diff options
315 files changed, 2490 insertions, 1527 deletions
@@ -842,10 +842,9 @@ D: ax25-utils maintainer. N: Helge Deller E: deller@gmx.de -E: hdeller@redhat.de -D: PA-RISC Linux hacker, LASI-, ASP-, WAX-, LCD/LED-driver -S: Schimmelsrain 1 -S: D-69231 Rauenberg +W: http://www.parisc-linux.org/ +D: PA-RISC Linux architecture maintainer +D: LASI-, ASP-, WAX-, LCD/LED-driver S: Germany N: Jean Delvare @@ -1361,7 +1360,7 @@ S: Stellenbosch, Western Cape S: South Africa N: Grant Grundler -E: grundler@parisc-linux.org +E: grantgrundler@gmail.com W: http://obmouse.sourceforge.net/ W: http://www.parisc-linux.org/ D: obmouse - rewrote Olivier Florent's Omnibook 600 "pop-up" mouse driver @@ -2492,7 +2491,7 @@ S: Syracuse, New York 13206 S: USA N: Kyle McMartin -E: kyle@parisc-linux.org +E: kyle@mcmartin.ca D: Linux/PARISC hacker D: AD1889 sound driver S: Ottawa, Canada @@ -3780,14 +3779,13 @@ S: 21513 Conradia Ct S: Cupertino, CA 95014 S: USA -N: Thibaut Varene -E: T-Bone@parisc-linux.org -W: http://www.parisc-linux.org/~varenet/ -P: 1024D/B7D2F063 E67C 0D43 A75E 12A5 BB1C FA2F 1E32 C3DA B7D2 F063 +N: Thibaut Varène +E: hacks+kernel@slashdirt.org +W: http://hacks.slashdirt.org/ D: PA-RISC port minion, PDC and GSCPS2 drivers, debuglocks and other bits D: Some ARM at91rm9200 bits, S1D13XXX FB driver, random patches here and there D: AD1889 sound driver -S: Paris, France +S: France N: Heikki Vatiainen E: hessu@cs.tut.fi diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst index 0797eec76be1..47e577264198 100644 --- a/Documentation/admin-guide/README.rst +++ b/Documentation/admin-guide/README.rst @@ -1,9 +1,9 @@ .. _readme: -Linux kernel release 4.x <http://kernel.org/> +Linux kernel release 5.x <http://kernel.org/> ============================================= -These are the release notes for Linux version 4. Read them carefully, +These are the release notes for Linux version 5. Read them carefully, as they tell you what this is all about, explain how to install the kernel, and what to do if something goes wrong. @@ -63,7 +63,7 @@ Installing the kernel source directory where you have permissions (e.g. your home directory) and unpack it:: - xz -cd linux-4.X.tar.xz | tar xvf - + xz -cd linux-5.x.tar.xz | tar xvf - Replace "X" with the version number of the latest kernel. @@ -72,26 +72,26 @@ Installing the kernel source files. They should match the library, and not get messed up by whatever the kernel-du-jour happens to be. - - You can also upgrade between 4.x releases by patching. Patches are + - You can also upgrade between 5.x releases by patching. Patches are distributed in the xz format. To install by patching, get all the newer patch files, enter the top level directory of the kernel source - (linux-4.X) and execute:: + (linux-5.x) and execute:: - xz -cd ../patch-4.x.xz | patch -p1 + xz -cd ../patch-5.x.xz | patch -p1 - Replace "x" for all versions bigger than the version "X" of your current + Replace "x" for all versions bigger than the version "x" of your current source tree, **in_order**, and you should be ok. You may want to remove the backup files (some-file-name~ or some-file-name.orig), and make sure that there are no failed patches (some-file-name# or some-file-name.rej). If there are, either you or I have made a mistake. - Unlike patches for the 4.x kernels, patches for the 4.x.y kernels + Unlike patches for the 5.x kernels, patches for the 5.x.y kernels (also known as the -stable kernels) are not incremental but instead apply - directly to the base 4.x kernel. For example, if your base kernel is 4.0 - and you want to apply the 4.0.3 patch, you must not first apply the 4.0.1 - and 4.0.2 patches. Similarly, if you are running kernel version 4.0.2 and - want to jump to 4.0.3, you must first reverse the 4.0.2 patch (that is, - patch -R) **before** applying the 4.0.3 patch. You can read more on this in + directly to the base 5.x kernel. For example, if your base kernel is 5.0 + and you want to apply the 5.0.3 patch, you must not first apply the 5.0.1 + and 5.0.2 patches. Similarly, if you are running kernel version 5.0.2 and + want to jump to 5.0.3, you must first reverse the 5.0.2 patch (that is, + patch -R) **before** applying the 5.0.3 patch. You can read more on this in :ref:`Documentation/process/applying-patches.rst <applying_patches>`. Alternatively, the script patch-kernel can be used to automate this @@ -114,7 +114,7 @@ Installing the kernel source Software requirements --------------------- - Compiling and running the 4.x kernels requires up-to-date + Compiling and running the 5.x kernels requires up-to-date versions of various software packages. Consult :ref:`Documentation/process/changes.rst <changes>` for the minimum version numbers required and how to get updates for these packages. Beware that using @@ -132,12 +132,12 @@ Build directory for the kernel place for the output files (including .config). Example:: - kernel source code: /usr/src/linux-4.X + kernel source code: /usr/src/linux-5.x build directory: /home/name/build/kernel To configure and build the kernel, use:: - cd /usr/src/linux-4.X + cd /usr/src/linux-5.x make O=/home/name/build/kernel menuconfig make O=/home/name/build/kernel sudo make O=/home/name/build/kernel modules_install install diff --git a/Documentation/networking/dsa/dsa.txt b/Documentation/networking/dsa/dsa.txt index 25170ad7d25b..101f2b2c69ad 100644 --- a/Documentation/networking/dsa/dsa.txt +++ b/Documentation/networking/dsa/dsa.txt @@ -533,16 +533,12 @@ Bridge VLAN filtering function that the driver has to call for each VLAN the given port is a member of. A switchdev object is used to carry the VID and bridge flags. -- port_fdb_prepare: bridge layer function invoked when the bridge prepares the - installation of a Forwarding Database entry. If the operation is not - supported, this function should return -EOPNOTSUPP to inform the bridge code - to fallback to a software implementation. No hardware setup must be done in - this function. See port_fdb_add for this and details. - - port_fdb_add: bridge layer function invoked when the bridge wants to install a Forwarding Database entry, the switch hardware should be programmed with the specified address in the specified VLAN Id in the forwarding database - associated with this VLAN ID + associated with this VLAN ID. If the operation is not supported, this + function should return -EOPNOTSUPP to inform the bridge code to fallback to + a software implementation. Note: VLAN ID 0 corresponds to the port private database, which, in the context of DSA, would be the its port-based VLAN, used by the associated bridge device. diff --git a/Documentation/networking/msg_zerocopy.rst b/Documentation/networking/msg_zerocopy.rst index fe46d4867e2d..18c1415e7bfa 100644 --- a/Documentation/networking/msg_zerocopy.rst +++ b/Documentation/networking/msg_zerocopy.rst @@ -7,7 +7,7 @@ Intro ===== The MSG_ZEROCOPY flag enables copy avoidance for socket send calls. -The feature is currently implemented for TCP sockets. +The feature is currently implemented for TCP and UDP sockets. Opportunity and Caveats diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 82236a17b5e6..97b7ca8b9b86 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -92,11 +92,11 @@ device. Switch ID ^^^^^^^^^ -The switchdev driver must implement the switchdev op switchdev_port_attr_get -for SWITCHDEV_ATTR_ID_PORT_PARENT_ID for each port netdev, returning the same -physical ID for each port of a switch. The ID must be unique between switches -on the same system. The ID does not need to be unique between switches on -different systems. +The switchdev driver must implement the net_device operation +ndo_get_port_parent_id for each port netdev, returning the same physical ID for +each port of a switch. The ID must be unique between switches on the same +system. The ID does not need to be unique between switches on different +systems. The switch ID is used to locate ports on a switch and to know if aggregated ports belong to the same switch. diff --git a/Documentation/process/applying-patches.rst b/Documentation/process/applying-patches.rst index dc2ddc345044..fbb9297e6360 100644 --- a/Documentation/process/applying-patches.rst +++ b/Documentation/process/applying-patches.rst @@ -216,14 +216,14 @@ You can use the ``interdiff`` program (http://cyberelk.net/tim/patchutils/) to generate a patch representing the differences between two patches and then apply the result. -This will let you move from something like 4.7.2 to 4.7.3 in a single +This will let you move from something like 5.7.2 to 5.7.3 in a single step. The -z flag to interdiff will even let you feed it patches in gzip or bzip2 compressed form directly without the use of zcat or bzcat or manual decompression. -Here's how you'd go from 4.7.2 to 4.7.3 in a single step:: +Here's how you'd go from 5.7.2 to 5.7.3 in a single step:: - interdiff -z ../patch-4.7.2.gz ../patch-4.7.3.gz | patch -p1 + interdiff -z ../patch-5.7.2.gz ../patch-5.7.3.gz | patch -p1 Although interdiff may save you a step or two you are generally advised to do the additional steps since interdiff can get things wrong in some cases. @@ -245,62 +245,67 @@ The patches are available at http://kernel.org/ Most recent patches are linked from the front page, but they also have specific homes. -The 4.x.y (-stable) and 4.x patches live at +The 5.x.y (-stable) and 5.x patches live at - https://www.kernel.org/pub/linux/kernel/v4.x/ + https://www.kernel.org/pub/linux/kernel/v5.x/ -The -rc patches live at +The -rc patches are not stored on the webserver but are generated on +demand from git tags such as - https://www.kernel.org/pub/linux/kernel/v4.x/testing/ + https://git.kernel.org/torvalds/p/v5.1-rc1/v5.0 +The stable -rc patches live at -The 4.x kernels + https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/ + + +The 5.x kernels =============== These are the base stable releases released by Linus. The highest numbered release is the most recent. If regressions or other serious flaws are found, then a -stable fix patch -will be released (see below) on top of this base. Once a new 4.x base +will be released (see below) on top of this base. Once a new 5.x base kernel is released, a patch is made available that is a delta between the -previous 4.x kernel and the new one. +previous 5.x kernel and the new one. -To apply a patch moving from 4.6 to 4.7, you'd do the following (note -that such patches do **NOT** apply on top of 4.x.y kernels but on top of the -base 4.x kernel -- if you need to move from 4.x.y to 4.x+1 you need to -first revert the 4.x.y patch). +To apply a patch moving from 5.6 to 5.7, you'd do the following (note +that such patches do **NOT** apply on top of 5.x.y kernels but on top of the +base 5.x kernel -- if you need to move from 5.x.y to 5.x+1 you need to +first revert the 5.x.y patch). Here are some examples:: - # moving from 4.6 to 4.7 + # moving from 5.6 to 5.7 - $ cd ~/linux-4.6 # change to kernel source dir - $ patch -p1 < ../patch-4.7 # apply the 4.7 patch + $ cd ~/linux-5.6 # change to kernel source dir + $ patch -p1 < ../patch-5.7 # apply the 5.7 patch $ cd .. - $ mv linux-4.6 linux-4.7 # rename source dir + $ mv linux-5.6 linux-5.7 # rename source dir - # moving from 4.6.1 to 4.7 + # moving from 5.6.1 to 5.7 - $ cd ~/linux-4.6.1 # change to kernel source dir - $ patch -p1 -R < ../patch-4.6.1 # revert the 4.6.1 patch - # source dir is now 4.6 - $ patch -p1 < ../patch-4.7 # apply new 4.7 patch + $ cd ~/linux-5.6.1 # change to kernel source dir + $ patch -p1 -R < ../patch-5.6.1 # revert the 5.6.1 patch + # source dir is now 5.6 + $ patch -p1 < ../patch-5.7 # apply new 5.7 patch $ cd .. - $ mv linux-4.6.1 linux-4.7 # rename source dir + $ mv linux-5.6.1 linux-5.7 # rename source dir -The 4.x.y kernels +The 5.x.y kernels ================= Kernels with 3-digit versions are -stable kernels. They contain small(ish) critical fixes for security problems or significant regressions discovered -in a given 4.x kernel. +in a given 5.x kernel. This is the recommended branch for users who want the most recent stable kernel and are not interested in helping test development/experimental versions. -If no 4.x.y kernel is available, then the highest numbered 4.x kernel is +If no 5.x.y kernel is available, then the highest numbered 5.x kernel is the current stable kernel. .. note:: @@ -308,23 +313,23 @@ the current stable kernel. The -stable team usually do make incremental patches available as well as patches against the latest mainline release, but I only cover the non-incremental ones below. The incremental ones can be found at - https://www.kernel.org/pub/linux/kernel/v4.x/incr/ + https://www.kernel.org/pub/linux/kernel/v5.x/incr/ -These patches are not incremental, meaning that for example the 4.7.3 -patch does not apply on top of the 4.7.2 kernel source, but rather on top -of the base 4.7 kernel source. +These patches are not incremental, meaning that for example the 5.7.3 +patch does not apply on top of the 5.7.2 kernel source, but rather on top +of the base 5.7 kernel source. -So, in order to apply the 4.7.3 patch to your existing 4.7.2 kernel -source you have to first back out the 4.7.2 patch (so you are left with a -base 4.7 kernel source) and then apply the new 4.7.3 patch. +So, in order to apply the 5.7.3 patch to your existing 5.7.2 kernel +source you have to first back out the 5.7.2 patch (so you are left with a +base 5.7 kernel source) and then apply the new 5.7.3 patch. Here's a small example:: - $ cd ~/linux-4.7.2 # change to the kernel source dir - $ patch -p1 -R < ../patch-4.7.2 # revert the 4.7.2 patch - $ patch -p1 < ../patch-4.7.3 # apply the new 4.7.3 patch + $ cd ~/linux-5.7.2 # change to the kernel source dir + $ patch -p1 -R < ../patch-5.7.2 # revert the 5.7.2 patch + $ patch -p1 < ../patch-5.7.3 # apply the new 5.7.3 patch $ cd .. - $ mv linux-4.7.2 linux-4.7.3 # rename the kernel source dir + $ mv linux-5.7.2 linux-5.7.3 # rename the kernel source dir The -rc kernels =============== @@ -343,38 +348,38 @@ This is a good branch to run for people who want to help out testing development kernels but do not want to run some of the really experimental stuff (such people should see the sections about -next and -mm kernels below). -The -rc patches are not incremental, they apply to a base 4.x kernel, just -like the 4.x.y patches described above. The kernel version before the -rcN +The -rc patches are not incremental, they apply to a base 5.x kernel, just +like the 5.x.y patches described above. The kernel version before the -rcN suffix denotes the version of the kernel that this -rc kernel will eventually turn into. -So, 4.8-rc5 means that this is the fifth release candidate for the 4.8 -kernel and the patch should be applied on top of the 4.7 kernel source. +So, 5.8-rc5 means that this is the fifth release candidate for the 5.8 +kernel and the patch should be applied on top of the 5.7 kernel source. Here are 3 examples of how to apply these patches:: - # first an example of moving from 4.7 to 4.8-rc3 + # first an example of moving from 5.7 to 5.8-rc3 - $ cd ~/linux-4.7 # change to the 4.7 source dir - $ patch -p1 < ../patch-4.8-rc3 # apply the 4.8-rc3 patch + $ cd ~/linux-5.7 # change to the 5.7 source dir + $ patch -p1 < ../patch-5.8-rc3 # apply the 5.8-rc3 patch $ cd .. - $ mv linux-4.7 linux-4.8-rc3 # rename the source dir + $ mv linux-5.7 linux-5.8-rc3 # rename the source dir - # now let's move from 4.8-rc3 to 4.8-rc5 + # now let's move from 5.8-rc3 to 5.8-rc5 - $ cd ~/linux-4.8-rc3 # change to the 4.8-rc3 dir - $ patch -p1 -R < ../patch-4.8-rc3 # revert the 4.8-rc3 patch - $ patch -p1 < ../patch-4.8-rc5 # apply the new 4.8-rc5 patch + $ cd ~/linux-5.8-rc3 # change to the 5.8-rc3 dir + $ patch -p1 -R < ../patch-5.8-rc3 # revert the 5.8-rc3 patch + $ patch -p1 < ../patch-5.8-rc5 # apply the new 5.8-rc5 patch $ cd .. - $ mv linux-4.8-rc3 linux-4.8-rc5 # rename the source dir + $ mv linux-5.8-rc3 linux-5.8-rc5 # rename the source dir - # finally let's try and move from 4.7.3 to 4.8-rc5 + # finally let's try and move from 5.7.3 to 5.8-rc5 - $ cd ~/linux-4.7.3 # change to the kernel source dir - $ patch -p1 -R < ../patch-4.7.3 # revert the 4.7.3 patch - $ patch -p1 < ../patch-4.8-rc5 # apply new 4.8-rc5 patch + $ cd ~/linux-5.7.3 # change to the kernel source dir + $ patch -p1 -R < ../patch-5.7.3 # revert the 5.7.3 patch + $ patch -p1 < ../patch-5.8-rc5 # apply new 5.8-rc5 patch $ cd .. - $ mv linux-4.7.3 linux-4.8-rc5 # rename the kernel source dir + $ mv linux-5.7.3 linux-5.8-rc5 # rename the kernel source dir The -mm patches and the linux-next tree diff --git a/Documentation/translations/it_IT/admin-guide/README.rst b/Documentation/translations/it_IT/admin-guide/README.rst index 80f5ffc94a9e..b37166817842 100644 --- a/Documentation/translations/it_IT/admin-guide/README.rst +++ b/Documentation/translations/it_IT/admin-guide/README.rst @@ -4,7 +4,7 @@ .. _it_readme: -Rilascio del kernel Linux 4.x <http://kernel.org/> +Rilascio del kernel Linux 5.x <http://kernel.org/> =================================================== .. warning:: diff --git a/MAINTAINERS b/MAINTAINERS index 35e6357f9d30..4f463de6e721 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -409,8 +409,7 @@ F: drivers/platform/x86/wmi.c F: include/uapi/linux/wmi.h AD1889 ALSA SOUND DRIVER -M: Thibaut Varene <T-Bone@parisc-linux.org> -W: http://wiki.parisc-linux.org/AD1889 +W: https://parisc.wiki.kernel.org/index.php/AD1889 L: linux-parisc@vger.kernel.org S: Maintained F: sound/pci/ad1889.* @@ -2865,7 +2864,7 @@ R: Martin KaFai Lau <kafai@fb.com> R: Song Liu <songliubraving@fb.com> R: Yonghong Song <yhs@fb.com> L: netdev@vger.kernel.org -L: linux-kernel@vger.kernel.org +L: bpf@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git Q: https://patchwork.ozlabs.org/project/netdev/list/?delegate=77147 @@ -2895,6 +2894,7 @@ N: bpf BPF JIT for ARM M: Shubham Bansal <illusionist.neo@gmail.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/arm/net/ @@ -2903,18 +2903,21 @@ M: Daniel Borkmann <daniel@iogearbox.net> M: Alexei Starovoitov <ast@kernel.org> M: Zi Shen Lim <zlim.lnx@gmail.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: arch/arm64/net/ BPF JIT for MIPS (32-BIT AND 64-BIT) M: Paul Burton <paul.burton@mips.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/mips/net/ BPF JIT for NFP NICs M: Jakub Kicinski <jakub.kicinski@netronome.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: drivers/net/ethernet/netronome/nfp/bpf/ @@ -2922,6 +2925,7 @@ BPF JIT for POWERPC (32-BIT AND 64-BIT) M: Naveen N. Rao <naveen.n.rao@linux.ibm.com> M: Sandipan Das <sandipan@linux.ibm.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/powerpc/net/ @@ -2929,6 +2933,7 @@ BPF JIT for S390 M: Martin Schwidefsky <schwidefsky@de.ibm.com> M: Heiko Carstens <heiko.carstens@de.ibm.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/s390/net/ X: arch/s390/net/pnet.c @@ -2936,12 +2941,14 @@ X: arch/s390/net/pnet.c BPF JIT for SPARC (32-BIT AND 64-BIT) M: David S. Miller <davem@davemloft.net> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/sparc/net/ BPF JIT for X86 32-BIT M: Wang YanQing <udknight@gmail.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: arch/x86/net/bpf_jit_comp32.c @@ -2949,6 +2956,7 @@ BPF JIT for X86 64-BIT M: Alexei Starovoitov <ast@kernel.org> M: Daniel Borkmann <daniel@iogearbox.net> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: arch/x86/net/ X: arch/x86/net/bpf_jit_comp32.c @@ -3403,9 +3411,8 @@ F: Documentation/media/v4l-drivers/cafe_ccic* F: drivers/media/platform/marvell-ccic/ CAIF NETWORK LAYER -M: Dmitry Tarnyagin <dmitry.tarnyagin@lockless.no> L: netdev@vger.kernel.org -S: Supported +S: Orphan F: Documentation/networking/caif/ F: drivers/net/caif/ F: include/uapi/linux/caif/ @@ -8524,6 +8531,7 @@ L7 BPF FRAMEWORK M: John Fastabend <john.fastabend@gmail.com> M: Daniel Borkmann <daniel@iogearbox.net> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: include/linux/skmsg.h F: net/core/skmsg.c @@ -11525,7 +11533,7 @@ F: Documentation/blockdev/paride.txt F: drivers/block/paride/ PARISC ARCHITECTURE -M: "James E.J. Bottomley" <jejb@parisc-linux.org> +M: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> M: Helge Deller <deller@gmx.de> L: linux-parisc@vger.kernel.org W: http://www.parisc-linux.org/ @@ -16751,6 +16759,7 @@ M: Jesper Dangaard Brouer <hawk@kernel.org> M: John Fastabend <john.fastabend@gmail.com> L: netdev@vger.kernel.org L: xdp-newbies@vger.kernel.org +L: bpf@vger.kernel.org S: Supported F: net/core/xdp.c F: include/net/xdp.h @@ -16764,6 +16773,7 @@ XDP SOCKETS (AF_XDP) M: Björn Töpel <bjorn.topel@intel.com> M: Magnus Karlsson <magnus.karlsson@intel.com> L: netdev@vger.kernel.org +L: bpf@vger.kernel.org S: Maintained F: kernel/bpf/xskmap.c F: net/xdp/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Shy Crocodile # *DOCUMENTATION* diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 376366a7db81..d750b302d5ab 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -191,7 +191,6 @@ config NR_CPUS config ARC_SMP_HALT_ON_RESET bool "Enable Halt-on-reset boot mode" - default y if ARC_UBOOT_SUPPORT help In SMP configuration cores can be configured as Halt-on-reset or they could all start at same time. For Halt-on-reset, non @@ -407,6 +406,14 @@ config ARC_HAS_ACCL_REGS (also referred to as r58:r59). These can also be used by gcc as GPR so kernel needs to save/restore per process +config ARC_IRQ_NO_AUTOSAVE + bool "Disable hardware autosave regfile on interrupts" + default n + help + On HS cores, taken interrupt auto saves the regfile on stack. + This is programmable and can be optionally disabled in which case + software INTERRUPT_PROLOGUE/EPILGUE do the needed work + endif # ISA_ARCV2 endmenu # "ARC CPU Configuration" @@ -515,17 +522,6 @@ config ARC_DBG_TLB_PARANOIA endif -config ARC_UBOOT_SUPPORT - bool "Support uboot arg Handling" - help - ARC Linux by default checks for uboot provided args as pointers to - external cmdline or DTB. This however breaks in absence of uboot, - when booting from Metaware debugger directly, as the registers are - not zeroed out on reset by mdb and/or ARCv2 based cores. The bogus - registers look like uboot args to kernel which then chokes. - So only enable the uboot arg checking/processing if users are sure - of uboot being in play. - config ARC_BUILTIN_DTB_NAME string "Built in DTB" help diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 6e84060e7c90..621f59407d76 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -31,7 +31,6 @@ CONFIG_ARC_CACHE_LINE_SHIFT=5 # CONFIG_ARC_HAS_LLSC is not set CONFIG_ARC_KVADDR_SIZE=402 CONFIG_ARC_EMUL_UNALIGNED=y -CONFIG_ARC_UBOOT_SUPPORT=y CONFIG_PREEMPT=y CONFIG_NET=y CONFIG_UNIX=y diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index 1e59a2e9c602..e447ace6fa1c 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -13,7 +13,6 @@ CONFIG_PARTITION_ADVANCED=y CONFIG_ARC_PLAT_AXS10X=y CONFIG_AXS103=y CONFIG_ISA_ARCV2=y -CONFIG_ARC_UBOOT_SUPPORT=y CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38" CONFIG_PREEMPT=y CONFIG_NET=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index b5c3f6c54b03..c82cdb10aaf4 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -15,8 +15,6 @@ CONFIG_AXS103=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set -# CONFIG_ARC_SMP_HALT_ON_RESET is not set -CONFIG_ARC_UBOOT_SUPPORT=y CONFIG_ARC_BUILTIN_DTB_NAME="vdk_hs38_smp" CONFIG_PREEMPT=y CONFIG_NET=y diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index f1b86cef0905..a27eafdc8260 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -151,6 +151,14 @@ struct bcr_isa_arcv2 { #endif }; +struct bcr_uarch_build_arcv2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad:8, prod:8, maj:8, min:8; +#else + unsigned int min:8, maj:8, prod:8, pad:8; +#endif +}; + struct bcr_mpy { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int pad:8, x1616:8, dsp:4, cycles:2, type:2, ver:8; diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index f393b663413e..2ad77fb43639 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -52,6 +52,17 @@ #define cache_line_size() SMP_CACHE_BYTES #define ARCH_DMA_MINALIGN SMP_CACHE_BYTES +/* + * Make sure slab-allocated buffers are 64-bit aligned when atomic64_t uses + * ARCv2 64-bit atomics (LLOCKD/SCONDD). This guarantess runtime 64-bit + * alignment for any atomic64_t embedded in buffer. + * Default ARCH_SLAB_MINALIGN is __alignof__(long long) which has a relaxed + * value of 4 (and not 8) in ARC ABI. + */ +#if defined(CONFIG_ARC_HAS_LL64) && defined(CONFIG_ARC_HAS_LLSC) +#define ARCH_SLAB_MINALIGN 8 +#endif + extern void arc_cache_init(void); extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len); extern void read_decode_cache_bcr(void); diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h index 309f4e6721b3..225e7df2d8ed 100644 --- a/arch/arc/include/asm/entry-arcv2.h +++ b/arch/arc/include/asm/entry-arcv2.h @@ -17,6 +17,33 @@ ; ; Now manually save: r12, sp, fp, gp, r25 +#ifdef CONFIG_ARC_IRQ_NO_AUTOSAVE +.ifnc \called_from, exception + st.as r9, [sp, -10] ; save r9 in it's final stack slot + sub sp, sp, 12 ; skip JLI, LDI, EI + + PUSH lp_count + PUSHAX lp_start + PUSHAX lp_end + PUSH blink + + PUSH r11 + PUSH r10 + + sub sp, sp, 4 ; skip r9 + + PUSH r8 + PUSH r7 + PUSH r6 + PUSH r5 + PUSH r4 + PUSH r3 + PUSH r2 + PUSH r1 + PUSH r0 +.endif +#endif + #ifdef CONFIG_ARC_HAS_ACCL_REGS PUSH r59 PUSH r58 @@ -86,6 +113,33 @@ POP r59 #endif +#ifdef CONFIG_ARC_IRQ_NO_AUTOSAVE +.ifnc \called_from, exception + POP r0 + POP r1 + POP r2 + POP r3 + POP r4 + POP r5 + POP r6 + POP r7 + POP r8 + POP r9 + POP r10 + POP r11 + + POP blink + POPAX lp_end + POPAX lp_start + + POP r9 + mov lp_count, r9 + + add sp, sp, 12 ; skip JLI, LDI, EI + ld.as r9, [sp, -10] ; reload r9 which got clobbered +.endif +#endif + .endm /*------------------------------------------------------------------------*/ diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h index c9173c02081c..eabc3efa6c6d 100644 --- a/arch/arc/include/asm/uaccess.h +++ b/arch/arc/include/asm/uaccess.h @@ -207,7 +207,7 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n) */ "=&r" (tmp), "+r" (to), "+r" (from) : - : "lp_count", "lp_start", "lp_end", "memory"); + : "lp_count", "memory"); return n; } @@ -433,7 +433,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) */ "=&r" (tmp), "+r" (to), "+r" (from) : - : "lp_count", "lp_start", "lp_end", "memory"); + : "lp_count", "memory"); return n; } @@ -653,7 +653,7 @@ static inline unsigned long __arc_clear_user(void __user *to, unsigned long n) " .previous \n" : "+r"(d_char), "+r"(res) : "i"(0) - : "lp_count", "lp_start", "lp_end", "memory"); + : "lp_count", "memory"); return res; } @@ -686,7 +686,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count) " .previous \n" : "+r"(res), "+r"(dst), "+r"(src), "=r"(val) : "g"(-EFAULT), "r"(count) - : "lp_count", "lp_start", "lp_end", "memory"); + : "lp_count", "memory"); return res; } diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index cc558a25b8fa..562089d62d9d 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -209,7 +209,9 @@ restore_regs: ;####### Return from Intr ####### debug_marker_l1: - bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot + ; bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot + btst r0, STATUS_DE_BIT ; Z flag set if bit clear + bnz .Lintr_ret_to_delay_slot ; branch if STATUS_DE_BIT set .Lisr_ret_fast_path: ; Handle special case #1: (Entry via Exception, Return via IRQ) diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S index 8b90d25a15cc..30e090625916 100644 --- a/arch/arc/kernel/head.S +++ b/arch/arc/kernel/head.S @@ -17,6 +17,7 @@ #include <asm/entry.h> #include <asm/arcregs.h> #include <asm/cache.h> +#include <asm/irqflags.h> .macro CPU_EARLY_SETUP @@ -47,6 +48,15 @@ sr r5, [ARC_REG_DC_CTRL] 1: + +#ifdef CONFIG_ISA_ARCV2 + ; Unaligned access is disabled at reset, so re-enable early as + ; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access + ; by default + lr r5, [status32] + bset r5, r5, STATUS_AD_BIT + kflag r5 +#endif .endm .section .init.text, "ax",@progbits @@ -90,15 +100,13 @@ ENTRY(stext) st.ab 0, [r5, 4] 1: -#ifdef CONFIG_ARC_UBOOT_SUPPORT ; Uboot - kernel ABI ; r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2 - ; r1 = magic number (board identity, unused as of now + ; r1 = magic number (always zero as of now) ; r2 = pointer to uboot provided cmdline or external DTB in mem - ; These are handled later in setup_arch() + ; These are handled later in handle_uboot_args() st r0, [@uboot_tag] st r2, [@uboot_arg] -#endif ; setup "current" tsk and optionally cache it in dedicated r25 mov r9, @init_task diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index 067ea362fb3e..cf18b3e5a934 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -49,11 +49,13 @@ void arc_init_IRQ(void) *(unsigned int *)&ictrl = 0; +#ifndef CONFIG_ARC_IRQ_NO_AUTOSAVE ictrl.save_nr_gpr_pairs = 6; /* r0 to r11 (r12 saved manually) */ ictrl.save_blink = 1; ictrl.save_lp_regs = 1; /* LP_COUNT, LP_START, LP_END */ ictrl.save_u_to_u = 0; /* user ctxt saved on kernel stack */ ictrl.save_idx_regs = 1; /* JLI, LDI, EI */ +#endif WRITE_AUX(AUX_IRQ_CTRL, ictrl); diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index feb90093e6b1..7b2340996cf8 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -199,20 +199,36 @@ static void read_arc_build_cfg_regs(void) cpu->bpu.ret_stk = 4 << bpu.rse; if (cpu->core.family >= 0x54) { - unsigned int exec_ctrl; - READ_BCR(AUX_EXEC_CTRL, exec_ctrl); - cpu->extn.dual_enb = !(exec_ctrl & 1); + struct bcr_uarch_build_arcv2 uarch; - /* dual issue always present for this core */ - cpu->extn.dual = 1; + /* + * The first 0x54 core (uarch maj:min 0:1 or 0:2) was + * dual issue only (HS4x). But next uarch rev (1:0) + * allows it be configured for single issue (HS3x) + * Ensure we fiddle with dual issue only on HS4x + */ + READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch); + + if (uarch.prod == 4) { + unsigned int exec_ctrl; + + /* dual issue hardware always present */ + cpu->extn.dual = 1; + + READ_BCR(AUX_EXEC_CTRL, exec_ctrl); + + /* dual issue hardware enabled ? */ + cpu->extn.dual_enb = !(exec_ctrl & 1); + + } } } READ_BCR(ARC_REG_AP_BCR, ap); if (ap.ver) { cpu->extn.ap_num = 2 << ap.num; - cpu->extn.ap_full = !!ap.min; + cpu->extn.ap_full = !ap.min; } READ_BCR(ARC_REG_SMART_BCR, bcr); @@ -462,43 +478,78 @@ void setup_processor(void) arc_chk_core_config(); } -static inline int is_kernel(unsigned long addr) +static inline bool uboot_arg_invalid(unsigned long addr) { - if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end) - return 1; - return 0; + /* + * Check that it is a untranslated address (although MMU is not enabled + * yet, it being a high address ensures this is not by fluke) + */ + if (addr < PAGE_OFFSET) + return true; + + /* Check that address doesn't clobber resident kernel image */ + return addr >= (unsigned long)_stext && addr <= (unsigned long)_end; } -void __init setup_arch(char **cmdline_p) +#define IGNORE_ARGS "Ignore U-boot args: " + +/* uboot_tag values for U-boot - kernel ABI revision 0; see head.S */ +#define UBOOT_TAG_NONE 0 +#define UBOOT_TAG_CMDLINE 1 +#define UBOOT_TAG_DTB 2 + +void __init handle_uboot_args(void) { -#ifdef CONFIG_ARC_UBOOT_SUPPORT - /* make sure that uboot passed pointer to cmdline/dtb is valid */ - if (uboot_tag && is_kernel((unsigned long)uboot_arg)) - panic("Invalid uboot arg\n"); - - /* See if u-boot passed an external Device Tree blob */ - machine_desc = setup_machine_fdt(uboot_arg); /* uboot_tag == 2 */ - if (!machine_desc) -#endif - { - /* No, so try the embedded one */ + bool use_embedded_dtb = true; + bool append_cmdline = false; + + /* check that we know this tag */ + if (uboot_tag != UBOOT_TAG_NONE && + uboot_tag != UBOOT_TAG_CMDLINE && + uboot_tag != UBOOT_TAG_DTB) { + pr_warn(IGNORE_ARGS "invalid uboot tag: '%08x'\n", uboot_tag); + goto ignore_uboot_args; + } + + if (uboot_tag != UBOOT_TAG_NONE && + uboot_arg_invalid((unsigned long)uboot_arg)) { + pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg); + goto ignore_uboot_args; + } + + /* see if U-boot passed an external Device Tree blob */ + if (uboot_tag == UBOOT_TAG_DTB) { + machine_desc = setup_machine_fdt((void *)uboot_arg); + + /* external Device Tree blob is invalid - use embedded one */ + use_embedded_dtb = !machine_desc; + } + + if (uboot_tag == UBOOT_TAG_CMDLINE) + append_cmdline = true; + +ignore_uboot_args: + + if (use_embedded_dtb) { machine_desc = setup_machine_fdt(__dtb_start); if (!machine_desc) panic("Embedded DT invalid\n"); + } - /* - * If we are here, it is established that @uboot_arg didn't - * point to DT blob. Instead if u-boot says it is cmdline, - * append to embedded DT cmdline. - * setup_machine_fdt() would have populated @boot_command_line - */ - if (uboot_tag == 1) { - /* Ensure a whitespace between the 2 cmdlines */ - strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); - strlcat(boot_command_line, uboot_arg, - COMMAND_LINE_SIZE); - } + /* + * NOTE: @boot_command_line is populated by setup_machine_fdt() so this + * append processing can only happen after. + */ + if (append_cmdline) { + /* Ensure a whitespace between the 2 cmdlines */ + strlcat(boot_command_line, " ", COMMAND_LINE_SIZE); + strlcat(boot_command_line, uboot_arg, COMMAND_LINE_SIZE); } +} + +void __init setup_arch(char **cmdline_p) +{ + handle_uboot_args(); /* Save unparsed command line copy for /proc/cmdline */ *cmdline_p = boot_command_line; diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S index d61044dd8b58..ea14b0bf3116 100644 --- a/arch/arc/lib/memcpy-archs.S +++ b/arch/arc/lib/memcpy-archs.S @@ -25,15 +25,11 @@ #endif #ifdef CONFIG_ARC_HAS_LL64 -# define PREFETCH_READ(RX) prefetch [RX, 56] -# define PREFETCH_WRITE(RX) prefetchw [RX, 64] # define LOADX(DST,RX) ldd.ab DST, [RX, 8] # define STOREX(SRC,RX) std.ab SRC, [RX, 8] # define ZOLSHFT 5 # define ZOLAND 0x1F #else -# define PREFETCH_READ(RX) prefetch [RX, 28] -# define PREFETCH_WRITE(RX) prefetchw [RX, 32] # define LOADX(DST,RX) ld.ab DST, [RX, 4] # define STOREX(SRC,RX) st.ab SRC, [RX, 4] # define ZOLSHFT 4 @@ -41,8 +37,6 @@ #endif ENTRY_CFI(memcpy) - prefetch [r1] ; Prefetch the read location - prefetchw [r0] ; Prefetch the write location mov.f 0, r2 ;;; if size is zero jz.d [blink] @@ -72,8 +66,6 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy32_64bytes ;; LOOP START LOADX (r6, r1) - PREFETCH_READ (r1) - PREFETCH_WRITE (r3) LOADX (r8, r1) LOADX (r10, r1) LOADX (r4, r1) @@ -117,9 +109,7 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy8bytes_1 ;; LOOP START ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location SHIFT_1 (r7, r6, 24) or r7, r7, r5 @@ -162,9 +152,7 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy8bytes_2 ;; LOOP START ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location SHIFT_1 (r7, r6, 16) or r7, r7, r5 @@ -204,9 +192,7 @@ ENTRY_CFI(memcpy) lpnz @.Lcopy8bytes_3 ;; LOOP START ld.ab r6, [r1, 4] - prefetch [r1, 28] ;Prefetch the next read location ld.ab r8, [r1,4] - prefetchw [r3, 32] ;Prefetch the next write location SHIFT_1 (r7, r6, 8) or r7, r7, r5 diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index f25c085b9874..23e00216e5a5 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -9,6 +9,7 @@ menuconfig ARC_SOC_HSDK bool "ARC HS Development Kit SOC" depends on ISA_ARCV2 select ARC_HAS_ACCL_REGS + select ARC_IRQ_NO_AUTOSAVE select CLK_HSDK select RESET_HSDK select HAVE_PCI diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 664e918e2624..26524b75970a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1400,6 +1400,7 @@ config NR_CPUS config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" depends on SMP + select GENERIC_IRQ_MIGRATION help Say Y here to experiment with turning CPUs off and on. CPUs can be controlled through /sys/devices/system/cpu. diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index b67f5fee1469..dce5be5df97b 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -729,7 +729,7 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii-txid"; + phy-mode = "rgmii-id"; }; &tscadc { diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 172c0224e7f6..b128998097ce 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -651,13 +651,13 @@ &cpsw_emac0 { phy-handle = <ðphy0>; - phy-mode = "rgmii-txid"; + phy-mode = "rgmii-id"; dual_emac_res_vlan = <1>; }; &cpsw_emac1 { phy-handle = <ðphy1>; - phy-mode = "rgmii-txid"; + phy-mode = "rgmii-id"; dual_emac_res_vlan = <2>; }; diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts index f3ac7483afed..5d04dc68cf57 100644 --- a/arch/arm/boot/dts/armada-xp-db.dts +++ b/arch/arm/boot/dts/armada-xp-db.dts @@ -144,30 +144,32 @@ status = "okay"; }; - nand@d0000 { + nand-controller@d0000 { status = "okay"; - label = "pxa3xx_nand-0"; - num-cs = <1>; - marvell,nand-keep-config; - nand-on-flash-bbt; - - partitions { - compatible = "fixed-partitions"; - #address-cells = <1>; - #size-cells = <1>; - - partition@0 { - label = "U-Boot"; - reg = <0 0x800000>; - }; - partition@800000 { - label = "Linux"; - reg = <0x800000 0x800000>; - }; - partition@1000000 { - label = "Filesystem"; - reg = <0x1000000 0x3f000000>; + nand@0 { + reg = <0>; + label = "pxa3xx_nand-0"; + nand-rb = <0>; + nand-on-flash-bbt; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + label = "U-Boot"; + reg = <0 0x800000>; + }; + partition@800000 { + label = "Linux"; + reg = <0x800000 0x800000>; + }; + partition@1000000 { + label = "Filesystem"; + reg = <0x1000000 0x3f000000>; + }; }; }; }; diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts index 1139e9469a83..b4cca507cf13 100644 --- a/arch/arm/boot/dts/armada-xp-gp.dts +++ b/arch/arm/boot/dts/armada-xp-gp.dts @@ -160,12 +160,15 @@ status = "okay"; }; - nand@d0000 { + nand-controller@d0000 { status = "okay"; - label = "pxa3xx_nand-0"; - num-cs = <1>; - marvell,nand-keep-config; - nand-on-flash-bbt; + + nand@0 { + reg = <0>; + label = "pxa3xx_nand-0"; + nand-rb = <0>; + nand-on-flash-bbt; + }; }; }; diff --git a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts index bbbb38888bb8..87dcb502f72d 100644 --- a/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts +++ b/arch/arm/boot/dts/armada-xp-lenovo-ix4-300d.dts @@ -81,49 +81,52 @@ }; - nand@d0000 { + nand-controller@d0000 { status = "okay"; - label = "pxa3xx_nand-0"; - num-cs = <1>; - marvell,nand-keep-config; - nand-on-flash-bbt; - - partitions { - compatible = "fixed-partitions"; - #address-cells = <1>; - #size-cells = <1>; - - partition@0 { - label = "u-boot"; - reg = <0x00000000 0x000e0000>; - read-only; - }; - - partition@e0000 { - label = "u-boot-env"; - reg = <0x000e0000 0x00020000>; - read-only; - }; - - partition@100000 { - label = "u-boot-env2"; - reg = <0x00100000 0x00020000>; - read-only; - }; - - partition@120000 { - label = "zImage"; - reg = <0x00120000 0x00400000>; - }; - - partition@520000 { - label = "initrd"; - reg = <0x00520000 0x00400000>; - }; - partition@e00000 { - label = "boot"; - reg = <0x00e00000 0x3f200000>; + nand@0 { + reg = <0>; + label = "pxa3xx_nand-0"; + nand-rb = <0>; + nand-on-flash-bbt; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + partition@0 { + label = "u-boot"; + reg = <0x00000000 0x000e0000>; + read-only; + }; + + partition@e0000 { + label = "u-boot-env"; + reg = <0x000e0000 0x00020000>; + read-only; + }; + + partition@100000 { + label = "u-boot-env2"; + reg = <0x00100000 0x00020000>; + read-only; + }; + + partition@120000 { + label = "zImage"; + reg = <0x00120000 0x00400000>; + }; + + partition@520000 { + label = "initrd"; + reg = <0x00520000 0x00400000>; + }; + + partition@e00000 { + label = "boot"; + reg = <0x00e00000 0x3f200000>; + }; }; }; }; diff --git a/arch/arm/boot/dts/gemini-dlink-dir-685.dts b/arch/arm/boot/dts/gemini-dlink-dir-685.dts index cc0c3cf89eaa..592111c8d6fd 100644 --- a/arch/arm/boot/dts/gemini-dlink-dir-685.dts +++ b/arch/arm/boot/dts/gemini-dlink-dir-685.dts @@ -443,7 +443,7 @@ }; display-controller@6a000000 { - status = "disabled"; + status = "okay"; port@0 { reg = <0>; diff --git a/arch/arm/boot/dts/tegra124-nyan.dtsi b/arch/arm/boot/dts/tegra124-nyan.dtsi index d5f11d6d987e..bc85b6a166c7 100644 --- a/arch/arm/boot/dts/tegra124-nyan.dtsi +++ b/arch/arm/boot/dts/tegra124-nyan.dtsi @@ -13,10 +13,25 @@ stdout-path = "serial0:115200n8"; }; - memory@80000000 { + /* + * Note that recent version of the device tree compiler (starting with + * version 1.4.2) warn about this node containing a reg property, but + * missing a unit-address. However, the bootloader on these Chromebook + * devices relies on the full name of this node to be exactly /memory. + * Adding the unit-address causes the bootloader to create a /memory + * node and write the memory bank configuration to that node, which in + * turn leads the kernel to believe that the device has 2 GiB of + * memory instead of the amount detected by the bootloader. + * + * The name of this node is effectively ABI and must not be changed. + */ + memory { + device_type = "memory"; reg = <0x0 0x80000000 0x0 0x80000000>; }; + /delete-node/ memory@80000000; + host1x@50000000 { hdmi@54280000 { status = "okay"; diff --git a/arch/arm/crypto/sha256-armv4.pl b/arch/arm/crypto/sha256-armv4.pl index b9ec44060ed3..a03cf4dfb781 100644 --- a/arch/arm/crypto/sha256-armv4.pl +++ b/arch/arm/crypto/sha256-armv4.pl @@ -212,10 +212,11 @@ K256: .global sha256_block_data_order .type sha256_block_data_order,%function sha256_block_data_order: +.Lsha256_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha256_block_data_order #else - adr r3,sha256_block_data_order + adr r3,.Lsha256_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap diff --git a/arch/arm/crypto/sha256-core.S_shipped b/arch/arm/crypto/sha256-core.S_shipped index 3b58300d611c..054aae0edfce 100644 --- a/arch/arm/crypto/sha256-core.S_shipped +++ b/arch/arm/crypto/sha256-core.S_shipped @@ -93,10 +93,11 @@ K256: .global sha256_block_data_order .type sha256_block_data_order,%function sha256_block_data_order: +.Lsha256_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha256_block_data_order #else - adr r3,sha256_block_data_order + adr r3,.Lsha256_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl index fb5d15048c0b..788c17b56ecc 100644 --- a/arch/arm/crypto/sha512-armv4.pl +++ b/arch/arm/crypto/sha512-armv4.pl @@ -274,10 +274,11 @@ WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) .global sha512_block_data_order .type sha512_block_data_order,%function sha512_block_data_order: +.Lsha512_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha512_block_data_order #else - adr r3,sha512_block_data_order + adr r3,.Lsha512_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped index b1c334a49cda..710ea309769e 100644 --- a/arch/arm/crypto/sha512-core.S_shipped +++ b/arch/arm/crypto/sha512-core.S_shipped @@ -141,10 +141,11 @@ WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) .global sha512_block_data_order .type sha512_block_data_order,%function sha512_block_data_order: +.Lsha512_block_data_order: #if __ARM_ARCH__<7 sub r3,pc,#8 @ sha512_block_data_order #else - adr r3,sha512_block_data_order + adr r3,.Lsha512_block_data_order #endif #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) ldr r12,.LOPENSSL_armcap diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h index c883fcbe93b6..46d41140df27 100644 --- a/arch/arm/include/asm/irq.h +++ b/arch/arm/include/asm/irq.h @@ -25,7 +25,6 @@ #ifndef __ASSEMBLY__ struct irqaction; struct pt_regs; -extern void migrate_irqs(void); extern void asm_do_IRQ(unsigned int, struct pt_regs *); void handle_IRQ(unsigned int, struct pt_regs *); diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c index 9908dacf9229..844861368cd5 100644 --- a/arch/arm/kernel/irq.c +++ b/arch/arm/kernel/irq.c @@ -31,7 +31,6 @@ #include <linux/smp.h> #include <linux/init.h> #include <linux/seq_file.h> -#include <linux/ratelimit.h> #include <linux/errno.h> #include <linux/list.h> #include <linux/kallsyms.h> @@ -109,64 +108,3 @@ int __init arch_probe_nr_irqs(void) return nr_irqs; } #endif - -#ifdef CONFIG_HOTPLUG_CPU -static bool migrate_one_irq(struct irq_desc *desc) -{ - struct irq_data *d = irq_desc_get_irq_data(desc); - const struct cpumask *affinity = irq_data_get_affinity_mask(d); - struct irq_chip *c; - bool ret = false; - - /* - * If this is a per-CPU interrupt, or the affinity does not - * include this CPU, then we have nothing to do. - */ - if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity)) - return false; - - if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) { - affinity = cpu_online_mask; - ret = true; - } - - c = irq_data_get_irq_chip(d); - if (!c->irq_set_affinity) - pr_debug("IRQ%u: unable to set affinity\n", d->irq); - else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret) - cpumask_copy(irq_data_get_affinity_mask(d), affinity); - - return ret; -} - -/* - * The current CPU has been marked offline. Migrate IRQs off this CPU. - * If the affinity settings do not allow other CPUs, force them onto any - * available CPU. - * - * Note: we must iterate over all IRQs, whether they have an attached - * action structure or not, as we need to get chained interrupts too. - */ -void migrate_irqs(void) -{ - unsigned int i; - struct irq_desc *desc; - unsigned long flags; - - local_irq_save(flags); - - for_each_irq_desc(i, desc) { - bool affinity_broken; - - raw_spin_lock(&desc->lock); - affinity_broken = migrate_one_irq(desc); - raw_spin_unlock(&desc->lock); - - if (affinity_broken) - pr_warn_ratelimited("IRQ%u no longer affine to CPU%u\n", - i, smp_processor_id()); - } - - local_irq_restore(flags); -} -#endif /* CONFIG_HOTPLUG_CPU */ diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 3bf82232b1be..1d6f5ea522f4 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -254,7 +254,7 @@ int __cpu_disable(void) /* * OK - migrate IRQs away from this CPU */ - migrate_irqs(); + irq_migrate_all_off_this_cpu(); /* * Flush user cache and TLB mappings, and then remove this CPU diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index f1e2922e447c..1e3e08a1c456 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -2390,4 +2390,6 @@ void arch_teardown_dma_ops(struct device *dev) return; arm_teardown_iommu_dma_ops(dev); + /* Let arch_setup_dma_ops() start again from scratch upon re-probe */ + set_dma_ops(dev, NULL); } diff --git a/arch/arm/probes/kprobes/opt-arm.c b/arch/arm/probes/kprobes/opt-arm.c index 2c118a6ab358..0dc23fc227ed 100644 --- a/arch/arm/probes/kprobes/opt-arm.c +++ b/arch/arm/probes/kprobes/opt-arm.c @@ -247,7 +247,7 @@ int arch_prepare_optimized_kprobe(struct optimized_kprobe *op, struct kprobe *or } /* Copy arch-dep-instance from template. */ - memcpy(code, (unsigned char *)optprobe_template_entry, + memcpy(code, (unsigned long *)&optprobe_template_entry, TMPL_END_IDX * sizeof(kprobe_opcode_t)); /* Adjust buffer according to instruction. */ diff --git a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts index 5b4a9609e31f..2468762283a5 100644 --- a/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts +++ b/arch/arm64/boot/dts/marvell/armada-8040-clearfog-gt-8k.dts @@ -351,7 +351,7 @@ reg = <0>; pinctrl-names = "default"; pinctrl-0 = <&cp0_copper_eth_phy_reset>; - reset-gpios = <&cp1_gpio1 11 GPIO_ACTIVE_LOW>; + reset-gpios = <&cp0_gpio2 11 GPIO_ACTIVE_LOW>; reset-assert-us = <10000>; }; diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 8d41b69ec2da..99bccaac31ad 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -37,7 +37,7 @@ }; memory@86200000 { - reg = <0x0 0x86200000 0x0 0x2600000>; + reg = <0x0 0x86200000 0x0 0x2d00000>; no-map; }; diff --git a/arch/arm64/crypto/chacha-neon-core.S b/arch/arm64/crypto/chacha-neon-core.S index 021bb9e9784b..706c4e10e9e2 100644 --- a/arch/arm64/crypto/chacha-neon-core.S +++ b/arch/arm64/crypto/chacha-neon-core.S @@ -158,8 +158,8 @@ ENTRY(hchacha_block_neon) mov w3, w2 bl chacha_permute - st1 {v0.16b}, [x1], #16 - st1 {v3.16b}, [x1] + st1 {v0.4s}, [x1], #16 + st1 {v3.4s}, [x1] ldp x29, x30, [sp], #16 ret @@ -532,6 +532,10 @@ ENTRY(chacha_4block_xor_neon) add v3.4s, v3.4s, v19.4s add a2, a2, w8 add a3, a3, w9 +CPU_BE( rev a0, a0 ) +CPU_BE( rev a1, a1 ) +CPU_BE( rev a2, a2 ) +CPU_BE( rev a3, a3 ) ld4r {v24.4s-v27.4s}, [x0], #16 ld4r {v28.4s-v31.4s}, [x0] @@ -552,6 +556,10 @@ ENTRY(chacha_4block_xor_neon) add v7.4s, v7.4s, v23.4s add a6, a6, w8 add a7, a7, w9 +CPU_BE( rev a4, a4 ) +CPU_BE( rev a5, a5 ) +CPU_BE( rev a6, a6 ) +CPU_BE( rev a7, a7 ) // x8[0-3] += s2[0] // x9[0-3] += s2[1] @@ -569,6 +577,10 @@ ENTRY(chacha_4block_xor_neon) add v11.4s, v11.4s, v27.4s add a10, a10, w8 add a11, a11, w9 +CPU_BE( rev a8, a8 ) +CPU_BE( rev a9, a9 ) +CPU_BE( rev a10, a10 ) +CPU_BE( rev a11, a11 ) // x12[0-3] += s3[0] // x13[0-3] += s3[1] @@ -586,6 +598,10 @@ ENTRY(chacha_4block_xor_neon) add v15.4s, v15.4s, v31.4s add a14, a14, w8 add a15, a15, w9 +CPU_BE( rev a12, a12 ) +CPU_BE( rev a13, a13 ) +CPU_BE( rev a14, a14 ) +CPU_BE( rev a15, a15 ) // interleave 32-bit words in state n, n+1 ldp w6, w7, [x2], #64 diff --git a/arch/arm64/include/asm/neon-intrinsics.h b/arch/arm64/include/asm/neon-intrinsics.h index 2ba6c6b9541f..71abfc7612b2 100644 --- a/arch/arm64/include/asm/neon-intrinsics.h +++ b/arch/arm64/include/asm/neon-intrinsics.h @@ -36,4 +36,8 @@ #include <arm_neon.h> #endif +#ifdef CONFIG_CC_IS_CLANG +#pragma clang diagnostic ignored "-Wincompatible-pointer-types" +#endif + #endif /* __ASM_NEON_INTRINSICS_H */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 15d79a8e5e5e..eecf7927dab0 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -539,8 +539,7 @@ set_hcr: /* GICv3 system register access */ mrs x0, id_aa64pfr0_el1 ubfx x0, x0, #24, #4 - cmp x0, #1 - b.ne 3f + cbz x0, 3f mrs_s x0, SYS_ICC_SRE_EL2 orr x0, x0, #ICC_SRE_EL2_SRE // Set ICC_SRE_EL2.SRE==1 diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 9dce33b0e260..ddaea0fd2fa4 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1702,19 +1702,20 @@ void syscall_trace_exit(struct pt_regs *regs) } /* - * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a - * We also take into account DIT (bit 24), which is not yet documented, and - * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be - * allocated an EL0 meaning in future. + * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a. + * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is + * not described in ARM DDI 0487D.a. + * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may + * be allocated an EL0 meaning in future. * Userspace cannot use these until they have an architectural meaning. * Note that this follows the SPSR_ELx format, not the AArch32 PSR format. * We also reserve IL for the kernel; SS is handled dynamically. */ #define SPSR_EL1_AARCH64_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \ - GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5)) + (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \ + GENMASK_ULL(20, 13) | GENMASK_ULL(11, 10) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ - (GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20)) + (GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20)) static int valid_compat_regs(struct user_pt_regs *regs) { diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index d09ec76f08cf..009849328289 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -339,6 +339,9 @@ void __init setup_arch(char **cmdline_p) smp_init_cpus(); smp_build_mpidr_hash(); + /* Init percpu seeds for random tags after cpus are set up. */ + kasan_init_tags(); + #ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Make sure init_thread_info.ttbr0 always generates translation diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 4b55b15707a3..f37a86d2a69d 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -252,8 +252,6 @@ void __init kasan_init(void) memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); - kasan_init_tags(); - /* At this point kasan is fully initialized. Enable error messages */ init_task.kasan_depth = 0; pr_info("KernelAddressSanitizer initialized\n"); diff --git a/arch/mips/bcm63xx/dev-enet.c b/arch/mips/bcm63xx/dev-enet.c index 07b4c65a88a4..8e73d65f3480 100644 --- a/arch/mips/bcm63xx/dev-enet.c +++ b/arch/mips/bcm63xx/dev-enet.c @@ -70,6 +70,8 @@ static struct platform_device bcm63xx_enet_shared_device = { static int shared_device_registered; +static u64 enet_dmamask = DMA_BIT_MASK(32); + static struct resource enet0_res[] = { { .start = -1, /* filled at runtime */ @@ -99,6 +101,8 @@ static struct platform_device bcm63xx_enet0_device = { .resource = enet0_res, .dev = { .platform_data = &enet0_pd, + .dma_mask = &enet_dmamask, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -131,6 +135,8 @@ static struct platform_device bcm63xx_enet1_device = { .resource = enet1_res, .dev = { .platform_data = &enet1_pd, + .dma_mask = &enet_dmamask, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; @@ -157,6 +163,8 @@ static struct platform_device bcm63xx_enetsw_device = { .resource = enetsw_res, .dev = { .platform_data = &enetsw_pd, + .dma_mask = &enet_dmamask, + .coherent_dma_mask = DMA_BIT_MASK(32), }, }; diff --git a/arch/mips/kernel/cmpxchg.c b/arch/mips/kernel/cmpxchg.c index 0b9535bc2c53..6b2a4a902a98 100644 --- a/arch/mips/kernel/cmpxchg.c +++ b/arch/mips/kernel/cmpxchg.c @@ -54,10 +54,9 @@ unsigned long __xchg_small(volatile void *ptr, unsigned long val, unsigned int s unsigned long __cmpxchg_small(volatile void *ptr, unsigned long old, unsigned long new, unsigned int size) { - u32 mask, old32, new32, load32; + u32 mask, old32, new32, load32, load; volatile u32 *ptr32; unsigned int shift; - u8 load; /* Check that ptr is naturally aligned */ WARN_ON((unsigned long)ptr & (size - 1)); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 8c6c48ed786a..d2e5a5ad0e6f 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -384,7 +384,8 @@ static void __init bootmem_init(void) init_initrd(); reserved_end = (unsigned long) PFN_UP(__pa_symbol(&_end)); - memblock_reserve(PHYS_OFFSET, reserved_end << PAGE_SHIFT); + memblock_reserve(PHYS_OFFSET, + (reserved_end << PAGE_SHIFT) - PHYS_OFFSET); /* * max_low_pfn is not a number of pages. The number of pages diff --git a/arch/mips/lantiq/xway/vmmc.c b/arch/mips/lantiq/xway/vmmc.c index 577ec81b557d..3deab9a77718 100644 --- a/arch/mips/lantiq/xway/vmmc.c +++ b/arch/mips/lantiq/xway/vmmc.c @@ -31,8 +31,8 @@ static int vmmc_probe(struct platform_device *pdev) dma_addr_t dma; cp1_base = - (void *) CPHYSADDR(dma_alloc_coherent(NULL, CP1_SIZE, - &dma, GFP_ATOMIC)); + (void *) CPHYSADDR(dma_alloc_coherent(&pdev->dev, CP1_SIZE, + &dma, GFP_KERNEL)); gpio_count = of_gpio_count(pdev->dev.of_node); while (gpio_count > 0) { diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index b16710a8a9e7..0effd3cba9a7 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -79,8 +79,6 @@ enum reg_val_type { REG_64BIT_32BIT, /* 32-bit compatible, need truncation for 64-bit ops. */ REG_32BIT, - /* 32-bit zero extended. */ - REG_32BIT_ZERO_EX, /* 32-bit no sign/zero extension needed. */ REG_32BIT_POS }; @@ -343,12 +341,15 @@ static int build_int_epilogue(struct jit_ctx *ctx, int dest_reg) const struct bpf_prog *prog = ctx->skf; int stack_adjust = ctx->stack_size; int store_offset = stack_adjust - 8; + enum reg_val_type td; int r0 = MIPS_R_V0; - if (dest_reg == MIPS_R_RA && - get_reg_val_type(ctx, prog->len, BPF_REG_0) == REG_32BIT_ZERO_EX) + if (dest_reg == MIPS_R_RA) { /* Don't let zero extended value escape. */ - emit_instr(ctx, sll, r0, r0, 0); + td = get_reg_val_type(ctx, prog->len, BPF_REG_0); + if (td == REG_64BIT) + emit_instr(ctx, sll, r0, r0, 0); + } if (ctx->flags & EBPF_SAVE_RA) { emit_instr(ctx, ld, MIPS_R_RA, store_offset, MIPS_R_SP); @@ -692,7 +693,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (dst < 0) return dst; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + if (td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } @@ -707,7 +708,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (dst < 0) return dst; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + if (td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } @@ -721,7 +722,7 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (dst < 0) return dst; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) + if (td == REG_64BIT) /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); if (insn->imm == 1) { @@ -860,13 +861,13 @@ static int build_one_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, if (src < 0 || dst < 0) return -EINVAL; td = get_reg_val_type(ctx, this_idx, insn->dst_reg); - if (td == REG_64BIT || td == REG_32BIT_ZERO_EX) { + if (td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } did_move = false; ts = get_reg_val_type(ctx, this_idx, insn->src_reg); - if (ts == REG_64BIT || ts == REG_32BIT_ZERO_EX) { + if (ts == REG_64BIT) { int tmp_reg = MIPS_R_AT; if (bpf_op == BPF_MOV) { @@ -1254,8 +1255,7 @@ jeq_common: if (insn->imm == 64 && td == REG_32BIT) emit_instr(ctx, dinsu, dst, MIPS_R_ZERO, 32, 32); - if (insn->imm != 64 && - (td == REG_64BIT || td == REG_32BIT_ZERO_EX)) { + if (insn->imm != 64 && td == REG_64BIT) { /* sign extend */ emit_instr(ctx, sll, dst, dst, 0); } @@ -1819,7 +1819,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) /* Update the icache */ flush_icache_range((unsigned long)ctx.target, - (unsigned long)(ctx.target + ctx.idx * sizeof(u32))); + (unsigned long)&ctx.target[ctx.idx]); if (bpf_jit_enable > 1) /* Dump JIT code */ diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 2582df1c529b..0964c236e3e5 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -308,15 +308,29 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, long do_syscall_trace_enter(struct pt_regs *regs) { - if (test_thread_flag(TIF_SYSCALL_TRACE) && - tracehook_report_syscall_entry(regs)) { + if (test_thread_flag(TIF_SYSCALL_TRACE)) { + int rc = tracehook_report_syscall_entry(regs); + /* - * Tracing decided this syscall should not happen or the - * debugger stored an invalid system call number. Skip - * the system call and the system call restart handling. + * As tracesys_next does not set %r28 to -ENOSYS + * when %r20 is set to -1, initialize it here. */ - regs->gr[20] = -1UL; - goto out; + regs->gr[28] = -ENOSYS; + + if (rc) { + /* + * A nonzero return code from + * tracehook_report_syscall_entry() tells us + * to prevent the syscall execution. Skip + * the syscall call and the syscall restart handling. + * + * Note that the tracer may also just change + * regs->gr[20] to an invalid syscall number, + * that is handled by tracesys_next. + */ + regs->gr[20] = -1UL; + return -1; + } } /* Do the secure computing check after ptrace. */ @@ -340,7 +354,6 @@ long do_syscall_trace_enter(struct pt_regs *regs) regs->gr[24] & 0xffffffff, regs->gr[23] & 0xffffffff); -out: /* * Sign extend the syscall number to 64bit since it may have been * modified by a compat ptrace call diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 7db3119f8a5b..145373f0e5dc 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1593,6 +1593,8 @@ static void pnv_ioda_setup_vf_PE(struct pci_dev *pdev, u16 num_vfs) pnv_pci_ioda2_setup_dma_pe(phb, pe); #ifdef CONFIG_IOMMU_API + iommu_register_group(&pe->table_group, + pe->phb->hose->global_number, pe->pe_number); pnv_ioda_setup_bus_iommu_group(pe, &pe->table_group, NULL); #endif } diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 45fb70b4bfa7..ef9448a907c6 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -1147,6 +1147,8 @@ static int pnv_tce_iommu_bus_notifier(struct notifier_block *nb, return 0; pe = &phb->ioda.pe_array[pdn->pe_number]; + if (!pe->table_group.group) + return 0; iommu_add_device(&pe->table_group, dev); return 0; case BUS_NOTIFY_DEL_DEVICE: diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index a153257bf7d9..d62fa148558b 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -297,7 +297,7 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->crycbd = 0; apie_h = vcpu->arch.sie_block->eca & ECA_APIE; - if (!apie_h && !key_msk) + if (!apie_h && (!key_msk || fmt_o == CRYCB_FORMAT0)) return 0; if (!crycb_addr) diff --git a/arch/sh/boot/dts/Makefile b/arch/sh/boot/dts/Makefile index 01d0f7fb14cc..2563d1e532e2 100644 --- a/arch/sh/boot/dts/Makefile +++ b/arch/sh/boot/dts/Makefile @@ -1,3 +1,3 @@ ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"") -obj-y += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o +obj-$(CONFIG_USE_BUILTIN_DTB) += $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o endif diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 705dafc2d11a..2bdbbbcfa393 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -841,7 +841,7 @@ union hv_gpa_page_range { * count is equal with how many entries of union hv_gpa_page_range can * be populated into the input parameter page. */ -#define HV_MAX_FLUSH_REP_COUNT (PAGE_SIZE - 2 * sizeof(u64) / \ +#define HV_MAX_FLUSH_REP_COUNT ((PAGE_SIZE - 2 * sizeof(u64)) / \ sizeof(union hv_gpa_page_range)) struct hv_guest_mapping_flush_list { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4660ce90de7f..180373360e34 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -299,6 +299,7 @@ union kvm_mmu_extended_role { unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; + unsigned int maxphyaddr:6; }; }; @@ -397,6 +398,7 @@ struct kvm_mmu { void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte); hpa_t root_hpa; + gpa_t root_cr3; union kvm_mmu_role mmu_role; u8 root_level; u8 shadow_root_level; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 780f2b42c8ef..c1334aaaa78d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -284,7 +284,7 @@ do { \ __put_user_goto(x, ptr, "l", "k", "ir", label); \ break; \ case 8: \ - __put_user_goto_u64((__typeof__(*ptr))(x), ptr, label); \ + __put_user_goto_u64(x, ptr, label); \ break; \ default: \ __put_user_bad(); \ @@ -431,8 +431,10 @@ do { \ ({ \ __label__ __pu_label; \ int __pu_err = -EFAULT; \ + __typeof__(*(ptr)) __pu_val; \ + __pu_val = x; \ __uaccess_begin(); \ - __put_user_size((x), (ptr), (size), __pu_label); \ + __put_user_size(__pu_val, (ptr), (size), __pu_label); \ __pu_err = 0; \ __pu_label: \ __uaccess_end(); \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index bbffa6c54697..c07958b59f50 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -335,6 +335,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, unsigned f_xsaves = kvm_x86_ops->xsaves_supported() ? F(XSAVES) : 0; unsigned f_umip = kvm_x86_ops->umip_emulated() ? F(UMIP) : 0; unsigned f_intel_pt = kvm_x86_ops->pt_supported() ? F(INTEL_PT) : 0; + unsigned f_la57 = 0; /* cpuid 1.edx */ const u32 kvm_cpuid_1_edx_x86_features = @@ -489,7 +490,10 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, // TSC_ADJUST is emulated entry->ebx |= F(TSC_ADJUST); entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; + f_la57 = entry->ecx & F(LA57); cpuid_mask(&entry->ecx, CPUID_7_ECX); + /* Set LA57 based on hardware capability. */ + entry->ecx |= f_la57; entry->ecx |= f_umip; /* PKU is not yet implemented for shadow paging. */ if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index da9c42349b1f..f2d1d230d5b8 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -3555,6 +3555,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, &invalid_list); mmu->root_hpa = INVALID_PAGE; } + mmu->root_cr3 = 0; } kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); @@ -3610,6 +3611,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->pae_root); } else BUG(); + vcpu->arch.mmu->root_cr3 = vcpu->arch.mmu->get_cr3(vcpu); return 0; } @@ -3618,10 +3620,11 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; u64 pdptr, pm_mask; - gfn_t root_gfn; + gfn_t root_gfn, root_cr3; int i; - root_gfn = vcpu->arch.mmu->get_cr3(vcpu) >> PAGE_SHIFT; + root_cr3 = vcpu->arch.mmu->get_cr3(vcpu); + root_gfn = root_cr3 >> PAGE_SHIFT; if (mmu_check_root(vcpu, root_gfn)) return 1; @@ -3646,7 +3649,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu->root_hpa = root; - return 0; + goto set_root_cr3; } /* @@ -3712,6 +3715,9 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_hpa = __pa(vcpu->arch.mmu->lm_root); } +set_root_cr3: + vcpu->arch.mmu->root_cr3 = root_cr3; + return 0; } @@ -4163,7 +4169,7 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3, struct kvm_mmu_root_info root; struct kvm_mmu *mmu = vcpu->arch.mmu; - root.cr3 = mmu->get_cr3(vcpu); + root.cr3 = mmu->root_cr3; root.hpa = mmu->root_hpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { @@ -4176,6 +4182,7 @@ static bool cached_root_available(struct kvm_vcpu *vcpu, gpa_t new_cr3, } mmu->root_hpa = root.hpa; + mmu->root_cr3 = root.cr3; return i < KVM_MMU_NUM_PREV_ROOTS; } @@ -4770,6 +4777,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu) ext.cr4_pse = !!is_pse(vcpu); ext.cr4_pke = !!kvm_read_cr4_bits(vcpu, X86_CR4_PKE); ext.cr4_la57 = !!kvm_read_cr4_bits(vcpu, X86_CR4_LA57); + ext.maxphyaddr = cpuid_maxphyaddr(vcpu); ext.valid = 1; @@ -5516,11 +5524,13 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu) vcpu->arch.walk_mmu = &vcpu->arch.root_mmu; vcpu->arch.root_mmu.root_hpa = INVALID_PAGE; + vcpu->arch.root_mmu.root_cr3 = 0; vcpu->arch.root_mmu.translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) vcpu->arch.root_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; vcpu->arch.guest_mmu.root_hpa = INVALID_PAGE; + vcpu->arch.guest_mmu.root_cr3 = 0; vcpu->arch.guest_mmu.translate_gpa = translate_gpa; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 6521134057e8..856fa409c536 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -117,67 +117,11 @@ __visible bool ex_handler_fprestore(const struct exception_table_entry *fixup, } EXPORT_SYMBOL_GPL(ex_handler_fprestore); -/* Helper to check whether a uaccess fault indicates a kernel bug. */ -static bool bogus_uaccess(struct pt_regs *regs, int trapnr, - unsigned long fault_addr) -{ - /* This is the normal case: #PF with a fault address in userspace. */ - if (trapnr == X86_TRAP_PF && fault_addr < TASK_SIZE_MAX) - return false; - - /* - * This code can be reached for machine checks, but only if the #MC - * handler has already decided that it looks like a candidate for fixup. - * This e.g. happens when attempting to access userspace memory which - * the CPU can't access because of uncorrectable bad memory. - */ - if (trapnr == X86_TRAP_MC) - return false; - - /* - * There are two remaining exception types we might encounter here: - * - #PF for faulting accesses to kernel addresses - * - #GP for faulting accesses to noncanonical addresses - * Complain about anything else. - */ - if (trapnr != X86_TRAP_PF && trapnr != X86_TRAP_GP) { - WARN(1, "unexpected trap %d in uaccess\n", trapnr); - return false; - } - - /* - * This is a faulting memory access in kernel space, on a kernel - * address, in a usercopy function. This can e.g. be caused by improper - * use of helpers like __put_user and by improper attempts to access - * userspace addresses in KERNEL_DS regions. - * The one (semi-)legitimate exception are probe_kernel_{read,write}(), - * which can be invoked from places like kgdb, /dev/mem (for reading) - * and privileged BPF code (for reading). - * The probe_kernel_*() functions set the kernel_uaccess_faults_ok flag - * to tell us that faulting on kernel addresses, and even noncanonical - * addresses, in a userspace accessor does not necessarily imply a - * kernel bug, root might just be doing weird stuff. - */ - if (current->kernel_uaccess_faults_ok) - return false; - - /* This is bad. Refuse the fixup so that we go into die(). */ - if (trapnr == X86_TRAP_PF) { - pr_emerg("BUG: pagefault on kernel address 0x%lx in non-whitelisted uaccess\n", - fault_addr); - } else { - pr_emerg("BUG: GPF in non-whitelisted uaccess (non-canonical address?)\n"); - } - return true; -} - __visible bool ex_handler_uaccess(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { - if (bogus_uaccess(regs, trapnr, fault_addr)) - return false; regs->ip = ex_fixup_addr(fixup); return true; } @@ -188,8 +132,6 @@ __visible bool ex_handler_ext(const struct exception_table_entry *fixup, unsigned long error_code, unsigned long fault_addr) { - if (bogus_uaccess(regs, trapnr, fault_addr)) - return false; /* Special hack for uaccess_err */ current->thread.uaccess_err = 1; regs->ip = ex_fixup_addr(fixup); diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 17eb09d222ff..ec78a04eb136 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -122,8 +122,10 @@ static void alg_do_release(const struct af_alg_type *type, void *private) int af_alg_release(struct socket *sock) { - if (sock->sk) + if (sock->sk) { sock_put(sock->sk); + sock->sk = NULL; + } return 0; } EXPORT_SYMBOL_GPL(af_alg_release); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 0ea2139c50d8..ccd296dbb95c 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -95,7 +95,7 @@ static void __update_runtime_status(struct device *dev, enum rpm_status status) static void pm_runtime_deactivate_timer(struct device *dev) { if (dev->power.timer_expires > 0) { - hrtimer_cancel(&dev->power.suspend_timer); + hrtimer_try_to_cancel(&dev->power.suspend_timer); dev->power.timer_expires = 0; } } diff --git a/drivers/clk/at91/at91sam9x5.c b/drivers/clk/at91/at91sam9x5.c index 2fe225a697df..3487e03d4bc6 100644 --- a/drivers/clk/at91/at91sam9x5.c +++ b/drivers/clk/at91/at91sam9x5.c @@ -144,8 +144,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np, return; at91sam9x5_pmc = pmc_data_allocate(PMC_MAIN + 1, - nck(at91sam9x5_systemck), - nck(at91sam9x35_periphck), 0); + nck(at91sam9x5_systemck), 31, 0); if (!at91sam9x5_pmc) return; @@ -210,7 +209,7 @@ static void __init at91sam9x5_pmc_setup(struct device_node *np, parent_names[1] = "mainck"; parent_names[2] = "plladivck"; parent_names[3] = "utmick"; - parent_names[4] = "mck"; + parent_names[4] = "masterck"; for (i = 0; i < 2; i++) { char name[6]; diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c index d69ad96fe988..cd0ef7274fdb 100644 --- a/drivers/clk/at91/sama5d2.c +++ b/drivers/clk/at91/sama5d2.c @@ -240,7 +240,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np) parent_names[1] = "mainck"; parent_names[2] = "plladivck"; parent_names[3] = "utmick"; - parent_names[4] = "mck"; + parent_names[4] = "masterck"; for (i = 0; i < 3; i++) { char name[6]; @@ -291,7 +291,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np) parent_names[1] = "mainck"; parent_names[2] = "plladivck"; parent_names[3] = "utmick"; - parent_names[4] = "mck"; + parent_names[4] = "masterck"; parent_names[5] = "audiopll_pmcck"; for (i = 0; i < ARRAY_SIZE(sama5d2_gck); i++) { hw = at91_clk_register_generated(regmap, &pmc_pcr_lock, diff --git a/drivers/clk/at91/sama5d4.c b/drivers/clk/at91/sama5d4.c index e358be7f6c8d..b645a9d59cdb 100644 --- a/drivers/clk/at91/sama5d4.c +++ b/drivers/clk/at91/sama5d4.c @@ -207,7 +207,7 @@ static void __init sama5d4_pmc_setup(struct device_node *np) parent_names[1] = "mainck"; parent_names[2] = "plladivck"; parent_names[3] = "utmick"; - parent_names[4] = "mck"; + parent_names[4] = "masterck"; for (i = 0; i < 3; i++) { char name[6]; diff --git a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c index 3b97f60540ad..609970c0b666 100644 --- a/drivers/clk/sunxi-ng/ccu-sun6i-a31.c +++ b/drivers/clk/sunxi-ng/ccu-sun6i-a31.c @@ -264,9 +264,9 @@ static SUNXI_CCU_GATE(ahb1_mmc1_clk, "ahb1-mmc1", "ahb1", static SUNXI_CCU_GATE(ahb1_mmc2_clk, "ahb1-mmc2", "ahb1", 0x060, BIT(10), 0); static SUNXI_CCU_GATE(ahb1_mmc3_clk, "ahb1-mmc3", "ahb1", - 0x060, BIT(12), 0); + 0x060, BIT(11), 0); static SUNXI_CCU_GATE(ahb1_nand1_clk, "ahb1-nand1", "ahb1", - 0x060, BIT(13), 0); + 0x060, BIT(12), 0); static SUNXI_CCU_GATE(ahb1_nand0_clk, "ahb1-nand0", "ahb1", 0x060, BIT(13), 0); static SUNXI_CCU_GATE(ahb1_sdram_clk, "ahb1-sdram", "ahb1", diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c index 621b1cd996db..ac12f261f8ca 100644 --- a/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c +++ b/drivers/clk/sunxi-ng/ccu-sun8i-v3s.c @@ -542,7 +542,7 @@ static struct ccu_reset_map sun8i_v3s_ccu_resets[] = { [RST_BUS_OHCI0] = { 0x2c0, BIT(29) }, [RST_BUS_VE] = { 0x2c4, BIT(0) }, - [RST_BUS_TCON0] = { 0x2c4, BIT(3) }, + [RST_BUS_TCON0] = { 0x2c4, BIT(4) }, [RST_BUS_CSI] = { 0x2c4, BIT(8) }, [RST_BUS_DE] = { 0x2c4, BIT(12) }, [RST_BUS_DBG] = { 0x2c4, BIT(31) }, diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 242c3370544e..9ed46d188cb5 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -187,8 +187,8 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy) cpufreq_cooling_unregister(priv->cdev); dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table); - kfree(priv); dev_pm_opp_remove_all_dynamic(priv->cpu_dev); + kfree(priv); return 0; } diff --git a/drivers/crypto/ccree/cc_pm.h b/drivers/crypto/ccree/cc_pm.h index f62624357020..907a6db4d6c0 100644 --- a/drivers/crypto/ccree/cc_pm.h +++ b/drivers/crypto/ccree/cc_pm.h @@ -30,7 +30,7 @@ static inline int cc_pm_init(struct cc_drvdata *drvdata) return 0; } -static void cc_pm_go(struct cc_drvdata *drvdata) {} +static inline void cc_pm_go(struct cc_drvdata *drvdata) {} static inline void cc_pm_fini(struct cc_drvdata *drvdata) {} diff --git a/drivers/gpio/gpio-mt7621.c b/drivers/gpio/gpio-mt7621.c index 00e954f22bc9..74401e0adb29 100644 --- a/drivers/gpio/gpio-mt7621.c +++ b/drivers/gpio/gpio-mt7621.c @@ -30,6 +30,7 @@ #define GPIO_REG_EDGE 0xA0 struct mtk_gc { + struct irq_chip irq_chip; struct gpio_chip chip; spinlock_t lock; int bank; @@ -189,13 +190,6 @@ mediatek_gpio_irq_type(struct irq_data *d, unsigned int type) return 0; } -static struct irq_chip mediatek_gpio_irq_chip = { - .irq_unmask = mediatek_gpio_irq_unmask, - .irq_mask = mediatek_gpio_irq_mask, - .irq_mask_ack = mediatek_gpio_irq_mask, - .irq_set_type = mediatek_gpio_irq_type, -}; - static int mediatek_gpio_xlate(struct gpio_chip *chip, const struct of_phandle_args *spec, u32 *flags) @@ -254,6 +248,13 @@ mediatek_gpio_bank_probe(struct device *dev, return ret; } + rg->irq_chip.name = dev_name(dev); + rg->irq_chip.parent_device = dev; + rg->irq_chip.irq_unmask = mediatek_gpio_irq_unmask; + rg->irq_chip.irq_mask = mediatek_gpio_irq_mask; + rg->irq_chip.irq_mask_ack = mediatek_gpio_irq_mask; + rg->irq_chip.irq_set_type = mediatek_gpio_irq_type; + if (mtk->gpio_irq) { /* * Manually request the irq here instead of passing @@ -270,14 +271,14 @@ mediatek_gpio_bank_probe(struct device *dev, return ret; } - ret = gpiochip_irqchip_add(&rg->chip, &mediatek_gpio_irq_chip, + ret = gpiochip_irqchip_add(&rg->chip, &rg->irq_chip, 0, handle_simple_irq, IRQ_TYPE_NONE); if (ret) { dev_err(dev, "failed to add gpiochip_irqchip\n"); return ret; } - gpiochip_set_chained_irqchip(&rg->chip, &mediatek_gpio_irq_chip, + gpiochip_set_chained_irqchip(&rg->chip, &rg->irq_chip, mtk->gpio_irq, NULL); } @@ -310,7 +311,6 @@ mediatek_gpio_probe(struct platform_device *pdev) mtk->gpio_irq = irq_of_parse_and_map(np, 0); mtk->dev = dev; platform_set_drvdata(pdev, mtk); - mediatek_gpio_irq_chip.name = dev_name(dev); for (i = 0; i < MTK_BANK_CNT; i++) { ret = mediatek_gpio_bank_probe(dev, np, i); diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c index e9600b556f39..bcc6be4a5cb2 100644 --- a/drivers/gpio/gpio-pxa.c +++ b/drivers/gpio/gpio-pxa.c @@ -245,6 +245,7 @@ static bool pxa_gpio_has_pinctrl(void) { switch (gpio_type) { case PXA3XX_GPIO: + case MMP2_GPIO: return false; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index b65e18101108..e860412043bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -212,6 +212,7 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags) } if (amdgpu_device_is_px(dev)) { + dev_pm_set_driver_flags(dev->dev, DPM_FLAG_NEVER_SKIP); pm_runtime_use_autosuspend(dev->dev); pm_runtime_set_autosuspend_delay(dev->dev, 5000); pm_runtime_set_active(dev->dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h index 698fd8a2f775..889e443eeee7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mode.h @@ -406,6 +406,7 @@ struct amdgpu_crtc { struct amdgpu_flip_work *pflip_works; enum amdgpu_flip_status pflip_status; int deferred_flip_completion; + u64 last_flip_vblank; /* pll sharing */ struct amdgpu_atom_ss ss; bool ss_enabled; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 942b5ebc6dc2..ead851413c0a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -652,12 +652,14 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev, struct ttm_bo_global *glob = adev->mman.bdev.glob; struct amdgpu_vm_bo_base *bo_base; +#if 0 if (vm->bulk_moveable) { spin_lock(&glob->lru_lock); ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move); spin_unlock(&glob->lru_lock); return; } +#endif memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move)); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 127b85983e8f..c816e55d43a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -128,7 +128,7 @@ static const struct soc15_reg_golden golden_settings_sdma0_4_2_init[] = { static const struct soc15_reg_golden golden_settings_sdma0_4_2[] = { - SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831d07), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CHICKEN_BITS, 0xfe931f07, 0x02831f07), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_CLK_CTRL, 0xffffffff, 0x3f000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG, 0x0000773f, 0x00004002), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_GB_ADDR_CONFIG_READ, 0x0000773f, 0x00004002), @@ -158,7 +158,7 @@ static const struct soc15_reg_golden golden_settings_sdma0_4_2[] = }; static const struct soc15_reg_golden golden_settings_sdma1_4_2[] = { - SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831d07), + SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831f07), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CLK_CTRL, 0xffffffff, 0x3f000100), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG, 0x0000773f, 0x00004002), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GB_ADDR_CONFIG_READ, 0x0000773f, 0x00004002), 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 c87fcda61b66..0642dfe22582 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -303,12 +303,11 @@ static void dm_pflip_high_irq(void *interrupt_params) return; } + /* Update to correct count(s) if racing with vblank irq */ + amdgpu_crtc->last_flip_vblank = drm_crtc_accurate_vblank_count(&amdgpu_crtc->base); /* wake up userspace */ if (amdgpu_crtc->event) { - /* Update to correct count(s) if racing with vblank irq */ - drm_crtc_accurate_vblank_count(&amdgpu_crtc->base); - drm_crtc_send_vblank_event(&amdgpu_crtc->base, amdgpu_crtc->event); /* page flip completed. clean up */ @@ -786,12 +785,13 @@ static int dm_suspend(void *handle) struct amdgpu_display_manager *dm = &adev->dm; int ret = 0; + WARN_ON(adev->dm.cached_state); + adev->dm.cached_state = drm_atomic_helper_suspend(adev->ddev); + s3_handle_mst(adev->ddev, true); amdgpu_dm_irq_suspend(adev); - WARN_ON(adev->dm.cached_state); - adev->dm.cached_state = drm_atomic_helper_suspend(adev->ddev); dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c index bbe051736a18..6e142c2db986 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c @@ -696,6 +696,11 @@ static void dce11_update_clocks(struct clk_mgr *clk_mgr, { struct dce_clk_mgr *clk_mgr_dce = TO_DCE_CLK_MGR(clk_mgr); struct dm_pp_power_level_change_request level_change_req; + int patched_disp_clk = context->bw.dce.dispclk_khz; + + /*TODO: W/A for dal3 linux, investigate why this works */ + if (!clk_mgr_dce->dfs_bypass_active) + patched_disp_clk = patched_disp_clk * 115 / 100; level_change_req.power_level = dce_get_required_clocks_state(clk_mgr, context); /* get max clock state from PPLIB */ @@ -705,9 +710,9 @@ static void dce11_update_clocks(struct clk_mgr *clk_mgr, clk_mgr_dce->cur_min_clks_state = level_change_req.power_level; } - if (should_set_clock(safe_to_lower, context->bw.dce.dispclk_khz, clk_mgr->clks.dispclk_khz)) { - context->bw.dce.dispclk_khz = dce_set_clock(clk_mgr, context->bw.dce.dispclk_khz); - clk_mgr->clks.dispclk_khz = context->bw.dce.dispclk_khz; + if (should_set_clock(safe_to_lower, patched_disp_clk, clk_mgr->clks.dispclk_khz)) { + context->bw.dce.dispclk_khz = dce_set_clock(clk_mgr, patched_disp_clk); + clk_mgr->clks.dispclk_khz = patched_disp_clk; } dce11_pplib_apply_display_requirements(clk_mgr->ctx->dc, context); } diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h index acd418515346..a6b80fdaa666 100644 --- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.h @@ -37,6 +37,10 @@ void dce100_prepare_bandwidth( struct dc *dc, struct dc_state *context); +void dce100_optimize_bandwidth( + struct dc *dc, + struct dc_state *context); + bool dce100_enable_display_power_gating(struct dc *dc, uint8_t controller_id, struct dc_bios *dcb, enum pipe_gating_control power_gating); diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c index a60a90e68d91..c4543178ba20 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_hw_sequencer.c @@ -77,6 +77,6 @@ void dce80_hw_sequencer_construct(struct dc *dc) dc->hwss.enable_display_power_gating = dce100_enable_display_power_gating; dc->hwss.pipe_control_lock = dce_pipe_control_lock; dc->hwss.prepare_bandwidth = dce100_prepare_bandwidth; - dc->hwss.optimize_bandwidth = dce100_prepare_bandwidth; + dc->hwss.optimize_bandwidth = dce100_optimize_bandwidth; } diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c index 2eca81b5cf2f..c109ace96be9 100644 --- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c @@ -792,9 +792,22 @@ bool dce80_validate_bandwidth( struct dc *dc, struct dc_state *context) { - /* TODO implement when needed but for now hardcode max value*/ - context->bw.dce.dispclk_khz = 681000; - context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ; + int i; + bool at_least_one_pipe = false; + + for (i = 0; i < dc->res_pool->pipe_count; i++) { + if (context->res_ctx.pipe_ctx[i].stream) + at_least_one_pipe = true; + } + + if (at_least_one_pipe) { + /* TODO implement when needed but for now hardcode max value*/ + context->bw.dce.dispclk_khz = 681000; + context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER_CZ; + } else { + context->bw.dce.dispclk_khz = 0; + context->bw.dce.yclk_khz = 0; + } return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 8ba895c4b445..d1a8f1c302a9 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -2693,8 +2693,8 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) .mirror = pipe_ctx->plane_state->horizontal_mirror }; - pos_cpy.x -= pipe_ctx->plane_state->dst_rect.x; - pos_cpy.y -= pipe_ctx->plane_state->dst_rect.y; + pos_cpy.x_hotspot += pipe_ctx->plane_state->dst_rect.x; + pos_cpy.y_hotspot += pipe_ctx->plane_state->dst_rect.y; if (pipe_ctx->plane_state->address.type == PLN_ADDR_TYPE_VIDEO_PROGRESSIVE) diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c index cb55bdc36f3f..6b6e037258c3 100644 --- a/drivers/gpu/drm/bochs/bochs_drv.c +++ b/drivers/gpu/drm/bochs/bochs_drv.c @@ -145,6 +145,10 @@ static int bochs_pci_probe(struct pci_dev *pdev, if (IS_ERR(dev)) return PTR_ERR(dev); + ret = pci_enable_device(pdev); + if (ret) + goto err_free_dev; + dev->pdev = pdev; pci_set_drvdata(pdev, dev); diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index c53ecbd9abdd..540a77a2ade9 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1608,6 +1608,15 @@ int drm_atomic_helper_async_check(struct drm_device *dev, old_plane_state->crtc != new_plane_state->crtc) return -EINVAL; + /* + * FIXME: Since prepare_fb and cleanup_fb are always called on + * the new_plane_state for async updates we need to block framebuffer + * changes. This prevents use of a fb that's been cleaned up and + * double cleanups from occuring. + */ + if (old_plane_state->fb != new_plane_state->fb) + return -EINVAL; + funcs = plane->helper_private; if (!funcs->atomic_async_update) return -EINVAL; diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 376ffe842e26..e8f694b57b8a 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -338,8 +338,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, bool *enabled, int width, int height) { struct drm_i915_private *dev_priv = to_i915(fb_helper->dev); - unsigned long conn_configured, conn_seq, mask; unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG); + unsigned long conn_configured, conn_seq; int i, j; bool *save_enabled; bool fallback = true, ret = true; @@ -357,10 +357,9 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper, drm_modeset_backoff(&ctx); memcpy(save_enabled, enabled, count); - mask = GENMASK(count - 1, 0); + conn_seq = GENMASK(count - 1, 0); conn_configured = 0; retry: - conn_seq = conn_configured; for (i = 0; i < count; i++) { struct drm_fb_helper_connector *fb_conn; struct drm_connector *connector; @@ -373,7 +372,8 @@ retry: if (conn_configured & BIT(i)) continue; - if (conn_seq == 0 && !connector->has_tile) + /* First pass, only consider tiled connectors */ + if (conn_seq == GENMASK(count - 1, 0) && !connector->has_tile) continue; if (connector->status == connector_status_connected) @@ -477,8 +477,10 @@ retry: conn_configured |= BIT(i); } - if ((conn_configured & mask) != mask && conn_configured != conn_seq) + if (conn_configured != conn_seq) { /* repeat until no more are found */ + conn_seq = conn_configured; goto retry; + } /* * If the BIOS didn't enable everything it could, fall back to have the diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c index dec1e081f529..6a8fb6fd183c 100644 --- a/drivers/gpu/drm/radeon/radeon_kms.c +++ b/drivers/gpu/drm/radeon/radeon_kms.c @@ -172,6 +172,7 @@ int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags) } if (radeon_is_px(dev)) { + dev_pm_set_driver_flags(dev->dev, DPM_FLAG_NEVER_SKIP); pm_runtime_use_autosuspend(dev->dev); pm_runtime_set_autosuspend_delay(dev->dev, 5000); pm_runtime_set_active(dev->dev); diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c index c13c0ba30f63..d499cd61c0e8 100644 --- a/drivers/infiniband/hw/cxgb4/device.c +++ b/drivers/infiniband/hw/cxgb4/device.c @@ -783,6 +783,7 @@ void c4iw_init_dev_ucontext(struct c4iw_rdev *rdev, static int c4iw_rdev_open(struct c4iw_rdev *rdev) { int err; + unsigned int factor; c4iw_init_dev_ucontext(rdev, &rdev->uctx); @@ -806,8 +807,18 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev) return -EINVAL; } - rdev->qpmask = rdev->lldi.udb_density - 1; - rdev->cqmask = rdev->lldi.ucq_density - 1; + /* This implementation requires a sge_host_page_size <= PAGE_SIZE. */ + if (rdev->lldi.sge_host_page_size > PAGE_SIZE) { + pr_err("%s: unsupported sge host page size %u\n", + pci_name(rdev->lldi.pdev), + rdev->lldi.sge_host_page_size); + return -EINVAL; + } + + factor = PAGE_SIZE / rdev->lldi.sge_host_page_size; + rdev->qpmask = (rdev->lldi.udb_density * factor) - 1; + rdev->cqmask = (rdev->lldi.ucq_density * factor) - 1; + pr_debug("dev %s stag start 0x%0x size 0x%0x num stags %d pbl start 0x%0x size 0x%0x rq start 0x%0x size 0x%0x qp qid start %u size %u cq qid start %u size %u srq size %u\n", pci_name(rdev->lldi.pdev), rdev->lldi.vr->stag.start, rdev->lldi.vr->stag.size, c4iw_num_stags(rdev), diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 31d91538bbf4..694324b37480 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -3032,7 +3032,6 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) { struct srp_target_port *target = host_to_target(scmnd->device->host); struct srp_rdma_ch *ch; - int i, j; u8 status; shost_printk(KERN_ERR, target->scsi_host, "SRP reset_device called\n"); @@ -3044,15 +3043,6 @@ static int srp_reset_device(struct scsi_cmnd *scmnd) if (status) return FAILED; - for (i = 0; i < target->ch_count; i++) { - ch = &target->ch[i]; - for (j = 0; j < target->req_ring_size; ++j) { - struct srp_request *req = &ch->req_ring[j]; - - srp_finish_req(ch, req, scmnd->device, DID_RESET << 16); - } - } - return SUCCESS; } diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c index dc9f14811e0f..58dc70bffd5b 100644 --- a/drivers/iommu/dmar.c +++ b/drivers/iommu/dmar.c @@ -144,7 +144,7 @@ dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event) for (tmp = dev; tmp; tmp = tmp->bus->self) level++; - size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path); + size = sizeof(*info) + level * sizeof(info->path[0]); if (size <= sizeof(dmar_pci_notify_info_buf)) { info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf; } else { diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c index d713271ebf7c..a64116586b4c 100644 --- a/drivers/mailbox/bcm-flexrm-mailbox.c +++ b/drivers/mailbox/bcm-flexrm-mailbox.c @@ -1396,9 +1396,9 @@ static void flexrm_shutdown(struct mbox_chan *chan) /* Clear ring flush state */ timeout = 1000; /* timeout of 1s */ - writel_relaxed(0x0, ring + RING_CONTROL); + writel_relaxed(0x0, ring->regs + RING_CONTROL); do { - if (!(readl_relaxed(ring + RING_FLUSH_DONE) & + if (!(readl_relaxed(ring->regs + RING_FLUSH_DONE) & FLUSH_DONE_MASK)) break; mdelay(1); diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index c6a7d4582dc6..38d9df3fb199 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -310,6 +310,7 @@ int mbox_flush(struct mbox_chan *chan, unsigned long timeout) return ret; } +EXPORT_SYMBOL_GPL(mbox_flush); /** * mbox_request_channel - Request a mailbox channel. diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 14f3fdb8c6bb..9ce8eb51a60f 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2380,12 +2380,6 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card, snprintf(md->disk->disk_name, sizeof(md->disk->disk_name), "mmcblk%u%s", card->host->index, subname ? subname : ""); - if (mmc_card_mmc(card)) - blk_queue_logical_block_size(md->queue.queue, - card->ext_csd.data_sector_size); - else - blk_queue_logical_block_size(md->queue.queue, 512); - set_capacity(md->disk, size); if (mmc_host_cmd23(card->host)) { diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 5bd58b95d318..b27a1e620233 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -95,7 +95,7 @@ static void mmc_should_fail_request(struct mmc_host *host, if (!data) return; - if (cmd->error || data->error || + if ((cmd && cmd->error) || data->error || !should_fail(&host->fail_mmc_request, data->blksz * data->blocks)) return; diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 35cc138b096d..15a45ec6518d 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -355,6 +355,7 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card) { struct mmc_host *host = card->host; u64 limit = BLK_BOUNCE_HIGH; + unsigned block_size = 512; if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask) limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT; @@ -368,7 +369,13 @@ static void mmc_setup_queue(struct mmc_queue *mq, struct mmc_card *card) blk_queue_max_hw_sectors(mq->queue, min(host->max_blk_count, host->max_req_size / 512)); blk_queue_max_segments(mq->queue, host->max_segs); - blk_queue_max_segment_size(mq->queue, host->max_seg_size); + + if (mmc_card_mmc(card)) + block_size = card->ext_csd.data_sector_size; + + blk_queue_logical_block_size(mq->queue, block_size); + blk_queue_max_segment_size(mq->queue, + round_down(host->max_seg_size, block_size)); INIT_WORK(&mq->recovery_work, mmc_mq_recovery_handler); INIT_WORK(&mq->complete_work, mmc_blk_mq_complete_work); diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c index 159270e947cf..a8af682a9182 100644 --- a/drivers/mmc/host/cqhci.c +++ b/drivers/mmc/host/cqhci.c @@ -201,7 +201,7 @@ static int cqhci_host_alloc_tdl(struct cqhci_host *cq_host) cq_host->desc_size = cq_host->slot_sz * cq_host->num_slots; cq_host->data_size = cq_host->trans_desc_len * cq_host->mmc->max_segs * - (cq_host->num_slots - 1); + cq_host->mmc->cqe_qdepth; pr_debug("%s: cqhci: desc_size: %zu data_sz: %zu slot-sz: %d\n", mmc_hostname(cq_host->mmc), cq_host->desc_size, cq_host->data_size, @@ -217,12 +217,21 @@ static int cqhci_host_alloc_tdl(struct cqhci_host *cq_host) cq_host->desc_size, &cq_host->desc_dma_base, GFP_KERNEL); + if (!cq_host->desc_base) + return -ENOMEM; + cq_host->trans_desc_base = dmam_alloc_coherent(mmc_dev(cq_host->mmc), cq_host->data_size, &cq_host->trans_desc_dma_base, GFP_KERNEL); - if (!cq_host->desc_base || !cq_host->trans_desc_base) + if (!cq_host->trans_desc_base) { + dmam_free_coherent(mmc_dev(cq_host->mmc), cq_host->desc_size, + cq_host->desc_base, + cq_host->desc_dma_base); + cq_host->desc_base = NULL; + cq_host->desc_dma_base = 0; return -ENOMEM; + } pr_debug("%s: cqhci: desc-base: 0x%p trans-base: 0x%p\n desc_dma 0x%llx trans_dma: 0x%llx\n", mmc_hostname(cq_host->mmc), cq_host->desc_base, cq_host->trans_desc_base, diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 10ba46b728e8..8ade14fb2148 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1450,6 +1450,7 @@ static int mmc_spi_probe(struct spi_device *spi) mmc->caps &= ~MMC_CAP_NEEDS_POLL; mmc_gpiod_request_cd_irq(mmc); } + mmc_detect_change(mmc, 0); /* Index 1 is write protect/read only */ status = mmc_gpiod_request_ro(mmc, NULL, 1, false, 0, NULL); diff --git a/drivers/mmc/host/renesas_sdhi_sys_dmac.c b/drivers/mmc/host/renesas_sdhi_sys_dmac.c index 8471160316e0..02cd878e209f 100644 --- a/drivers/mmc/host/renesas_sdhi_sys_dmac.c +++ b/drivers/mmc/host/renesas_sdhi_sys_dmac.c @@ -65,6 +65,7 @@ static const struct renesas_sdhi_of_data of_rcar_gen2_compatible = { .scc_offset = 0x0300, .taps = rcar_gen2_scc_taps, .taps_num = ARRAY_SIZE(rcar_gen2_scc_taps), + .max_blk_count = 0xffffffff, }; /* Definitions for sampling clocks */ diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index d0d319398a54..00d41b312c79 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1095,11 +1095,12 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host) writel(readl(host->ioaddr + SDHCI_HOST_CONTROL) | ESDHC_BURST_LEN_EN_INCR, host->ioaddr + SDHCI_HOST_CONTROL); + /* - * erratum ESDHC_FLAG_ERR004536 fix for MX6Q TO1.2 and MX6DL - * TO1.1, it's harmless for MX6SL - */ - writel(readl(host->ioaddr + 0x6c) | BIT(7), + * erratum ESDHC_FLAG_ERR004536 fix for MX6Q TO1.2 and MX6DL + * TO1.1, it's harmless for MX6SL + */ + writel(readl(host->ioaddr + 0x6c) & ~BIT(7), host->ioaddr + 0x6c); /* disable DLL_CTRL delay line settings */ diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h index c03529e3f01a..2adb0d24360f 100644 --- a/drivers/mmc/host/tmio_mmc.h +++ b/drivers/mmc/host/tmio_mmc.h @@ -277,6 +277,11 @@ static inline void sd_ctrl_write32_as_16_and_16(struct tmio_mmc_host *host, iowrite16(val >> 16, host->ctl + ((addr + 2) << host->bus_shift)); } +static inline void sd_ctrl_write32(struct tmio_mmc_host *host, int addr, u32 val) +{ + iowrite32(val, host->ctl + (addr << host->bus_shift)); +} + static inline void sd_ctrl_write32_rep(struct tmio_mmc_host *host, int addr, const u32 *buf, int count) { diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c index 085a0fab769c..f7a6f005899a 100644 --- a/drivers/mmc/host/tmio_mmc_core.c +++ b/drivers/mmc/host/tmio_mmc_core.c @@ -43,6 +43,7 @@ #include <linux/regulator/consumer.h> #include <linux/mmc/sdio.h> #include <linux/scatterlist.h> +#include <linux/sizes.h> #include <linux/spinlock.h> #include <linux/swiotlb.h> #include <linux/workqueue.h> @@ -629,7 +630,7 @@ static bool __tmio_mmc_sdcard_irq(struct tmio_mmc_host *host, int ireg, return false; } -static void __tmio_mmc_sdio_irq(struct tmio_mmc_host *host) +static bool __tmio_mmc_sdio_irq(struct tmio_mmc_host *host) { struct mmc_host *mmc = host->mmc; struct tmio_mmc_data *pdata = host->pdata; @@ -637,7 +638,7 @@ static void __tmio_mmc_sdio_irq(struct tmio_mmc_host *host) unsigned int sdio_status; if (!(pdata->flags & TMIO_MMC_SDIO_IRQ)) - return; + return false; status = sd_ctrl_read16(host, CTL_SDIO_STATUS); ireg = status & TMIO_SDIO_MASK_ALL & ~host->sdio_irq_mask; @@ -650,6 +651,8 @@ static void __tmio_mmc_sdio_irq(struct tmio_mmc_host *host) if (mmc->caps & MMC_CAP_SDIO_IRQ && ireg & TMIO_SDIO_STAT_IOIRQ) mmc_signal_sdio_irq(mmc); + + return ireg; } irqreturn_t tmio_mmc_irq(int irq, void *devid) @@ -668,9 +671,10 @@ irqreturn_t tmio_mmc_irq(int irq, void *devid) if (__tmio_mmc_sdcard_irq(host, ireg, status)) return IRQ_HANDLED; - __tmio_mmc_sdio_irq(host); + if (__tmio_mmc_sdio_irq(host)) + return IRQ_HANDLED; - return IRQ_HANDLED; + return IRQ_NONE; } EXPORT_SYMBOL_GPL(tmio_mmc_irq); @@ -700,7 +704,10 @@ static int tmio_mmc_start_data(struct tmio_mmc_host *host, /* Set transfer length / blocksize */ sd_ctrl_write16(host, CTL_SD_XFER_LEN, data->blksz); - sd_ctrl_write16(host, CTL_XFER_BLK_COUNT, data->blocks); + if (host->mmc->max_blk_count >= SZ_64K) + sd_ctrl_write32(host, CTL_XFER_BLK_COUNT, data->blocks); + else + sd_ctrl_write16(host, CTL_XFER_BLK_COUNT, data->blocks); tmio_mmc_start_dma(host, data); diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c index 22f753e555ac..83f88b8b5d9f 100644 --- a/drivers/mtd/devices/powernv_flash.c +++ b/drivers/mtd/devices/powernv_flash.c @@ -212,7 +212,7 @@ static int powernv_flash_set_driver_info(struct device *dev, * Going to have to check what details I need to set and how to * get them */ - mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%pOFn", dev->of_node); + mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node); mtd->type = MTD_NORFLASH; mtd->flags = MTD_WRITEABLE; mtd->size = size; diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 999b705769a8..3ef01baef9b6 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -507,6 +507,7 @@ static int mtd_nvmem_add(struct mtd_info *mtd) { struct nvmem_config config = {}; + config.id = -1; config.dev = &mtd->dev; config.name = mtd->name; config.owner = THIS_MODULE; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 485462d3087f..537c90c8eb0a 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1183,29 +1183,22 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb) } } - /* Link-local multicast packets should be passed to the - * stack on the link they arrive as well as pass them to the - * bond-master device. These packets are mostly usable when - * stack receives it with the link on which they arrive - * (e.g. LLDP) they also must be available on master. Some of - * the use cases include (but are not limited to): LLDP agents - * that must be able to operate both on enslaved interfaces as - * well as on bonds themselves; linux bridges that must be able - * to process/pass BPDUs from attached bonds when any kind of - * STP version is enabled on the network. + /* + * For packets determined by bond_should_deliver_exact_match() call to + * be suppressed we want to make an exception for link-local packets. + * This is necessary for e.g. LLDP daemons to be able to monitor + * inactive slave links without being forced to bind to them + * explicitly. + * + * At the same time, packets that are passed to the bonding master + * (including link-local ones) can have their originating interface + * determined via PACKET_ORIGDEV socket option. */ - if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) { - struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); - - if (nskb) { - nskb->dev = bond->dev; - nskb->queue_mapping = 0; - netif_rx(nskb); - } - return RX_HANDLER_PASS; - } - if (bond_should_deliver_exact_match(skb, slave, bond)) + if (bond_should_deliver_exact_match(skb, slave, bond)) { + if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) + return RX_HANDLER_PASS; return RX_HANDLER_EXACT; + } skb->dev = bond->dev; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 0e4bbdcc614f..c76892ac4e69 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -344,7 +344,8 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_CTRL, mgmt); } -static void b53_enable_vlan(struct b53_device *dev, bool enable) +static void b53_enable_vlan(struct b53_device *dev, bool enable, + bool enable_filtering) { u8 mgmt, vc0, vc1, vc4 = 0, vc5; @@ -369,8 +370,13 @@ static void b53_enable_vlan(struct b53_device *dev, bool enable) vc0 |= VC0_VLAN_EN | VC0_VID_CHK_EN | VC0_VID_HASH_VID; vc1 |= VC1_RX_MCST_UNTAG_EN | VC1_RX_MCST_FWD_EN; vc4 &= ~VC4_ING_VID_CHECK_MASK; - vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; - vc5 |= VC5_DROP_VTABLE_MISS; + if (enable_filtering) { + vc4 |= VC4_ING_VID_VIO_DROP << VC4_ING_VID_CHECK_S; + vc5 |= VC5_DROP_VTABLE_MISS; + } else { + vc4 |= VC4_ING_VID_VIO_FWD << VC4_ING_VID_CHECK_S; + vc5 &= ~VC5_DROP_VTABLE_MISS; + } if (is5325(dev)) vc0 &= ~VC0_RESERVED_1; @@ -420,6 +426,9 @@ static void b53_enable_vlan(struct b53_device *dev, bool enable) } b53_write8(dev, B53_CTRL_PAGE, B53_SWITCH_MODE, mgmt); + + dev->vlan_enabled = enable; + dev->vlan_filtering_enabled = enable_filtering; } static int b53_set_jumbo(struct b53_device *dev, bool enable, bool allow_10_100) @@ -632,25 +641,35 @@ static void b53_enable_mib(struct b53_device *dev) b53_write8(dev, B53_MGMT_PAGE, B53_GLOBAL_CONFIG, gc); } +static u16 b53_default_pvid(struct b53_device *dev) +{ + if (is5325(dev) || is5365(dev)) + return 1; + else + return 0; +} + int b53_configure_vlan(struct dsa_switch *ds) { struct b53_device *dev = ds->priv; struct b53_vlan vl = { 0 }; - int i; + int i, def_vid; + + def_vid = b53_default_pvid(dev); /* clear all vlan entries */ if (is5325(dev) || is5365(dev)) { - for (i = 1; i < dev->num_vlans; i++) + for (i = def_vid; i < dev->num_vlans; i++) b53_set_vlan_entry(dev, i, &vl); } else { b53_do_vlan_op(dev, VTA_CMD_CLEAR); } - b53_enable_vlan(dev, false); + b53_enable_vlan(dev, false, dev->vlan_filtering_enabled); b53_for_each_port(dev, i) b53_write16(dev, B53_VLAN_PAGE, - B53_VLAN_PORT_DEF_TAG(i), 1); + B53_VLAN_PORT_DEF_TAG(i), def_vid); if (!is5325(dev) && !is5365(dev)) b53_set_jumbo(dev, dev->enable_jumbo, false); @@ -1255,6 +1274,46 @@ EXPORT_SYMBOL(b53_phylink_mac_link_up); int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering) { + struct b53_device *dev = ds->priv; + struct net_device *bridge_dev; + unsigned int i; + u16 pvid, new_pvid; + + /* Handle the case were multiple bridges span the same switch device + * and one of them has a different setting than what is being requested + * which would be breaking filtering semantics for any of the other + * bridge devices. + */ + b53_for_each_port(dev, i) { + bridge_dev = dsa_to_port(ds, i)->bridge_dev; + if (bridge_dev && + bridge_dev != dsa_to_port(ds, port)->bridge_dev && + br_vlan_enabled(bridge_dev) != vlan_filtering) { + netdev_err(bridge_dev, + "VLAN filtering is global to the switch!\n"); + return -EINVAL; + } + } + + b53_read16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), &pvid); + new_pvid = pvid; + if (dev->vlan_filtering_enabled && !vlan_filtering) { + /* Filtering is currently enabled, use the default PVID since + * the bridge does not expect tagging anymore + */ + dev->ports[port].pvid = pvid; + new_pvid = b53_default_pvid(dev); + } else if (!dev->vlan_filtering_enabled && vlan_filtering) { + /* Filtering is currently disabled, restore the previous PVID */ + new_pvid = dev->ports[port].pvid; + } + + if (pvid != new_pvid) + b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), + new_pvid); + + b53_enable_vlan(dev, dev->vlan_enabled, vlan_filtering); + return 0; } EXPORT_SYMBOL(b53_vlan_filtering); @@ -1270,7 +1329,7 @@ int b53_vlan_prepare(struct dsa_switch *ds, int port, if (vlan->vid_end > dev->num_vlans) return -ERANGE; - b53_enable_vlan(dev, true); + b53_enable_vlan(dev, true, dev->vlan_filtering_enabled); return 0; } @@ -1300,7 +1359,7 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_fast_age_vlan(dev, vid); } - if (pvid) { + if (pvid && !dsa_is_cpu_port(ds, port)) { b53_write16(dev, B53_VLAN_PAGE, B53_VLAN_PORT_DEF_TAG(port), vlan->vid_end); b53_fast_age_vlan(dev, vid); @@ -1326,12 +1385,8 @@ int b53_vlan_del(struct dsa_switch *ds, int port, vl->members &= ~BIT(port); - if (pvid == vid) { - if (is5325(dev) || is5365(dev)) - pvid = 1; - else - pvid = 0; - } + if (pvid == vid) + pvid = b53_default_pvid(dev); if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag &= ~(BIT(port)); @@ -1644,10 +1699,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *br) b53_write16(dev, B53_PVLAN_PAGE, B53_PVLAN_PORT_MASK(port), pvlan); dev->ports[port].vlan_ctl_mask = pvlan; - if (is5325(dev) || is5365(dev)) - pvid = 1; - else - pvid = 0; + pvid = b53_default_pvid(dev); /* Make this port join all VLANs without VLAN entries */ if (is58xx(dev)) { diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index ec796482792d..4dc7ee38b258 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -91,6 +91,7 @@ enum { struct b53_port { u16 vlan_ctl_mask; struct ethtool_eee eee; + u16 pvid; }; struct b53_vlan { @@ -137,6 +138,8 @@ struct b53_device { unsigned int num_vlans; struct b53_vlan *vlans; + bool vlan_enabled; + bool vlan_filtering_enabled; unsigned int num_ports; struct b53_port *ports; }; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 17ec32b0a1cc..14138d423cf1 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -726,10 +726,11 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, { struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - struct ethtool_wolinfo pwol; + struct ethtool_wolinfo pwol = { }; /* Get the parent device WoL settings */ - p->ethtool_ops->get_wol(p, &pwol); + if (p->ethtool_ops->get_wol) + p->ethtool_ops->get_wol(p, &pwol); /* Advertise the parent device supported settings */ wol->supported = pwol.supported; @@ -750,9 +751,10 @@ static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, struct net_device *p = ds->ports[port].cpu_dp->master; struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); s8 cpu_port = ds->ports[port].cpu_dp->index; - struct ethtool_wolinfo pwol; + struct ethtool_wolinfo pwol = { }; - p->ethtool_ops->get_wol(p, &pwol); + if (p->ethtool_ops->get_wol) + p->ethtool_ops->get_wol(p, &pwol); if (wol->wolopts & ~pwol.supported) return -EINVAL; diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 693a67f45bef..ddc1f9ca8ebc 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -1162,6 +1162,12 @@ static struct platform_driver gswip_driver = { module_platform_driver(gswip_driver); +MODULE_FIRMWARE("lantiq/xrx300_phy11g_a21.bin"); +MODULE_FIRMWARE("lantiq/xrx300_phy22f_a21.bin"); +MODULE_FIRMWARE("lantiq/xrx200_phy11g_a14.bin"); +MODULE_FIRMWARE("lantiq/xrx200_phy11g_a22.bin"); +MODULE_FIRMWARE("lantiq/xrx200_phy22f_a14.bin"); +MODULE_FIRMWARE("lantiq/xrx200_phy22f_a22.bin"); MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>"); MODULE_DESCRIPTION("Lantiq / Intel GSWIP driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 12fd7ce3f1ff..7e3c00bd9532 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -896,7 +896,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, default: return U64_MAX; } - value = (((u64)high) << 16) | low; + value = (((u64)high) << 32) | low; return value; } @@ -3093,7 +3093,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = { .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, .port_link_state = mv88e6352_port_link_state, .port_get_cmode = mv88e6185_port_get_cmode, - .stats_snapshot = mv88e6320_g1_stats_snapshot, + .stats_snapshot = mv88e6xxx_g1_stats_snapshot, .stats_set_histogram = mv88e6095_g1_stats_set_histogram, .stats_get_sset_count = mv88e6095_stats_get_sset_count, .stats_get_strings = mv88e6095_stats_get_strings, @@ -4595,6 +4595,14 @@ static int mv88e6xxx_smi_init(struct mv88e6xxx_chip *chip, return 0; } +static void mv88e6xxx_ports_cmode_init(struct mv88e6xxx_chip *chip) +{ + int i; + + for (i = 0; i < mv88e6xxx_num_ports(chip); i++) + chip->ports[i].cmode = MV88E6XXX_PORT_STS_CMODE_INVALID; +} + static enum dsa_tag_protocol mv88e6xxx_get_tag_protocol(struct dsa_switch *ds, int port) { @@ -4631,6 +4639,8 @@ static const char *mv88e6xxx_drv_probe(struct device *dsa_dev, if (err) goto free; + mv88e6xxx_ports_cmode_init(chip); + mutex_lock(&chip->reg_lock); err = mv88e6xxx_switch_reset(chip); mutex_unlock(&chip->reg_lock); diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index ebd26b6a93e6..79ab51e69aee 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -398,6 +398,10 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, cmode = 0; } + /* cmode doesn't change, nothing to do for us */ + if (cmode == chip->ports[port].cmode) + return 0; + lane = mv88e6390x_serdes_get_lane(chip, port); if (lane < 0) return lane; @@ -408,7 +412,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, return err; } - err = mv88e6390_serdes_power(chip, port, false); + err = mv88e6390x_serdes_power(chip, port, false); if (err) return err; @@ -424,7 +428,7 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, if (err) return err; - err = mv88e6390_serdes_power(chip, port, true); + err = mv88e6390x_serdes_power(chip, port, true); if (err) return err; diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index e583641de758..4aadf321edb7 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -52,6 +52,7 @@ #define MV88E6185_PORT_STS_CMODE_1000BASE_X 0x0005 #define MV88E6185_PORT_STS_CMODE_PHY 0x0006 #define MV88E6185_PORT_STS_CMODE_DISABLED 0x0007 +#define MV88E6XXX_PORT_STS_CMODE_INVALID 0xff /* Offset 0x01: MAC (or PCS or Physical) Control Register */ #define MV88E6XXX_PORT_MAC_CTL 0x01 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 b58ca7cb8e9d..fbba300c1d01 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 @@ -275,6 +275,9 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self) { + /* Tx TC/Queue number config */ + hw_atl_rpb_tps_tx_tc_mode_set(self, 1U); + hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U); hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U); hw_atl_thm_lso_tcp_flag_of_last_pkt_set(self, 0x0F7FU); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index 939f77e2e117..8ac7a67b15c1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -1274,6 +1274,15 @@ void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en) HW_ATL_TPB_TX_BUF_EN_SHIFT, tx_buff_en); } +void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw, + u32 tx_traf_class_mode) +{ + aq_hw_write_reg_bit(aq_hw, HW_ATL_TPB_TX_TC_MODE_ADDR, + HW_ATL_TPB_TX_TC_MODE_MSK, + HW_ATL_TPB_TX_TC_MODE_SHIFT, + tx_traf_class_mode); +} + void hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(struct aq_hw_s *aq_hw, u32 tx_buff_hi_threshold_per_tc, u32 buffer) diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index 03c570d115fe..f529540bfd7e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -605,6 +605,10 @@ void hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(struct aq_hw_s *aq_hw, /* tpb */ +/* set TX Traffic Class Mode */ +void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw, + u32 tx_traf_class_mode); + /* set tx buffer enable */ void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index 8470d92db812..e91ffce005f1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -1948,6 +1948,19 @@ /* default value of bitfield tx_buf_en */ #define HW_ATL_TPB_TX_BUF_EN_DEFAULT 0x0 +/* register address for bitfield tx_tc_mode */ +#define HW_ATL_TPB_TX_TC_MODE_ADDR 0x00007900 +/* bitmask for bitfield tx_tc_mode */ +#define HW_ATL_TPB_TX_TC_MODE_MSK 0x00000100 +/* inverted bitmask for bitfield tx_tc_mode */ +#define HW_ATL_TPB_TX_TC_MODE_MSKN 0xFFFFFEFF +/* lower bit position of bitfield tx_tc_mode */ +#define HW_ATL_TPB_TX_TC_MODE_SHIFT 8 +/* width of bitfield tx_tc_mode */ +#define HW_ATL_TPB_TX_TC_MODE_WIDTH 1 +/* default value of bitfield tx_tc_mode */ +#define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0 + /* tx tx{b}_hi_thresh[c:0] bitfield definitions * preprocessor definitions for the bitfield "tx{b}_hi_thresh[c:0]". * parameter: buffer {b} | stride size 0x10 | range [0, 7] diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index bb41becb6609..31ff1e0d1baa 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -1335,13 +1335,11 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; struct atl2_adapter *adapter; - static int cards_found; + static int cards_found = 0; unsigned long mmio_start; int mmio_len; int err; - cards_found = 0; - err = pci_enable_device(pdev); if (err) return err; diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 28c9b0bdf2f6..bc3ac369cbe3 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -134,6 +134,10 @@ static void bcm_sysport_set_rx_csum(struct net_device *dev, priv->rx_chk_en = !!(wanted & NETIF_F_RXCSUM); reg = rxchk_readl(priv, RXCHK_CONTROL); + /* Clear L2 header checks, which would prevent BPDUs + * from being received. + */ + reg &= ~RXCHK_L2_HDR_DIS; if (priv->rx_chk_en) reg |= RXCHK_EN; else diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8bc7e495b027..803f7990d32b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -500,6 +500,12 @@ normal_tx: } length >>= 9; + if (unlikely(length >= ARRAY_SIZE(bnxt_lhint_arr))) { + dev_warn_ratelimited(&pdev->dev, "Dropped oversize %d bytes TX packet.\n", + skb->len); + i = 0; + goto tx_dma_error; + } flags |= bnxt_lhint_arr[length]; txbd->tx_bd_len_flags_type = cpu_to_le32(flags); @@ -3903,7 +3909,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, if (len) break; /* on first few passes, just barely sleep */ - if (i < DFLT_HWRM_CMD_TIMEOUT) + if (i < HWRM_SHORT_TIMEOUT_COUNTER) usleep_range(HWRM_SHORT_MIN_TIMEOUT, HWRM_SHORT_MAX_TIMEOUT); else @@ -3926,7 +3932,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, dma_rmb(); if (*valid) break; - udelay(1); + usleep_range(1, 5); } if (j >= HWRM_VALID_BIT_DELAY_USEC) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index a451796deefe..2fb653e0048d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -582,7 +582,7 @@ struct nqe_cn { (HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT + \ ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT)) -#define HWRM_VALID_BIT_DELAY_USEC 20 +#define HWRM_VALID_BIT_DELAY_USEC 150 #define BNXT_HWRM_CHNL_CHIMP 0 #define BNXT_HWRM_CHNL_KONG 1 diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h index f4d81765221e..62636c1ed141 100644 --- a/drivers/net/ethernet/cavium/thunder/nic.h +++ b/drivers/net/ethernet/cavium/thunder/nic.h @@ -271,7 +271,7 @@ struct xcast_addr_list { }; struct nicvf_work { - struct delayed_work work; + struct work_struct work; u8 mode; struct xcast_addr_list *mc; }; @@ -327,7 +327,11 @@ struct nicvf { struct nicvf_work rx_mode_work; /* spinlock to protect workqueue arguments from concurrent access */ spinlock_t rx_mode_wq_lock; - + /* workqueue for handling kernel ndo_set_rx_mode() calls */ + struct workqueue_struct *nicvf_rx_mode_wq; + /* mutex to protect VF's mailbox contents from concurrent access */ + struct mutex rx_mode_mtx; + struct delayed_work link_change_work; /* PTP timestamp */ struct cavium_ptp *ptp_clock; /* Inbound timestamping is on */ @@ -575,10 +579,8 @@ struct set_ptp { struct xcast { u8 msg; - union { - u8 mode; - u64 mac; - } data; + u8 mode; + u64 mac:48; }; /* 128 bit shared memory between PF and each VF */ diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c index 6c8dcb65ff03..c90252829ed3 100644 --- a/drivers/net/ethernet/cavium/thunder/nic_main.c +++ b/drivers/net/ethernet/cavium/thunder/nic_main.c @@ -57,14 +57,8 @@ struct nicpf { #define NIC_GET_BGX_FROM_VF_LMAC_MAP(map) ((map >> 4) & 0xF) #define NIC_GET_LMAC_FROM_VF_LMAC_MAP(map) (map & 0xF) u8 *vf_lmac_map; - struct delayed_work dwork; - struct workqueue_struct *check_link; - u8 *link; - u8 *duplex; - u32 *speed; u16 cpi_base[MAX_NUM_VFS_SUPPORTED]; u16 rssi_base[MAX_NUM_VFS_SUPPORTED]; - bool mbx_lock[MAX_NUM_VFS_SUPPORTED]; /* MSI-X */ u8 num_vec; @@ -929,6 +923,35 @@ static void nic_config_timestamp(struct nicpf *nic, int vf, struct set_ptp *ptp) nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3), pkind_val); } +/* Get BGX LMAC link status and update corresponding VF + * if there is a change, valid only if internal L2 switch + * is not present otherwise VF link is always treated as up + */ +static void nic_link_status_get(struct nicpf *nic, u8 vf) +{ + union nic_mbx mbx = {}; + struct bgx_link_status link; + u8 bgx, lmac; + + mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; + + /* Get BGX, LMAC indices for the VF */ + bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); + + /* Get interface link status */ + bgx_get_lmac_link_state(nic->node, bgx, lmac, &link); + + /* Send a mbox message to VF with current link status */ + mbx.link_status.link_up = link.link_up; + mbx.link_status.duplex = link.duplex; + mbx.link_status.speed = link.speed; + mbx.link_status.mac_type = link.mac_type; + + /* reply with link status */ + nic_send_msg_to_vf(nic, vf, &mbx); +} + /* Interrupt handler to handle mailbox messages from VFs */ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) { @@ -941,8 +964,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) int i; int ret = 0; - nic->mbx_lock[vf] = true; - mbx_addr = nic_get_mbx_addr(vf); mbx_data = (u64 *)&mbx; @@ -957,12 +978,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) switch (mbx.msg.msg) { case NIC_MBOX_MSG_READY: nic_mbx_send_ready(nic, vf); - if (vf < nic->num_vf_en) { - nic->link[vf] = 0; - nic->duplex[vf] = 0; - nic->speed[vf] = 0; - } - goto unlock; + return; case NIC_MBOX_MSG_QS_CFG: reg_addr = NIC_PF_QSET_0_127_CFG | (mbx.qs.num << NIC_QS_ID_SHIFT); @@ -1031,7 +1047,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_RSS_SIZE: nic_send_rss_size(nic, vf); - goto unlock; + return; case NIC_MBOX_MSG_RSS_CFG: case NIC_MBOX_MSG_RSS_CFG_CONT: nic_config_rss(nic, &mbx.rss_cfg); @@ -1039,7 +1055,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) case NIC_MBOX_MSG_CFG_DONE: /* Last message of VF config msg sequence */ nic_enable_vf(nic, vf, true); - goto unlock; + break; case NIC_MBOX_MSG_SHUTDOWN: /* First msg in VF teardown sequence */ if (vf >= nic->num_vf_en) @@ -1049,19 +1065,19 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_ALLOC_SQS: nic_alloc_sqs(nic, &mbx.sqs_alloc); - goto unlock; + return; case NIC_MBOX_MSG_NICVF_PTR: nic->nicvf[vf] = mbx.nicvf.nicvf; break; case NIC_MBOX_MSG_PNICVF_PTR: nic_send_pnicvf(nic, vf); - goto unlock; + return; case NIC_MBOX_MSG_SNICVF_PTR: nic_send_snicvf(nic, &mbx.nicvf); - goto unlock; + return; case NIC_MBOX_MSG_BGX_STATS: nic_get_bgx_stats(nic, &mbx.bgx_stats); - goto unlock; + return; case NIC_MBOX_MSG_LOOPBACK: ret = nic_config_loopback(nic, &mbx.lbk); break; @@ -1070,7 +1086,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) break; case NIC_MBOX_MSG_PFC: nic_pause_frame(nic, vf, &mbx.pfc); - goto unlock; + return; case NIC_MBOX_MSG_PTP_CFG: nic_config_timestamp(nic, vf, &mbx.ptp); break; @@ -1094,7 +1110,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); bgx_set_dmac_cam_filter(nic->node, bgx, lmac, - mbx.xcast.data.mac, + mbx.xcast.mac, vf < NIC_VF_PER_MBX_REG ? vf : vf - NIC_VF_PER_MBX_REG); break; @@ -1106,8 +1122,15 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) } bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode); + bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.mode); break; + case NIC_MBOX_MSG_BGX_LINK_CHANGE: + if (vf >= nic->num_vf_en) { + ret = -1; /* NACK */ + break; + } + nic_link_status_get(nic, vf); + return; default: dev_err(&nic->pdev->dev, "Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg); @@ -1121,8 +1144,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf) mbx.msg.msg, vf); nic_mbx_send_nack(nic, vf); } -unlock: - nic->mbx_lock[vf] = false; } static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq) @@ -1270,52 +1291,6 @@ static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic) return 0; } -/* Poll for BGX LMAC link status and update corresponding VF - * if there is a change, valid only if internal L2 switch - * is not present otherwise VF link is always treated as up - */ -static void nic_poll_for_link(struct work_struct *work) -{ - union nic_mbx mbx = {}; - struct nicpf *nic; - struct bgx_link_status link; - u8 vf, bgx, lmac; - - nic = container_of(work, struct nicpf, dwork.work); - - mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; - - for (vf = 0; vf < nic->num_vf_en; vf++) { - /* Poll only if VF is UP */ - if (!nic->vf_enabled[vf]) - continue; - - /* Get BGX, LMAC indices for the VF */ - bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]); - /* Get interface link status */ - bgx_get_lmac_link_state(nic->node, bgx, lmac, &link); - - /* Inform VF only if link status changed */ - if (nic->link[vf] == link.link_up) - continue; - - if (!nic->mbx_lock[vf]) { - nic->link[vf] = link.link_up; - nic->duplex[vf] = link.duplex; - nic->speed[vf] = link.speed; - - /* Send a mbox message to VF with current link status */ - mbx.link_status.link_up = link.link_up; - mbx.link_status.duplex = link.duplex; - mbx.link_status.speed = link.speed; - mbx.link_status.mac_type = link.mac_type; - nic_send_msg_to_vf(nic, vf, &mbx); - } - } - queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2); -} - static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct device *dev = &pdev->dev; @@ -1384,18 +1359,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (!nic->vf_lmac_map) goto err_release_regions; - nic->link = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL); - if (!nic->link) - goto err_release_regions; - - nic->duplex = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL); - if (!nic->duplex) - goto err_release_regions; - - nic->speed = devm_kmalloc_array(dev, max_lmac, sizeof(u32), GFP_KERNEL); - if (!nic->speed) - goto err_release_regions; - /* Initialize hardware */ nic_init_hw(nic); @@ -1411,22 +1374,8 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto err_unregister_interrupts; - /* Register a physical link status poll fn() */ - nic->check_link = alloc_workqueue("check_link_status", - WQ_UNBOUND | WQ_MEM_RECLAIM, 1); - if (!nic->check_link) { - err = -ENOMEM; - goto err_disable_sriov; - } - - INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link); - queue_delayed_work(nic->check_link, &nic->dwork, 0); - return 0; -err_disable_sriov: - if (nic->flags & NIC_SRIOV_ENABLED) - pci_disable_sriov(pdev); err_unregister_interrupts: nic_unregister_interrupts(nic); err_release_regions: @@ -1447,12 +1396,6 @@ static void nic_remove(struct pci_dev *pdev) if (nic->flags & NIC_SRIOV_ENABLED) pci_disable_sriov(pdev); - if (nic->check_link) { - /* Destroy work Queue */ - cancel_delayed_work_sync(&nic->dwork); - destroy_workqueue(nic->check_link); - } - nic_unregister_interrupts(nic); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 88f8a8fa93cd..503cfadff4ac 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -68,9 +68,6 @@ module_param(cpi_alg, int, 0444); MODULE_PARM_DESC(cpi_alg, "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)"); -/* workqueue for handling kernel ndo_set_rx_mode() calls */ -static struct workqueue_struct *nicvf_rx_mode_wq; - static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx) { if (nic->sqs_mode) @@ -127,6 +124,9 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) { int timeout = NIC_MBOX_MSG_TIMEOUT; int sleep = 10; + int ret = 0; + + mutex_lock(&nic->rx_mode_mtx); nic->pf_acked = false; nic->pf_nacked = false; @@ -139,7 +139,8 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) netdev_err(nic->netdev, "PF NACK to mbox msg 0x%02x from VF%d\n", (mbx->msg.msg & 0xFF), nic->vf_id); - return -EINVAL; + ret = -EINVAL; + break; } msleep(sleep); if (nic->pf_acked) @@ -149,10 +150,12 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx) netdev_err(nic->netdev, "PF didn't ACK to mbox msg 0x%02x from VF%d\n", (mbx->msg.msg & 0xFF), nic->vf_id); - return -EBUSY; + ret = -EBUSY; + break; } } - return 0; + mutex_unlock(&nic->rx_mode_mtx); + return ret; } /* Checks if VF is able to comminicate with PF @@ -172,6 +175,17 @@ static int nicvf_check_pf_ready(struct nicvf *nic) return 1; } +static void nicvf_send_cfg_done(struct nicvf *nic) +{ + union nic_mbx mbx = {}; + + mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; + if (nicvf_send_msg_to_pf(nic, &mbx)) { + netdev_err(nic->netdev, + "PF didn't respond to CFG DONE msg\n"); + } +} + static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx) { if (bgx->rx) @@ -228,21 +242,24 @@ static void nicvf_handle_mbx_intr(struct nicvf *nic) break; case NIC_MBOX_MSG_BGX_LINK_CHANGE: nic->pf_acked = true; - nic->link_up = mbx.link_status.link_up; - nic->duplex = mbx.link_status.duplex; - nic->speed = mbx.link_status.speed; - nic->mac_type = mbx.link_status.mac_type; - if (nic->link_up) { - netdev_info(nic->netdev, "Link is Up %d Mbps %s duplex\n", - nic->speed, - nic->duplex == DUPLEX_FULL ? - "Full" : "Half"); - netif_carrier_on(nic->netdev); - netif_tx_start_all_queues(nic->netdev); - } else { - netdev_info(nic->netdev, "Link is Down\n"); - netif_carrier_off(nic->netdev); - netif_tx_stop_all_queues(nic->netdev); + if (nic->link_up != mbx.link_status.link_up) { + nic->link_up = mbx.link_status.link_up; + nic->duplex = mbx.link_status.duplex; + nic->speed = mbx.link_status.speed; + nic->mac_type = mbx.link_status.mac_type; + if (nic->link_up) { + netdev_info(nic->netdev, + "Link is Up %d Mbps %s duplex\n", + nic->speed, + nic->duplex == DUPLEX_FULL ? + "Full" : "Half"); + netif_carrier_on(nic->netdev); + netif_tx_start_all_queues(nic->netdev); + } else { + netdev_info(nic->netdev, "Link is Down\n"); + netif_carrier_off(nic->netdev); + netif_tx_stop_all_queues(nic->netdev); + } } break; case NIC_MBOX_MSG_ALLOC_SQS: @@ -1311,6 +1328,11 @@ int nicvf_stop(struct net_device *netdev) struct nicvf_cq_poll *cq_poll = NULL; union nic_mbx mbx = {}; + cancel_delayed_work_sync(&nic->link_change_work); + + /* wait till all queued set_rx_mode tasks completes */ + drain_workqueue(nic->nicvf_rx_mode_wq); + mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN; nicvf_send_msg_to_pf(nic, &mbx); @@ -1410,13 +1432,27 @@ static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu) return nicvf_send_msg_to_pf(nic, &mbx); } +static void nicvf_link_status_check_task(struct work_struct *work_arg) +{ + struct nicvf *nic = container_of(work_arg, + struct nicvf, + link_change_work.work); + union nic_mbx mbx = {}; + mbx.msg.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE; + nicvf_send_msg_to_pf(nic, &mbx); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 2 * HZ); +} + int nicvf_open(struct net_device *netdev) { int cpu, err, qidx; struct nicvf *nic = netdev_priv(netdev); struct queue_set *qs = nic->qs; struct nicvf_cq_poll *cq_poll = NULL; - union nic_mbx mbx = {}; + + /* wait till all queued set_rx_mode tasks completes if any */ + drain_workqueue(nic->nicvf_rx_mode_wq); netif_carrier_off(netdev); @@ -1512,8 +1548,12 @@ int nicvf_open(struct net_device *netdev) nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx); /* Send VF config done msg to PF */ - mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE; - nicvf_write_to_mbx(nic, &mbx); + nicvf_send_cfg_done(nic); + + INIT_DELAYED_WORK(&nic->link_change_work, + nicvf_link_status_check_task); + queue_delayed_work(nic->nicvf_rx_mode_wq, + &nic->link_change_work, 0); return 0; cleanup: @@ -1941,15 +1981,17 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs, /* flush DMAC filters and reset RX mode */ mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST; - nicvf_send_msg_to_pf(nic, &mbx); + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; if (mode & BGX_XCAST_MCAST_FILTER) { /* once enabling filtering, we need to signal to PF to add * its' own LMAC to the filter to accept packets for it. */ mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; - mbx.xcast.data.mac = 0; - nicvf_send_msg_to_pf(nic, &mbx); + mbx.xcast.mac = 0; + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; } /* check if we have any specific MACs to be added to PF DMAC filter */ @@ -1957,23 +1999,25 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs, /* now go through kernel list of MACs and add them one by one */ for (idx = 0; idx < mc_addrs->count; idx++) { mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST; - mbx.xcast.data.mac = mc_addrs->mc[idx]; - nicvf_send_msg_to_pf(nic, &mbx); + mbx.xcast.mac = mc_addrs->mc[idx]; + if (nicvf_send_msg_to_pf(nic, &mbx) < 0) + goto free_mc; } - kfree(mc_addrs); } /* and finally set rx mode for PF accordingly */ mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST; - mbx.xcast.data.mode = mode; + mbx.xcast.mode = mode; nicvf_send_msg_to_pf(nic, &mbx); +free_mc: + kfree(mc_addrs); } static void nicvf_set_rx_mode_task(struct work_struct *work_arg) { struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work, - work.work); + work); struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work); u8 mode; struct xcast_addr_list *mc; @@ -2030,7 +2074,7 @@ static void nicvf_set_rx_mode(struct net_device *netdev) kfree(nic->rx_mode_work.mc); nic->rx_mode_work.mc = mc_list; nic->rx_mode_work.mode = mode; - queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0); + queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work); spin_unlock(&nic->rx_mode_wq_lock); } @@ -2187,8 +2231,12 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&nic->reset_task, nicvf_reset_task); - INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); + nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d", + WQ_MEM_RECLAIM, + nic->vf_id); + INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task); spin_lock_init(&nic->rx_mode_wq_lock); + mutex_init(&nic->rx_mode_mtx); err = register_netdev(netdev); if (err) { @@ -2228,13 +2276,15 @@ static void nicvf_remove(struct pci_dev *pdev) nic = netdev_priv(netdev); pnetdev = nic->pnicvf->netdev; - cancel_delayed_work_sync(&nic->rx_mode_work.work); - /* Check if this Qset is assigned to different VF. * If yes, clean primary and all secondary Qsets. */ if (pnetdev && (pnetdev->reg_state == NETREG_REGISTERED)) unregister_netdev(pnetdev); + if (nic->nicvf_rx_mode_wq) { + destroy_workqueue(nic->nicvf_rx_mode_wq); + nic->nicvf_rx_mode_wq = NULL; + } nicvf_unregister_interrupts(nic); pci_set_drvdata(pdev, NULL); if (nic->drv_stats) @@ -2261,17 +2311,11 @@ static struct pci_driver nicvf_driver = { static int __init nicvf_init_module(void) { pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION); - nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic", - WQ_MEM_RECLAIM); return pci_register_driver(&nicvf_driver); } static void __exit nicvf_cleanup_module(void) { - if (nicvf_rx_mode_wq) { - destroy_workqueue(nicvf_rx_mode_wq); - nicvf_rx_mode_wq = NULL; - } pci_unregister_driver(&nicvf_driver); } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index e337da6ba2a4..673c57b8023f 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1217,7 +1217,7 @@ static void bgx_init_hw(struct bgx *bgx) /* Disable MAC steering (NCSI traffic) */ for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++) - bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00); + bgx_reg_write(bgx, 0, BGX_CMR_RX_STEERING + (i * 8), 0x00); } static u8 bgx_get_lane2sds_cfg(struct bgx *bgx, struct lmac *lmac) diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index cbdd20b9ee6f..5cbc54e9eb19 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -60,7 +60,7 @@ #define RX_DMACX_CAM_EN BIT_ULL(48) #define RX_DMACX_CAM_LMACID(x) (((u64)x) << 49) #define RX_DMAC_COUNT 32 -#define BGX_CMR_RX_STREERING 0x300 +#define BGX_CMR_RX_STEERING 0x300 #define RX_TRAFFIC_STEER_RULE_COUNT 8 #define BGX_CMR_CHAN_MSK_AND 0x450 #define BGX_CMR_BIST_STATUS 0x460 diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c index c041f44324db..b3654598a2d5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c @@ -660,6 +660,7 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld) lld->cclk_ps = 1000000000 / adap->params.vpd.cclk; lld->udb_density = 1 << adap->params.sge.eq_qpp; lld->ucq_density = 1 << adap->params.sge.iq_qpp; + lld->sge_host_page_size = 1 << (adap->params.sge.hps + 10); lld->filt_mode = adap->params.tp.vlan_pri_map; /* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */ for (i = 0; i < NCHAN; i++) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h index 5fa9a2d5fc4b..21da34a4ca24 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h @@ -336,6 +336,7 @@ struct cxgb4_lld_info { unsigned int cclk_ps; /* Core clock period in psec */ unsigned short udb_density; /* # of user DB/page */ unsigned short ucq_density; /* # of user CQs/page */ + unsigned int sge_host_page_size; /* SGE host page size */ unsigned short filt_mode; /* filter optional components */ unsigned short tx_modq[NCHAN]; /* maps each tx channel to a */ /* scheduler queue */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index b8155f5e71b4..ac55db065f16 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -3128,6 +3128,9 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1); dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit); } + + put_device(&pdev->dev); + return 0; } EXPORT_SYMBOL(hns_dsaf_roce_reset); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f52e2c46e6a7..e4ff531db14a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3289,8 +3289,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) : !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); if (!ok) { + /* Log this in case the user has forgotten to give the kernel + * any buffers, even later in the application. + */ dev_info(&vsi->back->pdev->dev, - "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", + "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n", ring->xsk_umem ? "UMEM enabled " : "", ring->queue_index, pf_q); } @@ -6725,8 +6728,13 @@ void i40e_down(struct i40e_vsi *vsi) for (i = 0; i < vsi->num_queue_pairs; i++) { i40e_clean_tx_ring(vsi->tx_rings[i]); - if (i40e_enabled_xdp_vsi(vsi)) + if (i40e_enabled_xdp_vsi(vsi)) { + /* Make sure that in-progress ndo_xdp_xmit + * calls are completed. + */ + synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[i]); + } i40e_clean_rx_ring(vsi->rx_rings[i]); } @@ -11895,6 +11903,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, if (old_prog) bpf_prog_put(old_prog); + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) + for (i = 0; i < vsi->num_queue_pairs; i++) + if (vsi->xdp_rings[i]->xsk_umem) + (void)i40e_xsk_async_xmit(vsi->netdev, i); + return 0; } @@ -11955,8 +11971,13 @@ static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair) static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair) { i40e_clean_tx_ring(vsi->tx_rings[queue_pair]); - if (i40e_enabled_xdp_vsi(vsi)) + if (i40e_enabled_xdp_vsi(vsi)) { + /* Make sure that in-progress ndo_xdp_xmit calls are + * completed. + */ + synchronize_rcu(); i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]); + } i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index a7e14e98889f..6c97667d20ef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3709,6 +3709,7 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, struct i40e_netdev_priv *np = netdev_priv(dev); unsigned int queue_index = smp_processor_id(); struct i40e_vsi *vsi = np->vsi; + struct i40e_pf *pf = vsi->back; struct i40e_ring *xdp_ring; int drops = 0; int i; @@ -3716,7 +3717,8 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, if (test_bit(__I40E_VSI_DOWN, vsi->state)) return -ENETDOWN; - if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs) + if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs || + test_bit(__I40E_CONFIG_BUSY, pf->state)) return -ENXIO; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 870cf654e436..3827f16e6923 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -183,6 +183,11 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, err = i40e_queue_pair_enable(vsi, qid); if (err) return err; + + /* Kick start the NAPI context so that receiving will start */ + err = i40e_xsk_async_xmit(vsi->netdev, qid); + if (err) + return err; } return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index daff8183534b..cb35d8202572 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3953,8 +3953,11 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) else mrqc = IXGBE_MRQC_VMDQRSS64EN; - /* Enable L3/L4 for Tx Switched packets */ - mrqc |= IXGBE_MRQC_L3L4TXSWEN; + /* Enable L3/L4 for Tx Switched packets only for X550, + * older devices do not support this feature + */ + if (hw->mac.type >= ixgbe_mac_X550) + mrqc |= IXGBE_MRQC_L3L4TXSWEN; } else { if (tcs > 4) mrqc = IXGBE_MRQC_RTRSS8TCEN; @@ -10225,6 +10228,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; struct ixgbe_adapter *adapter = netdev_priv(dev); struct bpf_prog *old_prog; + bool need_reset; if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) return -EINVAL; @@ -10247,9 +10251,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) return -ENOMEM; old_prog = xchg(&adapter->xdp_prog, prog); + need_reset = (!!prog != !!old_prog); /* If transitioning XDP modes reconfigure rings */ - if (!!prog != !!old_prog) { + if (need_reset) { int err = ixgbe_setup_tc(dev, adapter->hw_tcs); if (err) { @@ -10265,6 +10270,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) if (old_prog) bpf_prog_put(old_prog); + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->xdp_ring[i]->xsk_umem) + (void)ixgbe_xsk_async_xmit(adapter->netdev, i); + return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 65c3e2c979d4..36a8879536a4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -144,11 +144,19 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, ixgbe_txrx_ring_disable(adapter, qid); err = ixgbe_add_xsk_umem(adapter, umem, qid); + if (err) + return err; - if (if_running) + if (if_running) { ixgbe_txrx_ring_enable(adapter, qid); - return err; + /* Kick start the NAPI context so that receiving will start */ + err = ixgbe_xsk_async_xmit(adapter->netdev, qid); + if (err) + return err; + } + + return 0; } static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) @@ -634,7 +642,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) dma_addr_t dma; while (budget-- > 0) { - if (unlikely(!ixgbe_desc_unused(xdp_ring))) { + if (unlikely(!ixgbe_desc_unused(xdp_ring)) || + !netif_carrier_ok(xdp_ring->netdev)) { work_done = false; break; } diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 2f427271a793..292a668ce88e 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2879,7 +2879,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) ret = mv643xx_eth_shared_of_probe(pdev); if (ret) - return ret; + goto err_put_clk; pd = dev_get_platdata(&pdev->dev); msp->tx_csum_limit = (pd != NULL && pd->tx_csum_limit) ? @@ -2887,6 +2887,11 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev) infer_hw_params(msp); return 0; + +err_put_clk: + if (!IS_ERR(msp->clk)) + clk_disable_unprepare(msp->clk); + return ret; } static int mv643xx_eth_shared_remove(struct platform_device *pdev) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 9d4568eb2297..8433fb9c3eee 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2146,7 +2146,7 @@ err_drop_frame: if (unlikely(!skb)) goto err_drop_frame_ret_pool; - dma_sync_single_range_for_cpu(dev->dev.parent, + dma_sync_single_range_for_cpu(&pp->bm_priv->pdev->dev, rx_desc->buf_phys_addr, MVNETA_MH_SIZE + NET_SKB_PAD, rx_bytes, diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index f3a5fa84860f..57727fe1501e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5073,7 +5073,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&hw->restart_work, sky2_restart); pci_set_drvdata(pdev, hw); - pdev->d3_delay = 200; + pdev->d3_delay = 300; return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 6b88881b8e35..c1438ae52a11 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3360,7 +3360,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, dev->addr_len = ETH_ALEN; mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]); if (!is_valid_ether_addr(dev->dev_addr)) { - en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n", + en_err(priv, "Port: %d, invalid mac burned: %pM, quitting\n", priv->port, dev->dev_addr); err = -EINVAL; goto out; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 32519c93df17..b65e274b02e9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -862,8 +862,9 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { bool configure = false; bool pfc = false; + u16 thres_cells; + u16 delay_cells; bool lossy; - u16 thres; for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) { if (prio_tc[j] == i) { @@ -877,10 +878,11 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, continue; lossy = !(pfc || pause_en); - thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); - delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc, - pause_en); - mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy); + thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu); + delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, + pfc, pause_en); + mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres_cells + delay_cells, + thres_cells, lossy); } return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl); diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c index f6ecfa778660..8f72587b5a2c 100644 --- a/drivers/net/ethernet/microchip/enc28j60.c +++ b/drivers/net/ethernet/microchip/enc28j60.c @@ -1681,5 +1681,5 @@ MODULE_DESCRIPTION(DRV_NAME " ethernet driver"); MODULE_AUTHOR("Claudio Lanconelli <lanconelli.claudio@eptar.com>"); MODULE_LICENSE("GPL"); module_param_named(debug, debug.msg_enable, int, 0); -MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., ffff=all)"); +MODULE_PARM_DESC(debug, "Debug verbosity level in amount of bits set (0=none, ..., 31=all)"); MODULE_ALIAS("spi:" DRV_NAME); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 310807ef328b..4d1b4a24907f 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1400,7 +1400,8 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx, } static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx, - unsigned int frame_length) + unsigned int frame_length, + int nr_frags) { /* called only from within lan743x_tx_xmit_frame. * assuming tx->ring_lock has already been acquired. @@ -1410,6 +1411,10 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx, /* wrap up previous descriptor */ tx->frame_data0 |= TX_DESC_DATA0_EXT_; + if (nr_frags <= 0) { + tx->frame_data0 |= TX_DESC_DATA0_LS_; + tx->frame_data0 |= TX_DESC_DATA0_IOC_; + } tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail]; tx_descriptor->data0 = tx->frame_data0; @@ -1514,8 +1519,11 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx, u32 tx_tail_flags = 0; /* wrap up previous descriptor */ - tx->frame_data0 |= TX_DESC_DATA0_LS_; - tx->frame_data0 |= TX_DESC_DATA0_IOC_; + if ((tx->frame_data0 & TX_DESC_DATA0_DTYPE_MASK_) == + TX_DESC_DATA0_DTYPE_DATA_) { + tx->frame_data0 |= TX_DESC_DATA0_LS_; + tx->frame_data0 |= TX_DESC_DATA0_IOC_; + } tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail]; buffer_info = &tx->buffer_info[tx->frame_tail]; @@ -1600,7 +1608,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, } if (gso) - lan743x_tx_frame_add_lso(tx, frame_length); + lan743x_tx_frame_add_lso(tx, frame_length, nr_frags); if (nr_frags <= 0) goto finish; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index e23ca90289f7..0a868c829b90 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1291,15 +1291,10 @@ wrp_alu64_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, static int wrp_alu32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, - enum alu_op alu_op, bool skip) + enum alu_op alu_op) { const struct bpf_insn *insn = &meta->insn; - if (skip) { - meta->skip = true; - return 0; - } - wrp_alu_imm(nfp_prog, insn->dst_reg * 2, alu_op, insn->imm); wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0); @@ -2309,7 +2304,7 @@ static int xor_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int xor_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !~meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR); } static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2319,7 +2314,7 @@ static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int and_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND, !~meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND); } static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2329,7 +2324,7 @@ static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int or_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR, !meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR); } static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2339,7 +2334,7 @@ static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int add_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD, !meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD); } static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) @@ -2349,7 +2344,7 @@ static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm); + return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB); } static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index beb8e5d6401a..ded556b7bab5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -1688,6 +1688,15 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn, eth_hlen = ETH_HLEN + (vlan_valid ? sizeof(u32) : 0); + if (!ether_addr_equal(ethh->h_dest, + p_hwfn->p_rdma_info->iwarp.mac_addr)) { + DP_VERBOSE(p_hwfn, + QED_MSG_RDMA, + "Got unexpected mac %pM instead of %pM\n", + ethh->h_dest, p_hwfn->p_rdma_info->iwarp.mac_addr); + return -EINVAL; + } + ether_addr_copy(remote_mac_addr, ethh->h_source); ether_addr_copy(local_mac_addr, ethh->h_dest); @@ -2605,7 +2614,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, struct qed_iwarp_info *iwarp_info; struct qed_ll2_acquire_data data; struct qed_ll2_cbs cbs; - u32 mpa_buff_size; + u32 buff_size; u16 n_ooo_bufs; int rc = 0; int i; @@ -2632,7 +2641,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, memset(&data, 0, sizeof(data)); data.input.conn_type = QED_LL2_TYPE_IWARP; - data.input.mtu = QED_IWARP_MAX_SYN_PKT_SIZE; + data.input.mtu = params->max_mtu; data.input.rx_num_desc = QED_IWARP_LL2_SYN_RX_SIZE; data.input.tx_num_desc = QED_IWARP_LL2_SYN_TX_SIZE; data.input.tx_max_bds_per_packet = 1; /* will never be fragmented */ @@ -2654,9 +2663,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, goto err; } + buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, QED_IWARP_LL2_SYN_RX_SIZE, - QED_IWARP_MAX_SYN_PKT_SIZE, + buff_size, iwarp_info->ll2_syn_handle); if (rc) goto err; @@ -2710,10 +2720,9 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, if (rc) goto err; - mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu); rc = qed_iwarp_ll2_alloc_buffers(p_hwfn, data.input.rx_num_desc, - mpa_buff_size, + buff_size, iwarp_info->ll2_mpa_handle); if (rc) goto err; @@ -2726,7 +2735,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn, iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps; - iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL); + iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL); if (!iwarp_info->mpa_intermediate_buf) goto err; diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h index b8f612d00241..7ac959038324 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h @@ -46,7 +46,6 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state); #define QED_IWARP_LL2_SYN_TX_SIZE (128) #define QED_IWARP_LL2_SYN_RX_SIZE (256) -#define QED_IWARP_MAX_SYN_PKT_SIZE (128) #define QED_IWARP_LL2_OOO_DEF_TX_SIZE (256) #define QED_IWARP_MAX_OOO (16) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 20299f6f65fc..736e29635b77 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -241,15 +241,18 @@ static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts) static int dwmac4_rx_check_timestamp(void *desc) { struct dma_desc *p = (struct dma_desc *)desc; + unsigned int rdes0 = le32_to_cpu(p->des0); + unsigned int rdes1 = le32_to_cpu(p->des1); + unsigned int rdes3 = le32_to_cpu(p->des3); u32 own, ctxt; int ret = 1; - own = p->des3 & RDES3_OWN; - ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR) + own = rdes3 & RDES3_OWN; + ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR) >> RDES3_CONTEXT_DESCRIPTOR_SHIFT); if (likely(!own && ctxt)) { - if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff)) /* Corrupted value */ ret = -EINVAL; else diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 5d85742a2be0..3c749c327cbd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -696,25 +696,27 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct ethtool_eee *edata) { struct stmmac_priv *priv = netdev_priv(dev); + int ret; - priv->eee_enabled = edata->eee_enabled; - - if (!priv->eee_enabled) + if (!edata->eee_enabled) { stmmac_disable_eee_mode(priv); - else { + } else { /* We are asking for enabling the EEE but it is safe * to verify all by invoking the eee_init function. * In case of failure it will return an error. */ - priv->eee_enabled = stmmac_eee_init(priv); - if (!priv->eee_enabled) + edata->eee_enabled = stmmac_eee_init(priv); + if (!edata->eee_enabled) return -EOPNOTSUPP; - - /* Do not change tx_lpi_timer in case of failure */ - priv->tx_lpi_timer = edata->tx_lpi_timer; } - return phy_ethtool_set_eee(dev->phydev, edata); + ret = phy_ethtool_set_eee(dev->phydev, edata); + if (ret) + return ret; + + priv->eee_enabled = edata->eee_enabled; + priv->tx_lpi_timer = edata->tx_lpi_timer; + return 0; } static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 1f612268c998..d847f672a705 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -259,7 +259,7 @@ static int netcp_module_probe(struct netcp_device *netcp_device, const char *name; char node_name[32]; - if (of_property_read_string(node, "label", &name) < 0) { + if (of_property_read_string(child, "label", &name) < 0) { snprintf(node_name, sizeof(node_name), "%pOFn", child); name = node_name; } diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 3377ac66a347..5583d993480d 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -692,15 +692,20 @@ out: static int geneve_open(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); - bool ipv6 = !!(geneve->info.mode & IP_TUNNEL_INFO_IPV6); bool metadata = geneve->collect_md; + bool ipv4, ipv6; int ret = 0; + ipv6 = geneve->info.mode & IP_TUNNEL_INFO_IPV6 || metadata; + ipv4 = !ipv6 || metadata; #if IS_ENABLED(CONFIG_IPV6) - if (ipv6 || metadata) + if (ipv6) { ret = geneve_sock_add(geneve, true); + if (ret < 0 && ret != -EAFNOSUPPORT) + ipv4 = false; + } #endif - if (!ret && (!ipv6 || metadata)) + if (ipv4) ret = geneve_sock_add(geneve, false); if (ret < 0) geneve_sock_release(geneve); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 256adbd044f5..cf4897043e83 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -744,6 +744,14 @@ void netvsc_linkstatus_callback(struct net_device *net, schedule_delayed_work(&ndev_ctx->dwork, 0); } +static void netvsc_comp_ipcsum(struct sk_buff *skb) +{ + struct iphdr *iph = (struct iphdr *)skb->data; + + iph->check = 0; + iph->check = ip_fast_csum(iph, iph->ihl); +} + static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, struct netvsc_channel *nvchan) { @@ -770,9 +778,17 @@ static struct sk_buff *netvsc_alloc_recv_skb(struct net_device *net, /* skb is already created with CHECKSUM_NONE */ skb_checksum_none_assert(skb); - /* - * In Linux, the IP checksum is always checked. - * Do L4 checksum offload if enabled and present. + /* Incoming packets may have IP header checksum verified by the host. + * They may not have IP header checksum computed after coalescing. + * We compute it here if the flags are set, because on Linux, the IP + * checksum is always checked. + */ + if (csum_info && csum_info->receive.ip_checksum_value_invalid && + csum_info->receive.ip_checksum_succeeded && + skb->protocol == htons(ETH_P_IP)) + netvsc_comp_ipcsum(skb); + + /* Do L4 checksum offload if enabled and present. */ if (csum_info && (net->features & NETIF_F_RXCSUM)) { if (csum_info->receive.tcp_checksum_succeeded || diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 7cdac77d0c68..07e41c42bcf5 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -499,6 +499,8 @@ static int ipvlan_nl_changelink(struct net_device *dev, if (!data) return 0; + if (!ns_capable(dev_net(ipvlan->phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; if (data[IFLA_IPVLAN_MODE]) { u16 nmode = nla_get_u16(data[IFLA_IPVLAN_MODE]); @@ -601,6 +603,8 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, struct ipvl_dev *tmp = netdev_priv(phy_dev); phy_dev = tmp->phy_dev; + if (!ns_capable(dev_net(phy_dev)->user_ns, CAP_NET_ADMIN)) + return -EPERM; } else if (!netif_is_ipvlan_port(phy_dev)) { /* Exit early if the underlying link is invalid or busy */ if (phy_dev->type != ARPHRD_ETHER || diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index da6a67d47ce9..56fa3606cb9c 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -19,6 +19,7 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/phy.h> +#include <linux/delay.h> #include <dt-bindings/net/ti-dp83867.h> @@ -325,6 +326,8 @@ static int dp83867_phy_reset(struct phy_device *phydev) if (err < 0) return err; + usleep_range(10, 20); + return dp83867_config_init(phydev); } diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 82ab6ed3b74e..6bac602094bd 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -26,6 +26,8 @@ #include <linux/marvell_phy.h> #include <linux/phy.h> +#define MDIO_AN_10GBT_CTRL_ADV_NBT_MASK 0x01e0 + enum { MV_PCS_BASE_T = 0x0000, MV_PCS_BASE_R = 0x1000, @@ -386,8 +388,10 @@ static int mv3310_config_aneg(struct phy_device *phydev) else reg = 0; + /* Make sure we clear unsupported 2.5G/5G advertising */ ret = mv3310_modify(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, - MDIO_AN_10GBT_CTRL_ADV10G, reg); + MDIO_AN_10GBT_CTRL_ADV10G | + MDIO_AN_10GBT_CTRL_ADV_NBT_MASK, reg); if (ret < 0) return ret; if (ret > 0) diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 66b9cfe692fc..7368616286ae 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -379,7 +379,6 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) err = device_register(&bus->dev); if (err) { pr_err("mii_bus %s failed to register\n", bus->id); - put_device(&bus->dev); return -EINVAL; } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index b1f959935f50..b7df0295a3ca 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -344,6 +344,17 @@ static int ksz8041_config_aneg(struct phy_device *phydev) return genphy_config_aneg(phydev); } +static int ksz8061_config_init(struct phy_device *phydev) +{ + int ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_DEVID1, 0xB61A); + if (ret) + return ret; + + return kszphy_config_init(phydev); +} + static int ksz9021_load_values_from_of(struct phy_device *phydev, const struct device_node *of_node, u16 reg, @@ -1040,7 +1051,7 @@ static struct phy_driver ksphy_driver[] = { .name = "Micrel KSZ8061", .phy_id_mask = MICREL_PHY_ID_MASK, .features = PHY_BASIC_FEATURES, - .config_init = kszphy_config_init, + .config_init = ksz8061_config_init, .ack_interrupt = kszphy_ack_interrupt, .config_intr = kszphy_config_intr, .suspend = genphy_suspend, diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 938803237d7f..85987aac31c4 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -320,6 +320,10 @@ static int phylink_get_mac_state(struct phylink *pl, struct phylink_link_state * linkmode_zero(state->lp_advertising); state->interface = pl->link_config.interface; state->an_enabled = pl->link_config.an_enabled; + state->speed = SPEED_UNKNOWN; + state->duplex = DUPLEX_UNKNOWN; + state->pause = MLO_PAUSE_NONE; + state->an_complete = 0; state->link = 1; return pl->ops->mac_link_state(ndev, state); diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index c6010fb1aa0f..cb4a23041a94 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -282,6 +282,13 @@ static struct phy_driver realtek_drvs[] = { .name = "RTL8366RB Gigabit Ethernet", .features = PHY_GBIT_FEATURES, .config_init = &rtl8366rb_config_init, + /* These interrupts are handled by the irq controller + * embedded inside the RTL8366RB, they get unmasked when the + * irq is requested and ACKed by reading the status register, + * which is done by the irqchip code. + */ + .ack_interrupt = genphy_no_ack_interrupt, + .config_intr = genphy_no_config_intr, .suspend = genphy_suspend, .resume = genphy_resume, }, diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c index 74a8782313cf..bd6084e315de 100644 --- a/drivers/net/phy/xilinx_gmii2rgmii.c +++ b/drivers/net/phy/xilinx_gmii2rgmii.c @@ -44,7 +44,10 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev) u16 val = 0; int err; - err = priv->phy_drv->read_status(phydev); + if (priv->phy_drv->read_status) + err = priv->phy_drv->read_status(phydev); + else + err = genphy_read_status(phydev); if (err < 0) return err; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 958f1cf67282..6ce3f666d142 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1256,7 +1256,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev, list_add_tail_rcu(&port->list, &team->port_list); team_port_enable(team, port); __team_compute_features(team); - __team_port_change_port_added(port, !!netif_carrier_ok(port_dev)); + __team_port_change_port_added(port, !!netif_oper_up(port_dev)); __team_options_change_check(team); netdev_info(dev, "Port device %s added\n", portname); @@ -2915,7 +2915,7 @@ static int team_device_event(struct notifier_block *unused, switch (event) { case NETDEV_UP: - if (netif_carrier_ok(dev)) + if (netif_oper_up(dev)) team_port_change_check(port, true); break; case NETDEV_DOWN: diff --git a/drivers/net/tun.c b/drivers/net/tun.c index fed298c0cb39..53f4f37b0ffd 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -2167,9 +2167,9 @@ static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) } add_wait_queue(&tfile->wq.wait, &wait); - current->state = TASK_INTERRUPTIBLE; while (1) { + set_current_state(TASK_INTERRUPTIBLE); ptr = ptr_ring_consume(&tfile->tx_ring); if (ptr) break; @@ -2185,7 +2185,7 @@ static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err) schedule(); } - current->state = TASK_RUNNING; + __set_current_state(TASK_RUNNING); remove_wait_queue(&tfile->wq.wait, &wait); out: diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 735ad838e2ba..18af2f8eee96 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1201,8 +1201,8 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x114f, 0x68a2, 8)}, /* Sierra Wireless MC7750 */ {QMI_FIXED_INTF(0x1199, 0x68a2, 8)}, /* Sierra Wireless MC7710 in QMI mode */ {QMI_FIXED_INTF(0x1199, 0x68a2, 19)}, /* Sierra Wireless MC7710 in QMI mode */ - {QMI_FIXED_INTF(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC7304/MC7354 */ - {QMI_FIXED_INTF(0x1199, 0x68c0, 10)}, /* Sierra Wireless MC7304/MC7354 */ + {QMI_QUIRK_SET_DTR(0x1199, 0x68c0, 8)}, /* Sierra Wireless MC7304/MC7354, WP76xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x68c0, 10)},/* Sierra Wireless MC7304/MC7354 */ {QMI_FIXED_INTF(0x1199, 0x901c, 8)}, /* Sierra Wireless EM7700 */ {QMI_FIXED_INTF(0x1199, 0x901f, 8)}, /* Sierra Wireless EM7355 */ {QMI_FIXED_INTF(0x1199, 0x9041, 8)}, /* Sierra Wireless MC7305/MC7355 */ diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 60dd1ec1665f..86c8c64fbb0f 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -557,6 +557,7 @@ enum spd_duplex { /* MAC PASSTHRU */ #define AD_MASK 0xfee0 #define BND_MASK 0x0004 +#define BD_MASK 0x0001 #define EFUSE 0xcfdb #define PASS_THRU_MASK 0x1 @@ -1176,9 +1177,9 @@ static int vendor_mac_passthru_addr_read(struct r8152 *tp, struct sockaddr *sa) return -ENODEV; } } else { - /* test for RTL8153-BND */ + /* test for RTL8153-BND and RTL8153-BD */ ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_MISC_1); - if ((ocp_data & BND_MASK) == 0) { + if ((ocp_data & BND_MASK) == 0 && (ocp_data & BD_MASK) == 0) { netif_dbg(tp, probe, tp->netdev, "Invalid variant for MAC pass through\n"); return -ENODEV; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 95909e262ba4..7c1430ed0244 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -1273,6 +1273,9 @@ static void vrf_setup(struct net_device *dev) /* default to no qdisc; user can add if desired */ dev->priv_flags |= IFF_NO_QUEUE; + + dev->min_mtu = 0; + dev->max_mtu = 0; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 320edcac4699..6359053bd0c7 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3554,7 +3554,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info) goto out_err; } - genlmsg_reply(skb, info); + res = genlmsg_reply(skb, info); break; } diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c index 0e6b43bb4678..a5ea3ba495a4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c @@ -158,39 +158,49 @@ static const struct ieee80211_ops mt76x0u_ops = { .get_txpower = mt76x02_get_txpower, }; -static int mt76x0u_register_device(struct mt76x02_dev *dev) +static int mt76x0u_init_hardware(struct mt76x02_dev *dev) { - struct ieee80211_hw *hw = dev->mt76.hw; int err; - err = mt76u_alloc_queues(&dev->mt76); - if (err < 0) - goto out_err; - - err = mt76u_mcu_init_rx(&dev->mt76); - if (err < 0) - goto out_err; - mt76x0_chip_onoff(dev, true, true); - if (!mt76x02_wait_for_mac(&dev->mt76)) { - err = -ETIMEDOUT; - goto out_err; - } + + if (!mt76x02_wait_for_mac(&dev->mt76)) + return -ETIMEDOUT; err = mt76x0u_mcu_init(dev); if (err < 0) - goto out_err; + return err; mt76x0_init_usb_dma(dev); err = mt76x0_init_hardware(dev); if (err < 0) - goto out_err; + return err; mt76_rmw(dev, MT_US_CYC_CFG, MT_US_CYC_CNT, 0x1e); mt76_wr(dev, MT_TXOP_CTRL_CFG, FIELD_PREP(MT_TXOP_TRUN_EN, 0x3f) | FIELD_PREP(MT_TXOP_EXT_CCA_DLY, 0x58)); + return 0; +} + +static int mt76x0u_register_device(struct mt76x02_dev *dev) +{ + struct ieee80211_hw *hw = dev->mt76.hw; + int err; + + err = mt76u_alloc_queues(&dev->mt76); + if (err < 0) + goto out_err; + + err = mt76u_mcu_init_rx(&dev->mt76); + if (err < 0) + goto out_err; + + err = mt76x0u_init_hardware(dev); + if (err < 0) + goto out_err; + err = mt76x0_register_device(dev); if (err < 0) goto out_err; @@ -301,6 +311,8 @@ static int __maybe_unused mt76x0_suspend(struct usb_interface *usb_intf, mt76u_stop_queues(&dev->mt76); mt76x0u_mac_stop(dev); + clear_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state); + mt76x0_chip_onoff(dev, false, false); usb_kill_urb(usb->mcu.res.urb); return 0; @@ -328,7 +340,7 @@ static int __maybe_unused mt76x0_resume(struct usb_interface *usb_intf) tasklet_enable(&usb->rx_tasklet); tasklet_enable(&usb->tx_tasklet); - ret = mt76x0_init_hardware(dev); + ret = mt76x0u_init_hardware(dev); if (ret) goto err; diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c index 0ccb021f1e78..10d580c3dea3 100644 --- a/drivers/net/xen-netback/hash.c +++ b/drivers/net/xen-netback/hash.c @@ -454,6 +454,8 @@ void xenvif_init_hash(struct xenvif *vif) if (xenvif_hash_cache_size == 0) return; + BUG_ON(vif->hash.cache.count); + spin_lock_init(&vif->hash.cache.lock); INIT_LIST_HEAD(&vif->hash.cache.list); } diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 182d6770f102..6da12518e693 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -153,6 +153,13 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb, { struct xenvif *vif = netdev_priv(dev); unsigned int size = vif->hash.size; + unsigned int num_queues; + + /* If queues are not set up internally - always return 0 + * as the packet going to be dropped anyway */ + num_queues = READ_ONCE(vif->num_queues); + if (num_queues < 1) + return 0; if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) return fallback(dev, skb, NULL) % dev->real_num_tx_queues; diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 80aae3a32c2a..f09948b009dd 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1072,11 +1072,6 @@ static int xenvif_handle_frag_list(struct xenvif_queue *queue, struct sk_buff *s skb_frag_size_set(&frags[i], len); } - /* Copied all the bits from the frag list -- free it. */ - skb_frag_list_init(skb); - xenvif_skb_zerocopy_prepare(queue, nskb); - kfree_skb(nskb); - /* Release all the original (foreign) frags. */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) skb_frag_unref(skb, f); @@ -1145,6 +1140,8 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) xenvif_fill_frags(queue, skb); if (unlikely(skb_has_frag_list(skb))) { + struct sk_buff *nskb = skb_shinfo(skb)->frag_list; + xenvif_skb_zerocopy_prepare(queue, nskb); if (xenvif_handle_frag_list(queue, skb)) { if (net_ratelimit()) netdev_err(queue->vif->dev, @@ -1153,6 +1150,9 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) kfree_skb(skb); continue; } + /* Copied all the bits from the frag list -- free it. */ + skb_frag_list_init(skb); + kfree_skb(nskb); } skb->dev = queue->vif->dev; diff --git a/drivers/pinctrl/meson/pinctrl-meson8b.c b/drivers/pinctrl/meson/pinctrl-meson8b.c index c69ca95b1ad5..0f140a802137 100644 --- a/drivers/pinctrl/meson/pinctrl-meson8b.c +++ b/drivers/pinctrl/meson/pinctrl-meson8b.c @@ -693,7 +693,7 @@ static const char * const sd_a_groups[] = { static const char * const sdxc_a_groups[] = { "sdxc_d0_0_a", "sdxc_d13_0_a", "sdxc_d47_a", "sdxc_clk_a", - "sdxc_cmd_a", "sdxc_d0_1_a", "sdxc_d0_13_1_a" + "sdxc_cmd_a", "sdxc_d0_1_a", "sdxc_d13_1_a" }; static const char * const pcm_a_groups[] = { diff --git a/drivers/pinctrl/qcom/pinctrl-qcs404.c b/drivers/pinctrl/qcom/pinctrl-qcs404.c index 7aae52a09ff0..4ffd56ff809e 100644 --- a/drivers/pinctrl/qcom/pinctrl-qcs404.c +++ b/drivers/pinctrl/qcom/pinctrl-qcs404.c @@ -79,7 +79,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ - .tile = NORTH, \ + .tile = SOUTH, \ .mux_bit = -1, \ .pull_bit = pull, \ .drv_bit = drv, \ diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c index a3c20e3a8b7c..3337b1e80412 100644 --- a/drivers/scsi/3w-9xxx.c +++ b/drivers/scsi/3w-9xxx.c @@ -2009,7 +2009,7 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) struct Scsi_Host *host = NULL; TW_Device_Extension *tw_dev; unsigned long mem_addr, mem_len; - int retval = -ENODEV; + int retval; retval = pci_enable_device(pdev); if (retval) { @@ -2020,8 +2020,10 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) pci_set_master(pdev); pci_try_set_mwi(pdev); - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (retval) + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) { TW_PRINTK(host, TW_DRIVER, 0x23, "Failed to set dma mask"); retval = -ENODEV; goto out_disable_device; @@ -2240,8 +2242,10 @@ static int twa_resume(struct pci_dev *pdev) pci_set_master(pdev); pci_try_set_mwi(pdev); - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (retval) + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) { TW_PRINTK(host, TW_DRIVER, 0x40, "Failed to set dma mask during resume"); retval = -ENODEV; goto out_disable_device; diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c index cd096104bcec..dda6fa857709 100644 --- a/drivers/scsi/3w-sas.c +++ b/drivers/scsi/3w-sas.c @@ -1573,8 +1573,10 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) pci_set_master(pdev); pci_try_set_mwi(pdev); - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (retval) + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) { TW_PRINTK(host, TW_DRIVER, 0x18, "Failed to set dma mask"); retval = -ENODEV; goto out_disable_device; @@ -1805,8 +1807,10 @@ static int twl_resume(struct pci_dev *pdev) pci_set_master(pdev); pci_try_set_mwi(pdev); - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (retval) + retval = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (retval) { TW_PRINTK(host, TW_DRIVER, 0x25, "Failed to set dma mask during resume"); retval = -ENODEV; goto out_disable_device; diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c index 07efcb9b5b94..bbdae67774f0 100644 --- a/drivers/scsi/aic94xx/aic94xx_init.c +++ b/drivers/scsi/aic94xx/aic94xx_init.c @@ -769,9 +769,11 @@ static int asd_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) if (err) goto Err_remove; - err = -ENODEV; - if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) { + err = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)); + if (err) + err = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)); + if (err) { + err = -ENODEV; asd_printk("no suitable DMA mask for %s\n", pci_name(dev)); goto Err_remove; } diff --git a/drivers/scsi/bfa/bfad.c b/drivers/scsi/bfa/bfad.c index 42a0caf6740d..88880a66a189 100644 --- a/drivers/scsi/bfa/bfad.c +++ b/drivers/scsi/bfa/bfad.c @@ -727,7 +727,7 @@ bfad_init_timer(struct bfad_s *bfad) int bfad_pci_init(struct pci_dev *pdev, struct bfad_s *bfad) { - int rc = -ENODEV; + int rc = -ENODEV; if (pci_enable_device(pdev)) { printk(KERN_ERR "pci_enable_device fail %p\n", pdev); @@ -739,8 +739,12 @@ bfad_pci_init(struct pci_dev *pdev, struct bfad_s *bfad) pci_set_master(pdev); - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (rc) + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + + if (rc) { + rc = -ENODEV; printk(KERN_ERR "dma_set_mask_and_coherent fail %p\n", pdev); goto out_release_region; } @@ -1534,6 +1538,7 @@ bfad_pci_slot_reset(struct pci_dev *pdev) { struct bfad_s *bfad = pci_get_drvdata(pdev); u8 byte; + int rc; dev_printk(KERN_ERR, &pdev->dev, "bfad_pci_slot_reset flags: 0x%x\n", bfad->bfad_flags); @@ -1561,8 +1566,11 @@ bfad_pci_slot_reset(struct pci_dev *pdev) pci_save_state(pdev); pci_set_master(pdev); - if (dma_set_mask_and_coherent(&bfad->pcidev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&bfad->pcidev->dev, DMA_BIT_MASK(32))) + rc = dma_set_mask_and_coherent(&bfad->pcidev->dev, DMA_BIT_MASK(64)); + if (rc) + rc = dma_set_mask_and_coherent(&bfad->pcidev->dev, + DMA_BIT_MASK(32)); + if (rc) goto out_disable_device; if (restart_bfa(bfad) == -1) diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c index cf629380a981..616b25bf7941 100644 --- a/drivers/scsi/csiostor/csio_init.c +++ b/drivers/scsi/csiostor/csio_init.c @@ -210,8 +210,11 @@ csio_pci_init(struct pci_dev *pdev, int *bars) pci_set_master(pdev); pci_try_set_mwi(pdev); - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { + rv = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (rv) + rv = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (rv) { + rv = -ENODEV; dev_err(&pdev->dev, "No suitable DMA available.\n"); goto err_release_regions; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index eed7fc5b3389..bc17fa0d8375 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -2323,6 +2323,7 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev, struct Scsi_Host *shost; struct hisi_hba *hisi_hba; struct device *dev = &pdev->dev; + int error; shost = scsi_host_alloc(hw->sht, sizeof(*hisi_hba)); if (!shost) { @@ -2343,8 +2344,11 @@ static struct Scsi_Host *hisi_sas_shost_alloc(struct platform_device *pdev, if (hisi_sas_get_fw_info(hisi_hba) < 0) goto err_out; - if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)) && - dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) { + error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); + if (error) + error = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); + + if (error) { dev_err(dev, "No usable DMA addressing method\n"); goto err_out; } diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index c92b3822c408..e0570fd8466e 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -2447,10 +2447,12 @@ hisi_sas_v3_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (rc) goto err_out_disable_device; - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) { + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (rc) + rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (rc) { dev_err(dev, "No usable DMA addressing method\n"); - rc = -EIO; + rc = -ENODEV; goto err_out_regions; } diff --git a/drivers/scsi/hptiop.c b/drivers/scsi/hptiop.c index 3eedfd4f8f57..251c084a6ff0 100644 --- a/drivers/scsi/hptiop.c +++ b/drivers/scsi/hptiop.c @@ -1292,6 +1292,7 @@ static int hptiop_probe(struct pci_dev *pcidev, const struct pci_device_id *id) dma_addr_t start_phy; void *start_virt; u32 offset, i, req_size; + int rc; dprintk("hptiop_probe(%p)\n", pcidev); @@ -1308,9 +1309,12 @@ static int hptiop_probe(struct pci_dev *pcidev, const struct pci_device_id *id) /* Enable 64bit DMA if possible */ iop_ops = (struct hptiop_adapter_ops *)id->driver_data; - if (dma_set_mask(&pcidev->dev, - DMA_BIT_MASK(iop_ops->hw_dma_bit_mask)) || - dma_set_mask(&pcidev->dev, DMA_BIT_MASK(32))) { + rc = dma_set_mask(&pcidev->dev, + DMA_BIT_MASK(iop_ops->hw_dma_bit_mask)); + if (rc) + rc = dma_set_mask(&pcidev->dev, DMA_BIT_MASK(32)); + + if (rc) { printk(KERN_ERR "hptiop: fail to set dma_mask\n"); goto disable_pci_device; } diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index b8d325ce8754..120fc520f27a 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -1459,7 +1459,13 @@ static int iscsi_xmit_task(struct iscsi_conn *conn) if (test_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx)) return -ENODATA; + spin_lock_bh(&conn->session->back_lock); + if (conn->task == NULL) { + spin_unlock_bh(&conn->session->back_lock); + return -ENODATA; + } __iscsi_get_task(task); + spin_unlock_bh(&conn->session->back_lock); spin_unlock_bh(&conn->session->frwd_lock); rc = conn->session->tt->xmit_task(task); spin_lock_bh(&conn->session->frwd_lock); diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 17eb4185f29d..f21c93bbb35c 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -828,6 +828,7 @@ static struct domain_device *sas_ex_discover_end_dev( rphy = sas_end_device_alloc(phy->port); if (!rphy) goto out_free; + rphy->identify.phy_identifier = phy_id; child->rphy = rphy; get_device(&rphy->dev); @@ -854,6 +855,7 @@ static struct domain_device *sas_ex_discover_end_dev( child->rphy = rphy; get_device(&rphy->dev); + rphy->identify.phy_identifier = phy_id; sas_fill_in_rphy(child, rphy); list_add_tail(&child->disco_list_node, &parent->port->disco_list); diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index bede11e16349..e1129260ed18 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -7361,15 +7361,18 @@ lpfc_sli_pci_mem_setup(struct lpfc_hba *phba) unsigned long bar0map_len, bar2map_len; int i, hbq_count; void *ptr; - int error = -ENODEV; + int error; if (!pdev) - return error; + return -ENODEV; /* Set the device DMA mask size */ - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) + error = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (error) + error = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (error) return error; + error = -ENODEV; /* Get the bus address of Bar0 and Bar2 and the number of bytes * required by each mapping. @@ -9742,11 +9745,13 @@ lpfc_sli4_pci_mem_setup(struct lpfc_hba *phba) uint32_t if_type; if (!pdev) - return error; + return -ENODEV; /* Set the device DMA mask size */ - if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)) || - dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32))) + error = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (error) + error = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (error) return error; /* diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 6d65ac584eba..a6828391d6b3 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -655,6 +655,7 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result) set_host_byte(cmd, DID_OK); return BLK_STS_TARGET; case DID_NEXUS_FAILURE: + set_host_byte(cmd, DID_OK); return BLK_STS_NEXUS; case DID_ALLOC_FAILURE: set_host_byte(cmd, DID_OK); @@ -2597,7 +2598,6 @@ void scsi_device_resume(struct scsi_device *sdev) * device deleted during suspend) */ mutex_lock(&sdev->state_mutex); - WARN_ON_ONCE(!sdev->quiesced_by); sdev->quiesced_by = NULL; blk_clear_pm_only(sdev->request_queue); if (sdev->sdev_state == SDEV_QUIESCE) diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index fff86940388b..a340af797a85 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -142,10 +142,12 @@ int sd_zbc_report_zones(struct gendisk *disk, sector_t sector, return -EOPNOTSUPP; /* - * Get a reply buffer for the number of requested zones plus a header. - * For ATA, buffers must be aligned to 512B. + * Get a reply buffer for the number of requested zones plus a header, + * without exceeding the device maximum command size. For ATA disks, + * buffers must be aligned to 512B. */ - buflen = roundup((nrz + 1) * 64, 512); + buflen = min(queue_max_hw_sectors(disk->queue) << 9, + roundup((nrz + 1) * 64, 512)); buf = kmalloc(buflen, gfp_mask); if (!buf) return -ENOMEM; diff --git a/drivers/tee/optee/core.c b/drivers/tee/optee/core.c index e5efce3c08e2..947f9b28de9e 100644 --- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -699,8 +699,10 @@ static int __init optee_driver_init(void) return -ENODEV; np = of_find_matching_node(fw_np, optee_match); - if (!np || !of_device_is_available(np)) + if (!np || !of_device_is_available(np)) { + of_node_put(np); return -ENODEV; + } optee = optee_probe(np); of_node_put(np); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 24a129fcdd61..a2e5dc7716e2 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1788,7 +1788,7 @@ static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len) ret = translate_desc(vq, (uintptr_t)vq->used + used_offset, len, iov, 64, VHOST_ACCESS_WO); - if (ret) + if (ret < 0) return ret; for (i = 0; i < ret; i++) { diff --git a/fs/afs/cell.c b/fs/afs/cell.c index cf445dbd5f2e..9de46116c749 100644 --- a/fs/afs/cell.c +++ b/fs/afs/cell.c @@ -173,6 +173,7 @@ static struct afs_cell *afs_alloc_cell(struct afs_net *net, rcu_assign_pointer(cell->vl_servers, vllist); cell->dns_expiry = TIME64_MAX; + __clear_bit(AFS_CELL_FL_NO_LOOKUP_YET, &cell->flags); } else { cell->dns_expiry = ktime_get_real_seconds(); } diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index 7cde3f46ad26..e996174cbfc0 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -14,13 +14,30 @@ #include <linux/err.h> #include <linux/fs.h> +static inline bool spacetab(char c) { return c == ' ' || c == '\t'; } +static inline char *next_non_spacetab(char *first, const char *last) +{ + for (; first <= last; first++) + if (!spacetab(*first)) + return first; + return NULL; +} +static inline char *next_terminator(char *first, const char *last) +{ + for (; first <= last; first++) + if (spacetab(*first) || !*first) + return first; + return NULL; +} + static int load_script(struct linux_binprm *bprm) { const char *i_arg, *i_name; - char *cp; + char *cp, *buf_end; struct file *file; int retval; + /* Not ours to exec if we don't start with "#!". */ if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!')) return -ENOEXEC; @@ -33,18 +50,40 @@ static int load_script(struct linux_binprm *bprm) if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE) return -ENOENT; - /* - * This section does the #! interpretation. - * Sorta complicated, but hopefully it will work. -TYT - */ - + /* Release since we are not mapping a binary into memory. */ allow_write_access(bprm->file); fput(bprm->file); bprm->file = NULL; - bprm->buf[BINPRM_BUF_SIZE - 1] = '\0'; - if ((cp = strchr(bprm->buf, '\n')) == NULL) - cp = bprm->buf+BINPRM_BUF_SIZE-1; + /* + * This section handles parsing the #! line into separate + * interpreter path and argument strings. We must be careful + * because bprm->buf is not yet guaranteed to be NUL-terminated + * (though the buffer will have trailing NUL padding when the + * file size was smaller than the buffer size). + * + * We do not want to exec a truncated interpreter path, so either + * we find a newline (which indicates nothing is truncated), or + * we find a space/tab/NUL after the interpreter path (which + * itself may be preceded by spaces/tabs). Truncating the + * arguments is fine: the interpreter can re-read the script to + * parse them on its own. + */ + buf_end = bprm->buf + sizeof(bprm->buf) - 1; + cp = strnchr(bprm->buf, sizeof(bprm->buf), '\n'); + if (!cp) { + cp = next_non_spacetab(bprm->buf + 2, buf_end); + if (!cp) + return -ENOEXEC; /* Entire buf is spaces/tabs */ + /* + * If there is no later space/tab/NUL we must assume the + * interpreter path is truncated. + */ + if (!next_terminator(cp, buf_end)) + return -ENOEXEC; + cp = buf_end; + } + /* NUL-terminate the buffer and any trailing spaces/tabs. */ *cp = '\0'; while (cp > bprm->buf) { cp--; diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 041c27ea8de1..f74193da0e09 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -616,7 +616,8 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, capsnap->size); spin_lock(&mdsc->snap_flush_lock); - list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); + if (list_empty(&ci->i_snap_flush_item)) + list_add_tail(&ci->i_snap_flush_item, &mdsc->snap_flush_list); spin_unlock(&mdsc->snap_flush_lock); return 1; /* caller may want to ceph_flush_snaps */ } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 32920a10100e..a7fa037b876b 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -859,6 +859,18 @@ static int hugetlbfs_migrate_page(struct address_space *mapping, rc = migrate_huge_page_move_mapping(mapping, newpage, page); if (rc != MIGRATEPAGE_SUCCESS) return rc; + + /* + * page_private is subpool pointer in hugetlb pages. Transfer to + * new page. PagePrivate is not associated with page_private for + * hugetlb pages and can not be set here as only page_huge_active + * pages can be migrated. + */ + if (page_private(page)) { + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + } + if (mode != MIGRATE_SYNC_NO_COPY) migrate_page_copy(newpage, page); else diff --git a/fs/namespace.c b/fs/namespace.c index a677b59efd74..678ef175d63a 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2698,7 +2698,6 @@ static long exact_copy_from_user(void *to, const void __user * from, if (!access_ok(from, n)) return n; - current->kernel_uaccess_faults_ok++; while (n) { if (__get_user(c, f)) { memset(t, 0, n); @@ -2708,7 +2707,6 @@ static long exact_copy_from_user(void *to, const void __user * from, f++; n--; } - current->kernel_uaccess_faults_ok--; return n; } diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c index 3f23b6840547..bf34ddaa2ad7 100644 --- a/fs/nfs/nfs4idmap.c +++ b/fs/nfs/nfs4idmap.c @@ -44,6 +44,7 @@ #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> +#include <keys/request_key_auth-type.h> #include <linux/module.h> #include "internal.h" @@ -59,7 +60,7 @@ static struct key_type key_type_id_resolver_legacy; struct idmap_legacy_upcalldata { struct rpc_pipe_msg pipe_msg; struct idmap_msg idmap_msg; - struct key_construction *key_cons; + struct key *authkey; struct idmap *idmap; }; @@ -384,7 +385,7 @@ static const match_table_t nfs_idmap_tokens = { { Opt_find_err, NULL } }; -static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); +static int nfs_idmap_legacy_upcall(struct key *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); static void idmap_release_pipe(struct inode *); @@ -549,11 +550,12 @@ nfs_idmap_prepare_pipe_upcall(struct idmap *idmap, static void nfs_idmap_complete_pipe_upcall_locked(struct idmap *idmap, int ret) { - struct key_construction *cons = idmap->idmap_upcall_data->key_cons; + struct key *authkey = idmap->idmap_upcall_data->authkey; kfree(idmap->idmap_upcall_data); idmap->idmap_upcall_data = NULL; - complete_request_key(cons, ret); + complete_request_key(authkey, ret); + key_put(authkey); } static void @@ -563,15 +565,14 @@ nfs_idmap_abort_pipe_upcall(struct idmap *idmap, int ret) nfs_idmap_complete_pipe_upcall_locked(idmap, ret); } -static int nfs_idmap_legacy_upcall(struct key_construction *cons, - const char *op, - void *aux) +static int nfs_idmap_legacy_upcall(struct key *authkey, void *aux) { struct idmap_legacy_upcalldata *data; + struct request_key_auth *rka = get_request_key_auth(authkey); struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; - struct key *key = cons->key; + struct key *key = rka->target_key; int ret = -ENOKEY; if (!aux) @@ -586,7 +587,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, msg = &data->pipe_msg; im = &data->idmap_msg; data->idmap = idmap; - data->key_cons = cons; + data->authkey = key_get(authkey); ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) @@ -604,7 +605,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, out2: kfree(data); out1: - complete_request_key(cons, ret); + complete_request_key(authkey, ret); return ret; } @@ -651,9 +652,10 @@ out: static ssize_t idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { + struct request_key_auth *rka; struct rpc_inode *rpci = RPC_I(file_inode(filp)); struct idmap *idmap = (struct idmap *)rpci->private; - struct key_construction *cons; + struct key *authkey; struct idmap_msg im; size_t namelen_in; int ret = -ENOKEY; @@ -665,7 +667,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (idmap->idmap_upcall_data == NULL) goto out_noupcall; - cons = idmap->idmap_upcall_data->key_cons; + authkey = idmap->idmap_upcall_data->authkey; + rka = get_request_key_auth(authkey); if (mlen != sizeof(im)) { ret = -ENOSPC; @@ -690,9 +693,9 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) ret = nfs_idmap_read_and_verify_message(&im, &idmap->idmap_upcall_data->idmap_msg, - cons->key, cons->authkey); + rka->target_key, authkey); if (ret >= 0) { - key_set_timeout(cons->key, nfs_idmap_cache_timeout); + key_set_timeout(rka->target_key, nfs_idmap_cache_timeout); ret = mlen; } diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c index a5a2fe76568f..b094d3d79354 100644 --- a/fs/orangefs/file.c +++ b/fs/orangefs/file.c @@ -398,8 +398,6 @@ static ssize_t orangefs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter loff_t pos = iocb->ki_pos; ssize_t rc = 0; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_read_iter\n"); orangefs_stats.reads++; @@ -416,8 +414,6 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite loff_t pos; ssize_t rc; - BUG_ON(iocb->private); - gossip_debug(GOSSIP_FILE_DEBUG, "orangefs_file_write_iter\n"); inode_lock(file->f_mapping->host); diff --git a/fs/proc/base.c b/fs/proc/base.c index 633a63462573..f5ed9512d193 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1086,10 +1086,6 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy) task_lock(p); if (!p->vfork_done && process_shares_mm(p, mm)) { - pr_info("updating oom_score_adj for %d (%s) from %d to %d because it shares mm with %d (%s). Report if this is unexpected.\n", - task_pid_nr(p), p->comm, - p->signal->oom_score_adj, oom_adj, - task_pid_nr(task), task->comm); p->signal->oom_score_adj = oom_adj; if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE)) p->signal->oom_score_adj_min = (short)oom_adj; diff --git a/include/keys/request_key_auth-type.h b/include/keys/request_key_auth-type.h new file mode 100644 index 000000000000..a726dd3f1dc6 --- /dev/null +++ b/include/keys/request_key_auth-type.h @@ -0,0 +1,36 @@ +/* request_key authorisation token key type + * + * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _KEYS_REQUEST_KEY_AUTH_TYPE_H +#define _KEYS_REQUEST_KEY_AUTH_TYPE_H + +#include <linux/key.h> + +/* + * Authorisation record for request_key(). + */ +struct request_key_auth { + struct key *target_key; + struct key *dest_keyring; + const struct cred *cred; + void *callout_info; + size_t callout_len; + pid_t pid; + char op[8]; +} __randomize_layout; + +static inline struct request_key_auth *get_request_key_auth(const struct key *key) +{ + return key->payload.data[0]; +} + + +#endif /* _KEYS_REQUEST_KEY_AUTH_TYPE_H */ diff --git a/include/keys/user-type.h b/include/keys/user-type.h index e098cbe27db5..12babe991594 100644 --- a/include/keys/user-type.h +++ b/include/keys/user-type.h @@ -31,7 +31,7 @@ struct user_key_payload { struct rcu_head rcu; /* RCU destructor */ unsigned short datalen; /* length of this data */ - char data[0]; /* actual data */ + char data[0] __aligned(__alignof__(u64)); /* actual data */ }; extern struct key_type key_type_user; diff --git a/include/linux/key-type.h b/include/linux/key-type.h index bc9af551fc83..e49d1de0614e 100644 --- a/include/linux/key-type.h +++ b/include/linux/key-type.h @@ -21,15 +21,6 @@ struct kernel_pkey_query; struct kernel_pkey_params; /* - * key under-construction record - * - passed to the request_key actor if supplied - */ -struct key_construction { - struct key *key; /* key being constructed */ - struct key *authkey;/* authorisation for key being constructed */ -}; - -/* * Pre-parsed payload, used by key add, update and instantiate. * * This struct will be cleared and data and datalen will be set with the data @@ -50,8 +41,7 @@ struct key_preparsed_payload { time64_t expiry; /* Expiry time of key */ } __randomize_layout; -typedef int (*request_key_actor_t)(struct key_construction *key, - const char *op, void *aux); +typedef int (*request_key_actor_t)(struct key *auth_key, void *aux); /* * Preparsed matching criterion. @@ -181,20 +171,20 @@ extern int key_instantiate_and_link(struct key *key, const void *data, size_t datalen, struct key *keyring, - struct key *instkey); + struct key *authkey); extern int key_reject_and_link(struct key *key, unsigned timeout, unsigned error, struct key *keyring, - struct key *instkey); -extern void complete_request_key(struct key_construction *cons, int error); + struct key *authkey); +extern void complete_request_key(struct key *authkey, int error); static inline int key_negate_and_link(struct key *key, unsigned timeout, struct key *keyring, - struct key *instkey) + struct key *authkey) { - return key_reject_and_link(key, timeout, ENOKEY, keyring, instkey); + return key_reject_and_link(key, timeout, ENOKEY, keyring, authkey); } extern int generic_key_instantiate(struct key *key, struct key_preparsed_payload *prep); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2b2a6dce1630..4c76fe2c8488 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -11,6 +11,8 @@ #define _LINUX_NETDEV_FEATURES_H #include <linux/types.h> +#include <linux/bitops.h> +#include <asm/byteorder.h> typedef u64 netdev_features_t; @@ -154,8 +156,26 @@ enum { #define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) #define NETIF_F_HW_TLS_RX __NETIF_F(HW_TLS_RX) -#define for_each_netdev_feature(mask_addr, bit) \ - for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) +/* Finds the next feature with the highest number of the range of start till 0. + */ +static inline int find_next_netdev_feature(u64 feature, unsigned long start) +{ + /* like BITMAP_LAST_WORD_MASK() for u64 + * this sets the most significant 64 - start to 0. + */ + feature &= ~0ULL >> (-start & ((sizeof(feature) * 8) - 1)); + + return fls64(feature) - 1; +} + +/* This goes for the MSB to the LSB through the set feature bits, + * mask_addr should be a u64 and bit an int + */ +#define for_each_netdev_feature(mask_addr, bit) \ + for ((bit) = find_next_netdev_feature((mask_addr), \ + NETDEV_FEATURE_COUNT); \ + (bit) >= 0; \ + (bit) = find_next_netdev_feature((mask_addr), (bit) - 1)) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 86dbb3e29139..848b54b7ec91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3861,7 +3861,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) if (debug_value == 0) /* no output */ return 0; /* set low N bits */ - return (1 << debug_value) - 1; + return (1U << debug_value) - 1; } static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) diff --git a/include/linux/phy.h b/include/linux/phy.h index 127fcc9c3778..333b56d8f746 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -992,6 +992,14 @@ static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; } +static inline int genphy_no_ack_interrupt(struct phy_device *phydev) +{ + return 0; +} +static inline int genphy_no_config_intr(struct phy_device *phydev) +{ + return 0; +} int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum); int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, diff --git a/include/linux/sched.h b/include/linux/sched.h index bba3afb4e9bf..f9b43c989577 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -739,12 +739,6 @@ struct task_struct { unsigned use_memdelay:1; #endif - /* - * May usercopy functions fault on kernel addresses? - * This is not just a single bit because this can potentially nest. - */ - unsigned int kernel_uaccess_faults_ok; - unsigned long atomic_flags; /* Flags requiring atomic access. */ struct restart_block restart_block; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 95d25b010a25..bdb9563c64a0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2434,7 +2434,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb, if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); - else + else if (offset_hint >= 0) skb_set_transport_header(skb, offset_hint); } @@ -4212,6 +4212,12 @@ static inline bool skb_is_gso_sctp(const struct sk_buff *skb) return skb_shinfo(skb)->gso_type & SKB_GSO_SCTP; } +static inline bool skb_is_gso_tcp(const struct sk_buff *skb) +{ + return skb_is_gso(skb) && + skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6); +} + static inline void skb_gso_reset(struct sk_buff *skb) { skb_shinfo(skb)->gso_size = 0; diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index cb462f9ab7dd..e0348cb0a1dd 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -57,6 +57,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + } else { + /* gso packets without NEEDS_CSUM do not set transport_offset. + * probe and drop if does not match one of the above types. + */ + if (gso_type && skb->network_header) { + if (!skb->protocol) + virtio_net_hdr_set_proto(skb, hdr); +retry: + skb_probe_transport_header(skb, -1); + if (!skb_transport_header_was_set(skb)) { + /* UFO does not specify ipv4 or 6: try both */ + if (gso_type & SKB_GSO_UDP && + skb->protocol == htons(ETH_P_IP)) { + skb->protocol = htons(ETH_P_IPV6); + goto retry; + } + return -EINVAL; + } + } } if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { diff --git a/include/net/icmp.h b/include/net/icmp.h index 6ac3a5bd0117..e0f709d26dde 100644 --- a/include/net/icmp.h +++ b/include/net/icmp.h @@ -22,6 +22,7 @@ #include <net/inet_sock.h> #include <net/snmp.h> +#include <net/ip.h> struct icmp_err { int errno; @@ -39,7 +40,13 @@ struct net_proto_family; struct sk_buff; struct net; -void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info); +void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, + const struct ip_options *opt); +static inline void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + __icmp_send(skb_in, type, code, info, &IPCB(skb_in)->opt); +} + int icmp_rcv(struct sk_buff *skb); int icmp_err(struct sk_buff *skb, u32 info); int icmp_init(void); diff --git a/include/net/ip.h b/include/net/ip.h index 8866bfce6121..be3cad9c2e4c 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -667,6 +667,8 @@ static inline int ip_options_echo(struct net *net, struct ip_options *dopt, } void ip_options_fragment(struct sk_buff *skb); +int __ip_options_compile(struct net *net, struct ip_options *opt, + struct sk_buff *skb, __be32 *info); int ip_options_compile(struct net *net, struct ip_options *opt, struct sk_buff *skb); int ip_options_get(struct net *net, struct ip_options_rcu **optp, @@ -716,7 +718,7 @@ extern int sysctl_icmp_msgs_burst; int ip_misc_proc_init(void); #endif -int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, +int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack); #endif /* _IP_H */ diff --git a/include/net/phonet/pep.h b/include/net/phonet/pep.h index b669fe6dbc3b..98f31c7ea23d 100644 --- a/include/net/phonet/pep.h +++ b/include/net/phonet/pep.h @@ -63,10 +63,11 @@ struct pnpipehdr { u8 state_after_reset; /* reset request */ u8 error_code; /* any response */ u8 pep_type; /* status indication */ - u8 data[1]; + u8 data0; /* anything else */ }; + u8 data[]; }; -#define other_pep_type data[1] +#define other_pep_type data[0] static inline struct pnpipehdr *pnp_hdr(struct sk_buff *skb) { diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 7298a53b9702..85386becbaea 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -853,7 +853,7 @@ static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) xfrm_pol_put(pols[i]); } -void __xfrm_state_destroy(struct xfrm_state *); +void __xfrm_state_destroy(struct xfrm_state *, bool); static inline void __xfrm_state_put(struct xfrm_state *x) { @@ -863,7 +863,13 @@ static inline void __xfrm_state_put(struct xfrm_state *x) static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) - __xfrm_state_destroy(x); + __xfrm_state_destroy(x, false); +} + +static inline void xfrm_state_put_sync(struct xfrm_state *x) +{ + if (refcount_dec_and_test(&x->refcnt)) + __xfrm_state_destroy(x, true); } static inline void xfrm_state_hold(struct xfrm_state *x) @@ -1590,7 +1596,7 @@ struct xfrmk_spdinfo { struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_delete(struct xfrm_state *x); -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid); +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); diff --git a/init/initramfs.c b/init/initramfs.c index 7cea802d00ef..fca899622937 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -550,6 +550,7 @@ skip: initrd_end = 0; } +#ifdef CONFIG_BLK_DEV_RAM #define BUF_SIZE 1024 static void __init clean_rootfs(void) { @@ -596,6 +597,7 @@ static void __init clean_rootfs(void) ksys_close(fd); kfree(buf); } +#endif static int __init populate_rootfs(void) { @@ -638,10 +640,8 @@ static int __init populate_rootfs(void) printk(KERN_INFO "Unpacking initramfs...\n"); err = unpack_to_rootfs((char *)initrd_start, initrd_end - initrd_start); - if (err) { + if (err) printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); - clean_rootfs(); - } free_initrd(); #endif } diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index abf1002080df..93a5cbbde421 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -471,6 +471,7 @@ static int trie_delete_elem(struct bpf_map *map, void *_key) } if (!node || node->prefixlen != key->prefixlen || + node->prefixlen != matchlen || (node->flags & LPM_TREE_NODE_FLAG_IM)) { ret = -ENOENT; goto out; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index d43b14535827..950ab2f28922 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -44,7 +44,7 @@ static void do_up_read(struct irq_work *entry) struct stack_map_irq_work *work; work = container_of(entry, struct stack_map_irq_work, irq_work); - up_read(work->sem); + up_read_non_owner(work->sem); work->sem = NULL; } @@ -338,6 +338,12 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, } else { work->sem = ¤t->mm->mmap_sem; irq_work_queue(&work->irq_work); + /* + * The irq_work will release the mmap_sem with + * up_read_non_owner(). The rwsem_release() is called + * here to release the lock from lockdep's perspective. + */ + rwsem_release(¤t->mm->mmap_sem.dep_map, 1, _RET_IP_); } } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8577bb7f8be6..84470d1480aa 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -559,12 +559,12 @@ static int map_create(union bpf_attr *attr) err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. - * bpf_map_put() is needed because the above + * bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ - bpf_map_put(map); + bpf_map_put_with_uref(map); return err; } @@ -1986,7 +1986,7 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr) fd = bpf_map_new_fd(map, f_flags); if (fd < 0) - bpf_map_put(map); + bpf_map_put_with_uref(map); return fd; } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 56674a7c3778..5fcce2f4209d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1617,12 +1617,13 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } -static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, - int size, enum bpf_access_type t) +static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, + u32 regno, int off, int size, + enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; - struct bpf_insn_access_aux info; + struct bpf_insn_access_aux info = {}; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", @@ -1636,6 +1637,8 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, return -EACCES; } + env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + return 0; } @@ -2032,7 +2035,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn verbose(env, "cannot write into socket\n"); return -EACCES; } - err = check_sock_access(env, regno, off, size, t); + err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { @@ -6917,7 +6920,8 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) u32 off_reg; aux = &env->insn_aux_data[i + delta]; - if (!aux->alu_state) + if (!aux->alu_state || + aux->alu_state == BPF_ALU_NON_POINTER) continue; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index c3484785b179..0e97ca9306ef 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -322,7 +322,7 @@ static bool update_stats(struct psi_group *group) expires = group->next_update; if (now < expires) goto out; - if (now - expires > psi_period) + if (now - expires >= psi_period) missed_periods = div_u64(now - expires, psi_period); /* diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c521b7347482..c4238b441624 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3384,6 +3384,8 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file const char tgid_space[] = " "; const char space[] = " "; + print_event_info(buf, m); + seq_printf(m, "# %s _-----=> irqs-off\n", tgid ? tgid_space : space); seq_printf(m, "# %s / _----=> need-resched\n", diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d5fb09ebba8b..9eaf07f99212 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -861,22 +861,14 @@ static const struct file_operations kprobe_profile_ops = { static nokprobe_inline int fetch_store_strlen(unsigned long addr) { - mm_segment_t old_fs; int ret, len = 0; u8 c; - old_fs = get_fs(); - set_fs(KERNEL_DS); - pagefault_disable(); - do { - ret = __copy_from_user_inatomic(&c, (u8 *)addr + len, 1); + ret = probe_mem_read(&c, (u8 *)addr + len, 1); len++; } while (c && ret == 0 && len < MAX_STRING_SIZE); - pagefault_enable(); - set_fs(old_fs); - return (ret < 0) ? ret : len; } diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index d8c474b6691e..9737059ec58b 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -113,6 +113,28 @@ config KASAN_INLINE endchoice +config KASAN_STACK_ENABLE + bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST + default !(CLANG_VERSION < 90000) + depends on KASAN + help + The LLVM stack address sanitizer has a know problem that + causes excessive stack usage in a lot of functions, see + https://bugs.llvm.org/show_bug.cgi?id=38809 + Disabling asan-stack makes it safe to run kernels build + with clang-8 with KASAN enabled, though it loses some of + the functionality. + This feature is always disabled when compile-testing with clang-8 + or earlier to avoid cluttering the output in stack overflow + warnings, but clang-8 users can still enable it for builds without + CONFIG_COMPILE_TEST. On gcc and later clang versions it is + assumed to always be safe to use and enabled by default. + +config KASAN_STACK + int + default 1 if KASAN_STACK_ENABLE || CC_IS_GCC + default 0 + config KASAN_S390_4_LEVEL_PAGING bool "KASan: use 4-level paging" depends on KASAN && S390 diff --git a/lib/assoc_array.c b/lib/assoc_array.c index c6659cb37033..59875eb278ea 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -768,9 +768,11 @@ all_leaves_cluster_together: new_s0->index_key[i] = ops->get_key_chunk(index_key, i * ASSOC_ARRAY_KEY_CHUNK_SIZE); - blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK); - pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank); - new_s0->index_key[keylen - 1] &= ~blank; + if (level & ASSOC_ARRAY_KEY_CHUNK_MASK) { + blank = ULONG_MAX << (level & ASSOC_ARRAY_KEY_CHUNK_MASK); + pr_devel("blank off [%zu] %d: %lx\n", keylen - 1, level, blank); + new_s0->index_key[keylen - 1] &= ~blank; + } /* This now reduces to a node splitting exercise for which we'll need * to regenerate the disparity table. diff --git a/mm/debug.c b/mm/debug.c index 0abb987dad9b..1611cf00a137 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -44,7 +44,7 @@ const struct trace_print_flags vmaflag_names[] = { void __dump_page(struct page *page, const char *reason) { - struct address_space *mapping = page_mapping(page); + struct address_space *mapping; bool page_poisoned = PagePoisoned(page); int mapcount; @@ -58,6 +58,8 @@ void __dump_page(struct page *page, const char *reason) goto hex_only; } + mapping = page_mapping(page); + /* * Avoid VM_BUG_ON() in page_mapcount(). * page->_mapcount space in struct page is used by sl[aou]b pages to diff --git a/mm/hugetlb.c b/mm/hugetlb.c index afef61656c1e..8dfdffc34a99 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3624,7 +3624,6 @@ retry_avoidcopy: copy_user_huge_page(new_page, old_page, address, vma, pages_per_huge_page(h)); __SetPageUptodate(new_page); - set_page_huge_active(new_page); mmu_notifier_range_init(&range, mm, haddr, haddr + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); @@ -3645,6 +3644,7 @@ retry_avoidcopy: make_huge_pte(vma, new_page, 1)); page_remove_rmap(old_page, true); hugepage_add_new_anon_rmap(new_page, vma, haddr); + set_page_huge_active(new_page); /* Make the old page be freed below */ new_page = old_page; } @@ -3729,6 +3729,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm, pte_t new_pte; spinlock_t *ptl; unsigned long haddr = address & huge_page_mask(h); + bool new_page = false; /* * Currently, we are forced to kill the process in the event the @@ -3790,7 +3791,7 @@ retry: } clear_huge_page(page, address, pages_per_huge_page(h)); __SetPageUptodate(page); - set_page_huge_active(page); + new_page = true; if (vma->vm_flags & VM_MAYSHARE) { int err = huge_add_to_page_cache(page, mapping, idx); @@ -3861,6 +3862,15 @@ retry: } spin_unlock(ptl); + + /* + * Only make newly allocated pages active. Existing pages found + * in the pagecache could be !page_huge_active() if they have been + * isolated for migration. + */ + if (new_page) + set_page_huge_active(page); + unlock_page(page); out: return ret; @@ -4095,7 +4105,6 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, * the set_pte_at() write. */ __SetPageUptodate(page); - set_page_huge_active(page); mapping = dst_vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, dst_vma, dst_addr); @@ -4163,6 +4172,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm, update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); + set_page_huge_active(page); if (vm_shared) unlock_page(page); ret = 0; diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index e2bb06c1b45e..5d1065efbd47 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -7,6 +7,8 @@ KCOV_INSTRUMENT := n CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_generic.o = -pg +CFLAGS_REMOVE_tags.o = -pg + # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 diff --git a/mm/kasan/common.c b/mm/kasan/common.c index 73c9cbfdedf4..09b534fbba17 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -361,10 +361,15 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object) * get different tags. */ static u8 assign_tag(struct kmem_cache *cache, const void *object, - bool init, bool krealloc) + bool init, bool keep_tag) { - /* Reuse the same tag for krealloc'ed objects. */ - if (krealloc) + /* + * 1. When an object is kmalloc()'ed, two hooks are called: + * kasan_slab_alloc() and kasan_kmalloc(). We assign the + * tag only in the first one. + * 2. We reuse the same tag for krealloc'ed objects. + */ + if (keep_tag) return get_tag(object); /* @@ -405,12 +410,6 @@ void * __must_check kasan_init_slab_obj(struct kmem_cache *cache, return (void *)object; } -void * __must_check kasan_slab_alloc(struct kmem_cache *cache, void *object, - gfp_t flags) -{ - return kasan_kmalloc(cache, object, cache->object_size, flags); -} - static inline bool shadow_invalid(u8 tag, s8 shadow_byte) { if (IS_ENABLED(CONFIG_KASAN_GENERIC)) @@ -467,7 +466,7 @@ bool kasan_slab_free(struct kmem_cache *cache, void *object, unsigned long ip) } static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object, - size_t size, gfp_t flags, bool krealloc) + size_t size, gfp_t flags, bool keep_tag) { unsigned long redzone_start; unsigned long redzone_end; @@ -485,7 +484,7 @@ static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object, KASAN_SHADOW_SCALE_SIZE); if (IS_ENABLED(CONFIG_KASAN_SW_TAGS)) - tag = assign_tag(cache, object, false, krealloc); + tag = assign_tag(cache, object, false, keep_tag); /* Tag is ignored in set_tag without CONFIG_KASAN_SW_TAGS */ kasan_unpoison_shadow(set_tag(object, tag), size); @@ -498,10 +497,16 @@ static void *__kasan_kmalloc(struct kmem_cache *cache, const void *object, return set_tag(object, tag); } +void * __must_check kasan_slab_alloc(struct kmem_cache *cache, void *object, + gfp_t flags) +{ + return __kasan_kmalloc(cache, object, cache->object_size, flags, false); +} + void * __must_check kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size, gfp_t flags) { - return __kasan_kmalloc(cache, object, size, flags, false); + return __kasan_kmalloc(cache, object, size, flags, true); } EXPORT_SYMBOL(kasan_kmalloc); diff --git a/mm/kasan/tags.c b/mm/kasan/tags.c index 0777649e07c4..63fca3172659 100644 --- a/mm/kasan/tags.c +++ b/mm/kasan/tags.c @@ -46,7 +46,7 @@ void kasan_init_tags(void) int cpu; for_each_possible_cpu(cpu) - per_cpu(prng_state, cpu) = get_random_u32(); + per_cpu(prng_state, cpu) = (u32)get_cycles(); } /* diff --git a/mm/kmemleak.c b/mm/kmemleak.c index f9d9dc250428..707fa5579f66 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -574,6 +574,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, unsigned long flags; struct kmemleak_object *object, *parent; struct rb_node **link, *rb_parent; + unsigned long untagged_ptr; object = kmem_cache_alloc(object_cache, gfp_kmemleak_mask(gfp)); if (!object) { @@ -619,8 +620,9 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, write_lock_irqsave(&kmemleak_lock, flags); - min_addr = min(min_addr, ptr); - max_addr = max(max_addr, ptr + size); + untagged_ptr = (unsigned long)kasan_reset_tag((void *)ptr); + min_addr = min(min_addr, untagged_ptr); + max_addr = max(max_addr, untagged_ptr + size); link = &object_tree_root.rb_node; rb_parent = NULL; while (*link) { @@ -1333,6 +1335,7 @@ static void scan_block(void *_start, void *_end, unsigned long *start = PTR_ALIGN(_start, BYTES_PER_POINTER); unsigned long *end = _end - (BYTES_PER_POINTER - 1); unsigned long flags; + unsigned long untagged_ptr; read_lock_irqsave(&kmemleak_lock, flags); for (ptr = start; ptr < end; ptr++) { @@ -1347,7 +1350,8 @@ static void scan_block(void *_start, void *_end, pointer = *ptr; kasan_enable_current(); - if (pointer < min_addr || pointer >= max_addr) + untagged_ptr = (unsigned long)kasan_reset_tag((void *)pointer); + if (untagged_ptr < min_addr || untagged_ptr >= max_addr) continue; /* diff --git a/mm/maccess.c b/mm/maccess.c index f3416632e5a4..ec00be51a24f 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -30,10 +30,8 @@ long __probe_kernel_read(void *dst, const void *src, size_t size) set_fs(KERNEL_DS); pagefault_disable(); - current->kernel_uaccess_faults_ok++; ret = __copy_from_user_inatomic(dst, (__force const void __user *)src, size); - current->kernel_uaccess_faults_ok--; pagefault_enable(); set_fs(old_fs); @@ -60,9 +58,7 @@ long __probe_kernel_write(void *dst, const void *src, size_t size) set_fs(KERNEL_DS); pagefault_disable(); - current->kernel_uaccess_faults_ok++; ret = __copy_to_user_inatomic((__force void __user *)dst, src, size); - current->kernel_uaccess_faults_ok--; pagefault_enable(); set_fs(old_fs); @@ -98,13 +94,11 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) set_fs(KERNEL_DS); pagefault_disable(); - current->kernel_uaccess_faults_ok++; do { ret = __get_user(*dst++, (const char __user __force *)src++); } while (dst[-1] && ret == 0 && src - unsafe_addr < count); - current->kernel_uaccess_faults_ok--; dst[-1] = '\0'; pagefault_enable(); set_fs(old_fs); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 124e794867c5..1ad28323fb9f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1188,11 +1188,13 @@ static inline int pageblock_free(struct page *page) return PageBuddy(page) && page_order(page) >= pageblock_order; } -/* Return the start of the next active pageblock after a given page */ -static struct page *next_active_pageblock(struct page *page) +/* Return the pfn of the start of the next active pageblock after a given pfn */ +static unsigned long next_active_pageblock(unsigned long pfn) { + struct page *page = pfn_to_page(pfn); + /* Ensure the starting page is pageblock-aligned */ - BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1)); + BUG_ON(pfn & (pageblock_nr_pages - 1)); /* If the entire pageblock is free, move to the end of free page */ if (pageblock_free(page)) { @@ -1200,16 +1202,16 @@ static struct page *next_active_pageblock(struct page *page) /* be careful. we don't have locks, page_order can be changed.*/ order = page_order(page); if ((order < MAX_ORDER) && (order >= pageblock_order)) - return page + (1 << order); + return pfn + (1 << order); } - return page + pageblock_nr_pages; + return pfn + pageblock_nr_pages; } -static bool is_pageblock_removable_nolock(struct page *page) +static bool is_pageblock_removable_nolock(unsigned long pfn) { + struct page *page = pfn_to_page(pfn); struct zone *zone; - unsigned long pfn; /* * We have to be careful here because we are iterating over memory @@ -1232,13 +1234,14 @@ static bool is_pageblock_removable_nolock(struct page *page) /* Checks if this range of memory is likely to be hot-removable. */ bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { - struct page *page = pfn_to_page(start_pfn); - unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page))); - struct page *end_page = pfn_to_page(end_pfn); + unsigned long end_pfn, pfn; + + end_pfn = min(start_pfn + nr_pages, + zone_end_pfn(page_zone(pfn_to_page(start_pfn)))); /* Check the starting page of each pageblock within the range */ - for (; page < end_page; page = next_active_pageblock(page)) { - if (!is_pageblock_removable_nolock(page)) + for (pfn = start_pfn; pfn < end_pfn; pfn = next_active_pageblock(pfn)) { + if (!is_pageblock_removable_nolock(pfn)) return false; cond_resched(); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d4496d9d34f5..ee2bce59d2bf 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1314,7 +1314,7 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; - const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long); + unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); if (copy > nbytes) { if (copy > PAGE_SIZE) @@ -1491,7 +1491,7 @@ static int kernel_get_mempolicy(int __user *policy, int uninitialized_var(pval); nodemask_t nodes; - if (nmask != NULL && maxnode < MAX_NUMNODES) + if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; err = do_get_mempolicy(&pval, &nodes, addr, flags); @@ -1527,7 +1527,7 @@ COMPAT_SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long nr_bits, alloc_size; DECLARE_BITMAP(bm, MAX_NUMNODES); - nr_bits = min_t(unsigned long, maxnode-1, MAX_NUMNODES); + nr_bits = min_t(unsigned long, maxnode-1, nr_node_ids); alloc_size = ALIGN(nr_bits, BITS_PER_LONG) / 8; if (nmask) diff --git a/mm/migrate.c b/mm/migrate.c index d4fd680be3b0..181f5d2718a9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1315,6 +1315,16 @@ static int unmap_and_move_huge_page(new_page_t get_new_page, lock_page(hpage); } + /* + * Check for pages which are in the process of being freed. Without + * page_mapping() set, hugetlbfs specific move page routine will not + * be called and we could leak usage counts for subpools. + */ + if (page_private(hpage) && !page_mapping(hpage)) { + rc = -EBUSY; + goto out_unlock; + } + if (PageAnon(hpage)) anon_vma = page_get_anon_vma(hpage); @@ -1345,6 +1355,7 @@ put_anon: put_new_page = NULL; } +out_unlock: unlock_page(hpage); out: if (rc != -EAGAIN) diff --git a/mm/mmap.c b/mm/mmap.c index f901065c4c64..fc1809b1bed6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2426,12 +2426,11 @@ int expand_downwards(struct vm_area_struct *vma, { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *prev; - int error; + int error = 0; address &= PAGE_MASK; - error = security_mmap_addr(address); - if (error) - return error; + if (address < mmap_min_addr) + return -EPERM; /* Enforce stack_guard_gap */ prev = vma->vm_prev; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 46285d28e43b..0b9f577b1a2a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2170,6 +2170,18 @@ static inline void boost_watermark(struct zone *zone) max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); + + /* + * high watermark may be uninitialised if fragmentation occurs + * very early in boot so do not boost. We do not fall + * through and boost by pageblock_nr_pages as failing + * allocations that early means that reclaim is not going + * to help and it may even be impossible to reclaim the + * boosted watermark resulting in a hang. + */ + if (!max_boost) + return; + max_boost = max(pageblock_nr_pages, max_boost); zone->watermark_boost = min(zone->watermark_boost + pageblock_nr_pages, @@ -4675,11 +4687,11 @@ refill: /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ - page_ref_add(page, size); + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); /* reset page count bias and offset to start of new frag */ nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = size + 1; + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; nc->offset = size; } @@ -4695,10 +4707,10 @@ refill: size = nc->size; #endif /* OK, page count is 0, we can safely set it */ - set_page_count(page, size + 1); + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size + 1; + nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = size - fragsz; } diff --git a/mm/shmem.c b/mm/shmem.c index 6ece1e2fe76e..2c012eee133d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2848,16 +2848,20 @@ static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode, static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); - int ret; + int ret = 0; /* * No ordinary (disk based) filesystem counts links as inodes; * but each new link needs a new dentry, pinning lowmem, and * tmpfs dentries cannot be pruned until they are unlinked. + * But if an O_TMPFILE file is linked into the tmpfs, the + * first link must skip that, to get the accounting right. */ - ret = shmem_reserve_inode(inode->i_sb); - if (ret) - goto out; + if (inode->i_nlink) { + ret = shmem_reserve_inode(inode->i_sb); + if (ret) + goto out; + } dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = current_time(inode); diff --git a/mm/slab.c b/mm/slab.c index 78eb8c5bf4e4..91c1863df93d 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2359,7 +2359,7 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, void *freelist; void *addr = page_address(page); - page->s_mem = kasan_reset_tag(addr) + colour_off; + page->s_mem = addr + colour_off; page->active = 0; if (OBJFREELIST_SLAB(cachep)) @@ -2368,6 +2368,7 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep, /* Slab management obj is off-slab. */ freelist = kmem_cache_alloc_node(cachep->freelist_cache, local_flags, nodeid); + freelist = kasan_reset_tag(freelist); if (!freelist) return NULL; } else { @@ -2681,6 +2682,13 @@ static struct page *cache_grow_begin(struct kmem_cache *cachep, offset *= cachep->colour_off; + /* + * Call kasan_poison_slab() before calling alloc_slabmgmt(), so + * page_address() in the latter returns a non-tagged pointer, + * as it should be for slab pages. + */ + kasan_poison_slab(page); + /* Get slab management. */ freelist = alloc_slabmgmt(cachep, page, offset, local_flags & ~GFP_CONSTRAINT_MASK, page_node); @@ -2689,7 +2697,6 @@ static struct page *cache_grow_begin(struct kmem_cache *cachep, slab_map_pages(cachep, page, freelist); - kasan_poison_slab(page); cache_init_objs(cachep, page); if (gfpflags_allow_blocking(local_flags)) @@ -3540,7 +3547,6 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { void *ret = slab_alloc(cachep, flags, _RET_IP_); - ret = kasan_slab_alloc(cachep, ret, flags); trace_kmem_cache_alloc(_RET_IP_, ret, cachep->object_size, cachep->size, flags); @@ -3630,7 +3636,6 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_); - ret = kasan_slab_alloc(cachep, ret, flags); trace_kmem_cache_alloc_node(_RET_IP_, ret, cachep->object_size, cachep->size, flags, nodeid); @@ -4408,6 +4413,8 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, unsigned int objnr; unsigned long offset; + ptr = kasan_reset_tag(ptr); + /* Find and validate object. */ cachep = page->slab_cache; objnr = obj_to_index(cachep, page, (void *)ptr); diff --git a/mm/slab.h b/mm/slab.h index 4190c24ef0e9..384105318779 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -437,11 +437,10 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, flags &= gfp_allowed_mask; for (i = 0; i < size; i++) { - void *object = p[i]; - - kmemleak_alloc_recursive(object, s->object_size, 1, + p[i] = kasan_slab_alloc(s, p[i], flags); + /* As p[i] might get tagged, call kmemleak hook after KASAN. */ + kmemleak_alloc_recursive(p[i], s->object_size, 1, s->flags, flags); - p[i] = kasan_slab_alloc(s, object, flags); } if (memcg_kmem_enabled()) diff --git a/mm/slab_common.c b/mm/slab_common.c index 81732d05e74a..f9d89c1b5977 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1228,8 +1228,9 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) flags |= __GFP_COMP; page = alloc_pages(flags, order); ret = page ? page_address(page) : NULL; - kmemleak_alloc(ret, size, 1, flags); ret = kasan_kmalloc_large(ret, size, flags); + /* As ret might get tagged, call kmemleak hook after KASAN. */ + kmemleak_alloc(ret, size, 1, flags); return ret; } EXPORT_SYMBOL(kmalloc_order); diff --git a/mm/slub.c b/mm/slub.c index 1e3d0ec4e200..dc777761b6b7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -249,7 +249,18 @@ static inline void *freelist_ptr(const struct kmem_cache *s, void *ptr, unsigned long ptr_addr) { #ifdef CONFIG_SLAB_FREELIST_HARDENED - return (void *)((unsigned long)ptr ^ s->random ^ ptr_addr); + /* + * When CONFIG_KASAN_SW_TAGS is enabled, ptr_addr might be tagged. + * Normally, this doesn't cause any issues, as both set_freepointer() + * and get_freepointer() are called with a pointer with the same tag. + * However, there are some issues with CONFIG_SLUB_DEBUG code. For + * example, when __free_slub() iterates over objects in a cache, it + * passes untagged pointers to check_object(). check_object() in turns + * calls get_freepointer() with an untagged pointer, which causes the + * freepointer to be restored incorrectly. + */ + return (void *)((unsigned long)ptr ^ s->random ^ + (unsigned long)kasan_reset_tag((void *)ptr_addr)); #else return ptr; #endif @@ -303,15 +314,10 @@ static inline void set_freepointer(struct kmem_cache *s, void *object, void *fp) __p < (__addr) + (__objects) * (__s)->size; \ __p += (__s)->size) -#define for_each_object_idx(__p, __idx, __s, __addr, __objects) \ - for (__p = fixup_red_left(__s, __addr), __idx = 1; \ - __idx <= __objects; \ - __p += (__s)->size, __idx++) - /* Determine object index from a given position */ static inline unsigned int slab_index(void *p, struct kmem_cache *s, void *addr) { - return (p - addr) / s->size; + return (kasan_reset_tag(p) - addr) / s->size; } static inline unsigned int order_objects(unsigned int order, unsigned int size) @@ -507,6 +513,7 @@ static inline int check_valid_pointer(struct kmem_cache *s, return 1; base = page_address(page); + object = kasan_reset_tag(object); object = restore_red_left(s, object); if (object < base || object >= base + page->objects * s->size || (object - base) % s->size) { @@ -1075,6 +1082,16 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page, init_tracking(s, object); } +static void setup_page_debug(struct kmem_cache *s, void *addr, int order) +{ + if (!(s->flags & SLAB_POISON)) + return; + + metadata_access_enable(); + memset(addr, POISON_INUSE, PAGE_SIZE << order); + metadata_access_disable(); +} + static inline int alloc_consistency_checks(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) @@ -1330,6 +1347,8 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, #else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) {} +static inline void setup_page_debug(struct kmem_cache *s, + void *addr, int order) {} static inline int alloc_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { return 0; } @@ -1374,8 +1393,10 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, */ static inline void *kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) { + ptr = kasan_kmalloc_large(ptr, size, flags); + /* As ptr might get tagged, call kmemleak hook after KASAN. */ kmemleak_alloc(ptr, size, 1, flags); - return kasan_kmalloc_large(ptr, size, flags); + return ptr; } static __always_inline void kfree_hook(void *x) @@ -1641,27 +1662,25 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node) if (page_is_pfmemalloc(page)) SetPageSlabPfmemalloc(page); + kasan_poison_slab(page); + start = page_address(page); - if (unlikely(s->flags & SLAB_POISON)) - memset(start, POISON_INUSE, PAGE_SIZE << order); - - kasan_poison_slab(page); + setup_page_debug(s, start, order); shuffle = shuffle_freelist(s, page); if (!shuffle) { - for_each_object_idx(p, idx, s, start, page->objects) { - if (likely(idx < page->objects)) { - next = p + s->size; - next = setup_object(s, page, next); - set_freepointer(s, p, next); - } else - set_freepointer(s, p, NULL); - } start = fixup_red_left(s, start); start = setup_object(s, page, start); page->freelist = start; + for (idx = 0, p = start; idx < page->objects - 1; idx++) { + next = p + s->size; + next = setup_object(s, page, next); + set_freepointer(s, p, next); + p = next; + } + set_freepointer(s, p, NULL); } page->inuse = page->objects; diff --git a/mm/swap.c b/mm/swap.c index 4929bc1be60e..4d7d37eb3c40 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -320,11 +320,6 @@ static inline void activate_page_drain(int cpu) { } -static bool need_activate_page_drain(int cpu) -{ - return false; -} - void activate_page(struct page *page) { struct zone *zone = page_zone(page); @@ -653,13 +648,15 @@ void lru_add_drain(void) put_cpu(); } +#ifdef CONFIG_SMP + +static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); } -static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); - /* * Doesn't need any cpu hotplug locking because we do rely on per-cpu * kworkers being shut down before our page_alloc_cpu_dead callback is @@ -702,6 +699,12 @@ void lru_add_drain_all(void) mutex_unlock(&lock); } +#else +void lru_add_drain_all(void) +{ + lru_add_drain(); +} +#endif /** * release_pages - batched put_page() diff --git a/mm/util.c b/mm/util.c index 1ea055138043..379319b1bcfd 100644 --- a/mm/util.c +++ b/mm/util.c @@ -150,7 +150,7 @@ void *memdup_user(const void __user *src, size_t len) { void *p; - p = kmalloc_track_caller(len, GFP_USER); + p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index fa2644d276ef..e31e1b20f7f4 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -13,27 +13,13 @@ #include <net/sock.h> #include <net/tcp.h> -static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx, - struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]) -{ - u32 ret; - - preempt_disable(); - rcu_read_lock(); - bpf_cgroup_storage_set(storage); - ret = BPF_PROG_RUN(prog, ctx); - rcu_read_unlock(); - preempt_enable(); - - return ret; -} - -static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret, - u32 *time) +static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, + u32 *retval, u32 *time) { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = { 0 }; enum bpf_cgroup_storage_type stype; u64 time_start, time_spent = 0; + int ret = 0; u32 i; for_each_cgroup_storage_type(stype) { @@ -48,25 +34,42 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *ret, if (!repeat) repeat = 1; + + rcu_read_lock(); + preempt_disable(); time_start = ktime_get_ns(); for (i = 0; i < repeat; i++) { - *ret = bpf_test_run_one(prog, ctx, storage); + bpf_cgroup_storage_set(storage); + *retval = BPF_PROG_RUN(prog, ctx); + + if (signal_pending(current)) { + ret = -EINTR; + break; + } + if (need_resched()) { - if (signal_pending(current)) - break; time_spent += ktime_get_ns() - time_start; + preempt_enable(); + rcu_read_unlock(); + cond_resched(); + + rcu_read_lock(); + preempt_disable(); time_start = ktime_get_ns(); } } time_spent += ktime_get_ns() - time_start; + preempt_enable(); + rcu_read_unlock(); + do_div(time_spent, repeat); *time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storage[stype]); - return 0; + return ret; } static int bpf_test_finish(const union bpf_attr *kattr, diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3aeff0895669..ac92b2eb32b1 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1204,14 +1204,7 @@ static void br_multicast_query_received(struct net_bridge *br, return; br_multicast_update_query_timer(br, query, max_delay); - - /* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules, - * the arrival port for IGMP Queries where the source address - * is 0.0.0.0 should not be added to router port list. - */ - if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) || - saddr->proto == htons(ETH_P_IPV6)) - br_multicast_mark_router(br, port); + br_multicast_mark_router(br, port); } static void br_ip4_multicast_query(struct net_bridge *br, diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3661cdd927f1..7e71b0df1fbc 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2058,6 +2058,8 @@ static int process_connect(struct ceph_connection *con) dout("process_connect on %p tag %d\n", con, (int)con->in_tag); if (con->auth) { + int len = le32_to_cpu(con->in_reply.authorizer_len); + /* * Any connection that defines ->get_authorizer() * should also define ->add_authorizer_challenge() and @@ -2067,8 +2069,7 @@ static int process_connect(struct ceph_connection *con) */ if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) { ret = con->ops->add_authorizer_challenge( - con, con->auth->authorizer_reply_buf, - le32_to_cpu(con->in_reply.authorizer_len)); + con, con->auth->authorizer_reply_buf, len); if (ret < 0) return ret; @@ -2078,10 +2079,12 @@ static int process_connect(struct ceph_connection *con) return 0; } - ret = con->ops->verify_authorizer_reply(con); - if (ret < 0) { - con->error_msg = "bad authorize reply"; - return ret; + if (len) { + ret = con->ops->verify_authorizer_reply(con); + if (ret < 0) { + con->error_msg = "bad authorize reply"; + return ret; + } } } diff --git a/net/compat.c b/net/compat.c index 959d1c51826d..3d348198004f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -388,8 +388,12 @@ static int __compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, unsigned int optlen) { int err; - struct socket *sock = sockfd_lookup(fd, &err); + struct socket *sock; + + if (optlen > INT_MAX) + return -EINVAL; + sock = sockfd_lookup(fd, &err); if (sock) { err = security_socket_setsockopt(sock, level, optname); if (err) { diff --git a/net/core/dev.c b/net/core/dev.c index 8e276e0192a1..5d03889502eb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8152,7 +8152,7 @@ static netdev_features_t netdev_sync_upper_features(struct net_device *lower, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { @@ -8172,7 +8172,7 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_features_t feature; int feature_bit; - for_each_netdev_feature(&upper_disables, feature_bit) { + for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", diff --git a/net/core/filter.c b/net/core/filter.c index 7a54dc11ac2d..f7d0004fc160 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2789,8 +2789,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2831,8 +2830,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) u32 off = skb_mac_header_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); @@ -2957,8 +2955,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_cow(skb, len_diff); @@ -2987,8 +2984,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) u32 off = skb_mac_header_len(skb) + bpf_skb_net_base_len(skb); int ret; - /* SCTP uses GSO_BY_FRAGS, thus cannot adjust it. */ - if (skb_is_gso(skb) && unlikely(skb_is_gso_sctp(skb))) + if (!skb_is_gso_tcp(skb)) return -ENOTSUPP; ret = skb_unclone(skb, GFP_ATOMIC); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 26d848484912..2415d9cb9b89 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -356,6 +356,8 @@ static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) */ void *netdev_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __netdev_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(netdev_alloc_frag); @@ -369,6 +371,8 @@ static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) void *napi_alloc_frag(unsigned int fragsz) { + fragsz = SKB_DATA_ALIGN(fragsz); + return __napi_alloc_frag(fragsz, GFP_ATOMIC); } EXPORT_SYMBOL(napi_alloc_frag); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index a1917025e155..410f19148106 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -612,8 +612,8 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, { struct device_node *ports, *port; struct dsa_port *dp; + int err = 0; u32 reg; - int err; ports = of_get_child_by_name(dn, "ports"); if (!ports) { @@ -624,19 +624,23 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds, for_each_available_child_of_node(ports, port) { err = of_property_read_u32(port, "reg", ®); if (err) - return err; + goto out_put_node; - if (reg >= ds->num_ports) - return -EINVAL; + if (reg >= ds->num_ports) { + err = -EINVAL; + goto out_put_node; + } dp = &ds->ports[reg]; err = dsa_port_parse_of(dp, port); if (err) - return err; + goto out_put_node; } - return 0; +out_put_node: + of_node_put(ports); + return err; } static int dsa_switch_parse_member_of(struct dsa_switch *ds, diff --git a/net/dsa/port.c b/net/dsa/port.c index 2d7e01b23572..c2261697ee83 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -69,7 +69,6 @@ static void dsa_port_set_state_now(struct dsa_port *dp, u8 state) int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) { - u8 stp_state = dp->bridge_dev ? BR_STATE_BLOCKING : BR_STATE_FORWARDING; struct dsa_switch *ds = dp->ds; int port = dp->index; int err; @@ -80,7 +79,8 @@ int dsa_port_enable(struct dsa_port *dp, struct phy_device *phy) return err; } - dsa_port_set_state_now(dp, stp_state); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_FORWARDING); return 0; } @@ -90,7 +90,8 @@ void dsa_port_disable(struct dsa_port *dp, struct phy_device *phy) struct dsa_switch *ds = dp->ds; int port = dp->index; - dsa_port_set_state_now(dp, BR_STATE_DISABLED); + if (!dp->bridge_dev) + dsa_port_set_state_now(dp, BR_STATE_DISABLED); if (ds->ops->port_disable) ds->ops->port_disable(ds, port, phy); @@ -291,6 +292,7 @@ static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) return ERR_PTR(-EPROBE_DEFER); } + of_node_put(phy_dn); return phydev; } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 777fa3b7fb13..f0165c5f376b 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -667,7 +667,8 @@ static int cipso_v4_map_lvl_valid(const struct cipso_v4_doi *doi_def, u8 level) case CIPSO_V4_MAP_PASS: return 0; case CIPSO_V4_MAP_TRANS: - if (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL) + if ((level < doi_def->map.std->lvl.cipso_size) && + (doi_def->map.std->lvl.cipso[level] < CIPSO_V4_INV_LVL)) return 0; break; } @@ -1735,13 +1736,26 @@ validate_return: */ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { + unsigned char optbuf[sizeof(struct ip_options) + 40]; + struct ip_options *opt = (struct ip_options *)optbuf; + if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; + /* + * We might be called above the IP layer, + * so we can not use icmp_send and IPCB here. + */ + + memset(opt, 0, sizeof(struct ip_options)); + opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); + if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + return; + if (gateway) - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_NET_ANO, 0, opt); else - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0); + __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_ANO, 0, opt); } /** diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5459f41fc26f..10e809b296ec 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -328,7 +328,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fe4f6a624238..ed14ec245584 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -710,6 +710,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_GATEWAY: cfg->fc_gw = nla_get_be32(attr); break; + case RTA_VIA: + NL_SET_ERR_MSG(extack, "IPv4 does not support RTA_VIA attribute"); + err = -EINVAL; + goto errout; case RTA_PRIORITY: cfg->fc_priority = nla_get_u32(attr); break; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 065997f414e6..3f24414150e2 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -570,7 +570,8 @@ relookup_failed: * MUST reply to only the first fragment. */ -void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) +void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, + const struct ip_options *opt) { struct iphdr *iph; int room; @@ -691,7 +692,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) iph->tos; mark = IP4_REPLY_MARK(net, skb_in->mark); - if (ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in)) + if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt)) goto out_unlock; @@ -742,7 +743,7 @@ out_bh_enable: local_bh_enable(); out:; } -EXPORT_SYMBOL(icmp_send); +EXPORT_SYMBOL(__icmp_send); static void icmp_socket_deliver(struct sk_buff *skb, u32 info) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 3978f807fa8b..6ae89f2b541b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1457,9 +1457,23 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((t->erspan_ver == 1 || t->erspan_ver == 2) && - !t->collect_md) - o_flags |= TUNNEL_KEY; + if (t->erspan_ver == 1 || t->erspan_ver == 2) { + if (!t->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) + goto nla_put_failure; + + if (t->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -1495,19 +1509,6 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) - goto nla_put_failure; - - if (t->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) - goto nla_put_failure; - } else if (t->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 51d8efba6de2..1f4737b77067 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -307,11 +307,10 @@ drop: } static int ip_rcv_finish_core(struct net *net, struct sock *sk, - struct sk_buff *skb) + struct sk_buff *skb, struct net_device *dev) { const struct iphdr *iph = ip_hdr(skb); int (*edemux)(struct sk_buff *skb); - struct net_device *dev = skb->dev; struct rtable *rt; int err; @@ -400,6 +399,7 @@ drop_error: static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { + struct net_device *dev = skb->dev; int ret; /* if ingress device is enslaved to an L3 master device pass the @@ -409,7 +409,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) if (!skb) return NET_RX_SUCCESS; - ret = ip_rcv_finish_core(net, sk, skb); + ret = ip_rcv_finish_core(net, sk, skb, dev); if (ret != NET_RX_DROP) ret = dst_input(skb); return ret; @@ -545,6 +545,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, INIT_LIST_HEAD(&sublist); list_for_each_entry_safe(skb, next, head, list) { + struct net_device *dev = skb->dev; struct dst_entry *dst; skb_list_del_init(skb); @@ -554,7 +555,7 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, skb = l3mdev_ip_rcv(skb); if (!skb) continue; - if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP) + if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP) continue; dst = skb_dst(skb); diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ed194d46c00e..32a35043c9f5 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -251,8 +251,9 @@ static void spec_dst_fill(__be32 *spec_dst, struct sk_buff *skb) * If opt == NULL, then skb->data should point to IP header. */ -int ip_options_compile(struct net *net, - struct ip_options *opt, struct sk_buff *skb) +int __ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb, + __be32 *info) { __be32 spec_dst = htonl(INADDR_ANY); unsigned char *pp_ptr = NULL; @@ -468,11 +469,22 @@ eol: return 0; error: - if (skb) { - icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24)); - } + if (info) + *info = htonl((pp_ptr-iph)<<24); return -EINVAL; } + +int ip_options_compile(struct net *net, + struct ip_options *opt, struct sk_buff *skb) +{ + int ret; + __be32 info; + + ret = __ip_options_compile(net, opt, skb, &info); + if (ret != 0 && skb) + icmp_send(skb, ICMP_PARAMETERPROB, 0, info); + return ret; +} EXPORT_SYMBOL(ip_options_compile); /* diff --git a/net/ipv4/netlink.c b/net/ipv4/netlink.c index f86bb4f06609..d8e3a1fb8e82 100644 --- a/net/ipv4/netlink.c +++ b/net/ipv4/netlink.c @@ -3,9 +3,10 @@ #include <linux/types.h> #include <net/net_namespace.h> #include <net/netlink.h> +#include <linux/in6.h> #include <net/ip.h> -int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, +int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, u8 family, struct netlink_ext_ack *extack) { *ip_proto = nla_get_u8(attr); @@ -13,11 +14,19 @@ int rtm_getroute_parse_ip_proto(struct nlattr *attr, u8 *ip_proto, switch (*ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: + return 0; case IPPROTO_ICMP: + if (family != AF_INET) + break; + return 0; +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: + if (family != AF_INET6) + break; return 0; - default: - NL_SET_ERR_MSG(extack, "Unsupported ip proto"); - return -EOPNOTSUPP; +#endif } + NL_SET_ERR_MSG(extack, "Unsupported ip proto"); + return -EOPNOTSUPP; } EXPORT_SYMBOL_GPL(rtm_getroute_parse_ip_proto); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5163b64f8fb3..7bb9128c8363 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2803,7 +2803,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], - &ip_proto, extack); + &ip_proto, AF_INET, extack); if (err) return err; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2079145a3b7c..cf3c5095c10e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2528,6 +2528,7 @@ void tcp_write_queue_purge(struct sock *sk) sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_sk(sk)->packets_out = 0; + inet_csk(sk)->icsk_backoff = 0; } int tcp_disconnect(struct sock *sk, int flags) @@ -2576,7 +2577,6 @@ int tcp_disconnect(struct sock *sk, int flags) tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; - icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index efc6fef692ff..ec3cea9d6828 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -536,12 +536,15 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (sock_owned_by_user(sk)) break; + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) + break; + icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); - skb = tcp_rtx_queue_head(sk); tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 730bc44dbad9..ccc78f3a4b60 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2347,6 +2347,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, /* "skb_mstamp_ns" is used as a start point for the retransmit timer */ skb->skb_mstamp_ns = tp->tcp_wstamp_ns = tp->tcp_clock_cache; list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); + tcp_init_tso_segs(skb, mss_now); goto repair; /* Skip network transmission */ } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 5c3cd5d84a6f..372fdc5381a9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -562,10 +562,12 @@ static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info) for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, u32 info); + const struct ip_tunnel_encap_ops *encap; - if (!iptun_encaps[i]) + encap = rcu_dereference(iptun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(iptun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, info)) return 0; } diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 5afe9f83374d..239d4a65ad6e 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -296,7 +296,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb->len += tailen; skb->data_len += tailen; skb->truesize += tailen; - if (sk) + if (sk && sk_fullsock(sk)) refcount_add(tailen, &sk->sk_wmem_alloc); goto out; diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c index b858bd5280bf..867474abe269 100644 --- a/net/ipv6/fou6.c +++ b/net/ipv6/fou6.c @@ -72,7 +72,7 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, static int gue6_err_proto_handler(int proto, struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { const struct inet6_protocol *ipprot; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 801a9a0c217e..26f25b6e2833 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1719,6 +1719,27 @@ static int ip6erspan_tap_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static void ip6erspan_set_version(struct nlattr *data[], + struct __ip6_tnl_parm *parms) +{ + if (!data) + return; + + parms->erspan_ver = 1; + if (data[IFLA_GRE_ERSPAN_VER]) + parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); + + if (parms->erspan_ver == 1) { + if (data[IFLA_GRE_ERSPAN_INDEX]) + parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); + } else if (parms->erspan_ver == 2) { + if (data[IFLA_GRE_ERSPAN_DIR]) + parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); + if (data[IFLA_GRE_ERSPAN_HWID]) + parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); + } +} + static void ip6gre_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { @@ -1767,20 +1788,6 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; - - parms->erspan_ver = 1; - if (data[IFLA_GRE_ERSPAN_VER]) - parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); - - if (parms->erspan_ver == 1) { - if (data[IFLA_GRE_ERSPAN_INDEX]) - parms->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); - } else if (parms->erspan_ver == 2) { - if (data[IFLA_GRE_ERSPAN_DIR]) - parms->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); - if (data[IFLA_GRE_ERSPAN_HWID]) - parms->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); - } } static int ip6gre_tap_init(struct net_device *dev) @@ -2100,9 +2107,23 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) struct __ip6_tnl_parm *p = &t->parms; __be16 o_flags = p->o_flags; - if ((p->erspan_ver == 1 || p->erspan_ver == 2) && - !p->collect_md) - o_flags |= TUNNEL_KEY; + if (p->erspan_ver == 1 || p->erspan_ver == 2) { + if (!p->collect_md) + o_flags |= TUNNEL_KEY; + + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) + goto nla_put_failure; + + if (p->erspan_ver == 1) { + if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + goto nla_put_failure; + } else { + if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) + goto nla_put_failure; + if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) + goto nla_put_failure; + } + } if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, @@ -2117,8 +2138,7 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) nla_put_u8(skb, IFLA_GRE_ENCAP_LIMIT, p->encap_limit) || nla_put_be32(skb, IFLA_GRE_FLOWINFO, p->flowinfo) || nla_put_u32(skb, IFLA_GRE_FLAGS, p->flags) || - nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark) || - nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) + nla_put_u32(skb, IFLA_GRE_FWMARK, p->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, @@ -2136,19 +2156,6 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, p->erspan_ver)) - goto nla_put_failure; - - if (p->erspan_ver == 1) { - if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, p->index)) - goto nla_put_failure; - } else if (p->erspan_ver == 2) { - if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, p->dir)) - goto nla_put_failure; - if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, p->hwid)) - goto nla_put_failure; - } - return 0; nla_put_failure: @@ -2203,6 +2210,7 @@ static int ip6erspan_newlink(struct net *src_net, struct net_device *dev, int err; ip6gre_netlink_parms(data, &nt->parms); + ip6erspan_set_version(data, &nt->parms); ign = net_generic(net, ip6gre_net_id); if (nt->parms.collect_md) { @@ -2248,6 +2256,7 @@ static int ip6erspan_changelink(struct net_device *dev, struct nlattr *tb[], if (IS_ERR(t)) return PTR_ERR(t); + ip6erspan_set_version(data, &p); ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); ip6erspan_tnl_change(t, &p, !tb[IFLA_MTU]); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 964491cf3672..8dad1d690b78 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1274,18 +1274,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock); static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { + struct fib6_info *from; struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); + net->ipv6.rt6_stats->fib_rt_cache--; + + /* purge completely the exception to allow releasing the held resources: + * some [sk] cache may keep the dst around for unlimited time + */ + from = rcu_dereference_protected(rt6_ex->rt6i->from, + lockdep_is_held(&rt6_exception_lock)); + rcu_assign_pointer(rt6_ex->rt6i->from, NULL); + fib6_info_release(from); + dst_dev_put(&rt6_ex->rt6i->dst); + hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; - net->ipv6.rt6_stats->fib_rt_cache--; } /* Remove oldest rt6_ex in bucket and free the memory @@ -1599,15 +1610,15 @@ static int rt6_remove_exception_rt(struct rt6_info *rt) static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct fib6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; - - if (!from || - !(rt->rt6i_flags & RTF_CACHE)) - return; + struct fib6_info *from; rcu_read_lock(); + from = rcu_dereference(rt->from); + if (!from || !(rt->rt6i_flags & RTF_CACHE)) + goto unlock; + bucket = rcu_dereference(from->rt6i_exception_bucket); #ifdef CONFIG_IPV6_SUBTREES @@ -1626,6 +1637,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) if (rt6_ex) rt6_ex->stamp = jiffies; +unlock: rcu_read_unlock(); } @@ -2742,20 +2754,24 @@ static int ip6_route_check_nh_onlink(struct net *net, u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT; + struct fib6_info *from; struct rt6_info *grt; int err; err = 0; grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0); if (grt) { + rcu_read_lock(); + from = rcu_dereference(grt->from); if (!grt->dst.error && /* ignore match if it is the default route */ - grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) && + from && !ipv6_addr_any(&from->fib6_dst.addr) && (grt->rt6i_flags & flags || dev != grt->dst.dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } + rcu_read_unlock(); ip6_rt_put(grt); } @@ -4166,6 +4182,10 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } + if (tb[RTA_VIA]) { + NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); + goto errout; + } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; @@ -4649,7 +4669,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; - rtm->rtm_table = table; + rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; @@ -4873,7 +4893,8 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], - &fl6.flowi6_proto, extack); + &fl6.flowi6_proto, AF_INET6, + extack); if (err) goto errout; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index e8a1dabef803..09e440e8dfae 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1873,6 +1873,7 @@ static int __net_init sit_init_net(struct net *net) err_reg_dev: ipip6_dev_free(sitn->fb_tunnel_dev); + free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 2596ffdeebea..b444483cdb2b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -288,8 +288,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int peeked, peeking, off; int err; int is_udplite = IS_UDPLITE(sk); + struct udp_mib __percpu *mib; bool checksum_valid = false; - struct udp_mib *mib; int is_udp4; if (flags & MSG_ERRQUEUE) @@ -420,17 +420,19 @@ EXPORT_SYMBOL(udpv6_encap_enable); */ static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info) + u8 type, u8 code, int offset, __be32 info) { int i; for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, - u8 type, u8 code, int offset, u32 info); + u8 type, u8 code, int offset, __be32 info); + const struct ip6_tnl_encap_ops *encap; - if (!ip6tun_encaps[i]) + encap = rcu_dereference(ip6tun_encaps[i]); + if (!encap) continue; - handler = rcu_dereference(ip6tun_encaps[i]->err_handler); + handler = encap->err_handler; if (handler && !handler(skb, opt, type, code, offset, info)) return 0; } diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index f5b4febeaa25..bc65db782bfb 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -344,8 +344,8 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net) struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net); unsigned int i; - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); xfrm_flush_gc(); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++) WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i])); diff --git a/net/key/af_key.c b/net/key/af_key.c index 655c787f9d54..5651c29cb5bd 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -196,30 +196,22 @@ static int pfkey_release(struct socket *sock) return 0; } -static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, - gfp_t allocation, struct sock *sk) +static int pfkey_broadcast_one(struct sk_buff *skb, gfp_t allocation, + struct sock *sk) { int err = -ENOBUFS; - sock_hold(sk); - if (*skb2 == NULL) { - if (refcount_read(&skb->users) != 1) { - *skb2 = skb_clone(skb, allocation); - } else { - *skb2 = skb; - refcount_inc(&skb->users); - } - } - if (*skb2 != NULL) { - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) { - skb_set_owner_r(*skb2, sk); - skb_queue_tail(&sk->sk_receive_queue, *skb2); - sk->sk_data_ready(sk); - *skb2 = NULL; - err = 0; - } + if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return err; + + skb = skb_clone(skb, allocation); + + if (skb) { + skb_set_owner_r(skb, sk); + skb_queue_tail(&sk->sk_receive_queue, skb); + sk->sk_data_ready(sk); + err = 0; } - sock_put(sk); return err; } @@ -234,7 +226,6 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, { struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); struct sock *sk; - struct sk_buff *skb2 = NULL; int err = -ESRCH; /* XXX Do we need something like netlink_overrun? I think @@ -253,7 +244,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, * socket. */ if (pfk->promisc) - pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* the exact target will be processed later */ if (sk == one_sk) @@ -268,7 +259,7 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, continue; } - err2 = pfkey_broadcast_one(skb, &skb2, GFP_ATOMIC, sk); + err2 = pfkey_broadcast_one(skb, GFP_ATOMIC, sk); /* Error is cleared after successful sending to at least one * registered KM */ @@ -278,9 +269,8 @@ static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); + err = pfkey_broadcast_one(skb, allocation, one_sk); - kfree_skb(skb2); kfree_skb(skb); return err; } @@ -1783,7 +1773,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m if (proto == 0) return -EINVAL; - err = xfrm_state_flush(net, proto, true); + err = xfrm_state_flush(net, proto, true, false); err2 = unicast_flush_resp(sk, hdr); if (err || err2) { if (err == -ESRCH) /* empty table - go quietly */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2493c74c2d37..96496b2c1670 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -941,6 +941,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER; int err; + int prev_beacon_int; old = sdata_dereference(sdata->u.ap.beacon, sdata); if (old) @@ -963,6 +964,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->needed_rx_chains = sdata->local->rx_chains; + prev_beacon_int = sdata->vif.bss_conf.beacon_int; sdata->vif.bss_conf.beacon_int = params->beacon_interval; if (params->he_cap) @@ -974,8 +976,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, if (!err) ieee80211_vif_copy_chanctx_to_vlans(sdata, false); mutex_unlock(&local->mtx); - if (err) + if (err) { + sdata->vif.bss_conf.beacon_int = prev_beacon_int; return err; + } /* * Apply control port protocol, this allows us to diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 87a729926734..977dea436ee8 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -615,13 +615,13 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, * We need a bit of data queued to build aggregates properly, so * instruct the TCP stack to allow more than a single ms of data * to be queued in the stack. The value is a bit-shift of 1 - * second, so 8 is ~4ms of queued data. Only affects local TCP + * second, so 7 is ~8ms of queued data. Only affects local TCP * sockets. * This is the default, anyhow - drivers may need to override it * for local reasons (longer buffers, longer completion time, or * similar). */ - local->hw.tx_sk_pacing_shift = 8; + local->hw.tx_sk_pacing_shift = 7; /* set up some defaults */ local->hw.queues = 1; diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index cad6592c52a1..2ec7011a4d07 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -70,6 +70,7 @@ enum mesh_deferred_task_flags { * @dst: mesh path destination mac address * @mpp: mesh proxy mac address * @rhash: rhashtable list pointer + * @walk_list: linked list containing all mesh_path objects. * @gate_list: list pointer for known gates list * @sdata: mesh subif * @next_hop: mesh neighbor to which frames for this destination will be @@ -105,6 +106,7 @@ struct mesh_path { u8 dst[ETH_ALEN]; u8 mpp[ETH_ALEN]; /* used for MPP or MAP */ struct rhash_head rhash; + struct hlist_node walk_list; struct hlist_node gate_list; struct ieee80211_sub_if_data *sdata; struct sta_info __rcu *next_hop; @@ -133,12 +135,16 @@ struct mesh_path { * gate's mpath may or may not be resolved and active. * @gates_lock: protects updates to known_gates * @rhead: the rhashtable containing struct mesh_paths, keyed by dest addr + * @walk_head: linked list containging all mesh_path objects + * @walk_lock: lock protecting walk_head * @entries: number of entries in the table */ struct mesh_table { struct hlist_head known_gates; spinlock_t gates_lock; struct rhashtable rhead; + struct hlist_head walk_head; + spinlock_t walk_lock; atomic_t entries; /* Up to MAX_MESH_NEIGHBOURS */ }; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index a5125624a76d..88a6d5e18ccc 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -59,8 +59,10 @@ static struct mesh_table *mesh_table_alloc(void) return NULL; INIT_HLIST_HEAD(&newtbl->known_gates); + INIT_HLIST_HEAD(&newtbl->walk_head); atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); + spin_lock_init(&newtbl->walk_lock); return newtbl; } @@ -249,28 +251,15 @@ mpp_path_lookup(struct ieee80211_sub_if_data *sdata, const u8 *dst) static struct mesh_path * __mesh_path_lookup_by_idx(struct mesh_table *tbl, int idx) { - int i = 0, ret; - struct mesh_path *mpath = NULL; - struct rhashtable_iter iter; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return NULL; - - rhashtable_walk_start(&iter); + int i = 0; + struct mesh_path *mpath; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (i++ == idx) break; } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); - if (IS_ERR(mpath) || !mpath) + if (!mpath) return NULL; if (mpath_expired(mpath)) { @@ -432,6 +421,7 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, return ERR_PTR(-ENOMEM); tbl = sdata->u.mesh.mesh_paths; + spin_lock_bh(&tbl->walk_lock); do { ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, @@ -441,20 +431,20 @@ struct mesh_path *mesh_path_add(struct ieee80211_sub_if_data *sdata, mpath = rhashtable_lookup_fast(&tbl->rhead, dst, mesh_rht_params); - + else if (!ret) + hlist_add_head(&new_mpath->walk_list, &tbl->walk_head); } while (unlikely(ret == -EEXIST && !mpath)); + spin_unlock_bh(&tbl->walk_lock); - if (ret && ret != -EEXIST) - return ERR_PTR(ret); - - /* At this point either new_mpath was added, or we found a - * matching entry already in the table; in the latter case - * free the unnecessary new entry. - */ - if (ret == -EEXIST) { + if (ret) { kfree(new_mpath); + + if (ret != -EEXIST) + return ERR_PTR(ret); + new_mpath = mpath; } + sdata->u.mesh.mesh_paths_generation++; return new_mpath; } @@ -480,9 +470,17 @@ int mpp_path_add(struct ieee80211_sub_if_data *sdata, memcpy(new_mpath->mpp, mpp, ETH_ALEN); tbl = sdata->u.mesh.mpp_paths; + + spin_lock_bh(&tbl->walk_lock); ret = rhashtable_lookup_insert_fast(&tbl->rhead, &new_mpath->rhash, mesh_rht_params); + if (!ret) + hlist_add_head_rcu(&new_mpath->walk_list, &tbl->walk_head); + spin_unlock_bh(&tbl->walk_lock); + + if (ret) + kfree(new_mpath); sdata->u.mesh.mpp_paths_generation++; return ret; @@ -503,20 +501,9 @@ void mesh_plink_broken(struct sta_info *sta) struct mesh_table *tbl = sdata->u.mesh.mesh_paths; static const u8 bcast[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + rcu_read_lock(); + hlist_for_each_entry_rcu(mpath, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta && mpath->flags & MESH_PATH_ACTIVE && !(mpath->flags & MESH_PATH_FIXED)) { @@ -530,8 +517,7 @@ void mesh_plink_broken(struct sta_info *sta) WLAN_REASON_MESH_PATH_DEST_UNREACHABLE, bcast); } } - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + rcu_read_unlock(); } static void mesh_path_free_rcu(struct mesh_table *tbl, @@ -551,6 +537,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, static void __mesh_path_del(struct mesh_table *tbl, struct mesh_path *mpath) { + hlist_del_rcu(&mpath->walk_list); rhashtable_remove_fast(&tbl->rhead, &mpath->rhash, mesh_rht_params); mesh_path_free_rcu(tbl, mpath); } @@ -571,27 +558,14 @@ void mesh_path_flush_by_nexthop(struct sta_info *sta) struct ieee80211_sub_if_data *sdata = sta->sdata; struct mesh_table *tbl = sdata->u.mesh.mesh_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (rcu_access_pointer(mpath->next_hop) == sta) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, @@ -599,51 +573,26 @@ static void mpp_flush_by_proxy(struct ieee80211_sub_if_data *sdata, { struct mesh_table *tbl = sdata->u.mesh.mpp_paths; struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + struct hlist_node *n; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if (ether_addr_equal(mpath->mpp, proxy)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } static void table_flush_by_iface(struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; - - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_ATOMIC); - if (ret) - return; - - rhashtable_walk_start(&iter); + struct hlist_node *n; - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } /** @@ -675,15 +624,15 @@ static int table_path_del(struct mesh_table *tbl, { struct mesh_path *mpath; - rcu_read_lock(); + spin_lock_bh(&tbl->walk_lock); mpath = rhashtable_lookup_fast(&tbl->rhead, addr, mesh_rht_params); if (!mpath) { - rcu_read_unlock(); + spin_unlock_bh(&tbl->walk_lock); return -ENXIO; } __mesh_path_del(tbl, mpath); - rcu_read_unlock(); + spin_unlock_bh(&tbl->walk_lock); return 0; } @@ -854,28 +803,16 @@ void mesh_path_tbl_expire(struct ieee80211_sub_if_data *sdata, struct mesh_table *tbl) { struct mesh_path *mpath; - struct rhashtable_iter iter; - int ret; + struct hlist_node *n; - ret = rhashtable_walk_init(&tbl->rhead, &iter, GFP_KERNEL); - if (ret) - return; - - rhashtable_walk_start(&iter); - - while ((mpath = rhashtable_walk_next(&iter))) { - if (IS_ERR(mpath) && PTR_ERR(mpath) == -EAGAIN) - continue; - if (IS_ERR(mpath)) - break; + spin_lock_bh(&tbl->walk_lock); + hlist_for_each_entry_safe(mpath, n, &tbl->walk_head, walk_list) { if ((!(mpath->flags & MESH_PATH_RESOLVING)) && (!(mpath->flags & MESH_PATH_FIXED)) && time_after(jiffies, mpath->exp_time + MESH_PATH_EXPIRE)) __mesh_path_del(tbl, mpath); } - - rhashtable_walk_stop(&iter); - rhashtable_walk_exit(&iter); + spin_unlock_bh(&tbl->walk_lock); } void mesh_path_expire(struct ieee80211_sub_if_data *sdata) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index bb4d71efb6fb..c2a6da5d80da 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2644,6 +2644,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; u16 ac, q, hdrlen; + int tailroom = 0; hdr = (struct ieee80211_hdr *) skb->data; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -2732,8 +2733,12 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) if (!ifmsh->mshcfg.dot11MeshForwarding) goto out; + if (sdata->crypto_tx_tailroom_needed_cnt) + tailroom = IEEE80211_ENCRYPT_TAILROOM; + fwd_skb = skb_copy_expand(skb, local->tx_headroom + - sdata->encrypt_headroom, 0, GFP_ATOMIC); + sdata->encrypt_headroom, + tailroom, GFP_ATOMIC); if (!fwd_skb) goto out; diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7d55d4c04088..fa763e2e50ec 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1838,6 +1838,9 @@ static int rtm_to_route_config(struct sk_buff *skb, goto errout; break; } + case RTA_GATEWAY: + NL_SET_ERR_MSG(extack, "MPLS does not support RTA_GATEWAY attribute"); + goto errout; case RTA_VIA: { if (nla_get_via(nla, &cfg->rc_via_alen, diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 86afacb07e5f..ac8d848d7624 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -896,12 +896,13 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, { struct ip_vs_dest *dest; unsigned int atype, i; - int ret = 0; EnterFunction(2); #ifdef CONFIG_IP_VS_IPV6 if (udest->af == AF_INET6) { + int ret; + atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5a92f23f179f..4893f248dfdc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -313,6 +313,9 @@ static int nft_delrule_by_chain(struct nft_ctx *ctx) int err; list_for_each_entry(rule, &ctx->chain->rules, list) { + if (!nft_is_active_next(ctx->net, rule)) + continue; + err = nft_delrule(ctx, rule); if (err < 0) return err; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index ea7c67050792..ee3e5b6471a6 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -903,7 +903,8 @@ int netlbl_bitmap_walk(const unsigned char *bitmap, u32 bitmap_len, (state == 0 && (byte & bitmask) == 0)) return bit_spot; - bit_spot++; + if (++bit_spot >= bitmap_len) + return -1; bitmask >>= 1; if (bitmask == 0) { byte = bitmap[++byte_offset]; diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 6a196e438b6c..d1fc019e932e 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -419,6 +419,10 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) sock->service_name, sock->service_name_len, &service_name_tlv_length); + if (!service_name_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += service_name_tlv_length; } @@ -429,9 +433,17 @@ int nfc_llcp_send_connect(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; pr_debug("SKB size %d SN length %zu\n", size, sock->service_name_len); @@ -484,9 +496,17 @@ int nfc_llcp_send_cc(struct nfc_llcp_sock *sock) miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&miux, 0, &miux_tlv_length); + if (!miux_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += miux_tlv_length; rw_tlv = nfc_llcp_build_tlv(LLCP_TLV_RW, &rw, 0, &rw_tlv_length); + if (!rw_tlv) { + err = -ENOMEM; + goto error_tlv; + } size += rw_tlv_length; skb = llcp_allocate_pdu(sock, LLCP_PDU_CC, size); diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index ef4026a23e80..4fa015208aab 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -532,10 +532,10 @@ static u8 nfc_llcp_reserve_sdp_ssap(struct nfc_llcp_local *local) static int nfc_llcp_build_gb(struct nfc_llcp_local *local) { - u8 *gb_cur, *version_tlv, version, version_length; - u8 *lto_tlv, lto_length; - u8 *wks_tlv, wks_length; - u8 *miux_tlv, miux_length; + u8 *gb_cur, version, version_length; + u8 lto_length, wks_length, miux_length; + u8 *version_tlv = NULL, *lto_tlv = NULL, + *wks_tlv = NULL, *miux_tlv = NULL; __be16 wks = cpu_to_be16(local->local_wks); u8 gb_len = 0; int ret = 0; @@ -543,17 +543,33 @@ static int nfc_llcp_build_gb(struct nfc_llcp_local *local) version = LLCP_VERSION_11; version_tlv = nfc_llcp_build_tlv(LLCP_TLV_VERSION, &version, 1, &version_length); + if (!version_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += version_length; lto_tlv = nfc_llcp_build_tlv(LLCP_TLV_LTO, &local->lto, 1, <o_length); + if (!lto_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += lto_length; pr_debug("Local wks 0x%lx\n", local->local_wks); wks_tlv = nfc_llcp_build_tlv(LLCP_TLV_WKS, (u8 *)&wks, 2, &wks_length); + if (!wks_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += wks_length; miux_tlv = nfc_llcp_build_tlv(LLCP_TLV_MIUX, (u8 *)&local->miux, 0, &miux_length); + if (!miux_tlv) { + ret = -ENOMEM; + goto out; + } gb_len += miux_length; gb_len += ARRAY_SIZE(llcp_magic); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 9fc76b19cd3c..db3473540303 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -132,7 +132,7 @@ static int pep_indicate(struct sock *sk, u8 id, u8 code, ph->utid = 0; ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -153,7 +153,7 @@ static int pipe_handler_request(struct sock *sk, u8 id, u8 code, ph->utid = id; /* whatever */ ph->message_id = id; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = code; + ph->error_code = code; return pn_skb_send(sk, skb, NULL); } @@ -208,7 +208,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, struct pnpipehdr *ph; struct sockaddr_pn dst; u8 data[4] = { - oph->data[0], /* PEP type */ + oph->pep_type, /* PEP type */ code, /* error code, at an unusual offset */ PAD, PAD, }; @@ -221,7 +221,7 @@ static int pep_ctrlreq_error(struct sock *sk, struct sk_buff *oskb, u8 code, ph->utid = oph->utid; ph->message_id = PNS_PEP_CTRL_RESP; ph->pipe_handle = oph->pipe_handle; - ph->data[0] = oph->data[1]; /* CTRL id */ + ph->data0 = oph->data[0]; /* CTRL id */ pn_skb_get_src_sockaddr(oskb, &dst); return pn_skb_send(sk, skb, &dst); @@ -272,17 +272,17 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) return -EINVAL; hdr = pnp_hdr(skb); - if (hdr->data[0] != PN_PEP_TYPE_COMMON) { + if (hdr->pep_type != PN_PEP_TYPE_COMMON) { net_dbg_ratelimited("Phonet unknown PEP type: %u\n", - (unsigned int)hdr->data[0]); + (unsigned int)hdr->pep_type); return -EOPNOTSUPP; } - switch (hdr->data[1]) { + switch (hdr->data[0]) { case PN_PEP_IND_FLOW_CONTROL: switch (pn->tx_fc) { case PN_LEGACY_FLOW_CONTROL: - switch (hdr->data[4]) { + switch (hdr->data[3]) { case PEP_IND_BUSY: atomic_set(&pn->tx_credits, 0); break; @@ -292,7 +292,7 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) } break; case PN_ONE_CREDIT_FLOW_CONTROL: - if (hdr->data[4] == PEP_IND_READY) + if (hdr->data[3] == PEP_IND_READY) atomic_set(&pn->tx_credits, wake = 1); break; } @@ -301,12 +301,12 @@ static int pipe_rcv_status(struct sock *sk, struct sk_buff *skb) case PN_PEP_IND_ID_MCFC_GRANT_CREDITS: if (pn->tx_fc != PN_MULTI_CREDIT_FLOW_CONTROL) break; - atomic_add(wake = hdr->data[4], &pn->tx_credits); + atomic_add(wake = hdr->data[3], &pn->tx_credits); break; default: net_dbg_ratelimited("Phonet unknown PEP indication: %u\n", - (unsigned int)hdr->data[1]); + (unsigned int)hdr->data[0]); return -EOPNOTSUPP; } if (wake) @@ -318,7 +318,7 @@ static int pipe_rcv_created(struct sock *sk, struct sk_buff *skb) { struct pep_sock *pn = pep_sk(sk); struct pnpipehdr *hdr = pnp_hdr(skb); - u8 n_sb = hdr->data[0]; + u8 n_sb = hdr->data0; pn->rx_fc = pn->tx_fc = PN_LEGACY_FLOW_CONTROL; __skb_pull(skb, sizeof(*hdr)); @@ -506,7 +506,7 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb) return -ECONNREFUSED; /* Parse sub-blocks */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[6], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -739,7 +739,7 @@ static int pipe_do_remove(struct sock *sk) ph->utid = 0; ph->message_id = PNS_PIPE_REMOVE_REQ; ph->pipe_handle = pn->pipe_handle; - ph->data[0] = PAD; + ph->data0 = PAD; return pn_skb_send(sk, skb, NULL); } @@ -817,7 +817,7 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp, peer_type = hdr->other_pep_type << 8; /* Parse sub-blocks (options) */ - n_sb = hdr->data[4]; + n_sb = hdr->data[3]; while (n_sb > 0) { u8 type, buf[1], len = sizeof(buf); const u8 *data = pep_get_sb(skb, &type, &len, buf); @@ -1109,7 +1109,7 @@ static int pipe_skb_send(struct sock *sk, struct sk_buff *skb) ph->utid = 0; if (pn->aligned) { ph->message_id = PNS_PIPE_ALIGNED_DATA; - ph->data[0] = 0; /* padding */ + ph->data0 = 0; /* padding */ } else ph->message_id = PNS_PIPE_DATA; ph->pipe_handle = pn->pipe_handle; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8af6c11d2482..faa1addf89b3 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -199,8 +199,7 @@ err3: err2: kfree(tname); err1: - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); + tcf_idr_release(*a, bind); return err; } diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 64dba3708fce..cfceed28c333 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -189,8 +189,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - if (ret == ACT_P_CREATED) - tcf_idr_release(*a, bind); + tcf_idr_release(*a, bind); return -ENOMEM; } diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 8b43fe0130f7..3f943de9a2c9 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -377,7 +377,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; release_tun_meta: - dst_release(&metadata->dst); + if (metadata) + dst_release(&metadata->dst); err_out: if (exists) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 75046ec72144..cc9d8133afcd 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -447,6 +447,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, int nb = 0; int count = 1; int rc = NET_XMIT_SUCCESS; + int rc_drop = NET_XMIT_DROP; /* Do not fool qdisc_drop_all() */ skb->prev = NULL; @@ -486,6 +487,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->duplicate = 0; rootq->enqueue(skb2, rootq, to_free); q->duplicate = dupsave; + rc_drop = NET_XMIT_SUCCESS; } /* @@ -498,7 +500,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb_is_gso(skb)) { segs = netem_segment(skb, sch, to_free); if (!segs) - return NET_XMIT_DROP; + return rc_drop; } else { segs = skb; } @@ -521,8 +523,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, 1<<(prandom_u32() % 8); } - if (unlikely(sch->q.qlen >= sch->limit)) - return qdisc_drop_all(skb, sch, to_free); + if (unlikely(sch->q.qlen >= sch->limit)) { + qdisc_drop_all(skb, sch, to_free); + return rc_drop; + } qdisc_qstats_backlog_inc(sch, skb); diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 64bef313d436..5cb7c1ff97e9 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -192,7 +192,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, if (unlikely(!max_data)) { max_data = sctp_min_frag_point(sctp_sk(asoc->base.sk), sctp_datachk_len(&asoc->stream)); - pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%Zu)", + pr_warn_ratelimited("%s: asoc:%p frag_point is zero, forcing max_data to default minimum (%zu)", __func__, asoc, max_data); } diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 033696e6f74f..ad158d311ffa 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -207,7 +207,8 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if (time_before(transport->hb_timer.expires, expires) && + if ((time_before(transport->hb_timer.expires, expires) || + !timer_pending(&transport->hb_timer)) && !mod_timer(&transport->hb_timer, expires + prandom_u32_max(transport->rto))) sctp_transport_hold(transport); diff --git a/net/smc/smc.h b/net/smc/smc.h index 5721416d0605..adbdf195eb08 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -113,9 +113,9 @@ struct smc_host_cdc_msg { /* Connection Data Control message */ } __aligned(8); enum smc_urg_state { - SMC_URG_VALID, /* data present */ - SMC_URG_NOTYET, /* data pending */ - SMC_URG_READ /* data was already read */ + SMC_URG_VALID = 1, /* data present */ + SMC_URG_NOTYET = 2, /* data pending */ + SMC_URG_READ = 3, /* data was already read */ }; struct smc_connection { diff --git a/net/socket.c b/net/socket.c index d80d87a395ea..320f51b22b19 100644 --- a/net/socket.c +++ b/net/socket.c @@ -577,6 +577,7 @@ static void __sock_release(struct socket *sock, struct inode *inode) if (inode) inode_lock(inode); sock->ops->release(sock); + sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1217c90a363b..70343ac448b1 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -379,16 +379,18 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout) #define tipc_wait_for_cond(sock_, timeo_, condition_) \ ({ \ + DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ struct sock *sk_; \ int rc_; \ \ while ((rc_ = !(condition_))) { \ - DEFINE_WAIT_FUNC(wait_, woken_wake_function); \ + /* coupled with smp_wmb() in tipc_sk_proto_rcv() */ \ + smp_rmb(); \ sk_ = (sock_)->sk; \ rc_ = tipc_sk_sock_err((sock_), timeo_); \ if (rc_) \ break; \ - prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \ + add_wait_queue(sk_sleep(sk_), &wait_); \ release_sock(sk_); \ *(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \ sched_annotate_sleep(); \ @@ -1677,7 +1679,7 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk) static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) { struct sock *sk = sock->sk; - DEFINE_WAIT(wait); + DEFINE_WAIT_FUNC(wait, woken_wake_function); long timeo = *timeop; int err = sock_error(sk); @@ -1685,15 +1687,17 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) return err; for (;;) { - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); if (timeo && skb_queue_empty(&sk->sk_receive_queue)) { if (sk->sk_shutdown & RCV_SHUTDOWN) { err = -ENOTCONN; break; } + add_wait_queue(sk_sleep(sk), &wait); release_sock(sk); - timeo = schedule_timeout(timeo); + timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); + sched_annotate_sleep(); lock_sock(sk); + remove_wait_queue(sk_sleep(sk), &wait); } err = 0; if (!skb_queue_empty(&sk->sk_receive_queue)) @@ -1709,7 +1713,6 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) if (err) break; } - finish_wait(sk_sleep(sk), &wait); *timeop = timeo; return err; } @@ -1982,6 +1985,8 @@ static void tipc_sk_proto_rcv(struct sock *sk, return; case SOCK_WAKEUP: tipc_dest_del(&tsk->cong_links, msg_orignode(hdr), 0); + /* coupled with smp_rmb() in tipc_wait_for_cond() */ + smp_wmb(); tsk->cong_link_cnt--; wakeup = true; break; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 74d1eed7cbd4..a95d479caeea 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -890,7 +890,7 @@ retry: addr->hash ^= sk->sk_type; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(&unix_socket_table[addr->hash], sk); spin_unlock(&unix_table_lock); err = 0; @@ -1060,7 +1060,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) err = 0; __unix_remove_socket(sk); - u->addr = addr; + smp_store_release(&u->addr, addr); __unix_insert_socket(list, sk); out_unlock: @@ -1331,15 +1331,29 @@ restart: RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq); otheru = unix_sk(other); - /* copy address information from listening to new sock*/ - if (otheru->addr) { - refcount_inc(&otheru->addr->refcnt); - newu->addr = otheru->addr; - } + /* copy address information from listening to new sock + * + * The contents of *(otheru->addr) and otheru->path + * are seen fully set up here, since we have found + * otheru in hash under unix_table_lock. Insertion + * into the hash chain we'd found it in had been done + * in an earlier critical area protected by unix_table_lock, + * the same one where we'd set *(otheru->addr) contents, + * as well as otheru->path and otheru->addr itself. + * + * Using smp_store_release() here to set newu->addr + * is enough to make those stores, as well as stores + * to newu->path visible to anyone who gets newu->addr + * by smp_load_acquire(). IOW, the same warranties + * as for unix_sock instances bound in unix_bind() or + * in unix_autobind(). + */ if (otheru->path.dentry) { path_get(&otheru->path); newu->path = otheru->path; } + refcount_inc(&otheru->addr->refcnt); + smp_store_release(&newu->addr, otheru->addr); /* Set credentials */ copy_peercred(sk, other); @@ -1453,7 +1467,7 @@ out: static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sock *sk = sock->sk; - struct unix_sock *u; + struct unix_address *addr; DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr); int err = 0; @@ -1468,19 +1482,15 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) sock_hold(sk); } - u = unix_sk(sk); - unix_state_lock(sk); - if (!u->addr) { + addr = smp_load_acquire(&unix_sk(sk)->addr); + if (!addr) { sunaddr->sun_family = AF_UNIX; sunaddr->sun_path[0] = 0; err = sizeof(short); } else { - struct unix_address *addr = u->addr; - err = addr->len; memcpy(sunaddr, addr->name, addr->len); } - unix_state_unlock(sk); sock_put(sk); out: return err; @@ -2073,11 +2083,11 @@ static int unix_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, static void unix_copy_addr(struct msghdr *msg, struct sock *sk) { - struct unix_sock *u = unix_sk(sk); + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); - if (u->addr) { - msg->msg_namelen = u->addr->len; - memcpy(msg->msg_name, u->addr->name, u->addr->len); + if (addr) { + msg->msg_namelen = addr->len; + memcpy(msg->msg_name, addr->name, addr->len); } } @@ -2581,15 +2591,14 @@ static int unix_open_file(struct sock *sk) if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; - unix_state_lock(sk); + if (!smp_load_acquire(&unix_sk(sk)->addr)) + return -ENOENT; + path = unix_sk(sk)->path; - if (!path.dentry) { - unix_state_unlock(sk); + if (!path.dentry) return -ENOENT; - } path_get(&path); - unix_state_unlock(sk); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) @@ -2830,7 +2839,7 @@ static int unix_seq_show(struct seq_file *seq, void *v) (s->sk_state == TCP_ESTABLISHED ? SS_CONNECTING : SS_DISCONNECTING), sock_i_ino(s)); - if (u->addr) { + if (u->addr) { // under unix_table_lock here int i, len; seq_putc(seq, ' '); diff --git a/net/unix/diag.c b/net/unix/diag.c index 384c84e83462..3183d9b8ab33 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -10,7 +10,8 @@ static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb) { - struct unix_address *addr = unix_sk(sk)->addr; + /* might or might not have unix_table_lock */ + struct unix_address *addr = smp_load_acquire(&unix_sk(sk)->addr); if (!addr) return 0; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index ec3a828672ef..eff31348e20b 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -679,8 +679,7 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr; int len, i, rc = 0; - if (!sock_flag(sk, SOCK_ZAPPED) || - addr_len != sizeof(struct sockaddr_x25) || + if (addr_len != sizeof(struct sockaddr_x25) || addr->sx25_family != AF_X25) { rc = -EINVAL; goto out; @@ -699,9 +698,13 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } lock_sock(sk); - x25_sk(sk)->source_addr = addr->sx25_addr; - x25_insert_socket(sk); - sock_reset_flag(sk, SOCK_ZAPPED); + if (sock_flag(sk, SOCK_ZAPPED)) { + x25_sk(sk)->source_addr = addr->sx25_addr; + x25_insert_socket(sk); + sock_reset_flag(sk, SOCK_ZAPPED); + } else { + rc = -EINVAL; + } release_sock(sk); SOCK_DEBUG(sk, "x25_bind: socket is bound\n"); out: diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index d4de871e7d4d..37e1fe180769 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -125,9 +125,10 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, return 0; err_unreg_umem: - xdp_clear_umem_at_qid(dev, queue_id); if (!force_zc) err = 0; /* fallback to copy mode */ + if (err) + xdp_clear_umem_at_qid(dev, queue_id); out_rtnl_unlock: rtnl_unlock(); return err; @@ -259,10 +260,10 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem) if (!umem->pgs) return -ENOMEM; - down_write(¤t->mm->mmap_sem); - npgs = get_user_pages(umem->address, umem->npgs, - gup_flags, &umem->pgs[0], NULL); - up_write(¤t->mm->mmap_sem); + down_read(¤t->mm->mmap_sem); + npgs = get_user_pages_longterm(umem->address, umem->npgs, + gup_flags, &umem->pgs[0], NULL); + up_read(¤t->mm->mmap_sem); if (npgs != umem->npgs) { if (npgs >= 0) { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index a03268454a27..85e4fe4f18cc 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -366,7 +366,6 @@ static int xsk_release(struct socket *sock) xskq_destroy(xs->rx); xskq_destroy(xs->tx); - xdp_put_umem(xs->umem); sock_orphan(sk); sock->sk = NULL; @@ -669,6 +668,8 @@ static int xsk_mmap(struct file *file, struct socket *sock, if (!umem) return -EINVAL; + /* Matches the smp_wmb() in XDP_UMEM_REG */ + smp_rmb(); if (offset == XDP_UMEM_PGOFF_FILL_RING) q = READ_ONCE(umem->fq); else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) @@ -678,6 +679,8 @@ static int xsk_mmap(struct file *file, struct socket *sock, if (!q) return -EINVAL; + /* Matches the smp_wmb() in xsk_init_queue */ + smp_rmb(); qpg = virt_to_head_page(q->ring); if (size > (PAGE_SIZE << compound_order(qpg))) return -EINVAL; @@ -714,6 +717,18 @@ static const struct proto_ops xsk_proto_ops = { .sendpage = sock_no_sendpage, }; +static void xsk_destruct(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + return; + + xdp_put_umem(xs->umem); + + sk_refcnt_debug_dec(sk); +} + static int xsk_create(struct net *net, struct socket *sock, int protocol, int kern) { @@ -740,6 +755,9 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, sk->sk_family = PF_XDP; + sk->sk_destruct = xsk_destruct; + sk_refcnt_debug_inc(sk); + sock_set_flag(sk, SOCK_RCU_FREE); xs = xdp_sk(sk); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 6be8c7df15bb..dbb3c1945b5c 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -76,10 +76,10 @@ static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb) int ifindex; struct xfrm_if *xi; - if (!skb->dev) + if (!secpath_exists(skb) || !skb->dev) return NULL; - xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id); + xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); ifindex = skb->dev->ifindex; for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ba0a4048c846..8d1a898d0ba5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3314,8 +3314,10 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, if (ifcb) { xi = ifcb->decode_session(skb); - if (xi) + if (xi) { if_id = xi->p.if_id; + net = xi->net; + } } rcu_read_unlock(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 23c92891758a..1bb971f46fc6 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -432,7 +432,7 @@ void xfrm_state_free(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_free); -static void xfrm_state_gc_destroy(struct xfrm_state *x) +static void ___xfrm_state_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); @@ -474,7 +474,7 @@ static void xfrm_state_gc_task(struct work_struct *work) synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) - xfrm_state_gc_destroy(x); + ___xfrm_state_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) @@ -598,14 +598,19 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) } EXPORT_SYMBOL(xfrm_state_alloc); -void __xfrm_state_destroy(struct xfrm_state *x) +void __xfrm_state_destroy(struct xfrm_state *x, bool sync) { WARN_ON(x->km.state != XFRM_STATE_DEAD); - spin_lock_bh(&xfrm_state_gc_lock); - hlist_add_head(&x->gclist, &xfrm_state_gc_list); - spin_unlock_bh(&xfrm_state_gc_lock); - schedule_work(&xfrm_state_gc_work); + if (sync) { + synchronize_rcu(); + ___xfrm_state_destroy(x); + } else { + spin_lock_bh(&xfrm_state_gc_lock); + hlist_add_head(&x->gclist, &xfrm_state_gc_list); + spin_unlock_bh(&xfrm_state_gc_lock); + schedule_work(&xfrm_state_gc_work); + } } EXPORT_SYMBOL(__xfrm_state_destroy); @@ -708,7 +713,7 @@ xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool } #endif -int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) +int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync) { int i, err = 0, cnt = 0; @@ -730,7 +735,10 @@ restart: err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); - xfrm_state_put(x); + if (sync) + xfrm_state_put_sync(x); + else + xfrm_state_put(x); if (!err) cnt++; @@ -2215,7 +2223,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) if (atomic_read(&t->tunnel_users) == 2) xfrm_state_delete(t); atomic_dec(&t->tunnel_users); - xfrm_state_put(t); + xfrm_state_put_sync(t); x->tunnel = NULL; } } @@ -2375,8 +2383,8 @@ void xfrm_state_fini(struct net *net) unsigned int sz; flush_work(&net->xfrm.state_hash_work); - xfrm_state_flush(net, IPSEC_PROTO_ANY, false); flush_work(&xfrm_state_gc_work); + xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true); WARN_ON(!list_empty(&net->xfrm.state_all)); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c6d26afcf89d..a131f9ff979e 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1932,7 +1932,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, struct xfrm_usersa_flush *p = nlmsg_data(nlh); int err; - err = xfrm_state_flush(net, p->proto, true); + err = xfrm_state_flush(net, p->proto, true, false); if (err) { if (err == -ESRCH) /* empty table */ return 0; diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 25c259df8ffa..6deabedc67fc 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -26,7 +26,7 @@ else CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \ $(call cc-param,asan-globals=1) \ $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \ - $(call cc-param,asan-stack=1) \ + $(call cc-param,asan-stack=$(CONFIG_KASAN_STACK)) \ $(call cc-param,asan-use-after-scope=1) \ $(call cc-param,asan-instrument-allocas=1) endif diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 77cebad0474e..f75e7bda4889 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -118,8 +118,8 @@ static int read_symbol(FILE *in, struct sym_entry *s) fprintf(stderr, "Read error or end of file.\n"); return -1; } - if (strlen(sym) > KSYM_NAME_LEN) { - fprintf(stderr, "Symbol %s too long for kallsyms (%zu vs %d).\n" + if (strlen(sym) >= KSYM_NAME_LEN) { + fprintf(stderr, "Symbol %s too long for kallsyms (%zu >= %d).\n" "Please increase KSYM_NAME_LEN both in kernel and kallsyms.c\n", sym, strlen(sym), KSYM_NAME_LEN); return -1; diff --git a/security/keys/internal.h b/security/keys/internal.h index 479909b858c7..8f533c81aa8d 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -186,20 +186,9 @@ static inline int key_permission(const key_ref_t key_ref, unsigned perm) return key_task_permission(key_ref, current_cred(), perm); } -/* - * Authorisation record for request_key(). - */ -struct request_key_auth { - struct key *target_key; - struct key *dest_keyring; - const struct cred *cred; - void *callout_info; - size_t callout_len; - pid_t pid; -} __randomize_layout; - extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, + const char *op, const void *callout_info, size_t callout_len, struct key *dest_keyring); diff --git a/security/keys/key.c b/security/keys/key.c index 44a80d6741a1..696f1c092c50 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -265,8 +265,8 @@ struct key *key_alloc(struct key_type *type, const char *desc, spin_lock(&user->lock); if (!(flags & KEY_ALLOC_QUOTA_OVERRUN)) { - if (user->qnkeys + 1 >= maxkeys || - user->qnbytes + quotalen >= maxbytes || + if (user->qnkeys + 1 > maxkeys || + user->qnbytes + quotalen > maxbytes || user->qnbytes + quotalen < user->qnbytes) goto no_quota; } @@ -297,6 +297,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, key->gid = gid; key->perm = perm; key->restrict_link = restrict_link; + key->last_used_at = ktime_get_real_seconds(); if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) key->flags |= 1 << KEY_FLAG_IN_QUOTA; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index e8093d025966..7bbe03593e58 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -25,6 +25,7 @@ #include <linux/security.h> #include <linux/uio.h> #include <linux/uaccess.h> +#include <keys/request_key_auth-type.h> #include "internal.h" #define KEY_MAX_DESC_SIZE 4096 diff --git a/security/keys/keyring.c b/security/keys/keyring.c index eadebb92986a..f81372f53dd7 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -661,9 +661,6 @@ static bool search_nested_keyrings(struct key *keyring, BUG_ON((ctx->flags & STATE_CHECKS) == 0 || (ctx->flags & STATE_CHECKS) == STATE_CHECKS); - if (ctx->index_key.description) - ctx->index_key.desc_len = strlen(ctx->index_key.description); - /* Check to see if this top-level keyring is what we are looking for * and whether it is valid or not. */ @@ -914,6 +911,7 @@ key_ref_t keyring_search(key_ref_t keyring, struct keyring_search_context ctx = { .index_key.type = type, .index_key.description = description, + .index_key.desc_len = strlen(description), .cred = current_cred(), .match_data.cmp = key_default_cmp, .match_data.raw_data = description, diff --git a/security/keys/proc.c b/security/keys/proc.c index d2b802072693..78ac305d715e 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -165,8 +165,7 @@ static int proc_keys_show(struct seq_file *m, void *v) int rc; struct keyring_search_context ctx = { - .index_key.type = key->type, - .index_key.description = key->description, + .index_key = key->index_key, .cred = m->file->f_cred, .match_data.cmp = lookup_user_key_possessed, .match_data.raw_data = key, diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 02c77e928f68..0e0b9ccad2f8 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -19,6 +19,7 @@ #include <linux/security.h> #include <linux/user_namespace.h> #include <linux/uaccess.h> +#include <keys/request_key_auth-type.h> #include "internal.h" /* Session keyring create vs join semaphore */ diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 301f0e300dbd..7a0c6b666ff0 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -18,31 +18,30 @@ #include <linux/keyctl.h> #include <linux/slab.h> #include "internal.h" +#include <keys/request_key_auth-type.h> #define key_negative_timeout 60 /* default timeout on a negative key's existence */ /** * complete_request_key - Complete the construction of a key. - * @cons: The key construction record. + * @auth_key: The authorisation key. * @error: The success or failute of the construction. * * Complete the attempt to construct a key. The key will be negated * if an error is indicated. The authorisation key will be revoked * unconditionally. */ -void complete_request_key(struct key_construction *cons, int error) +void complete_request_key(struct key *authkey, int error) { - kenter("{%d,%d},%d", cons->key->serial, cons->authkey->serial, error); + struct request_key_auth *rka = get_request_key_auth(authkey); + struct key *key = rka->target_key; + + kenter("%d{%d},%d", authkey->serial, key->serial, error); if (error < 0) - key_negate_and_link(cons->key, key_negative_timeout, NULL, - cons->authkey); + key_negate_and_link(key, key_negative_timeout, NULL, authkey); else - key_revoke(cons->authkey); - - key_put(cons->key); - key_put(cons->authkey); - kfree(cons); + key_revoke(authkey); } EXPORT_SYMBOL(complete_request_key); @@ -91,21 +90,19 @@ static int call_usermodehelper_keys(const char *path, char **argv, char **envp, * Request userspace finish the construction of a key * - execute "/sbin/request-key <op> <key> <uid> <gid> <keyring> <keyring> <keyring>" */ -static int call_sbin_request_key(struct key_construction *cons, - const char *op, - void *aux) +static int call_sbin_request_key(struct key *authkey, void *aux) { static char const request_key[] = "/sbin/request-key"; + struct request_key_auth *rka = get_request_key_auth(authkey); const struct cred *cred = current_cred(); key_serial_t prkey, sskey; - struct key *key = cons->key, *authkey = cons->authkey, *keyring, - *session; + struct key *key = rka->target_key, *keyring, *session; char *argv[9], *envp[3], uid_str[12], gid_str[12]; char key_str[12], keyring_str[3][12]; char desc[20]; int ret, i; - kenter("{%d},{%d},%s", key->serial, authkey->serial, op); + kenter("{%d},{%d},%s", key->serial, authkey->serial, rka->op); ret = install_user_keyrings(); if (ret < 0) @@ -163,7 +160,7 @@ static int call_sbin_request_key(struct key_construction *cons, /* set up the argument list */ i = 0; argv[i++] = (char *)request_key; - argv[i++] = (char *) op; + argv[i++] = (char *)rka->op; argv[i++] = key_str; argv[i++] = uid_str; argv[i++] = gid_str; @@ -191,7 +188,7 @@ error_link: key_put(keyring); error_alloc: - complete_request_key(cons, ret); + complete_request_key(authkey, ret); kleave(" = %d", ret); return ret; } @@ -205,42 +202,31 @@ static int construct_key(struct key *key, const void *callout_info, size_t callout_len, void *aux, struct key *dest_keyring) { - struct key_construction *cons; request_key_actor_t actor; struct key *authkey; int ret; kenter("%d,%p,%zu,%p", key->serial, callout_info, callout_len, aux); - cons = kmalloc(sizeof(*cons), GFP_KERNEL); - if (!cons) - return -ENOMEM; - /* allocate an authorisation key */ - authkey = request_key_auth_new(key, callout_info, callout_len, + authkey = request_key_auth_new(key, "create", callout_info, callout_len, dest_keyring); - if (IS_ERR(authkey)) { - kfree(cons); - ret = PTR_ERR(authkey); - authkey = NULL; - } else { - cons->authkey = key_get(authkey); - cons->key = key_get(key); + if (IS_ERR(authkey)) + return PTR_ERR(authkey); - /* make the call */ - actor = call_sbin_request_key; - if (key->type->request_key) - actor = key->type->request_key; + /* Make the call */ + actor = call_sbin_request_key; + if (key->type->request_key) + actor = key->type->request_key; - ret = actor(cons, "create", aux); + ret = actor(authkey, aux); - /* check that the actor called complete_request_key() prior to - * returning an error */ - WARN_ON(ret < 0 && - !test_bit(KEY_FLAG_REVOKED, &authkey->flags)); - key_put(authkey); - } + /* check that the actor called complete_request_key() prior to + * returning an error */ + WARN_ON(ret < 0 && + !test_bit(KEY_FLAG_REVOKED, &authkey->flags)); + key_put(authkey); kleave(" = %d", ret); return ret; } @@ -275,7 +261,7 @@ static int construct_get_dest_keyring(struct key **_dest_keyring) if (cred->request_key_auth) { authkey = cred->request_key_auth; down_read(&authkey->sem); - rka = authkey->payload.data[0]; + rka = get_request_key_auth(authkey); if (!test_bit(KEY_FLAG_REVOKED, &authkey->flags)) dest_keyring = @@ -545,6 +531,7 @@ struct key *request_key_and_link(struct key_type *type, struct keyring_search_context ctx = { .index_key.type = type, .index_key.description = description, + .index_key.desc_len = strlen(description), .cred = current_cred(), .match_data.cmp = key_default_cmp, .match_data.raw_data = description, diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index 87ea2f54dedc..bda6201c6c45 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -17,7 +17,7 @@ #include <linux/slab.h> #include <linux/uaccess.h> #include "internal.h" -#include <keys/user-type.h> +#include <keys/request_key_auth-type.h> static int request_key_auth_preparse(struct key_preparsed_payload *); static void request_key_auth_free_preparse(struct key_preparsed_payload *); @@ -68,7 +68,7 @@ static int request_key_auth_instantiate(struct key *key, static void request_key_auth_describe(const struct key *key, struct seq_file *m) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); seq_puts(m, "key:"); seq_puts(m, key->description); @@ -83,7 +83,7 @@ static void request_key_auth_describe(const struct key *key, static long request_key_auth_read(const struct key *key, char __user *buffer, size_t buflen) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); size_t datalen; long ret; @@ -109,7 +109,7 @@ static long request_key_auth_read(const struct key *key, */ static void request_key_auth_revoke(struct key *key) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); kenter("{%d}", key->serial); @@ -136,7 +136,7 @@ static void free_request_key_auth(struct request_key_auth *rka) */ static void request_key_auth_destroy(struct key *key) { - struct request_key_auth *rka = key->payload.data[0]; + struct request_key_auth *rka = get_request_key_auth(key); kenter("{%d}", key->serial); @@ -147,8 +147,9 @@ static void request_key_auth_destroy(struct key *key) * Create an authorisation token for /sbin/request-key or whoever to gain * access to the caller's security data. */ -struct key *request_key_auth_new(struct key *target, const void *callout_info, - size_t callout_len, struct key *dest_keyring) +struct key *request_key_auth_new(struct key *target, const char *op, + const void *callout_info, size_t callout_len, + struct key *dest_keyring) { struct request_key_auth *rka, *irka; const struct cred *cred = current->cred; @@ -166,6 +167,7 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, if (!rka->callout_info) goto error_free_rka; rka->callout_len = callout_len; + strlcpy(rka->op, op, sizeof(rka->op)); /* see if the calling process is already servicing the key request of * another process */ @@ -245,7 +247,7 @@ struct key *key_get_instantiation_authkey(key_serial_t target_id) struct key *authkey; key_ref_t authkey_ref; - sprintf(description, "%x", target_id); + ctx.index_key.desc_len = sprintf(description, "%x", target_id); authkey_ref = search_process_keyrings(&ctx); diff --git a/security/lsm_audit.c b/security/lsm_audit.c index f84001019356..33028c098ef3 100644 --- a/security/lsm_audit.c +++ b/security/lsm_audit.c @@ -321,6 +321,7 @@ static void dump_common_audit_data(struct audit_buffer *ab, if (a->u.net->sk) { struct sock *sk = a->u.net->sk; struct unix_sock *u; + struct unix_address *addr; int len = 0; char *p = NULL; @@ -351,14 +352,15 @@ static void dump_common_audit_data(struct audit_buffer *ab, #endif case AF_UNIX: u = unix_sk(sk); + addr = smp_load_acquire(&u->addr); + if (!addr) + break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } - if (!u->addr) - break; - len = u->addr->len-sizeof(short); - p = &u->addr->name->sun_path[0]; + len = addr->len-sizeof(short); + p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 6df758adff84..1ffa36e987b4 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1855,6 +1855,8 @@ enum { ALC887_FIXUP_BASS_CHMAP, ALC1220_FIXUP_GB_DUAL_CODECS, ALC1220_FIXUP_CLEVO_P950, + ALC1220_FIXUP_SYSTEM76_ORYP5, + ALC1220_FIXUP_SYSTEM76_ORYP5_PINS, }; static void alc889_fixup_coef(struct hda_codec *codec, @@ -2056,6 +2058,17 @@ static void alc1220_fixup_clevo_p950(struct hda_codec *codec, snd_hda_override_conn_list(codec, 0x1b, 1, conn1); } +static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action); + +static void alc1220_fixup_system76_oryp5(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + alc1220_fixup_clevo_p950(codec, fix, action); + alc_fixup_headset_mode_no_hp_mic(codec, fix, action); +} + static const struct hda_fixup alc882_fixups[] = { [ALC882_FIXUP_ABIT_AW9D_MAX] = { .type = HDA_FIXUP_PINS, @@ -2300,6 +2313,19 @@ static const struct hda_fixup alc882_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc1220_fixup_clevo_p950, }, + [ALC1220_FIXUP_SYSTEM76_ORYP5] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc1220_fixup_system76_oryp5, + }, + [ALC1220_FIXUP_SYSTEM76_ORYP5_PINS] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + {} + }, + .chained = true, + .chain_id = ALC1220_FIXUP_SYSTEM76_ORYP5, + }, }; static const struct snd_pci_quirk alc882_fixup_tbl[] = { @@ -2376,6 +2402,8 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950), + SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), + SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS), SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD), SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD), SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530), @@ -5632,6 +5660,7 @@ enum { ALC294_FIXUP_ASUS_SPK, ALC225_FIXUP_HEADSET_JACK, ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE, + ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6587,6 +6616,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, + [ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Disable PCBEEP-IN passthrough */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x36 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 }, + { } + }, + .chained = true, + .chain_id = ALC285_FIXUP_LENOVO_HEADPHONE_NOISE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7272,7 +7312,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x19, 0x03a11020}, {0x21, 0x0321101f}), - SND_HDA_PIN_QUIRK(0x10ec0285, 0x17aa, "Lenovo", ALC285_FIXUP_LENOVO_HEADPHONE_NOISE, + SND_HDA_PIN_QUIRK(0x10ec0285, 0x17aa, "Lenovo", ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE, {0x12, 0x90a60130}, {0x14, 0x90170110}, {0x19, 0x04a11040}, diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c index 37e001cf9cd1..3fe34417ec89 100644 --- a/sound/soc/generic/simple-card.c +++ b/sound/soc/generic/simple-card.c @@ -462,7 +462,7 @@ static int asoc_simple_card_parse_of(struct simple_card_data *priv) conf_idx = 0; node = of_get_child_by_name(top, PREFIX "dai-link"); if (!node) { - node = dev->of_node; + node = of_node_get(top); loop = 0; } diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index ce00fe2f6aae..d4bde4834ce5 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -604,6 +604,7 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, unsigned int fmt) { struct i2s_dai *i2s = to_info(dai); + struct i2s_dai *other = get_other_dai(i2s); int lrp_shift, sdf_shift, sdf_mask, lrp_rlow, mod_slave; u32 mod, tmp = 0; unsigned long flags; @@ -661,7 +662,8 @@ static int i2s_set_fmt(struct snd_soc_dai *dai, * CLK_I2S_RCLK_SRC clock is not exposed so we ensure any * clock configuration assigned in DT is not overwritten. */ - if (i2s->rclk_srcrate == 0 && i2s->clk_data.clks == NULL) + if (i2s->rclk_srcrate == 0 && i2s->clk_data.clks == NULL && + other->clk_data.clks == NULL) i2s_set_sysclk(dai, SAMSUNG_I2S_RCLKSRC_0, 0, SND_SOC_CLOCK_IN); break; @@ -699,6 +701,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai) { struct i2s_dai *i2s = to_info(dai); + struct i2s_dai *other = get_other_dai(i2s); u32 mod, mask = 0, val = 0; struct clk *rclksrc; unsigned long flags; @@ -784,6 +787,9 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, i2s->frmclk = params_rate(params); rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC]; + if (!rclksrc || IS_ERR(rclksrc)) + rclksrc = other->clk_table[CLK_I2S_RCLK_SRC]; + if (rclksrc && !IS_ERR(rclksrc)) i2s->rclk_srcrate = clk_get_rate(rclksrc); diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index fc79ec6927e3..731b963b6995 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -2487,6 +2487,7 @@ int snd_soc_tplg_component_load(struct snd_soc_component *comp, struct snd_soc_tplg_ops *ops, const struct firmware *fw, u32 id) { struct soc_tplg tplg; + int ret; /* setup parsing context */ memset(&tplg, 0, sizeof(tplg)); @@ -2500,7 +2501,12 @@ int snd_soc_tplg_component_load(struct snd_soc_component *comp, tplg.bytes_ext_ops = ops->bytes_ext_ops; tplg.bytes_ext_ops_count = ops->bytes_ext_ops_count; - return soc_tplg_load(&tplg); + ret = soc_tplg_load(&tplg); + /* free the created components if fail to load topology */ + if (ret) + snd_soc_tplg_component_remove(comp, SND_SOC_TPLG_INDEX_ALL); + + return ret; } EXPORT_SYMBOL_GPL(snd_soc_tplg_component_load); diff --git a/tools/testing/selftests/bpf/test_lpm_map.c b/tools/testing/selftests/bpf/test_lpm_map.c index 147e34cfceb7..02d7c871862a 100644 --- a/tools/testing/selftests/bpf/test_lpm_map.c +++ b/tools/testing/selftests/bpf/test_lpm_map.c @@ -474,6 +474,16 @@ static void test_lpm_delete(void) assert(bpf_map_lookup_elem(map_fd, key, &value) == -1 && errno == ENOENT); + key->prefixlen = 30; // unused prefix so far + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + + key->prefixlen = 16; // same prefix as the root node + inet_pton(AF_INET, "192.255.0.0", key->data); + assert(bpf_map_delete_elem(map_fd, key) == -1 && + errno == ENOENT); + /* assert initial lookup */ key->prefixlen = 32; inet_pton(AF_INET, "192.168.0.1", key->data); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 802b4af18729..1080ff55a788 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -388,6 +388,7 @@ fib_carrier_unicast_test() set -e $IP link set dev dummy0 carrier off + sleep 1 set +e echo " Carrier down" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index e2c94e47707c..912b2dc50be3 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -103,6 +103,15 @@ # and check that configured MTU is used on link creation and changes, and # that MTU is properly calculated instead when MTU is not configured from # userspace +# +# - cleanup_ipv4_exception +# Similar to pmtu_ipv4_vxlan4_exception, but explicitly generate PMTU +# exceptions on multiple CPUs and check that the veth device tear-down +# happens in a timely manner +# +# - cleanup_ipv6_exception +# Same as above, but use IPv6 transport from A to B + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -135,7 +144,9 @@ tests=" pmtu_vti6_default_mtu vti6: default MTU assignment pmtu_vti4_link_add_mtu vti4: MTU setting on link creation pmtu_vti6_link_add_mtu vti6: MTU setting on link creation - pmtu_vti6_link_change_mtu vti6: MTU changes on link changes" + pmtu_vti6_link_change_mtu vti6: MTU changes on link changes + cleanup_ipv4_exception ipv4: cleanup of cached exceptions + cleanup_ipv6_exception ipv6: cleanup of cached exceptions" NS_A="ns-$(mktemp -u XXXXXX)" NS_B="ns-$(mktemp -u XXXXXX)" @@ -263,8 +274,6 @@ setup_fou_or_gue() { ${ns_a} ip link set ${encap}_a up ${ns_b} ip link set ${encap}_b up - - sleep 1 } setup_fou44() { @@ -302,6 +311,10 @@ setup_gue66() { setup_namespaces() { for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do ip netns add ${n} || return 1 + + # Disable DAD, so that we don't have to wait to use the + # configured IPv6 addresses + ip netns exec ${n} sysctl -q net/ipv6/conf/default/accept_dad=0 done } @@ -337,8 +350,6 @@ setup_vti() { ${ns_a} ip link set vti${proto}_a up ${ns_b} ip link set vti${proto}_b up - - sleep 1 } setup_vti4() { @@ -375,8 +386,6 @@ setup_vxlan_or_geneve() { ${ns_a} ip link set ${type}_a up ${ns_b} ip link set ${type}_b up - - sleep 1 } setup_geneve4() { @@ -588,8 +597,8 @@ test_pmtu_ipvX() { mtu "${ns_b}" veth_B-R2 1500 # Create route exceptions - ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst1} > /dev/null - ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1800 ${dst2} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst1} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1800 ${dst2} > /dev/null # Check that exceptions have been created with the correct PMTU pmtu_1="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst1})" @@ -621,7 +630,7 @@ test_pmtu_ipvX() { # Decrease remote MTU on path via R2, get new exception mtu "${ns_r2}" veth_R2-B 400 mtu "${ns_b}" veth_B-R2 400 - ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1 @@ -638,7 +647,7 @@ test_pmtu_ipvX() { check_pmtu_value "1500" "${pmtu_2}" "increasing local MTU" || return 1 # Get new exception - ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s 1400 ${dst2} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s 1400 ${dst2} > /dev/null pmtu_2="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst2})" check_pmtu_value "lock 552" "${pmtu_2}" "exceeding MTU, with MTU < min_pmtu" || return 1 } @@ -687,7 +696,7 @@ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() { mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000)) mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000)) - ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" @@ -767,7 +776,7 @@ test_pmtu_ipvX_over_fouY_or_gueY() { mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000)) mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000)) - ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null + ${ns_a} ${ping} -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${dst} > /dev/null # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})" @@ -825,13 +834,13 @@ test_pmtu_vti4_exception() { # Send DF packet without exceeding link layer MTU, check that no # exception is created - ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null + ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1 # Now exceed link layer MTU by one byte, check that exception is created # with the right PMTU value - ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null + ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})" check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))" } @@ -847,7 +856,7 @@ test_pmtu_vti6_exception() { mtu "${ns_b}" veth_b 4000 mtu "${ns_a}" vti6_a 5000 mtu "${ns_b}" vti6_b 5000 - ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${tunnel6_b_addr} > /dev/null + ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr} > /dev/null # Check that exception was created pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})" @@ -1008,6 +1017,61 @@ test_pmtu_vti6_link_change_mtu() { return ${fail} } +check_command() { + cmd=${1} + + if ! which ${cmd} > /dev/null 2>&1; then + err " missing required command: '${cmd}'" + return 1 + fi + return 0 +} + +test_cleanup_vxlanX_exception() { + outer="${1}" + encap="vxlan" + ll_mtu=4000 + + check_command taskset || return 2 + cpu_list=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) + + setup namespaces routing ${encap}${outer} || return 2 + trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \ + "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \ + "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B + + # Create route exception by exceeding link layer MTU + mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000)) + mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000)) + mtu "${ns_b}" veth_B-R1 ${ll_mtu} + mtu "${ns_r1}" veth_R1-B ${ll_mtu} + + mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000)) + mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000)) + + # Fill exception cache for multiple CPUs (2) + # we can always use inner IPv4 for that + for cpu in ${cpu_list}; do + taskset --cpu-list ${cpu} ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((${ll_mtu} + 500)) ${tunnel4_b_addr} > /dev/null + done + + ${ns_a} ip link del dev veth_A-R1 & + iplink_pid=$! + sleep 1 + if [ "$(cat /proc/${iplink_pid}/cmdline 2>/dev/null | tr -d '\0')" = "iplinkdeldevveth_A-R1" ]; then + err " can't delete veth device in a timely manner, PMTU dst likely leaked" + return 1 + fi +} + +test_cleanup_ipv6_exception() { + test_cleanup_vxlanX_exception 6 +} + +test_cleanup_ipv4_exception() { + test_cleanup_vxlanX_exception 4 +} + usage() { echo echo "$0 [OPTIONS] [TEST]..." diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh index aeac53a99aeb..ac2a30be9b32 100755 --- a/tools/testing/selftests/net/udpgro.sh +++ b/tools/testing/selftests/net/udpgro.sh @@ -37,7 +37,7 @@ run_one() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \ + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \ echo "ok" || \ echo "failed" & @@ -81,7 +81,7 @@ run_one_nat() { # will land on the 'plain' one ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 & pid=$! - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${family} -b ${addr2%/*} ${rx_args} && \ + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \ echo "ok" || \ echo "failed"& @@ -99,8 +99,8 @@ run_one_2sock() { cfg_veth - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -p 12345 & - ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} && \ + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 & + ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \ echo "ok" || \ echo "failed" & diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 0c960f673324..db3d4a8b5a4c 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -45,6 +45,8 @@ static int cfg_alen = sizeof(struct sockaddr_in6); static int cfg_expected_pkt_nr; static int cfg_expected_pkt_len; static int cfg_expected_gso_size; +static int cfg_connect_timeout_ms; +static int cfg_rcv_timeout_ms; static struct sockaddr_storage cfg_bind_addr; static bool interrupted; @@ -87,7 +89,7 @@ static unsigned long gettimeofday_ms(void) return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); } -static void do_poll(int fd) +static void do_poll(int fd, int timeout_ms) { struct pollfd pfd; int ret; @@ -102,8 +104,16 @@ static void do_poll(int fd) break; if (ret == -1) error(1, errno, "poll"); - if (ret == 0) - continue; + if (ret == 0) { + if (!timeout_ms) + continue; + + timeout_ms -= 10; + if (timeout_ms <= 0) { + interrupted = true; + break; + } + } if (pfd.revents != POLLIN) error(1, errno, "poll: 0x%x expected 0x%x\n", pfd.revents, POLLIN); @@ -134,7 +144,7 @@ static int do_socket(bool do_tcp) if (listen(accept_fd, 1)) error(1, errno, "listen"); - do_poll(accept_fd); + do_poll(accept_fd, cfg_connect_timeout_ms); if (interrupted) exit(0); @@ -273,7 +283,9 @@ static void do_flush_udp(int fd) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-Grtv] [-b addr] [-p port] [-l pktlen] [-n packetnr] [-S gsosize]", filepath); + error(1, 0, "Usage: %s [-C connect_timeout] [-Grtv] [-b addr] [-p port]" + " [-l pktlen] [-n packetnr] [-R rcv_timeout] [-S gsosize]", + filepath); } static void parse_opts(int argc, char **argv) @@ -282,7 +294,7 @@ static void parse_opts(int argc, char **argv) /* bind to any by default */ setup_sockaddr(PF_INET6, "::", &cfg_bind_addr); - while ((c = getopt(argc, argv, "4b:Gl:n:p:rS:tv")) != -1) { + while ((c = getopt(argc, argv, "4b:C:Gl:n:p:rR:S:tv")) != -1) { switch (c) { case '4': cfg_family = PF_INET; @@ -292,6 +304,9 @@ static void parse_opts(int argc, char **argv) case 'b': setup_sockaddr(cfg_family, optarg, &cfg_bind_addr); break; + case 'C': + cfg_connect_timeout_ms = strtoul(optarg, NULL, 0); + break; case 'G': cfg_gro_segment = true; break; @@ -307,6 +322,9 @@ static void parse_opts(int argc, char **argv) case 'r': cfg_read_all = true; break; + case 'R': + cfg_rcv_timeout_ms = strtoul(optarg, NULL, 0); + break; case 'S': cfg_expected_gso_size = strtol(optarg, NULL, 0); break; @@ -329,8 +347,9 @@ static void parse_opts(int argc, char **argv) static void do_recv(void) { + int timeout_ms = cfg_tcp ? cfg_rcv_timeout_ms : cfg_connect_timeout_ms; unsigned long tnow, treport; - int fd, loop = 0; + int fd; fd = do_socket(cfg_tcp); @@ -342,12 +361,7 @@ static void do_recv(void) treport = gettimeofday_ms() + 1000; do { - /* force termination after the second poll(); this cope both - * with sender slower than receiver and missing packet errors - */ - if (cfg_expected_pkt_nr && loop++) - interrupted = true; - do_poll(fd); + do_poll(fd, timeout_ms); if (cfg_tcp) do_flush_tcp(fd); @@ -365,6 +379,8 @@ static void do_recv(void) treport = tnow + 1000; } + timeout_ms = cfg_rcv_timeout_ms; + } while (!interrupted); if (cfg_expected_pkt_nr && (packets != cfg_expected_pkt_nr)) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 585845203db8..076bc38963bf 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4044,7 +4044,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) } add_uevent_var(env, "PID=%d", kvm->userspace_pid); - if (kvm->debugfs_dentry) { + if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL); if (p) { |