trigger_type(clint_timer_irq)); + return 0; +} + +static int clint_timer_dying_cpu(unsigned int cpu) +{ + disable_percpu_irq(clint_timer_irq); + return 0; +} + +static irqreturn_t clint_timer_interrupt(int irq, void *dev_id) +{ + struct clock_event_device *evdev = this_cpu_ptr(&clint_clock_event); + + csr_clear(CSR_IE, IE_TIE); + evdev->event_handler(evdev); + + return IRQ_HANDLED; +} + +static int __init clint_timer_init_dt(struct device_node *np) +{ + int rc; + u32 i, nr_irqs; + void __iomem *base; + struct of_phandle_args oirq; + + /* + * Ensure that CLINT device interrupts are either RV_IRQ_TIMER or + * RV_IRQ_SOFT. If it's anything else then we ignore the device. + */ + nr_irqs = of_irq_count(np); + for (i = 0; i < nr_irqs; i++) { + if (of_irq_parse_one(np, i, &oirq)) { + pr_err("%pOFP: failed to parse irq %d.\n", np, i); + continue; + } + + if ((oirq.args_count != 1) || + (oirq.args[0] != RV_IRQ_TIMER && + oirq.args[0] != RV_IRQ_SOFT)) { + pr_err("%pOFP: invalid irq %d (hwirq %d)\n", + np, i, oirq.args[0]); + return -ENODEV; + } + + /* Find parent irq domain and map timer irq */ + if (!clint_timer_irq && + oirq.args[0] == RV_IRQ_TIMER && + irq_find_host(oirq.np)) + clint_timer_irq = irq_of_parse_and_map(np, i); + } + + /* If CLINT timer irq not found then fail */ + if (!clint_timer_irq) { + pr_err("%pOFP: timer irq not found\n", np); + return -ENODEV; + } + + base = of_iomap(np, 0); + if (!base) { + pr_err("%pOFP: could not map registers\n", np); + return -ENODEV; + } + + clint_ipi_base = base + CLINT_IPI_OFF; + clint_timer_cmp = base + CLINT_TIMER_CMP_OFF; + clint_timer_val = base + CLINT_TIMER_VAL_OFF; + clint_timer_freq = riscv_timebase; + + pr_info("%pOFP: timer running at %ld Hz\n", np, clint_timer_freq); + + rc = clocksource_register_hz(&clint_clocksource, clint_timer_freq); + if (rc) { + pr_err("%pOFP: clocksource register failed [%d]\n", np, rc); + goto fail_iounmap; + } + + sched_clock_register(clint_get_cycles64, 64, clint_timer_freq); + + rc = request_percpu_irq(clint_timer_irq, clint_timer_interrupt, + "clint-timer", &clint_clock_event); + if (rc) { + pr_err("registering percpu irq failed [%d]\n", rc); + goto fail_iounmap; + } + + rc = cpuhp_setup_state(CPUHP_AP_CLINT_TIMER_STARTING, + "clockevents/clint/timer:starting", + clint_timer_starting_cpu, + clint_timer_dying_cpu); + if (rc) { + pr_err("%pOFP: cpuhp setup state failed [%d]\n", np, rc); + goto fail_free_irq; + } + + riscv_set_ipi_ops(&clint_ipi_ops); + clint_clear_ipi(); + + return 0; + +fail_free_irq: + free_irq(clint_timer_irq, &clint_clock_event); +fail_iounmap: + iounmap(base); + return rc; +} + +TIMER_OF_DECLARE(clint_timer, "riscv,clint0", clint_timer_init_dt); +TIMER_OF_DECLARE(clint_timer1, "sifive,clint0", clint_timer_init_dt); diff --git a/drivers/clocksource/timer-riscv.c b/drivers/clocksource/timer-riscv.c index 9de1dabfb126..c51c5ed15aa7 100644 --- a/drivers/clocksource/timer-riscv.c +++ b/drivers/clocksource/timer-riscv.c @@ -19,26 +19,13 @@ #include <linux/of_irq.h> #include <asm/smp.h> #include <asm/sbi.h> - -u64 __iomem *riscv_time_cmp; -u64 __iomem *riscv_time_val; - -static inline void mmio_set_timer(u64 val) -{ - void __iomem *r; - - r = riscv_time_cmp + cpuid_to_hartid_map(smp_processor_id()); - writeq_relaxed(val, r); -} +#include <asm/timex.h> static int riscv_clock_next_event(unsigned long delta, struct clock_event_device *ce) { csr_set(CSR_IE, IE_TIE); - if (IS_ENABLED(CONFIG_RISCV_SBI)) - sbi_set_timer(get_cycles64() + delta); - else - mmio_set_timer(get_cycles64() + delta); + sbi_set_timer(get_cycles64() + delta); return 0; } diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 5860ca41185c..2acd9f9284a2 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1710,9 +1710,9 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) - tp_event = HW_EVENT_ERR_FATAL; - else tp_event = HW_EVENT_ERR_UNCORRECTED; + else + tp_event = HW_EVENT_ERR_FATAL; } else { tp_event = HW_EVENT_ERR_CORRECTED; } diff --git a/drivers/edac/pnd2_edac.c b/drivers/edac/pnd2_edac.c index fd363746f5b0..b8fc4b84fd86 100644 --- a/drivers/edac/pnd2_edac.c +++ b/drivers/edac/pnd2_edac.c @@ -1155,7 +1155,7 @@ static void pnd2_mce_output_error(struct mem_ctl_info *mci, const struct mce *m, u32 optypenum = GET_BITFIELD(m->status, 4, 6); int rc; - tp_event = uc_err ? (ripv ? HW_EVENT_ERR_FATAL : HW_EVENT_ERR_UNCORRECTED) : + tp_event = uc_err ? (ripv ? HW_EVENT_ERR_UNCORRECTED : HW_EVENT_ERR_FATAL) : HW_EVENT_ERR_CORRECTED; /* diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index d414698ca324..c5ab634cb6a4 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -2982,9 +2982,9 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) { - tp_event = HW_EVENT_ERR_FATAL; - } else { tp_event = HW_EVENT_ERR_UNCORRECTED; + } else { + tp_event = HW_EVENT_ERR_FATAL; } } else { tp_event = HW_EVENT_ERR_CORRECTED; diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index 6d8d6dc626bf..2b4ce8e5ac2f 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -493,9 +493,9 @@ static void skx_mce_output_error(struct mem_ctl_info *mci, if (uncorrected_error) { core_err_cnt = 1; if (ripv) { - tp_event = HW_EVENT_ERR_FATAL; - } else { tp_event = HW_EVENT_ERR_UNCORRECTED; + } else { + tp_event = HW_EVENT_ERR_FATAL; } } else { tp_event = HW_EVENT_ERR_CORRECTED; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index fdd1db025dbf..3aa07c3b5136 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -381,6 +381,7 @@ static int __init efisubsys_init(void) efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { pr_err("efi: Firmware registration failed.\n"); + destroy_workqueue(efi_rts_wq); return -ENOMEM; } @@ -424,6 +425,7 @@ err_unregister: generic_ops_unregister(); err_put: kobject_put(efi_kobj); + destroy_workqueue(efi_rts_wq); return error; } diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c index 6bca70bbb43d..f735db55adc0 100644 --- a/drivers/firmware/efi/libstub/efi-stub-helper.c +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c @@ -187,20 +187,28 @@ int efi_printk(const char *fmt, ...) */ efi_status_t efi_parse_options(char const *cmdline) { - size_t len = strlen(cmdline) + 1; + size_t len; efi_status_t status; char *str, *buf; + if (!cmdline) + return EFI_SUCCESS; + + len = strnlen(cmdline, COMMAND_LINE_SIZE - 1) + 1; status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, len, (void **)&buf); if (status != EFI_SUCCESS) return status; - str = skip_spaces(memcpy(buf, cmdline, len)); + memcpy(buf, cmdline, len - 1); + buf[len - 1] = '\0'; + str = skip_spaces(buf); while (*str) { char *param, *val; str = next_arg(str, ¶m, &val); + if (!val && !strcmp(param, "--")) + break; if (!strcmp(param, "nokaslr")) { efi_nokaslr = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index c7fd0c47b254..1102de76d876 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -195,19 +195,32 @@ static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev, unsigned int engine_id, unsigned int queue_id) { - uint32_t sdma_engine_reg_base[2] = { - SOC15_REG_OFFSET(SDMA0, 0, - mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL, - SOC15_REG_OFFSET(SDMA1, 0, - mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL - }; - uint32_t retval = sdma_engine_reg_base[engine_id] + uint32_t sdma_engine_reg_base = 0; + uint32_t sdma_rlc_reg_offset; + + switch (engine_id) { + default: + dev_warn(adev->dev, + "Invalid sdma engine id (%d), using engine id 0\n", + engine_id); + fallthrough; + case 0: + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA0, 0, + mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; + break; + case 1: + sdma_engine_reg_base = SOC15_REG_OFFSET(SDMA1, 0, + mmSDMA1_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL; + break; + } + + sdma_rlc_reg_offset = sdma_engine_reg_base + queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL); pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id, - queue_id, retval); + queue_id, sdma_rlc_reg_offset); - return retval; + return sdma_rlc_reg_offset; } static inline struct v9_mqd *get_mqd(void *mqd) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index bcce4c0be462..1bedb416eebd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1243,7 +1243,6 @@ void amdgpu_ras_debugfs_remove(struct amdgpu_device *adev, if (!obj || !obj->ent) return; - debugfs_remove(obj->ent); obj->ent = NULL; put_obj(obj); } @@ -1257,7 +1256,6 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev) amdgpu_ras_debugfs_remove(adev, &obj->head); } - debugfs_remove_recursive(con->dir); con->dir = NULL; } /* debugfs end */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 134cc36e30c5..0739e259bf91 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -462,7 +462,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev, unsigned int pages; int i, r; - *sgt = kmalloc(sizeof(*sg), GFP_KERNEL); + *sgt = kmalloc(sizeof(**sgt), GFP_KERNEL); if (!*sgt) return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index cb9d60a4e05e..b95f22262a90 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -691,6 +691,7 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_FIFO_SIZES, 0xffffffff, 0x00000f00), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_UTCL1_CNTL1, 0x30000000, 0x30000000) }; static const struct soc15_reg_rlcg rlcg_access_gc_9_0[] = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c index fa0bca3e1f73..5d2505956f84 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c +++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_1.c @@ -135,6 +135,12 @@ static void gfxhub_v2_1_init_cache_regs(struct amdgpu_device *adev) { uint32_t tmp; + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + /* Setup L2 cache */ tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_CNTL); tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL, ENABLE_L2_CACHE, 1); @@ -190,6 +196,12 @@ static void gfxhub_v2_1_enable_system_domain(struct amdgpu_device *adev) static void gfxhub_v2_1_disable_identity_aperture(struct amdgpu_device *adev) { + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32, 0xFFFFFFFF); WREG32_SOC15(GC, 0, mmGCVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_HI32, @@ -326,6 +338,13 @@ void gfxhub_v2_1_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; + + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + tmp = RREG32_SOC15(GC, 0, mmGCVM_L2_PROTECTION_FAULT_CNTL); tmp = REG_SET_FIELD(tmp, GCVM_L2_PROTECTION_FAULT_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index 757fa8e83f5b..c79fc54bc3c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -134,6 +134,12 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev) { uint32_t tmp; + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + /* Setup L2 cache */ tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL); tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL, ENABLE_L2_CACHE, 1); @@ -189,6 +195,12 @@ static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev) static void mmhub_v2_0_disable_identity_aperture(struct amdgpu_device *adev) { + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CONTEXT1_IDENTITY_APERTURE_LOW_ADDR_LO32, 0xFFFFFFFF); @@ -318,6 +330,13 @@ void mmhub_v2_0_gart_disable(struct amdgpu_device *adev) void mmhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev, bool value) { u32 tmp; + + /* These registers are not accessible to VF-SRIOV. + * The PF will program them instead. + */ + if (amdgpu_sriov_vf(adev)) + return; + tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_L2_PROTECTION_FAULT_CNTL); tmp = REG_SET_FIELD(tmp, MMVM_L2_PROTECTION_FAULT_CNTL, RANGE_PROTECTION_FAULT_ENABLE_DEFAULT, value); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index d488d250805d..e16874f30d5d 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -179,12 +179,11 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) } break; case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: err = psp_init_ta_microcode(&adev->psp, chip_name); if (err) return err; break; - case CHIP_NAVY_FLOUNDER: - break; default: BUG(); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index e4b33c67b634..df9338257ae0 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2196,6 +2196,7 @@ void amdgpu_dm_update_connector_after_detect( drm_connector_update_edid_property(connector, aconnector->edid); + drm_add_edid_modes(connector, aconnector->edid); if (aconnector->dc_link->aux_mode) drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c index 078b7e344185..2d5c7daaee23 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -1108,6 +1108,18 @@ static enum bp_result bios_parser_enable_disp_power_gating( action); } +static enum bp_result bios_parser_enable_lvtma_control( + struct dc_bios *dcb, + uint8_t uc_pwr_on) +{ + struct bios_parser *bp = BP_FROM_DCB(dcb); + + if (!bp->cmd_tbl.enable_lvtma_control) + return BP_RESULT_FAILURE; + + return bp->cmd_tbl.enable_lvtma_control(bp, uc_pwr_on); +} + static bool bios_parser_is_accelerated_mode( struct dc_bios *dcb) { @@ -2208,7 +2220,9 @@ static const struct dc_vbios_funcs vbios_funcs = { .get_board_layout_info = bios_get_board_layout_info, .pack_data_tables = bios_parser_pack_data_tables, - .get_atom_dc_golden_table = bios_get_atom_dc_golden_table + .get_atom_dc_golden_table = bios_get_atom_dc_golden_table, + + .enable_lvtma_control = bios_parser_enable_lvtma_control }; static bool bios_parser2_construct( diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index bed91572f82a..eb3ae5c3677c 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -904,6 +904,33 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id) return 0; } +/****************************************************************************** + ****************************************************************************** + ** + ** LVTMA CONTROL + ** + ****************************************************************************** + *****************************************************************************/ + +static enum bp_result enable_lvtma_control( + struct bios_parser *bp, + uint8_t uc_pwr_on); + +static void init_enable_lvtma_control(struct bios_parser *bp) +{ + /* TODO add switch for table vrsion */ + bp->cmd_tbl.enable_lvtma_control = enable_lvtma_control; + +} + +static enum bp_result enable_lvtma_control( + struct bios_parser *bp, + uint8_t uc_pwr_on) +{ + enum bp_result result = BP_RESULT_FAILURE; + return result; +} + void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) { init_dig_encoder_control(bp); @@ -919,4 +946,5 @@ void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp) init_set_dce_clock(bp); init_get_smu_clock_info(bp); + init_enable_lvtma_control(bp); } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h index 7a2af24dfe60..7bdce013cde5 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.h +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.h @@ -94,7 +94,8 @@ struct cmd_tbl { struct bp_set_dce_clock_parameters *bp_params); unsigned int (*get_smu_clock_info)( struct bios_parser *bp, uint8_t id); - + enum bp_result (*enable_lvtma_control)(struct bios_parser *bp, + uint8_t uc_pwr_on); }; void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 4bd6e03a7ef3..117d8aaf2a9b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3286,12 +3286,11 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx) core_link_set_avmute(pipe_ctx, true); } + dc->hwss.blank_stream(pipe_ctx); #if defined(CONFIG_DRM_AMD_DC_HDCP) update_psp_stream_config(pipe_ctx, true); #endif - dc->hwss.blank_stream(pipe_ctx); - if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) deallocate_mst_payload(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h index d06d07042a12..0811f941f430 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h @@ -136,6 +136,10 @@ struct dc_vbios_funcs { enum bp_result (*get_atom_dc_golden_table)( struct dc_bios *dcb); + + enum bp_result (*enable_lvtma_control)( + struct dc_bios *bios, + uint8_t uc_pwr_on); }; struct bios_registers { diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h index 70ec691e14d2..99c68ca9c7e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.h @@ -49,7 +49,7 @@ #define DCN_PANEL_CNTL_REG_LIST()\ DCN_PANEL_CNTL_SR(PWRSEQ_CNTL, LVTMA), \ DCN_PANEL_CNTL_SR(PWRSEQ_STATE, LVTMA), \ - DCE_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \ + DCN_PANEL_CNTL_SR(PWRSEQ_REF_DIV, LVTMA), \ SR(BL_PWM_CNTL), \ SR(BL_PWM_CNTL2), \ SR(BL_PWM_PERIOD_CNTL), \ diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 49380ed3aeae..45c9e9027886 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -842,6 +842,17 @@ void dce110_edp_power_control( cntl.coherent = false; cntl.lanes_number = LANE_COUNT_FOUR; cntl.hpd_sel = link->link_enc->hpd_source; + + if (ctx->dc->ctx->dmub_srv && + ctx->dc->debug.dmub_command_table) { + if (cntl.action == TRANSMITTER_CONTROL_POWER_ON) + bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_POWER_ON); + else + bp_result = ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_POWER_OFF); + } + bp_result = link_transmitter_control(ctx->dc_bios, &cntl); if (!power_up) @@ -919,8 +930,21 @@ void dce110_edp_backlight_control( /*edp 1.2*/ if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) edp_receiver_ready_T7(link); + + if (ctx->dc->ctx->dmub_srv && + ctx->dc->debug.dmub_command_table) { + if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) + ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_LCD_BLON); + else + ctx->dc_bios->funcs->enable_lvtma_control(ctx->dc_bios, + LVTMA_CONTROL_LCD_BLOFF); + } + link_transmitter_control(ctx->dc_bios, &cntl); + + if (enable && link->dpcd_sink_ext_caps.bits.oled) msleep(OLED_POST_T7_DELAY); diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c index 07b2f9399671..842abb4c475b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c @@ -121,35 +121,35 @@ void enc1_update_generic_info_packet( switch (packet_index) { case 0: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC0_FRAME_UPDATE, 1); + AFMT_GENERIC0_IMMEDIATE_UPDATE, 1); break; case 1: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC1_FRAME_UPDATE, 1); + AFMT_GENERIC1_IMMEDIATE_UPDATE, 1); break; case 2: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC2_FRAME_UPDATE, 1); + AFMT_GENERIC2_IMMEDIATE_UPDATE, 1); break; case 3: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC3_FRAME_UPDATE, 1); + AFMT_GENERIC3_IMMEDIATE_UPDATE, 1); break; case 4: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC4_FRAME_UPDATE, 1); + AFMT_GENERIC4_IMMEDIATE_UPDATE, 1); break; case 5: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC5_FRAME_UPDATE, 1); + AFMT_GENERIC5_IMMEDIATE_UPDATE, 1); break; case 6: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC6_FRAME_UPDATE, 1); + AFMT_GENERIC6_IMMEDIATE_UPDATE, 1); break; case 7: REG_UPDATE(AFMT_VBI_PACKET_CONTROL1, - AFMT_GENERIC7_FRAME_UPDATE, 1); + AFMT_GENERIC7_IMMEDIATE_UPDATE, 1); break; default: break; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h index ed385b1477be..30eae7459d50 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h @@ -281,7 +281,14 @@ struct dcn10_stream_enc_registers { SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_FRAME_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC0_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC1_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC2_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC3_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC4_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_IMMEDIATE_UPDATE, mask_sh),\ + SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_IMMEDIATE_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC5_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC6_FRAME_UPDATE, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL1, AFMT_GENERIC7_FRAME_UPDATE, mask_sh),\ @@ -345,7 +352,14 @@ struct dcn10_stream_enc_registers { type AFMT_GENERIC2_FRAME_UPDATE;\ type AFMT_GENERIC3_FRAME_UPDATE;\ type AFMT_GENERIC4_FRAME_UPDATE;\ + type AFMT_GENERIC0_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC1_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC2_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC3_IMMEDIATE_UPDATE;\ type AFMT_GENERIC4_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC5_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC6_IMMEDIATE_UPDATE;\ + type AFMT_GENERIC7_IMMEDIATE_UPDATE;\ type AFMT_GENERIC5_FRAME_UPDATE;\ type AFMT_GENERIC6_FRAME_UPDATE;\ type AFMT_GENERIC7_FRAME_UPDATE;\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index 66180b4332f1..c8cfd3ba1c15 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1457,8 +1457,8 @@ static void dcn20_update_dchubp_dpp( /* Any updates are handled in dc interface, just need to apply existing for plane enable */ if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed || - pipe_ctx->update_flags.bits.scaler || pipe_ctx->update_flags.bits.viewport) - && pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { + pipe_ctx->update_flags.bits.scaler || viewport_changed == true) && + pipe_ctx->stream->cursor_attributes.address.quad_part != 0) { dc->hwss.set_cursor_position(pipe_ctx); dc->hwss.set_cursor_attribute(pipe_ctx); diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h index bf0044f7417e..dcbf28dd72d4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h @@ -167,7 +167,9 @@ LE_SF(DCIO_SOFT_RESET, UNIPHYB_SOFT_RESET, mask_sh),\ LE_SF(DCIO_SOFT_RESET, UNIPHYC_SOFT_RESET, mask_sh),\ LE_SF(DCIO_SOFT_RESET, UNIPHYD_SOFT_RESET, mask_sh),\ - LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh) + LE_SF(DCIO_SOFT_RESET, UNIPHYE_SOFT_RESET, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh) #define LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh)\ LINK_ENCODER_MASK_SH_LIST_DCN10(mask_sh),\ diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 790baf552695..9140b3fc767a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3141,7 +3141,7 @@ static bool dcn20_validate_bandwidth_internal(struct dc *dc, struct dc_state *co int vlevel = 0; int pipe_split_from[MAX_PIPES]; int pipe_cnt = 0; - display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_KERNEL); + display_e2e_pipe_params_st *pipes = kzalloc(dc->res_pool->pipe_count * sizeof(display_e2e_pipe_params_st), GFP_ATOMIC); DC_LOGGER_INIT(dc->ctx->logger); BW_VAL_TRACE_COUNT(); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h index 8e9fd59ccde8..2fbf879cd327 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_link_encoder.h @@ -61,7 +61,10 @@ DPCS_DCN2_MASK_SH_LIST(mask_sh),\ LE_SF(DPCSTX0_DPCSTX_TX_CNTL, DPCS_TX_DATA_ORDER_INVERT_18_BIT, mask_sh),\ LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL0, RDPCS_PHY_TX_VBOOST_LVL, mask_sh),\ - LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh) + LE_SF(RDPCSTX0_RDPCSTX_CLOCK_CNTL, RDPCS_TX_CLK_EN, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, mask_sh),\ + LE_SF(RDPCSTX0_RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, mask_sh) + void dcn30_link_encoder_construct( struct dcn20_link_encoder *enc20, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 653a571e366d..ebe0cc5b833b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -491,6 +491,7 @@ static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = { [id] = {\ LE_DCN3_REG_LIST(id), \ UNIPHY_DCN2_REG_LIST(phyid), \ + SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \ } static const struct dce110_aux_registers_shift aux_shift = { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c index b54814f11b74..2beb284f89b0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/display_mode_vba_30.c @@ -63,6 +63,7 @@ typedef struct { #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define DCN30_MAX_DSC_IMAGE_WIDTH 5184 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib); static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation( @@ -3984,6 +3985,9 @@ void dml30_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l } else if (v->PlaneRequiredDISPCLKWithoutODMCombine > v->MaxDispclkRoundedDownToDFSGranularity) { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1; + } else if (v->DSCEnabled[k] && (v->HActive[k] > DCN30_MAX_DSC_IMAGE_WIDTH)) { + v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_2to1; + v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithODMCombine2To1; } else { v->ODMCombineEnablePerState[i][k] = dm_odm_combine_mode_disabled; v->PlaneRequiredDISPCLK = v->PlaneRequiredDISPCLKWithoutODMCombine; diff --git a/drivers/gpu/drm/amd/display/include/bios_parser_types.h b/drivers/gpu/drm/amd/display/include/bios_parser_types.h index c30437ae8395..21011edea337 100644 --- a/drivers/gpu/drm/amd/display/include/bios_parser_types.h +++ b/drivers/gpu/drm/amd/display/include/bios_parser_types.h @@ -101,6 +101,13 @@ enum bp_pipe_control_action { ASIC_PIPE_INIT }; +enum bp_lvtma_control_action { + LVTMA_CONTROL_LCD_BLOFF = 2, + LVTMA_CONTROL_LCD_BLON = 3, + LVTMA_CONTROL_POWER_ON = 12, + LVTMA_CONTROL_POWER_OFF = 13 +}; + struct bp_encoder_control { enum bp_encoder_control_action action; enum engine_id engine_id; diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h index 89ef9f6860e5..16df2a485dd0 100644 --- a/drivers/gpu/drm/amd/display/include/fixed31_32.h +++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h @@ -431,6 +431,9 @@ struct fixed31_32 dc_fixpt_log(struct fixed31_32 arg); */ static inline struct fixed31_32 dc_fixpt_pow(struct fixed31_32 arg1, struct fixed31_32 arg2) { + if (arg1.value == 0) + return arg2.value == 0 ? dc_fixpt_one : dc_fixpt_zero; + return dc_fixpt_exp( dc_fixpt_mul( dc_fixpt_log(arg1), diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 81820f3d6b3b..d988533d4af5 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -324,22 +324,44 @@ static void apply_below_the_range(struct core_freesync *core_freesync, /* Choose number of frames to insert based on how close it * can get to the mid point of the variable range. + * - Delta for CEIL: delta_from_mid_point_in_us_1 + * - Delta for FLOOR: delta_from_mid_point_in_us_2 */ - if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us && - (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 || - mid_point_frames_floor < 2)) { + if ((last_render_time_in_us / mid_point_frames_ceil) < in_out_vrr->min_duration_in_us) { + /* Check for out of range. + * If using CEIL produces a value that is out of range, + * then we are forced to use FLOOR. + */ + frames_to_insert = mid_point_frames_floor; + } else if (mid_point_frames_floor < 2) { + /* Check if FLOOR would result in non-LFC. In this case + * choose to use CEIL + */ + frames_to_insert = mid_point_frames_ceil; + } else if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { + /* If choosing CEIL results in a frame duration that is + * closer to the mid point of the range. + * Choose CEIL + */ frames_to_insert = mid_point_frames_ceil; - delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - - delta_from_mid_point_in_us_1; } else { + /* If choosing FLOOR results in a frame duration that is + * closer to the mid point of the range. + * Choose FLOOR + */ frames_to_insert = mid_point_frames_floor; - delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 - - delta_from_mid_point_in_us_2; } /* Prefer current frame multiplier when BTR is enabled unless it drifts * too far from the midpoint */ + if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) { + delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 - + delta_from_mid_point_in_us_1; + } else { + delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_1 - + delta_from_mid_point_in_us_2; + } if (in_out_vrr->btr.frames_to_insert != 0 && delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) { if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) < diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index 6c991de8f371..fb962b9ceffb 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -2204,14 +2204,17 @@ static const struct throttling_logging_label { }; static void arcturus_log_thermal_throttling_event(struct smu_context *smu) { + int ret; int throttler_idx, throtting_events = 0, buf_idx = 0; struct amdgpu_device *adev = smu->adev; uint32_t throttler_status; char log_buf[256]; - arcturus_get_smu_metrics_data(smu, - METRICS_THROTTLER_STATUS, - &throttler_status); + ret = arcturus_get_smu_metrics_data(smu, + METRICS_THROTTLER_STATUS, + &throttler_status); + if (ret) + return; memset(log_buf, 0, sizeof(log_buf)); for (throttler_idx = 0; throttler_idx < ARRAY_SIZE(logging_label); diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 3b8839641770..ea70d736f6a8 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -979,10 +979,7 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - uint64_t features_enabled; - int i; - bool enabled; - int ret = 0; + int i, ret = 0; PP_ASSERT_WITH_CODE((ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisableAllSmuFeatures, @@ -990,17 +987,8 @@ static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) "[DisableAllSMUFeatures] Failed to disable all smu features!", return ret); - ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); - PP_ASSERT_WITH_CODE(!ret, - "[DisableAllSMUFeatures] Failed to get enabled smc features!", - return ret); - - for (i = 0; i < GNLD_FEATURES_MAX; i++) { - enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? - true : false; - data->smu_features[i].enabled = enabled; - data->smu_features[i].supported = enabled; - } + for (i = 0; i < GNLD_FEATURES_MAX; i++) + data->smu_features[i].enabled = 0; return 0; } @@ -1652,12 +1640,6 @@ static void vega20_init_powergate_state(struct pp_hwmgr *hwmgr) data->uvd_power_gated = true; data->vce_power_gated = true; - - if (data->smu_features[GNLD_DPM_UVD].enabled) - data->uvd_power_gated = false; - - if (data->smu_features[GNLD_DPM_VCE].enabled) - data->vce_power_gated = false; } static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) @@ -3230,10 +3212,11 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf) static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfeature_masks) { - uint64_t features_enabled; - uint64_t features_to_enable; - uint64_t features_to_disable; - int ret = 0; + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + uint64_t features_enabled, features_to_enable, features_to_disable; + int i, ret = 0; + bool enabled; if (new_ppfeature_masks >= (1ULL << GNLD_FEATURES_MAX)) return -EINVAL; @@ -3262,6 +3245,17 @@ static int vega20_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe return ret; } + /* Update the cached feature enablement state */ + ret = vega20_get_enabled_smc_features(hwmgr, &features_enabled); + if (ret) + return ret; + + for (i = 0; i < GNLD_FEATURES_MAX; i++) { + enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? + true : false; + data->smu_features[i].enabled = enabled; + } + return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 729ec6e0d43a..b2ec3a5141cc 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -14930,7 +14930,7 @@ static int intel_atomic_check(struct drm_device *dev, if (any_ms && !check_digital_port_conflicts(state)) { drm_dbg_kms(&dev_priv->drm, "rejecting conflicting digital port configuration\n"); - ret = EINVAL; + ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 3644752cc5ec..5a5cfe25085b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -2044,9 +2044,12 @@ DEFINE_SHOW_ATTRIBUTE(i915_hdcp_sink_capability); static int i915_lpsp_capability_show(struct seq_file *m, void *data) { struct drm_connector *connector = m->private; - struct intel_encoder *encoder = - intel_attached_encoder(to_intel_connector(connector)); struct drm_i915_private *i915 = to_i915(connector->dev); + struct intel_encoder *encoder; + + encoder = intel_attached_encoder(to_intel_connector(connector)); + if (!encoder) + return -ENODEV; if (connector->status != connector_status_connected) return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 0c713e83274d..e0fcb89c736b 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -4147,6 +4147,12 @@ static const struct i915_power_well_desc tgl_power_wells[] = { }, }, { + .name = "TC cold off", + .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, + .ops = &tgl_tc_cold_off_ops, + .id = DISP_PW_ID_NONE, + }, + { .name = "AUX A", .domains = TGL_AUX_A_IO_POWER_DOMAINS, .ops = &icl_aux_power_well_ops, @@ -4332,12 +4338,6 @@ static const struct i915_power_well_desc tgl_power_wells[] = { .hsw.irq_pipe_mask = BIT(PIPE_D), }, }, - { - .name = "TC cold off", - .domains = TGL_TC_COLD_OFF_POWER_DOMAINS, - .ops = &tgl_tc_cold_off_ops, - .id = DISP_PW_ID_NONE, - }, }; static const struct i915_power_well_desc rkl_power_wells[] = { @@ -5240,10 +5240,10 @@ struct buddy_page_mask { }; static const struct buddy_page_mask tgl_buddy_page_masks[] = { - { .num_channels = 1, .type = INTEL_DRAM_LPDDR4, .page_mask = 0xE }, { .num_channels = 1, .type = INTEL_DRAM_DDR4, .page_mask = 0xF }, { .num_channels = 2, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x1C }, { .num_channels = 2, .type = INTEL_DRAM_DDR4, .page_mask = 0x1F }, + { .num_channels = 4, .type = INTEL_DRAM_LPDDR4, .page_mask = 0x38 }, {} }; diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index 072725a448db..ad86c5eb5bba 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -70,6 +70,7 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, { u8 *cfg_base = vgpu_cfg_space(vgpu); u8 mask, new, old; + pci_power_t pwr; int i = 0; for (; i < bytes && (off + i < sizeof(pci_cfg_space_rw_bmp)); i++) { @@ -91,6 +92,15 @@ static void vgpu_pci_cfg_mem_write(struct intel_vgpu *vgpu, unsigned int off, /* For other configuration space directly copy as it is. */ if (i < bytes) memcpy(cfg_base + off + i, src + i, bytes - i); + + if (off == vgpu->cfg_space.pmcsr_off && vgpu->cfg_space.pmcsr_off) { + pwr = (pci_power_t __force)(*(u16*)(&vgpu_cfg_space(vgpu)[off]) + & PCI_PM_CTRL_STATE_MASK); + if (pwr == PCI_D3hot) + vgpu->d3_entered = true; + gvt_dbg_core("vgpu-%d power status changed to %d\n", + vgpu->id, pwr); + } } /** @@ -366,6 +376,7 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, struct intel_gvt *gvt = vgpu->gvt; const struct intel_gvt_device_info *info = &gvt->device_info; u16 *gmch_ctl; + u8 next; memcpy(vgpu_cfg_space(vgpu), gvt->firmware.cfg_space, info->cfg_space_size); @@ -401,6 +412,19 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, pci_resource_len(gvt->gt->i915->drm.pdev, 2); memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4); + + /* PM Support */ + vgpu->cfg_space.pmcsr_off = 0; + if (vgpu_cfg_space(vgpu)[PCI_STATUS] & PCI_STATUS_CAP_LIST) { + next = vgpu_cfg_space(vgpu)[PCI_CAPABILITY_LIST]; + do { + if (vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_ID] == PCI_CAP_ID_PM) { + vgpu->cfg_space.pmcsr_off = next + PCI_PM_CTRL; + break; + } + next = vgpu_cfg_space(vgpu)[next + PCI_CAP_LIST_NEXT]; + } while (next); + } } /** diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 210016192ce7..a3a4305eda01 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2501,7 +2501,7 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) return create_scratch_page_tree(vgpu); } -static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) { struct list_head *pos, *n; struct intel_vgpu_mm *mm; diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 320b8d6ad92f..52d0d88abd86 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -279,4 +279,6 @@ int intel_vgpu_emulate_ggtt_mmio_read(struct intel_vgpu *vgpu, int intel_vgpu_emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, void *p_data, unsigned int bytes); +void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu); + #endif /* _GVT_GTT_H_ */ diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index a4a6db6b7f90..ff7f2515a6fe 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -106,6 +106,7 @@ struct intel_vgpu_pci_bar { struct intel_vgpu_cfg_space { unsigned char virtual_cfg_space[PCI_CFG_SPACE_EXP_SIZE]; struct intel_vgpu_pci_bar bar[INTEL_GVT_MAX_BAR_NUM]; + u32 pmcsr_off; }; #define vgpu_cfg_space(vgpu) ((vgpu)->cfg_space.virtual_cfg_space) @@ -198,6 +199,8 @@ struct intel_vgpu { struct intel_vgpu_submission submission; struct radix_tree_root page_track_tree; u32 hws_pga[I915_NUM_ENGINES]; + /* Set on PCI_D3, reset on DMLR, not reflecting the actual PM state */ + bool d3_entered; struct dentry *debugfs; diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 7d361623ff67..8fa9b31a2484 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -257,6 +257,7 @@ void intel_gvt_release_vgpu(struct intel_vgpu *vgpu) intel_gvt_deactivate_vgpu(vgpu); mutex_lock(&vgpu->vgpu_lock); + vgpu->d3_entered = false; intel_vgpu_clean_workloads(vgpu, ALL_ENGINES); intel_vgpu_dmabuf_cleanup(vgpu); mutex_unlock(&vgpu->vgpu_lock); @@ -393,6 +394,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL); idr_init(&vgpu->object_idr); intel_vgpu_init_cfg_space(vgpu, param->primary); + vgpu->d3_entered = false; ret = intel_vgpu_init_mmio(vgpu); if (ret) @@ -557,10 +559,15 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, /* full GPU reset or device model level reset */ if (engine_mask == ALL_ENGINES || dmlr) { intel_vgpu_select_submission_ops(vgpu, ALL_ENGINES, 0); - intel_vgpu_invalidate_ppgtt(vgpu); + if (engine_mask == ALL_ENGINES) + intel_vgpu_invalidate_ppgtt(vgpu); /*fence will not be reset during virtual reset */ if (dmlr) { - intel_vgpu_reset_gtt(vgpu); + if(!vgpu->d3_entered) { + intel_vgpu_invalidate_ppgtt(vgpu); + intel_vgpu_destroy_all_ppgtt_mm(vgpu); + } + intel_vgpu_reset_ggtt(vgpu, true); intel_vgpu_reset_resource(vgpu); } @@ -572,7 +579,14 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, intel_vgpu_reset_cfg_space(vgpu); /* only reset the failsafe mode when dmlr reset */ vgpu->failsafe = false; - vgpu->pv_notified = false; + /* + * PCI_D0 is set before dmlr, so reset d3_entered here + * after done using. + */ + if(vgpu->d3_entered) + vgpu->d3_entered = false; + else + vgpu->pv_notified = false; } } diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index 28bc5f13ae52..056994224c6b 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -445,8 +445,6 @@ static void i915_pmu_event_destroy(struct perf_event *event) container_of(event->pmu, typeof(*i915), pmu.base); drm_WARN_ON(&i915->drm, event->parent); - - module_put(THIS_MODULE); } static int @@ -538,10 +536,8 @@ static int i915_pmu_event_init(struct perf_event *event) if (ret) return ret; - if (!event->parent) { - __module_get(THIS_MODULE); + if (!event->parent) event->destroy = i915_pmu_event_destroy; - } return 0; } @@ -1130,6 +1126,7 @@ void i915_pmu_register(struct drm_i915_private *i915) if (!pmu->base.attr_groups) goto err_attr; + pmu->base.module = THIS_MODULE; pmu->base.task_ctx_nr = perf_invalid_context; pmu->base.event_init = i915_pmu_event_init; pmu->base.add = i915_pmu_event_add; diff --git a/drivers/gpu/drm/i915/selftests/i915_buddy.c b/drivers/gpu/drm/i915/selftests/i915_buddy.c index 939a6caebb03..632b912b0bc9 100644 --- a/drivers/gpu/drm/i915/selftests/i915_buddy.c +++ b/drivers/gpu/drm/i915/selftests/i915_buddy.c @@ -8,8 +8,6 @@ #include "../i915_selftest.h" #include "i915_random.h" -#define SZ_8G (1ULL << 33) - static void __igt_dump_block(struct i915_buddy_mm *mm, struct i915_buddy_block *block, bool buddy) @@ -281,18 +279,22 @@ static int igt_check_mm(struct i915_buddy_mm *mm) static void igt_mm_config(u64 *size, u64 *chunk_size) { I915_RND_STATE(prng); - u64 s, ms; + u32 s, ms; /* Nothing fancy, just try to get an interesting bit pattern */ prandom_seed_state(&prng, i915_selftest.random_seed); - s = i915_prandom_u64_state(&prng) & (SZ_8G - 1); - ms = BIT_ULL(12 + (prandom_u32_state(&prng) % ilog2(s >> 12))); - s = max(s & -ms, ms); + /* Let size be a random number of pages up to 8 GB (2M pages) */ + s = 1 + i915_prandom_u32_max_state((BIT(33 - 12)) - 1, &prng); + /* Let the chunk size be a random power of 2 less than size */ + ms = BIT(i915_prandom_u32_max_state(ilog2(s), &prng)); + /* Round size down to the chunk size */ + s &= -ms; - *chunk_size = ms; - *size = s; + /* Convert from pages to bytes */ + *chunk_size = (u64)ms << 12; + *size = (u64)s << 12; } static int igt_buddy_alloc_smoke(void *arg) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index b9810bf156c3..f127e633f7ca 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -78,6 +78,7 @@ static void mock_device_release(struct drm_device *dev) drm_mode_config_cleanup(&i915->drm); out: + i915_params_free(&i915->params); put_device(&i915->drm.pdev->dev); i915->drm.pdev = NULL; } @@ -165,6 +166,8 @@ struct drm_i915_private *mock_gem_device(void) i915->drm.pdev = pdev; drmm_add_final_kfree(&i915->drm, i915); + i915_params_copy(&i915->params, &i915_modparams); + intel_runtime_pm_init_early(&i915->runtime_pm); /* Using the global GTT may ask questions about KMS users, so prepare */ diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 7a2430e34e00..c8da7adc6b30 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -179,6 +179,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, virtio_gpu_cmd_submit(vgdev, buf, exbuf->size, vfpriv->ctx_id, buflist, out_fence); + dma_fence_put(&out_fence->f); virtio_gpu_notify(vgdev); return 0; diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index 2cdd3cd9ce75..e83651b7747d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -79,6 +79,7 @@ void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo) } sg_free_table(shmem->pages); + kfree(shmem->pages); shmem->pages = NULL; drm_gem_shmem_unpin(&bo->base.base); } diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index ef0cd2998671..c36b4d2b61e0 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2751,7 +2751,7 @@ static int __init ib_core_init(void) ret = addr_init(); if (ret) { - pr_warn("Could't init IB address resolution\n"); + pr_warn("Couldn't init IB address resolution\n"); goto err_ibnl; } diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index dad0df8a2467..17ac8b7c5710 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -821,7 +821,8 @@ static int bnxt_re_handle_qp_async_event(struct creq_qp_event *qp_event, struct ib_event event; unsigned int flags; - if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR) { + if (qp->qplib_qp.state == CMDQ_MODIFY_QP_NEW_STATE_ERR && + rdma_is_kernel_res(&qp->ib_qp.res)) { flags = bnxt_re_lock_cqs(qp); bnxt_qplib_add_flush_qp(&qp->qplib_qp); bnxt_re_unlock_cqs(qp, flags); diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c index 9af82ff933d7..73d197e21730 100644 --- a/drivers/infiniband/hw/hfi1/tid_rdma.c +++ b/drivers/infiniband/hw/hfi1/tid_rdma.c @@ -3215,6 +3215,7 @@ bool hfi1_tid_rdma_wqe_interlock(struct rvt_qp *qp, struct rvt_swqe *wqe) case IB_WR_ATOMIC_CMP_AND_SWP: case IB_WR_ATOMIC_FETCH_AND_ADD: case IB_WR_RDMA_WRITE: + case IB_WR_RDMA_WRITE_WITH_IMM: switch (prev->wr.opcode) { case IB_WR_TID_RDMA_WRITE: req = wqe_to_tid_req(prev); diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index da9888deff8c..6edcbdcd8f43 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -65,8 +65,6 @@ #define HNS_ROCE_CQE_WCMD_EMPTY_BIT 0x2 #define HNS_ROCE_MIN_CQE_CNT 16 -#define HNS_ROCE_RESERVED_SGE 1 - #define HNS_ROCE_MAX_IRQ_NUM 128 #define HNS_ROCE_SGE_IN_WQE 2 diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 07b4c85d341d..aeb3a6fa7d47 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -535,7 +535,7 @@ static void hns_roce_set_sdb_ext(struct hns_roce_dev *hr_dev, u32 ext_sdb_alept, roce_write(hr_dev, ROCEE_EXT_DB_SQ_H_REG, val); dev_dbg(dev, "ext SDB depth: 0x%x\n", db->ext_db->esdb_dep); - dev_dbg(dev, "ext SDB threshold: epmty: 0x%x, ful: 0x%x\n", + dev_dbg(dev, "ext SDB threshold: empty: 0x%x, ful: 0x%x\n", ext_sdb_alept, ext_sdb_alful); } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index d2968594664b..4cda95ed1fbe 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -633,7 +633,7 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, wqe_idx = (hr_qp->rq.head + nreq) & (hr_qp->rq.wqe_cnt - 1); - if (unlikely(wr->num_sge >= hr_qp->rq.max_gs)) { + if (unlikely(wr->num_sge > hr_qp->rq.max_gs)) { ibdev_err(ibdev, "rq:num_sge=%d >= qp->sq.max_gs=%d\n", wr->num_sge, hr_qp->rq.max_gs); ret = -EINVAL; @@ -653,7 +653,6 @@ static int hns_roce_v2_post_recv(struct ib_qp *ibqp, if (wr->num_sge < hr_qp->rq.max_gs) { dseg->lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY); dseg->addr = 0; - dseg->len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH); } /* rq support inline data */ @@ -787,8 +786,8 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq, } if (wr->num_sge < srq->max_gs) { - dseg[i].len = cpu_to_le32(HNS_ROCE_INVALID_SGE_LENGTH); - dseg[i].lkey = cpu_to_le32(HNS_ROCE_INVALID_LKEY); + dseg[i].len = 0; + dseg[i].lkey = cpu_to_le32(0x100); dseg[i].addr = 0; } @@ -5070,7 +5069,7 @@ static int hns_roce_v2_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *attr) attr->srq_limit = limit_wl; attr->max_wr = srq->wqe_cnt - 1; - attr->max_sge = srq->max_gs - HNS_ROCE_RESERVED_SGE; + attr->max_sge = srq->max_gs; out: hns_roce_free_cmd_mailbox(hr_dev, mailbox); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1fb1c583d0f8..ac29be43b6bd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -92,9 +92,7 @@ #define HNS_ROCE_V2_CQC_TIMER_ENTRY_SZ PAGE_SIZE #define HNS_ROCE_V2_PAGE_SIZE_SUPPORTED 0xFFFFF000 #define HNS_ROCE_V2_MAX_INNER_MTPT_NUM 2 -#define HNS_ROCE_INVALID_LKEY 0x0 -#define HNS_ROCE_INVALID_SGE_LENGTH 0x80000000 - +#define HNS_ROCE_INVALID_LKEY 0x100 #define HNS_ROCE_CMQ_TX_TIMEOUT 30000 #define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE 2 #define HNS_ROCE_V2_RSV_QPS 8 diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index e94ca130ff5e..c063c450c715 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -386,8 +386,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, return -EINVAL; } - hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge) + - HNS_ROCE_RESERVED_SGE); + hr_qp->rq.max_gs = roundup_pow_of_two(max(1U, cap->max_recv_sge)); if (hr_dev->caps.max_rq_sg <= HNS_ROCE_SGE_IN_WQE) hr_qp->rq.wqe_shift = ilog2(hr_dev->caps.max_rq_desc_sz); @@ -402,7 +401,7 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap, hr_qp->rq_inl_buf.wqe_cnt = 0; cap->max_recv_wr = cnt; - cap->max_recv_sge = hr_qp->rq.max_gs - HNS_ROCE_RESERVED_SGE; + cap->max_recv_sge = hr_qp->rq.max_gs; return 0; } diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index f40a000e94ee..b9e2dbd372b6 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -297,7 +297,7 @@ int hns_roce_create_srq(struct ib_srq *ib_srq, spin_lock_init(&srq->lock); srq->wqe_cnt = roundup_pow_of_two(init_attr->attr.max_wr + 1); - srq->max_gs = init_attr->attr.max_sge + HNS_ROCE_RESERVED_SGE; + srq->max_gs = init_attr->attr.max_sge; if (udata) { ret = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c9abe1c01e4e..662e7fc7f628 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -120,7 +120,7 @@ static void usnic_ib_qp_grp_modify_active_to_err(struct usnic_ib_dev *us_ibdev) IB_QPS_ERR, NULL); if (status) { - usnic_err("Failed to transistion qp grp %u from %s to %s\n", + usnic_err("Failed to transition qp grp %u from %s to %s\n", qp_grp->grp_id, usnic_ib_qp_grp_state_to_string (cur_state), diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 4959f5df21bd..5141d49a046b 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -1035,8 +1035,8 @@ static void *iommu_dma_alloc(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) && !gfpflags_allow_blocking(gfp) && !coherent) - cpu_addr = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &page, - gfp); + page = dma_alloc_from_pool(dev, PAGE_ALIGN(size), &cpu_addr, + gfp, NULL); else cpu_addr = iommu_dma_alloc_pages(dev, size, &page, gfp, attrs); if (!cpu_addr) diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 31e43a2197a3..cddaa43a9d52 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -130,7 +130,7 @@ static inline struct bonding *__get_bond_by_port(struct port *port) /** * __get_first_agg - get the first aggregator in the bond - * @bond: the bond we're looking at + * @port: the port we're looking at * * Return the aggregator of the first slave in @bond, or %NULL if it can't be * found. @@ -1626,7 +1626,7 @@ static int agg_device_up(const struct aggregator *agg) /** * ad_agg_selection_logic - select an aggregation group for a team - * @aggregator: the aggregator we're looking at + * @agg: the aggregator we're looking at * @update_slave_arr: Does slave array need update? * * It is assumed that only one aggregator may be selected for a team. @@ -1810,7 +1810,7 @@ static void ad_initialize_agg(struct aggregator *aggregator) /** * ad_initialize_port - initialize a given port's parameters - * @aggregator: the aggregator we're looking at + * @port: the port we're looking at * @lacp_fast: boolean. whether fast periodic should be used */ static void ad_initialize_port(struct port *port, int lacp_fast) @@ -1967,6 +1967,7 @@ static void ad_marker_response_received(struct bond_marker *marker, /** * bond_3ad_initiate_agg_selection - initate aggregator selection * @bond: bonding struct + * @timeout: timeout value to set * * Set the aggregation selection timer, to initiate an agg selection in * the very near future. Called during first initialization, and during @@ -2259,7 +2260,7 @@ void bond_3ad_update_ad_actor_settings(struct bonding *bond) /** * bond_3ad_state_machine_handler - handle state machines timeout - * @bond: bonding struct to work on + * @work: work context to fetch bonding struct to work on from * * The state machine handling concept in this module is to check every tick * which state machine should operate any function. The execution order is @@ -2500,7 +2501,7 @@ void bond_3ad_adapter_speed_duplex_changed(struct slave *slave) /** * bond_3ad_handle_link_change - handle a slave's link status change indication * @slave: slave struct to work on - * @status: whether the link is now up or down + * @link: whether the link is now up or down * * Handle reselection of aggregator (if needed) for this port. */ @@ -2551,7 +2552,7 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) /** * bond_3ad_set_carrier - set link state for bonding master - * @bond - bonding structure + * @bond: bonding structure * * if we have an active aggregator, we're up, if not, we're down. * Presumes that we cannot have an active aggregator if there are @@ -2664,7 +2665,7 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, /** * bond_3ad_update_lacp_rate - change the lacp rate - * @bond - bonding struct + * @bond: bonding struct * * When modify lacp_rate parameter via sysfs, * update actor_oper_port_state of each port. diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 095ea51d1853..4e1b7deb724b 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1206,8 +1206,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav /** * alb_set_mac_address - * @bond: - * @addr: + * @bond: bonding we're working on + * @addr: MAC address to set * * In TLB mode all slaves are configured to the bond's hw address, but set * their dev_addr field to different addresses (based on their permanent hw diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5ad43aaf76e5..c5d3032dd1a2 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -322,6 +322,7 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, /** * bond_vlan_rx_add_vid - Propagates adding an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being added */ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, @@ -355,6 +356,7 @@ unwind: /** * bond_vlan_rx_kill_vid - Propagates deleting an id to slaves * @bond_dev: bonding net device that got called + * @proto: network protocol ID * @vid: vlan id being removed */ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, @@ -948,7 +950,7 @@ static bool bond_should_notify_peers(struct bonding *bond) /** * change_active_interface - change the active slave into the specified one * @bond: our bonding struct - * @new: the new slave to make the active one + * @new_active: the new slave to make the active one * * Set the new slave to the bond's settings and unset them on the old * curr_active_slave. @@ -2205,7 +2207,8 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = __bond_release_one(bond_dev, slave_dev, false, true); - if (ret == 0 && !bond_has_slaves(bond)) { + if (ret == 0 && !bond_has_slaves(bond) && + bond_dev->reg_state != NETREG_UNREGISTERING) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); @@ -2945,6 +2948,9 @@ static int bond_ab_arp_inspect(struct bonding *bond) if (bond_time_in_interval(bond, last_rx, 1)) { bond_propose_link_state(slave, BOND_LINK_UP); commit++; + } else if (slave->link == BOND_LINK_BACK) { + bond_propose_link_state(slave, BOND_LINK_FAIL); + commit++; } continue; } @@ -3053,6 +3059,19 @@ static void bond_ab_arp_commit(struct bonding *bond) continue; + case BOND_LINK_FAIL: + bond_set_slave_link_state(slave, BOND_LINK_FAIL, + BOND_SLAVE_NOTIFY_NOW); + bond_set_slave_inactive_flags(slave, + BOND_SLAVE_NOTIFY_NOW); + + /* A slave has just been enslaved and has become + * the current active slave. + */ + if (rtnl_dereference(bond->curr_active_slave)) + RCU_INIT_POINTER(bond->current_arp_slave, NULL); + continue; + default: slave_err(bond->dev, slave->dev, "impossible: link_new_state %d on slave\n", @@ -3103,8 +3122,6 @@ static bool bond_ab_arp_probe(struct bonding *bond) return should_notify_rtnl; } - bond_set_slave_inactive_flags(curr_arp_slave, BOND_SLAVE_NOTIFY_LATER); - bond_for_each_slave_rcu(bond, slave, iter) { if (!found && !before && bond_slave_is_up(slave)) before = slave; @@ -4552,13 +4569,23 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } +static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed) +{ + if (speed == 0 || speed == SPEED_UNKNOWN) + speed = slave->speed; + else + speed = min(speed, slave->speed); + + return speed; +} + static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, struct ethtool_link_ksettings *cmd) { struct bonding *bond = netdev_priv(bond_dev); - unsigned long speed = 0; struct list_head *iter; struct slave *slave; + u32 speed = 0; cmd->base.duplex = DUPLEX_UNKNOWN; cmd->base.port = PORT_OTHER; @@ -4570,8 +4597,13 @@ static int bond_ethtool_get_link_ksettings(struct net_device *bond_dev, */ bond_for_each_slave(bond, slave, iter) { if (bond_slave_can_tx(slave)) { - if (slave->speed != SPEED_UNKNOWN) - speed += slave->speed; + if (slave->speed != SPEED_UNKNOWN) { + if (BOND_MODE(bond) == BOND_MODE_BROADCAST) + speed = bond_mode_bcast_speed(slave, + speed); + else + speed += slave->speed; + } if (cmd->base.duplex == DUPLEX_UNKNOWN && slave->duplex != DUPLEX_UNKNOWN) cmd->base.duplex = slave->duplex; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 6500179c2ca2..0837ae0e0c5e 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1554,6 +1554,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, return ret; switch (ret) { + case -ETIMEDOUT: + return ret; case -ENOSPC: dev_dbg(dev->dev, "{%pM,%.4d} no space left in ARL\n", addr, vid); diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index f121619d81fe..2d23ccef7d0e 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -9,7 +9,7 @@ config NET_DSA_MSCC_FELIX select NET_DSA_TAG_OCELOT select FSL_ENETC_MDIO help - This driver supports network switches from the the Vitesse / + This driver supports network switches from the Vitesse / Microsemi / Microchip Ocelot family of switching cores that are connected to their host CPU via Ethernet. The following switches are supported: diff --git a/drivers/net/ethernet/3com/3c574_cs.c b/drivers/net/ethernet/3com/3c574_cs.c index ef1c3151fbb2..bd0ada4e81b0 100644 --- a/drivers/net/ethernet/3com/3c574_cs.c +++ b/drivers/net/ethernet/3com/3c574_cs.c @@ -951,7 +951,7 @@ static struct net_device_stats *el3_get_stats(struct net_device *dev) static void update_stats(struct net_device *dev) { unsigned int ioaddr = dev->base_addr; - u8 rx, tx, up; + u8 up; pr_debug("%s: updating the statistics.\n", dev->name); @@ -972,8 +972,8 @@ static void update_stats(struct net_device *dev) dev->stats.tx_packets += (up&0x30) << 4; /* Rx packets */ inb(ioaddr + 7); /* Tx deferrals */ inb(ioaddr + 8); - rx = inw(ioaddr + 10); - tx = inw(ioaddr + 12); + /* rx */ inw(ioaddr + 10); + /* tx */ inw(ioaddr + 12); EL3WINDOW(4); /* BadSSD */ inb(ioaddr + 12); diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c index aeae7966a082..08db4c9da2fa 100644 --- a/drivers/net/ethernet/8390/axnet_cs.c +++ b/drivers/net/ethernet/8390/axnet_cs.c @@ -898,6 +898,7 @@ static int ax_close(struct net_device *dev) /** * axnet_tx_timeout - handle transmit time out condition * @dev: network device which has apparently fallen asleep + * @txqueue: unused * * Called by kernel when device never acknowledges a transmit has * completed (or failed) - i.e. never posted a Tx related interrupt. diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 2a6c9725e092..a3a8edf9a734 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2180,13 +2180,10 @@ static void ena_del_napi_in_range(struct ena_adapter *adapter, int i; for (i = first_index; i < first_index + count; i++) { - /* Check if napi was initialized before */ - if (!ENA_IS_XDP_INDEX(adapter, i) || - adapter->ena_napi[i].xdp_ring) - netif_napi_del(&adapter->ena_napi[i].napi); - else - WARN_ON(ENA_IS_XDP_INDEX(adapter, i) && - adapter->ena_napi[i].xdp_ring); + netif_napi_del(&adapter->ena_napi[i].napi); + + WARN_ON(!ENA_IS_XDP_INDEX(adapter, i) && + adapter->ena_napi[i].xdp_ring); } } @@ -3601,16 +3598,14 @@ static void ena_fw_reset_device(struct work_struct *work) { struct ena_adapter *adapter = container_of(work, struct ena_adapter, reset_task); - struct pci_dev *pdev = adapter->pdev; - if (unlikely(!test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { - dev_err(&pdev->dev, - "device reset schedule while reset bit is off\n"); - return; - } rtnl_lock(); - ena_destroy_device(adapter, false); - ena_restore_device(adapter); + + if (likely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { + ena_destroy_device(adapter, false); + ena_restore_device(adapter); + } + rtnl_unlock(); } @@ -3692,7 +3687,7 @@ static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, } u64_stats_update_begin(&tx_ring->syncp); - tx_ring->tx_stats.missed_tx = missed_tx; + tx_ring->tx_stats.missed_tx += missed_tx; u64_stats_update_end(&tx_ring->syncp); return rc; @@ -4389,8 +4384,11 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown) netdev->rx_cpu_rmap = NULL; } #endif /* CONFIG_RFS_ACCEL */ - del_timer_sync(&adapter->timer_service); + /* Make sure timer and reset routine won't be called after + * freeing device resources. + */ + del_timer_sync(&adapter->timer_service); cancel_work_sync(&adapter->reset_task); rtnl_lock(); /* lock released inside the below if-else block */ @@ -4558,6 +4556,9 @@ static void ena_keep_alive_wd(void *adapter_data, tx_drops = ((u64)desc->tx_drops_high << 32) | desc->tx_drops_low; u64_stats_update_begin(&adapter->syncp); + /* These stats are accumulated by the device, so the counters indicate + * all drops since last reset. + */ adapter->dev_stats.rx_drops = rx_drops; adapter->dev_stats.tx_drops = tx_drops; u64_stats_update_end(&adapter->syncp); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 16a944707ba9..8941ac4df9e3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -1631,8 +1631,8 @@ static int hw_atl_b0_get_mac_temp(struct aq_hw_s *self, u32 *temp) hw_atl_ts_reset_set(self, 0); } - err = readx_poll_timeout_atomic(hw_atl_b0_ts_ready_and_latch_high_get, - self, val, val == 1, 10000U, 500000U); + err = readx_poll_timeout(hw_atl_b0_ts_ready_and_latch_high_get, self, + val, val == 1, 10000U, 500000U); if (err) return err; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index d2b587d1670a..869431a1eedd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2553,19 +2553,22 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) pkt_len = ETH_HLEN + sizeof(CXGB4_SELFTEST_LB_STR); - flits = DIV_ROUND_UP(pkt_len + sizeof(struct cpl_tx_pkt) + - sizeof(*wr), sizeof(__be64)); + flits = DIV_ROUND_UP(pkt_len + sizeof(*cpl) + sizeof(*wr), + sizeof(__be64)); ndesc = flits_to_desc(flits); lb = &pi->ethtool_lb; lb->loopback = 1; q = &adap->sge.ethtxq[pi->first_qset]; + __netif_tx_lock(q->txq, smp_processor_id()); reclaim_completed_tx(adap, &q->q, -1, true); credits = txq_avail(&q->q) - ndesc; - if (unlikely(credits < 0)) + if (unlikely(credits < 0)) { + __netif_tx_unlock(q->txq); return -ENOMEM; + } wr = (void *)&q->q.desc[q->q.pidx]; memset(wr, 0, sizeof(struct tx_desc)); @@ -2598,6 +2601,7 @@ int cxgb4_selftest_lb_pkt(struct net_device *netdev) init_completion(&lb->completion); txq_advance(&q->q, ndesc); cxgb4_ring_tx_db(adap, &q->q, ndesc); + __netif_tx_unlock(q->txq); /* wait for the pkt to return */ ret = wait_for_completion_timeout(&lb->completion, 10 * HZ); diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 66e67b24a887..62e271aea4a5 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -2389,7 +2389,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) dev_info(dev, "probe %s ID %d\n", dev_name(dev), id); - netdev = alloc_etherdev_mq(sizeof(*port), TX_QUEUE_NUM); + netdev = devm_alloc_etherdev_mqs(dev, sizeof(*port), TX_QUEUE_NUM, TX_QUEUE_NUM); if (!netdev) { dev_err(dev, "Can't allocate ethernet device #%d\n", id); return -ENOMEM; @@ -2521,7 +2521,6 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) } port->netdev = NULL; - free_netdev(netdev); return ret; } @@ -2530,7 +2529,6 @@ static int gemini_ethernet_port_remove(struct platform_device *pdev) struct gemini_ethernet_port *port = platform_get_drvdata(pdev); gemini_port_remove(port); - free_netdev(port->netdev); return 0; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 9934421814b4..fb37816a74db 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3715,11 +3715,11 @@ failed_mii_init: failed_irq: failed_init: fec_ptp_stop(pdev); - if (fep->reg_phy) - regulator_disable(fep->reg_phy); failed_reset: pm_runtime_put_noidle(&pdev->dev); pm_runtime_disable(&pdev->dev); + if (fep->reg_phy) + regulator_disable(fep->reg_phy); failed_regulator: clk_disable_unprepare(fep->clk_ahb); failed_clk_ahb: diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index b513b8c5c3b5..41dd3d0f3452 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -750,8 +750,10 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) continue; err = gfar_parse_group(child, priv, model); - if (err) + if (err) { + of_node_put(child); goto err_grp_init; + } } } else { /* SQ_SG_MODE */ err = gfar_parse_group(np, priv, model); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index a62ddd626929..c0c8efe42fce 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -981,7 +981,7 @@ struct i40e_aqc_set_vsi_promiscuous_modes { #define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04 #define I40E_AQC_SET_VSI_DEFAULT 0x08 #define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10 -#define I40E_AQC_SET_VSI_PROMISC_TX 0x8000 +#define I40E_AQC_SET_VSI_PROMISC_RX_ONLY 0x8000 __le16 seid; __le16 vlan_tag; #define I40E_AQC_SET_VSI_VLAN_VALID 0x8000 diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index afad5e9f80e0..6ab52cbd697a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1967,6 +1967,21 @@ i40e_status i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags, } /** + * i40e_is_aq_api_ver_ge + * @aq: pointer to AdminQ info containing HW API version to compare + * @maj: API major value + * @min: API minor value + * + * Assert whether current HW API version is greater/equal than provided. + **/ +static bool i40e_is_aq_api_ver_ge(struct i40e_adminq_info *aq, u16 maj, + u16 min) +{ + return (aq->api_maj_ver > maj || + (aq->api_maj_ver == maj && aq->api_min_ver >= min)); +} + +/** * i40e_aq_add_vsi * @hw: pointer to the hw struct * @vsi_ctx: pointer to a vsi context struct @@ -2091,18 +2106,16 @@ i40e_status i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw, if (set) { flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST; - if (rx_only_promisc && - (((hw->aq.api_maj_ver == 1) && (hw->aq.api_min_ver >= 5)) || - (hw->aq.api_maj_ver > 1))) - flags |= I40E_AQC_SET_VSI_PROMISC_TX; + if (rx_only_promisc && i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY; } cmd->promiscuous_flags = cpu_to_le16(flags); cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST); - if (((hw->aq.api_maj_ver >= 1) && (hw->aq.api_min_ver >= 5)) || - (hw->aq.api_maj_ver > 1)) - cmd->valid_flags |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_TX); + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + cmd->valid_flags |= + cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY); cmd->seid = cpu_to_le16(seid); status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); @@ -2199,11 +2212,17 @@ enum i40e_status_code i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw, i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_vsi_promiscuous_modes); - if (enable) + if (enable) { flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST; + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + flags |= I40E_AQC_SET_VSI_PROMISC_RX_ONLY; + } cmd->promiscuous_flags = cpu_to_le16(flags); cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_UNICAST); + if (i40e_is_aq_api_ver_ge(&hw->aq, 1, 5)) + cmd->valid_flags |= + cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_RX_ONLY); cmd->seid = cpu_to_le16(seid); cmd->vlan_tag = cpu_to_le16(vid | I40E_AQC_SET_VSI_VLAN_VALID); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b5399357a667..2e433fdbf2c3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -15463,6 +15463,9 @@ static void i40e_remove(struct pci_dev *pdev) i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), 0); i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), 0); + while (test_bit(__I40E_RESET_RECOVERY_PENDING, pf->state)) + usleep_range(1000, 2000); + /* no more scheduling of any task */ set_bit(__I40E_SUSPENDED, pf->state); set_bit(__I40E_DOWN, pf->state); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 7a6f2a0d413f..9593aa4eea36 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5142,6 +5142,8 @@ static int igc_probe(struct pci_dev *pdev, device_set_wakeup_enable(&adapter->pdev->dev, adapter->flags & IGC_FLAG_WOL_SUPPORTED); + igc_ptp_init(adapter); + /* reset the hardware with the new settings */ igc_reset(adapter); @@ -5158,9 +5160,6 @@ static int igc_probe(struct pci_dev *pdev, /* carrier off reporting is important to ethtool even BEFORE open */ netif_carrier_off(netdev); - /* do hw tstamp init after resetting */ - igc_ptp_init(adapter); - /* Check if Media Autosense is enabled */ adapter->ei = *ei; diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index e67d4655b47e..36c999250fcc 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -496,8 +496,6 @@ void igc_ptp_init(struct igc_adapter *adapter) adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; - igc_ptp_reset(adapter); - adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, &adapter->pdev->dev); if (IS_ERR(adapter->ptp_clock)) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index e67b1a59ecb7..0fcd82036d4e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -193,7 +193,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, } /* alloc the udl from per cpu ddp pool */ - ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_KERNEL, &ddp->udp); + ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp); if (!ddp->udl) { e_err(drv, "failed allocated ddp context\n"); goto out_noddp_unmap; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 5975521a4c86..93c4cf7fedbf 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1226,8 +1226,8 @@ int otx2_config_npa(struct otx2_nic *pfvf) if (!hw->pool_cnt) return -EINVAL; - qset->pool = devm_kzalloc(pfvf->dev, sizeof(struct otx2_pool) * - hw->pool_cnt, GFP_KERNEL); + qset->pool = devm_kcalloc(pfvf->dev, hw->pool_cnt, + sizeof(struct otx2_pool), GFP_KERNEL); if (!qset->pool) return -ENOMEM; diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c index 9729983f4840..c54b7f8243f3 100644 --- a/drivers/net/ethernet/sfc/ef100.c +++ b/drivers/net/ethernet/sfc/ef100.c @@ -142,7 +142,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio /* Temporarily map new BAR. */ rc = efx_init_io(efx, bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -160,7 +160,7 @@ static int ef100_pci_parse_continue_entry(struct efx_nic *efx, int entry_locatio /* Put old BAR back. */ rc = efx_init_io(efx, previous_bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, previous_bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -334,7 +334,7 @@ static int ef100_pci_parse_xilinx_cap(struct efx_nic *efx, int vndr_cap, /* Temporarily map BAR. */ rc = efx_init_io(efx, bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, bar)); if (rc) { netif_err(efx, probe, efx->net_dev, @@ -495,7 +495,7 @@ static int ef100_pci_probe(struct pci_dev *pci_dev, /* Set up basic I/O (BAR mappings etc) */ rc = efx_init_io(efx, fcw.bar, - DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), + (dma_addr_t)DMA_BIT_MASK(ESF_GZ_TX_SEND_ADDR_WIDTH), pci_resource_len(efx->pci_dev, fcw.bar)); if (rc) goto fail; diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 206d70f9d95b..19fe86b3b316 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -431,18 +431,18 @@ static int ef100_reset(struct efx_nic *efx, enum reset_type reset_type) /* A RESET_TYPE_ALL will cause filters to be removed, so we remove filters * and reprobe after reset to avoid removing filters twice */ - down_read(&efx->filter_sem); + down_write(&efx->filter_sem); ef100_filter_table_down(efx); - up_read(&efx->filter_sem); + up_write(&efx->filter_sem); rc = efx_mcdi_reset(efx, reset_type); if (rc) return rc; netif_device_attach(efx->net_dev); - down_read(&efx->filter_sem); + down_write(&efx->filter_sem); rc = ef100_filter_table_up(efx); - up_read(&efx->filter_sem); + up_write(&efx->filter_sem); if (rc) return rc; @@ -739,6 +739,7 @@ const struct efx_nic_type ef100_pf_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = ef100_rx_write, .rx_packet = __ef100_rx_packet, + .rx_buf_hash_valid = ef100_rx_buf_hash_valid, .fini_dmaq = efx_fini_dmaq, .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, .filter_table_probe = ef100_filter_table_up, @@ -820,6 +821,7 @@ const struct efx_nic_type ef100_vf_nic_type = { .rx_remove = efx_mcdi_rx_remove, .rx_write = ef100_rx_write, .rx_packet = __ef100_rx_packet, + .rx_buf_hash_valid = ef100_rx_buf_hash_valid, .fini_dmaq = efx_fini_dmaq, .max_rx_ip_filters = EFX_MCDI_FILTER_TBL_ROWS, .filter_table_probe = ef100_filter_table_up, diff --git a/drivers/net/ethernet/sfc/ef100_rx.c b/drivers/net/ethernet/sfc/ef100_rx.c index 13ba1a4f66fc..012925e878f4 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.c +++ b/drivers/net/ethernet/sfc/ef100_rx.c @@ -31,6 +31,11 @@ #define ESF_GZ_RX_PREFIX_NT_OR_INNER_L3_CLASS_WIDTH \ ESF_GZ_RX_PREFIX_HCLASS_NT_OR_INNER_L3_CLASS_WIDTH +bool ef100_rx_buf_hash_valid(const u8 *prefix) +{ + return PREFIX_FIELD(prefix, RSS_HASH_VALID); +} + static bool check_fcs(struct efx_channel *channel, u32 *prefix) { u16 rxclass; diff --git a/drivers/net/ethernet/sfc/ef100_rx.h b/drivers/net/ethernet/sfc/ef100_rx.h index f2f266863966..fe45b36458d1 100644 --- a/drivers/net/ethernet/sfc/ef100_rx.h +++ b/drivers/net/ethernet/sfc/ef100_rx.h @@ -14,6 +14,7 @@ #include "net_driver.h" +bool ef100_rx_buf_hash_valid(const u8 *prefix); void efx_ef100_ev_rx(struct efx_channel *channel, const efx_qword_t *p_event); void ef100_rx_write(struct efx_rx_queue *rx_queue); void __ef100_rx_packet(struct efx_channel *channel); diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index a9808e86068d..daf0c00c1242 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -45,6 +45,14 @@ static inline void efx_rx_flush_packet(struct efx_channel *channel) __ef100_rx_packet, __efx_rx_packet, channel); } +static inline bool efx_rx_buf_hash_valid(struct efx_nic *efx, const u8 *prefix) +{ + if (efx->type->rx_buf_hash_valid) + return INDIRECT_CALL_1(efx->type->rx_buf_hash_valid, + ef100_rx_buf_hash_valid, + prefix); + return true; +} /* Maximum number of TCP segments we support for soft-TSO */ #define EFX_TSO_MAX_SEGS 100 diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 7bb7ecb480ae..062462a13847 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -846,6 +846,7 @@ struct efx_async_filter_insertion { * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds * @timer_max_ns: Interrupt timer maximum value, in nanoseconds * @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues + * @irqs_hooked: Channel interrupts are hooked * @irq_rx_mod_step_us: Step size for IRQ moderation for RX event queues * @irq_rx_moderation_us: IRQ moderation time for RX event queues * @msg_enable: Log message enable flags @@ -1004,6 +1005,7 @@ struct efx_nic { unsigned int timer_quantum_ns; unsigned int timer_max_ns; bool irq_rx_adaptive; + bool irqs_hooked; unsigned int irq_mod_step_us; unsigned int irq_rx_moderation_us; u32 msg_enable; @@ -1265,6 +1267,7 @@ struct efx_udp_tunnel { * @rx_write: Write RX descriptors and doorbell * @rx_defer_refill: Generate a refill reminder event * @rx_packet: Receive the queued RX buffer on a channel + * @rx_buf_hash_valid: Determine whether the RX prefix contains a valid hash * @ev_probe: Allocate resources for event queue * @ev_init: Initialise event queue on the NIC * @ev_fini: Deinitialise event queue on the NIC @@ -1409,6 +1412,7 @@ struct efx_nic_type { void (*rx_write)(struct efx_rx_queue *rx_queue); void (*rx_defer_refill)(struct efx_rx_queue *rx_queue); void (*rx_packet)(struct efx_channel *channel); + bool (*rx_buf_hash_valid)(const u8 *prefix); int (*ev_probe)(struct efx_channel *channel); int (*ev_init)(struct efx_channel *channel); void (*ev_fini)(struct efx_channel *channel); diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index d994d136bb03..d1e908846f5d 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -129,6 +129,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx) #endif } + efx->irqs_hooked = true; return 0; fail2: @@ -154,6 +155,8 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) efx->net_dev->rx_cpu_rmap = NULL; #endif + if (!efx->irqs_hooked) + return; if (EFX_INT_MODE_USE_MSI(efx)) { /* Disable MSI/MSI-X interrupts */ efx_for_each_channel(channel, efx) @@ -163,6 +166,7 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) /* Disable legacy interrupt */ free_irq(efx->legacy_irq, efx); } + efx->irqs_hooked = false; } /* Register dump */ diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index fb77c7bbe4af..5e29284c89c9 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -525,7 +525,8 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, return; } - if (efx->net_dev->features & NETIF_F_RXHASH) + if (efx->net_dev->features & NETIF_F_RXHASH && + efx_rx_buf_hash_valid(efx, eh)) skb_set_hash(skb, efx_rx_buf_hash(efx, eh), PKT_HASH_TYPE_L3); if (csum) { @@ -848,6 +849,7 @@ void efx_remove_filters(struct efx_nic *efx) efx_for_each_channel(channel, efx) { cancel_delayed_work_sync(&channel->filter_work); kfree(channel->rps_flow_id); + channel->rps_flow_id = NULL; } #endif down_write(&efx->filter_sem); diff --git a/drivers/net/fddi/skfp/cfm.c b/drivers/net/fddi/skfp/cfm.c index e9bf42996de8..4eea3408034b 100644 --- a/drivers/net/fddi/skfp/cfm.c +++ b/drivers/net/fddi/skfp/cfm.c @@ -36,10 +36,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)cfm.c 2.18 98/10/06 (C) SK " ; -#endif - /* * FSM Macros */ @@ -208,7 +204,6 @@ void cfm(struct s_smc *smc, int event) { int state ; /* remember last state */ int cond ; - int oldstate ; /* We will do the following: */ /* - compute the variable WC_Flag for every port (This is where */ @@ -222,7 +217,6 @@ void cfm(struct s_smc *smc, int event) /* - change the portstates */ cem_priv_state (smc, event); - oldstate = smc->mib.fddiSMTCF_State ; do { DB_CFM("CFM : state %s%s event %s", smc->mib.fddiSMTCF_State & AFLAG ? "ACTIONS " : "", @@ -250,18 +244,11 @@ void cfm(struct s_smc *smc, int event) if (cond != smc->mib.fddiSMTPeerWrapFlag) smt_srf_event(smc,SMT_COND_SMT_PEER_WRAP,0,cond) ; -#if 0 /* - * Don't send ever MAC_PATH_CHANGE events. Our MAC is hard-wired + * Don't ever send MAC_PATH_CHANGE events. Our MAC is hard-wired * to the primary path. */ - /* - * path change - */ - if (smc->mib.fddiSMTCF_State != oldstate) { - smt_srf_event(smc,SMT_EVENT_MAC_PATH_CHANGE,INDEX_MAC,0) ; - } -#endif + #endif /* no SLIM_SMT */ /* diff --git a/drivers/net/fddi/skfp/fplustm.c b/drivers/net/fddi/skfp/fplustm.c index 02966d141948..4cbb145c74ab 100644 --- a/drivers/net/fddi/skfp/fplustm.c +++ b/drivers/net/fddi/skfp/fplustm.c @@ -21,10 +21,6 @@ #include <linux/bitrev.h> #include <linux/etherdevice.h> -#ifndef lint -static const char ID_sccs[] = "@(#)fplustm.c 1.32 99/02/23 (C) SK " ; -#endif - #ifndef UNUSED #ifdef lint #define UNUSED(x) (x) = (x) diff --git a/drivers/net/fddi/skfp/hwmtm.c b/drivers/net/fddi/skfp/hwmtm.c index 3412e0fb0ac4..107039056511 100644 --- a/drivers/net/fddi/skfp/hwmtm.c +++ b/drivers/net/fddi/skfp/hwmtm.c @@ -10,10 +10,6 @@ * ******************************************************************************/ -#ifndef lint -static char const ID_sccs[] = "@(#)hwmtm.c 1.40 99/05/31 (C) SK" ; -#endif - #define HWMTM #ifndef FDDI diff --git a/drivers/net/fddi/skfp/smt.c b/drivers/net/fddi/skfp/smt.c index b8c59d803ce6..774a6e3b0a67 100644 --- a/drivers/net/fddi/skfp/smt.c +++ b/drivers/net/fddi/skfp/smt.c @@ -20,10 +20,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)smt.c 2.43 98/11/23 (C) SK " ; -#endif - /* * FC in SMbuf */ @@ -1561,7 +1557,7 @@ u_long smt_get_tid(struct s_smc *smc) return tid & 0x3fffffffL; } - +#ifdef LITTLE_ENDIAN /* * table of parameter lengths */ @@ -1641,6 +1637,7 @@ static const struct smt_pdef { } ; #define N_SMT_PLEN ARRAY_SIZE(smt_pdef) +#endif int smt_check_para(struct s_smc *smc, struct smt_header *sm, const u_short list[]) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 787f17e2a971..64b0a74c1523 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -367,7 +367,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, } rcu_read_unlock(); - while (unlikely(txq >= ndev->real_num_tx_queues)) + while (txq >= ndev->real_num_tx_queues) txq -= ndev->real_num_tx_queues; return txq; @@ -502,7 +502,7 @@ static int netvsc_vf_xmit(struct net_device *net, struct net_device *vf_netdev, int rc; skb->dev = vf_netdev; - skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping; + skb_record_rx_queue(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); rc = dev_queue_xmit(skb); if (likely(rc == NET_XMIT_SUCCESS || rc == NET_XMIT_CN)) { diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 15e87c097b0b..5bca94c99006 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -106,12 +106,21 @@ static void ipvlan_port_destroy(struct net_device *dev) kfree(port); } +#define IPVLAN_ALWAYS_ON_OFLOADS \ + (NETIF_F_SG | NETIF_F_HW_CSUM | \ + NETIF_F_GSO_ROBUST | NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL) + +#define IPVLAN_ALWAYS_ON \ + (IPVLAN_ALWAYS_ON_OFLOADS | NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED) + #define IPVLAN_FEATURES \ - (NETIF_F_SG | NETIF_F_CSUM_MASK | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ + (NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | \ NETIF_F_GSO | NETIF_F_ALL_TSO | NETIF_F_GSO_ROBUST | \ NETIF_F_GRO | NETIF_F_RXCSUM | \ NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER) + /* NETIF_F_GSO_ENCAP_ALL NETIF_F_GSO_SOFTWARE Newly added */ + #define IPVLAN_STATE_MASK \ ((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT)) @@ -125,7 +134,9 @@ static int ipvlan_init(struct net_device *dev) dev->state = (dev->state & ~IPVLAN_STATE_MASK) | (phy_dev->state & IPVLAN_STATE_MASK); dev->features = phy_dev->features & IPVLAN_FEATURES; - dev->features |= NETIF_F_LLTX | NETIF_F_VLAN_CHALLENGED; + dev->features |= IPVLAN_ALWAYS_ON; + dev->vlan_features = phy_dev->vlan_features & IPVLAN_FEATURES; + dev->vlan_features |= IPVLAN_ALWAYS_ON_OFLOADS; dev->hw_enc_features |= dev->features; dev->gso_max_size = phy_dev->gso_max_size; dev->gso_max_segs = phy_dev->gso_max_segs; @@ -227,7 +238,14 @@ static netdev_features_t ipvlan_fix_features(struct net_device *dev, { struct ipvl_dev *ipvlan = netdev_priv(dev); - return features & (ipvlan->sfeatures | ~IPVLAN_FEATURES); + features |= NETIF_F_ALL_FOR_ALL; + features &= (ipvlan->sfeatures | ~IPVLAN_FEATURES); + features = netdev_increment_features(ipvlan->phy_dev->features, + features, features); + features |= IPVLAN_ALWAYS_ON; + features &= (IPVLAN_FEATURES | IPVLAN_ALWAYS_ON); + + return features; } static void ipvlan_change_rx_flags(struct net_device *dev, int change) @@ -734,10 +752,9 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: list_for_each_entry(ipvlan, &port->ipvlans, pnode) { - ipvlan->dev->features = dev->features & IPVLAN_FEATURES; ipvlan->dev->gso_max_size = dev->gso_max_size; ipvlan->dev->gso_max_segs = dev->gso_max_segs; - netdev_features_change(ipvlan->dev); + netdev_update_features(ipvlan->dev); } break; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 4942f6112e51..5da04e997989 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1269,6 +1269,9 @@ static void macvlan_port_destroy(struct net_device *dev) static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { + struct nlattr *nla, *head; + int rem, len; + if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; @@ -1316,6 +1319,20 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], return -EADDRNOTAVAIL; } + if (data[IFLA_MACVLAN_MACADDR_DATA]) { + head = nla_data(data[IFLA_MACVLAN_MACADDR_DATA]); + len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); + + nla_for_each_attr(nla, head, len, rem) { + if (nla_type(nla) != IFLA_MACVLAN_MACADDR || + nla_len(nla) != ETH_ALEN) + return -EINVAL; + + if (!is_valid_ether_addr(nla_data(nla))) + return -EADDRNOTAVAIL; + } + } + if (data[IFLA_MACVLAN_MACADDR_COUNT]) return -EINVAL; @@ -1372,10 +1389,6 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode, len = nla_len(data[IFLA_MACVLAN_MACADDR_DATA]); nla_for_each_attr(nla, head, len, rem) { - if (nla_type(nla) != IFLA_MACVLAN_MACADDR || - nla_len(nla) != ETH_ALEN) - continue; - addr = nla_data(nla); ret = macvlan_hash_add_source(vlan, addr); if (ret) diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index a4fbf3a4fa97..6bc7406a1ce7 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -1738,13 +1738,13 @@ static int __phy_write_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb, return 0; } -/* Trigger a read to the spcified MCB */ +/* Trigger a read to the specified MCB */ static int phy_update_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb) { return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_READ); } -/* Trigger a write to the spcified MCB */ +/* Trigger a write to the specified MCB */ static int phy_commit_mcb_s6g(struct phy_device *phydev, u32 reg, u8 mcb) { return __phy_write_mcb_s6g(phydev, reg, mcb, PHY_MCB_S6G_WRITE); diff --git a/drivers/net/wan/dlci.c b/drivers/net/wan/dlci.c index 7bcee41905cf..3ca4daf63389 100644 --- a/drivers/net/wan/dlci.c +++ b/drivers/net/wan/dlci.c @@ -295,14 +295,13 @@ static int dlci_close(struct net_device *dev) { struct dlci_local *dlp; struct frad_local *flp; - int err; netif_stop_queue(dev); dlp = netdev_priv(dev); flp = netdev_priv(dlp->slave); - err = (*flp->deactivate)(dlp->slave, dev); + (*flp->deactivate)(dlp->slave, dev); return 0; } diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index dfc16770458d..386ed2aa31fd 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -230,6 +230,7 @@ static void hdlc_setup_dev(struct net_device *dev) dev->max_mtu = HDLC_MAX_MTU; dev->type = ARPHRD_RAWHDLC; dev->hard_header_len = 16; + dev->needed_headroom = 0; dev->addr_len = 0; dev->header_ops = &hdlc_null_ops; } diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index f70336bb6f52..f52b9fed0593 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -107,8 +107,14 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) { int result; + /* There should be a pseudo header of 1 byte added by upper layers. + * Check to make sure it is there before reading it. + */ + if (skb->len < 1) { + kfree_skb(skb); + return NETDEV_TX_OK; + } - /* X.25 to LAPB */ switch (skb->data[0]) { case X25_IFACE_DATA: /* Data to be transmitted */ skb_pull(skb, 1); @@ -294,6 +300,15 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return result; memcpy(&state(hdlc)->settings, &new_settings, size); + + /* There's no header_ops so hard_header_len should be 0. */ + dev->hard_header_len = 0; + /* When transmitting data: + * first we'll remove a pseudo header of 1 byte, + * then we'll prepend an LAPB header of at most 3 bytes. + */ + dev->needed_headroom = 3 - 1; + dev->type = ARPHRD_X25; call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, dev); netif_dormant_off(dev); diff --git a/drivers/of/address.c b/drivers/of/address.c index 590493e04b01..da4f7341323f 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -128,15 +128,29 @@ static unsigned int of_bus_pci_get_flags(const __be32 *addr) * PCI bus specific translator */ +static bool of_node_is_pcie(struct device_node *np) +{ + bool is_pcie = of_node_name_eq(np, "pcie"); + + if (is_pcie) + pr_warn_once("%pOF: Missing device_type\n", np); + + return is_pcie; +} + static int of_bus_pci_match(struct device_node *np) { /* * "pciex" is PCI Express * "vci" is for the /chaos bridge on 1st-gen PCI powermacs * "ht" is hypertransport + * + * If none of the device_type match, and that the node name is + * "pcie", accept the device as PCI (with a warning). */ return of_node_is_type(np, "pci") || of_node_is_type(np, "pciex") || - of_node_is_type(np, "vci") || of_node_is_type(np, "ht"); + of_node_is_type(np, "vci") || of_node_is_type(np, "ht") || + of_node_is_pcie(np); } static void of_bus_pci_count_cells(struct device_node *np, @@ -985,6 +999,11 @@ int of_dma_get_range(struct device_node *np, u64 *dma_addr, u64 *paddr, u64 *siz /* Don't error out as we'd break some existing DTs */ continue; } + if (range.cpu_addr == OF_BAD_ADDR) { + pr_err("translation of DMA address(%llx) to CPU address failed node(%pOF)\n", + range.bus_addr, node); + continue; + } dma_offset = range.cpu_addr - range.bus_addr; /* Take lower and upper limits */ diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 9d7fb45b1786..9668ea04cc80 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -893,8 +893,10 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) * have OPP table for the device, while others don't and * opp_set_rate() just needs to behave like clk_set_rate(). */ - if (!_get_opp_count(opp_table)) - return 0; + if (!_get_opp_count(opp_table)) { + ret = 0; + goto put_opp_table; + } if (!opp_table->required_opp_tables && !opp_table->regulators && !opp_table->paths) { @@ -905,7 +907,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) ret = _set_opp_bw(opp_table, NULL, dev, true); if (ret) - return ret; + goto put_opp_table; if (opp_table->regulator_enabled) { regulator_disable(opp_table->regulators[0]); @@ -932,10 +934,13 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq) /* Return early if nothing to do */ if (old_freq == freq) { - dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", - __func__, freq); - ret = 0; - goto put_opp_table; + if (!opp_table->required_opp_tables && !opp_table->regulators && + !opp_table->paths) { + dev_dbg(dev, "%s: old/new frequencies (%lu Hz) are same, nothing to do\n", + __func__, freq); + ret = 0; + goto put_opp_table; + } } /* diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index b59f84918fe0..c9e790c74051 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -83,21 +83,19 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) struct zpci_dev *zdev = container_of(hotplug_slot, struct zpci_dev, hotplug_slot); struct pci_dev *pdev; - struct zpci_bus *zbus = zdev->zbus; int rc; if (!zpci_fn_configured(zdev->state)) return -EIO; - pdev = pci_get_slot(zbus->bus, zdev->devfn); - if (pdev) { - if (pci_num_vf(pdev)) - return -EBUSY; - - pci_stop_and_remove_bus_device_locked(pdev); + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (pdev && pci_num_vf(pdev)) { pci_dev_put(pdev); + return -EBUSY; } + zpci_remove_device(zdev); + rc = zpci_disable_device(zdev); if (rc) return rc; diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 64ebed129dbf..f357f9a32b3a 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -556,13 +556,14 @@ int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients, return -1; for (i = 0; i < num_clients; i++) { - if (IS_ENABLED(CONFIG_DMA_VIRT_OPS) && - clients[i]->dma_ops == &dma_virt_ops) { +#ifdef CONFIG_DMA_VIRT_OPS + if (clients[i]->dma_ops == &dma_virt_ops) { if (verbose) dev_warn(clients[i], "cannot be used for peer-to-peer DMA because the driver makes use of dma_virt_ops\n"); return -1; } +#endif pci_client = find_parent_pci_dev(clients[i]); if (!pci_client) { @@ -842,9 +843,10 @@ static int __pci_p2pdma_map_sg(struct pci_p2pdma_pagemap *p2p_pgmap, * this should never happen because it will be prevented * by the check in pci_p2pdma_distance_many() */ - if (WARN_ON_ONCE(IS_ENABLED(CONFIG_DMA_VIRT_OPS) && - dev->dma_ops == &dma_virt_ops)) +#ifdef CONFIG_DMA_VIRT_OPS + if (WARN_ON_ONCE(dev->dma_ops == &dma_virt_ops)) return 0; +#endif for_each_sg(sg, s, nents, i) { paddr = sg_phys(s); diff --git a/drivers/ptp/ptp_clockmatrix.c b/drivers/ptp/ptp_clockmatrix.c index 73aaae5574ed..e020faff7da5 100644 --- a/drivers/ptp/ptp_clockmatrix.c +++ b/drivers/ptp/ptp_clockmatrix.c @@ -142,16 +142,15 @@ static int idtcm_strverscmp(const char *ver1, const char *ver2) return result; } -static int idtcm_xfer(struct idtcm *idtcm, - u8 regaddr, - u8 *buf, - u16 count, - bool write) +static int idtcm_xfer_read(struct idtcm *idtcm, + u8 regaddr, + u8 *buf, + u16 count) { struct i2c_client *client = idtcm->client; struct i2c_msg msg[2]; int cnt; - char *fmt = "i2c_transfer failed at %d in %s for %s, at addr: %04X!\n"; + char *fmt = "i2c_transfer failed at %d in %s, at addr: %04X!\n"; msg[0].addr = client->addr; msg[0].flags = 0; @@ -159,7 +158,7 @@ static int idtcm_xfer(struct idtcm *idtcm, msg[0].buf = ®addr; msg[1].addr = client->addr; - msg[1].flags = write ? 0 : I2C_M_RD; + msg[1].flags = I2C_M_RD; msg[1].len = count; msg[1].buf = buf; @@ -170,7 +169,6 @@ static int idtcm_xfer(struct idtcm *idtcm, fmt, __LINE__, __func__, - write ? "write" : "read", regaddr); return cnt; } else if (cnt != 2) { @@ -182,6 +180,37 @@ static int idtcm_xfer(struct idtcm *idtcm, return 0; } +static int idtcm_xfer_write(struct idtcm *idtcm, + u8 regaddr, + u8 *buf, + u16 count) +{ + struct i2c_client *client = idtcm->client; + /* we add 1 byte for device register */ + u8 msg[IDTCM_MAX_WRITE_COUNT + 1]; + int cnt; + char *fmt = "i2c_master_send failed at %d in %s, at addr: %04X!\n"; + + if (count > IDTCM_MAX_WRITE_COUNT) + return -EINVAL; + + msg[0] = regaddr; + memcpy(&msg[1], buf, count); + + cnt = i2c_master_send(client, msg, count + 1); + + if (cnt < 0) { + dev_err(&client->dev, + fmt, + __LINE__, + __func__, + regaddr); + return cnt; + } + + return 0; +} + static int idtcm_page_offset(struct idtcm *idtcm, u8 val) { u8 buf[4]; @@ -195,7 +224,7 @@ static int idtcm_page_offset(struct idtcm *idtcm, u8 val) buf[2] = 0x10; buf[3] = 0x20; - err = idtcm_xfer(idtcm, PAGE_ADDR, buf, sizeof(buf), 1); + err = idtcm_xfer_write(idtcm, PAGE_ADDR, buf, sizeof(buf)); if (err) { idtcm->page_offset = 0xff; @@ -223,11 +252,12 @@ static int _idtcm_rdwr(struct idtcm *idtcm, err = idtcm_page_offset(idtcm, hi); if (err) - goto out; + return err; - err = idtcm_xfer(idtcm, lo, buf, count, write); -out: - return err; + if (write) + return idtcm_xfer_write(idtcm, lo, buf, count); + + return idtcm_xfer_read(idtcm, lo, buf, count); } static int idtcm_read(struct idtcm *idtcm, diff --git a/drivers/ptp/ptp_clockmatrix.h b/drivers/ptp/ptp_clockmatrix.h index ffae56c5d97f..82840d72364a 100644 --- a/drivers/ptp/ptp_clockmatrix.h +++ b/drivers/ptp/ptp_clockmatrix.h @@ -55,6 +55,8 @@ #define PEROUT_ENABLE_OUTPUT_MASK (0xdeadbeef) +#define IDTCM_MAX_WRITE_COUNT (512) + /* Values of DPLL_N.DPLL_MODE.PLL_MODE */ enum pll_mode { PLL_MODE_MIN = 0, diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 94edbb33d0d1..aca022239b33 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -677,6 +677,11 @@ static int slow_eval_known_fn(struct subchannel *sch, void *data) rc = css_evaluate_known_subchannel(sch, 1); if (rc == -EAGAIN) css_schedule_eval(sch->schid); + /* + * The loop might take long time for platforms with lots of + * known devices. Allow scheduling here. + */ + cond_resched(); } return 0; } diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c index c795f22249d8..140186fe1d1e 100644 --- a/drivers/s390/scsi/zfcp_fsf.c +++ b/drivers/s390/scsi/zfcp_fsf.c @@ -434,7 +434,7 @@ static void zfcp_fsf_req_complete(struct zfcp_fsf_req *req) return; } - del_timer(&req->timer); + del_timer_sync(&req->timer); zfcp_fsf_protstatus_eval(req); zfcp_fsf_fsfstatus_eval(req); req->handler(req); @@ -867,7 +867,7 @@ static int zfcp_fsf_req_send(struct zfcp_fsf_req *req) req->qdio_req.qdio_outb_usage = atomic_read(&qdio->req_q_free); req->issued = get_tod_clock(); if (zfcp_qdio_send(qdio, &req->qdio_req)) { - del_timer(&req->timer); + del_timer_sync(&req->timer); /* lookup request again, list might have changed */ zfcp_reqlist_find_rm(adapter->req_list, req_id); zfcp_erp_adapter_reopen(adapter, 0, "fsrs__1"); diff --git a/drivers/scsi/qla2xxx/qla_dbg.h b/drivers/scsi/qla2xxx/qla_dbg.h index 91eb6901815c..e1d7de63e8f8 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.h +++ b/drivers/scsi/qla2xxx/qla_dbg.h @@ -380,5 +380,8 @@ extern int qla24xx_soft_reset(struct qla_hw_data *); static inline int ql_mask_match(uint level) { + if (ql2xextended_error_logging == 1) + ql2xextended_error_logging = QL_DBG_DEFAULT1_MASK; + return (level & ql2xextended_error_logging) == level; } diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index 8c92af5e4390..1bc090d8a71b 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -3880,6 +3880,7 @@ struct qla_hw_data { uint32_t scm_supported_f:1; /* Enabled in Driver */ uint32_t scm_enabled:1; + uint32_t max_req_queue_warned:1; } flags; uint16_t max_exchg; diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c index df670fba2ab8..de9fd7f688d0 100644 --- a/drivers/scsi/qla2xxx/qla_gs.c +++ b/drivers/scsi/qla2xxx/qla_gs.c @@ -1505,11 +1505,11 @@ qla2x00_prep_ct_fdmi_req(struct ct_sns_pkt *p, uint16_t cmd, static uint qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha) { + uint speeds = 0; + if (IS_CNA_CAPABLE(ha)) return FDMI_PORT_SPEED_10GB; if (IS_QLA28XX(ha) || IS_QLA27XX(ha)) { - uint speeds = 0; - if (ha->max_supported_speed == 2) { if (ha->min_supported_speed <= 6) speeds |= FDMI_PORT_SPEED_64GB; @@ -1536,9 +1536,16 @@ qla25xx_fdmi_port_speed_capability(struct qla_hw_data *ha) } return speeds; } - if (IS_QLA2031(ha)) - return FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB| - FDMI_PORT_SPEED_4GB; + if (IS_QLA2031(ha)) { + if ((ha->pdev->subsystem_vendor == 0x103C) && + (ha->pdev->subsystem_device == 0x8002)) { + speeds = FDMI_PORT_SPEED_16GB; + } else { + speeds = FDMI_PORT_SPEED_16GB|FDMI_PORT_SPEED_8GB| + FDMI_PORT_SPEED_4GB; + } + return speeds; + } if (IS_QLA25XX(ha)) return FDMI_PORT_SPEED_8GB|FDMI_PORT_SPEED_4GB| FDMI_PORT_SPEED_2GB|FDMI_PORT_SPEED_1GB; @@ -3436,7 +3443,6 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp) list_for_each_entry(fcport, &vha->vp_fcports, list) { if ((fcport->flags & FCF_FABRIC_DEVICE) != 0) { fcport->scan_state = QLA_FCPORT_SCAN; - fcport->logout_on_delete = 0; } } goto login_logout; @@ -3532,10 +3538,22 @@ login_logout: } if (fcport->scan_state != QLA_FCPORT_FOUND) { + bool do_delete = false; + + if (fcport->scan_needed && + fcport->disc_state == DSC_LOGIN_PEND) { + /* Cable got disconnected after we sent + * a login. Do delete to prevent timeout. + */ + fcport->logout_on_delete = 1; + do_delete = true; + } + fcport->scan_needed = 0; - if ((qla_dual_mode_enabled(vha) || - qla_ini_mode_enabled(vha)) && - atomic_read(&fcport->state) == FCS_ONLINE) { + if (((qla_dual_mode_enabled(vha) || + qla_ini_mode_enabled(vha)) && + atomic_read(&fcport->state) == FCS_ONLINE) || + do_delete) { if (fcport->loop_id != FC_NO_LOOP_ID) { if (fcport->flags & FCF_FCP2_DEVICE) fcport->logout_on_delete = 0; @@ -3736,6 +3754,18 @@ static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res) unsigned long flags; const char *name = sp->name; + if (res == QLA_OS_TIMER_EXPIRED) { + /* switch is ignoring all commands. + * This might be a zone disable behavior. + * This means we hit 64s timeout. + * 22s GPNFT + 44s Abort = 64s + */ + ql_dbg(ql_dbg_disc, vha, 0xffff, + "%s: Switch Zone check please .\n", + name); + qla2x00_mark_all_devices_lost(vha); + } + /* * We are in an Interrupt context, queue up this * sp for GNNFT_DONE work. This will allow all diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 27bcd346af7c..ab5275dbc338 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -2024,8 +2024,8 @@ qla24xx_els_ct_entry(scsi_qla_host_t *vha, struct req_que *req, res = DID_ERROR << 16; } } - ql_dbg(ql_dbg_user, vha, 0x503f, - "ELS IOCB Done -%s error hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n", + ql_dbg(ql_dbg_disc, vha, 0x503f, + "ELS IOCB Done -%s hdl=%x comp_status=0x%x error subcode 1=0x%x error subcode 2=0x%x total_byte=0x%x\n", type, sp->handle, comp_status, fw_status[1], fw_status[2], le32_to_cpu(ese->total_byte_count)); goto els_ct_done; diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 73883435ab58..226f1428d3e5 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -334,14 +334,6 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (time_after(jiffies, wait_time)) break; - /* - * Check if it's UNLOADING, cause we cannot poll in - * this case, or else a NULL pointer dereference - * is triggered. - */ - if (unlikely(test_bit(UNLOADING, &base_vha->dpc_flags))) - return QLA_FUNCTION_TIMEOUT; - /* Check for pending interrupts. */ qla2x00_poll(ha->rsp_q_map[0]); @@ -5240,7 +5232,7 @@ qla2x00_read_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t *data) mcp->mb[8] = MSW(risc_addr); mcp->out_mb = MBX_8|MBX_1|MBX_0; mcp->in_mb = MBX_3|MBX_2|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (rval != QLA_SUCCESS) { @@ -5428,7 +5420,7 @@ qla2x00_write_ram_word(scsi_qla_host_t *vha, uint32_t risc_addr, uint32_t data) mcp->mb[8] = MSW(risc_addr); mcp->out_mb = MBX_8|MBX_3|MBX_2|MBX_1|MBX_0; mcp->in_mb = MBX_1|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (rval != QLA_SUCCESS) { @@ -5700,7 +5692,7 @@ qla24xx_set_fcp_prio(scsi_qla_host_t *vha, uint16_t loop_id, uint16_t priority, mcp->mb[9] = vha->vp_idx; mcp->out_mb = MBX_9|MBX_4|MBX_3|MBX_2|MBX_1|MBX_0; mcp->in_mb = MBX_4|MBX_3|MBX_1|MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); if (mb != NULL) { @@ -5787,7 +5779,7 @@ qla82xx_mbx_intr_enable(scsi_qla_host_t *vha) mcp->out_mb = MBX_1|MBX_0; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -5822,7 +5814,7 @@ qla82xx_mbx_intr_disable(scsi_qla_host_t *vha) mcp->out_mb = MBX_1|MBX_0; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -6014,7 +6006,7 @@ qla81xx_set_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg) if (IS_QLA8031(ha)) mcp->out_mb |= MBX_6|MBX_5|MBX_4|MBX_3; mcp->in_mb = MBX_0; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); @@ -6050,7 +6042,7 @@ qla81xx_get_led_config(scsi_qla_host_t *vha, uint16_t *led_cfg) mcp->in_mb = MBX_2|MBX_1|MBX_0; if (IS_QLA8031(ha)) mcp->in_mb |= MBX_6|MBX_5|MBX_4|MBX_3; - mcp->tov = 30; + mcp->tov = MBX_TOV_SECONDS; mcp->flags = 0; rval = qla2x00_mailbox_command(vha, mcp); diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index fa695a4007f8..90bbc61f361b 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -536,6 +536,11 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, struct nvme_private *priv = fd->private; struct qla_nvme_rport *qla_rport = rport->private; + if (!priv) { + /* nvme association has been torn down */ + return rval; + } + fcport = qla_rport->fcport; if (!qpair || !fcport || (qpair && !qpair->fw_started) || @@ -687,7 +692,15 @@ int qla_nvme_register_hba(struct scsi_qla_host *vha) tmpl = &qla_nvme_fc_transport; WARN_ON(vha->nvme_local_port); - WARN_ON(ha->max_req_queues < 3); + + if (ha->max_req_queues < 3) { + if (!ha->flags.max_req_queue_warned) + ql_log(ql_log_info, vha, 0x2120, + "%s: Disabling FC-NVME due to lack of free queue pairs (%d).\n", + __func__, ha->max_req_queues); + ha->flags.max_req_queue_warned = 1; + return ret; + } qla_nvme_fc_transport.max_hw_queues = min((uint8_t)(qla_nvme_fc_transport.max_hw_queues), diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 9b59f032a569..8da00ba54aec 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -2017,6 +2017,11 @@ skip_pio: /* Determine queue resources */ ha->max_req_queues = ha->max_rsp_queues = 1; ha->msix_count = QLA_BASE_VECTORS; + + /* Check if FW supports MQ or not */ + if (!(ha->fw_attributes & BIT_6)) + goto mqiobase_exit; + if (!ql2xmqsupport || !ql2xnvmeenable || (!IS_QLA25XX(ha) && !IS_QLA81XX(ha))) goto mqiobase_exit; @@ -2829,10 +2834,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) /* This may fail but that's ok */ pci_enable_pcie_error_reporting(pdev); - /* Turn off T10-DIF when FC-NVMe is enabled */ - if (ql2xnvmeenable) - ql2xenabledif = 0; - ha = kzalloc(sizeof(struct qla_hw_data), GFP_KERNEL); if (!ha) { ql_log_pci(ql_log_fatal, pdev, 0x0009, diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index fbb80a043b4f..90289162dbd4 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -1270,7 +1270,7 @@ void qlt_schedule_sess_for_deletion(struct fc_port *sess) qla24xx_chk_fcp_state(sess); - ql_dbg(ql_dbg_tgt, sess->vha, 0xe001, + ql_dbg(ql_dbg_disc, sess->vha, 0xe001, "Scheduling sess %p for deletion %8phC\n", sess, sess->port_name); diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 064ed680c053..139f0073da37 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -5490,9 +5490,11 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip, u64 d = ktime_get_boottime_ns() - ns_from_boot; if (kt <= d) { /* elapsed duration >= kt */ + spin_lock_irqsave(&sqp->qc_lock, iflags); sqcp->a_cmnd = NULL; atomic_dec(&devip->num_in_q); clear_bit(k, sqp->in_use_bm); + spin_unlock_irqrestore(&sqp->qc_lock, iflags); if (new_sd_dp) kfree(sd_dp); /* call scsi_done() from this thread */ diff --git a/drivers/scsi/ufs/ti-j721e-ufs.c b/drivers/scsi/ufs/ti-j721e-ufs.c index 46bb905b4d6a..eafe0db98d54 100644 --- a/drivers/scsi/ufs/ti-j721e-ufs.c +++ b/drivers/scsi/ufs/ti-j721e-ufs.c @@ -38,6 +38,7 @@ static int ti_j721e_ufs_probe(struct platform_device *pdev) /* Select MPHY refclk frequency */ clk = devm_clk_get(dev, NULL); if (IS_ERR(clk)) { + ret = PTR_ERR(clk); dev_err(dev, "Cannot claim MPHY clock.\n"); goto clk_err; } diff --git a/drivers/scsi/ufs/ufs-mediatek.c b/drivers/scsi/ufs/ufs-mediatek.c index 29cd017c1aa0..1755dd6b04ae 100644 --- a/drivers/scsi/ufs/ufs-mediatek.c +++ b/drivers/scsi/ufs/ufs-mediatek.c @@ -212,7 +212,7 @@ static int ufs_mtk_wait_link_state(struct ufs_hba *hba, u32 state, ktime_t timeout, time_checked; u32 val; - timeout = ktime_add_us(ktime_get(), ms_to_ktime(max_wait_ms)); + timeout = ktime_add_ms(ktime_get(), max_wait_ms); do { time_checked = ktime_get(); ufshcd_writel(hba, 0x20, REG_UFS_DEBUG_SEL); diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c index f407b13883ac..5a95a7bfbab0 100644 --- a/drivers/scsi/ufs/ufshcd-pci.c +++ b/drivers/scsi/ufs/ufshcd-pci.c @@ -44,11 +44,23 @@ static int ufs_intel_link_startup_notify(struct ufs_hba *hba, return err; } +static int ufs_intel_ehl_init(struct ufs_hba *hba) +{ + hba->quirks |= UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8; + return 0; +} + static struct ufs_hba_variant_ops ufs_intel_cnl_hba_vops = { .name = "intel-pci", .link_startup_notify = ufs_intel_link_startup_notify, }; +static struct ufs_hba_variant_ops ufs_intel_ehl_hba_vops = { + .name = "intel-pci", + .init = ufs_intel_ehl_init, + .link_startup_notify = ufs_intel_link_startup_notify, +}; + #ifdef CONFIG_PM_SLEEP /** * ufshcd_pci_suspend - suspend power management function @@ -177,8 +189,8 @@ static const struct dev_pm_ops ufshcd_pci_pm_ops = { static const struct pci_device_id ufshcd_pci_tbl[] = { { PCI_VENDOR_ID_SAMSUNG, 0xC00C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, { PCI_VDEVICE(INTEL, 0x9DFA), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, - { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, - { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_cnl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x4B41), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, + { PCI_VDEVICE(INTEL, 0x4B43), (kernel_ulong_t)&ufs_intel_ehl_hba_vops }, { } /* terminate list */ }; diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 307622284239..da199fa7a3e0 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1561,6 +1561,7 @@ unblock_reqs: int ufshcd_hold(struct ufs_hba *hba, bool async) { int rc = 0; + bool flush_result; unsigned long flags; if (!ufshcd_is_clkgating_allowed(hba)) @@ -1592,7 +1593,9 @@ start: break; } spin_unlock_irqrestore(hba->host->host_lock, flags); - flush_work(&hba->clk_gating.ungate_work); + flush_result = flush_work(&hba->clk_gating.ungate_work); + if (hba->clk_gating.is_suspended && !flush_result) + goto out; spin_lock_irqsave(hba->host->host_lock, flags); goto start; } @@ -5941,7 +5944,7 @@ static irqreturn_t ufshcd_sl_intr(struct ufs_hba *hba, u32 intr_status) */ static irqreturn_t ufshcd_intr(int irq, void *__hba) { - u32 intr_status, enabled_intr_status; + u32 intr_status, enabled_intr_status = 0; irqreturn_t retval = IRQ_NONE; struct ufs_hba *hba = __hba; int retries = hba->nutrs; @@ -5955,7 +5958,7 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) * read, make sure we handle them by checking the interrupt status * again in a loop until we process all of the reqs before returning. */ - do { + while (intr_status && retries--) { enabled_intr_status = intr_status & ufshcd_readl(hba, REG_INTERRUPT_ENABLE); if (intr_status) @@ -5964,9 +5967,9 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) retval |= ufshcd_sl_intr(hba, enabled_intr_status); intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); - } while (intr_status && --retries); + } - if (retval == IRQ_NONE) { + if (enabled_intr_status && retval == IRQ_NONE) { dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x\n", __func__, intr_status); ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: "); @@ -6434,14 +6437,8 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) goto out; } - if (!(reg & (1 << tag))) { - dev_err(hba->dev, - "%s: cmd was completed, but without a notifying intr, tag = %d", - __func__, tag); - } - /* Print Transfer Request of aborted task */ - dev_err(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag); + dev_info(hba->dev, "%s: Device abort task at tag %d\n", __func__, tag); /* * Print detailed info about aborted request. @@ -6462,6 +6459,13 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) } hba->req_abort_count++; + if (!(reg & (1 << tag))) { + dev_err(hba->dev, + "%s: cmd was completed, but without a notifying intr, tag = %d", + __func__, tag); + goto cleanup; + } + /* Skip task abort in case previous aborts failed and report failure */ if (lrbp->req_abort_skip) { err = -EIO; @@ -6492,7 +6496,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) /* command completed already */ dev_err(hba->dev, "%s: cmd at tag %d successfully cleared from DB.\n", __func__, tag); - goto out; + goto cleanup; } else { dev_err(hba->dev, "%s: no response from device. tag = %d, err %d\n", @@ -6526,6 +6530,7 @@ static int ufshcd_abort(struct scsi_cmnd *cmd) goto out; } +cleanup: scsi_dma_unmap(cmd); spin_lock_irqsave(host->host_lock, flags); diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h index b2ef18f1b746..363589c0bd37 100644 --- a/drivers/scsi/ufs/ufshcd.h +++ b/drivers/scsi/ufs/ufshcd.h @@ -520,6 +520,12 @@ enum ufshcd_quirks { * OCS FATAL ERROR with device error through sense data */ UFSHCD_QUIRK_BROKEN_OCS_FATAL_ERROR = 1 << 10, + + /* + * This quirk needs to be enabled if the host controller has + * auto-hibernate capability but it doesn't work. + */ + UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8 = 1 << 11, }; enum ufshcd_caps { @@ -803,7 +809,8 @@ return true; static inline bool ufshcd_is_auto_hibern8_supported(struct ufs_hba *hba) { - return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT); + return (hba->capabilities & MASK_AUTO_HIBERN8_SUPPORT) && + !(hba->quirks & UFSHCD_QUIRK_BROKEN_AUTO_HIBERN8); } static inline bool ufshcd_is_auto_hibern8_enabled(struct ufs_hba *hba) diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index c3008e423f59..c6ea760ea5f0 100644 --- a/drivers/spi/Kconfig +++ b/drivers/spi/Kconfig @@ -1017,4 +1017,7 @@ config SPI_SLAVE_SYSTEM_CONTROL endif # SPI_SLAVE +config SPI_DYNAMIC + def_bool ACPI || OF_DYNAMIC || SPI_SLAVE + endif # SPI diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index 4c643dfc7fbb..d4b33b358a31 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -13,6 +13,7 @@ #include <linux/iopoll.h> #include <linux/module.h> #include <linux/of_platform.h> +#include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/reset.h> #include <linux/spi/spi.h> @@ -441,7 +442,8 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, { u32 div, mbrdiv; - div = DIV_ROUND_UP(spi->clk_rate, speed_hz); + /* Ensure spi->clk_rate is even */ + div = DIV_ROUND_UP(spi->clk_rate & ~0x1, speed_hz); /* * SPI framework set xfer->speed_hz to master->max_speed_hz if @@ -467,20 +469,27 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz, /** * stm32h7_spi_prepare_fthlv - Determine FIFO threshold level * @spi: pointer to the spi controller data structure + * @xfer_len: length of the message to be transferred */ -static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi) +static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi, u32 xfer_len) { - u32 fthlv, half_fifo; + u32 fthlv, half_fifo, packet; /* data packet should not exceed 1/2 of fifo space */ half_fifo = (spi->fifo_size / 2); + /* data_packet should not exceed transfer length */ + if (half_fifo > xfer_len) + packet = xfer_len; + else + packet = half_fifo; + if (spi->cur_bpw <= 8) - fthlv = half_fifo; + fthlv = packet; else if (spi->cur_bpw <= 16) - fthlv = half_fifo / 2; + fthlv = packet / 2; else - fthlv = half_fifo / 4; + fthlv = packet / 4; /* align packet size with data registers access */ if (spi->cur_bpw > 8) @@ -488,6 +497,9 @@ static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi) else fthlv -= (fthlv % 4); /* multiple of 4 */ + if (!fthlv) + fthlv = 1; + return fthlv; } @@ -966,13 +978,13 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id) if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0))) stm32h7_spi_read_rxfifo(spi, false); - writel_relaxed(mask, spi->base + STM32H7_SPI_IFCR); + writel_relaxed(sr & mask, spi->base + STM32H7_SPI_IFCR); spin_unlock_irqrestore(&spi->lock, flags); if (end) { - spi_finalize_current_transfer(master); stm32h7_spi_disable(spi); + spi_finalize_current_transfer(master); } return IRQ_HANDLED; @@ -1393,7 +1405,7 @@ static void stm32h7_spi_set_bpw(struct stm32_spi *spi) cfg1_setb |= (bpw << STM32H7_SPI_CFG1_DSIZE_SHIFT) & STM32H7_SPI_CFG1_DSIZE; - spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi); + spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi, spi->cur_xferlen); fthlv = spi->cur_fthlv - 1; cfg1_clrb |= STM32H7_SPI_CFG1_FTHLV; @@ -1585,39 +1597,33 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi, unsigned long flags; unsigned int comm_type; int nb_words, ret = 0; + int mbr; spin_lock_irqsave(&spi->lock, flags); - if (spi->cur_bpw != transfer->bits_per_word) { - spi->cur_bpw = transfer->bits_per_word; - spi->cfg->set_bpw(spi); - } - - if (spi->cur_speed != transfer->speed_hz) { - int mbr; + spi->cur_xferlen = transfer->len; - /* Update spi->cur_speed with real clock speed */ - mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz, - spi->cfg->baud_rate_div_min, - spi->cfg->baud_rate_div_max); - if (mbr < 0) { - ret = mbr; - goto out; - } + spi->cur_bpw = transfer->bits_per_word; + spi->cfg->set_bpw(spi); - transfer->speed_hz = spi->cur_speed; - stm32_spi_set_mbr(spi, mbr); + /* Update spi->cur_speed with real clock speed */ + mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz, + spi->cfg->baud_rate_div_min, + spi->cfg->baud_rate_div_max); + if (mbr < 0) { + ret = mbr; + goto out; } + transfer->speed_hz = spi->cur_speed; + stm32_spi_set_mbr(spi, mbr); + comm_type = stm32_spi_communication_type(spi_dev, transfer); - if (spi->cur_comm != comm_type) { - ret = spi->cfg->set_mode(spi, comm_type); + ret = spi->cfg->set_mode(spi, comm_type); + if (ret < 0) + goto out; - if (ret < 0) - goto out; - - spi->cur_comm = comm_type; - } + spi->cur_comm = comm_type; if (spi->cfg->set_data_idleness) spi->cfg->set_data_idleness(spi, transfer->len); @@ -1635,8 +1641,6 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi, goto out; } - spi->cur_xferlen = transfer->len; - dev_dbg(spi->dev, "transfer communication mode set to %d\n", spi->cur_comm); dev_dbg(spi->dev, @@ -1996,6 +2000,8 @@ static int stm32_spi_remove(struct platform_device *pdev) pm_runtime_disable(&pdev->dev); + pinctrl_pm_select_sleep_state(&pdev->dev); + return 0; } @@ -2007,13 +2013,18 @@ static int stm32_spi_runtime_suspend(struct device *dev) clk_disable_unprepare(spi->clk); - return 0; + return pinctrl_pm_select_sleep_state(dev); } static int stm32_spi_runtime_resume(struct device *dev) { struct spi_master *master = dev_get_drvdata(dev); struct stm32_spi *spi = spi_master_get_devdata(master); + int ret; + + ret = pinctrl_pm_select_default_state(dev); + if (ret) + return ret; return clk_prepare_enable(spi->clk); } @@ -2043,10 +2054,23 @@ static int stm32_spi_resume(struct device *dev) return ret; ret = spi_master_resume(master); - if (ret) + if (ret) { clk_disable_unprepare(spi->clk); + return ret; + } - return ret; + ret = pm_runtime_get_sync(dev); + if (ret) { + dev_err(dev, "Unable to power device:%d\n", ret); + return ret; + } + + spi->cfg->config(spi); + + pm_runtime_mark_last_busy(dev); + pm_runtime_put_autosuspend(dev); + + return 0; } #endif diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 6626587e77b4..dc12af018350 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -475,6 +475,12 @@ static LIST_HEAD(spi_controller_list); */ static DEFINE_MUTEX(board_lock); +/* + * Prevents addition of devices with same chip select and + * addition of devices below an unregistering controller. + */ +static DEFINE_MUTEX(spi_add_lock); + /** * spi_alloc_device - Allocate a new SPI device * @ctlr: Controller to which device is connected @@ -554,7 +560,6 @@ static int spi_dev_check(struct device *dev, void *data) */ int spi_add_device(struct spi_device *spi) { - static DEFINE_MUTEX(spi_add_lock); struct spi_controller *ctlr = spi->controller; struct device *dev = ctlr->dev.parent; int status; @@ -582,6 +587,13 @@ int spi_add_device(struct spi_device *spi) goto done; } + /* Controller may unregister concurrently */ + if (IS_ENABLED(CONFIG_SPI_DYNAMIC) && + !device_is_registered(&ctlr->dev)) { + status = -ENODEV; + goto done; + } + /* Descriptors take precedence */ if (ctlr->cs_gpiods) spi->cs_gpiod = ctlr->cs_gpiods[spi->chip_select]; @@ -2795,6 +2807,10 @@ void spi_unregister_controller(struct spi_controller *ctlr) struct spi_controller *found; int id = ctlr->bus_num; + /* Prevent addition of new devices, unregister existing ones */ + if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) + mutex_lock(&spi_add_lock); + device_for_each_child(&ctlr->dev, NULL, __unregister); /* First make sure that this controller was ever added */ @@ -2815,6 +2831,9 @@ void spi_unregister_controller(struct spi_controller *ctlr) if (found == ctlr) idr_remove(&spi_master_idr, id); mutex_unlock(&board_lock); + + if (IS_ENABLED(CONFIG_SPI_DYNAMIC)) + mutex_unlock(&spi_add_lock); } EXPORT_SYMBOL_GPL(spi_unregister_controller); diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h index 86a02aff8735..61ca8ab165dc 100644 --- a/drivers/vfio/pci/vfio_pci_private.h +++ b/drivers/vfio/pci/vfio_pci_private.h @@ -33,12 +33,14 @@ struct vfio_pci_ioeventfd { struct list_head next; + struct vfio_pci_device *vdev; struct virqfd *virqfd; void __iomem *addr; uint64_t data; loff_t pos; int bar; int count; + bool test_mem; }; struct vfio_pci_irq_ctx { diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 916b184df3a5..9e353c484ace 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -37,17 +37,70 @@ #define vfio_ioread8 ioread8 #define vfio_iowrite8 iowrite8 +#define VFIO_IOWRITE(size) \ +static int vfio_pci_iowrite##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + vfio_iowrite##size(val, io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOWRITE(8) +VFIO_IOWRITE(16) +VFIO_IOWRITE(32) +#ifdef iowrite64 +VFIO_IOWRITE(64) +#endif + +#define VFIO_IOREAD(size) \ +static int vfio_pci_ioread##size(struct vfio_pci_device *vdev, \ + bool test_mem, u##size *val, void __iomem *io) \ +{ \ + if (test_mem) { \ + down_read(&vdev->memory_lock); \ + if (!__vfio_pci_memory_enabled(vdev)) { \ + up_read(&vdev->memory_lock); \ + return -EIO; \ + } \ + } \ + \ + *val = vfio_ioread##size(io); \ + \ + if (test_mem) \ + up_read(&vdev->memory_lock); \ + \ + return 0; \ +} + +VFIO_IOREAD(8) +VFIO_IOREAD(16) +VFIO_IOREAD(32) + /* * Read or write from an __iomem region (MMIO or I/O port) with an excluded * range which is inaccessible. The excluded range drops writes and fills * reads with -1. This is intended for handling MSI-X vector tables and * leftover space for ROM BARs. */ -static ssize_t do_io_rw(void __iomem *io, char __user *buf, +static ssize_t do_io_rw(struct vfio_pci_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, size_t x_end, bool iswrite) { ssize_t done = 0; + int ret; while (count) { size_t fillable, filled; @@ -66,9 +119,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 4)) return -EFAULT; - vfio_iowrite32(val, io + off); + ret = vfio_pci_iowrite32(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread32(io + off); + ret = vfio_pci_ioread32(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 4)) return -EFAULT; @@ -82,9 +141,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 2)) return -EFAULT; - vfio_iowrite16(val, io + off); + ret = vfio_pci_iowrite16(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread16(io + off); + ret = vfio_pci_ioread16(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 2)) return -EFAULT; @@ -98,9 +163,15 @@ static ssize_t do_io_rw(void __iomem *io, char __user *buf, if (copy_from_user(&val, buf, 1)) return -EFAULT; - vfio_iowrite8(val, io + off); + ret = vfio_pci_iowrite8(vdev, test_mem, + val, io + off); + if (ret) + return ret; } else { - val = vfio_ioread8(io + off); + ret = vfio_pci_ioread8(vdev, test_mem, + &val, io + off); + if (ret) + return ret; if (copy_to_user(buf, &val, 1)) return -EFAULT; @@ -178,14 +249,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, count = min(count, (size_t)(end - pos)); - if (res->flags & IORESOURCE_MEM) { - down_read(&vdev->memory_lock); - if (!__vfio_pci_memory_enabled(vdev)) { - up_read(&vdev->memory_lock); - return -EIO; - } - } - if (bar == PCI_ROM_RESOURCE) { /* * The ROM can fill less space than the BAR, so we start the @@ -213,7 +276,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, x_end = vdev->msix_offset + vdev->msix_size; } - done = do_io_rw(io, buf, pos, count, x_start, x_end, iswrite); + done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, + count, x_start, x_end, iswrite); if (done >= 0) *ppos += done; @@ -221,9 +285,6 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, if (bar == PCI_ROM_RESOURCE) pci_unmap_rom(pdev, io); out: - if (res->flags & IORESOURCE_MEM) - up_read(&vdev->memory_lock); - return done; } @@ -278,7 +339,12 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_device *vdev, char __user *buf, return ret; } - done = do_io_rw(iomem, buf, off, count, 0, 0, iswrite); + /* + * VGA MMIO is a legacy, non-BAR resource that hopefully allows + * probing, so we don't currently worry about access in relation + * to the memory enable bit in the command register. + */ + done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite); vga_put(vdev->pdev, rsrc); @@ -296,17 +362,21 @@ static int vfio_pci_ioeventfd_handler(void *opaque, void *unused) switch (ioeventfd->count) { case 1: - vfio_iowrite8(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite8(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 2: - vfio_iowrite16(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite16(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; case 4: - vfio_iowrite32(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite32(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #ifdef iowrite64 case 8: - vfio_iowrite64(ioeventfd->data, ioeventfd->addr); + vfio_pci_iowrite64(ioeventfd->vdev, ioeventfd->test_mem, + ioeventfd->data, ioeventfd->addr); break; #endif } @@ -378,11 +448,13 @@ long vfio_pci_ioeventfd(struct vfio_pci_device *vdev, loff_t offset, goto out_unlock; } + ioeventfd->vdev = vdev; ioeventfd->addr = vdev->barmap[bar] + pos; ioeventfd->data = data; ioeventfd->pos = pos; ioeventfd->bar = bar; ioeventfd->count = count; + ioeventfd->test_mem = vdev->pdev->resource[bar].flags & IORESOURCE_MEM; ret = vfio_virqfd_enable(ioeventfd, vfio_pci_ioeventfd_handler, NULL, NULL, &ioeventfd->virqfd, fd); diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 6990fc711a80..c992973cc2d5 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1424,13 +1424,16 @@ static int vfio_bus_type(struct device *dev, void *data) static int vfio_iommu_replay(struct vfio_iommu *iommu, struct vfio_domain *domain) { - struct vfio_domain *d; + struct vfio_domain *d = NULL; struct rb_node *n; unsigned long limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; int ret; /* Arbitrarily pick the first domain in the list for lookups */ - d = list_first_entry(&iommu->domain_list, struct vfio_domain, next); + if (!list_empty(&iommu->domain_list)) + d = list_first_entry(&iommu->domain_list, + struct vfio_domain, next); + n = rb_first(&iommu->dma_list); for (; n; n = rb_next(n)) { @@ -1448,6 +1451,11 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, phys_addr_t p; dma_addr_t i; + if (WARN_ON(!d)) { /* mapped w/o a domain?! */ + ret = -EINVAL; + goto unwind; + } + phys = iommu_iova_to_phys(d->domain, iova); if (WARN_ON(!phys)) { @@ -1477,7 +1485,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, if (npage <= 0) { WARN_ON(!npage); ret = (int)npage; - return ret; + goto unwind; } phys = pfn << PAGE_SHIFT; @@ -1486,14 +1494,67 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu, ret = iommu_map(domain->domain, iova, phys, size, dma->prot | domain->prot); - if (ret) - return ret; + if (ret) { + if (!dma->iommu_mapped) + vfio_unpin_pages_remote(dma, iova, + phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, + true); + goto unwind; + } iova += size; } + } + + /* All dmas are now mapped, defer to second tree walk for unwind */ + for (n = rb_first(&iommu->dma_list); n; n = rb_next(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma->iommu_mapped = true; } + return 0; + +unwind: + for (; n; n = rb_prev(n)) { + struct vfio_dma *dma = rb_entry(n, struct vfio_dma, node); + dma_addr_t iova; + + if (dma->iommu_mapped) { + iommu_unmap(domain->domain, dma->iova, dma->size); + continue; + } + + iova = dma->iova; + while (iova < dma->iova + dma->size) { + phys_addr_t phys, p; + size_t size; + dma_addr_t i; + + phys = iommu_iova_to_phys(domain->domain, iova); + if (!phys) { + iova += PAGE_SIZE; + continue; + } + + size = PAGE_SIZE; + p = phys + size; + i = iova + size; + while (i < dma->iova + dma->size && + p == iommu_iova_to_phys(domain->domain, i)) { + size += PAGE_SIZE; + p += PAGE_SIZE; + i += PAGE_SIZE; + } + + iommu_unmap(domain->domain, iova, size); + vfio_unpin_pages_remote(dma, iova, phys >> PAGE_SHIFT, + size >> PAGE_SHIFT, true); + } + } + + return ret; } /* diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 65491ae74808..e57c00824965 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -453,7 +453,7 @@ static int efifb_probe(struct platform_device *dev) info->apertures->ranges[0].base = efifb_fix.smem_start; info->apertures->ranges[0].size = size_remap; - if (efi_enabled(EFI_BOOT) && + if (efi_enabled(EFI_MEMMAP) && !efi_mem_desc_lookup(efifb_fix.smem_start, &md)) { if ((efifb_fix.smem_start + efifb_fix.smem_len) > (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) { diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c index b79879aacc02..7b784af604fd 100644 --- a/fs/afs/dynroot.c +++ b/fs/afs/dynroot.c @@ -382,15 +382,17 @@ void afs_dynroot_depopulate(struct super_block *sb) net->dynroot_sb = NULL; mutex_unlock(&net->proc_cells_lock); - inode_lock(root->d_inode); - - /* Remove all the pins for dirs created for manually added cells */ - list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { - if (subdir->d_fsdata) { - subdir->d_fsdata = NULL; - dput(subdir); + if (root) { + inode_lock(root->d_inode); + + /* Remove all the pins for dirs created for manually added cells */ + list_for_each_entry_safe(subdir, tmp, &root->d_subdirs, d_child) { + if (subdir->d_fsdata) { + subdir->d_fsdata = NULL; + dput(subdir); + } } - } - inode_unlock(root->d_inode); + inode_unlock(root->d_inode); + } } diff --git a/fs/afs/fs_operation.c b/fs/afs/fs_operation.c index 24fd163c6323..97cab12b0a6c 100644 --- a/fs/afs/fs_operation.c +++ b/fs/afs/fs_operation.c @@ -235,6 +235,7 @@ int afs_put_operation(struct afs_operation *op) afs_end_cursor(&op->ac); afs_put_serverlist(op->net, op->server_list); afs_put_volume(op->net, op->volume, afs_volume_trace_put_put_op); + key_put(op->key); kfree(op); return ret; } diff --git a/fs/buffer.c b/fs/buffer.c index 061dd202979d..d468ed9981e0 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3157,6 +3157,15 @@ int __sync_dirty_buffer(struct buffer_head *bh, int op_flags) WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { + /* + * The bh should be mapped, but it might not be if the + * device was hot-removed. Not much we can do but fail the I/O. + */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + get_bh(bh); bh->b_end_io = end_buffer_write_sync; ret = submit_bh(REQ_OP_WRITE, op_flags, bh); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 12eebcdea9c8..e0decff22ae2 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1994,9 +1994,11 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) * not already there, and calling reverse_path_check() * during ep_insert(). */ - if (list_empty(&epi->ffd.file->f_tfile_llink)) + if (list_empty(&epi->ffd.file->f_tfile_llink)) { + get_file(epi->ffd.file); list_add(&epi->ffd.file->f_tfile_llink, &tfile_check_list); + } } } mutex_unlock(&ep->mtx); @@ -2040,6 +2042,7 @@ static void clear_tfile_check_list(void) file = list_first_entry(&tfile_check_list, struct file, f_tfile_llink); list_del_init(&file->f_tfile_llink); + fput(file); } INIT_LIST_HEAD(&tfile_check_list); } @@ -2200,25 +2203,22 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, full_check = 1; if (is_file_epoll(tf.file)) { error = -ELOOP; - if (ep_loop_check(ep, tf.file) != 0) { - clear_tfile_check_list(); + if (ep_loop_check(ep, tf.file) != 0) goto error_tgt_fput; - } - } else + } else { + get_file(tf.file); list_add(&tf.file->f_tfile_llink, &tfile_check_list); + } error = epoll_mutex_lock(&ep->mtx, 0, nonblock); - if (error) { -out_del: - list_del(&tf.file->f_tfile_llink); + if (error) goto error_tgt_fput; - } if (is_file_epoll(tf.file)) { tep = tf.file->private_data; error = epoll_mutex_lock(&tep->mtx, 1, nonblock); if (error) { mutex_unlock(&ep->mtx); - goto out_del; + goto error_tgt_fput; } } } @@ -2239,8 +2239,6 @@ out_del: error = ep_insert(ep, epds, tf.file, fd, full_check); } else error = -EEXIST; - if (full_check) - clear_tfile_check_list(); break; case EPOLL_CTL_DEL: if (epi) @@ -2263,8 +2261,10 @@ out_del: mutex_unlock(&ep->mtx); error_tgt_fput: - if (full_check) + if (full_check) { + clear_tfile_check_list(); mutex_unlock(&epmutex); + } fdput(tf); error_fput: diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 1afa5a4bcb5f..619dd35ddd48 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -110,7 +110,7 @@ config EXT4_KUNIT_TESTS This builds the ext4 KUnit tests. KUnit tests run during boot and output the results to the debug log - in TAP format (http://testanything.org/). Only useful for kernel devs + in TAP format (https://testanything.org/). Only useful for kernel devs running KUnit test harness and are not for inclusion into a production build. diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index 1ba46d87cdf1..48c3df47748d 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -413,7 +413,8 @@ verified: * Return buffer_head on success or an ERR_PTR in case of failure. */ struct buffer_head * -ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) +ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group, + bool ignore_locked) { struct ext4_group_desc *desc; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -441,6 +442,12 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) return ERR_PTR(-ENOMEM); } + if (ignore_locked && buffer_locked(bh)) { + /* buffer under IO already, return if called for prefetching */ + put_bh(bh); + return NULL; + } + if (bitmap_uptodate(bh)) goto verify; @@ -487,10 +494,11 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) * submit the buffer_head for reading */ set_buffer_new(bh); - trace_ext4_read_block_bitmap_load(sb, block_group); + trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked); bh->b_end_io = ext4_end_bitmap_read; get_bh(bh); - submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh); + submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO | + (ignore_locked ? REQ_RAHEAD : 0), bh); return bh; verify: err = ext4_validate_block_bitmap(sb, desc, block_group, bh); @@ -534,7 +542,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group) struct buffer_head *bh; int err; - bh = ext4_read_block_bitmap_nowait(sb, block_group); + bh = ext4_read_block_bitmap_nowait(sb, block_group, false); if (IS_ERR(bh)) return bh; err = ext4_wait_block_bitmap(sb, block_group, bh); diff --git a/fs/ext4/block_validity.c b/fs/ext4/block_validity.c index 16e9b2fda03a..c54ba52f2dd4 100644 --- a/fs/ext4/block_validity.c +++ b/fs/ext4/block_validity.c @@ -24,6 +24,7 @@ struct ext4_system_zone { struct rb_node node; ext4_fsblk_t start_blk; unsigned int count; + u32 ino; }; static struct kmem_cache *ext4_system_zone_cachep; @@ -45,7 +46,8 @@ void ext4_exit_system_zone(void) static inline int can_merge(struct ext4_system_zone *entry1, struct ext4_system_zone *entry2) { - if ((entry1->start_blk + entry1->count) == entry2->start_blk) + if ((entry1->start_blk + entry1->count) == entry2->start_blk && + entry1->ino == entry2->ino) return 1; return 0; } @@ -66,9 +68,9 @@ static void release_system_zone(struct ext4_system_blocks *system_blks) */ static int add_system_zone(struct ext4_system_blocks *system_blks, ext4_fsblk_t start_blk, - unsigned int count) + unsigned int count, u32 ino) { - struct ext4_system_zone *new_entry = NULL, *entry; + struct ext4_system_zone *new_entry, *entry; struct rb_node **n = &system_blks->root.rb_node, *node; struct rb_node *parent = NULL, *new_node = NULL; @@ -79,30 +81,21 @@ static int add_system_zone(struct ext4_system_blocks *system_blks, n = &(*n)->rb_left; else if (start_blk >= (entry->start_blk + entry->count)) n = &(*n)->rb_right; - else { - if (start_blk + count > (entry->start_blk + - entry->count)) - entry->count = (start_blk + count - - entry->start_blk); - new_node = *n; - new_entry = rb_entry(new_node, struct ext4_system_zone, - node); - break; - } + else /* Unexpected overlap of system zones. */ + return -EFSCORRUPTED; } - if (!new_entry) { - new_entry = kmem_cache_alloc(ext4_system_zone_cachep, - GFP_KERNEL); - if (!new_entry) - return -ENOMEM; - new_entry->start_blk = start_blk; - new_entry->count = count; - new_node = &new_entry->node; - - rb_link_node(new_node, parent, n); - rb_insert_color(new_node, &system_blks->root); - } + new_entry = kmem_cache_alloc(ext4_system_zone_cachep, + GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + new_entry->start_blk = start_blk; + new_entry->count = count; + new_entry->ino = ino; + new_node = &new_entry->node; + + rb_link_node(new_node, parent, n); + rb_insert_color(new_node, &system_blks->root); /* Can we merge to the left? */ node = rb_prev(new_node); @@ -151,40 +144,6 @@ static void debug_print_tree(struct ext4_sb_info *sbi) printk(KERN_CONT "\n"); } -/* - * Returns 1 if the passed-in block region (start_blk, - * start_blk+count) is valid; 0 if some part of the block region - * overlaps with filesystem metadata blocks. - */ -static int ext4_data_block_valid_rcu(struct ext4_sb_info *sbi, - struct ext4_system_blocks *system_blks, - ext4_fsblk_t start_blk, - unsigned int count) -{ - struct ext4_system_zone *entry; - struct rb_node *n; - - if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || - (start_blk + count < start_blk) || - (start_blk + count > ext4_blocks_count(sbi->s_es))) - return 0; - - if (system_blks == NULL) - return 1; - - n = system_blks->root.rb_node; - while (n) { - entry = rb_entry(n, struct ext4_system_zone, node); - if (start_blk + count - 1 < entry->start_blk) - n = n->rb_left; - else if (start_blk >= (entry->start_blk + entry->count)) - n = n->rb_right; - else - return 0; - } - return 1; -} - static int ext4_protect_reserved_inode(struct super_block *sb, struct ext4_system_blocks *system_blks, u32 ino) @@ -214,19 +173,18 @@ static int ext4_protect_reserved_inode(struct super_block *sb, if (n == 0) { i++; } else { - if (!ext4_data_block_valid_rcu(sbi, system_blks, - map.m_pblk, n)) { - err = -EFSCORRUPTED; - __ext4_error(sb, __func__, __LINE__, -err, - map.m_pblk, "blocks %llu-%llu " - "from inode %u overlap system zone", - map.m_pblk, - map.m_pblk + map.m_len - 1, ino); + err = add_system_zone(system_blks, map.m_pblk, n, ino); + if (err < 0) { + if (err == -EFSCORRUPTED) { + __ext4_error(sb, __func__, __LINE__, + -err, map.m_pblk, + "blocks %llu-%llu from inode %u overlap system zone", + map.m_pblk, + map.m_pblk + map.m_len - 1, + ino); + } break; } - err = add_system_zone(system_blks, map.m_pblk, n); - if (err < 0) - break; i += n; } } @@ -262,14 +220,6 @@ int ext4_setup_system_zone(struct super_block *sb) int flex_size = ext4_flex_bg_size(sbi); int ret; - if (!test_opt(sb, BLOCK_VALIDITY)) { - if (sbi->system_blks) - ext4_release_system_zone(sb); - return 0; - } - if (sbi->system_blks) - return 0; - system_blks = kzalloc(sizeof(*system_blks), GFP_KERNEL); if (!system_blks) return -ENOMEM; @@ -277,22 +227,25 @@ int ext4_setup_system_zone(struct super_block *sb) for (i=0; i < ngroups; i++) { cond_resched(); if (ext4_bg_has_super(sb, i) && - ((i < 5) || ((i % flex_size) == 0))) - add_system_zone(system_blks, + ((i < 5) || ((i % flex_size) == 0))) { + ret = add_system_zone(system_blks, ext4_group_first_block_no(sb, i), - ext4_bg_num_gdb(sb, i) + 1); + ext4_bg_num_gdb(sb, i) + 1, 0); + if (ret) + goto err; + } gdp = ext4_get_group_desc(sb, i, NULL); ret = add_system_zone(system_blks, - ext4_block_bitmap(sb, gdp), 1); + ext4_block_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, - ext4_inode_bitmap(sb, gdp), 1); + ext4_inode_bitmap(sb, gdp), 1, 0); if (ret) goto err; ret = add_system_zone(system_blks, ext4_inode_table(sb, gdp), - sbi->s_itb_per_group); + sbi->s_itb_per_group, 0); if (ret) goto err; } @@ -341,11 +294,24 @@ void ext4_release_system_zone(struct super_block *sb) call_rcu(&system_blks->rcu, ext4_destroy_system_zone); } -int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, +/* + * Returns 1 if the passed-in block region (start_blk, + * start_blk+count) is valid; 0 if some part of the block region + * overlaps with some other filesystem metadata blocks. + */ +int ext4_inode_block_valid(struct inode *inode, ext4_fsblk_t start_blk, unsigned int count) { + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_system_blocks *system_blks; - int ret; + struct ext4_system_zone *entry; + struct rb_node *n; + int ret = 1; + + if ((start_blk <= le32_to_cpu(sbi->s_es->s_first_data_block)) || + (start_blk + count < start_blk) || + (start_blk + count > ext4_blocks_count(sbi->s_es))) + return 0; /* * Lock the system zone to prevent it being released concurrently @@ -354,8 +320,22 @@ int ext4_data_block_valid(struct ext4_sb_info *sbi, ext4_fsblk_t start_blk, */ rcu_read_lock(); system_blks = rcu_dereference(sbi->system_blks); - ret = ext4_data_block_valid_rcu(sbi, system_blks, start_blk, - count); + if (system_blks == NULL) + goto out_rcu; + + n = system_blks->root.rb_node; + while (n) { + entry = rb_entry(n, struct ext4_system_zone, node); + if (start_blk + count - 1 < entry->start_blk) + n = n->rb_left; + else if (start_blk >= (entry->start_blk + entry->count)) + n = n->rb_right; + else { + ret = (entry->ino == inode->i_ino); + break; + } + } +out_rcu: rcu_read_unlock(); return ret; } @@ -374,8 +354,7 @@ int ext4_check_blockref(const char *function, unsigned int line, while (bref < p+max) { blk = le32_to_cpu(*bref++); if (blk && - unlikely(!ext4_data_block_valid(EXT4_SB(inode->i_sb), - blk, 1))) { + unlikely(!ext4_inode_block_valid(inode, blk, 1))) { ext4_error_inode(inode, function, line, blk, "invalid block"); return -EFSCORRUPTED; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 42f5060f3cdf..523e00d7b392 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -434,10 +434,36 @@ struct flex_groups { #define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ -#define EXT4_FL_USER_VISIBLE 0x725BDFFF /* User visible flags */ -#define EXT4_FL_USER_MODIFIABLE 0x624BC0FF /* User modifiable flags */ - -/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ +/* User modifiable flags */ +#define EXT4_FL_USER_MODIFIABLE (EXT4_SECRM_FL | \ + EXT4_UNRM_FL | \ + EXT4_COMPR_FL | \ + EXT4_SYNC_FL | \ + EXT4_IMMUTABLE_FL | \ + EXT4_APPEND_FL | \ + EXT4_NODUMP_FL | \ + EXT4_NOATIME_FL | \ + EXT4_JOURNAL_DATA_FL | \ + EXT4_NOTAIL_FL | \ + EXT4_DIRSYNC_FL | \ + EXT4_TOPDIR_FL | \ + EXT4_EXTENTS_FL | \ + 0x00400000 /* EXT4_EOFBLOCKS_FL */ | \ + EXT4_DAX_FL | \ + EXT4_PROJINHERIT_FL | \ + EXT4_CASEFOLD_FL) + +/* User visible flags */ +#define EXT4_FL_USER_VISIBLE (EXT4_FL_USER_MODIFIABLE | \ + EXT4_DIRTY_FL | \ + EXT4_COMPRBLK_FL | \ + EXT4_NOCOMPR_FL | \ + EXT4_ENCRYPT_FL | \ + EXT4_INDEX_FL | \ + EXT4_VERITY_FL | \ + EXT4_INLINE_DATA_FL) + +/* Flags we can manipulate with through FS_IOC_FSSETXATTR */ #define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \ EXT4_IMMUTABLE_FL | \ EXT4_APPEND_FL | \ @@ -669,8 +695,6 @@ enum { /* * ioctl commands */ -#define EXT4_IOC_GETFLAGS FS_IOC_GETFLAGS -#define EXT4_IOC_SETFLAGS FS_IOC_SETFLAGS #define EXT4_IOC_GETVERSION _IOR('f', 3, long) #define EXT4_IOC_SETVERSION _IOW('f', 4, long) #define EXT4_IOC_GETVERSION_OLD FS_IOC_GETVERSION @@ -687,17 +711,11 @@ enum { #define EXT4_IOC_RESIZE_FS _IOW('f', 16, __u64) #define EXT4_IOC_SWAP_BOOT _IO('f', 17) #define EXT4_IOC_PRECACHE_EXTENTS _IO('f', 18) -#define EXT4_IOC_SET_ENCRYPTION_POLICY FS_IOC_SET_ENCRYPTION_POLICY -#define EXT4_IOC_GET_ENCRYPTION_PWSALT FS_IOC_GET_ENCRYPTION_PWSALT -#define EXT4_IOC_GET_ENCRYPTION_POLICY FS_IOC_GET_ENCRYPTION_POLICY /* ioctl codes 19--39 are reserved for fscrypt */ #define EXT4_IOC_CLEAR_ES_CACHE _IO('f', 40) #define EXT4_IOC_GETSTATE _IOW('f', 41, __u32) #define EXT4_IOC_GET_ES_CACHE _IOWR('f', 42, struct fiemap) -#define EXT4_IOC_FSGETXATTR FS_IOC_FSGETXATTR -#define EXT4_IOC_FSSETXATTR FS_IOC_FSSETXATTR - #define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32) /* @@ -722,8 +740,6 @@ enum { /* * ioctl commands in 32 bit emulation */ -#define EXT4_IOC32_GETFLAGS FS_IOC32_GETFLAGS -#define EXT4_IOC32_SETFLAGS FS_IOC32_SETFLAGS #define EXT4_IOC32_GETVERSION _IOR('f', 3, int) #define EXT4_IOC32_SETVERSION _IOW('f', 4, int) #define EXT4_IOC32_GETRSVSZ _IOR('f', 5, int) @@ -1054,6 +1070,7 @@ struct ext4_inode_info { struct timespec64 i_crtime; /* mballoc */ + atomic_t i_prealloc_active; struct list_head i_prealloc_list; spinlock_t i_prealloc_lock; @@ -1172,6 +1189,7 @@ struct ext4_inode_info { #define EXT4_MOUNT_JOURNAL_CHECKSUM 0x800000 /* Journal checksums */ #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT 0x1000000 /* Journal Async Commit */ #define EXT4_MOUNT_WARN_ON_ERROR 0x2000000 /* Trigger WARN_ON on error */ +#define EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS 0x4000000 #define EXT4_MOUNT_DELALLOC 0x8000000 /* Delalloc support */ #define EXT4_MOUNT_DATA_ERR_ABORT 0x10000000 /* Abort on file data write */ #define EXT4_MOUNT_BLOCK_VALIDITY 0x20000000 /* Block validity checking */ @@ -1501,10 +1519,13 @@ struct ext4_sb_info { unsigned int s_mb_stats; unsigned int s_mb_order2_reqs; unsigned int s_mb_group_prealloc; + unsigned int s_mb_max_inode_prealloc; unsigned int s_max_dir_size_kb; /* where last allocation was done - for stream allocation */ unsigned long s_mb_last_group; unsigned long s_mb_last_start; + unsigned int s_mb_prefetch; + unsigned int s_mb_prefetch_limit; /* stats for buddy allocator */ atomic_t s_bal_reqs; /* number of reqs with len > 1 */ @@ -1572,6 +1593,8 @@ struct ext4_sb_info { struct ratelimit_state s_err_ratelimit_state; struct ratelimit_state s_warning_ratelimit_state; struct ratelimit_state s_msg_ratelimit_state; + atomic_t s_warning_count; + atomic_t s_msg_count; /* Encryption context for '-o test_dummy_encryption' */ struct fscrypt_dummy_context s_dummy_enc_ctx; @@ -1585,6 +1608,9 @@ struct ext4_sb_info { #ifdef CONFIG_EXT4_DEBUG unsigned long s_simulate_fail; #endif + /* Record the errseq of the backing block device */ + errseq_t s_bdev_wb_err; + spinlock_t s_bdev_wb_lock; }; static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb) @@ -2313,9 +2339,15 @@ struct ext4_lazy_init { struct mutex li_list_mtx; }; +enum ext4_li_mode { + EXT4_LI_MODE_PREFETCH_BBITMAP, + EXT4_LI_MODE_ITABLE, +}; + struct ext4_li_request { struct super_block *lr_super; - struct ext4_sb_info *lr_sbi; + enum ext4_li_mode lr_mode; + ext4_group_t lr_first_not_zeroed; ext4_group_t lr_next_group; struct list_head lr_request; unsigned long lr_next_sched; @@ -2446,7 +2478,8 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb, extern int ext4_should_retry_alloc(struct super_block *sb, int *retries); extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb, - ext4_group_t block_group); + ext4_group_t block_group, + bool ignore_locked); extern int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group, struct buffer_head *bh); @@ -2651,9 +2684,15 @@ extern int ext4_mb_release(struct super_block *); extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *, struct ext4_allocation_request *, int *); extern int ext4_mb_reserve_blocks(struct super_block *, int); -extern void ext4_discard_preallocations(struct inode *); +extern void ext4_discard_preallocations(struct inode *, unsigned int); extern int __init ext4_init_mballoc(void); extern void ext4_exit_mballoc(void); +extern ext4_group_t ext4_mb_prefetch(struct super_block *sb, + ext4_group_t group, + unsigned int nr, int *cnt); +extern void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, + unsigned int nr); + extern void ext4_free_blocks(handle_t *handle, struct inode *inode, struct buffer_head *bh, ext4_fsblk_t block, unsigned long count, int flags); @@ -2765,8 +2804,7 @@ extern int ext4_search_dir(struct buffer_head *bh, struct ext4_filename *fname, unsigned int offset, struct ext4_dir_entry_2 **res_dir); -extern int ext4_generic_delete_entry(handle_t *handle, - struct inode *dir, +extern int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, @@ -2924,12 +2962,6 @@ do { \ #endif -extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb, - __u32 compat); -extern int ext4_update_rocompat_feature(handle_t *handle, - struct super_block *sb, __u32 rocompat); -extern int ext4_update_incompat_feature(handle_t *handle, - struct super_block *sb, __u32 incompat); extern ext4_fsblk_t ext4_block_bitmap(struct super_block *sb, struct ext4_group_desc *bg); extern ext4_fsblk_t ext4_inode_bitmap(struct super_block *sb, @@ -3145,6 +3177,7 @@ struct ext4_group_info { (1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT) #define EXT4_GROUP_INFO_IBITMAP_CORRUPT \ (1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT) +#define EXT4_GROUP_INFO_BBITMAP_READ_BIT 4 #define EXT4_MB_GRP_NEED_INIT(grp) \ (test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state))) @@ -3159,6 +3192,8 @@ struct ext4_group_info { (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) #define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \ (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state))) +#define EXT4_MB_GRP_TEST_AND_SET_READ(grp) \ + (test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state))) #define EXT4_MAX_CONTENTION 8 #define EXT4_CONTENTION_THRESHOLD 2 @@ -3363,9 +3398,9 @@ extern void ext4_release_system_zone(struct super_block *sb); extern int ext4_setup_system_zone(struct super_block *sb); extern int __init ext4_init_system_zone(void); extern void ext4_exit_system_zone(void); -extern int ext4_data_block_valid(struct ext4_sb_info *sbi, - ext4_fsblk_t start_blk, - unsigned int count); +extern int ext4_inode_block_valid(struct inode *inode, + ext4_fsblk_t start_blk, + unsigned int count); extern int ext4_check_blockref(const char *, unsigned int, struct inode *, __le32 *, unsigned int); diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 0c76cdd44d90..760b9ee49dc0 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -195,6 +195,28 @@ static void ext4_journal_abort_handle(const char *caller, unsigned int line, jbd2_journal_abort_handle(handle); } +static void ext4_check_bdev_write_error(struct super_block *sb) +{ + struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; + struct ext4_sb_info *sbi = EXT4_SB(sb); + int err; + + /* + * If the block device has write error flag, it may have failed to + * async write out metadata buffers in the background. In this case, + * we could read old data from disk and write it out again, which + * may lead to on-disk filesystem inconsistency. + */ + if (errseq_check(&mapping->wb_err, READ_ONCE(sbi->s_bdev_wb_err))) { + spin_lock(&sbi->s_bdev_wb_lock); + err = errseq_check_and_advance(&mapping->wb_err, &sbi->s_bdev_wb_err); + spin_unlock(&sbi->s_bdev_wb_lock); + if (err) + ext4_error_err(sb, -err, + "Error while async write back metadata"); + } +} + int __ext4_journal_get_write_access(const char *where, unsigned int line, handle_t *handle, struct buffer_head *bh) { @@ -202,6 +224,9 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line, might_sleep(); + if (bh->b_bdev->bd_super) + ext4_check_bdev_write_error(bh->b_bdev->bd_super); + if (ext4_handle_valid(handle)) { err = jbd2_journal_get_write_access(handle, bh); if (err) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 221f240eae60..a0481582187a 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; @@ -340,7 +340,7 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) */ if (lblock + len <= lblock) return 0; - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); + return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, @@ -348,7 +348,7 @@ static int ext4_valid_extent_idx(struct inode *inode, { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); - return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, 1); + return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, @@ -507,14 +507,10 @@ __read_extent_tree_block(const char *function, unsigned int line, } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; - if (!ext4_has_feature_journal(inode->i_sb) || - (inode->i_ino != - le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) { - err = __ext4_ext_check(function, line, inode, - ext_block_hdr(bh), depth, pblk); - if (err) - goto errout; - } + err = __ext4_ext_check(function, line, inode, + ext_block_hdr(bh), depth, pblk); + if (err) + goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries @@ -693,10 +689,8 @@ void ext4_ext_drop_refs(struct ext4_ext_path *path) return; depth = path->p_depth; for (i = 0; i <= depth; i++, path++) { - if (path->p_bh) { - brelse(path->p_bh); - path->p_bh = NULL; - } + brelse(path->p_bh); + path->p_bh = NULL; } } @@ -1915,7 +1909,7 @@ out: /* * ext4_ext_insert_extent: - * tries to merge requsted extent into the existing extent or + * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ @@ -3125,7 +3119,7 @@ static int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states - * of which are deterimined by split_flag. + * of which are determined by split_flag. * * There are two cases: * a> the extent are splitted into two extent. @@ -3650,7 +3644,7 @@ static int ext4_split_convert_extents(handle_t *handle, eof_block = map->m_lblk + map->m_len; /* * It is safe to convert extent to initialized via explicit - * zeroout only if extent is fully insde i_size or new_size. + * zeroout only if extent is fully inside i_size or new_size. */ depth = ext_depth(inode); ex = path[depth].p_ext; @@ -4272,7 +4266,7 @@ got_allocated_blocks: * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, @@ -4495,7 +4489,7 @@ static long ext4_zero_range(struct file *file, loff_t offset, } /* - * Round up offset. This is not fallocate, we neet to zero out + * Round up offset. This is not fallocate, we need to zero out * blocks, so convert interior block aligned part of the range to * unwritten and possibly manually zero out unaligned parts of the * range. @@ -5299,7 +5293,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) } down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start); @@ -5313,7 +5307,7 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) up_write(&EXT4_I(inode)->i_data_sem); goto out_stop; } - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_ext_shift_extents(inode, handle, punch_stop, punch_stop - punch_start, SHIFT_LEFT); @@ -5445,7 +5439,7 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) goto out_stop; down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); path = ext4_find_extent(inode, offset_lblk, NULL, 0); if (IS_ERR(path)) { @@ -5579,7 +5573,7 @@ ext4_swap_extents(handle_t *handle, struct inode *inode1, } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; - /* Do we have somthing to swap ? */ + /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) goto finish; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 129cc1dd6b79..7d61069531d3 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -145,10 +145,9 @@ static int ext4_release_file(struct inode *inode, struct file *filp) /* if we are the last writer on the inode, drop the block reservation */ if ((filp->f_mode & FMODE_WRITE) && (atomic_read(&inode->i_writecount) == 1) && - !EXT4_I(inode)->i_reserved_data_blocks) - { + !EXT4_I(inode)->i_reserved_data_blocks) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); } if (is_dx(inode) && filp->private_data) @@ -428,6 +427,10 @@ restart: */ if (*ilock_shared && (!IS_NOSEC(inode) || *extend || !ext4_overwrite_io(inode, offset, count))) { + if (iocb->ki_flags & IOCB_NOWAIT) { + ret = -EAGAIN; + goto out; + } inode_unlock_shared(inode); *ilock_shared = false; inode_lock(inode); @@ -812,7 +815,7 @@ out: return err; } -static int ext4_file_open(struct inode * inode, struct file * filp) +static int ext4_file_open(struct inode *inode, struct file *filp) { int ret; diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c index 3e133793a5a3..2924261226e0 100644 --- a/fs/ext4/hash.c +++ b/fs/ext4/hash.c @@ -233,7 +233,7 @@ static int __ext4fs_dirhash(const char *name, int len, break; case DX_HASH_HALF_MD4_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; - /* fall through */ + fallthrough; case DX_HASH_HALF_MD4: p = name; while (len > 0) { @@ -247,7 +247,7 @@ static int __ext4fs_dirhash(const char *name, int len, break; case DX_HASH_TEA_UNSIGNED: str2hashbuf = str2hashbuf_unsigned; - /* fall through */ + fallthrough; case DX_HASH_TEA: p = name; while (len > 0) { diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index be2b66eb65f7..80c9f33800be 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -696,7 +696,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode, * i_mutex. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; @@ -858,8 +858,7 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode, else if (ext4_should_journal_data(inode)) flags |= EXT4_FREE_BLOCKS_FORGET; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), block_to_free, - count)) { + if (!ext4_inode_block_valid(inode, block_to_free, count)) { EXT4_ERROR_INODE(inode, "attempt to clear invalid " "blocks %llu len %lu", (unsigned long long) block_to_free, count); @@ -1004,8 +1003,7 @@ static void ext4_free_branches(handle_t *handle, struct inode *inode, if (!nr) continue; /* A hole */ - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), - nr, 1)) { + if (!ext4_inode_block_valid(inode, nr, 1)) { EXT4_ERROR_INODE(inode, "invalid indirect mapped " "block %lu (level %d)", @@ -1182,21 +1180,21 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_IND_BLOCK: nr = i_data[EXT4_DIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_DIND_BLOCK: nr = i_data[EXT4_TIND_BLOCK]; if (nr) { ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_TIND_BLOCK: ; } @@ -1436,7 +1434,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 1); i_data[EXT4_IND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_IND_BLOCK: if (++n >= n2) break; @@ -1445,7 +1443,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 2); i_data[EXT4_DIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_DIND_BLOCK: if (++n >= n2) break; @@ -1454,7 +1452,7 @@ do_indirects: ext4_free_branches(handle, inode, NULL, &nr, &nr+1, 3); i_data[EXT4_TIND_BLOCK] = 0; } - /* fall through */ + fallthrough; case EXT4_TIND_BLOCK: ; } diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index c3a1ad2db122..75c97bca0815 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -276,7 +276,7 @@ static int ext4_create_inline_data(handle_t *handle, len = 0; } - /* Insert the the xttr entry. */ + /* Insert the xttr entry. */ i.value = value; i.value_len = len; @@ -1706,7 +1706,7 @@ int ext4_delete_inline_entry(handle_t *handle, if (err) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, bh, + err = ext4_generic_delete_entry(dir, de_del, bh, inline_start, inline_size, 0); if (err) goto out; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 44bad4bb8831..3a196d81f594 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -383,7 +383,7 @@ void ext4_da_update_reserve_space(struct inode *inode, */ if ((ei->i_reserved_data_blocks == 0) && !inode_is_open_for_write(inode)) - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); } static int __check_block_validity(struct inode *inode, const char *func, @@ -394,8 +394,7 @@ static int __check_block_validity(struct inode *inode, const char *func, (inode->i_ino == le32_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_journal_inum))) return 0; - if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk, - map->m_len)) { + if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, @@ -3288,7 +3287,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait) if (PageChecked(page)) return 0; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page, wait); + return jbd2_journal_try_to_free_buffers(journal, page); else return try_to_free_buffers(page); } @@ -4056,7 +4055,7 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) if (stop_block > first_block) { down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ret = ext4_es_remove_extent(inode, first_block, stop_block - first_block); @@ -4163,7 +4162,7 @@ int ext4_truncate(struct inode *inode) trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) - return 0; + goto out_trace; if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); @@ -4172,16 +4171,14 @@ int ext4_truncate(struct inode *inode) int has_inline = 1; err = ext4_inline_data_truncate(inode, &has_inline); - if (err) - return err; - if (has_inline) - return 0; + if (err || has_inline) + goto out_trace; } /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { if (ext4_inode_attach_jinode(inode) < 0) - return 0; + goto out_trace; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) @@ -4190,8 +4187,10 @@ int ext4_truncate(struct inode *inode) credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); - if (IS_ERR(handle)) - return PTR_ERR(handle); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + goto out_trace; + } if (inode->i_size & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, mapping, inode->i_size); @@ -4211,7 +4210,7 @@ int ext4_truncate(struct inode *inode) down_write(&EXT4_I(inode)->i_data_sem); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) err = ext4_ext_truncate(handle, inode); @@ -4242,6 +4241,7 @@ out_stop: err = err2; ext4_journal_stop(handle); +out_trace: trace_ext4_truncate_exit(inode); return err; } @@ -4760,7 +4760,7 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ret = 0; if (ei->i_file_acl && - !ext4_data_block_valid(EXT4_SB(sb), ei->i_file_acl, 1)) { + !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) { ext4_error_inode(inode, function, line, 0, "iget: bad extended attribute block %llu", ei->i_file_acl); diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 999cf6add39c..36eca3bc036a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -202,7 +202,7 @@ static long swap_inode_boot_loader(struct super_block *sb, reset_inode_seed(inode); reset_inode_seed(inode_bl); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { @@ -819,12 +819,12 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) switch (cmd) { case FS_IOC_GETFSMAP: return ext4_ioc_getfsmap(sb, (void __user *)arg); - case EXT4_IOC_GETFLAGS: + case FS_IOC_GETFLAGS: flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (S_ISREG(inode->i_mode)) flags &= ~EXT4_PROJINHERIT_FL; return put_user(flags, (int __user *) arg); - case EXT4_IOC_SETFLAGS: { + case FS_IOC_SETFLAGS: { int err; if (!inode_owner_or_capable(inode)) @@ -1129,12 +1129,12 @@ resizefs_out: case EXT4_IOC_PRECACHE_EXTENTS: return ext4_ext_precache(inode); - case EXT4_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); - case EXT4_IOC_GET_ENCRYPTION_PWSALT: { + case FS_IOC_GET_ENCRYPTION_PWSALT: { #ifdef CONFIG_FS_ENCRYPTION int err, err2; struct ext4_sb_info *sbi = EXT4_SB(sb); @@ -1174,7 +1174,7 @@ resizefs_out: return -EOPNOTSUPP; #endif } - case EXT4_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); @@ -1236,7 +1236,7 @@ resizefs_out: case EXT4_IOC_GET_ES_CACHE: return ext4_ioctl_get_es_cache(filp, arg); - case EXT4_IOC_FSGETXATTR: + case FS_IOC_FSGETXATTR: { struct fsxattr fa; @@ -1247,7 +1247,7 @@ resizefs_out: return -EFAULT; return 0; } - case EXT4_IOC_FSSETXATTR: + case FS_IOC_FSSETXATTR: { struct fsxattr fa, old_fa; int err; @@ -1313,11 +1313,11 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { - case EXT4_IOC32_GETFLAGS: - cmd = EXT4_IOC_GETFLAGS; + case FS_IOC32_GETFLAGS: + cmd = FS_IOC_GETFLAGS; break; - case EXT4_IOC32_SETFLAGS: - cmd = EXT4_IOC_SETFLAGS; + case FS_IOC32_SETFLAGS: + cmd = FS_IOC_SETFLAGS; break; case EXT4_IOC32_GETVERSION: cmd = EXT4_IOC_GETVERSION; @@ -1361,9 +1361,9 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_RESIZE_FS: case FITRIM: case EXT4_IOC_PRECACHE_EXTENTS: - case EXT4_IOC_SET_ENCRYPTION_POLICY: - case EXT4_IOC_GET_ENCRYPTION_PWSALT: - case EXT4_IOC_GET_ENCRYPTION_POLICY: + case FS_IOC_SET_ENCRYPTION_POLICY: + case FS_IOC_GET_ENCRYPTION_PWSALT: + case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: @@ -1377,8 +1377,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: - case EXT4_IOC_FSGETXATTR: - case EXT4_IOC_FSSETXATTR: + case FS_IOC_FSGETXATTR: + case FS_IOC_FSSETXATTR: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index c0a331e2feb0..132c118d12e1 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -922,7 +922,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp) bh[i] = NULL; continue; } - bh[i] = ext4_read_block_bitmap_nowait(sb, group); + bh[i] = ext4_read_block_bitmap_nowait(sb, group, false); if (IS_ERR(bh[i])) { err = PTR_ERR(bh[i]); bh[i] = NULL; @@ -1279,9 +1279,6 @@ ext4_mb_load_buddy_gfp(struct super_block *sb, ext4_group_t group, e4b->bd_buddy_page = page; e4b->bd_buddy = page_address(page) + (poff * sb->s_blocksize); - BUG_ON(e4b->bd_bitmap_page == NULL); - BUG_ON(e4b->bd_buddy_page == NULL); - return 0; err: @@ -1743,10 +1740,6 @@ static void ext4_mb_use_best_found(struct ext4_allocation_context *ac, } -/* - * regular allocator, for general purposes allocation - */ - static void ext4_mb_check_limits(struct ext4_allocation_context *ac, struct ext4_buddy *e4b, int finish_group) @@ -2119,13 +2112,11 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, BUG_ON(cr < 0 || cr >= 4); - free = grp->bb_free; - if (free == 0) - return false; - if (cr <= 2 && free < ac->ac_g_ex.fe_len) + if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) return false; - if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(grp))) + free = grp->bb_free; + if (free == 0) return false; fragments = grp->bb_fragments; @@ -2142,8 +2133,10 @@ static bool ext4_mb_good_group(struct ext4_allocation_context *ac, ((group % flex_size) == 0)) return false; - if ((ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) || - (free / fragments) >= ac->ac_g_ex.fe_len) + if (free < ac->ac_g_ex.fe_len) + return false; + + if (ac->ac_2order > ac->ac_sb->s_blocksize_bits+1) return true; if (grp->bb_largest_free_order < ac->ac_2order) @@ -2177,6 +2170,7 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, { struct ext4_group_info *grp = ext4_get_group_info(ac->ac_sb, group); struct super_block *sb = ac->ac_sb; + struct ext4_sb_info *sbi = EXT4_SB(sb); bool should_lock = ac->ac_flags & EXT4_MB_STRICT_CHECK; ext4_grpblk_t free; int ret = 0; @@ -2195,7 +2189,25 @@ static int ext4_mb_good_group_nolock(struct ext4_allocation_context *ac, /* We only do this if the grp has never been initialized */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grp))) { - ret = ext4_mb_init_group(ac->ac_sb, group, GFP_NOFS); + struct ext4_group_desc *gdp = + ext4_get_group_desc(sb, group, NULL); + int ret; + + /* cr=0/1 is a very optimistic search to find large + * good chunks almost for free. If buddy data is not + * ready, then this optimization makes no sense. But + * we never skip the first block group in a flex_bg, + * since this gets used for metadata block allocation, + * and we want to make sure we locate metadata blocks + * in the first block group in the flex_bg if possible. + */ + if (cr < 2 && + (!sbi->s_log_groups_per_flex || + ((group & ((1 << sbi->s_log_groups_per_flex) - 1)) != 0)) && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) + return 0; + ret = ext4_mb_init_group(sb, group, GFP_NOFS); if (ret) return ret; } @@ -2209,15 +2221,95 @@ out: return ret; } +/* + * Start prefetching @nr block bitmaps starting at @group. + * Return the next group which needs to be prefetched. + */ +ext4_group_t ext4_mb_prefetch(struct super_block *sb, ext4_group_t group, + unsigned int nr, int *cnt) +{ + ext4_group_t ngroups = ext4_get_groups_count(sb); + struct buffer_head *bh; + struct blk_plug plug; + + blk_start_plug(&plug); + while (nr-- > 0) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, + NULL); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + + /* + * Prefetch block groups with free blocks; but don't + * bother if it is marked uninitialized on disk, since + * it won't require I/O to read. Also only try to + * prefetch once, so we avoid getblk() call, which can + * be expensive. + */ + if (!EXT4_MB_GRP_TEST_AND_SET_READ(grp) && + EXT4_MB_GRP_NEED_INIT(grp) && + ext4_free_group_clusters(sb, gdp) > 0 && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { + bh = ext4_read_block_bitmap_nowait(sb, group, true); + if (bh && !IS_ERR(bh)) { + if (!buffer_uptodate(bh) && cnt) + (*cnt)++; + brelse(bh); + } + } + if (++group >= ngroups) + group = 0; + } + blk_finish_plug(&plug); + return group; +} + +/* + * Prefetching reads the block bitmap into the buffer cache; but we + * need to make sure that the buddy bitmap in the page cache has been + * initialized. Note that ext4_mb_init_group() will block if the I/O + * is not yet completed, or indeed if it was not initiated by + * ext4_mb_prefetch did not start the I/O. + * + * TODO: We should actually kick off the buddy bitmap setup in a work + * queue when the buffer I/O is completed, so that we don't block + * waiting for the block allocation bitmap read to finish when + * ext4_mb_prefetch_fini is called from ext4_mb_regular_allocator(). + */ +void ext4_mb_prefetch_fini(struct super_block *sb, ext4_group_t group, + unsigned int nr) +{ + while (nr-- > 0) { + struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, + NULL); + struct ext4_group_info *grp = ext4_get_group_info(sb, group); + + if (!group) + group = ext4_get_groups_count(sb); + group--; + grp = ext4_get_group_info(sb, group); + + if (EXT4_MB_GRP_NEED_INIT(grp) && + ext4_free_group_clusters(sb, gdp) > 0 && + !(ext4_has_group_desc_csum(sb) && + (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)))) { + if (ext4_mb_init_group(sb, group, GFP_NOFS)) + break; + } + } +} + static noinline_for_stack int ext4_mb_regular_allocator(struct ext4_allocation_context *ac) { - ext4_group_t ngroups, group, i; + ext4_group_t prefetch_grp = 0, ngroups, group, i; int cr = -1; int err = 0, first_err = 0; + unsigned int nr = 0, prefetch_ios = 0; struct ext4_sb_info *sbi; struct super_block *sb; struct ext4_buddy e4b; + int lost; sb = ac->ac_sb; sbi = EXT4_SB(sb); @@ -2237,8 +2329,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac) goto out; /* - * ac->ac2_order is set only if the fe_len is a power of 2 - * if ac2_order is set we also set criteria to 0 so that we + * ac->ac_2order is set only if the fe_len is a power of 2 + * if ac->ac_2order is set we also set criteria to 0 so that we * try exact allocation using buddy. */ i = fls(ac->ac_g_ex.fe_len); @@ -2282,6 +2374,7 @@ repeat: * from the goal value specified */ group = ac->ac_g_ex.fe_group; + prefetch_grp = group; for (i = 0; i < ngroups; group++, i++) { int ret = 0; @@ -2293,6 +2386,29 @@ repeat: if (group >= ngroups) group = 0; + /* + * Batch reads of the block allocation bitmaps + * to get multiple READs in flight; limit + * prefetching at cr=0/1, otherwise mballoc can + * spend a lot of time loading imperfect groups + */ + if ((prefetch_grp == group) && + (cr > 1 || + prefetch_ios < sbi->s_mb_prefetch_limit)) { + unsigned int curr_ios = prefetch_ios; + + nr = sbi->s_mb_prefetch; + if (ext4_has_feature_flex_bg(sb)) { + nr = (group / sbi->s_mb_prefetch) * + sbi->s_mb_prefetch; + nr = nr + sbi->s_mb_prefetch - group; + } + prefetch_grp = ext4_mb_prefetch(sb, group, + nr, &prefetch_ios); + if (prefetch_ios == curr_ios) + nr = 0; + } + /* This now checks without needing the buddy page */ ret = ext4_mb_good_group_nolock(ac, group, cr); if (ret <= 0) { @@ -2341,22 +2457,24 @@ repeat: * We've been searching too long. Let's try to allocate * the best chunk we've found so far */ - ext4_mb_try_best_found(ac, &e4b); if (ac->ac_status != AC_STATUS_FOUND) { /* * Someone more lucky has already allocated it. * The only thing we can do is just take first * found block(s) - printk(KERN_DEBUG "EXT4-fs: someone won our chunk\n"); */ + lost = atomic_inc_return(&sbi->s_mb_lost_chunks); + mb_debug(sb, "lost chunk, group: %u, start: %d, len: %d, lost: %d\n", + ac->ac_b_ex.fe_group, ac->ac_b_ex.fe_start, + ac->ac_b_ex.fe_len, lost); + ac->ac_b_ex.fe_group = 0; ac->ac_b_ex.fe_start = 0; ac->ac_b_ex.fe_len = 0; ac->ac_status = AC_STATUS_CONTINUE; ac->ac_flags |= EXT4_MB_HINT_FIRST; cr = 3; - atomic_inc(&sbi->s_mb_lost_chunks); goto repeat; } } @@ -2367,6 +2485,10 @@ out: mb_debug(sb, "Best len %d, origin len %d, ac_status %u, ac_flags 0x%x, cr %d ret %d\n", ac->ac_b_ex.fe_len, ac->ac_o_ex.fe_len, ac->ac_status, ac->ac_flags, cr, err); + + if (nr) + ext4_mb_prefetch_fini(sb, prefetch_grp, nr); + return err; } @@ -2439,7 +2561,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) for (i = 0; i <= 13; i++) seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ? sg.info.bb_counters[i] : 0); - seq_printf(seq, " ]\n"); + seq_puts(seq, " ]\n"); return 0; } @@ -2613,6 +2735,26 @@ static int ext4_mb_init_backend(struct super_block *sb) goto err_freebuddy; } + if (ext4_has_feature_flex_bg(sb)) { + /* a single flex group is supposed to be read by a single IO */ + sbi->s_mb_prefetch = 1 << sbi->s_es->s_log_groups_per_flex; + sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ + } else { + sbi->s_mb_prefetch = 32; + } + if (sbi->s_mb_prefetch > ext4_get_groups_count(sb)) + sbi->s_mb_prefetch = ext4_get_groups_count(sb); + /* now many real IOs to prefetch within a single allocation at cr=0 + * given cr=0 is an CPU-related optimization we shouldn't try to + * load too many groups, at some point we should start to use what + * we've got in memory. + * with an average random access time 5ms, it'd take a second to get + * 200 groups (* N with flex_bg), so let's make this limit 4 + */ + sbi->s_mb_prefetch_limit = sbi->s_mb_prefetch * 4; + if (sbi->s_mb_prefetch_limit > ext4_get_groups_count(sb)) + sbi->s_mb_prefetch_limit = ext4_get_groups_count(sb); + return 0; err_freebuddy: @@ -2736,6 +2878,7 @@ int ext4_mb_init(struct super_block *sb) sbi->s_mb_stats = MB_DEFAULT_STATS; sbi->s_mb_stream_request = MB_DEFAULT_STREAM_THRESHOLD; sbi->s_mb_order2_reqs = MB_DEFAULT_ORDER2_REQS; + sbi->s_mb_max_inode_prealloc = MB_DEFAULT_MAX_INODE_PREALLOC; /* * The default group preallocation is 512, which for 4k block * sizes translates to 2 megabytes. However for bigalloc file @@ -3090,7 +3233,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac, block = ext4_grp_offs_to_block(sb, &ac->ac_b_ex); len = EXT4_C2B(sbi, ac->ac_b_ex.fe_len); - if (!ext4_data_block_valid(sbi, block, len)) { + if (!ext4_inode_block_valid(ac->ac_inode, block, len)) { ext4_error(sb, "Allocating blocks %llu-%llu which overlap " "fs metadata", block, block+len); /* File system mounted not to panic on error @@ -3674,6 +3817,26 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap, mb_debug(sb, "preallocated %d for group %u\n", preallocated, group); } +static void ext4_mb_mark_pa_deleted(struct super_block *sb, + struct ext4_prealloc_space *pa) +{ + struct ext4_inode_info *ei; + + if (pa->pa_deleted) { + ext4_warning(sb, "deleted pa, type:%d, pblk:%llu, lblk:%u, len:%d\n", + pa->pa_type, pa->pa_pstart, pa->pa_lstart, + pa->pa_len); + return; + } + + pa->pa_deleted = 1; + + if (pa->pa_type == MB_INODE_PA) { + ei = EXT4_I(pa->pa_inode); + atomic_dec(&ei->i_prealloc_active); + } +} + static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; @@ -3706,7 +3869,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, return; } - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); grp_blk = pa->pa_pstart; @@ -3830,6 +3993,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac) spin_lock(pa->pa_obj_lock); list_add_rcu(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); + atomic_inc(&ei->i_prealloc_active); } /* @@ -4040,7 +4204,7 @@ repeat: } /* seems this one can be freed ... */ - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); /* we can trust pa_free ... */ free += pa->pa_free; @@ -4103,7 +4267,7 @@ out_dbg: * * FIXME!! Make sure it is valid at all the call sites */ -void ext4_discard_preallocations(struct inode *inode) +void ext4_discard_preallocations(struct inode *inode, unsigned int needed) { struct ext4_inode_info *ei = EXT4_I(inode); struct super_block *sb = inode->i_sb; @@ -4121,15 +4285,19 @@ void ext4_discard_preallocations(struct inode *inode) mb_debug(sb, "discard preallocation for inode %lu\n", inode->i_ino); - trace_ext4_discard_preallocations(inode); + trace_ext4_discard_preallocations(inode, + atomic_read(&ei->i_prealloc_active), needed); INIT_LIST_HEAD(&list); + if (needed == 0) + needed = UINT_MAX; + repeat: /* first, collect all pa's in the inode */ spin_lock(&ei->i_prealloc_lock); - while (!list_empty(&ei->i_prealloc_list)) { - pa = list_entry(ei->i_prealloc_list.next, + while (!list_empty(&ei->i_prealloc_list) && needed) { + pa = list_entry(ei->i_prealloc_list.prev, struct ext4_prealloc_space, pa_inode_list); BUG_ON(pa->pa_obj_lock != &ei->i_prealloc_lock); spin_lock(&pa->pa_lock); @@ -4146,10 +4314,11 @@ repeat: } if (pa->pa_deleted == 0) { - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); list_add(&pa->u.pa_tmp_list, &list); + needed--; continue; } @@ -4399,7 +4568,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ac->ac_g_ex = ac->ac_o_ex; ac->ac_flags = ar->flags; - /* we have to define context: we'll we work with a file or + /* we have to define context: we'll work with a file or * locality group. this is a policy, actually */ ext4_mb_group_or_file(ac); @@ -4450,7 +4619,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb, BUG_ON(pa->pa_type != MB_GROUP_PA); /* seems this one can be freed ... */ - pa->pa_deleted = 1; + ext4_mb_mark_pa_deleted(sb, pa); spin_unlock(&pa->pa_lock); list_del_rcu(&pa->pa_inode_list); @@ -4549,10 +4718,29 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac) } /* + * if per-inode prealloc list is too long, trim some PA + */ +static void ext4_mb_trim_inode_pa(struct inode *inode) +{ + struct ext4_inode_info *ei = EXT4_I(inode); + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); + int count, delta; + + count = atomic_read(&ei->i_prealloc_active); + delta = (sbi->s_mb_max_inode_prealloc >> 2) + 1; + if (count > sbi->s_mb_max_inode_prealloc + delta) { + count -= sbi->s_mb_max_inode_prealloc; + ext4_discard_preallocations(inode, count); + } +} + +/* * release all resource we used in allocation */ static int ext4_mb_release_context(struct ext4_allocation_context *ac) { + struct inode *inode = ac->ac_inode; + struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb); struct ext4_prealloc_space *pa = ac->ac_pa; if (pa) { @@ -4564,21 +4752,31 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) pa->pa_free -= ac->ac_b_ex.fe_len; pa->pa_len -= ac->ac_b_ex.fe_len; spin_unlock(&pa->pa_lock); + + /* + * We want to add the pa to the right bucket. + * Remove it from the list and while adding + * make sure the list to which we are adding + * doesn't grow big. + */ + if (likely(pa->pa_free)) { + spin_lock(pa->pa_obj_lock); + list_del_rcu(&pa->pa_inode_list); + spin_unlock(pa->pa_obj_lock); + ext4_mb_add_n_trim(ac); + } } - } - if (pa) { - /* - * We want to add the pa to the right bucket. - * Remove it from the list and while adding - * make sure the list to which we are adding - * doesn't grow big. - */ - if ((pa->pa_type == MB_GROUP_PA) && likely(pa->pa_free)) { + + if (pa->pa_type == MB_INODE_PA) { + /* + * treat per-inode prealloc list as a lru list, then try + * to trim the least recently used PA. + */ spin_lock(pa->pa_obj_lock); - list_del_rcu(&pa->pa_inode_list); + list_move(&pa->pa_inode_list, &ei->i_prealloc_list); spin_unlock(pa->pa_obj_lock); - ext4_mb_add_n_trim(ac); } + ext4_mb_put_pa(ac, ac->ac_sb, pa); } if (ac->ac_bitmap_page) @@ -4588,6 +4786,7 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac) if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC) mutex_unlock(&ac->ac_lg->lg_mutex); ext4_mb_collect_stats(ac); + ext4_mb_trim_inode_pa(inode); return 0; } @@ -4915,7 +5114,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, sbi = EXT4_SB(sb); if (!(flags & EXT4_FREE_BLOCKS_VALIDATED) && - !ext4_data_block_valid(sbi, block, count)) { + !ext4_inode_block_valid(inode, block, count)) { ext4_error(sb, "Freeing blocks not in datazone - " "block = %llu, count = %lu", block, count); goto error_return; diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h index 6b4d17c2935d..e75b4749aa1c 100644 --- a/fs/ext4/mballoc.h +++ b/fs/ext4/mballoc.h @@ -73,6 +73,10 @@ */ #define MB_DEFAULT_GROUP_PREALLOC 512 +/* + * maximum length of inode prealloc list + */ +#define MB_DEFAULT_MAX_INODE_PREALLOC 512 struct ext4_free_data { /* this links the free block information from sb_info */ diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 1ed86fb6c302..0d601b822875 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -686,8 +686,8 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk, out: if (*moved_len) { - ext4_discard_preallocations(orig_inode); - ext4_discard_preallocations(donor_inode); + ext4_discard_preallocations(orig_inode, 0); + ext4_discard_preallocations(donor_inode, 0); } ext4_ext_drop_refs(path); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 56738b538ddf..153a9fbe1dd0 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1396,8 +1396,8 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ - if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data, - bh->b_size, offset)) + if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf, + buf_size, offset)) return -1; *res_dir = de; return 1; @@ -1858,7 +1858,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, blocksize, hinfo, map); map -= count; dx_sort_map(map, count); - /* Split the existing block in the middle, size-wise */ + /* Ensure that neither split block is over half full */ size = 0; move = 0; for (i = count-1; i >= 0; i--) { @@ -1868,8 +1868,18 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, size += map[i].size; move++; } - /* map index at which we will split */ - split = count - move; + /* + * map index at which we will split + * + * If the sum of active entries didn't exceed half the block size, just + * split it in half by count; each resulting block will have at least + * half the space free. + */ + if (i > 0) + split = count - move; + else + split = count/2; + hash2 = map[split].hash; continued = hash2 == map[split - 1].hash; dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n", @@ -2455,8 +2465,7 @@ cleanup: * ext4_generic_delete_entry deletes a directory entry by merging it * with the previous entry */ -int ext4_generic_delete_entry(handle_t *handle, - struct inode *dir, +int ext4_generic_delete_entry(struct inode *dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh, void *entry_buf, @@ -2472,7 +2481,7 @@ int ext4_generic_delete_entry(handle_t *handle, de = (struct ext4_dir_entry_2 *)entry_buf; while (i < buf_size - csum_size) { if (ext4_check_dir_entry(dir, NULL, de, bh, - bh->b_data, bh->b_size, i)) + entry_buf, buf_size, i)) return -EFSCORRUPTED; if (de == de_del) { if (pde) @@ -2517,8 +2526,7 @@ static int ext4_delete_entry(handle_t *handle, if (unlikely(err)) goto out; - err = ext4_generic_delete_entry(handle, dir, de_del, - bh, bh->b_data, + err = ext4_generic_delete_entry(dir, de_del, bh, bh->b_data, dir->i_sb->s_blocksize, csum_size); if (err) goto out; @@ -3193,30 +3201,33 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) * in separate transaction */ retval = dquot_initialize(dir); if (retval) - return retval; + goto out_trace; retval = dquot_initialize(d_inode(dentry)); if (retval) - return retval; + goto out_trace; - retval = -ENOENT; bh = ext4_find_entry(dir, &dentry->d_name, &de, NULL); - if (IS_ERR(bh)) - return PTR_ERR(bh); - if (!bh) - goto end_unlink; + if (IS_ERR(bh)) { + retval = PTR_ERR(bh); + goto out_trace; + } + if (!bh) { + retval = -ENOENT; + goto out_trace; + } inode = d_inode(dentry); - retval = -EFSCORRUPTED; - if (le32_to_cpu(de->inode) != inode->i_ino) - goto end_unlink; + if (le32_to_cpu(de->inode) != inode->i_ino) { + retval = -EFSCORRUPTED; + goto out_bh; + } handle = ext4_journal_start(dir, EXT4_HT_DIR, EXT4_DATA_TRANS_BLOCKS(dir->i_sb)); if (IS_ERR(handle)) { retval = PTR_ERR(handle); - handle = NULL; - goto end_unlink; + goto out_bh; } if (IS_DIRSYNC(dir)) @@ -3224,12 +3235,12 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) retval = ext4_delete_entry(handle, dir, de, bh); if (retval) - goto end_unlink; + goto out_handle; dir->i_ctime = dir->i_mtime = current_time(dir); ext4_update_dx_flag(dir); retval = ext4_mark_inode_dirty(handle, dir); if (retval) - goto end_unlink; + goto out_handle; if (inode->i_nlink == 0) ext4_warning_inode(inode, "Deleting file '%.*s' with no links", dentry->d_name.len, dentry->d_name.name); @@ -3251,10 +3262,11 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry) d_invalidate(dentry); #endif -end_unlink: +out_handle: + ext4_journal_stop(handle); +out_bh: brelse(bh); - if (handle) - ext4_journal_stop(handle); +out_trace: trace_ext4_unlink_exit(dentry, retval); return retval; } diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c index f2df2db0786c..f014c5e473a9 100644 --- a/fs/ext4/readpage.c +++ b/fs/ext4/readpage.c @@ -140,7 +140,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx) return; } ctx->cur_step++; - /* fall-through */ + fallthrough; case STEP_VERITY: if (ctx->enabled_steps & (1 << STEP_VERITY)) { INIT_WORK(&ctx->work, verity_work); @@ -148,7 +148,7 @@ static void bio_post_read_processing(struct bio_post_read_ctx *ctx) return; } ctx->cur_step++; - /* fall-through */ + fallthrough; default: __read_end_io(ctx->bio); } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 0907f907c47d..ea425b49b345 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -66,10 +66,10 @@ static int ext4_load_journal(struct super_block *, struct ext4_super_block *, unsigned long journal_devnum); static int ext4_show_options(struct seq_file *seq, struct dentry *root); static int ext4_commit_super(struct super_block *sb, int sync); -static void ext4_mark_recovery_complete(struct super_block *sb, +static int ext4_mark_recovery_complete(struct super_block *sb, struct ext4_super_block *es); -static void ext4_clear_journal_err(struct super_block *sb, - struct ext4_super_block *es); +static int ext4_clear_journal_err(struct super_block *sb, + struct ext4_super_block *es); static int ext4_sync_fs(struct super_block *sb, int wait); static int ext4_remount(struct super_block *sb, int *flags, char *data); static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf); @@ -744,6 +744,7 @@ void __ext4_msg(struct super_block *sb, struct va_format vaf; va_list args; + atomic_inc(&EXT4_SB(sb)->s_msg_count); if (!___ratelimit(&(EXT4_SB(sb)->s_msg_ratelimit_state), "EXT4-fs")) return; @@ -754,9 +755,12 @@ void __ext4_msg(struct super_block *sb, va_end(args); } -#define ext4_warning_ratelimit(sb) \ - ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), \ - "EXT4-fs warning") +static int ext4_warning_ratelimit(struct super_block *sb) +{ + atomic_inc(&EXT4_SB(sb)->s_warning_count); + return ___ratelimit(&(EXT4_SB(sb)->s_warning_ratelimit_state), + "EXT4-fs warning"); +} void __ext4_warning(struct super_block *sb, const char *function, unsigned int line, const char *fmt, ...) @@ -1123,6 +1127,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) inode_set_iversion(&ei->vfs_inode, 1); spin_lock_init(&ei->i_raw_lock); INIT_LIST_HEAD(&ei->i_prealloc_list); + atomic_set(&ei->i_prealloc_active, 0); spin_lock_init(&ei->i_prealloc_lock); ext4_es_init_tree(&ei->i_es_tree); rwlock_init(&ei->i_es_lock); @@ -1216,7 +1221,7 @@ void ext4_clear_inode(struct inode *inode) { invalidate_inode_buffers(inode); clear_inode(inode); - ext4_discard_preallocations(inode); + ext4_discard_preallocations(inode, 0); ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS); dquot_drop(inode); if (EXT4_I(inode)->jinode) { @@ -1288,8 +1293,8 @@ static int bdev_try_to_free_page(struct super_block *sb, struct page *page, if (!page_has_buffers(page)) return 0; if (journal) - return jbd2_journal_try_to_free_buffers(journal, page, - wait & ~__GFP_DIRECT_RECLAIM); + return jbd2_journal_try_to_free_buffers(journal, page); + return try_to_free_buffers(page); } @@ -1522,6 +1527,7 @@ enum { Opt_dioread_nolock, Opt_dioread_lock, Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable, Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache, + Opt_prefetch_block_bitmaps, }; static const match_table_t tokens = { @@ -1614,6 +1620,7 @@ static const match_table_t tokens = { {Opt_inlinecrypt, "inlinecrypt"}, {Opt_nombcache, "nombcache"}, {Opt_nombcache, "no_mbcache"}, /* for backward compatibility */ + {Opt_prefetch_block_bitmaps, "prefetch_block_bitmaps"}, {Opt_removed, "check=none"}, /* mount option from ext2/3 */ {Opt_removed, "nocheck"}, /* mount option from ext2/3 */ {Opt_removed, "reservation"}, /* mount option from ext2/3 */ @@ -1831,6 +1838,8 @@ static const struct mount_opts { {Opt_max_dir_size_kb, 0, MOPT_GTE0}, {Opt_test_dummy_encryption, 0, MOPT_STRING}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, + {Opt_prefetch_block_bitmaps, EXT4_MOUNT_PREFETCH_BLOCK_BITMAPS, + MOPT_SET}, {Opt_err, 0, 0} }; @@ -3213,15 +3222,34 @@ static void print_daily_error_info(struct timer_list *t) static int ext4_run_li_request(struct ext4_li_request *elr) { struct ext4_group_desc *gdp = NULL; - ext4_group_t group, ngroups; - struct super_block *sb; + struct super_block *sb = elr->lr_super; + ext4_group_t ngroups = EXT4_SB(sb)->s_groups_count; + ext4_group_t group = elr->lr_next_group; unsigned long timeout = 0; + unsigned int prefetch_ios = 0; int ret = 0; - sb = elr->lr_super; - ngroups = EXT4_SB(sb)->s_groups_count; + if (elr->lr_mode == EXT4_LI_MODE_PREFETCH_BBITMAP) { + elr->lr_next_group = ext4_mb_prefetch(sb, group, + EXT4_SB(sb)->s_mb_prefetch, &prefetch_ios); + if (prefetch_ios) + ext4_mb_prefetch_fini(sb, elr->lr_next_group, + prefetch_ios); + trace_ext4_prefetch_bitmaps(sb, group, elr->lr_next_group, + prefetch_ios); + if (group >= elr->lr_next_group) { + ret = 1; + if (elr->lr_first_not_zeroed != ngroups && + !sb_rdonly(sb) && test_opt(sb, INIT_INODE_TABLE)) { + elr->lr_next_group = elr->lr_first_not_zeroed; + elr->lr_mode = EXT4_LI_MODE_ITABLE; + ret = 0; + } + } + return ret; + } - for (group = elr->lr_next_group; group < ngroups; group++) { + for (; group < ngroups; group++) { gdp = ext4_get_group_desc(sb, group, NULL); if (!gdp) { ret = 1; @@ -3239,9 +3267,10 @@ static int ext4_run_li_request(struct ext4_li_request *elr) timeout = jiffies; ret = ext4_init_inode_table(sb, group, elr->lr_timeout ? 0 : 1); + trace_ext4_lazy_itable_init(sb, group); if (elr->lr_timeout == 0) { timeout = (jiffies - timeout) * - elr->lr_sbi->s_li_wait_mult; + EXT4_SB(elr->lr_super)->s_li_wait_mult; elr->lr_timeout = timeout; } elr->lr_next_sched = jiffies + elr->lr_timeout; @@ -3256,15 +3285,11 @@ static int ext4_run_li_request(struct ext4_li_request *elr) */ static void ext4_remove_li_request(struct ext4_li_request *elr) { - struct ext4_sb_info *sbi; - if (!elr) return; - sbi = elr->lr_sbi; - list_del(&elr->lr_request); - sbi->s_li_request = NULL; + EXT4_SB(elr->lr_super)->s_li_request = NULL; kfree(elr); } @@ -3473,7 +3498,6 @@ static int ext4_li_info_new(void) static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, ext4_group_t start) { - struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_li_request *elr; elr = kzalloc(sizeof(*elr), GFP_KERNEL); @@ -3481,8 +3505,13 @@ static struct ext4_li_request *ext4_li_request_new(struct super_block *sb, return NULL; elr->lr_super = sb; - elr->lr_sbi = sbi; - elr->lr_next_group = start; + elr->lr_first_not_zeroed = start; + if (test_opt(sb, PREFETCH_BLOCK_BITMAPS)) + elr->lr_mode = EXT4_LI_MODE_PREFETCH_BBITMAP; + else { + elr->lr_mode = EXT4_LI_MODE_ITABLE; + elr->lr_next_group = start; + } /* * Randomize first schedule time of the request to @@ -3512,8 +3541,9 @@ int ext4_register_li_request(struct super_block *sb, goto out; } - if (first_not_zeroed == ngroups || sb_rdonly(sb) || - !test_opt(sb, INIT_INODE_TABLE)) + if (!test_opt(sb, PREFETCH_BLOCK_BITMAPS) && + (first_not_zeroed == ngroups || sb_rdonly(sb) || + !test_opt(sb, INIT_INODE_TABLE))) goto out; elr = ext4_li_request_new(sb, first_not_zeroed); @@ -4710,11 +4740,13 @@ no_journal: ext4_set_resv_clusters(sb); - err = ext4_setup_system_zone(sb); - if (err) { - ext4_msg(sb, KERN_ERR, "failed to initialize system " - "zone (%d)", err); - goto failed_mount4a; + if (test_opt(sb, BLOCK_VALIDITY)) { + err = ext4_setup_system_zone(sb); + if (err) { + ext4_msg(sb, KERN_ERR, "failed to initialize system " + "zone (%d)", err); + goto failed_mount4a; + } } ext4_ext_init(sb); @@ -4777,12 +4809,23 @@ no_journal: } #endif /* CONFIG_QUOTA */ + /* + * Save the original bdev mapping's wb_err value which could be + * used to detect the metadata async write error. + */ + spin_lock_init(&sbi->s_bdev_wb_lock); + if (!sb_rdonly(sb)) + errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + &sbi->s_bdev_wb_err); + sb->s_bdev->bd_super = sb; EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS; ext4_orphan_cleanup(sb, es); EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS; if (needs_recovery) { ext4_msg(sb, KERN_INFO, "recovery complete"); - ext4_mark_recovery_complete(sb, es); + err = ext4_mark_recovery_complete(sb, es); + if (err) + goto failed_mount8; } if (EXT4_SB(sb)->s_journal) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) @@ -4816,6 +4859,8 @@ no_journal: ratelimit_state_init(&sbi->s_err_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_warning_ratelimit_state, 5 * HZ, 10); ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10); + atomic_set(&sbi->s_warning_count, 0); + atomic_set(&sbi->s_msg_count, 0); kfree(orig_data); return 0; @@ -4825,10 +4870,8 @@ cantfind_ext4: ext4_msg(sb, KERN_ERR, "VFS: Can't find ext4 filesystem"); goto failed_mount; -#ifdef CONFIG_QUOTA failed_mount8: ext4_unregister_sysfs(sb); -#endif failed_mount7: ext4_unregister_li_request(sb); failed_mount6: @@ -4968,7 +5011,8 @@ static journal_t *ext4_get_journal(struct super_block *sb, struct inode *journal_inode; journal_t *journal; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; journal_inode = ext4_get_journal_inode(sb, journal_inum); if (!journal_inode) @@ -4998,7 +5042,8 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb, struct ext4_super_block *es; struct block_device *bdev; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return NULL; bdev = ext4_blkdev_get(j_dev, sb); if (bdev == NULL) @@ -5089,8 +5134,10 @@ static int ext4_load_journal(struct super_block *sb, dev_t journal_dev; int err = 0; int really_read_only; + int journal_dev_ro; - BUG_ON(!ext4_has_feature_journal(sb)); + if (WARN_ON_ONCE(!ext4_has_feature_journal(sb))) + return -EFSCORRUPTED; if (journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -5100,7 +5147,31 @@ static int ext4_load_journal(struct super_block *sb, } else journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev)); - really_read_only = bdev_read_only(sb->s_bdev); + if (journal_inum && journal_dev) { + ext4_msg(sb, KERN_ERR, + "filesystem has both journal inode and journal device!"); + return -EINVAL; + } + + if (journal_inum) { + journal = ext4_get_journal(sb, journal_inum); + if (!journal) + return -EINVAL; + } else { + journal = ext4_get_dev_journal(sb, journal_dev); + if (!journal) + return -EINVAL; + } + + journal_dev_ro = bdev_read_only(journal->j_dev); + really_read_only = bdev_read_only(sb->s_bdev) | journal_dev_ro; + + if (journal_dev_ro && !sb_rdonly(sb)) { + ext4_msg(sb, KERN_ERR, + "journal device read-only, try mounting with '-o ro'"); + err = -EROFS; + goto err_out; + } /* * Are we loading a blank journal or performing recovery after a @@ -5115,27 +5186,14 @@ static int ext4_load_journal(struct super_block *sb, ext4_msg(sb, KERN_ERR, "write access " "unavailable, cannot proceed " "(try mounting with noload)"); - return -EROFS; + err = -EROFS; + goto err_out; } ext4_msg(sb, KERN_INFO, "write access will " "be enabled during recovery"); } } - if (journal_inum && journal_dev) { - ext4_msg(sb, KERN_ERR, "filesystem has both journal " - "and inode journals!"); - return -EINVAL; - } - - if (journal_inum) { - if (!(journal = ext4_get_journal(sb, journal_inum))) - return -EINVAL; - } else { - if (!(journal = ext4_get_dev_journal(sb, journal_dev))) - return -EINVAL; - } - if (!(journal->j_flags & JBD2_BARRIER)) ext4_msg(sb, KERN_INFO, "barriers disabled"); @@ -5155,12 +5213,16 @@ static int ext4_load_journal(struct super_block *sb, if (err) { ext4_msg(sb, KERN_ERR, "error loading journal"); - jbd2_journal_destroy(journal); - return err; + goto err_out; } EXT4_SB(sb)->s_journal = journal; - ext4_clear_journal_err(sb, es); + err = ext4_clear_journal_err(sb, es); + if (err) { + EXT4_SB(sb)->s_journal = NULL; + jbd2_journal_destroy(journal); + return err; + } if (!really_read_only && journal_devnum && journal_devnum != le32_to_cpu(es->s_journal_dev)) { @@ -5171,6 +5233,10 @@ static int ext4_load_journal(struct super_block *sb, } return 0; + +err_out: + jbd2_journal_destroy(journal); + return err; } static int ext4_commit_super(struct super_block *sb, int sync) @@ -5183,13 +5249,6 @@ static int ext4_commit_super(struct super_block *sb, int sync) return error; /* - * The superblock bh should be mapped, but it might not be if the - * device was hot-removed. Not much we can do but fail the I/O. - */ - if (!buffer_mapped(sbh)) - return error; - - /* * If the file system is mounted read-only, don't update the * superblock write time. This avoids updating the superblock * write time when we are mounting the root file system @@ -5256,26 +5315,32 @@ static int ext4_commit_super(struct super_block *sb, int sync) * remounting) the filesystem readonly, then we will end up with a * consistent fs on disk. Record that fact. */ -static void ext4_mark_recovery_complete(struct super_block *sb, - struct ext4_super_block *es) +static int ext4_mark_recovery_complete(struct super_block *sb, + struct ext4_super_block *es) { + int err; journal_t *journal = EXT4_SB(sb)->s_journal; if (!ext4_has_feature_journal(sb)) { - BUG_ON(journal != NULL); - return; + if (journal != NULL) { + ext4_error(sb, "Journal got removed while the fs was " + "mounted!"); + return -EFSCORRUPTED; + } + return 0; } jbd2_journal_lock_updates(journal); - if (jbd2_journal_flush(journal) < 0) + err = jbd2_journal_flush(journal); + if (err < 0) goto out; if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) { ext4_clear_feature_journal_needs_recovery(sb); ext4_commit_super(sb, 1); } - out: jbd2_journal_unlock_updates(journal); + return err; } /* @@ -5283,14 +5348,17 @@ out: * has recorded an error from a previous lifetime, move that error to the * main filesystem now. */ -static void ext4_clear_journal_err(struct super_block *sb, +static int ext4_clear_journal_err(struct super_block *sb, struct ext4_super_block *es) { journal_t *journal; int j_errno; const char *errstr; - BUG_ON(!ext4_has_feature_journal(sb)); + if (!ext4_has_feature_journal(sb)) { + ext4_error(sb, "Journal got removed while the fs was mounted!"); + return -EFSCORRUPTED; + } journal = EXT4_SB(sb)->s_journal; @@ -5315,6 +5383,7 @@ static void ext4_clear_journal_err(struct super_block *sb, jbd2_journal_clear_err(journal); jbd2_journal_update_sb_errno(journal); } + return 0; } /* @@ -5457,7 +5526,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) { struct ext4_super_block *es; struct ext4_sb_info *sbi = EXT4_SB(sb); - unsigned long old_sb_flags; + unsigned long old_sb_flags, vfs_flags; struct ext4_mount_options old_opts; int enable_quota = 0; ext4_group_t g; @@ -5500,6 +5569,14 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) if (sbi->s_journal && sbi->s_journal->j_task->io_context) journal_ioprio = sbi->s_journal->j_task->io_context->ioprio; + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from *flags to s_flags + */ + vfs_flags = SB_LAZYTIME | SB_I_VERSION; + sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; goto restore_opts; @@ -5553,9 +5630,6 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) set_task_ioprio(sbi->s_journal->j_task, journal_ioprio); } - if (*flags & SB_LAZYTIME) - sb->s_flags |= SB_LAZYTIME; - if ((bool)(*flags & SB_RDONLY) != sb_rdonly(sb)) { if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED) { err = -EROFS; @@ -5585,8 +5659,13 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) (sbi->s_mount_state & EXT4_VALID_FS)) es->s_state = cpu_to_le16(sbi->s_mount_state); - if (sbi->s_journal) + if (sbi->s_journal) { + /* + * We let remount-ro finish even if marking fs + * as clean failed... + */ ext4_mark_recovery_complete(sb, es); + } if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); } else { @@ -5629,13 +5708,24 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } /* + * Update the original bdev mapping's wb_err value + * which could be used to detect the metadata async + * write error. + */ + errseq_check_and_advance(&sb->s_bdev->bd_inode->i_mapping->wb_err, + &sbi->s_bdev_wb_err); + + /* * Mounting a RDONLY partition read-write, so reread * and store the current valid flag. (It may have * been changed by e2fsck since we originally mounted * the partition.) */ - if (sbi->s_journal) - ext4_clear_journal_err(sb, es); + if (sbi->s_journal) { + err = ext4_clear_journal_err(sb, es); + if (err) + goto restore_opts; + } sbi->s_mount_state = le16_to_cpu(es->s_state); err = ext4_setup_super(sb, es, 0); @@ -5665,7 +5755,17 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) ext4_register_li_request(sb, first_not_zeroed); } - ext4_setup_system_zone(sb); + /* + * Handle creation of system zone data early because it can fail. + * Releasing of existing data is done when we are sure remount will + * succeed. + */ + if (test_opt(sb, BLOCK_VALIDITY) && !sbi->system_blks) { + err = ext4_setup_system_zone(sb); + if (err) + goto restore_opts; + } + if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) { err = ext4_commit_super(sb, 1); if (err) @@ -5686,8 +5786,16 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) } } #endif + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); + + /* + * Some options can be enabled by ext4 and/or by VFS mount flag + * either way we need to make sure it matches in both *flags and + * s_flags. Copy those selected flags from s_flags to *flags + */ + *flags = (*flags & ~vfs_flags) | (sb->s_flags & vfs_flags); - *flags = (*flags & ~SB_LAZYTIME) | (sb->s_flags & SB_LAZYTIME); ext4_msg(sb, KERN_INFO, "re-mounted. Opts: %s", orig_data); kfree(orig_data); return 0; @@ -5701,6 +5809,8 @@ restore_opts: sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) + ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA sbi->s_jquota_fmt = old_opts.s_jquota_fmt; for (i = 0; i < EXT4_MAXQUOTAS; i++) { diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 6c9fc9e21c13..bfabb799fa45 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -189,6 +189,9 @@ static struct ext4_attr ext4_attr_##_name = { \ #define EXT4_RW_ATTR_SBI_UL(_name,_elname) \ EXT4_ATTR_OFFSET(_name, 0644, pointer_ul, ext4_sb_info, _elname) +#define EXT4_RO_ATTR_SBI_ATOMIC(_name,_elname) \ + EXT4_ATTR_OFFSET(_name, 0444, pointer_atomic, ext4_sb_info, _elname) + #define EXT4_ATTR_PTR(_name,_mode,_id,_ptr) \ static struct ext4_attr ext4_attr_##_name = { \ .attr = {.name = __stringify(_name), .mode = _mode }, \ @@ -215,6 +218,7 @@ EXT4_RW_ATTR_SBI_UI(mb_min_to_scan, s_mb_min_to_scan); EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs); EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request); EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc); +EXT4_RW_ATTR_SBI_UI(mb_max_inode_prealloc, s_mb_max_inode_prealloc); EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb); EXT4_ATTR(trigger_fs_error, 0200, trigger_test_error); EXT4_RW_ATTR_SBI_UI(err_ratelimit_interval_ms, s_err_ratelimit_state.interval); @@ -226,6 +230,8 @@ EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst); #ifdef CONFIG_EXT4_DEBUG EXT4_RW_ATTR_SBI_UL(simulate_fail, s_simulate_fail); #endif +EXT4_RO_ATTR_SBI_ATOMIC(warning_count, s_warning_count); +EXT4_RO_ATTR_SBI_ATOMIC(msg_count, s_msg_count); EXT4_RO_ATTR_ES_UI(errors_count, s_error_count); EXT4_RO_ATTR_ES_U8(first_error_errcode, s_first_error_errcode); EXT4_RO_ATTR_ES_U8(last_error_errcode, s_last_error_errcode); @@ -240,6 +246,8 @@ EXT4_RO_ATTR_ES_STRING(last_error_func, s_last_error_func, 32); EXT4_ATTR(first_error_time, 0444, first_error_time); EXT4_ATTR(last_error_time, 0444, last_error_time); EXT4_ATTR(journal_task, 0444, journal_task); +EXT4_RW_ATTR_SBI_UI(mb_prefetch, s_mb_prefetch); +EXT4_RW_ATTR_SBI_UI(mb_prefetch_limit, s_mb_prefetch_limit); static unsigned int old_bump_val = 128; EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val); @@ -257,6 +265,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(mb_order2_req), ATTR_LIST(mb_stream_req), ATTR_LIST(mb_group_prealloc), + ATTR_LIST(mb_max_inode_prealloc), ATTR_LIST(max_writeback_mb_bump), ATTR_LIST(extent_max_zeroout_kb), ATTR_LIST(trigger_fs_error), @@ -267,6 +276,8 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(msg_ratelimit_interval_ms), ATTR_LIST(msg_ratelimit_burst), ATTR_LIST(errors_count), + ATTR_LIST(warning_count), + ATTR_LIST(msg_count), ATTR_LIST(first_error_ino), ATTR_LIST(last_error_ino), ATTR_LIST(first_error_block), @@ -283,6 +294,8 @@ static struct attribute *ext4_attrs[] = { #ifdef CONFIG_EXT4_DEBUG ATTR_LIST(simulate_fail), #endif + ATTR_LIST(mb_prefetch), + ATTR_LIST(mb_prefetch_limit), NULL, }; ATTRIBUTE_GROUPS(ext4); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 7d2f6576d954..cba4b877c606 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1356,8 +1356,7 @@ retry: block = 0; while (wsize < bufsize) { - if (bh != NULL) - brelse(bh); + brelse(bh); csize = (bufsize - wsize) > blocksize ? blocksize : bufsize - wsize; bh = ext4_getblk(handle, ea_inode, block, 0); diff --git a/fs/io_uring.c b/fs/io_uring.c index dc506b75659c..91e2cc8414f9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -540,7 +540,6 @@ enum { REQ_F_ISREG_BIT, REQ_F_COMP_LOCKED_BIT, REQ_F_NEED_CLEANUP_BIT, - REQ_F_OVERFLOW_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, REQ_F_NO_FILE_TABLE_BIT, @@ -583,8 +582,6 @@ enum { REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT), /* needs cleanup */ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), - /* in overflow list */ - REQ_F_OVERFLOW = BIT(REQ_F_OVERFLOW_BIT), /* already went through poll handler */ REQ_F_POLLED = BIT(REQ_F_POLLED_BIT), /* buffer already selected */ @@ -946,7 +943,8 @@ static void io_get_req_task(struct io_kiocb *req) static inline void io_clean_op(struct io_kiocb *req) { - if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED)) + if (req->flags & (REQ_F_NEED_CLEANUP | REQ_F_BUFFER_SELECTED | + REQ_F_INFLIGHT)) __io_clean_op(req); } @@ -1366,7 +1364,6 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx, bool force) req = list_first_entry(&ctx->cq_overflow_list, struct io_kiocb, compl.list); list_move(&req->compl.list, &list); - req->flags &= ~REQ_F_OVERFLOW; if (cqe) { WRITE_ONCE(cqe->user_data, req->user_data); WRITE_ONCE(cqe->res, req->result); @@ -1419,7 +1416,6 @@ static void __io_cqring_fill_event(struct io_kiocb *req, long res, long cflags) ctx->rings->sq_flags |= IORING_SQ_CQ_OVERFLOW; } io_clean_op(req); - req->flags |= REQ_F_OVERFLOW; req->result = res; req->compl.cflags = cflags; refcount_inc(&req->refs); @@ -1563,17 +1559,6 @@ static bool io_dismantle_req(struct io_kiocb *req) if (req->file) io_put_file(req, req->file, (req->flags & REQ_F_FIXED_FILE)); - if (req->flags & REQ_F_INFLIGHT) { - struct io_ring_ctx *ctx = req->ctx; - unsigned long flags; - - spin_lock_irqsave(&ctx->inflight_lock, flags); - list_del(&req->inflight_entry); - if (waitqueue_active(&ctx->inflight_wait)) - wake_up(&ctx->inflight_wait); - spin_unlock_irqrestore(&ctx->inflight_lock, flags); - } - return io_req_clean_work(req); } @@ -2819,22 +2804,15 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, return __io_iov_buffer_select(req, iov, needs_lock); } -static ssize_t io_import_iovec(int rw, struct io_kiocb *req, - struct iovec **iovec, struct iov_iter *iter, - bool needs_lock) +static ssize_t __io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct iov_iter *iter, + bool needs_lock) { void __user *buf = u64_to_user_ptr(req->rw.addr); size_t sqe_len = req->rw.len; ssize_t ret; u8 opcode; - if (req->io) { - struct io_async_rw *iorw = &req->io->rw; - - *iovec = NULL; - return iov_iter_count(&iorw->iter); - } - opcode = req->opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { *iovec = NULL; @@ -2848,10 +2826,8 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { if (req->flags & REQ_F_BUFFER_SELECT) { buf = io_rw_buffer_select(req, &sqe_len, needs_lock); - if (IS_ERR(buf)) { - *iovec = NULL; + if (IS_ERR(buf)) return PTR_ERR(buf); - } req->rw.len = sqe_len; } @@ -2879,6 +2855,16 @@ static ssize_t io_import_iovec(int rw, struct io_kiocb *req, return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter); } +static ssize_t io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct iov_iter *iter, + bool needs_lock) +{ + if (!req->io) + return __io_import_iovec(rw, req, iovec, iter, needs_lock); + *iovec = NULL; + return iov_iter_count(&req->io->rw.iter); +} + /* * For files that don't have ->read_iter() and ->write_iter(), handle them * by looping over ->read() or ->write() manually. @@ -3001,11 +2987,8 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw, ssize_t ret; iorw->iter.iov = iorw->fast_iov; - /* reset ->io around the iovec import, we don't want to use it */ - req->io = NULL; - ret = io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov, + ret = __io_import_iovec(rw, req, (struct iovec **) &iorw->iter.iov, &iorw->iter, !force_nonblock); - req->io = container_of(iorw, struct io_async_ctx, rw); if (unlikely(ret < 0)) return ret; @@ -3074,27 +3057,6 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, return 1; } -static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, - struct wait_page_queue *wait, - wait_queue_func_t func, - void *data) -{ - /* Can't support async wakeup with polled IO */ - if (kiocb->ki_flags & IOCB_HIPRI) - return -EINVAL; - if (kiocb->ki_filp->f_mode & FMODE_BUF_RASYNC) { - wait->wait.func = func; - wait->wait.private = data; - wait->wait.flags = 0; - INIT_LIST_HEAD(&wait->wait.entry); - kiocb->ki_flags |= IOCB_WAITQ; - kiocb->ki_waitq = wait; - return 0; - } - - return -EOPNOTSUPP; -} - /* * This controls whether a given IO request should be armed for async page * based retry. If we return false here, the request is handed to the async @@ -3109,16 +3071,17 @@ static inline int kiocb_wait_page_queue_init(struct kiocb *kiocb, */ static bool io_rw_should_retry(struct io_kiocb *req) { + struct wait_page_queue *wait = &req->io->rw.wpq; struct kiocb *kiocb = &req->rw.kiocb; - int ret; /* never retry for NOWAIT, we just complete with -EAGAIN */ if (req->flags & REQ_F_NOWAIT) return false; /* Only for buffered IO */ - if (kiocb->ki_flags & IOCB_DIRECT) + if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI)) return false; + /* * just use poll if we can, and don't attempt if the fs doesn't * support callback based unlocks @@ -3126,14 +3089,15 @@ static bool io_rw_should_retry(struct io_kiocb *req) if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC)) return false; - ret = kiocb_wait_page_queue_init(kiocb, &req->io->rw.wpq, - io_async_buf_func, req); - if (!ret) { - io_get_req_task(req); - return true; - } + wait->wait.func = io_async_buf_func; + wait->wait.private = req; + wait->wait.flags = 0; + INIT_LIST_HEAD(&wait->wait.entry); + kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_waitq = wait; - return false; + io_get_req_task(req); + return true; } static int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) @@ -3238,6 +3202,7 @@ done: kiocb_done(kiocb, ret, cs); ret = 0; out_free: + /* it's reportedly faster than delegating the null check to kfree() */ if (iovec) kfree(iovec); return ret; @@ -3334,6 +3299,7 @@ copy_iov: return -EAGAIN; } out_free: + /* it's reportedly faster than delegating the null check to kfree() */ if (iovec) kfree(iovec); return ret; @@ -5653,6 +5619,18 @@ static void __io_clean_op(struct io_kiocb *req) } req->flags &= ~REQ_F_NEED_CLEANUP; } + + if (req->flags & REQ_F_INFLIGHT) { + struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; + + spin_lock_irqsave(&ctx->inflight_lock, flags); + list_del(&req->inflight_entry); + if (waitqueue_active(&ctx->inflight_wait)) + wake_up(&ctx->inflight_wait); + spin_unlock_irqrestore(&ctx->inflight_lock, flags); + req->flags &= ~REQ_F_INFLIGHT; + } } static int io_issue_sqe(struct io_kiocb *req, const struct io_uring_sqe *sqe, @@ -7979,7 +7957,13 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) ACCT_LOCKED); INIT_WORK(&ctx->exit_work, io_ring_exit_work); - queue_work(system_wq, &ctx->exit_work); + /* + * Use system_unbound_wq to avoid spawning tons of event kworkers + * if we're exiting a ton of rings at the same time. It just adds + * noise and overhead, there's no discernable change in runtime + * over using system_wq. + */ + queue_work(system_unbound_wq, &ctx->exit_work); } static int io_uring_release(struct inode *inode, struct file *file) @@ -8063,6 +8047,33 @@ static bool io_timeout_remove_link(struct io_ring_ctx *ctx, return found; } +static bool io_cancel_link_cb(struct io_wq_work *work, void *data) +{ + return io_match_link(container_of(work, struct io_kiocb, work), data); +} + +static void io_attempt_cancel(struct io_ring_ctx *ctx, struct io_kiocb *req) +{ + enum io_wq_cancel cret; + + /* cancel this particular work, if it's running */ + cret = io_wq_cancel_work(ctx->io_wq, &req->work); + if (cret != IO_WQ_CANCEL_NOTFOUND) + return; + + /* find links that hold this pending, cancel those */ + cret = io_wq_cancel_cb(ctx->io_wq, io_cancel_link_cb, req, true); + if (cret != IO_WQ_CANCEL_NOTFOUND) + return; + + /* if we have a poll link holding this pending, cancel that */ + if (io_poll_remove_link(ctx, req)) + return; + + /* final option, timeout link is holding this req pending */ + io_timeout_remove_link(ctx, req); +} + static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { @@ -8094,35 +8105,9 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, /* We need to keep going until we don't find a matching req */ if (!cancel_req) break; - - if (cancel_req->flags & REQ_F_OVERFLOW) { - spin_lock_irq(&ctx->completion_lock); - list_del(&cancel_req->compl.list); - cancel_req->flags &= ~REQ_F_OVERFLOW; - - io_cqring_mark_overflow(ctx); - WRITE_ONCE(ctx->rings->cq_overflow, - atomic_inc_return(&ctx->cached_cq_overflow)); - io_commit_cqring(ctx); - spin_unlock_irq(&ctx->completion_lock); - - /* - * Put inflight ref and overflow ref. If that's - * all we had, then we're done with this request. - */ - if (refcount_sub_and_test(2, &cancel_req->refs)) { - io_free_req(cancel_req); - finish_wait(&ctx->inflight_wait, &wait); - continue; - } - } else { - io_wq_cancel_work(ctx->io_wq, &cancel_req->work); - /* could be a link, check and remove if it is */ - if (!io_poll_remove_link(ctx, cancel_req)) - io_timeout_remove_link(ctx, cancel_req); - io_put_req(cancel_req); - } - + /* cancel this request, or head link requests */ + io_attempt_cancel(ctx, cancel_req); + io_put_req(cancel_req); schedule(); finish_wait(&ctx->inflight_wait, &wait); } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e4944436e733..17fdc482f554 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -1285,7 +1285,7 @@ journal_t *jbd2_journal_init_inode(struct inode *inode) * superblock as being NULL to prevent the journal destroy from writing * back a bogus superblock. */ -static void journal_fail_superblock (journal_t *journal) +static void journal_fail_superblock(journal_t *journal) { struct buffer_head *bh = journal->j_sb_buffer; brelse(bh); @@ -1367,8 +1367,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) int ret; /* Buffer got discarded which means block device got invalidated */ - if (!buffer_mapped(bh)) + if (!buffer_mapped(bh)) { + unlock_buffer(bh); return -EIO; + } trace_jbd2_write_superblock(journal, write_flags); if (!(journal->j_flags & JBD2_BARRIER)) @@ -1815,7 +1817,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features () - Check if features specified are used. + *int jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -1825,7 +1827,7 @@ int jbd2_journal_destroy(journal_t *journal) * features. Return true (non-zero) if it does. **/ -int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, +int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; @@ -1860,7 +1862,7 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, * all of a given set of features on this journal. Return true * (non-zero) if it can. */ -int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat, +int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { if (!compat && !ro && !incompat) @@ -1882,7 +1884,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com } /** - * int jbd2_journal_set_features () - Mark a given journal feature in the superblock + * int jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount @@ -1893,7 +1895,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com * */ -int jbd2_journal_set_features (journal_t *journal, unsigned long compat, +int jbd2_journal_set_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { #define INCOMPAT_FEATURE_ON(f) \ diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 2ed278f0dced..faa97d748474 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -690,14 +690,11 @@ static int do_one_pass(journal_t *journal, * number. */ if (pass == PASS_SCAN && jbd2_has_feature_checksum(journal)) { - int chksum_err, chksum_seen; struct commit_header *cbh = (struct commit_header *)bh->b_data; unsigned found_chksum = be32_to_cpu(cbh->h_chksum[0]); - chksum_err = chksum_seen = 0; - if (info->end_transaction) { journal->j_failed_commit = info->end_transaction; @@ -705,42 +702,23 @@ static int do_one_pass(journal_t *journal, break; } - if (crc32_sum == found_chksum && - cbh->h_chksum_type == JBD2_CRC32_CHKSUM && - cbh->h_chksum_size == - JBD2_CRC32_CHKSUM_SIZE) - chksum_seen = 1; - else if (!(cbh->h_chksum_type == 0 && - cbh->h_chksum_size == 0 && - found_chksum == 0 && - !chksum_seen)) - /* - * If fs is mounted using an old kernel and then - * kernel with journal_chksum is used then we - * get a situation where the journal flag has - * checksum flag set but checksums are not - * present i.e chksum = 0, in the individual - * commit blocks. - * Hence to avoid checksum failures, in this - * situation, this extra check is added. - */ - chksum_err = 1; - - if (chksum_err) { - info->end_transaction = next_commit_ID; - - if (!jbd2_has_feature_async_commit(journal)) { - journal->j_failed_commit = - next_commit_ID; - brelse(bh); - break; - } - } + /* Neither checksum match nor unused? */ + if (!((crc32_sum == found_chksum && + cbh->h_chksum_type == + JBD2_CRC32_CHKSUM && + cbh->h_chksum_size == + JBD2_CRC32_CHKSUM_SIZE) || + (cbh->h_chksum_type == 0 && + cbh->h_chksum_size == 0 && + found_chksum == 0))) + goto chksum_error; + crc32_sum = ~0; } if (pass == PASS_SCAN && !jbd2_commit_block_csum_verify(journal, bh->b_data)) { + chksum_error: info->end_transaction = next_commit_ID; if (!jbd2_has_feature_async_commit(journal)) { diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index e91aad3637a2..43985738aa86 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -2026,6 +2026,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh) */ static void __jbd2_journal_unfile_buffer(struct journal_head *jh) { + J_ASSERT_JH(jh, jh->b_transaction != NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + __jbd2_journal_temp_unlink_buffer(jh); jh->b_transaction = NULL; } @@ -2078,10 +2081,6 @@ out: * int jbd2_journal_try_to_free_buffers() - try to free page buffers. * @journal: journal for operation * @page: to try and free - * @gfp_mask: we use the mask to detect how hard should we try to release - * buffers. If __GFP_DIRECT_RECLAIM and __GFP_FS is set, we wait for commit - * code to release the buffers. - * * * For all the buffers on this page, * if they are fully written out ordered data, move them onto BUF_CLEAN @@ -2112,11 +2111,11 @@ out: * * Return 0 on failure, 1 on success */ -int jbd2_journal_try_to_free_buffers(journal_t *journal, - struct page *page, gfp_t gfp_mask) +int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page) { struct buffer_head *head; struct buffer_head *bh; + bool has_write_io_error = false; int ret = 0; J_ASSERT(PageLocked(page)); @@ -2141,11 +2140,26 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal, jbd2_journal_put_journal_head(jh); if (buffer_jbd(bh)) goto busy; + + /* + * If we free a metadata buffer which has been failed to + * write out, the jbd2 checkpoint procedure will not detect + * this failure and may lead to filesystem inconsistency + * after cleanup journal tail. + */ + if (buffer_write_io_error(bh)) { + pr_err("JBD2: Error while async write back metadata bh %llu.", + (unsigned long long)bh->b_blocknr); + has_write_io_error = true; + } } while ((bh = bh->b_this_page) != head); ret = try_to_free_buffers(page); busy: + if (has_write_io_error) + jbd2_journal_abort(journal, -EIO); + return ret; } @@ -2572,6 +2586,13 @@ bool __jbd2_journal_refile_buffer(struct journal_head *jh) was_dirty = test_clear_buffer_jbddirty(bh); __jbd2_journal_temp_unlink_buffer(jh); + + /* + * b_transaction must be set, otherwise the new b_transaction won't + * be holding jh reference + */ + J_ASSERT_JH(jh, jh->b_transaction != NULL); + /* * We set b_transaction here because b_next_transaction will inherit * our jh reference and thus __jbd2_journal_file_buffer() must not diff --git a/fs/romfs/storage.c b/fs/romfs/storage.c index 6b2b4362089e..b57b3ffcbc32 100644 --- a/fs/romfs/storage.c +++ b/fs/romfs/storage.c @@ -217,10 +217,8 @@ int romfs_dev_read(struct super_block *sb, unsigned long pos, size_t limit; limit = romfs_maxsize(sb); - if (pos >= limit) + if (pos >= limit || buflen > limit - pos) return -EIO; - if (buflen > limit - pos) - buflen = limit - pos; #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 76bb1c846845..8a19773b5a0b 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -87,7 +87,11 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, int error, i; struct bio *bio; - bio = bio_alloc(GFP_NOIO, page_count); + if (page_count <= BIO_MAX_PAGES) + bio = bio_alloc(GFP_NOIO, page_count); + else + bio = bio_kmalloc(GFP_NOIO, page_count); + if (!bio) return -ENOMEM; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index a2710e654b64..3215023d4852 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -132,6 +132,7 @@ enum cpuhp_state { CPUHP_AP_MIPS_GIC_TIMER_STARTING, CPUHP_AP_ARC_TIMER_STARTING, CPUHP_AP_RISCV_TIMER_STARTING, + CPUHP_AP_CLINT_TIMER_STARTING, CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, CPUHP_AP_KVM_STARTING, diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h index 5a3ce2a24794..6e87225600ae 100644 --- a/include/linux/dma-direct.h +++ b/include/linux/dma-direct.h @@ -73,9 +73,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size, } u64 dma_direct_get_required_mask(struct device *dev); -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, - u64 *phys_mask); -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size); void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs); void dma_direct_free(struct device *dev, size_t size, void *cpu_addr, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 016b96b384bd..52635e91143b 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -522,8 +522,9 @@ void *dma_common_pages_remap(struct page **pages, size_t size, pgprot_t prot, const void *caller); void dma_common_free_remap(void *cpu_addr, size_t size); -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags); +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t flags, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)); bool dma_free_from_pool(struct device *dev, void *start, size_t size); int diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 4aaa29772bb0..08f904943ab2 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1381,7 +1381,7 @@ extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); extern int jbd2_journal_invalidatepage(journal_t *, struct page *, unsigned int, unsigned int); -extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +extern int jbd2_journal_try_to_free_buffers(journal_t *journal, struct page *page); extern int jbd2_journal_stop(handle_t *); extern int jbd2_journal_flush (journal_t *); extern void jbd2_journal_lock_updates (journal_t *); diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index aac42c28fe62..9b67394471e1 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -58,7 +58,6 @@ struct nf_ipv6_ops { int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); #if IS_MODULE(CONFIG_IPV6) - int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); int (*br_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, @@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #include <net/netfilter/ipv6/nf_defrag_ipv6.h> -static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, - u32 user) -{ -#if IS_MODULE(CONFIG_IPV6) - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return 1; - - return v6_ops->br_defrag(net, skb, user); -#elif IS_BUILTIN(CONFIG_IPV6) - return nf_ct_frag6_gather(net, skb, user); -#else - return 1; -#endif -} - int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index a124c21e3204..e8cbc2e795d5 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -117,7 +117,9 @@ static inline pgd_t *pgd_offset_pgd(pgd_t *pgd, unsigned long address) * a shortcut which implies the use of the kernel's pgd, instead * of a process's */ +#ifndef pgd_offset_k #define pgd_offset_k(address) pgd_offset(&init_mm, (address)) +#endif /* * In many cases it is known that a virtual address is mapped at PMD or PTE diff --git a/include/linux/phylink.h b/include/linux/phylink.h index a8e876317e25..c36fb41a7d90 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -402,7 +402,8 @@ void pcs_get_state(struct phylink_pcs *pcs, * For most 10GBASE-R, there is no advertisement. */ int pcs_config(struct phylink_pcs *pcs, unsigned int mode, - phy_interface_t interface, const unsigned long *advertising); + phy_interface_t interface, const unsigned long *advertising, + bool permit_pause_to_mac); /** * pcs_an_restart() - restart 802.3z BaseX autonegotiation diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 917d88edb7b9..a8ec3b6093fc 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -36,6 +36,9 @@ struct user_struct { defined(CONFIG_NET) || defined(CONFIG_IO_URING) atomic_long_t locked_vm; #endif +#ifdef CONFIG_WATCH_QUEUE + atomic_t nr_watches; /* The number of watches this user currently has */ +#endif /* Miscellaneous per-user rate limit */ struct ratelimit_state ratelimit; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index ba3f6c15ad2b..18f783dcd55f 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -97,7 +97,8 @@ bool ipv6_chk_custom_prefix(const struct in6_addr *addr, int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); -struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr); +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, + struct net_device *dev); struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *addr, diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index cc41d692ae8e..4c8b99ec8606 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -746,24 +746,29 @@ TRACE_EVENT(ext4_mb_release_group_pa, ); TRACE_EVENT(ext4_discard_preallocations, - TP_PROTO(struct inode *inode), + TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed), - TP_ARGS(inode), + TP_ARGS(inode, len, needed), TP_STRUCT__entry( - __field( dev_t, dev ) - __field( ino_t, ino ) + __field( dev_t, dev ) + __field( ino_t, ino ) + __field( unsigned int, len ) + __field( unsigned int, needed ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; + __entry->len = len; + __entry->needed = needed; ), - TP_printk("dev %d,%d ino %lu", + TP_printk("dev %d,%d ino %lu len: %u needed %u", MAJOR(__entry->dev), MINOR(__entry->dev), - (unsigned long) __entry->ino) + (unsigned long) __entry->ino, __entry->len, + __entry->needed) ); TRACE_EVENT(ext4_mb_discard_preallocations, @@ -1312,18 +1317,34 @@ DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load, TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_read_block_bitmap_load, +DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, TP_PROTO(struct super_block *sb, unsigned long group), TP_ARGS(sb, group) ); -DEFINE_EVENT(ext4__bitmap_load, ext4_load_inode_bitmap, +TRACE_EVENT(ext4_read_block_bitmap_load, + TP_PROTO(struct super_block *sb, unsigned long group, bool prefetch), - TP_PROTO(struct super_block *sb, unsigned long group), + TP_ARGS(sb, group, prefetch), - TP_ARGS(sb, group) + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( bool, prefetch ) + + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->prefetch = prefetch; + ), + + TP_printk("dev %d,%d group %u prefetch %d", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->prefetch) ); TRACE_EVENT(ext4_direct_IO_enter, @@ -2726,6 +2747,50 @@ TRACE_EVENT(ext4_error, __entry->function, __entry->line) ); +TRACE_EVENT(ext4_prefetch_bitmaps, + TP_PROTO(struct super_block *sb, ext4_group_t group, + ext4_group_t next, unsigned int prefetch_ios), + + TP_ARGS(sb, group, next, prefetch_ios), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + __field( __u32, next ) + __field( __u32, ios ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + __entry->next = next; + __entry->ios = prefetch_ios; + ), + + TP_printk("dev %d,%d group %u next %u ios %u", + MAJOR(__entry->dev), MINOR(__entry->dev), + __entry->group, __entry->next, __entry->ios) +); + +TRACE_EVENT(ext4_lazy_itable_init, + TP_PROTO(struct super_block *sb, ext4_group_t group), + + TP_ARGS(sb, group), + + TP_STRUCT__entry( + __field( dev_t, dev ) + __field( __u32, group ) + ), + + TP_fast_assign( + __entry->dev = sb->s_dev; + __entry->group = group; + ), + + TP_printk("dev %d,%d group %u", + MAJOR(__entry->dev), MINOR(__entry->dev), __entry->group) +); + #endif /* _TRACE_EXT4_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 0480f893facd..b6238b2209b7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -767,7 +767,7 @@ union bpf_attr { * * Also, note that **bpf_trace_printk**\ () is slow, and should * only be used for debugging purposes. For this reason, a notice - * bloc (spanning several lines) is printed to kernel logs and + * block (spanning several lines) is printed to kernel logs and * states that the helper should not be used "for production use" * the first time this helper is used (or more precisely, when * **trace_printk**\ () buffers are allocated). For passing values @@ -1033,14 +1033,14 @@ union bpf_attr { * * int ret; * struct bpf_tunnel_key key = {}; - * + * * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); * if (ret < 0) * return TC_ACT_SHOT; // drop packet - * + * * if (key.remote_ipv4 != 0x0a000001) * return TC_ACT_SHOT; // drop packet - * + * * return TC_ACT_OK; // accept packet * * This interface can also be used with all encapsulation devices @@ -1147,7 +1147,7 @@ union bpf_attr { * Description * Retrieve the realm or the route, that is to say the * **tclassid** field of the destination for the *skb*. The - * indentifier retrieved is a user-provided tag, similar to the + * identifier retrieved is a user-provided tag, similar to the * one used with the net_cls cgroup (see description for * **bpf_get_cgroup_classid**\ () helper), but here this tag is * held by a route (a destination entry), not by a task. diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index b6715964b685..8faa2ce89396 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -67,6 +67,9 @@ static void bpf_iter_done_stop(struct seq_file *seq) iter_priv->done_stop = true; } +/* maximum visited objects before bailing out */ +#define MAX_ITER_OBJECTS 1000000 + /* bpf_seq_read, a customized and simpler version for bpf iterator. * no_llseek is assumed for this file. * The following are differences from seq_read(): @@ -79,7 +82,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, { struct seq_file *seq = file->private_data; size_t n, offs, copied = 0; - int err = 0; + int err = 0, num_objs = 0; void *p; mutex_lock(&seq->lock); @@ -135,6 +138,7 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, while (1) { loff_t pos = seq->index; + num_objs++; offs = seq->count; p = seq->op->next(seq, p, &seq->index); if (pos == seq->index) { @@ -153,6 +157,15 @@ static ssize_t bpf_seq_read(struct file *file, char __user *buf, size_t size, if (seq->count >= size) break; + if (num_objs >= MAX_ITER_OBJECTS) { + if (offs == 0) { + err = -EAGAIN; + seq->op->stop(seq, p); + goto done; + } + break; + } + err = seq->op->show(seq, p); if (err > 0) { bpf_iter_dec_seq_num(seq); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 4fd830a62be2..cfed0ac44d38 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -213,11 +213,13 @@ static int stack_map_get_build_id_32(void *page_addr, phdr = (Elf32_Phdr *)(page_addr + sizeof(Elf32_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } @@ -236,11 +238,13 @@ static int stack_map_get_build_id_64(void *page_addr, phdr = (Elf64_Phdr *)(page_addr + sizeof(Elf64_Ehdr)); - for (i = 0; i < ehdr->e_phnum; ++i) - if (phdr[i].p_type == PT_NOTE) - return stack_map_parse_build_id(page_addr, build_id, - page_addr + phdr[i].p_offset, - phdr[i].p_filesz); + for (i = 0; i < ehdr->e_phnum; ++i) { + if (phdr[i].p_type == PT_NOTE && + !stack_map_parse_build_id(page_addr, build_id, + page_addr + phdr[i].p_offset, + phdr[i].p_filesz)) + return 0; + } return -EINVAL; } diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 232df29793e9..99af4cea1102 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -29,8 +29,9 @@ static struct task_struct *task_seq_get_next(struct pid_namespace *ns, rcu_read_lock(); retry: - pid = idr_get_next(&ns->idr, tid); + pid = find_ge_pid(*tid, ns); if (pid) { + *tid = pid_nr_ns(pid, ns); task = get_pid_task(pid, PIDTYPE_PID); if (!task) { ++*tid; @@ -178,10 +179,11 @@ again: f = fcheck_files(curr_files, curr_fd); if (!f) continue; + if (!get_file_rcu(f)) + continue; /* set info->fd */ info->fd = curr_fd; - get_file(f); rcu_read_unlock(); return f; } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index bb0041e99659..db6ef07aec3b 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -43,7 +43,7 @@ u64 dma_direct_get_required_mask(struct device *dev) return (1ULL << (fls64(max_dma) - 1)) * 2 - 1; } -gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, +static gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, u64 *phys_limit) { u64 dma_limit = min_not_zero(dma_mask, dev->bus_dma_limit); @@ -68,7 +68,7 @@ gfp_t dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask, return 0; } -bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) +static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size) { return phys_to_dma_direct(dev, phys) + size - 1 <= min_not_zero(dev->coherent_dma_mask, dev->bus_dma_limit); @@ -161,8 +161,13 @@ void *dma_direct_alloc_pages(struct device *dev, size_t size, size = PAGE_ALIGN(size); if (dma_should_alloc_from_pool(dev, gfp, attrs)) { - ret = dma_alloc_from_pool(dev, size, &page, gfp); - if (!ret) + u64 phys_mask; + + gfp |= dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, + &phys_mask); + page = dma_alloc_from_pool(dev, size, &ret, gfp, + dma_coherent_ok); + if (!page) return NULL; goto done; } diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c index 6bc74a2d5127..06582b488e31 100644 --- a/kernel/dma/pool.c +++ b/kernel/dma/pool.c @@ -3,7 +3,9 @@ * Copyright (C) 2012 ARM Ltd. * Copyright (C) 2020 Google LLC */ +#include <linux/cma.h> #include <linux/debugfs.h> +#include <linux/dma-contiguous.h> #include <linux/dma-direct.h> #include <linux/dma-noncoherent.h> #include <linux/init.h> @@ -55,6 +57,29 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size) pool_size_kernel += size; } +static bool cma_in_zone(gfp_t gfp) +{ + unsigned long size; + phys_addr_t end; + struct cma *cma; + + cma = dev_get_cma_area(NULL); + if (!cma) + return false; + + size = cma_get_size(cma); + if (!size) + return false; + + /* CMA can't cross zone boundaries, see cma_activate_area() */ + end = cma_get_base(cma) + size - 1; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return end <= DMA_BIT_MASK(zone_dma_bits); + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return end <= DMA_BIT_MASK(32); + return true; +} + static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, gfp_t gfp) { @@ -68,7 +93,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size, do { pool_size = 1 << (PAGE_SHIFT + order); - page = alloc_pages(gfp, order); + if (cma_in_zone(gfp)) + page = dma_alloc_from_contiguous(NULL, 1 << order, + order, false); + if (!page) + page = alloc_pages(gfp, order); } while (!page && order-- > 0); if (!page) goto out; @@ -196,93 +225,75 @@ static int __init dma_atomic_pool_init(void) } postcore_initcall(dma_atomic_pool_init); -static inline struct gen_pool *dma_guess_pool_from_device(struct device *dev) +static inline struct gen_pool *dma_guess_pool(struct gen_pool *prev, gfp_t gfp) { - u64 phys_mask; - gfp_t gfp; - - gfp = dma_direct_optimal_gfp_mask(dev, dev->coherent_dma_mask, - &phys_mask); - if (IS_ENABLED(CONFIG_ZONE_DMA) && gfp == GFP_DMA) + if (prev == NULL) { + if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32)) + return atomic_pool_dma32; + if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA)) + return atomic_pool_dma; + return atomic_pool_kernel; + } + if (prev == atomic_pool_kernel) + return atomic_pool_dma32 ? atomic_pool_dma32 : atomic_pool_dma; + if (prev == atomic_pool_dma32) return atomic_pool_dma; - if (IS_ENABLED(CONFIG_ZONE_DMA32) && gfp == GFP_DMA32) - return atomic_pool_dma32; - return atomic_pool_kernel; + return NULL; } -static inline struct gen_pool *dma_get_safer_pool(struct gen_pool *bad_pool) +static struct page *__dma_alloc_from_pool(struct device *dev, size_t size, + struct gen_pool *pool, void **cpu_addr, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { - if (bad_pool == atomic_pool_kernel) - return atomic_pool_dma32 ? : atomic_pool_dma; + unsigned long addr; + phys_addr_t phys; - if (bad_pool == atomic_pool_dma32) - return atomic_pool_dma; + addr = gen_pool_alloc(pool, size); + if (!addr) + return NULL; - return NULL; -} + phys = gen_pool_virt_to_phys(pool, addr); + if (phys_addr_ok && !phys_addr_ok(dev, phys, size)) { + gen_pool_free(pool, addr, size); + return NULL; + } -static inline struct gen_pool *dma_guess_pool(struct device *dev, - struct gen_pool *bad_pool) -{ - if (bad_pool) - return dma_get_safer_pool(bad_pool); + if (gen_pool_avail(pool) < atomic_pool_size) + schedule_work(&atomic_pool_work); - return dma_guess_pool_from_device(dev); + *cpu_addr = (void *)addr; + memset(*cpu_addr, 0, size); + return pfn_to_page(__phys_to_pfn(phys)); } -void *dma_alloc_from_pool(struct device *dev, size_t size, - struct page **ret_page, gfp_t flags) +struct page *dma_alloc_from_pool(struct device *dev, size_t size, + void **cpu_addr, gfp_t gfp, + bool (*phys_addr_ok)(struct device *, phys_addr_t, size_t)) { struct gen_pool *pool = NULL; - unsigned long val = 0; - void *ptr = NULL; - phys_addr_t phys; - - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) { - WARN(1, "Failed to get suitable pool for %s\n", - dev_name(dev)); - break; - } - - val = gen_pool_alloc(pool, size); - if (!val) - continue; - - phys = gen_pool_virt_to_phys(pool, val); - if (dma_coherent_ok(dev, phys, size)) - break; - - gen_pool_free(pool, val, size); - val = 0; - } - - - if (val) { - *ret_page = pfn_to_page(__phys_to_pfn(phys)); - ptr = (void *)val; - memset(ptr, 0, size); + struct page *page; - if (gen_pool_avail(pool) < atomic_pool_size) - schedule_work(&atomic_pool_work); + while ((pool = dma_guess_pool(pool, gfp))) { + page = __dma_alloc_from_pool(dev, size, pool, cpu_addr, + phys_addr_ok); + if (page) + return page; } - return ptr; + WARN(1, "Failed to get suitable pool for %s\n", dev_name(dev)); + return NULL; } bool dma_free_from_pool(struct device *dev, void *start, size_t size) { struct gen_pool *pool = NULL; - while (1) { - pool = dma_guess_pool(dev, pool); - if (!pool) - return false; - - if (gen_pool_has_addr(pool, (unsigned long)start, size)) { - gen_pool_free(pool, (unsigned long)start, size); - return true; - } + while ((pool = dma_guess_pool(pool, 0))) { + if (!gen_pool_has_addr(pool, (unsigned long)start, size)) + continue; + gen_pool_free(pool, (unsigned long)start, size); + return true; } + + return false; } diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 9852e0d62d95..fcae019158ca 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -65,7 +65,8 @@ static long syscall_trace_enter(struct pt_regs *regs, long syscall, syscall_enter_audit(regs, syscall); - return ret ? : syscall; + /* The above might have changed the syscall number */ + return ret ? : syscall_get_nr(current, regs); } noinstr long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 649fd53dc9ad..0e18aaf23a7b 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -205,7 +205,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) munlock_vma_page(old_page); put_page(old_page); diff --git a/kernel/relay.c b/kernel/relay.c index 72fe443ea78f..fb4e0c530c08 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -197,6 +197,7 @@ free_buf: static void relay_destroy_channel(struct kref *kref) { struct rchan *chan = container_of(kref, struct rchan, kref); + free_percpu(chan->buf); kfree(chan); } diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index f74020f6bd9d..0ef8f65bd2d7 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -393,6 +393,7 @@ static void free_watch(struct rcu_head *rcu) struct watch *watch = container_of(rcu, struct watch, rcu); put_watch_queue(rcu_access_pointer(watch->queue)); + atomic_dec(&watch->cred->user->nr_watches); put_cred(watch->cred); } @@ -452,6 +453,13 @@ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) watch->cred = get_current_cred(); rcu_assign_pointer(watch->watch_list, wlist); + if (atomic_inc_return(&watch->cred->user->nr_watches) > + task_rlimit(current, RLIMIT_NOFILE)) { + atomic_dec(&watch->cred->user->nr_watches); + put_cred(watch->cred); + return -EAGAIN; + } + spin_lock_bh(&wqueue->lock); kref_get(&wqueue->usage); kref_get(&watch->usage); diff --git a/lib/Makefile b/lib/Makefile index e290fc5707ea..a4a4c6864f51 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -15,11 +15,16 @@ KCOV_INSTRUMENT_debugobjects.o := n KCOV_INSTRUMENT_dynamic_debug.o := n KCOV_INSTRUMENT_fault-inject.o := n +# string.o implements standard library functions like memset/memcpy etc. +# Use -ffreestanding to ensure that the compiler does not try to "optimize" +# them into calls to themselves. +CFLAGS_string.o := -ffreestanding + # Early boot use of cmdline, don't instrument it ifdef CONFIG_AMD_MEM_ENCRYPT KASAN_SANITIZE_string.o := n -CFLAGS_string.o := -fno-stack-protector +CFLAGS_string.o += -fno-stack-protector endif # Used by KCSAN while enabled, avoid recursion. diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index aabf65d4d91b..1f87aec9ab5c 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -655,7 +655,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) snprintf(cft->name, MAX_CFTYPE_NAME, "%s.events", buf); cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_show; - cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]), + cft->file_offset = offsetof(struct hugetlb_cgroup, events_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; /* Add the events.local file */ @@ -664,7 +664,7 @@ static void __init __hugetlb_cgroup_file_dfl_init(int idx) cft->private = MEMFILE_PRIVATE(idx, 0); cft->seq_show = hugetlb_events_local_show; cft->file_offset = offsetof(struct hugetlb_cgroup, - events_local_file[idx]), + events_local_file[idx]); cft->flags = CFTYPE_NOT_ON_ROOT; /* NULL terminate the last cft */ diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 15a9af791014..e749e568e1ea 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -466,7 +466,7 @@ int __khugepaged_enter(struct mm_struct *mm) return -ENOMEM; /* __khugepaged_exit() must not run from under us */ - VM_BUG_ON_MM(khugepaged_test_exit(mm), mm); + VM_BUG_ON_MM(atomic_read(&mm->mm_users) == 0, mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) { free_mm_slot(mm_slot); return 0; diff --git a/mm/memory.c b/mm/memory.c index 3a7779d9891d..602f4283122f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4247,6 +4247,9 @@ static vm_fault_t handle_pte_fault(struct vm_fault *vmf) vmf->flags & FAULT_FLAG_WRITE)) { update_mmu_cache(vmf->vma, vmf->address, vmf->pte); } else { + /* Skip spurious TLB flush for retried page fault */ + if (vmf->flags & FAULT_FLAG_TRIED) + goto unlock; /* * This is needed only for protection faults but the arch code * is not yet telling us if this is a protection fault or not. diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0e2bab486fea..fab5e97dc9ca 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1302,6 +1302,11 @@ static void free_pcppages_bulk(struct zone *zone, int count, struct page *page, *tmp; LIST_HEAD(head); + /* + * Ensure proper count is passed which otherwise would stuck in the + * below while (list_empty(list)) loop. + */ + count = min(pcp->count, count); while (count) { struct list_head *list; @@ -7888,7 +7893,7 @@ int __meminit init_per_zone_wmark_min(void) return 0; } -core_initcall(init_per_zone_wmark_min) +postcore_initcall(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so diff --git a/mm/rodata_test.c b/mm/rodata_test.c index 2a99df7beeb3..2613371945b7 100644 --- a/mm/rodata_test.c +++ b/mm/rodata_test.c @@ -7,6 +7,7 @@ */ #define pr_fmt(fmt) "rodata_test: " fmt +#include <linux/rodata_test.h> #include <linux/uaccess.h> #include <asm/sections.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index b482d240f9a2..be4724b916b3 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -104,6 +104,8 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next, mask); + + cond_resched(); } while (pmd++, addr = next, addr != end); } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 1641f414d1ba..ebe33b60efd6 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2238,6 +2238,10 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, struct ebt_table *t; struct net *net = sock_net(sk); + if ((cmd == EBT_SO_GET_INFO || cmd == EBT_SO_GET_INIT_INFO) && + *len != sizeof(struct compat_ebt_replace)) + return -EINVAL; + if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 809673222382..8d033a75a766 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -168,6 +168,7 @@ static unsigned int nf_ct_br_defrag4(struct sk_buff *skb, static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, const struct nf_hook_state *state) { +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) u16 zone_id = NF_CT_DEFAULT_ZONE_ID; enum ip_conntrack_info ctinfo; struct br_input_skb_cb cb; @@ -180,14 +181,17 @@ static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm)); - err = nf_ipv6_br_defrag(state->net, skb, - IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); + err = nf_ct_frag6_gather(state->net, skb, + IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); /* queued */ if (err == -EINPROGRESS) return NF_STOLEN; br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size); return err == 0 ? NF_ACCEPT : NF_DROP; +#else + return NF_ACCEPT; +#endif } static int nf_ct_br_ip_check(const struct sk_buff *skb) diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 78ff9b3f1d40..b93876c57fc4 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -398,6 +398,7 @@ static int j1939_sk_init(struct sock *sk) spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); sk->sk_destruct = j1939_sk_sock_destruct; + sk->sk_protocol = CAN_J1939; return 0; } @@ -466,6 +467,14 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) goto out_release_sock; } + if (!ndev->ml_priv) { + netdev_warn_once(ndev, + "No CAN mid layer private allocated, please fix your driver and use alloc_candev()!\n"); + dev_put(ndev); + ret = -ENODEV; + goto out_release_sock; + } + priv = j1939_netdev_start(ndev); dev_put(ndev); if (IS_ERR(priv)) { @@ -553,6 +562,11 @@ static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr, static void j1939_sk_sock2sockaddr_can(struct sockaddr_can *addr, const struct j1939_sock *jsk, int peer) { + /* There are two holes (2 bytes and 3 bytes) to clear to avoid + * leaking kernel information to user space. + */ + memset(addr, 0, J1939_MIN_NAMELEN); + addr->can_family = AF_CAN; addr->can_ifindex = jsk->ifindex; addr->can_addr.j1939.pgn = jsk->addr.pgn; diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 9f99af5b0b11..a8dd956b5e8e 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -352,17 +352,16 @@ void j1939_session_skb_queue(struct j1939_session *session, skb_queue_tail(&session->skb_queue, skb); } -static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +static struct +sk_buff *j1939_session_skb_find_by_offset(struct j1939_session *session, + unsigned int offset_start) { struct j1939_priv *priv = session->priv; + struct j1939_sk_buff_cb *do_skcb; struct sk_buff *skb = NULL; struct sk_buff *do_skb; - struct j1939_sk_buff_cb *do_skcb; - unsigned int offset_start; unsigned long flags; - offset_start = session->pkt.dpo * 7; - spin_lock_irqsave(&session->skb_queue.lock, flags); skb_queue_walk(&session->skb_queue, do_skb) { do_skcb = j1939_skb_to_cb(do_skb); @@ -382,6 +381,14 @@ static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) return skb; } +static struct sk_buff *j1939_session_skb_find(struct j1939_session *session) +{ + unsigned int offset_start; + + offset_start = session->pkt.dpo * 7; + return j1939_session_skb_find_by_offset(session, offset_start); +} + /* see if we are receiver * returns 0 for broadcasts, although we will receive them */ @@ -716,10 +723,12 @@ static int j1939_session_tx_rts(struct j1939_session *session) return ret; session->last_txcmd = dat[0]; - if (dat[0] == J1939_TP_CMD_BAM) + if (dat[0] == J1939_TP_CMD_BAM) { j1939_tp_schedule_txtimer(session, 50); - - j1939_tp_set_rxtimeout(session, 1250); + j1939_tp_set_rxtimeout(session, 250); + } else { + j1939_tp_set_rxtimeout(session, 1250); + } netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session); @@ -766,7 +775,7 @@ static int j1939_session_tx_dat(struct j1939_session *session) int ret = 0; u8 dat[8]; - se_skb = j1939_session_skb_find(session); + se_skb = j1939_session_skb_find_by_offset(session, session->pkt.tx * 7); if (!se_skb) return -ENOBUFS; @@ -787,6 +796,18 @@ static int j1939_session_tx_dat(struct j1939_session *session) if (len > 7) len = 7; + if (offset + len > se_skb->len) { + netdev_err_once(priv->ndev, + "%s: 0x%p: requested data outside of queued buffer: offset %i, len %i, pkt.tx: %i\n", + __func__, session, skcb->offset, se_skb->len , session->pkt.tx); + return -EOVERFLOW; + } + + if (!len) { + ret = -ENOBUFS; + break; + } + memcpy(&dat[1], &tpdat[offset], len); ret = j1939_tp_tx_dat(session, dat, len + 1); if (ret < 0) { @@ -1055,9 +1076,9 @@ static void __j1939_session_cancel(struct j1939_session *session, lockdep_assert_held(&session->priv->active_session_list_lock); session->err = j1939_xtp_abort_to_errno(priv, err); + session->state = J1939_SESSION_WAITING_ABORT; /* do not send aborts on incoming broadcasts */ if (!j1939_cb_is_broadcast(&session->skcb)) { - session->state = J1939_SESSION_WAITING_ABORT; j1939_xtp_tx_abort(priv, &session->skcb, !session->transmission, err, session->skcb.addr.pgn); @@ -1120,6 +1141,9 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer) * cleanup including propagation of the error to user space. */ break; + case -EOVERFLOW: + j1939_session_cancel(session, J1939_XTP_ABORT_ECTS_TOO_BIG); + break; case 0: session->tx_retry = 0; break; @@ -1651,8 +1675,12 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, return; } session = j1939_xtp_rx_rts_session_new(priv, skb); - if (!session) + if (!session) { + if (cmd == J1939_TP_CMD_BAM && j1939_sk_recv_match(priv, skcb)) + netdev_info(priv->ndev, "%s: failed to create TP BAM session\n", + __func__); return; + } } else { if (j1939_xtp_rx_rts_session_active(session, skb)) { j1939_session_put(session); @@ -1661,11 +1689,15 @@ static void j1939_xtp_rx_rts(struct j1939_priv *priv, struct sk_buff *skb, } session->last_cmd = cmd; - j1939_tp_set_rxtimeout(session, 1250); - - if (cmd != J1939_TP_CMD_BAM && !session->transmission) { - j1939_session_txtimer_cancel(session); - j1939_tp_schedule_txtimer(session, 0); + if (cmd == J1939_TP_CMD_BAM) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); + } else { + if (!session->transmission) { + j1939_session_txtimer_cancel(session); + j1939_tp_schedule_txtimer(session, 0); + } + j1939_tp_set_rxtimeout(session, 1250); } j1939_session_put(session); @@ -1716,6 +1748,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, int offset; int nbytes; bool final = false; + bool remain = false; bool do_cts_eoma = false; int packet; @@ -1750,7 +1783,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, __func__, session); goto out_session_cancel; } - se_skb = j1939_session_skb_find(session); + + se_skb = j1939_session_skb_find_by_offset(session, packet * 7); if (!se_skb) { netdev_warn(priv->ndev, "%s: 0x%p: no skb found\n", __func__, session); @@ -1769,7 +1803,20 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } tpdat = se_skb->data; - memcpy(&tpdat[offset], &dat[1], nbytes); + if (!session->transmission) { + memcpy(&tpdat[offset], &dat[1], nbytes); + } else { + int err; + + err = memcmp(&tpdat[offset], &dat[1], nbytes); + if (err) + netdev_err_once(priv->ndev, + "%s: 0x%p: Data of RX-looped back packet (%*ph) doesn't match TX data (%*ph)!\n", + __func__, session, + nbytes, &dat[1], + nbytes, &tpdat[offset]); + } + if (packet == session->pkt.rx) session->pkt.rx++; @@ -1777,6 +1824,8 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, j1939_cb_is_broadcast(&session->skcb)) { if (session->pkt.rx >= session->pkt.total) final = true; + else + remain = true; } else { /* never final, an EOMA must follow */ if (session->pkt.rx >= session->pkt.last) @@ -1784,7 +1833,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session, } if (final) { + j1939_session_timers_cancel(session); j1939_session_completed(session); + } else if (remain) { + if (!session->transmission) + j1939_tp_set_rxtimeout(session, 750); } else if (do_cts_eoma) { j1939_tp_set_rxtimeout(session, 1250); if (!session->transmission) @@ -1829,6 +1882,13 @@ static void j1939_xtp_rx_dat(struct j1939_priv *priv, struct sk_buff *skb) else j1939_xtp_rx_dat_one(session, skb); } + + if (j1939_cb_is_broadcast(skcb)) { + session = j1939_session_get_by_addr(priv, &skcb->addr, false, + false); + if (session) + j1939_xtp_rx_dat_one(session, skb); + } } /* j1939 main intf */ @@ -1920,7 +1980,7 @@ static void j1939_tp_cmd_recv(struct j1939_priv *priv, struct sk_buff *skb) if (j1939_tp_im_transmitter(skcb)) j1939_xtp_rx_rts(priv, skb, true); - if (j1939_tp_im_receiver(skcb)) + if (j1939_tp_im_receiver(skcb) || j1939_cb_is_broadcast(skcb)) j1939_xtp_rx_rts(priv, skb, false); break; @@ -1984,7 +2044,7 @@ int j1939_tp_recv(struct j1939_priv *priv, struct sk_buff *skb) { struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb); - if (!j1939_tp_im_involved_anydir(skcb)) + if (!j1939_tp_im_involved_anydir(skcb) && !j1939_cb_is_broadcast(skcb)) return 0; switch (skcb->addr.pgn) { @@ -2017,6 +2077,10 @@ void j1939_simple_recv(struct j1939_priv *priv, struct sk_buff *skb) if (!skb->sk) return; + if (skb->sk->sk_family != AF_CAN || + skb->sk->sk_protocol != CAN_J1939) + return; + j1939_session_list_lock(priv); session = j1939_session_get_simple(priv, skb); j1939_session_list_unlock(priv); diff --git a/net/core/dev.c b/net/core/dev.c index 7df6c9617321..d42c9ea0c3c0 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8742,13 +8742,15 @@ struct bpf_xdp_link { int flags; }; -static enum bpf_xdp_mode dev_xdp_mode(u32 flags) +static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; - return XDP_MODE_SKB; + if (flags & XDP_FLAGS_SKB_MODE) + return XDP_MODE_SKB; + return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) @@ -8896,7 +8898,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack return -EINVAL; } - mode = dev_xdp_mode(flags); + mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); @@ -8913,10 +8915,6 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } - if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { - NL_SET_ERR_MSG(extack, "XDP program already attached"); - return -EBUSY; - } /* put effective new program into new_prog */ if (link) @@ -8927,6 +8925,10 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; + if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { + NL_SET_ERR_MSG(extack, "XDP program already attached"); + return -EBUSY; + } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; @@ -8984,7 +8986,7 @@ static int dev_xdp_detach_link(struct net_device *dev, ASSERT_RTNL(); - mode = dev_xdp_mode(link->flags); + mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; @@ -9080,7 +9082,7 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, goto out_unlock; } - mode = dev_xdp_mode(xdp_link->flags); + mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); @@ -9164,7 +9166,7 @@ out_put_dev: int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { - enum bpf_xdp_mode mode = dev_xdp_mode(flags); + enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; diff --git a/net/core/devlink.c b/net/core/devlink.c index e674f0f46dc2..e5feb87beca7 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4063,7 +4063,7 @@ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) { lockdep_assert_held(&devlink->lock); - if (WARN_ON(xa_load(&devlink->snapshot_ids, id))) + if (xa_load(&devlink->snapshot_ids, id)) return -EEXIST; return xa_err(xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), diff --git a/net/core/filter.c b/net/core/filter.c index 7124f0fe6974..b2df52086445 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8317,15 +8317,31 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ + int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 2; \ BUILD_BUG_ON(sizeof_field(OBJ, OBJ_FIELD) > \ sizeof_field(struct bpf_sock_ops, BPF_FIELD)); \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + fullsock_reg = reg; \ + jmp += 2; \ + } \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ - si->dst_reg, si->src_reg, \ + fullsock_reg, si->src_reg, \ offsetof(struct bpf_sock_ops_kern, \ is_fullsock)); \ - *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ + if (si->dst_reg == si->src_reg) \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, sk),\ si->dst_reg, si->src_reg, \ @@ -8334,6 +8350,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, OBJ_FIELD), \ si->dst_reg, si->dst_reg, \ offsetof(OBJ, OBJ_FIELD)); \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_JMP_A(1); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } \ + } while (0) + +#define SOCK_OPS_GET_SK() \ + do { \ + int fullsock_reg = si->dst_reg, reg = BPF_REG_9, jmp = 1; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_STX_MEM(BPF_DW, si->src_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + fullsock_reg = reg; \ + jmp += 2; \ + } \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, \ + is_fullsock), \ + fullsock_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + is_fullsock)); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp); \ + if (si->dst_reg == si->src_reg) \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, sk),\ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, sk));\ + if (si->dst_reg == si->src_reg) { \ + *insn++ = BPF_JMP_A(1); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } \ } while (0) #define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ @@ -8620,17 +8679,7 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); break; case offsetof(struct bpf_sock_ops, sk): - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, - is_fullsock), - si->dst_reg, si->src_reg, - offsetof(struct bpf_sock_ops_kern, - is_fullsock)); - *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( - struct bpf_sock_ops_kern, sk), - si->dst_reg, si->src_reg, - offsetof(struct bpf_sock_ops_kern, sk)); + SOCK_OPS_GET_SK(); break; } return insn - insn_buf; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7e2e502ef519..e18184ffa9c3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5418,8 +5418,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb) skb = skb_share_check(skb, GFP_ATOMIC); if (unlikely(!skb)) goto err_free; - - if (unlikely(!pskb_may_pull(skb, VLAN_HLEN))) + /* We may access the two bytes after vlan_hdr in vlan_set_encap_proto(). */ + if (unlikely(!pskb_may_pull(skb, VLAN_HLEN + sizeof(unsigned short)))) goto err_free; vhdr = (struct vlan_hdr *)skb->data; @@ -5987,9 +5987,13 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, if (skb_has_frag_list(skb)) skb_clone_fraglist(skb); - if (k == 0) { - /* split line is in frag list */ - pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask); + /* split line is in frag list */ + if (k == 0 && pskb_carve_frag_list(skb, shinfo, off - pos, gfp_mask)) { + /* skb_frag_unref() is not needed here as shinfo->nr_frags = 0. */ + if (skb_has_frag_list(skb)) + kfree_skb_list(skb_shinfo(skb)->frag_list); + kfree(data); + return -ENOMEM; } skb_release_data(skb); diff --git a/net/ethtool/features.c b/net/ethtool/features.c index 4e632dc987d8..495635f152ba 100644 --- a/net/ethtool/features.c +++ b/net/ethtool/features.c @@ -224,7 +224,9 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) DECLARE_BITMAP(wanted_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(active_diff_mask, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(old_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(old_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(new_active, NETDEV_FEATURE_COUNT); + DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT); DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT); struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1]; @@ -250,6 +252,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) rtnl_lock(); ethnl_features_to_bitmap(old_active, dev->features); + ethnl_features_to_bitmap(old_wanted, dev->wanted_features); ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT, tb[ETHTOOL_A_FEATURES_WANTED], netdev_features_strings, info->extack); @@ -261,17 +264,15 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info) goto out_rtnl; } - /* set req_wanted bits not in req_mask from old_active */ + /* set req_wanted bits not in req_mask from old_wanted */ bitmap_and(req_wanted, req_wanted, req_mask, NETDEV_FEATURE_COUNT); - bitmap_andnot(new_active, old_active, req_mask, NETDEV_FEATURE_COUNT); - bitmap_or(req_wanted, new_active, req_wanted, NETDEV_FEATURE_COUNT); - if (bitmap_equal(req_wanted, old_active, NETDEV_FEATURE_COUNT)) { - ret = 0; - goto out_rtnl; + bitmap_andnot(new_wanted, old_wanted, req_mask, NETDEV_FEATURE_COUNT); + bitmap_or(req_wanted, new_wanted, req_wanted, NETDEV_FEATURE_COUNT); + if (!bitmap_equal(req_wanted, old_wanted, NETDEV_FEATURE_COUNT)) { + dev->wanted_features &= ~dev->hw_features; + dev->wanted_features |= ethnl_bitmap_to_features(req_wanted) & dev->hw_features; + __netdev_update_features(dev); } - - dev->wanted_features = ethnl_bitmap_to_features(req_wanted); - __netdev_update_features(dev); ethnl_features_to_bitmap(new_active, dev->features); mod = !bitmap_equal(old_active, new_active, NETDEV_FEATURE_COUNT); diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 60db5a6487cc..87983e70f03f 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -661,13 +661,13 @@ config TCP_CONG_BBR BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to maximize network utilization and minimize queues. It builds an explicit - model of the the bottleneck delivery rate and path round-trip - propagation delay. It tolerates packet loss and delay unrelated to - congestion. It can operate over LAN, WAN, cellular, wifi, or cable - modem links. It can coexist with flows that use loss-based congestion - control, and can operate with shallow buffers, deep buffers, - bufferbloat, policers, or AQM schemes that do not provide a delay - signal. It requires the fq ("Fair Queue") pacing packet scheduler. + model of the bottleneck delivery rate and path round-trip propagation + delay. It tolerates packet loss and delay unrelated to congestion. It + can operate over LAN, WAN, cellular, wifi, or cable modem links. It can + coexist with flows that use loss-based congestion control, and can + operate with shallow buffers, deep buffers, bufferbloat, policers, or + AQM schemes that do not provide a delay signal. It requires the fq + ("Fair Queue") pacing packet scheduler. choice prompt "Default TCP congestion control" diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index cc8049b100b2..134e92382275 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -446,7 +446,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[], unsigned int i, j; u8 nhg_fdb = 0; - if (len & (sizeof(struct nexthop_grp) - 1)) { + if (!len || len & (sizeof(struct nexthop_grp) - 1)) { NL_SET_ERR_MSG(extack, "Invalid length for nexthop group attribute"); return -EINVAL; @@ -1187,6 +1187,9 @@ static struct nexthop *nexthop_create_group(struct net *net, struct nexthop *nh; int i; + if (WARN_ON(!num_nh)) + return ERR_PTR(-EINVAL); + nh = nexthop_alloc(); if (!nh) return ERR_PTR(-ENOMEM); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 8e761b8c47c6..01146b66d666 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1893,12 +1893,13 @@ EXPORT_SYMBOL(ipv6_chk_addr); * 2. does the address exist on the specific device * (skip_dev_check = false) */ -int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, - const struct net_device *dev, bool skip_dev_check, - int strict, u32 banned_flags) +static struct net_device * +__ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, bool skip_dev_check, + int strict, u32 banned_flags) { unsigned int hash = inet6_addr_hash(net, addr); - const struct net_device *l3mdev; + struct net_device *l3mdev, *ndev; struct inet6_ifaddr *ifp; u32 ifp_flags; @@ -1909,10 +1910,11 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, dev = NULL; hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (!net_eq(dev_net(ifp->idev->dev), net)) + ndev = ifp->idev->dev; + if (!net_eq(dev_net(ndev), net)) continue; - if (l3mdev_master_dev_rcu(ifp->idev->dev) != l3mdev) + if (l3mdev_master_dev_rcu(ndev) != l3mdev) continue; /* Decouple optimistic from tentative for evaluation here. @@ -1923,15 +1925,23 @@ int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, : ifp->flags; if (ipv6_addr_equal(&ifp->addr, addr) && !(ifp_flags&banned_flags) && - (!dev || ifp->idev->dev == dev || + (!dev || ndev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict))) { rcu_read_unlock(); - return 1; + return ndev; } } rcu_read_unlock(); - return 0; + return NULL; +} + +int ipv6_chk_addr_and_flags(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, bool skip_dev_check, + int strict, u32 banned_flags) +{ + return __ipv6_chk_addr_and_flags(net, addr, dev, skip_dev_check, + strict, banned_flags) ? 1 : 0; } EXPORT_SYMBOL(ipv6_chk_addr_and_flags); @@ -1990,35 +2000,11 @@ EXPORT_SYMBOL(ipv6_chk_prefix); * * The caller should be protected by RCU, or RTNL. */ -struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr) +struct net_device *ipv6_dev_find(struct net *net, const struct in6_addr *addr, + struct net_device *dev) { - unsigned int hash = inet6_addr_hash(net, addr); - struct inet6_ifaddr *ifp, *result = NULL; - struct net_device *dev = NULL; - - rcu_read_lock(); - hlist_for_each_entry_rcu(ifp, &inet6_addr_lst[hash], addr_lst) { - if (net_eq(dev_net(ifp->idev->dev), net) && - ipv6_addr_equal(&ifp->addr, addr)) { - result = ifp; - break; - } - } - - if (!result) { - struct rt6_info *rt; - - rt = rt6_lookup(net, addr, NULL, 0, NULL, 0); - if (rt) { - dev = rt->dst.dev; - ip6_rt_put(rt); - } - } else { - dev = result->idev->dev; - } - rcu_read_unlock(); - - return dev; + return __ipv6_chk_addr_and_flags(net, addr, dev, !dev, 1, + IFA_F_TENTATIVE); } EXPORT_SYMBOL(ipv6_dev_find); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index f635914f42ec..a0217e5bf3bc 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -915,7 +915,15 @@ int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb, struct metadata_dst *tun_dst, bool log_ecn_err) { - return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate, + int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, + const struct ipv6hdr *ipv6h, + struct sk_buff *skb); + + dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate; + if (tpi->proto == htons(ETH_P_IP)) + dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate; + + return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 409e79b84a83..6d0e942d082d 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = { .route_input = ip6_route_input, .fragment = ip6_fragment, .reroute = nf_ip6_reroute, -#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - .br_defrag = nf_ct_frag6_gather, -#endif #if IS_MODULE(CONFIG_IPV6) .br_fragment = br_ip6_fragment, #endif diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8c1d1a595701..1aad411a0e46 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -725,8 +725,10 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, if (!psize) return -EINVAL; - if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) + if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) { + iov_iter_revert(&msg->msg_iter, psize); return -ENOMEM; + } } else { offset = dfrag->offset; psize = min_t(size_t, dfrag->data_len, avail_size); @@ -737,8 +739,11 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, */ ret = do_tcp_sendpages(ssk, page, offset, psize, msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT); - if (ret <= 0) + if (ret <= 0) { + if (!retransmission) + iov_iter_revert(&msg->msg_iter, psize); return ret; + } frag_truesize += ret; if (!retransmission) { @@ -1388,7 +1393,9 @@ static void mptcp_worker(struct work_struct *work) struct mptcp_data_frag *dfrag; u64 orig_write_seq; size_t copied = 0; - struct msghdr msg; + struct msghdr msg = { + .msg_flags = MSG_DONTWAIT, + }; long timeo = 0; lock_sock(sk); @@ -1421,7 +1428,6 @@ static void mptcp_worker(struct work_struct *work) lock_sock(ssk); - msg.msg_flags = MSG_DONTWAIT; orig_len = dfrag->data_len; orig_offset = dfrag->offset; orig_write_seq = dfrag->data_seq; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d878e34e3354..fd814e514f94 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2018,8 +2018,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nla[NFTA_CHAIN_NAME]) { chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); } else { - if (!(flags & NFT_CHAIN_BINDING)) - return -EINVAL; + if (!(flags & NFT_CHAIN_BINDING)) { + err = -EINVAL; + goto err1; + } snprintf(name, sizeof(name), "__chain%llu", ++chain_id); chain->name = kstrdup(name, GFP_KERNEL); diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6428856ccbec..8e56f353ff35 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -27,8 +27,6 @@ struct nft_xt_match_priv { void *info; }; -static refcount_t nft_compat_pending_destroy = REFCOUNT_INIT(1); - static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { @@ -215,6 +213,17 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return 0; } +static void nft_compat_wait_for_destructors(void) +{ + /* xtables matches or targets can have side effects, e.g. + * creation/destruction of /proc files. + * The xt ->destroy functions are run asynchronously from + * work queue. If we have pending invocations we thus + * need to wait for those to finish. + */ + nf_tables_trans_destroy_flush_work(); +} + static int nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -238,14 +247,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); - /* xtables matches or targets can have side effects, e.g. - * creation/destruction of /proc files. - * The xt ->destroy functions are run asynchronously from - * work queue. If we have pending invocations we thus - * need to wait for those to finish. - */ - if (refcount_read(&nft_compat_pending_destroy) > 1) - nf_tables_trans_destroy_flush_work(); + nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); if (ret < 0) @@ -260,7 +262,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, static void __nft_mt_tg_destroy(struct module *me, const struct nft_expr *expr) { - refcount_dec(&nft_compat_pending_destroy); module_put(me); kfree(expr->ops); } @@ -468,6 +469,8 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); + nft_compat_wait_for_destructors(); + return xt_check_match(&par, size, proto, inv); } @@ -716,14 +719,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { static struct nft_expr_type nft_match_type; -static void nft_mt_tg_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - enum nft_trans_phase phase) -{ - if (phase == NFT_TRANS_COMMIT) - refcount_inc(&nft_compat_pending_destroy); -} - static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -762,7 +757,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, ops->type = &nft_match_type; ops->eval = nft_match_eval; ops->init = nft_match_init; - ops->deactivate = nft_mt_tg_deactivate, ops->destroy = nft_match_destroy; ops->dump = nft_match_dump; ops->validate = nft_match_validate; @@ -853,7 +847,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); ops->init = nft_target_init; ops->destroy = nft_target_destroy; - ops->deactivate = nft_mt_tg_deactivate, ops->dump = nft_target_dump; ops->validate = nft_target_validate; ops->data = target; @@ -917,8 +910,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - - WARN_ON_ONCE(refcount_read(&nft_compat_pending_destroy) != 1); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 07782836fad6..3c48cdc8935d 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -44,7 +44,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; @@ -141,7 +141,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr, err = ipv4_find_option(nft_net(pkt), skb, &offset, priv->type); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index f6491853c797..2b3e26f7496f 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -51,6 +51,9 @@ static int add_policy(struct nl_policy_dump **statep, if (!state) return -ENOMEM; + memset(&state->policies[state->n_alloc], 0, + flex_array_size(state, policies, n_alloc - state->n_alloc)); + state->policies[state->n_alloc].policy = policy; state->policies[state->n_alloc].maxtype = maxtype; state->n_alloc = n_alloc; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index b4c0db0b7d31..90c558f89d46 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -692,23 +692,25 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) */ static int qrtr_port_assign(struct qrtr_sock *ipc, int *port) { + u32 min_port; int rc; mutex_lock(&qrtr_port_lock); if (!*port) { - rc = idr_alloc(&qrtr_ports, ipc, - QRTR_MIN_EPH_SOCKET, QRTR_MAX_EPH_SOCKET + 1, - GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = QRTR_MIN_EPH_SOCKET; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, QRTR_MAX_EPH_SOCKET, GFP_ATOMIC); + if (!rc) + *port = min_port; } else if (*port < QRTR_MIN_EPH_SOCKET && !capable(CAP_NET_ADMIN)) { rc = -EACCES; } else if (*port == QRTR_PORT_CTRL) { - rc = idr_alloc(&qrtr_ports, ipc, 0, 1, GFP_ATOMIC); + min_port = 0; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, 0, GFP_ATOMIC); } else { - rc = idr_alloc(&qrtr_ports, ipc, *port, *port + 1, GFP_ATOMIC); - if (rc >= 0) - *port = rc; + min_port = *port; + rc = idr_alloc_u32(&qrtr_ports, ipc, &min_port, *port, GFP_ATOMIC); + if (!rc) + *port = min_port; } mutex_unlock(&qrtr_port_lock); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index e6ad42b11835..2c3619165680 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -704,7 +704,7 @@ static int tcf_ct_handle_fragments(struct net *net, struct sk_buff *skb, err = ip_defrag(net, skb, user); local_bh_enable(); if (err && err != -EINPROGRESS) - goto out_free; + return err; if (!err) { *defrag = true; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index bda2536dd740..6dc95dcc0ff4 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -88,12 +88,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, int ret; if (outcnt <= stream->outcnt) - return 0; + goto out; ret = genradix_prealloc(&stream->out, outcnt, gfp); if (ret) return ret; +out: stream->outcnt = outcnt; return 0; } @@ -104,12 +105,13 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, int ret; if (incnt <= stream->incnt) - return 0; + goto out; ret = genradix_prealloc(&stream->in, incnt, gfp); if (ret) return ret; +out: stream->incnt = incnt; return 0; } diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index e1f64f4ba236..da9ba6d1679b 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -170,13 +170,15 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && !list_empty(&smc->conn.lgr->list)) { struct smc_connection *conn = &smc->conn; - struct smcd_diag_dmbinfo dinfo = { - .linkid = *((u32 *)conn->lgr->id), - .peer_gid = conn->lgr->peer_gid, - .my_gid = conn->lgr->smcd->local_gid, - .token = conn->rmb_desc->token, - .peer_token = conn->peer_token - }; + struct smcd_diag_dmbinfo dinfo; + + memset(&dinfo, 0, sizeof(dinfo)); + + dinfo.linkid = *((u32 *)conn->lgr->id); + dinfo.peer_gid = conn->lgr->peer_gid; + dinfo.my_gid = conn->lgr->smcd->local_gid; + dinfo.token = conn->rmb_desc->token; + dinfo.peer_token = conn->peer_token; if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0) goto errout; diff --git a/net/tipc/Kconfig b/net/tipc/Kconfig index 9dd780215eef..be1c4003d67d 100644 --- a/net/tipc/Kconfig +++ b/net/tipc/Kconfig @@ -6,6 +6,7 @@ menuconfig TIPC tristate "The TIPC Protocol" depends on INET + depends on IPV6 || IPV6=n help The Transparent Inter Process Communication (TIPC) protocol is specially designed for intra cluster communication. This protocol diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index 001bcb0f2480..c38babaa4e57 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -757,10 +757,12 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err) switch (err) { case 0: this_cpu_inc(tx->stats->stat[STAT_ASYNC_OK]); + rcu_read_lock(); if (likely(test_bit(0, &b->up))) b->media->send_msg(net, skb, b, &tx_ctx->dst); else kfree_skb(skb); + rcu_read_unlock(); break; case -EINPROGRESS: return; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 217516357ef2..90e3c70a91ad 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -275,8 +275,9 @@ err_out: static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, struct tipc_nl_compat_msg *msg) { - int err; + struct nlmsghdr *nlh; struct sk_buff *arg; + int err; if (msg->req_type && (!msg->req_size || !TLV_CHECK_TYPE(msg->req, msg->req_type))) @@ -305,6 +306,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; } + nlh = nlmsg_put(arg, 0, 0, tipc_genl_family.id, 0, NLM_F_MULTI); + if (!nlh) { + kfree_skb(arg); + kfree_skb(msg->rep); + msg->rep = NULL; + return -EMSGSIZE; + } + nlmsg_end(arg, nlh); + err = __tipc_nl_compat_dumpit(cmd, msg, arg); if (err) { kfree_skb(msg->rep); diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 53f0de0676b7..911d13cd2e67 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -660,6 +660,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, struct udp_tunnel_sock_cfg tuncfg = {NULL}; struct nlattr *opts[TIPC_NLA_UDP_MAX + 1]; u8 node_id[NODE_ID_LEN] = {0,}; + struct net_device *dev; int rmcast = 0; ub = kzalloc(sizeof(*ub), GFP_ATOMIC); @@ -714,8 +715,6 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, rcu_assign_pointer(ub->bearer, b); tipc_udp_media_addr_set(&b->addr, &local); if (local.proto == htons(ETH_P_IP)) { - struct net_device *dev; - dev = __ip_dev_find(net, local.ipv4.s_addr, false); if (!dev) { err = -ENODEV; @@ -738,9 +737,8 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, b->mtu = b->media->mtu; #if IS_ENABLED(CONFIG_IPV6) } else if (local.proto == htons(ETH_P_IPV6)) { - struct net_device *dev; - - dev = ipv6_dev_find(net, &local.ipv6); + dev = ub->ifindex ? __dev_get_by_index(net, ub->ifindex) : NULL; + dev = ipv6_dev_find(net, &local.ipv6, dev); if (!dev) { err = -ENODEV; goto err; diff --git a/scripts/Makefile.extrawarn b/scripts/Makefile.extrawarn index 62c275685b75..95e4cdb94fe9 100644 --- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -66,7 +66,6 @@ KBUILD_CFLAGS += -Wnested-externs KBUILD_CFLAGS += -Wshadow KBUILD_CFLAGS += $(call cc-option, -Wlogical-op) KBUILD_CFLAGS += -Wmissing-field-initializers -KBUILD_CFLAGS += -Wsign-compare KBUILD_CFLAGS += -Wtype-limits KBUILD_CFLAGS += $(call cc-option, -Wmaybe-uninitialized) KBUILD_CFLAGS += $(call cc-option, -Wunused-macros) @@ -87,6 +86,7 @@ KBUILD_CFLAGS += -Wpacked KBUILD_CFLAGS += -Wpadded KBUILD_CFLAGS += -Wpointer-arith KBUILD_CFLAGS += -Wredundant-decls +KBUILD_CFLAGS += -Wsign-compare KBUILD_CFLAGS += -Wswitch-default KBUILD_CFLAGS += $(call cc-option, -Wpacked-bitfield-compat) diff --git a/scripts/extract-cert.c b/scripts/extract-cert.c index b071bf476fea..3bc48c726c41 100644 --- a/scripts/extract-cert.c +++ b/scripts/extract-cert.c @@ -71,7 +71,7 @@ static void drain_openssl_errors(void) static const char *key_pass; static BIO *wb; static char *cert_dst; -int kbuild_verbose; +static int kbuild_verbose; static void write_cert(X509 *x509) { diff --git a/scripts/genksyms/keywords.c b/scripts/genksyms/keywords.c index 7a85c4e21175..057c6cabad1d 100644 --- a/scripts/genksyms/keywords.c +++ b/scripts/genksyms/keywords.c @@ -25,9 +25,9 @@ static struct resword { { "__int128_t", BUILTIN_INT_KEYW }, { "__uint128_t", BUILTIN_INT_KEYW }, - // According to rth, c99 defines "_Bool", __restrict", __restrict__", "restrict". KAO + // According to rth, c99 defines "_Bool", "__restrict", "__restrict__", "restrict". KAO { "_Bool", BOOL_KEYW }, - { "_restrict", RESTRICT_KEYW }, + { "__restrict", RESTRICT_KEYW }, { "__restrict__", RESTRICT_KEYW }, { "restrict", RESTRICT_KEYW }, { "asm", ASM_KEYW }, diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc index bc390df49f1f..8638785328a7 100644 --- a/scripts/kconfig/qconf.cc +++ b/scripts/kconfig/qconf.cc @@ -885,7 +885,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowName(bool))); connect(parent(), SIGNAL(showNameChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showName); headerPopup->addAction(action); @@ -894,7 +894,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowRange(bool))); connect(parent(), SIGNAL(showRangeChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showRange); headerPopup->addAction(action); @@ -903,7 +903,7 @@ void ConfigList::contextMenuEvent(QContextMenuEvent *e) connect(action, SIGNAL(toggled(bool)), parent(), SLOT(setShowData(bool))); connect(parent(), SIGNAL(showDataChanged(bool)), - action, SLOT(setOn(bool))); + action, SLOT(setChecked(bool))); action->setChecked(showData); headerPopup->addAction(action); } @@ -1012,6 +1012,16 @@ ConfigInfoView::ConfigInfoView(QWidget* parent, const char *name) configSettings->endGroup(); connect(configApp, SIGNAL(aboutToQuit()), SLOT(saveSettings())); } + + contextMenu = createStandardContextMenu(); + QAction *action = new QAction("Show Debug Info", contextMenu); + + action->setCheckable(true); + connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); + connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setChecked(bool))); + action->setChecked(showDebug()); + contextMenu->addSeparator(); + contextMenu->addAction(action); } void ConfigInfoView::saveSettings(void) @@ -1066,80 +1076,80 @@ void ConfigInfoView::symbolInfo(void) void ConfigInfoView::menuInfo(void) { struct symbol* sym; - QString head, debug, help; + QString info; + QTextStream stream(&info); sym = _menu->sym; if (sym) { if (_menu->prompt) { - head += "<big><b>"; - head += print_filter(_menu->prompt->text); - head += "</b></big>"; + stream << "<big><b>"; + stream << print_filter(_menu->prompt->text); + stream << "</b></big>"; if (sym->name) { - head += " ("; + stream << " ("; if (showDebug()) - head += QString().sprintf("<a href=\"s%s\">", sym->name); - head += print_filter(sym->name); + stream << "<a href=\"s" << sym->name << "\">"; + stream << print_filter(sym->name); if (showDebug()) - head += "</a>"; - head += ")"; + stream << "</a>"; + stream << ")"; } } else if (sym->name) { - head += "<big><b>"; + stream << "<big><b>"; if (showDebug()) - head += QString().sprintf("<a href=\"s%s\">", sym->name); - head += print_filter(sym->name); + stream << "<a href=\"s" << sym->name << "\">"; + stream << print_filter(sym->name); if (showDebug()) - head += "</a>"; - head += "</b></big>"; + stream << "</a>"; + stream << "</b></big>"; } - head += "<br><br>"; + stream << "<br><br>"; if (showDebug()) - debug = debug_info(sym); + stream << debug_info(sym); - struct gstr help_gstr = str_new(); - menu_get_ext_help(_menu, &help_gstr); - help = print_filter(str_get(&help_gstr)); - str_free(&help_gstr); } else if (_menu->prompt) { - head += "<big><b>"; - head += print_filter(_menu->prompt->text); - head += "</b></big><br><br>"; + stream << "<big><b>"; + stream << print_filter(_menu->prompt->text); + stream << "</b></big><br><br>"; if (showDebug()) { if (_menu->prompt->visible.expr) { - debug += " dep: "; - expr_print(_menu->prompt->visible.expr, expr_print_help, &debug, E_NONE); - debug += "<br><br>"; + stream << " dep: "; + expr_print(_menu->prompt->visible.expr, + expr_print_help, &stream, E_NONE); + stream << "<br><br>"; } } } if (showDebug()) - debug += QString().sprintf("defined at %s:%d<br><br>", _menu->file->name, _menu->lineno); + stream << "defined at " << _menu->file->name << ":" + << _menu->lineno << "<br><br>"; - setText(head + debug + help); + setText(info); } QString ConfigInfoView::debug_info(struct symbol *sym) { QString debug; + QTextStream stream(&debug); - debug += "type: "; - debug += print_filter(sym_type_name(sym->type)); + stream << "type: "; + stream << print_filter(sym_type_name(sym->type)); if (sym_is_choice(sym)) - debug += " (choice)"; + stream << " (choice)"; debug += "<br>"; if (sym->rev_dep.expr) { - debug += "reverse dep: "; - expr_print(sym->rev_dep.expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << "reverse dep: "; + expr_print(sym->rev_dep.expr, expr_print_help, &stream, E_NONE); + stream << "<br>"; } for (struct property *prop = sym->prop; prop; prop = prop->next) { switch (prop->type) { case P_PROMPT: case P_MENU: - debug += QString().sprintf("prompt: <a href=\"m%s\">", sym->name); - debug += print_filter(prop->text); - debug += "</a><br>"; + stream << "prompt: <a href=\"m" << sym->name << "\">"; + stream << print_filter(prop->text); + stream << "</a><br>"; break; case P_DEFAULT: case P_SELECT: @@ -1147,30 +1157,33 @@ QString ConfigInfoView::debug_info(struct symbol *sym) case P_COMMENT: case P_IMPLY: case P_SYMBOL: - debug += prop_get_type_name(prop->type); - debug += ": "; - expr_print(prop->expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << prop_get_type_name(prop->type); + stream << ": "; + expr_print(prop->expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; break; case P_CHOICE: if (sym_is_choice(sym)) { - debug += "choice: "; - expr_print(prop->expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << "choice: "; + expr_print(prop->expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; } break; default: - debug += "unknown property: "; - debug += prop_get_type_name(prop->type); - debug += "<br>"; + stream << "unknown property: "; + stream << prop_get_type_name(prop->type); + stream << "<br>"; } if (prop->visible.expr) { - debug += " dep: "; - expr_print(prop->visible.expr, expr_print_help, &debug, E_NONE); - debug += "<br>"; + stream << " dep: "; + expr_print(prop->visible.expr, expr_print_help, + &stream, E_NONE); + stream << "<br>"; } } - debug += "<br>"; + stream << "<br>"; return debug; } @@ -1208,15 +1221,15 @@ QString ConfigInfoView::print_filter(const QString &str) void ConfigInfoView::expr_print_help(void *data, struct symbol *sym, const char *str) { - QString* text = reinterpret_cast<QString*>(data); - QString str2 = print_filter(str); + QTextStream *stream = reinterpret_cast<QTextStream *>(data); if (sym && sym->name && !(sym->flags & SYMBOL_CONST)) { - *text += QString().sprintf("<a href=\"s%s\">", sym->name); - *text += str2; - *text += "</a>"; - } else - *text += str2; + *stream << "<a href=\"s" << sym->name << "\">"; + *stream << print_filter(str); + *stream << "</a>"; + } else { + *stream << print_filter(str); + } } void ConfigInfoView::clicked(const QUrl &url) @@ -1228,7 +1241,6 @@ void ConfigInfoView::clicked(const QUrl &url) struct menu *m = NULL; if (count < 1) { - qInfo() << "Clicked link is empty"; delete[] data; return; } @@ -1241,7 +1253,6 @@ void ConfigInfoView::clicked(const QUrl &url) strcat(data, "$"); result = sym_re_search(data); if (!result) { - qInfo() << "Clicked symbol is invalid:" << data; delete[] data; return; } @@ -1268,23 +1279,10 @@ void ConfigInfoView::clicked(const QUrl &url) delete data; } -QMenu* ConfigInfoView::createStandardContextMenu(const QPoint & pos) -{ - QMenu* popup = Parent::createStandardContextMenu(pos); - QAction* action = new QAction("Show Debug Info", popup); - - action->setCheckable(true); - connect(action, SIGNAL(toggled(bool)), SLOT(setShowDebug(bool))); - connect(this, SIGNAL(showDebugChanged(bool)), action, SLOT(setOn(bool))); - action->setChecked(showDebug()); - popup->addSeparator(); - popup->addAction(action); - return popup; -} - -void ConfigInfoView::contextMenuEvent(QContextMenuEvent *e) +void ConfigInfoView::contextMenuEvent(QContextMenuEvent *event) { - Parent::contextMenuEvent(e); + contextMenu->popup(event->globalPos()); + event->accept(); } ConfigSearchWindow::ConfigSearchWindow(ConfigMainWindow *parent) diff --git a/scripts/kconfig/qconf.h b/scripts/kconfig/qconf.h index 461df6419f15..f97376a8123f 100644 --- a/scripts/kconfig/qconf.h +++ b/scripts/kconfig/qconf.h @@ -30,7 +30,7 @@ public: }; enum colIdx { - promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx, colNr + promptColIdx, nameColIdx, noColIdx, modColIdx, yesColIdx, dataColIdx }; enum listMode { singleMode, menuMode, symbolMode, fullMode, listMode @@ -215,6 +215,7 @@ public: class ConfigInfoView : public QTextBrowser { Q_OBJECT typedef class QTextBrowser Parent; + QMenu *contextMenu; public: ConfigInfoView(QWidget* parent, const char *name = 0); bool showDebug(void) const { return _showDebug; } @@ -235,8 +236,7 @@ protected: QString debug_info(struct symbol *sym); static QString print_filter(const QString &str); static void expr_print_help(void *data, struct symbol *sym, const char *str); - QMenu *createStandardContextMenu(const QPoint & pos); - void contextMenuEvent(QContextMenuEvent *e); + void contextMenuEvent(QContextMenuEvent *event); struct symbol *sym; struct menu *_menu; diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c index 09ddab5f5cae..9766f6af8743 100644 --- a/sound/hda/hdac_bus.c +++ b/sound/hda/hdac_bus.c @@ -46,6 +46,18 @@ int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev, INIT_LIST_HEAD(&bus->hlink_list); init_waitqueue_head(&bus->rirb_wq); bus->irq = -1; + + /* + * Default value of '8' is as per the HD audio specification (Rev 1.0a). + * Following relation is used to derive STRIPE control value. + * For sample rate <= 48K: + * { ((num_channels * bits_per_sample) / number of SDOs) >= 8 } + * For sample rate > 48K: + * { ((num_channels * bits_per_sample * rate/48000) / + * number of SDOs) >= 8 } + */ + bus->sdo_limit = 8; + return 0; } EXPORT_SYMBOL_GPL(snd_hdac_bus_init); diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index 011b17cc1efa..b98449fd92f3 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -529,17 +529,6 @@ bool snd_hdac_bus_init_chip(struct hdac_bus *bus, bool full_reset) bus->chip_init = true; - /* - * Default value of '8' is as per the HD audio specification (Rev 1.0a). - * Following relation is used to derive STRIPE control value. - * For sample rate <= 48K: - * { ((num_channels * bits_per_sample) / number of SDOs) >= 8 } - * For sample rate > 48K: - * { ((num_channels * bits_per_sample * rate/48000) / - * number of SDOs) >= 8 } - */ - bus->sdo_limit = 8; - return true; } EXPORT_SYMBOL_GPL(snd_hdac_bus_init_chip); diff --git a/sound/isa/sscape.c b/sound/isa/sscape.c index 5363d88cc4b9..2e5a5c5279e8 100644 --- a/sound/isa/sscape.c +++ b/sound/isa/sscape.c @@ -308,7 +308,7 @@ static inline int verify_mpu401(const struct snd_mpu401 *mpu) } /* - * This is apparently the standard way to initailise an MPU-401 + * This is apparently the standard way to initialise an MPU-401 */ static inline void initialise_mpu401(const struct snd_mpu401 *mpu) { @@ -339,7 +339,7 @@ static void soundscape_free(struct snd_card *c) } /* - * Tell the SoundScape to begin a DMA tranfer using the given channel. + * Tell the SoundScape to begin a DMA transfer using the given channel. * All locking issues are left to the caller. */ static void sscape_start_dma_unsafe(unsigned io_base, enum GA_REG reg) @@ -803,7 +803,7 @@ static int mpu401_open(struct snd_mpu401 *mpu) } /* - * Initialse an MPU-401 subdevice for MIDI support on the SoundScape. + * Initialise an MPU-401 subdevice for MIDI support on the SoundScape. */ static int create_mpu401(struct snd_card *card, int devnum, unsigned long port, int irq) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7f9d35273734..a1fa983d2a94 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7694,6 +7694,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NT950XCJ-X716A)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), @@ -7955,6 +7957,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"}, {.id = ALC298_FIXUP_HUAWEI_MBX_STEREO, .name = "huawei-mbx-stereo"}, {.id = ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE, .name = "alc256-medion-headset"}, + {.id = ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, .name = "alc298-samsung-headphone"}, {} }; #define ALC225_STANDARD_PINS \ diff --git a/sound/soc/amd/acp3x-rt5682-max9836.c b/sound/soc/amd/acp3x-rt5682-max9836.c index 55815fdaa1aa..406526e79af3 100644 --- a/sound/soc/amd/acp3x-rt5682-max9836.c +++ b/sound/soc/amd/acp3x-rt5682-max9836.c @@ -138,7 +138,7 @@ static int acp3x_1015_hw_params(struct snd_pcm_substream *substream, srate = params_rate(params); for_each_rtd_codec_dais(rtd, i, codec_dai) { - if (strcmp(codec_dai->component->name, "rt1015-aif")) + if (strcmp(codec_dai->name, "rt1015-aif")) continue; ret = snd_soc_dai_set_bclk_ratio(codec_dai, 64); if (ret < 0) diff --git a/sound/soc/amd/renoir/acp3x-pdm-dma.c b/sound/soc/amd/renoir/acp3x-pdm-dma.c index 623dfd3ea705..7b14d9a81b97 100644 --- a/sound/soc/amd/renoir/acp3x-pdm-dma.c +++ b/sound/soc/amd/renoir/acp3x-pdm-dma.c @@ -314,40 +314,30 @@ static int acp_pdm_dma_close(struct snd_soc_component *component, return 0; } -static int acp_pdm_dai_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct snd_soc_dai *dai) +static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, + int cmd, struct snd_soc_dai *dai) { struct pdm_stream_instance *rtd; + int ret; + bool pdm_status; unsigned int ch_mask; rtd = substream->runtime->private_data; - switch (params_channels(params)) { + ret = 0; + switch (substream->runtime->channels) { case TWO_CH: ch_mask = 0x00; break; default: return -EINVAL; } - rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS); - rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base + - ACP_WOV_PDM_DECIMATION_FACTOR); - return 0; -} - -static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, - int cmd, struct snd_soc_dai *dai) -{ - struct pdm_stream_instance *rtd; - int ret; - bool pdm_status; - - rtd = substream->runtime->private_data; - ret = 0; switch (cmd) { case SNDRV_PCM_TRIGGER_START: case SNDRV_PCM_TRIGGER_RESUME: case SNDRV_PCM_TRIGGER_PAUSE_RELEASE: + rn_writel(ch_mask, rtd->acp_base + ACP_WOV_PDM_NO_OF_CHANNELS); + rn_writel(PDM_DECIMATION_FACTOR, rtd->acp_base + + ACP_WOV_PDM_DECIMATION_FACTOR); rtd->bytescount = acp_pdm_get_byte_count(rtd, substream->stream); pdm_status = check_pdm_dma_status(rtd->acp_base); @@ -369,7 +359,6 @@ static int acp_pdm_dai_trigger(struct snd_pcm_substream *substream, } static struct snd_soc_dai_ops acp_pdm_dai_ops = { - .hw_params = acp_pdm_dai_hw_params, .trigger = acp_pdm_dai_trigger, }; diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c index 4428c62e25cf..3ddd822240e3 100644 --- a/sound/soc/codecs/msm8916-wcd-analog.c +++ b/sound/soc/codecs/msm8916-wcd-analog.c @@ -19,8 +19,8 @@ #define CDC_D_REVISION1 (0xf000) #define CDC_D_PERPH_SUBTYPE (0xf005) -#define CDC_D_INT_EN_SET (0x015) -#define CDC_D_INT_EN_CLR (0x016) +#define CDC_D_INT_EN_SET (0xf015) +#define CDC_D_INT_EN_CLR (0xf016) #define MBHC_SWITCH_INT BIT(7) #define MBHC_MIC_ELECTRICAL_INS_REM_DET BIT(6) #define MBHC_BUTTON_PRESS_DET BIT(5) diff --git a/sound/soc/codecs/wm8958-dsp2.c b/sound/soc/codecs/wm8958-dsp2.c index 68a3b48e6b31..3bce9a14f0f3 100644 --- a/sound/soc/codecs/wm8958-dsp2.c +++ b/sound/soc/codecs/wm8958-dsp2.c @@ -412,8 +412,12 @@ int wm8958_aif_ev(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); + struct wm8994 *control = dev_get_drvdata(component->dev->parent); int i; + if (control->type != WM8958) + return 0; + switch (event) { case SND_SOC_DAPM_POST_PMU: case SND_SOC_DAPM_PRE_PMU: diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c index 317916cb4e27..0623a2251084 100644 --- a/sound/soc/codecs/wm8962.c +++ b/sound/soc/codecs/wm8962.c @@ -151,7 +151,6 @@ static const struct reg_default wm8962_reg[] = { { 40, 0x0000 }, /* R40 - SPKOUTL volume */ { 41, 0x0000 }, /* R41 - SPKOUTR volume */ - { 48, 0x0000 }, /* R48 - Additional control(4) */ { 49, 0x0010 }, /* R49 - Class D Control 1 */ { 51, 0x0003 }, /* R51 - Class D Control 2 */ @@ -842,6 +841,7 @@ static bool wm8962_readable_register(struct device *dev, unsigned int reg) case WM8962_SPKOUTL_VOLUME: case WM8962_SPKOUTR_VOLUME: case WM8962_THERMAL_SHUTDOWN_STATUS: + case WM8962_ADDITIONAL_CONTROL_4: case WM8962_CLASS_D_CONTROL_1: case WM8962_CLASS_D_CONTROL_2: case WM8962_CLOCKING_4: diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c index a84ae879d37e..038be667c1a6 100644 --- a/sound/soc/codecs/wm8994.c +++ b/sound/soc/codecs/wm8994.c @@ -43,10 +43,12 @@ #define WM8994_NUM_DRC 3 #define WM8994_NUM_EQ 3 -static struct { +struct wm8994_reg_mask { unsigned int reg; unsigned int mask; -} wm8994_vu_bits[] = { +}; + +static struct wm8994_reg_mask wm8994_vu_bits[] = { { WM8994_LEFT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU }, { WM8994_RIGHT_LINE_INPUT_1_2_VOLUME, WM8994_IN1_VU }, { WM8994_LEFT_LINE_INPUT_3_4_VOLUME, WM8994_IN2_VU }, @@ -60,14 +62,10 @@ static struct { { WM8994_AIF1_DAC1_LEFT_VOLUME, WM8994_AIF1DAC1_VU }, { WM8994_AIF1_DAC1_RIGHT_VOLUME, WM8994_AIF1DAC1_VU }, - { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU }, - { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU }, { WM8994_AIF2_DAC_LEFT_VOLUME, WM8994_AIF2DAC_VU }, { WM8994_AIF2_DAC_RIGHT_VOLUME, WM8994_AIF2DAC_VU }, { WM8994_AIF1_ADC1_LEFT_VOLUME, WM8994_AIF1ADC1_VU }, { WM8994_AIF1_ADC1_RIGHT_VOLUME, WM8994_AIF1ADC1_VU }, - { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU }, - { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, { WM8994_AIF2_ADC_LEFT_VOLUME, WM8994_AIF2ADC_VU }, { WM8994_AIF2_ADC_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, { WM8994_DAC1_LEFT_VOLUME, WM8994_DAC1_VU }, @@ -76,6 +74,14 @@ static struct { { WM8994_DAC2_RIGHT_VOLUME, WM8994_DAC2_VU }, }; +/* VU bitfields for ADC2, DAC2 not available on WM1811 */ +static struct wm8994_reg_mask wm8994_adc2_dac2_vu_bits[] = { + { WM8994_AIF1_DAC2_LEFT_VOLUME, WM8994_AIF1DAC2_VU }, + { WM8994_AIF1_DAC2_RIGHT_VOLUME, WM8994_AIF1DAC2_VU }, + { WM8994_AIF1_ADC2_LEFT_VOLUME, WM8994_AIF1ADC2_VU }, + { WM8994_AIF1_ADC2_RIGHT_VOLUME, WM8994_AIF1ADC2_VU }, +}; + static int wm8994_drc_base[] = { WM8994_AIF1_DRC1_1, WM8994_AIF1_DRC2_1, @@ -1030,6 +1036,26 @@ static bool wm8994_check_class_w_digital(struct snd_soc_component *component) return true; } +static void wm8994_update_vu_bits(struct snd_soc_component *component) +{ + struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); + struct wm8994 *control = wm8994->wm8994; + int i; + + for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) + snd_soc_component_write(component, wm8994_vu_bits[i].reg, + snd_soc_component_read(component, + wm8994_vu_bits[i].reg)); + if (control->type == WM1811) + return; + + for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++) + snd_soc_component_write(component, + wm8994_adc2_dac2_vu_bits[i].reg, + snd_soc_component_read(component, + wm8994_adc2_dac2_vu_bits[i].reg)); +} + static int aif_mclk_set(struct snd_soc_component *component, int aif, bool enable) { struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); @@ -1076,7 +1102,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w, struct wm8994_priv *wm8994 = snd_soc_component_get_drvdata(component); struct wm8994 *control = wm8994->wm8994; int mask = WM8994_AIF1DAC1L_ENA | WM8994_AIF1DAC1R_ENA; - int ret, i; + int ret; int dac; int adc; int val; @@ -1144,10 +1170,7 @@ static int aif1clk_ev(struct snd_soc_dapm_widget *w, break; case SND_SOC_DAPM_POST_PMU: - for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) - snd_soc_component_write(component, wm8994_vu_bits[i].reg, - snd_soc_component_read(component, - wm8994_vu_bits[i].reg)); + wm8994_update_vu_bits(component); break; case SND_SOC_DAPM_PRE_PMD: @@ -1181,7 +1204,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w, struct snd_kcontrol *kcontrol, int event) { struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm); - int ret, i; + int ret; int dac; int adc; int val; @@ -1237,10 +1260,7 @@ static int aif2clk_ev(struct snd_soc_dapm_widget *w, break; case SND_SOC_DAPM_POST_PMU: - for (i = 0; i < ARRAY_SIZE(wm8994_vu_bits); i++) - snd_soc_component_write(component, wm8994_vu_bits[i].reg, - snd_soc_component_read(component, - wm8994_vu_bits[i].reg)); + wm8994_update_vu_bits(component); break; case SND_SOC_DAPM_PRE_PMD: @@ -4346,6 +4366,14 @@ static int wm8994_component_probe(struct snd_soc_component *component) wm8994_vu_bits[i].mask, wm8994_vu_bits[i].mask); + if (control->type != WM1811) { + for (i = 0; i < ARRAY_SIZE(wm8994_adc2_dac2_vu_bits); i++) + snd_soc_component_update_bits(component, + wm8994_adc2_dac2_vu_bits[i].reg, + wm8994_adc2_dac2_vu_bits[i].mask, + wm8994_adc2_dac2_vu_bits[i].mask); + } + /* Set the low bit of the 3D stereo depth so TLV matches */ snd_soc_component_update_bits(component, WM8994_AIF1_DAC1_FILTERS_2, 1 << WM8994_AIF1DAC1_3D_GAIN_SHIFT, diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index de136c0a497d..52adedc03245 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -73,6 +73,7 @@ struct cpu_priv { * @codec_priv: CODEC private data * @cpu_priv: CPU private data * @card: ASoC card structure + * @streams: Mask of current active streams * @sample_rate: Current sample rate * @sample_format: Current sample format * @asrc_rate: ASRC sample rate used by Back-Ends @@ -89,6 +90,7 @@ struct fsl_asoc_card_priv { struct codec_priv codec_priv; struct cpu_priv cpu_priv; struct snd_soc_card card; + u8 streams; u32 sample_rate; snd_pcm_format_t sample_format; u32 asrc_rate; @@ -151,21 +153,17 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream); struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card); bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK; + struct codec_priv *codec_priv = &priv->codec_priv; struct cpu_priv *cpu_priv = &priv->cpu_priv; struct device *dev = rtd->card->dev; + unsigned int pll_out; int ret; priv->sample_rate = params_rate(params); priv->sample_format = params_format(params); + priv->streams |= BIT(substream->stream); - /* - * If codec-dai is DAI Master and all configurations are already in the - * set_bias_level(), bypass the remaining settings in hw_params(). - * Note: (dai_fmt & CBM_CFM) includes CBM_CFM and CBM_CFS. - */ - if ((priv->card.set_bias_level && - priv->dai_fmt & SND_SOC_DAIFMT_CBM_CFM) || - fsl_asoc_card_is_ac97(priv)) + if (fsl_asoc_card_is_ac97(priv)) return 0; /* Specific configurations of DAIs starts from here */ @@ -174,7 +172,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, cpu_priv->sysclk_dir[tx]); if (ret && ret != -ENOTSUPP) { dev_err(dev, "failed to set sysclk for cpu dai\n"); - return ret; + goto fail; } if (cpu_priv->slot_width) { @@ -182,6 +180,68 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, cpu_priv->slot_width); if (ret && ret != -ENOTSUPP) { dev_err(dev, "failed to set TDM slot for cpu dai\n"); + goto fail; + } + } + + /* Specific configuration for PLL */ + if (codec_priv->pll_id && codec_priv->fll_id) { + if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE) + pll_out = priv->sample_rate * 384; + else + pll_out = priv->sample_rate * 256; + + ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0), + codec_priv->pll_id, + codec_priv->mclk_id, + codec_priv->mclk_freq, pll_out); + if (ret) { + dev_err(dev, "failed to start FLL: %d\n", ret); + goto fail; + } + + ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0), + codec_priv->fll_id, + pll_out, SND_SOC_CLOCK_IN); + + if (ret && ret != -ENOTSUPP) { + dev_err(dev, "failed to set SYSCLK: %d\n", ret); + goto fail; + } + } + + return 0; + +fail: + priv->streams &= ~BIT(substream->stream); + return ret; +} + +static int fsl_asoc_card_hw_free(struct snd_pcm_substream *substream) +{ + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(rtd->card); + struct codec_priv *codec_priv = &priv->codec_priv; + struct device *dev = rtd->card->dev; + int ret; + + priv->streams &= ~BIT(substream->stream); + + if (!priv->streams && codec_priv->pll_id && codec_priv->fll_id) { + /* Force freq to be 0 to avoid error message in codec */ + ret = snd_soc_dai_set_sysclk(asoc_rtd_to_codec(rtd, 0), + codec_priv->mclk_id, + 0, + SND_SOC_CLOCK_IN); + if (ret) { + dev_err(dev, "failed to switch away from FLL: %d\n", ret); + return ret; + } + + ret = snd_soc_dai_set_pll(asoc_rtd_to_codec(rtd, 0), + codec_priv->pll_id, 0, 0, 0); + if (ret && ret != -ENOTSUPP) { + dev_err(dev, "failed to stop FLL: %d\n", ret); return ret; } } @@ -191,6 +251,7 @@ static int fsl_asoc_card_hw_params(struct snd_pcm_substream *substream, static const struct snd_soc_ops fsl_asoc_card_ops = { .hw_params = fsl_asoc_card_hw_params, + .hw_free = fsl_asoc_card_hw_free, }; static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd, @@ -254,75 +315,6 @@ static struct snd_soc_dai_link fsl_asoc_card_dai[] = { }, }; -static int fsl_asoc_card_set_bias_level(struct snd_soc_card *card, - struct snd_soc_dapm_context *dapm, - enum snd_soc_bias_level level) -{ - struct fsl_asoc_card_priv *priv = snd_soc_card_get_drvdata(card); - struct snd_soc_pcm_runtime *rtd; - struct snd_soc_dai *codec_dai; - struct codec_priv *codec_priv = &priv->codec_priv; - struct device *dev = card->dev; - unsigned int pll_out; - int ret; - - rtd = snd_soc_get_pcm_runtime(card, &card->dai_link[0]); - codec_dai = asoc_rtd_to_codec(rtd, 0); - if (dapm->dev != codec_dai->dev) - return 0; - - switch (level) { - case SND_SOC_BIAS_PREPARE: - if (dapm->bias_level != SND_SOC_BIAS_STANDBY) - break; - - if (priv->sample_format == SNDRV_PCM_FORMAT_S24_LE) - pll_out = priv->sample_rate * 384; - else - pll_out = priv->sample_rate * 256; - - ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, - codec_priv->mclk_id, - codec_priv->mclk_freq, pll_out); - if (ret) { - dev_err(dev, "failed to start FLL: %d\n", ret); - return ret; - } - - ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->fll_id, - pll_out, SND_SOC_CLOCK_IN); - if (ret && ret != -ENOTSUPP) { - dev_err(dev, "failed to set SYSCLK: %d\n", ret); - return ret; - } - break; - - case SND_SOC_BIAS_STANDBY: - if (dapm->bias_level != SND_SOC_BIAS_PREPARE) - break; - - ret = snd_soc_dai_set_sysclk(codec_dai, codec_priv->mclk_id, - codec_priv->mclk_freq, - SND_SOC_CLOCK_IN); - if (ret && ret != -ENOTSUPP) { - dev_err(dev, "failed to switch away from FLL: %d\n", ret); - return ret; - } - - ret = snd_soc_dai_set_pll(codec_dai, codec_priv->pll_id, 0, 0, 0); - if (ret) { - dev_err(dev, "failed to stop FLL: %d\n", ret); - return ret; - } - break; - - default: - break; - } - - return 0; -} - static int fsl_asoc_card_audmux_init(struct device_node *np, struct fsl_asoc_card_priv *priv) { @@ -611,7 +603,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) /* Diversify the card configurations */ if (of_device_is_compatible(np, "fsl,imx-audio-cs42888")) { codec_dai_name = "cs42888"; - priv->card.set_bias_level = NULL; priv->cpu_priv.sysclk_freq[TX] = priv->codec_priv.mclk_freq; priv->cpu_priv.sysclk_freq[RX] = priv->codec_priv.mclk_freq; priv->cpu_priv.sysclk_dir[TX] = SND_SOC_CLOCK_OUT; @@ -628,26 +619,22 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8962")) { codec_dai_name = "wm8962"; - priv->card.set_bias_level = fsl_asoc_card_set_bias_level; priv->codec_priv.mclk_id = WM8962_SYSCLK_MCLK; priv->codec_priv.fll_id = WM8962_SYSCLK_FLL; priv->codec_priv.pll_id = WM8962_FLL; priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8960")) { codec_dai_name = "wm8960-hifi"; - priv->card.set_bias_level = fsl_asoc_card_set_bias_level; priv->codec_priv.fll_id = WM8960_SYSCLK_AUTO; priv->codec_priv.pll_id = WM8960_SYSCLK_AUTO; priv->dai_fmt |= SND_SOC_DAIFMT_CBM_CFM; } else if (of_device_is_compatible(np, "fsl,imx-audio-ac97")) { codec_dai_name = "ac97-hifi"; - priv->card.set_bias_level = NULL; priv->dai_fmt = SND_SOC_DAIFMT_AC97; priv->card.dapm_routes = audio_map_ac97; priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_ac97); } else if (of_device_is_compatible(np, "fsl,imx-audio-mqs")) { codec_dai_name = "fsl-mqs-dai"; - priv->card.set_bias_level = NULL; priv->dai_fmt = SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS | SND_SOC_DAIFMT_NB_NF; @@ -657,7 +644,6 @@ static int fsl_asoc_card_probe(struct platform_device *pdev) priv->card.num_dapm_routes = ARRAY_SIZE(audio_map_tx); } else if (of_device_is_compatible(np, "fsl,imx-audio-wm8524")) { codec_dai_name = "wm8524-hifi"; - priv->card.set_bias_level = NULL; priv->dai_fmt |= SND_SOC_DAIFMT_CBS_CFS; priv->dai_link[1].dpcm_capture = 0; priv->dai_link[2].dpcm_capture = 0; diff --git a/sound/soc/fsl/mpc5200_dma.c b/sound/soc/fsl/mpc5200_dma.c index 9e4f66b6b92b..231984882176 100644 --- a/sound/soc/fsl/mpc5200_dma.c +++ b/sound/soc/fsl/mpc5200_dma.c @@ -339,7 +339,6 @@ static int psc_dma_new(struct snd_soc_component *component, static void psc_dma_free(struct snd_soc_component *component, struct snd_pcm *pcm) { - struct snd_soc_pcm_runtime *rtd = pcm->private_data; struct snd_pcm_substream *substream; int stream; diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 49b9f18472bc..b1cac7abdc0a 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -331,7 +331,7 @@ static int sst_media_open(struct snd_pcm_substream *substream, ret_val = power_up_sst(stream); if (ret_val < 0) - return ret_val; + goto out_power_up; /* Make sure, that the period size is always even */ snd_pcm_hw_constraint_step(substream->runtime, 0, @@ -340,8 +340,9 @@ static int sst_media_open(struct snd_pcm_substream *substream, return snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS); out_ops: - kfree(stream); mutex_unlock(&sst_lock); +out_power_up: + kfree(stream); return ret_val; } diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c index 2a5302f1db98..0168af849272 100644 --- a/sound/soc/qcom/qdsp6/q6afe-dai.c +++ b/sound/soc/qcom/qdsp6/q6afe-dai.c @@ -1150,206 +1150,206 @@ static int q6afe_of_xlate_dai_name(struct snd_soc_component *component, } static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = { - SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, 0, 0, 0), + SND_SOC_DAPM_AIF_IN("HDMI_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_0_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_1_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_2_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_3_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_4_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_5_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_IN("SLIMBUS_6_RX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_0_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_1_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_2_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_3_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_TX", NULL, 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_TX", NULL, 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_MI2S_RX_SD1", "Secondary MI2S Playback SD1", - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRI_MI2S_RX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRI_MI2S_TX", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("PRIMARY_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("PRIMARY_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("SEC_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("SEC_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("TERT_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("TERT_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUAT_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUAT_TDM_TX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_IN("QUIN_TDM_RX_7", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_0", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_1", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_2", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_3", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_4", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_5", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_6", NULL, - 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), SND_SOC_DAPM_AIF_OUT("QUIN_TDM_TX_7", NULL, - 0, 0, 0, 0), - SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, 0, 0, 0), + 0, SND_SOC_NOPM, 0, 0), + SND_SOC_DAPM_AIF_OUT("DISPLAY_PORT_RX", "NULL", 0, SND_SOC_NOPM, 0, 0), }; static const struct snd_soc_component_driver q6afe_dai_component = { diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c index eaa95b5a7b66..25d23e0266c7 100644 --- a/sound/soc/qcom/qdsp6/q6routing.c +++ b/sound/soc/qcom/qdsp6/q6routing.c @@ -973,6 +973,20 @@ static int msm_routing_probe(struct snd_soc_component *c) return 0; } +static unsigned int q6routing_reg_read(struct snd_soc_component *component, + unsigned int reg) +{ + /* default value */ + return 0; +} + +static int q6routing_reg_write(struct snd_soc_component *component, + unsigned int reg, unsigned int val) +{ + /* dummy */ + return 0; +} + static const struct snd_soc_component_driver msm_soc_routing_component = { .probe = msm_routing_probe, .name = DRV_NAME, @@ -981,6 +995,8 @@ static const struct snd_soc_component_driver msm_soc_routing_component = { .num_dapm_widgets = ARRAY_SIZE(msm_qdsp6_widgets), .dapm_routes = intercon, .num_dapm_routes = ARRAY_SIZE(intercon), + .read = q6routing_reg_read, + .write = q6routing_reg_write, }; static int q6pcm_routing_probe(struct platform_device *pdev) diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index f0b4f4bc44a4..5504b92946e3 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -406,7 +406,7 @@ static unsigned int soc_component_read_no_lock( ret = -EIO; if (ret < 0) - soc_component_ret(component, ret); + return soc_component_ret(component, ret); return val; } diff --git a/sound/soc/tegra/tegra186_dspk.c b/sound/soc/tegra/tegra186_dspk.c index fe7117171a0e..0cbe31e2c7e9 100644 --- a/sound/soc/tegra/tegra186_dspk.c +++ b/sound/soc/tegra/tegra186_dspk.c @@ -71,7 +71,7 @@ static int tegra186_dspk_put_control(struct snd_kcontrol *kcontrol, return 0; } -static int tegra186_dspk_runtime_suspend(struct device *dev) +static int __maybe_unused tegra186_dspk_runtime_suspend(struct device *dev) { struct tegra186_dspk *dspk = dev_get_drvdata(dev); @@ -83,7 +83,7 @@ static int tegra186_dspk_runtime_suspend(struct device *dev) return 0; } -static int tegra186_dspk_runtime_resume(struct device *dev) +static int __maybe_unused tegra186_dspk_runtime_resume(struct device *dev) { struct tegra186_dspk *dspk = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_admaif.c b/sound/soc/tegra/tegra210_admaif.c index 4894e8e6ee7f..1268046b345d 100644 --- a/sound/soc/tegra/tegra210_admaif.c +++ b/sound/soc/tegra/tegra210_admaif.c @@ -219,7 +219,7 @@ static const struct regmap_config tegra186_admaif_regmap_config = { .cache_type = REGCACHE_FLAT, }; -static int tegra_admaif_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_admaif_runtime_suspend(struct device *dev) { struct tegra_admaif *admaif = dev_get_drvdata(dev); @@ -229,7 +229,7 @@ static int tegra_admaif_runtime_suspend(struct device *dev) return 0; } -static int tegra_admaif_runtime_resume(struct device *dev) +static int __maybe_unused tegra_admaif_runtime_resume(struct device *dev) { struct tegra_admaif *admaif = dev_get_drvdata(dev); diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c index 5123a96fdde8..66287a7c9865 100644 --- a/sound/soc/tegra/tegra210_ahub.c +++ b/sound/soc/tegra/tegra210_ahub.c @@ -564,7 +564,7 @@ static const struct of_device_id tegra_ahub_of_match[] = { }; MODULE_DEVICE_TABLE(of, tegra_ahub_of_match); -static int tegra_ahub_runtime_suspend(struct device *dev) +static int __maybe_unused tegra_ahub_runtime_suspend(struct device *dev) { struct tegra_ahub *ahub = dev_get_drvdata(dev); @@ -576,7 +576,7 @@ static int tegra_ahub_runtime_suspend(struct device *dev) return 0; } -static int tegra_ahub_runtime_resume(struct device *dev) +static int __maybe_unused tegra_ahub_runtime_resume(struct device *dev) { struct tegra_ahub *ahub = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_dmic.c b/sound/soc/tegra/tegra210_dmic.c index d682414ad90d..a661f40bc41c 100644 --- a/sound/soc/tegra/tegra210_dmic.c +++ b/sound/soc/tegra/tegra210_dmic.c @@ -40,7 +40,7 @@ static const struct reg_default tegra210_dmic_reg_defaults[] = { { TEGRA210_DMIC_LP_BIQUAD_1_COEF_4, 0x0 }, }; -static int tegra210_dmic_runtime_suspend(struct device *dev) +static int __maybe_unused tegra210_dmic_runtime_suspend(struct device *dev) { struct tegra210_dmic *dmic = dev_get_drvdata(dev); @@ -52,7 +52,7 @@ static int tegra210_dmic_runtime_suspend(struct device *dev) return 0; } -static int tegra210_dmic_runtime_resume(struct device *dev) +static int __maybe_unused tegra210_dmic_runtime_resume(struct device *dev) { struct tegra210_dmic *dmic = dev_get_drvdata(dev); int err; diff --git a/sound/soc/tegra/tegra210_i2s.c b/sound/soc/tegra/tegra210_i2s.c index 722092181583..a383bd5c51cd 100644 --- a/sound/soc/tegra/tegra210_i2s.c +++ b/sound/soc/tegra/tegra210_i2s.c @@ -164,7 +164,7 @@ static int tegra210_i2s_init(struct snd_soc_dapm_widget *w, return tegra210_i2s_sw_reset(compnt, is_playback); } -static int tegra210_i2s_runtime_suspend(struct device *dev) +static int __maybe_unused tegra210_i2s_runtime_suspend(struct device *dev) { struct tegra210_i2s *i2s = dev_get_drvdata(dev); @@ -176,7 +176,7 @@ static int tegra210_i2s_runtime_suspend(struct device *dev) return 0; } -static int tegra210_i2s_runtime_resume(struct device *dev) +static int __maybe_unused tegra210_i2s_runtime_resume(struct device *dev) { struct tegra210_i2s *i2s = dev_get_drvdata(dev); int err; diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 6b0f3a8469ef..81e987eaf063 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -2371,7 +2371,7 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, int num_ins; struct usb_mixer_elem_info *cval; struct snd_kcontrol *kctl; - int i, err, nameid, type, len; + int i, err, nameid, type, len, val; const struct procunit_info *info; const struct procunit_value_info *valinfo; const struct usbmix_name_map *map; @@ -2474,6 +2474,12 @@ static int build_audio_procunit(struct mixer_build *state, int unitid, break; } + err = get_cur_ctl_value(cval, cval->control << 8, &val); + if (err < 0) { + usb_mixer_elem_info_free(cval); + return -EINVAL; + } + kctl = snd_ctl_new1(&mixer_procunit_ctl, cval); if (!kctl) { usb_mixer_elem_info_free(cval); diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index d79e3ddc5690..f4fb002e3ef4 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2680,6 +2680,10 @@ YAMAHA_DEVICE(0x7010, "UB99"), .data = (const struct snd_usb_audio_quirk[]) { { .ifnum = 0, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + { + .ifnum = 0, .type = QUIRK_AUDIO_FIXED_ENDPOINT, .data = &(const struct audioformat) { .formats = SNDRV_PCM_FMTBIT_S24_3LE, @@ -2690,6 +2694,32 @@ YAMAHA_DEVICE(0x7010, "UB99"), .attributes = UAC_EP_CS_ATTR_SAMPLE_RATE, .endpoint = 0x01, .ep_attr = USB_ENDPOINT_XFER_ISOC, + .datainterval = 1, + .maxpacksize = 0x024c, + .rates = SNDRV_PCM_RATE_44100 | + SNDRV_PCM_RATE_48000, + .rate_min = 44100, + .rate_max = 48000, + .nr_rates = 2, + .rate_table = (unsigned int[]) { + 44100, 48000 + } + } + }, + { + .ifnum = 0, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S24_3LE, + .channels = 2, + .iface = 0, + .altsetting = 1, + .altset_idx = 1, + .attributes = 0, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC, + .datainterval = 1, + .maxpacksize = 0x0126, .rates = SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000, .rate_min = 44100, @@ -3714,8 +3744,8 @@ ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ * they pretend to be 96kHz mono as a workaround for stereo being broken * by that... * - * They also have swapped L-R channels, but that's for userspace to deal - * with. + * They also have an issue with initial stream alignment that causes the + * channels to be swapped and out of phase, which is dealt with in quirks.c. */ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE | diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index ede162f83eea..0e9310727281 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -67,7 +67,7 @@ static int dump_prog_id_as_func_ptr(const struct btf_dumper *d, if (!info->btf_id || !info->nr_func_info || btf__get_from_id(info->btf_id, &prog_btf)) goto print; - finfo = (struct bpf_func_info *)info->func_info; + finfo = u64_to_ptr(info->func_info); func_type = btf__type_by_id(prog_btf, finfo->type_id); if (!func_type || !btf_is_func(func_type)) goto print; diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c index 8a4c2b3b0cd6..f61184653633 100644 --- a/tools/bpf/bpftool/gen.c +++ b/tools/bpf/bpftool/gen.c @@ -143,6 +143,20 @@ static int codegen_datasec_def(struct bpf_object *obj, var_name, align); return -EINVAL; } + /* Assume 32-bit architectures when generating data section + * struct memory layout. Given bpftool can't know which target + * host architecture it's emitting skeleton for, we need to be + * conservative and assume 32-bit one to ensure enough padding + * bytes are generated for pointer and long types. This will + * still work correctly for 64-bit architectures, because in + * the worst case we'll generate unnecessary padding field, + * which on 64-bit architectures is not strictly necessary and + * would be handled by natural 8-byte alignment. But it still + * will be a correct memory layout, based on recorded offsets + * in BTF. + */ + if (align > 4) + align = 4; align_off = (off + align - 1) / align * align; if (align_off != need_off) { @@ -397,7 +411,7 @@ static int do_skeleton(int argc, char **argv) { \n\ struct %1$s *obj; \n\ \n\ - obj = (typeof(obj))calloc(1, sizeof(*obj)); \n\ + obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\ if (!obj) \n\ return NULL; \n\ if (%1$s__create_skeleton(obj)) \n\ @@ -461,7 +475,7 @@ static int do_skeleton(int argc, char **argv) { \n\ struct bpf_object_skeleton *s; \n\ \n\ - s = (typeof(s))calloc(1, sizeof(*s)); \n\ + s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\ if (!s) \n\ return -1; \n\ obj->skeleton = s; \n\ @@ -479,7 +493,7 @@ static int do_skeleton(int argc, char **argv) /* maps */ \n\ s->map_cnt = %zu; \n\ s->map_skel_sz = sizeof(*s->maps); \n\ - s->maps = (typeof(s->maps))calloc(s->map_cnt, s->map_skel_sz);\n\ + s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\ if (!s->maps) \n\ goto err; \n\ ", @@ -515,7 +529,7 @@ static int do_skeleton(int argc, char **argv) /* programs */ \n\ s->prog_cnt = %zu; \n\ s->prog_skel_sz = sizeof(*s->progs); \n\ - s->progs = (typeof(s->progs))calloc(s->prog_cnt, s->prog_skel_sz);\n\ + s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\ if (!s->progs) \n\ goto err; \n\ ", diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 1b793759170e..a89f09e3c848 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -106,7 +106,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: jsonw_string_field(json_wtr, "tp_name", - (const char *)info->raw_tracepoint.tp_name); + u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); @@ -185,7 +185,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) switch (info->type) { case BPF_LINK_TYPE_RAW_TRACEPOINT: printf("\n\ttp '%s' ", - (const char *)info->raw_tracepoint.tp_name); + (const char *)u64_to_ptr(info->raw_tracepoint.tp_name)); break; case BPF_LINK_TYPE_TRACING: err = get_prog_info(info->prog_id, &prog_info); diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index e3a79b5a9960..c46e52137b87 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -21,7 +21,15 @@ /* Make sure we do not use kernel-only integer typedefs */ #pragma GCC poison u8 u16 u32 u64 s8 s16 s32 s64 -#define ptr_to_u64(ptr) ((__u64)(unsigned long)(ptr)) +static inline __u64 ptr_to_u64(const void *ptr) +{ + return (__u64)(unsigned long)ptr; +} + +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *)(unsigned long)ptr; +} #define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) #define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c index e3b116325403..df7d8ec76036 100644 --- a/tools/bpf/bpftool/pids.c +++ b/tools/bpf/bpftool/pids.c @@ -134,6 +134,8 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type) while (true) { ret = read(fd, buf, sizeof(buf)); if (ret < 0) { + if (errno == EAGAIN) + continue; err = -errno; p_err("failed to read PID iterator output: %d", err); goto out; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 158995d853b0..d393eb8263a6 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -428,14 +428,14 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, p_info("no instructions returned"); return -1; } - buf = (unsigned char *)(info->jited_prog_insns); + buf = u64_to_ptr(info->jited_prog_insns); member_len = info->jited_prog_len; } else { /* DUMP_XLATED */ if (info->xlated_prog_len == 0 || !info->xlated_prog_insns) { p_err("error retrieving insn dump: kernel.kptr_restrict set?"); return -1; } - buf = (unsigned char *)info->xlated_prog_insns; + buf = u64_to_ptr(info->xlated_prog_insns); member_len = info->xlated_prog_len; } @@ -444,7 +444,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, return -1; } - func_info = (void *)info->func_info; + func_info = u64_to_ptr(info->func_info); if (info->nr_line_info) { prog_linfo = bpf_prog_linfo__new(info); @@ -462,7 +462,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, n = write(fd, buf, member_len); close(fd); - if (n != member_len) { + if (n != (ssize_t)member_len) { p_err("error writing output file: %s", n < 0 ? strerror(errno) : "short write"); return -1; @@ -492,13 +492,13 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, __u32 i; if (info->nr_jited_ksyms) { kernel_syms_load(&dd); - ksyms = (__u64 *) info->jited_ksyms; + ksyms = u64_to_ptr(info->jited_ksyms); } if (json_output) jsonw_start_array(json_wtr); - lens = (__u32 *) info->jited_func_lens; + lens = u64_to_ptr(info->jited_func_lens); for (i = 0; i < info->nr_jited_func_lens; i++) { if (ksyms) { sym = kernel_syms_search(&dd, ksyms[i]); @@ -559,7 +559,7 @@ prog_dump(struct bpf_prog_info *info, enum dump_mode mode, } else { kernel_syms_load(&dd); dd.nr_jited_ksyms = info->nr_jited_ksyms; - dd.jited_ksyms = (__u64 *) info->jited_ksyms; + dd.jited_ksyms = u64_to_ptr(info->jited_ksyms); dd.btf = btf; dd.func_info = func_info; dd.finfo_rec_size = info->func_info_rec_size; @@ -1681,7 +1681,7 @@ static char *profile_target_name(int tgt_fd) goto out; } - func_info = (struct bpf_func_info *)(info_linear->info.func_info); + func_info = u64_to_ptr(info_linear->info.func_info); t = btf__type_by_id(btf, func_info[0].type_id); if (!t) { p_err("btf %d doesn't have type %d", diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index 4d9ecb975862..0def0bb1f783 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -233,6 +233,39 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) return btf_id__add(root, id, false); } +/* + * The data of compressed section should be aligned to 4 + * (for 32bit) or 8 (for 64 bit) bytes. The binutils ld + * sets sh_addralign to 1, which makes libelf fail with + * misaligned section error during the update: + * FAILED elf_update(WRITE): invalid section alignment + * + * While waiting for ld fix, we fix the compressed sections + * sh_addralign value manualy. + */ +static int compressed_section_fix(Elf *elf, Elf_Scn *scn, GElf_Shdr *sh) +{ + int expected = gelf_getclass(elf) == ELFCLASS32 ? 4 : 8; + + if (!(sh->sh_flags & SHF_COMPRESSED)) + return 0; + + if (sh->sh_addralign == expected) + return 0; + + pr_debug2(" - fixing wrong alignment sh_addralign %u, expected %u\n", + sh->sh_addralign, expected); + + sh->sh_addralign = expected; + + if (gelf_update_shdr(scn, sh) == 0) { + printf("FAILED cannot update section header: %s\n", + elf_errmsg(-1)); + return -1; + } + return 0; +} + static int elf_collect(struct object *obj) { Elf_Scn *scn = NULL; @@ -309,6 +342,9 @@ static int elf_collect(struct object *obj) obj->efile.idlist_shndx = idx; obj->efile.idlist_addr = sh.sh_addr; } + + if (compressed_section_fix(elf, scn, &sh)) + return -1; } return 0; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 0480f893facd..b6238b2209b7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -767,7 +767,7 @@ union bpf_attr { * * Also, note that **bpf_trace_printk**\ () is slow, and should * only be used for debugging purposes. For this reason, a notice - * bloc (spanning several lines) is printed to kernel logs and + * block (spanning several lines) is printed to kernel logs and * states that the helper should not be used "for production use" * the first time this helper is used (or more precisely, when * **trace_printk**\ () buffers are allocated). For passing values @@ -1033,14 +1033,14 @@ union bpf_attr { * * int ret; * struct bpf_tunnel_key key = {}; - * + * * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); * if (ret < 0) * return TC_ACT_SHOT; // drop packet - * + * * if (key.remote_ipv4 != 0x0a000001) * return TC_ACT_SHOT; // drop packet - * + * * return TC_ACT_OK; // accept packet * * This interface can also be used with all encapsulation devices @@ -1147,7 +1147,7 @@ union bpf_attr { * Description * Retrieve the realm or the route, that is to say the * **tclassid** field of the destination for the *skb*. The - * indentifier retrieved is a user-provided tag, similar to the + * identifier retrieved is a user-provided tag, similar to the * one used with the net_cls cgroup (see description for * **bpf_get_cgroup_classid**\ () helper), but here this tag is * held by a route (a destination entry), not by a task. diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h index bc14db706b88..e9a4ecddb7a5 100644 --- a/tools/lib/bpf/bpf_helpers.h +++ b/tools/lib/bpf/bpf_helpers.h @@ -40,7 +40,7 @@ * Helper macro to manipulate data structures */ #ifndef offsetof -#define offsetof(TYPE, MEMBER) __builtin_offsetof(TYPE, MEMBER) +#define offsetof(TYPE, MEMBER) ((unsigned long)&((TYPE *)0)->MEMBER) #endif #ifndef container_of #define container_of(ptr, type, member) \ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 4843e44916f7..7dfca7016aaa 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -41,6 +41,7 @@ struct btf { __u32 types_size; __u32 data_size; int fd; + int ptr_sz; }; static inline __u64 ptr_to_u64(const void *ptr) @@ -221,6 +222,70 @@ const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) return btf->types[type_id]; } +static int determine_ptr_size(const struct btf *btf) +{ + const struct btf_type *t; + const char *name; + int i; + + for (i = 1; i <= btf->nr_types; i++) { + t = btf__type_by_id(btf, i); + if (!btf_is_int(t)) + continue; + + name = btf__name_by_offset(btf, t->name_off); + if (!name) + continue; + + if (strcmp(name, "long int") == 0 || + strcmp(name, "long unsigned int") == 0) { + if (t->size != 4 && t->size != 8) + continue; + return t->size; + } + } + + return -1; +} + +static size_t btf_ptr_sz(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + return btf->ptr_sz < 0 ? sizeof(void *) : btf->ptr_sz; +} + +/* Return pointer size this BTF instance assumes. The size is heuristically + * determined by looking for 'long' or 'unsigned long' integer type and + * recording its size in bytes. If BTF type information doesn't have any such + * type, this function returns 0. In the latter case, native architecture's + * pointer size is assumed, so will be either 4 or 8, depending on + * architecture that libbpf was compiled for. It's possible to override + * guessed value by using btf__set_pointer_size() API. + */ +size_t btf__pointer_size(const struct btf *btf) +{ + if (!btf->ptr_sz) + ((struct btf *)btf)->ptr_sz = determine_ptr_size(btf); + + if (btf->ptr_sz < 0) + /* not enough BTF type info to guess */ + return 0; + + return btf->ptr_sz; +} + +/* Override or set pointer size in bytes. Only values of 4 and 8 are + * supported. + */ +int btf__set_pointer_size(struct btf *btf, size_t ptr_sz) +{ + if (ptr_sz != 4 && ptr_sz != 8) + return -EINVAL; + btf->ptr_sz = ptr_sz; + return 0; +} + static bool btf_type_is_void(const struct btf_type *t) { return t == &btf_void || btf_is_fwd(t); @@ -253,7 +318,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) size = t->size; goto done; case BTF_KIND_PTR: - size = sizeof(void *); + size = btf_ptr_sz(btf); goto done; case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: @@ -293,9 +358,9 @@ int btf__align_of(const struct btf *btf, __u32 id) switch (kind) { case BTF_KIND_INT: case BTF_KIND_ENUM: - return min(sizeof(void *), (size_t)t->size); + return min(btf_ptr_sz(btf), (size_t)t->size); case BTF_KIND_PTR: - return sizeof(void *); + return btf_ptr_sz(btf); case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -533,6 +598,18 @@ struct btf *btf__parse_elf(const char *path, struct btf_ext **btf_ext) if (IS_ERR(btf)) goto done; + switch (gelf_getclass(elf)) { + case ELFCLASS32: + btf__set_pointer_size(btf, 4); + break; + case ELFCLASS64: + btf__set_pointer_size(btf, 8); + break; + default: + pr_warn("failed to get ELF class (bitness) for %s\n", path); + break; + } + if (btf_ext && btf_ext_data) { *btf_ext = btf_ext__new(btf_ext_data->d_buf, btf_ext_data->d_size); diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index f4a1a1d2b9a3..1ca14448df4c 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -76,6 +76,8 @@ LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); +LIBBPF_API size_t btf__pointer_size(const struct btf *btf); +LIBBPF_API int btf__set_pointer_size(struct btf *btf, size_t ptr_sz); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id); diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index cf711168d34a..57c00fa63932 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -13,6 +13,7 @@ #include <errno.h> #include <linux/err.h> #include <linux/btf.h> +#include <linux/kernel.h> #include "btf.h" #include "hashmap.h" #include "libbpf.h" @@ -60,6 +61,7 @@ struct btf_dump { const struct btf_ext *btf_ext; btf_dump_printf_fn_t printf_fn; struct btf_dump_opts opts; + int ptr_sz; bool strip_mods; /* per-type auxiliary state */ @@ -138,6 +140,7 @@ struct btf_dump *btf_dump__new(const struct btf *btf, d->btf_ext = btf_ext; d->printf_fn = printf_fn; d->opts.ctx = opts ? opts->ctx : NULL; + d->ptr_sz = btf__pointer_size(btf) ? : sizeof(void *); d->type_names = hashmap__new(str_hash_fn, str_equal_fn, NULL); if (IS_ERR(d->type_names)) { @@ -549,6 +552,9 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) } } +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t); + static void btf_dump_emit_struct_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t); static void btf_dump_emit_struct_def(struct btf_dump *d, __u32 id, @@ -671,6 +677,9 @@ static void btf_dump_emit_type(struct btf_dump *d, __u32 id, __u32 cont_id) switch (kind) { case BTF_KIND_INT: + /* Emit type alias definitions if necessary */ + btf_dump_emit_missing_aliases(d, id, t); + tstate->emit_state = EMITTED; break; case BTF_KIND_ENUM: @@ -797,7 +806,7 @@ static void btf_dump_emit_bit_padding(const struct btf_dump *d, int align, int lvl) { int off_diff = m_off - cur_off; - int ptr_bits = sizeof(void *) * 8; + int ptr_bits = d->ptr_sz * 8; if (off_diff <= 0) /* no gap */ @@ -870,7 +879,7 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, ": %d", m_sz); off = m_off + m_sz; } else { - m_sz = max(0, btf__resolve_size(d->btf, m->type)); + m_sz = max((__s64)0, btf__resolve_size(d->btf, m->type)); off = m_off + m_sz * 8; } btf_dump_printf(d, ";"); @@ -890,6 +899,32 @@ static void btf_dump_emit_struct_def(struct btf_dump *d, btf_dump_printf(d, " __attribute__((packed))"); } +static const char *missing_base_types[][2] = { + /* + * GCC emits typedefs to its internal __PolyX_t types when compiling Arm + * SIMD intrinsics. Alias them to standard base types. + */ + { "__Poly8_t", "unsigned char" }, + { "__Poly16_t", "unsigned short" }, + { "__Poly64_t", "unsigned long long" }, + { "__Poly128_t", "unsigned __int128" }, +}; + +static void btf_dump_emit_missing_aliases(struct btf_dump *d, __u32 id, + const struct btf_type *t) +{ + const char *name = btf_dump_type_name(d, id); + int i; + + for (i = 0; i < ARRAY_SIZE(missing_base_types); i++) { + if (strcmp(name, missing_base_types[i][0]) == 0) { + btf_dump_printf(d, "typedef %s %s;\n\n", + missing_base_types[i][1], name); + break; + } + } +} + static void btf_dump_emit_enum_fwd(struct btf_dump *d, __u32 id, const struct btf_type *t) { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0a06124f7999..0ad0b0491e1f 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2264,7 +2264,7 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict, data = elf_getdata(scn, NULL); if (!scn || !data) { pr_warn("failed to get Elf_Data from map section %d (%s)\n", - obj->efile.maps_shndx, MAPS_ELF_SEC); + obj->efile.btf_maps_shndx, MAPS_ELF_SEC); return -EINVAL; } @@ -2434,6 +2434,8 @@ static int bpf_object__init_btf(struct bpf_object *obj, BTF_ELF_SEC, err); goto out; } + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); err = 0; } if (btf_ext_data) { @@ -2542,6 +2544,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj) if (IS_ERR(kern_btf)) return PTR_ERR(kern_btf); + /* enforce 8-byte pointers for BPF-targeted BTFs */ + btf__set_pointer_size(obj->btf, 8); bpf_object__sanitize_btf(obj, kern_btf); } @@ -3478,10 +3482,11 @@ bpf_object__probe_global_data(struct bpf_object *obj) map = bpf_create_map_xattr(&map_attr); if (map < 0) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + ret = -errno; + cp = libbpf_strerror_r(ret, errmsg, sizeof(errmsg)); pr_warn("Error in %s():%s(%d). Couldn't create simple array map.\n", - __func__, cp, errno); - return -errno; + __func__, cp, -ret); + return ret; } insns[0].imm = map; @@ -5194,7 +5199,8 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj, static int bpf_object__collect_map_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data) { - int i, j, nrels, new_sz, ptr_sz = sizeof(void *); + const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *); + int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; const struct btf_member *member; @@ -5243,7 +5249,7 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, vi = btf_var_secinfos(sec) + map->btf_var_idx; if (vi->offset <= rel.r_offset && - rel.r_offset + sizeof(void *) <= vi->offset + vi->size) + rel.r_offset + bpf_ptr_sz <= vi->offset + vi->size) break; } if (j == obj->nr_maps) { @@ -5279,17 +5285,20 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, return -EINVAL; moff = rel.r_offset - vi->offset - moff; - if (moff % ptr_sz) + /* here we use BPF pointer size, which is always 64 bit, as we + * are parsing ELF that was built for BPF target + */ + if (moff % bpf_ptr_sz) return -EINVAL; - moff /= ptr_sz; + moff /= bpf_ptr_sz; if (moff >= map->init_slots_sz) { new_sz = moff + 1; - tmp = realloc(map->init_slots, new_sz * ptr_sz); + tmp = realloc(map->init_slots, new_sz * host_ptr_sz); if (!tmp) return -ENOMEM; map->init_slots = tmp; memset(map->init_slots + map->init_slots_sz, 0, - (new_sz - map->init_slots_sz) * ptr_sz); + (new_sz - map->init_slots_sz) * host_ptr_sz); map->init_slots_sz = new_sz; } map->init_slots[moff] = targ_map; @@ -6012,9 +6021,10 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path, } if (bpf_obj_pin(prog->instances.fds[instance], path)) { - cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg)); + err = -errno; + cp = libbpf_strerror_r(err, errmsg, sizeof(errmsg)); pr_warn("failed to pin program: %s\n", cp); - return -errno; + return err; } pr_debug("pinned program '%s'\n", path); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 0c4722bfdd0a..e35bd6cdbdbf 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -295,5 +295,7 @@ LIBBPF_0.1.0 { bpf_program__set_sk_lookup; btf__parse; btf__parse_raw; + btf__pointer_size; btf__set_fd; + btf__set_pointer_size; } LIBBPF_0.0.9; diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 1bb204cee853..9a0946ddb705 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -6,7 +6,6 @@ test_lpm_map test_tag FEATURE-DUMP.libbpf fixdep -test_align test_dev_cgroup /test_progs* test_tcpbpf_user diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index a83b5827532f..fc946b7ac288 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -32,7 +32,7 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ - test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ + test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ test_cgroup_storage \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl \ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c index 7afa4160416f..284d5921c345 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c @@ -159,15 +159,15 @@ void test_bpf_obj_id(void) /* Check getting link info */ info_len = sizeof(struct bpf_link_info) * 2; bzero(&link_infos[i], info_len); - link_infos[i].raw_tracepoint.tp_name = (__u64)&tp_name; + link_infos[i].raw_tracepoint.tp_name = ptr_to_u64(&tp_name); link_infos[i].raw_tracepoint.tp_name_len = sizeof(tp_name); err = bpf_obj_get_info_by_fd(bpf_link__fd(links[i]), &link_infos[i], &info_len); if (CHECK(err || link_infos[i].type != BPF_LINK_TYPE_RAW_TRACEPOINT || link_infos[i].prog_id != prog_infos[i].id || - link_infos[i].raw_tracepoint.tp_name != (__u64)&tp_name || - strcmp((char *)link_infos[i].raw_tracepoint.tp_name, + link_infos[i].raw_tracepoint.tp_name != ptr_to_u64(&tp_name) || + strcmp(u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter") || info_len != sizeof(struct bpf_link_info), "get-link-info(fd)", @@ -178,7 +178,7 @@ void test_bpf_obj_id(void) link_infos[i].type, BPF_LINK_TYPE_RAW_TRACEPOINT, link_infos[i].id, link_infos[i].prog_id, prog_infos[i].id, - (char *)link_infos[i].raw_tracepoint.tp_name, + (const char *)u64_to_ptr(link_infos[i].raw_tracepoint.tp_name), "sys_enter")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c index cb33a7ee4e04..39fb81d9daeb 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c @@ -12,15 +12,16 @@ void btf_dump_printf(void *ctx, const char *fmt, va_list args) static struct btf_dump_test_case { const char *name; const char *file; + bool known_ptr_sz; struct btf_dump_opts opts; } btf_dump_test_cases[] = { - {"btf_dump: syntax", "btf_dump_test_case_syntax", {}}, - {"btf_dump: ordering", "btf_dump_test_case_ordering", {}}, - {"btf_dump: padding", "btf_dump_test_case_padding", {}}, - {"btf_dump: packing", "btf_dump_test_case_packing", {}}, - {"btf_dump: bitfields", "btf_dump_test_case_bitfields", {}}, - {"btf_dump: multidim", "btf_dump_test_case_multidim", {}}, - {"btf_dump: namespacing", "btf_dump_test_case_namespacing", {}}, + {"btf_dump: syntax", "btf_dump_test_case_syntax", true, {}}, + {"btf_dump: ordering", "btf_dump_test_case_ordering", false, {}}, + {"btf_dump: padding", "btf_dump_test_case_padding", true, {}}, + {"btf_dump: packing", "btf_dump_test_case_packing", true, {}}, + {"btf_dump: bitfields", "btf_dump_test_case_bitfields", true, {}}, + {"btf_dump: multidim", "btf_dump_test_case_multidim", false, {}}, + {"btf_dump: namespacing", "btf_dump_test_case_namespacing", false, {}}, }; static int btf_dump_all_types(const struct btf *btf, @@ -62,6 +63,18 @@ static int test_btf_dump_case(int n, struct btf_dump_test_case *t) goto done; } + /* tests with t->known_ptr_sz have no "long" or "unsigned long" type, + * so it's impossible to determine correct pointer size; but if they + * do, it should be 8 regardless of host architecture, becaues BPF + * target is always 64-bit + */ + if (!t->known_ptr_sz) { + btf__set_pointer_size(btf, 8); + } else { + CHECK(btf__pointer_size(btf) != 8, "ptr_sz", "exp %d, got %zu\n", + 8, btf__pointer_size(btf)); + } + snprintf(out_file, sizeof(out_file), "/tmp/%s.output.XXXXXX", t->file); fd = mkstemp(out_file); if (CHECK(fd < 0, "create_tmp", "failed to create file: %d\n", fd)) { diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c index b093787e9448..1931a158510e 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_extern.c +++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c @@ -159,8 +159,8 @@ void test_core_extern(void) exp = (uint64_t *)&t->data; for (j = 0; j < n; j++) { CHECK(got[j] != exp[j], "check_res", - "result #%d: expected %lx, but got %lx\n", - j, exp[j], got[j]); + "result #%d: expected %llx, but got %llx\n", + j, (__u64)exp[j], (__u64)got[j]); } cleanup: test_core_extern__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 084ed26a7d78..a54eafc5e4b3 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -237,8 +237,8 @@ .union_sz = sizeof(((type *)0)->union_field), \ .arr_sz = sizeof(((type *)0)->arr_field), \ .arr_elem_sz = sizeof(((type *)0)->arr_field[0]), \ - .ptr_sz = sizeof(((type *)0)->ptr_field), \ - .enum_sz = sizeof(((type *)0)->enum_field), \ + .ptr_sz = 8, /* always 8-byte pointer for BPF */ \ + .enum_sz = sizeof(((type *)0)->enum_field), \ } #define SIZE_CASE(name) { \ @@ -432,20 +432,20 @@ static struct core_reloc_test_case test_cases[] = { .sb4 = -1, .sb20 = -0x17654321, .u32 = 0xBEEF, - .s32 = -0x3FEDCBA987654321, + .s32 = -0x3FEDCBA987654321LL, }), BITFIELDS_CASE(bitfields___bitfield_vs_int, { - .ub1 = 0xFEDCBA9876543210, + .ub1 = 0xFEDCBA9876543210LL, .ub2 = 0xA6, - .ub7 = -0x7EDCBA987654321, - .sb4 = -0x6123456789ABCDE, - .sb20 = 0xD00D, + .ub7 = -0x7EDCBA987654321LL, + .sb4 = -0x6123456789ABCDELL, + .sb20 = 0xD00DLL, .u32 = -0x76543, - .s32 = 0x0ADEADBEEFBADB0B, + .s32 = 0x0ADEADBEEFBADB0BLL, }), BITFIELDS_CASE(bitfields___just_big_enough, { - .ub1 = 0xF, - .ub2 = 0x0812345678FEDCBA, + .ub1 = 0xFLL, + .ub2 = 0x0812345678FEDCBALL, }), BITFIELDS_ERR_CASE(bitfields___err_too_big_bitfield), diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c index a895bfed55db..197d0d217b56 100644 --- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c @@ -16,7 +16,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, __u32 duration = 0, retval; struct bpf_map *data_map; const int zero = 0; - u64 *result = NULL; + __u64 *result = NULL; err = bpf_prog_load(target_obj_file, BPF_PROG_TYPE_UNSPEC, &pkt_obj, &pkt_fd); @@ -29,7 +29,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, link = calloc(sizeof(struct bpf_link *), prog_cnt); prog = calloc(sizeof(struct bpf_program *), prog_cnt); - result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64)); + result = malloc((prog_cnt + 32 /* spare */) * sizeof(__u64)); if (CHECK(!link || !prog || !result, "alloc_memory", "failed to alloc memory")) goto close_prog; @@ -72,7 +72,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file, goto close_prog; for (i = 0; i < prog_cnt; i++) - if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %ld\n", + if (CHECK(result[i] != 1, "result", "fexit_bpf2bpf failed err %llu\n", result[i])) goto close_prog; diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index f11f187990e9..cd6dc80edf18 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -591,7 +591,7 @@ void test_flow_dissector(void) CHECK_ATTR(tattr.data_size_out != sizeof(flow_keys) || err || tattr.retval != 1, tests[i].name, - "err %d errno %d retval %d duration %d size %u/%lu\n", + "err %d errno %d retval %d duration %d size %u/%zu\n", err, errno, tattr.retval, tattr.duration, tattr.data_size_out, sizeof(flow_keys)); CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c index e3cb62b0a110..9efa7e50eab2 100644 --- a/tools/testing/selftests/bpf/prog_tests/global_data.c +++ b/tools/testing/selftests/bpf/prog_tests/global_data.c @@ -5,7 +5,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) { int i, err, map_fd; - uint64_t num; + __u64 num; map_fd = bpf_find_map(__func__, obj, "result_number"); if (CHECK_FAIL(map_fd < 0)) @@ -14,7 +14,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) struct { char *name; uint32_t key; - uint64_t num; + __u64 num; } tests[] = { { "relocate .bss reference", 0, 0 }, { "relocate .data reference", 1, 42 }, @@ -32,7 +32,7 @@ static void test_global_data_number(struct bpf_object *obj, __u32 duration) for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) { err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num); CHECK(err || num != tests[i].num, tests[i].name, - "err %d result %lx expected %lx\n", + "err %d result %llx expected %llx\n", err, num, tests[i].num); } } diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 43d0b5578f46..9c3c5c0f068f 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -21,7 +21,7 @@ void test_mmap(void) const long page_size = sysconf(_SC_PAGE_SIZE); int err, duration = 0, i, data_map_fd, data_map_id, tmp_fd, rdmap_fd; struct bpf_map *data_map, *bss_map; - void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2; + void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp0, *tmp1, *tmp2; struct test_mmap__bss *bss_data; struct bpf_map_info map_info; __u32 map_info_sz = sizeof(map_info); @@ -183,16 +183,23 @@ void test_mmap(void) /* check some more advanced mmap() manipulations */ + tmp0 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_ANONYMOUS, + -1, 0); + if (CHECK(tmp0 == MAP_FAILED, "adv_mmap0", "errno %d\n", errno)) + goto cleanup; + /* map all but last page: pages 1-3 mapped */ - tmp1 = mmap(NULL, 3 * page_size, PROT_READ, MAP_SHARED, + tmp1 = mmap(tmp0, 3 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, data_map_fd, 0); - if (CHECK(tmp1 == MAP_FAILED, "adv_mmap1", "errno %d\n", errno)) + if (CHECK(tmp0 != tmp1, "adv_mmap1", "tmp0: %p, tmp1: %p\n", tmp0, tmp1)) { + munmap(tmp0, 4 * page_size); goto cleanup; + } /* unmap second page: pages 1, 3 mapped */ err = munmap(tmp1 + page_size, page_size); if (CHECK(err, "adv_mmap2", "errno %d\n", errno)) { - munmap(tmp1, map_sz); + munmap(tmp1, 4 * page_size); goto cleanup; } @@ -201,7 +208,7 @@ void test_mmap(void) MAP_SHARED | MAP_FIXED, data_map_fd, 0); if (CHECK(tmp2 == MAP_FAILED, "adv_mmap3", "errno %d\n", errno)) { munmap(tmp1, page_size); - munmap(tmp1 + 2*page_size, page_size); + munmap(tmp1 + 2*page_size, 2 * page_size); goto cleanup; } CHECK(tmp1 + page_size != tmp2, "adv_mmap4", @@ -211,7 +218,7 @@ void test_mmap(void) tmp2 = mmap(tmp1, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, data_map_fd, 0); if (CHECK(tmp2 == MAP_FAILED, "adv_mmap5", "errno %d\n", errno)) { - munmap(tmp1, 3 * page_size); /* unmap page 1 */ + munmap(tmp1, 4 * page_size); /* unmap page 1 */ goto cleanup; } CHECK(tmp1 != tmp2, "adv_mmap6", "tmp1: %p, tmp2: %p\n", tmp1, tmp2); diff --git a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c index dde2b7ae7bc9..935a294f049a 100644 --- a/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c +++ b/tools/testing/selftests/bpf/prog_tests/prog_run_xattr.c @@ -28,7 +28,7 @@ void test_prog_run_xattr(void) "err %d errno %d retval %d\n", err, errno, tattr.retval); CHECK_ATTR(tattr.data_size_out != sizeof(pkt_v4), "data_size_out", - "incorrect output size, want %lu have %u\n", + "incorrect output size, want %zu have %u\n", sizeof(pkt_v4), tattr.data_size_out); CHECK_ATTR(buf[5] != 0, "overflow", diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c index c571584c00f5..9ff0412e1fd3 100644 --- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c +++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c @@ -309,6 +309,7 @@ static void v4_to_v6(struct sockaddr_storage *ss) v6->sin6_addr.s6_addr[10] = 0xff; v6->sin6_addr.s6_addr[11] = 0xff; memcpy(&v6->sin6_addr.s6_addr[12], &v4.sin_addr.s_addr, 4); + memset(&v6->sin6_addr.s6_addr[0], 0, 10); } static int udp_recv_send(int server_fd) diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c index 25de86af2d03..fafeddaad6a9 100644 --- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c +++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c @@ -81,7 +81,7 @@ void test_skb_ctx(void) CHECK_ATTR(tattr.ctx_size_out != sizeof(skb), "ctx_size_out", - "incorrect output size, want %lu have %u\n", + "incorrect output size, want %zu have %u\n", sizeof(skb), tattr.ctx_size_out); for (i = 0; i < 5; i++) diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c index 25b068591e9a..193002b14d7f 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c +++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c @@ -19,7 +19,7 @@ static int libbpf_debug_print(enum libbpf_print_level level, log_buf = va_arg(args, char *); if (!log_buf) goto out; - if (strstr(log_buf, err_str) == 0) + if (err_str && strstr(log_buf, err_str) == 0) found = true; out: printf(format, log_buf); diff --git a/tools/testing/selftests/bpf/prog_tests/varlen.c b/tools/testing/selftests/bpf/prog_tests/varlen.c index c75525eab02c..dd324b4933db 100644 --- a/tools/testing/selftests/bpf/prog_tests/varlen.c +++ b/tools/testing/selftests/bpf/prog_tests/varlen.c @@ -44,25 +44,25 @@ void test_varlen(void) CHECK_VAL(bss->payload1_len2, size2); CHECK_VAL(bss->total1, size1 + size2); CHECK(memcmp(bss->payload1, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload2_len1, size1); CHECK_VAL(data->payload2_len2, size2); CHECK_VAL(data->total2, size1 + size2); CHECK(memcmp(data->payload2, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload3_len1, size1); CHECK_VAL(data->payload3_len2, size2); CHECK_VAL(data->total3, size1 + size2); CHECK(memcmp(data->payload3, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); CHECK_VAL(data->payload4_len1, size1); CHECK_VAL(data->payload4_len2, size2); CHECK_VAL(data->total4, size1 + size2); CHECK(memcmp(data->payload4, exp_str, size1 + size2), "content_check", - "doesn't match!"); + "doesn't match!\n"); cleanup: test_varlen__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index 34d84717c946..69139ed66216 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -1,5 +1,10 @@ #include <stdint.h> #include <stdbool.h> + +void preserce_ptr_sz_fn(long x) {} + +#define __bpf_aligned __attribute__((aligned(8))) + /* * KERNEL */ @@ -444,51 +449,51 @@ struct core_reloc_primitives { char a; int b; enum core_reloc_primitives_enum c; - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___diff_enum_def { char a; int b; - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; enum { X = 100, Y = 200, - } c; /* inline enum def with differing set of values */ + } c __bpf_aligned; /* inline enum def with differing set of values */ }; struct core_reloc_primitives___diff_func_proto { - void (*f)(int); /* incompatible function prototype */ - void *d; - enum core_reloc_primitives_enum c; + void (*f)(int) __bpf_aligned; /* incompatible function prototype */ + void *d __bpf_aligned; + enum core_reloc_primitives_enum c __bpf_aligned; int b; char a; }; struct core_reloc_primitives___diff_ptr_type { - const char * const d; /* different pointee type + modifiers */ - char a; + const char * const d __bpf_aligned; /* different pointee type + modifiers */ + char a __bpf_aligned; int b; enum core_reloc_primitives_enum c; - int (*f)(const char *); + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_enum { char a[1]; int b; int c; /* int instead of enum */ - void *d; - int (*f)(const char *); + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_int { char a[1]; - int *b; /* ptr instead of int */ - enum core_reloc_primitives_enum c; - void *d; - int (*f)(const char *); + int *b __bpf_aligned; /* ptr instead of int */ + enum core_reloc_primitives_enum c __bpf_aligned; + void *d __bpf_aligned; + int (*f)(const char *) __bpf_aligned; }; struct core_reloc_primitives___err_non_ptr { @@ -496,7 +501,7 @@ struct core_reloc_primitives___err_non_ptr { int b; enum core_reloc_primitives_enum c; int d; /* int instead of ptr */ - int (*f)(const char *); + int (*f)(const char *) __bpf_aligned; }; /* @@ -507,7 +512,7 @@ struct core_reloc_mods_output { }; typedef const int int_t; -typedef const char *char_ptr_t; +typedef const char *char_ptr_t __bpf_aligned; typedef const int arr_t[7]; struct core_reloc_mods_substruct { @@ -523,9 +528,9 @@ typedef struct { struct core_reloc_mods { int a; int_t b; - char *c; + char *c __bpf_aligned; char_ptr_t d; - int e[3]; + int e[3] __bpf_aligned; arr_t f; struct core_reloc_mods_substruct g; core_reloc_mods_substruct_t h; @@ -535,9 +540,9 @@ struct core_reloc_mods { struct core_reloc_mods___mod_swap { int b; int_t a; - char *d; + char *d __bpf_aligned; char_ptr_t c; - int f[3]; + int f[3] __bpf_aligned; arr_t e; struct { int y; @@ -555,7 +560,7 @@ typedef arr1_t arr2_t; typedef arr2_t arr3_t; typedef arr3_t arr4_t; -typedef const char * const volatile fancy_char_ptr_t; +typedef const char * const volatile fancy_char_ptr_t __bpf_aligned; typedef core_reloc_mods_substruct_t core_reloc_mods_substruct_tt; @@ -567,7 +572,7 @@ struct core_reloc_mods___typedefs { arr4_t e; fancy_char_ptr_t d; fancy_char_ptr_t c; - int3_t b; + int3_t b __bpf_aligned; int3_t a; }; @@ -739,19 +744,19 @@ struct core_reloc_bitfields___bit_sz_change { int8_t sb4: 1; /* 4 -> 1 */ int32_t sb20: 30; /* 20 -> 30 */ /* non-bitfields */ - uint16_t u32; /* 32 -> 16 */ - int64_t s32; /* 32 -> 64 */ + uint16_t u32; /* 32 -> 16 */ + int64_t s32 __bpf_aligned; /* 32 -> 64 */ }; /* turn bitfield into non-bitfield and vice versa */ struct core_reloc_bitfields___bitfield_vs_int { uint64_t ub1; /* 3 -> 64 non-bitfield */ uint8_t ub2; /* 20 -> 8 non-bitfield */ - int64_t ub7; /* 7 -> 64 non-bitfield signed */ - int64_t sb4; /* 4 -> 64 non-bitfield signed */ - uint64_t sb20; /* 20 -> 16 non-bitfield unsigned */ - int32_t u32: 20; /* 32 non-bitfield -> 20 bitfield */ - uint64_t s32: 60; /* 32 non-bitfield -> 60 bitfield */ + int64_t ub7 __bpf_aligned; /* 7 -> 64 non-bitfield signed */ + int64_t sb4 __bpf_aligned; /* 4 -> 64 non-bitfield signed */ + uint64_t sb20 __bpf_aligned; /* 20 -> 16 non-bitfield unsigned */ + int32_t u32: 20; /* 32 non-bitfield -> 20 bitfield */ + uint64_t s32: 60 __bpf_aligned; /* 32 non-bitfield -> 60 bitfield */ }; struct core_reloc_bitfields___just_big_enough { diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 1f1966e86e9f..3e6912e4df3d 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -54,6 +54,7 @@ SEC("sockops") int bpf_testcb(struct bpf_sock_ops *skops) { char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)]; + struct bpf_sock_ops *reuse = skops; struct tcphdr *thdr; int good_call_rv = 0; int bad_call_rv = 0; @@ -62,6 +63,46 @@ int bpf_testcb(struct bpf_sock_ops *skops) int v = 0; int op; + /* Test reading fields in bpf_sock_ops using single register */ + asm volatile ( + "%[reuse] = *(u32 *)(%[reuse] +96)" + : [reuse] "+r"(reuse) + :); + + asm volatile ( + "%[op] = *(u32 *)(%[skops] +96)" + : [op] "+r"(op) + : [skops] "r"(skops) + :); + + asm volatile ( + "r9 = %[skops];\n" + "r8 = *(u32 *)(r9 +164);\n" + "*(u32 *)(r9 +164) = r8;\n" + :: [skops] "r"(skops) + : "r9", "r8"); + + asm volatile ( + "r1 = %[skops];\n" + "r1 = *(u64 *)(r1 +184);\n" + "if r1 == 0 goto +1;\n" + "r1 = *(u32 *)(r1 +4);\n" + :: [skops] "r"(skops):"r1"); + + asm volatile ( + "r9 = %[skops];\n" + "r9 = *(u64 *)(r9 +184);\n" + "if r9 == 0 goto +1;\n" + "r9 = *(u32 *)(r9 +4);\n" + :: [skops] "r"(skops):"r9"); + + asm volatile ( + "r1 = %[skops];\n" + "r2 = *(u64 *)(r1 +184);\n" + "if r2 == 0 goto +1;\n" + "r2 = *(u32 *)(r2 +4);\n" + :: [skops] "r"(skops):"r1", "r2"); + op = (int) skops->op; update_event_map(op); diff --git a/tools/testing/selftests/bpf/progs/test_varlen.c b/tools/testing/selftests/bpf/progs/test_varlen.c index cd4b72c55dfe..913acdffd90f 100644 --- a/tools/testing/selftests/bpf/progs/test_varlen.c +++ b/tools/testing/selftests/bpf/progs/test_varlen.c @@ -15,9 +15,9 @@ int test_pid = 0; bool capture = false; /* .bss */ -long payload1_len1 = 0; -long payload1_len2 = 0; -long total1 = 0; +__u64 payload1_len1 = 0; +__u64 payload1_len2 = 0; +__u64 total1 = 0; char payload1[MAX_LEN + MAX_LEN] = {}; /* .data */ diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 305fae8f80a9..c75fc6447186 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -3883,7 +3883,7 @@ static int test_big_btf_info(unsigned int test_num) info_garbage.garbage = 0; err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len); if (CHECK(err || info_len != sizeof(*info), - "err:%d errno:%d info_len:%u sizeof(*info):%lu", + "err:%d errno:%d info_len:%u sizeof(*info):%zu", err, errno, info_len, sizeof(*info))) { err = -1; goto done; @@ -4094,7 +4094,7 @@ static int do_test_get_info(unsigned int test_num) if (CHECK(err || !info.id || info_len != sizeof(info) || info.btf_size != raw_btf_size || (ret = memcmp(raw_btf, user_btf, expected_nbytes)), - "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", + "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%zu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d", err, errno, info.id, info_len, sizeof(info), raw_btf_size, info.btf_size, expected_nbytes, ret)) { err = -1; @@ -4730,7 +4730,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, nexpected_line = snprintf(expected_line, line_size, "%s%u: {%u,0,%d,0x%x,0x%x,0x%x," - "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s," + "{%llu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s," "%u,0x%x,[[%d,%d],[%d,%d]]}\n", percpu_map ? "\tcpu" : "", percpu_map ? cpu : next_key, @@ -4738,7 +4738,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind, v->unused_bits2a, v->bits28, v->unused_bits2b, - v->ui64, + (__u64)v->ui64, v->ui8a[0], v->ui8a[1], v->ui8a[2], v->ui8a[3], v->ui8a[4], v->ui8a[5], diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 6e09bf738473..dbb820dde138 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -135,6 +135,11 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +static inline void *u64_to_ptr(__u64 ptr) +{ + return (void *) (unsigned long) ptr; +} + int bpf_find_map(const char *test, struct bpf_object *obj, const char *name); int compare_map_keys(int map1_fd, int map2_fd); int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len); diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index 8162c58a1234..b8d14f9db5f9 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -40,11 +40,11 @@ static void guest_code(void) /* Single step test, covers 2 basic instructions and 2 emulated */ asm volatile("ss_start: " - "xor %%rax,%%rax\n\t" + "xor %%eax,%%eax\n\t" "cpuid\n\t" "movl $0x1a0,%%ecx\n\t" "rdmsr\n\t" - : : : "rax", "ecx"); + : : : "eax", "ebx", "ecx", "edx"); /* DR6.BD test */ asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax"); diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh index 18c5de53558a..bf361f30d6ef 100755 --- a/tools/testing/selftests/net/icmp_redirect.sh +++ b/tools/testing/selftests/net/icmp_redirect.sh @@ -180,6 +180,8 @@ setup() ;; r[12]) ip netns exec $ns sysctl -q -w net.ipv4.ip_forward=1 ip netns exec $ns sysctl -q -w net.ipv4.conf.all.send_redirects=1 + ip netns exec $ns sysctl -q -w net.ipv4.conf.default.rp_filter=0 + ip netns exec $ns sysctl -q -w net.ipv4.conf.all.rp_filter=0 ip netns exec $ns sysctl -q -w net.ipv6.conf.all.forwarding=1 ip netns exec $ns sysctl -q -w net.ipv6.route.mtu_expires=10 diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh index d3e0809ab368..a47d1d832210 100755 --- a/tools/testing/selftests/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/netfilter/nft_flowtable.sh @@ -2,13 +2,18 @@ # SPDX-License-Identifier: GPL-2.0 # # This tests basic flowtable functionality. -# Creates following topology: +# Creates following default topology: # # Originator (MTU 9000) <-Router1-> MTU 1500 <-Router2-> Responder (MTU 2000) # Router1 is the one doing flow offloading, Router2 has no special # purpose other than having a link that is smaller than either Originator # and responder, i.e. TCPMSS announced values are too large and will still # result in fragmentation and/or PMTU discovery. +# +# You can check with different Orgininator/Link/Responder MTU eg: +# sh nft_flowtable.sh -o1000 -l500 -r100 +# + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -21,29 +26,18 @@ ns2out="" log_netns=$(sysctl -n net.netfilter.nf_log_all_netns) -nft --version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without nft tool" - exit $ksft_skip -fi - -ip -Version > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without ip tool" - exit $ksft_skip -fi - -which nc > /dev/null 2>&1 -if [ $? -ne 0 ];then - echo "SKIP: Could not run test without nc (netcat)" - exit $ksft_skip -fi +checktool (){ + $1 > /dev/null 2>&1 + if [ $? -ne 0 ];then + echo "SKIP: Could not $2" + exit $ksft_skip + fi +} -ip netns add nsr1 -if [ $? -ne 0 ];then - echo "SKIP: Could not create net namespace" - exit $ksft_skip -fi +checktool "nft --version" "run test without nft tool" +checktool "ip -Version" "run test without ip tool" +checktool "which nc" "run test without nc (netcat)" +checktool "ip netns add nsr1" "create net namespace" ip netns add ns1 ip netns add ns2 @@ -89,11 +83,24 @@ ip -net nsr2 addr add dead:2::1/64 dev veth1 # ns2 is going via nsr2 with a smaller mtu, so that TCPMSS announced by both peers # is NOT the lowest link mtu. -ip -net nsr1 link set veth0 mtu 9000 -ip -net ns1 link set eth0 mtu 9000 +omtu=9000 +lmtu=1500 +rmtu=2000 + +while getopts "o:l:r:" o +do + case $o in + o) omtu=$OPTARG;; + l) lmtu=$OPTARG;; + r) rmtu=$OPTARG;; + esac +done + +ip -net nsr1 link set veth0 mtu $omtu +ip -net ns1 link set eth0 mtu $omtu -ip -net nsr2 link set veth1 mtu 2000 -ip -net ns2 link set eth0 mtu 2000 +ip -net nsr2 link set veth1 mtu $rmtu +ip -net ns2 link set eth0 mtu $rmtu # transfer-net between nsr1 and nsr2. # these addresses are not used for connections. @@ -147,7 +154,7 @@ table inet filter { # as PMTUd is off. # This rule is deleted for the last test, when we expect PMTUd # to kick in and ensure all packets meet mtu requirements. - meta length gt 1500 accept comment something-to-grep-for + meta length gt $lmtu accept comment something-to-grep-for # next line blocks connection w.o. working offload. # we only do this for reverse dir, because we expect packets to @@ -243,8 +250,14 @@ test_tcp_forwarding_ip() sleep 3 - kill $lpid - kill $cpid + if ps -p $lpid > /dev/null;then + kill $lpid + fi + + if ps -p $cpid > /dev/null;then + kill $cpid + fi + wait check_transfer "$ns1in" "$ns2out" "ns1 -> ns2" diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 737666db02de..67cd0b88a6b6 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -482,7 +482,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; - need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end); + need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end, + range->flags); need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) |