diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2026-02-26 21:20:47 +0300 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2026-03-05 23:11:05 +0300 |
| commit | 0b1324cdd8de9f54f9daf689a4ae59783c333510 (patch) | |
| tree | 991952409fe93bd0ea73f8683b497e31bfe6952f | |
| parent | ab99e1167293726f016360a5dbbbc10386fd7d66 (diff) | |
| parent | abacaf559950eec0d99d37ff6b92049409af5943 (diff) | |
| download | linux-0b1324cdd8de9f54f9daf689a4ae59783c333510.tar.xz | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR (net-7.0-rc3).
No conflicts.
Adjacent changes:
net/netfilter/nft_set_rbtree.c
fb7fb4016300 ("netfilter: nf_tables: clone set on flush only")
3aea466a4399 ("netfilter: nft_set_rbtree: don't disable bh when acquiring tree lock")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
591 files changed, 7278 insertions, 3295 deletions
@@ -210,7 +210,12 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch> Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com> Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com> +Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@linaro.org> +Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@free.fr> +Daniel Lezcano <daniel.lezcano@kernel.org> <daniel.lezcano@linexp.org> +Daniel Lezcano <daniel.lezcano@kernel.org> <dlezcano@fr.ibm.com> Daniel Thompson <danielt@kernel.org> <daniel.thompson@linaro.org> +Daniele Alessandrelli <daniele.alessandrelli@gmail.com> <daniele.alessandrelli@intel.com> Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com> David Brownell <david-b@pacbell.net> David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org> @@ -348,6 +353,7 @@ Jarkko Sakkinen <jarkko@kernel.org> <jarkko.sakkinen@opinsys.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com> Jason Gunthorpe <jgg@ziepe.ca> <jgg@nvidia.com> Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com> +Jason Xing <kerneljasonxing@gmail.com> <kernelxing@tencent.com> <javier@osg.samsung.com> <javier.martinez@collabora.co.uk> Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com> Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com> @@ -396,6 +402,7 @@ Jiri Slaby <jirislaby@kernel.org> <xslaby@fi.muni.cz> Jisheng Zhang <jszhang@kernel.org> <jszhang@marvell.com> Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Jishnu Prakash <quic_jprakash@quicinc.com> <jprakash@codeaurora.org> +Joe Damato <joe@dama.to> <jdamato@fastly.com> Joel Granados <joel.granados@kernel.org> <j.granados@samsung.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> @@ -876,6 +883,7 @@ Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com> Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> +Vlastimil Babka <vbabka@kernel.org> <vbabka@suse.cz> WangYuli <wangyuli@aosc.io> <wangyl5933@chinaunicom.cn> WangYuli <wangyuli@aosc.io> <wangyuli@deepin.org> Weiwen Hu <huweiwen@linux.alibaba.com> <sehuww@mail.scut.edu.cn> @@ -890,7 +898,8 @@ Yanteng Si <si.yanteng@linux.dev> <siyanteng@loongson.cn> Ying Huang <huang.ying.caritas@gmail.com> <ying.huang@intel.com> Yixun Lan <dlan@kernel.org> <dlan@gentoo.org> Yixun Lan <dlan@kernel.org> <yixun.lan@amlogic.com> -Yosry Ahmed <yosry.ahmed@linux.dev> <yosryahmed@google.com> +Yosry Ahmed <yosry@kernel.org> <yosryahmed@google.com> +Yosry Ahmed <yosry@kernel.org> <yosry.ahmed@linux.dev> Yu-Chun Lin <eleanor.lin@realtek.com> <eleanor15x@gmail.com> Yusuke Goda <goda.yusuke@renesas.com> Zack Rusin <zack.rusin@broadcom.com> <zackr@vmware.com> @@ -1242,6 +1242,10 @@ N: Veaceslav Falico E: vfalico@gmail.com D: Co-maintainer and co-author of the network bonding driver. +N: Thomas Falcon +E: tlfalcon@linux.ibm.com +D: Initial author of the IBM ibmvnic network driver + N: János Farkas E: chexum@shadow.banki.hu D: romfs, various (mostly networking) fixes @@ -2415,6 +2419,10 @@ S: Am Muehlenweg 38 S: D53424 Remagen S: Germany +N: Jonathan Lemon +E: jonathan.lemon@gmail.com +D: OpenCompute PTP clock driver (ptp_ocp) + N: Colin Leroy E: colin@colino.net W: http://www.geekounet.org/ diff --git a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml index ec0c2168e4b9..6bcfff970117 100644 --- a/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml +++ b/Documentation/devicetree/bindings/net/can/nxp,sja1000.yaml @@ -87,6 +87,7 @@ required: allOf: - $ref: can-controller.yaml# + - $ref: /schemas/memory-controllers/mc-peripheral-props.yaml - if: properties: compatible: diff --git a/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml b/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml index d6b3b5a5c0b3..fe4ac9350ba0 100644 --- a/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml +++ b/Documentation/devicetree/bindings/regulator/mt6359-regulator.yaml @@ -287,7 +287,7 @@ examples: regulator-max-microvolt = <1700000>; }; mt6359_vrfck_1_ldo_reg: ldo_vrfck_1 { - regulator-name = "vrfck"; + regulator-name = "vrfck_1"; regulator-min-microvolt = <1240000>; regulator-max-microvolt = <1600000>; }; @@ -309,7 +309,7 @@ examples: regulator-max-microvolt = <3300000>; }; mt6359_vemc_1_ldo_reg: ldo_vemc_1 { - regulator-name = "vemc"; + regulator-name = "vemc_1"; regulator-min-microvolt = <2500000>; regulator-max-microvolt = <3300000>; }; diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml index 81838577cf9c..8ebebcebca16 100644 --- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml +++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml @@ -26,21 +26,6 @@ allOf: properties: compatible: contains: - enum: - - baikal,bt1-sys-ssi - then: - properties: - mux-controls: - maxItems: 1 - required: - - mux-controls - else: - required: - - interrupts - - if: - properties: - compatible: - contains: const: amd,pensando-elba-spi then: required: @@ -75,10 +60,6 @@ properties: const: intel,mountevans-imc-ssi - description: AMD Pensando Elba SoC SPI Controller const: amd,pensando-elba-spi - - description: Baikal-T1 SPI Controller - const: baikal,bt1-ssi - - description: Baikal-T1 System Boot SPI Controller - const: baikal,bt1-sys-ssi - description: Canaan Kendryte K210 SoS SPI Controller const: canaan,k210-spi - description: Renesas RZ/N1 SPI Controller @@ -170,6 +151,7 @@ required: - "#address-cells" - "#size-cells" - clocks + - interrupts examples: - | @@ -190,15 +172,4 @@ examples: rx-sample-delay-ns = <7>; }; }; - - | - spi@1f040100 { - compatible = "baikal,bt1-sys-ssi"; - reg = <0x1f040100 0x900>, - <0x1c000000 0x1000000>; - #address-cells = <1>; - #size-cells = <0>; - mux-controls = <&boot_mux>; - clocks = <&ccu_sys>; - clock-names = "ssi_clk"; - }; ... diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml index badb2fe57c98..f87b5a05e5e9 100644 --- a/Documentation/netlink/specs/nfsd.yaml +++ b/Documentation/netlink/specs/nfsd.yaml @@ -152,7 +152,7 @@ operations: - compound-ops - name: threads-set - doc: set the number of running threads + doc: set the maximum number of running threads attribute-set: server flags: [admin-perm] do: @@ -165,7 +165,7 @@ operations: - min-threads - name: threads-get - doc: get the number of running threads + doc: get the maximum number of running threads attribute-set: server do: reply: diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index fc5736839edd..6f85e1b321dd 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1396,7 +1396,10 @@ or its flags may be modified, but it may not be resized. Memory for the region is taken starting at the address denoted by the field userspace_addr, which must point at user addressable memory for the entire memory slot size. Any object may back this memory, including -anonymous memory, ordinary files, and hugetlbfs. +anonymous memory, ordinary files, and hugetlbfs. Changes in the backing +of the memory region are automatically reflected into the guest. +For example, an mmap() that affects the region will be made visible +immediately. Another example is madvise(MADV_DROP). On architectures that support a form of address tagging, userspace_addr must be an untagged address. @@ -1412,11 +1415,6 @@ use it. The latter can be set, if KVM_CAP_READONLY_MEM capability allows it, to make a new slot read-only. In this case, writes to this memory will be posted to userspace as KVM_EXIT_MMIO exits. -When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of -the memory region are automatically reflected into the guest. For example, an -mmap() that affects the region will be made visible immediately. Another -example is madvise(MADV_DROP). - For TDX guest, deleting/moving memory region loses guest memory contents. Read only region isn't supported. Only as-id 0 is supported. diff --git a/MAINTAINERS b/MAINTAINERS index 2265e2c9bfbe..7b277d5bf3d1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -993,10 +993,8 @@ F: Documentation/devicetree/bindings/thermal/amazon,al-thermal.yaml F: drivers/thermal/thermal_mmio.c AMAZON ETHERNET DRIVERS -M: Shay Agroskin <shayagr@amazon.com> M: Arthur Kiyanovski <akiyano@amazon.com> -R: David Arinzon <darinzon@amazon.com> -R: Saeed Bishara <saeedb@amazon.com> +M: David Arinzon <darinzon@amazon.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/amazon/ena.rst @@ -4617,7 +4615,6 @@ F: drivers/bluetooth/ BLUETOOTH SUBSYSTEM M: Marcel Holtmann <marcel@holtmann.org> -M: Johan Hedberg <johan.hedberg@gmail.com> M: Luiz Augusto von Dentz <luiz.dentz@gmail.com> L: linux-bluetooth@vger.kernel.org S: Supported @@ -6212,6 +6209,7 @@ F: drivers/scsi/fnic/ CISCO SCSI HBA DRIVER M: Karan Tilak Kumar <kartilak@cisco.com> +M: Narsimhulu Musini <nmusini@cisco.com> M: Sesidhar Baddela <sebaddel@cisco.com> L: linux-scsi@vger.kernel.org S: Supported @@ -6278,7 +6276,7 @@ S: Maintained F: include/linux/clk.h CLOCKSOURCE, CLOCKEVENT DRIVERS -M: Daniel Lezcano <daniel.lezcano@linaro.org> +M: Daniel Lezcano <daniel.lezcano@kernel.org> M: Thomas Gleixner <tglx@kernel.org> L: linux-kernel@vger.kernel.org S: Supported @@ -6667,7 +6665,7 @@ F: rust/kernel/cpu.rs CPU IDLE TIME MANAGEMENT FRAMEWORK M: "Rafael J. Wysocki" <rafael@kernel.org> -M: Daniel Lezcano <daniel.lezcano@linaro.org> +M: Daniel Lezcano <daniel.lezcano@kernel.org> R: Christian Loehle <christian.loehle@arm.com> L: linux-pm@vger.kernel.org S: Maintained @@ -6697,7 +6695,7 @@ F: arch/x86/kernel/msr.c CPUIDLE DRIVER - ARM BIG LITTLE M: Lorenzo Pieralisi <lpieralisi@kernel.org> -M: Daniel Lezcano <daniel.lezcano@linaro.org> +M: Daniel Lezcano <daniel.lezcano@kernel.org> L: linux-pm@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -6705,7 +6703,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git F: drivers/cpuidle/cpuidle-big_little.c CPUIDLE DRIVER - ARM EXYNOS -M: Daniel Lezcano <daniel.lezcano@linaro.org> +M: Daniel Lezcano <daniel.lezcano@kernel.org> M: Kukjin Kim <kgene@kernel.org> R: Krzysztof Kozlowski <krzk@kernel.org> L: linux-pm@vger.kernel.org @@ -10170,8 +10168,8 @@ F: drivers/i2c/busses/i2c-cpm.c FREESCALE IMX / MXC FEC DRIVER M: Wei Fang <wei.fang@nxp.com> +R: Frank Li <frank.li@nxp.com> R: Shenwei Wang <shenwei.wang@nxp.com> -R: Clark Wang <xiaoning.wang@nxp.com> L: imx@lists.linux.dev L: netdev@vger.kernel.org S: Maintained @@ -10483,7 +10481,7 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/trace/ftrace* F: arch/*/*/*/*ftrace* F: arch/*/*/*ftrace* -F: include/*/ftrace.h +F: include/*/*ftrace* F: kernel/trace/fgraph.c F: kernel/trace/ftrace* F: samples/ftrace @@ -12215,7 +12213,6 @@ IBM Power SRIOV Virtual NIC Device Driver M: Haren Myneni <haren@linux.ibm.com> M: Rick Lindsley <ricklind@linux.ibm.com> R: Nick Child <nnac123@linux.ibm.com> -R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/ibm/ibmvnic.* @@ -15374,10 +15371,8 @@ F: drivers/crypto/marvell/ F: include/linux/soc/marvell/octeontx2/ MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2) -M: Mirko Lindner <mlindner@marvell.com> -M: Stephen Hemminger <stephen@networkplumber.org> L: netdev@vger.kernel.org -S: Odd fixes +S: Orphan F: drivers/net/ethernet/marvell/sk* MARVELL LIBERTAS WIRELESS DRIVER @@ -15474,7 +15469,6 @@ MARVELL OCTEONTX2 RVU ADMIN FUNCTION DRIVER M: Sunil Goutham <sgoutham@marvell.com> M: Linu Cherian <lcherian@marvell.com> M: Geetha sowjanya <gakula@marvell.com> -M: Jerin Jacob <jerinj@marvell.com> M: hariprasad <hkelam@marvell.com> M: Subbaraya Sundeep <sbhatta@marvell.com> L: netdev@vger.kernel.org @@ -15489,7 +15483,7 @@ S: Supported F: drivers/perf/marvell_pem_pmu.c MARVELL PRESTERA ETHERNET SWITCH DRIVER -M: Taras Chornyi <taras.chornyi@plvision.eu> +M: Elad Nachman <enachman@marvell.com> S: Supported W: https://github.com/Marvell-switching/switchdev-prestera F: drivers/net/ethernet/marvell/prestera/ @@ -16163,7 +16157,6 @@ F: drivers/dma/mediatek/ MEDIATEK ETHERNET DRIVER M: Felix Fietkau <nbd@nbd.name> -M: Sean Wang <sean.wang@mediatek.com> M: Lorenzo Bianconi <lorenzo@kernel.org> L: netdev@vger.kernel.org S: Maintained @@ -16356,8 +16349,6 @@ F: include/soc/mediatek/smi.h MEDIATEK SWITCH DRIVER M: Chester A. Unal <chester.a.unal@arinc9.com> M: Daniel Golle <daniel@makrotopia.org> -M: DENG Qingfang <dqfext@gmail.com> -M: Sean Wang <sean.wang@mediatek.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mt7530-mdio.c @@ -16654,7 +16645,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> -R: Vlastimil Babka <vbabka@suse.cz> +R: Vlastimil Babka <vbabka@kernel.org> R: Mike Rapoport <rppt@kernel.org> R: Suren Baghdasaryan <surenb@google.com> R: Michal Hocko <mhocko@suse.com> @@ -16784,7 +16775,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: David Hildenbrand <david@kernel.org> R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> -R: Vlastimil Babka <vbabka@suse.cz> +R: Vlastimil Babka <vbabka@kernel.org> R: Mike Rapoport <rppt@kernel.org> R: Suren Baghdasaryan <surenb@google.com> R: Michal Hocko <mhocko@suse.com> @@ -16839,7 +16830,7 @@ F: mm/oom_kill.c MEMORY MANAGEMENT - PAGE ALLOCATOR M: Andrew Morton <akpm@linux-foundation.org> -M: Vlastimil Babka <vbabka@suse.cz> +M: Vlastimil Babka <vbabka@kernel.org> R: Suren Baghdasaryan <surenb@google.com> R: Michal Hocko <mhocko@suse.com> R: Brendan Jackman <jackmanb@google.com> @@ -16885,7 +16876,7 @@ M: David Hildenbrand <david@kernel.org> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> R: Rik van Riel <riel@surriel.com> R: Liam R. Howlett <Liam.Howlett@oracle.com> -R: Vlastimil Babka <vbabka@suse.cz> +R: Vlastimil Babka <vbabka@kernel.org> R: Harry Yoo <harry.yoo@oracle.com> R: Jann Horn <jannh@google.com> L: linux-mm@kvack.org @@ -16984,7 +16975,7 @@ MEMORY MAPPING M: Andrew Morton <akpm@linux-foundation.org> M: Liam R. Howlett <Liam.Howlett@oracle.com> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> -R: Vlastimil Babka <vbabka@suse.cz> +R: Vlastimil Babka <vbabka@kernel.org> R: Jann Horn <jannh@google.com> R: Pedro Falcato <pfalcato@suse.de> L: linux-mm@kvack.org @@ -17014,7 +17005,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: Suren Baghdasaryan <surenb@google.com> M: Liam R. Howlett <Liam.Howlett@oracle.com> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> -R: Vlastimil Babka <vbabka@suse.cz> +R: Vlastimil Babka <vbabka@kernel.org> R: Shakeel Butt <shakeel.butt@linux.dev> L: linux-mm@kvack.org S: Maintained @@ -17030,7 +17021,7 @@ M: Andrew Morton <akpm@linux-foundation.org> M: Liam R. Howlett <Liam.Howlett@oracle.com> M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> M: David Hildenbrand <david@kernel.org> -R: Vlastimil Babka <vbabka@suse.cz> +R: Vlastimil Babka <vbabka@kernel.org> R: Jann Horn <jannh@google.com> L: linux-mm@kvack.org S: Maintained @@ -19225,8 +19216,6 @@ F: tools/objtool/ OCELOT ETHERNET SWITCH DRIVER M: Vladimir Oltean <vladimir.oltean@nxp.com> -M: Claudiu Manoil <claudiu.manoil@nxp.com> -M: Alexandre Belloni <alexandre.belloni@bootlin.com> M: UNGLinuxDriver@microchip.com L: netdev@vger.kernel.org S: Supported @@ -19812,7 +19801,6 @@ F: arch/*/boot/dts/ F: include/dt-bindings/ OPENCOMPUTE PTP CLOCK DRIVER -M: Jonathan Lemon <jonathan.lemon@gmail.com> M: Vadim Fedorenko <vadim.fedorenko@linux.dev> L: netdev@vger.kernel.org S: Maintained @@ -20507,7 +20495,7 @@ F: Documentation/devicetree/bindings/pci/hisilicon,kirin-pcie.yaml F: drivers/pci/controller/dwc/pcie-kirin.c PCIE DRIVER FOR HISILICON STB -M: Shawn Guo <shawn.guo@linaro.org> +M: Shawn Guo <shawnguo@kernel.org> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/hisilicon-histb-pcie.txt @@ -21456,9 +21444,8 @@ S: Supported F: drivers/scsi/qedi/ QLOGIC QL4xxx ETHERNET DRIVER -M: Manish Chopra <manishc@marvell.com> L: netdev@vger.kernel.org -S: Maintained +S: Orphan F: drivers/net/ethernet/qlogic/qed/ F: drivers/net/ethernet/qlogic/qede/ F: include/linux/qed/ @@ -23172,7 +23159,7 @@ K: \b(?i:rust)\b RUST [ALLOC] M: Danilo Krummrich <dakr@kernel.org> R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> -R: Vlastimil Babka <vbabka@suse.cz> +R: Vlastimil Babka <vbabka@kernel.org> R: Liam R. Howlett <Liam.Howlett@oracle.com> R: Uladzislau Rezki <urezki@gmail.com> L: rust-for-linux@vger.kernel.org @@ -24348,7 +24335,7 @@ F: Documentation/devicetree/bindings/nvmem/layouts/kontron,sl28-vpd.yaml F: drivers/nvmem/layouts/sl28vpd.c SLAB ALLOCATOR -M: Vlastimil Babka <vbabka@suse.cz> +M: Vlastimil Babka <vbabka@kernel.org> M: Andrew Morton <akpm@linux-foundation.org> R: Christoph Lameter <cl@gentwo.org> R: David Rientjes <rientjes@google.com> @@ -26215,7 +26202,7 @@ F: drivers/media/radio/radio-raremono.c THERMAL M: Rafael J. Wysocki <rafael@kernel.org> -M: Daniel Lezcano <daniel.lezcano@linaro.org> +M: Daniel Lezcano <daniel.lezcano@kernel.org> R: Zhang Rui <rui.zhang@intel.com> R: Lukasz Luba <lukasz.luba@arm.com> L: linux-pm@vger.kernel.org @@ -26245,7 +26232,7 @@ F: drivers/thermal/amlogic_thermal.c THERMAL/CPU_COOLING M: Amit Daniel Kachhap <amit.kachhap@gmail.com> -M: Daniel Lezcano <daniel.lezcano@linaro.org> +M: Daniel Lezcano <daniel.lezcano@kernel.org> M: Viresh Kumar <viresh.kumar@linaro.org> R: Lukasz Luba <lukasz.luba@arm.com> L: linux-pm@vger.kernel.org @@ -29184,7 +29171,7 @@ K: zstd ZSWAP COMPRESSED SWAP CACHING M: Johannes Weiner <hannes@cmpxchg.org> -M: Yosry Ahmed <yosry.ahmed@linux.dev> +M: Yosry Ahmed <yosry@kernel.org> M: Nhat Pham <nphamcs@gmail.com> R: Chengming Zhou <chengming.zhou@linux.dev> L: linux-mm@kvack.org @@ -2,7 +2,7 @@ VERSION = 7 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 83e03abbb2ca..8cbd1e96fd50 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -264,19 +264,33 @@ __iowrite64_copy(void __iomem *to, const void *from, size_t count) typedef int (*ioremap_prot_hook_t)(phys_addr_t phys_addr, size_t size, pgprot_t *prot); int arm64_ioremap_prot_hook_register(const ioremap_prot_hook_t hook); +void __iomem *__ioremap_prot(phys_addr_t phys, size_t size, pgprot_t prot); -#define ioremap_prot ioremap_prot +static inline void __iomem *ioremap_prot(phys_addr_t phys, size_t size, + pgprot_t user_prot) +{ + pgprot_t prot; + ptdesc_t user_prot_val = pgprot_val(user_prot); + + if (WARN_ON_ONCE(!(user_prot_val & PTE_USER))) + return NULL; -#define _PAGE_IOREMAP PROT_DEVICE_nGnRE + prot = __pgprot_modify(PAGE_KERNEL, PTE_ATTRINDX_MASK, + user_prot_val & PTE_ATTRINDX_MASK); + return __ioremap_prot(phys, size, prot); +} +#define ioremap_prot ioremap_prot +#define ioremap(addr, size) \ + __ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRE)) #define ioremap_wc(addr, size) \ - ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC)) + __ioremap_prot((addr), (size), __pgprot(PROT_NORMAL_NC)) #define ioremap_np(addr, size) \ - ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE)) + __ioremap_prot((addr), (size), __pgprot(PROT_DEVICE_nGnRnE)) #define ioremap_encrypted(addr, size) \ - ioremap_prot((addr), (size), PAGE_KERNEL) + __ioremap_prot((addr), (size), PAGE_KERNEL) /* * io{read,write}{16,32,64}be() macros @@ -297,7 +311,7 @@ static inline void __iomem *ioremap_cache(phys_addr_t addr, size_t size) if (pfn_is_map_memory(__phys_to_pfn(addr))) return (void __iomem *)__phys_to_virt(addr); - return ioremap_prot(addr, size, __pgprot(PROT_NORMAL)); + return __ioremap_prot(addr, size, __pgprot(PROT_NORMAL)); } /* diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 5d5a3bbdb95e..2ca264b3db5f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -1616,7 +1616,8 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); (kvm_has_feat((k), ID_AA64MMFR3_EL1, S1PIE, IMP)) #define kvm_has_s1poe(k) \ - (kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP)) + (system_supports_poe() && \ + kvm_has_feat((k), ID_AA64MMFR3_EL1, S1POE, IMP)) #define kvm_has_ras(k) \ (kvm_has_feat((k), ID_AA64PFR0_EL1, RAS, IMP)) diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 905c658057a4..091544e6af44 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -397,6 +397,8 @@ int kvm_vcpu_allocate_vncr_tlb(struct kvm_vcpu *vcpu); int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu); void kvm_handle_s1e2_tlbi(struct kvm_vcpu *vcpu, u32 inst, u64 val); +u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime); + #define vncr_fixmap(c) \ ({ \ u32 __c = (c); \ diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index d27e8872fe3c..2b32639160de 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -164,9 +164,6 @@ static inline bool __pure lpa2_is_enabled(void) #define _PAGE_GCS (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_WRITE | PTE_USER) #define _PAGE_GCS_RO (_PAGE_DEFAULT | PTE_NG | PTE_UXN | PTE_USER) -#define PAGE_GCS __pgprot(_PAGE_GCS) -#define PAGE_GCS_RO __pgprot(_PAGE_GCS_RO) - #define PIE_E0 ( \ PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS), PIE_GCS) | \ PIRx_ELx_PERM_PREP(pte_pi_index(_PAGE_GCS_RO), PIE_R) | \ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index a2d65d7d6aae..1416e652612b 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -31,19 +31,11 @@ */ #define __TLBI_0(op, arg) asm (ARM64_ASM_PREAMBLE \ "tlbi " #op "\n" \ - ALTERNATIVE("nop\n nop", \ - "dsb ish\n tlbi " #op, \ - ARM64_WORKAROUND_REPEAT_TLBI, \ - CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ : : ) #define __TLBI_1(op, arg) asm (ARM64_ASM_PREAMBLE \ - "tlbi " #op ", %0\n" \ - ALTERNATIVE("nop\n nop", \ - "dsb ish\n tlbi " #op ", %0", \ - ARM64_WORKAROUND_REPEAT_TLBI, \ - CONFIG_ARM64_WORKAROUND_REPEAT_TLBI) \ - : : "r" (arg)) + "tlbi " #op ", %x0\n" \ + : : "rZ" (arg)) #define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg) @@ -181,6 +173,34 @@ static inline unsigned long get_trans_granule(void) (__pages >> (5 * (scale) + 1)) - 1; \ }) +#define __repeat_tlbi_sync(op, arg...) \ +do { \ + if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI)) \ + break; \ + __tlbi(op, ##arg); \ + dsb(ish); \ +} while (0) + +/* + * Complete broadcast TLB maintenance issued by the host which invalidates + * stage 1 information in the host's own translation regime. + */ +static inline void __tlbi_sync_s1ish(void) +{ + dsb(ish); + __repeat_tlbi_sync(vale1is, 0); +} + +/* + * Complete broadcast TLB maintenance issued by hyp code which invalidates + * stage 1 translation information in any translation regime. + */ +static inline void __tlbi_sync_s1ish_hyp(void) +{ + dsb(ish); + __repeat_tlbi_sync(vale2is, 0); +} + /* * TLB Invalidation * ================ @@ -279,7 +299,7 @@ static inline void flush_tlb_all(void) { dsb(ishst); __tlbi(vmalle1is); - dsb(ish); + __tlbi_sync_s1ish(); isb(); } @@ -291,7 +311,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm) asid = __TLBI_VADDR(0, ASID(mm)); __tlbi(aside1is, asid); __tlbi_user(aside1is, asid); - dsb(ish); + __tlbi_sync_s1ish(); mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); } @@ -345,20 +365,11 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { flush_tlb_page_nosync(vma, uaddr); - dsb(ish); + __tlbi_sync_s1ish(); } static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) { - /* - * TLB flush deferral is not required on systems which are affected by - * ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation - * will have two consecutive TLBI instructions with a dsb(ish) in between - * defeating the purpose (i.e save overall 'dsb ish' cost). - */ - if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI)) - return false; - return true; } @@ -374,7 +385,7 @@ static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) */ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) { - dsb(ish); + __tlbi_sync_s1ish(); } /* @@ -509,7 +520,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, { __flush_tlb_range_nosync(vma->vm_mm, start, end, stride, last_level, tlb_level); - dsb(ish); + __tlbi_sync_s1ish(); } static inline void local_flush_tlb_contpte(struct vm_area_struct *vma, @@ -557,7 +568,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end dsb(ishst); __flush_tlb_range_op(vaale1is, start, pages, stride, 0, TLBI_TTL_UNKNOWN, false, lpa2_is_enabled()); - dsb(ish); + __tlbi_sync_s1ish(); isb(); } @@ -571,7 +582,7 @@ static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr) dsb(ishst); __tlbi(vaae1is, addr); - dsb(ish); + __tlbi_sync_s1ish(); isb(); } diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index af90128cfed5..a9d884fd1d00 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -377,7 +377,7 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) prot = __acpi_get_writethrough_mem_attribute(); } } - return ioremap_prot(phys, size, prot); + return __ioremap_prot(phys, size, prot); } /* diff --git a/arch/arm64/kernel/sys_compat.c b/arch/arm64/kernel/sys_compat.c index 4a609e9b65de..b9d4998c97ef 100644 --- a/arch/arm64/kernel/sys_compat.c +++ b/arch/arm64/kernel/sys_compat.c @@ -37,7 +37,7 @@ __do_compat_cache_op(unsigned long start, unsigned long end) * We pick the reserved-ASID to minimise the impact. */ __tlbi(aside1is, __TLBI_VADDR(0, 0)); - dsb(ish); + __tlbi_sync_s1ish(); } ret = caches_clean_inval_user_pou(start, start + chunk); diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 3fe1faab0362..b32f13358fbb 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -400,16 +400,25 @@ static inline int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val) { /* - * Abort call on counterless CPU or when interrupts are - * disabled - can lead to deadlock in smp sync call. + * Abort call on counterless CPU. */ if (!cpu_has_amu_feat(cpu)) return -EOPNOTSUPP; - if (WARN_ON_ONCE(irqs_disabled())) - return -EPERM; - - smp_call_function_single(cpu, func, val, 1); + if (irqs_disabled()) { + /* + * When IRQs are disabled (tick path: sched_tick -> + * topology_scale_freq_tick or cppc_scale_freq_tick), only local + * CPU counter reads are allowed. Remote CPU counter read would + * require smp_call_function_single() which is unsafe with IRQs + * disabled. + */ + if (WARN_ON_ONCE(cpu != smp_processor_id())) + return -EPERM; + func(val); + } else { + smp_call_function_single(cpu, func, val, 1); + } return 0; } diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 4f803fd1c99a..7d1f22fd490b 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,7 +21,6 @@ menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" select KVM_COMMON select KVM_GENERIC_HARDWARE_ENABLING - select KVM_GENERIC_MMU_NOTIFIER select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_GENERIC_DIRTYLOG_READ_PROTECT diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 29f0326f7e00..410ffd41fd73 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -358,7 +358,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_IOEVENTFD: case KVM_CAP_USER_MEMORY: - case KVM_CAP_SYNC_MMU: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_ONE_REG: case KVM_CAP_ARM_PSCI: diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 885bd5bb2f41..6588ea251ed7 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -540,31 +540,8 @@ static int walk_s1(struct kvm_vcpu *vcpu, struct s1_walk_info *wi, wr->pa |= va & GENMASK_ULL(va_bottom - 1, 0); wr->nG = (wi->regime != TR_EL2) && (desc & PTE_NG); - if (wr->nG) { - u64 asid_ttbr, tcr; - - switch (wi->regime) { - case TR_EL10: - tcr = vcpu_read_sys_reg(vcpu, TCR_EL1); - asid_ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL1) : - vcpu_read_sys_reg(vcpu, TTBR0_EL1)); - break; - case TR_EL20: - tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); - asid_ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL2) : - vcpu_read_sys_reg(vcpu, TTBR0_EL2)); - break; - default: - BUG(); - } - - wr->asid = FIELD_GET(TTBR_ASID_MASK, asid_ttbr); - if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || - !(tcr & TCR_ASID16)) - wr->asid &= GENMASK(7, 0); - } + if (wr->nG) + wr->asid = get_asid_by_regime(vcpu, wi->regime); return 0; diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index ae8391baebc3..218976287d3f 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -271,7 +271,7 @@ static void fixmap_clear_slot(struct hyp_fixmap_slot *slot) */ dsb(ishst); __tlbi_level(vale2is, __TLBI_VADDR(addr, 0), level); - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); } diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 8e29d7734a15..2f029bfe4755 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -342,6 +342,7 @@ static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struc /* No restrictions for non-protected VMs. */ if (!kvm_vm_is_protected(kvm)) { hyp_vm->kvm.arch.flags = host_arch_flags; + hyp_vm->kvm.arch.flags &= ~BIT_ULL(KVM_ARCH_FLAG_ID_REGS_INITIALIZED); bitmap_copy(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features, @@ -391,7 +392,7 @@ static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu) if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE)) return; - sve_state = kern_hyp_va(hyp_vcpu->vcpu.arch.sve_state); + sve_state = hyp_vcpu->vcpu.arch.sve_state; hyp_unpin_shared_mem(sve_state, sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu)); } @@ -471,6 +472,35 @@ err: return ret; } +static int vm_copy_id_regs(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu); + const struct kvm *host_kvm = hyp_vm->host_kvm; + struct kvm *kvm = &hyp_vm->kvm; + + if (!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &host_kvm->arch.flags)) + return -EINVAL; + + if (test_and_set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags)) + return 0; + + memcpy(kvm->arch.id_regs, host_kvm->arch.id_regs, sizeof(kvm->arch.id_regs)); + + return 0; +} + +static int pkvm_vcpu_init_sysregs(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + int ret = 0; + + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + kvm_init_pvm_id_regs(&hyp_vcpu->vcpu); + else + ret = vm_copy_id_regs(hyp_vcpu); + + return ret; +} + static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, struct pkvm_hyp_vm *hyp_vm, struct kvm_vcpu *host_vcpu) @@ -490,8 +520,9 @@ static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags); hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; - if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) - kvm_init_pvm_id_regs(&hyp_vcpu->vcpu); + ret = pkvm_vcpu_init_sysregs(hyp_vcpu); + if (ret) + goto done; ret = pkvm_vcpu_init_traps(hyp_vcpu); if (ret) diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index 48da9ca9763f..3dc1ce0d27fe 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -169,7 +169,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, */ dsb(ish); __tlbi(vmalle1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); exit_vmid_context(&cxt); @@ -226,7 +226,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, dsb(ish); __tlbi(vmalle1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); exit_vmid_context(&cxt); @@ -240,7 +240,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) enter_vmid_context(mmu, &cxt, false); __tlbi(vmalls12e1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); exit_vmid_context(&cxt); @@ -266,5 +266,5 @@ void __kvm_flush_vm_context(void) /* Same remark as in enter_vmid_context() */ dsb(ish); __tlbi(alle1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); } diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 0e4ddd28ef5d..9b480f947da2 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -501,7 +501,7 @@ static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, *unmapped += granule; } - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); mm_ops->put_page(ctx->ptep); diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c index ec2569818629..35855dadfb1b 100644 --- a/arch/arm64/kvm/hyp/vhe/tlb.c +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -115,7 +115,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, */ dsb(ish); __tlbi(vmalle1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); exit_vmid_context(&cxt); @@ -176,7 +176,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, dsb(ish); __tlbi(vmalle1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); exit_vmid_context(&cxt); @@ -192,7 +192,7 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) enter_vmid_context(mmu, &cxt); __tlbi(vmalls12e1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); exit_vmid_context(&cxt); @@ -217,7 +217,7 @@ void __kvm_flush_vm_context(void) { dsb(ishst); __tlbi(alle1is); - dsb(ish); + __tlbi_sync_s1ish_hyp(); } /* @@ -358,7 +358,7 @@ int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding) default: ret = -EINVAL; } - dsb(ish); + __tlbi_sync_s1ish_hyp(); isb(); if (mmu) diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 070a01e53fcb..ec2eee857208 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1754,14 +1754,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, } /* - * Both the canonical IPA and fault IPA must be hugepage-aligned to - * ensure we find the right PFN and lay down the mapping in the right - * place. + * Both the canonical IPA and fault IPA must be aligned to the + * mapping size to ensure we find the right PFN and lay down the + * mapping in the right place. */ - if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) { - fault_ipa &= ~(vma_pagesize - 1); - ipa &= ~(vma_pagesize - 1); - } + fault_ipa = ALIGN_DOWN(fault_ipa, vma_pagesize); + ipa = ALIGN_DOWN(ipa, vma_pagesize); gfn = ipa >> PAGE_SHIFT; mte_allowed = kvm_vma_mte_allowed(vma); diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index 620126d1f0dc..12c9f6e8dfda 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -854,6 +854,33 @@ int kvm_inject_s2_fault(struct kvm_vcpu *vcpu, u64 esr_el2) return kvm_inject_nested_sync(vcpu, esr_el2); } +u16 get_asid_by_regime(struct kvm_vcpu *vcpu, enum trans_regime regime) +{ + enum vcpu_sysreg ttbr_elx; + u64 tcr; + u16 asid; + + switch (regime) { + case TR_EL10: + tcr = vcpu_read_sys_reg(vcpu, TCR_EL1); + ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL1 : TTBR0_EL1; + break; + case TR_EL20: + tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); + ttbr_elx = (tcr & TCR_A1) ? TTBR1_EL2 : TTBR0_EL2; + break; + default: + BUG(); + } + + asid = FIELD_GET(TTBRx_EL1_ASID, vcpu_read_sys_reg(vcpu, ttbr_elx)); + if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || + !(tcr & TCR_ASID16)) + asid &= GENMASK(7, 0); + + return asid; +} + static void invalidate_vncr(struct vncr_tlb *vt) { vt->valid = false; @@ -1154,9 +1181,6 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm) { int i; - if (!kvm->arch.nested_mmus_size) - return; - for (i = 0; i < kvm->arch.nested_mmus_size; i++) { struct kvm_s2_mmu *mmu = &kvm->arch.nested_mmus[i]; @@ -1336,20 +1360,8 @@ static bool kvm_vncr_tlb_lookup(struct kvm_vcpu *vcpu) if (read_vncr_el2(vcpu) != vt->gva) return false; - if (vt->wr.nG) { - u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); - u64 ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL2) : - vcpu_read_sys_reg(vcpu, TTBR0_EL2)); - u16 asid; - - asid = FIELD_GET(TTBR_ASID_MASK, ttbr); - if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || - !(tcr & TCR_ASID16)) - asid &= GENMASK(7, 0); - - return asid == vt->wr.asid; - } + if (vt->wr.nG) + return get_asid_by_regime(vcpu, TR_EL20) == vt->wr.asid; return true; } @@ -1452,21 +1464,8 @@ static void kvm_map_l1_vncr(struct kvm_vcpu *vcpu) if (read_vncr_el2(vcpu) != vt->gva) return; - if (vt->wr.nG) { - u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); - u64 ttbr = ((tcr & TCR_A1) ? - vcpu_read_sys_reg(vcpu, TTBR1_EL2) : - vcpu_read_sys_reg(vcpu, TTBR0_EL2)); - u16 asid; - - asid = FIELD_GET(TTBR_ASID_MASK, ttbr); - if (!kvm_has_feat_enum(vcpu->kvm, ID_AA64MMFR0_EL1, ASIDBITS, 16) || - !(tcr & TCR_ASID16)) - asid &= GENMASK(7, 0); - - if (asid != vt->wr.asid) - return; - } + if (vt->wr.nG && get_asid_by_regime(vcpu, TR_EL20) != vt->wr.asid) + return; vt->cpu = smp_processor_id(); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index a7cd0badc20c..1b4cacb6e918 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1816,6 +1816,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, ID_AA64MMFR3_EL1_SCTLRX | ID_AA64MMFR3_EL1_S1POE | ID_AA64MMFR3_EL1_S1PIE; + + if (!system_supports_poe()) + val &= ~ID_AA64MMFR3_EL1_S1POE; break; case SYS_ID_MMFR4_EL1: val &= ~ID_MMFR4_EL1_CCIDX; diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c index d02341303899..e278e060e78a 100644 --- a/arch/arm64/lib/delay.c +++ b/arch/arm64/lib/delay.c @@ -32,7 +32,11 @@ static inline unsigned long xloops_to_cycles(unsigned long xloops) * Note that userspace cannot change the offset behind our back either, * as the vcpu mutex is held as long as KVM_RUN is in progress. */ -#define __delay_cycles() __arch_counter_get_cntvct_stable() +static cycles_t notrace __delay_cycles(void) +{ + guard(preempt_notrace)(); + return __arch_counter_get_cntvct_stable(); +} void __delay(unsigned long cycles) { diff --git a/arch/arm64/mm/ioremap.c b/arch/arm64/mm/ioremap.c index b12cbed9b5ad..6eef48ef6278 100644 --- a/arch/arm64/mm/ioremap.c +++ b/arch/arm64/mm/ioremap.c @@ -14,8 +14,8 @@ int arm64_ioremap_prot_hook_register(ioremap_prot_hook_t hook) return 0; } -void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, - pgprot_t pgprot) +void __iomem *__ioremap_prot(phys_addr_t phys_addr, size_t size, + pgprot_t pgprot) { unsigned long last_addr = phys_addr + size - 1; @@ -39,7 +39,7 @@ void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, return generic_ioremap_prot(phys_addr, size, pgprot); } -EXPORT_SYMBOL(ioremap_prot); +EXPORT_SYMBOL(__ioremap_prot); /* * Must be called after early_fixmap_init diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 08ee177432c2..92b2f5097a96 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -34,6 +34,8 @@ static pgprot_t protection_map[16] __ro_after_init = { [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC }; +static ptdesc_t gcs_page_prot __ro_after_init = _PAGE_GCS_RO; + /* * You really shouldn't be using read() or write() on /dev/mem. This might go * away in the future. @@ -73,9 +75,11 @@ static int __init adjust_protection_map(void) protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; } - if (lpa2_is_enabled()) + if (lpa2_is_enabled()) { for (int i = 0; i < ARRAY_SIZE(protection_map); i++) pgprot_val(protection_map[i]) &= ~PTE_SHARED; + gcs_page_prot &= ~PTE_SHARED; + } return 0; } @@ -87,7 +91,11 @@ pgprot_t vm_get_page_prot(vm_flags_t vm_flags) /* Short circuit GCS to avoid bloating the table. */ if (system_supports_gcs() && (vm_flags & VM_SHADOW_STACK)) { - prot = _PAGE_GCS_RO; + /* Honour mprotect(PROT_NONE) on shadow stack mappings */ + if (vm_flags & VM_ACCESS_FLAGS) + prot = gcs_page_prot; + else + prot = pgprot_val(protection_map[VM_NONE]); } else { prot = pgprot_val(protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 356d33c7a4ae..adf84962d579 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -2119,7 +2119,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) extable_offset = round_up(prog_size + PLT_TARGET_SIZE, extable_align); image_size = extable_offset + extable_size; ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr, - sizeof(u32), &header, &image_ptr, + sizeof(u64), &header, &image_ptr, jit_fill_hole); if (!ro_header) { prog = orig_prog; diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig index ed4f724db774..8e5213609975 100644 --- a/arch/loongarch/kvm/Kconfig +++ b/arch/loongarch/kvm/Kconfig @@ -28,7 +28,6 @@ config KVM select KVM_COMMON select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_GENERIC_HARDWARE_ENABLING - select KVM_GENERIC_MMU_NOTIFIER select KVM_MMIO select VIRT_XFER_TO_GUEST_WORK select SCHED_INFO diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c index 63fd40530aa9..5282158b8122 100644 --- a/arch/loongarch/kvm/vm.c +++ b/arch/loongarch/kvm/vm.c @@ -118,7 +118,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: case KVM_CAP_READONLY_MEM: - case KVM_CAP_SYNC_MMU: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_IOEVENTFD: case KVM_CAP_MP_STATE: diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index cc13cc35f208..b1b9a1d67758 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -23,7 +23,6 @@ config KVM select KVM_COMMON select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER select KVM_GENERIC_HARDWARE_ENABLING select HAVE_KVM_READONLY_MEM help diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index b0fb92fda4d4..29d9f630edfb 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -1035,7 +1035,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ONE_REG: case KVM_CAP_ENABLE_CAP: case KVM_CAP_READONLY_MEM: - case KVM_CAP_SYNC_MMU: case KVM_CAP_IMMEDIATE_EXIT: r = 1; break; diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index c9a2d50ff1b0..9a0d1c1aca6c 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -38,7 +38,6 @@ config KVM_BOOK3S_64_HANDLER config KVM_BOOK3S_PR_POSSIBLE bool select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER config KVM_BOOK3S_HV_POSSIBLE bool @@ -81,7 +80,6 @@ config KVM_BOOK3S_64_HV tristate "KVM for POWER7 and later using hypervisor mode in host" depends on KVM_BOOK3S_64 && PPC_POWERNV select KVM_BOOK3S_HV_POSSIBLE - select KVM_GENERIC_MMU_NOTIFIER select KVM_BOOK3S_HV_PMU select CMA help @@ -203,7 +201,6 @@ config KVM_E500V2 depends on !CONTEXT_TRACKING_USER select KVM select KVM_MMIO - select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500 guest kernels in virtual machines on E500v2 host processors. @@ -220,7 +217,6 @@ config KVM_E500MC select KVM select KVM_MMIO select KVM_BOOKE_HV - select KVM_GENERIC_MMU_NOTIFIER help Support running unmodified E500MC/E5500/E6500 guest kernels in virtual machines on E500MC/E5500/E6500 host processors. diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 9a89a6d98f97..00302399fc37 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -623,12 +623,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = !!(hv_enabled && kvmppc_hv_ops->enable_nested && !kvmppc_hv_ops->enable_nested(NULL)); break; -#endif - case KVM_CAP_SYNC_MMU: - BUILD_BUG_ON(!IS_ENABLED(CONFIG_KVM_GENERIC_MMU_NOTIFIER)); - r = 1; - break; -#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE case KVM_CAP_PPC_HTAB_FD: r = hv_enabled; break; diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index 77379f77840a..ec2cee0a39e0 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -30,7 +30,6 @@ config KVM select KVM_GENERIC_HARDWARE_ENABLING select KVM_MMIO select VIRT_XFER_TO_GUEST_WORK - select KVM_GENERIC_MMU_NOTIFIER select SCHED_INFO select GUEST_PERF_EVENTS if PERF_EVENTS help diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c index 7cbd2340c190..58bce57dc55b 100644 --- a/arch/riscv/kvm/vm.c +++ b/arch/riscv/kvm/vm.c @@ -181,7 +181,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_IOEVENTFD: case KVM_CAP_USER_MEMORY: - case KVM_CAP_SYNC_MMU: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_ONE_REG: case KVM_CAP_READONLY_MEM: diff --git a/arch/s390/include/asm/idle.h b/arch/s390/include/asm/idle.h index 09f763b9eb40..32536ee34aa0 100644 --- a/arch/s390/include/asm/idle.h +++ b/arch/s390/include/asm/idle.h @@ -19,9 +19,9 @@ struct s390_idle_data { unsigned long mt_cycles_enter[8]; }; +DECLARE_PER_CPU(struct s390_idle_data, s390_idle); + extern struct device_attribute dev_attr_idle_count; extern struct device_attribute dev_attr_idle_time_us; -void psw_idle(struct s390_idle_data *data, unsigned long psw_mask); - #endif /* _S390_IDLE_H */ diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h index 9d25fb35a042..b1db75d14e9d 100644 --- a/arch/s390/include/asm/vtime.h +++ b/arch/s390/include/asm/vtime.h @@ -2,6 +2,12 @@ #ifndef _S390_VTIME_H #define _S390_VTIME_H +#include <asm/lowcore.h> +#include <asm/cpu_mf.h> +#include <asm/idle.h> + +DECLARE_PER_CPU(u64, mt_cycles[8]); + static inline void update_timer_sys(void) { struct lowcore *lc = get_lowcore(); @@ -20,4 +26,32 @@ static inline void update_timer_mcck(void) lc->last_update_timer = lc->mcck_enter_timer; } +static inline void update_timer_idle(void) +{ + struct s390_idle_data *idle = this_cpu_ptr(&s390_idle); + struct lowcore *lc = get_lowcore(); + u64 cycles_new[8]; + int i, mtid; + + mtid = smp_cpu_mtid; + if (mtid) { + stcctm(MT_DIAG, mtid, cycles_new); + for (i = 0; i < mtid; i++) + __this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]); + } + /* + * This is a bit subtle: Forward last_update_clock so it excludes idle + * time. For correct steal time calculation in do_account_vtime() add + * passed wall time before idle_enter to steal_timer: + * During the passed wall time before idle_enter CPU time may have + * been accounted to system, hardirq, softirq, etc. lowcore fields. + * The accounted CPU times will be subtracted again from steal_timer + * when accumulated steal time is calculated in do_account_vtime(). + */ + lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock; + lc->last_update_clock = lc->int_clock; + lc->system_timer += lc->last_update_timer - idle->timer_idle_enter; + lc->last_update_timer = lc->sys_enter_timer; +} + #endif /* _S390_VTIME_H */ diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index dd55cc6bbc28..fb67b4abe68c 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -56,8 +56,6 @@ long sys_s390_pci_mmio_write(unsigned long, const void __user *, size_t); long sys_s390_pci_mmio_read(unsigned long, void __user *, size_t); long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user *return_code, unsigned long flags); -DECLARE_PER_CPU(u64, mt_cycles[8]); - unsigned long stack_alloc(void); void stack_free(unsigned long stack); diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c index 39cb8d0ae348..1f1b06b6b4ef 100644 --- a/arch/s390/kernel/idle.c +++ b/arch/s390/kernel/idle.c @@ -15,37 +15,22 @@ #include <trace/events/power.h> #include <asm/cpu_mf.h> #include <asm/cputime.h> +#include <asm/idle.h> #include <asm/nmi.h> #include <asm/smp.h> -#include "entry.h" -static DEFINE_PER_CPU(struct s390_idle_data, s390_idle); +DEFINE_PER_CPU(struct s390_idle_data, s390_idle); void account_idle_time_irq(void) { struct s390_idle_data *idle = this_cpu_ptr(&s390_idle); - struct lowcore *lc = get_lowcore(); unsigned long idle_time; - u64 cycles_new[8]; - int i; - if (smp_cpu_mtid) { - stcctm(MT_DIAG, smp_cpu_mtid, cycles_new); - for (i = 0; i < smp_cpu_mtid; i++) - this_cpu_add(mt_cycles[i], cycles_new[i] - idle->mt_cycles_enter[i]); - } - - idle_time = lc->int_clock - idle->clock_idle_enter; - - lc->steal_timer += idle->clock_idle_enter - lc->last_update_clock; - lc->last_update_clock = lc->int_clock; - - lc->system_timer += lc->last_update_timer - idle->timer_idle_enter; - lc->last_update_timer = lc->sys_enter_timer; + idle_time = get_lowcore()->int_clock - idle->clock_idle_enter; /* Account time spent with enabled wait psw loaded as idle time. */ - WRITE_ONCE(idle->idle_time, READ_ONCE(idle->idle_time) + idle_time); - WRITE_ONCE(idle->idle_count, READ_ONCE(idle->idle_count) + 1); + __atomic64_add(idle_time, &idle->idle_time); + __atomic64_add_const(1, &idle->idle_count); account_idle_time(cputime_to_nsecs(idle_time)); } diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index dcdc7e274848..049c557c452f 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -2377,7 +2377,7 @@ void __init setup_ipl(void) atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb); } -void s390_reset_system(void) +void __no_stack_protector s390_reset_system(void) { /* Disable prefixing */ set_prefix(0); diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index f81723bc8856..7fdf960191d3 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -146,6 +146,12 @@ void noinstr do_io_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); bool from_idle; + from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); + if (from_idle) { + update_timer_idle(); + regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); + } + irq_enter_rcu(); if (user_mode(regs)) { @@ -154,7 +160,6 @@ void noinstr do_io_irq(struct pt_regs *regs) current->thread.last_break = regs->last_break; } - from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); if (from_idle) account_idle_time_irq(); @@ -171,9 +176,6 @@ void noinstr do_io_irq(struct pt_regs *regs) set_irq_regs(old_regs); irqentry_exit(regs, state); - - if (from_idle) - regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); } void noinstr do_ext_irq(struct pt_regs *regs) @@ -182,6 +184,12 @@ void noinstr do_ext_irq(struct pt_regs *regs) struct pt_regs *old_regs = set_irq_regs(regs); bool from_idle; + from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); + if (from_idle) { + update_timer_idle(); + regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); + } + irq_enter_rcu(); if (user_mode(regs)) { @@ -194,7 +202,6 @@ void noinstr do_ext_irq(struct pt_regs *regs) regs->int_parm = get_lowcore()->ext_params; regs->int_parm_long = get_lowcore()->ext_params2; - from_idle = test_and_clear_cpu_flag(CIF_ENABLED_WAIT); if (from_idle) account_idle_time_irq(); @@ -203,9 +210,6 @@ void noinstr do_ext_irq(struct pt_regs *regs) irq_exit_rcu(); set_irq_regs(old_regs); irqentry_exit(regs, state); - - if (from_idle) - regs->psw.mask &= ~(PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_WAIT); } static void show_msi_interrupt(struct seq_file *p, int irq) diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 234a0ba30510..bf48744d0912 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -48,8 +48,7 @@ static inline void set_vtimer(u64 expires) static inline int virt_timer_forward(u64 elapsed) { - BUG_ON(!irqs_disabled()); - + lockdep_assert_irqs_disabled(); if (list_empty(&virt_timer_list)) return 0; elapsed = atomic64_add_return(elapsed, &virt_timer_elapsed); @@ -137,23 +136,16 @@ static int do_account_vtime(struct task_struct *tsk) lc->system_timer += timer; /* Update MT utilization calculation */ - if (smp_cpu_mtid && - time_after64(jiffies_64, this_cpu_read(mt_scaling_jiffies))) + if (smp_cpu_mtid && time_after64(jiffies_64, __this_cpu_read(mt_scaling_jiffies))) update_mt_scaling(); /* Calculate cputime delta */ - user = update_tsk_timer(&tsk->thread.user_timer, - READ_ONCE(lc->user_timer)); - guest = update_tsk_timer(&tsk->thread.guest_timer, - READ_ONCE(lc->guest_timer)); - system = update_tsk_timer(&tsk->thread.system_timer, - READ_ONCE(lc->system_timer)); - hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, - READ_ONCE(lc->hardirq_timer)); - softirq = update_tsk_timer(&tsk->thread.softirq_timer, - READ_ONCE(lc->softirq_timer)); - lc->steal_timer += - clock - user - guest - system - hardirq - softirq; + user = update_tsk_timer(&tsk->thread.user_timer, lc->user_timer); + guest = update_tsk_timer(&tsk->thread.guest_timer, lc->guest_timer); + system = update_tsk_timer(&tsk->thread.system_timer, lc->system_timer); + hardirq = update_tsk_timer(&tsk->thread.hardirq_timer, lc->hardirq_timer); + softirq = update_tsk_timer(&tsk->thread.softirq_timer, lc->softirq_timer); + lc->steal_timer += clock - user - guest - system - hardirq - softirq; /* Push account value */ if (user) { @@ -225,10 +217,6 @@ static u64 vtime_delta(void) return timer - lc->last_update_timer; } -/* - * Update process times based on virtual cpu times stored by entry.S - * to the lowcore fields user_timer, system_timer & steal_clock. - */ void vtime_account_kernel(struct task_struct *tsk) { struct lowcore *lc = get_lowcore(); @@ -238,27 +226,17 @@ void vtime_account_kernel(struct task_struct *tsk) lc->guest_timer += delta; else lc->system_timer += delta; - - virt_timer_forward(delta); } EXPORT_SYMBOL_GPL(vtime_account_kernel); void vtime_account_softirq(struct task_struct *tsk) { - u64 delta = vtime_delta(); - - get_lowcore()->softirq_timer += delta; - - virt_timer_forward(delta); + get_lowcore()->softirq_timer += vtime_delta(); } void vtime_account_hardirq(struct task_struct *tsk) { - u64 delta = vtime_delta(); - - get_lowcore()->hardirq_timer += delta; - - virt_timer_forward(delta); + get_lowcore()->hardirq_timer += vtime_delta(); } /* diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig index 917ac740513e..5b835bc6a194 100644 --- a/arch/s390/kvm/Kconfig +++ b/arch/s390/kvm/Kconfig @@ -28,9 +28,7 @@ config KVM select HAVE_KVM_INVALID_WAKEUPS select HAVE_KVM_NO_POLL select KVM_VFIO - select MMU_NOTIFIER select VIRT_XFER_TO_GUEST_WORK - select KVM_GENERIC_MMU_NOTIFIER select KVM_MMU_LOCKLESS_AGING help Support hosting paravirtualized guest machines using the SIE diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7a175d86cef0..bc7d6fa66eaf 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -601,7 +601,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) switch (ext) { case KVM_CAP_S390_PSW: case KVM_CAP_S390_GMAP: - case KVM_CAP_SYNC_MMU: #ifdef CONFIG_KVM_S390_UCONTROL case KVM_CAP_S390_UCONTROL: #endif diff --git a/arch/s390/mm/pfault.c b/arch/s390/mm/pfault.c index 2f829448c719..6ecd6b0a22a8 100644 --- a/arch/s390/mm/pfault.c +++ b/arch/s390/mm/pfault.c @@ -62,7 +62,7 @@ int __pfault_init(void) "0: nopr %%r7\n" EX_TABLE(0b, 0b) : [rc] "+d" (rc) - : [refbk] "a" (&pfault_init_refbk), "m" (pfault_init_refbk) + : [refbk] "a" (virt_to_phys(&pfault_init_refbk)), "m" (pfault_init_refbk) : "cc"); return rc; } @@ -84,7 +84,7 @@ void __pfault_fini(void) "0: nopr %%r7\n" EX_TABLE(0b, 0b) : - : [refbk] "a" (&pfault_fini_refbk), "m" (pfault_fini_refbk) + : [refbk] "a" (virt_to_phys(&pfault_fini_refbk)), "m" (pfault_fini_refbk) : "cc"); } diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c index 46ef88bc9c26..7613ab0ffb89 100644 --- a/arch/sparc/kernel/iommu.c +++ b/arch/sparc/kernel/iommu.c @@ -312,6 +312,8 @@ static dma_addr_t dma_4u_map_phys(struct device *dev, phys_addr_t phys, if (direction != DMA_TO_DEVICE) iopte_protection |= IOPTE_WRITE; + phys &= IO_PAGE_MASK; + for (i = 0; i < npages; i++, base++, phys += IO_PAGE_SIZE) iopte_val(*base) = iopte_protection | phys; diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index 440284cc804e..61f14b4c8f90 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -410,6 +410,8 @@ static dma_addr_t dma_4v_map_phys(struct device *dev, phys_addr_t phys, iommu_batch_start(dev, prot, entry); + phys &= IO_PAGE_MASK; + for (i = 0; i < npages; i++, phys += IO_PAGE_SIZE) { long err = iommu_batch_add(phys, mask); if (unlikely(err < 0L)) diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 012b2bcaa8a0..20fc33300a95 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -69,11 +69,11 @@ struct io_thread_req { }; -static struct io_thread_req * (*irq_req_buffer)[]; +static struct io_thread_req **irq_req_buffer; static struct io_thread_req *irq_remainder; static int irq_remainder_size; -static struct io_thread_req * (*io_req_buffer)[]; +static struct io_thread_req **io_req_buffer; static struct io_thread_req *io_remainder; static int io_remainder_size; @@ -398,7 +398,7 @@ static int thread_fd = -1; static int bulk_req_safe_read( int fd, - struct io_thread_req * (*request_buffer)[], + struct io_thread_req **request_buffer, struct io_thread_req **remainder, int *remainder_size, int max_recs @@ -465,7 +465,7 @@ static irqreturn_t ubd_intr(int irq, void *dev) &irq_remainder, &irq_remainder_size, UBD_REQ_BUFFER_SIZE)) >= 0) { for (i = 0; i < len / sizeof(struct io_thread_req *); i++) - ubd_end_request((*irq_req_buffer)[i]); + ubd_end_request(irq_req_buffer[i]); } if (len < 0 && len != -EAGAIN) @@ -1512,7 +1512,7 @@ void *io_thread(void *arg) } for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { - struct io_thread_req *req = (*io_req_buffer)[count]; + struct io_thread_req *req = io_req_buffer[count]; int i; io_count++; diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c index a9b72997103d..88c757ac8ccd 100644 --- a/arch/x86/entry/entry_fred.c +++ b/arch/x86/entry/entry_fred.c @@ -160,8 +160,6 @@ void __init fred_complete_exception_setup(void) static noinstr void fred_extint(struct pt_regs *regs) { unsigned int vector = regs->fred_ss.vector; - unsigned int index = array_index_nospec(vector - FIRST_SYSTEM_VECTOR, - NR_SYSTEM_VECTORS); if (WARN_ON_ONCE(vector < FIRST_EXTERNAL_VECTOR)) return; @@ -170,7 +168,8 @@ static noinstr void fred_extint(struct pt_regs *regs) irqentry_state_t state = irqentry_enter(regs); instrumentation_begin(); - sysvec_table[index](regs); + sysvec_table[array_index_nospec(vector - FIRST_SYSTEM_VECTOR, + NR_SYSTEM_VECTORS)](regs); instrumentation_end(); irqentry_exit(regs, state); } else { diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 5ed6e0b7e715..0a1d08136cc1 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6497,6 +6497,32 @@ static struct intel_uncore_type gnr_uncore_ubox = { .attr_update = uncore_alias_groups, }; +static struct uncore_event_desc gnr_uncore_imc_events[] = { + INTEL_UNCORE_EVENT_DESC(clockticks, "event=0x01,umask=0x00"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0, "event=0x05,umask=0xcf"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1, "event=0x06,umask=0xcf"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_read_sch1.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0, "event=0x05,umask=0xf0"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch0.unit, "MiB"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1, "event=0x06,umask=0xf0"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.scale, "6.103515625e-5"), + INTEL_UNCORE_EVENT_DESC(cas_count_write_sch1.unit, "MiB"), + { /* end: all zeroes */ }, +}; + +static struct intel_uncore_type gnr_uncore_imc = { + SPR_UNCORE_MMIO_COMMON_FORMAT(), + .name = "imc", + .fixed_ctr_bits = 48, + .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, + .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, + .event_descs = gnr_uncore_imc_events, +}; + static struct intel_uncore_type gnr_uncore_pciex8 = { SPR_UNCORE_PCI_COMMON_FORMAT(), .name = "pciex8", @@ -6544,7 +6570,7 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = { NULL, &spr_uncore_pcu, &gnr_uncore_ubox, - &spr_uncore_imc, + &gnr_uncore_imc, NULL, &gnr_uncore_upi, NULL, diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 9b4e04690e1a..80c1696d8d59 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -7,7 +7,7 @@ #include <linux/objtool.h> #include <asm/asm.h> -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ struct bug_entry; extern void __WARN_trap(struct bug_entry *bug, ...); #endif @@ -137,7 +137,7 @@ do { \ #ifdef HAVE_ARCH_BUG_FORMAT_ARGS -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/static_call_types.h> DECLARE_STATIC_CALL(WARN_trap, __WARN_trap); @@ -153,7 +153,7 @@ struct arch_va_list { struct sysv_va_list args; }; extern void *__warn_args(struct arch_va_list *args, struct pt_regs *regs); -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #define __WARN_bug_entry(flags, format) ({ \ struct bug_entry *bug; \ diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h index c40b9ebc1fb4..ab3fbbd947ed 100644 --- a/arch/x86/include/asm/cfi.h +++ b/arch/x86/include/asm/cfi.h @@ -111,6 +111,12 @@ extern bhi_thunk __bhi_args_end[]; struct pt_regs; +#ifdef CONFIG_CALL_PADDING +#define CFI_OFFSET (CONFIG_FUNCTION_PADDING_CFI+5) +#else +#define CFI_OFFSET 5 +#endif + #ifdef CONFIG_CFI enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); #define __bpfcall @@ -119,11 +125,9 @@ static inline int cfi_get_offset(void) { switch (cfi_mode) { case CFI_FINEIBT: - return 16; + return /* fineibt_prefix_size */ 16; case CFI_KCFI: - if (IS_ENABLED(CONFIG_CALL_PADDING)) - return 16; - return 5; + return CFI_OFFSET; default: return 0; } diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index a1193e9d65f2..462754b0bf8a 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -77,7 +77,7 @@ static __always_inline void native_local_irq_restore(unsigned long flags) #endif #ifndef CONFIG_PARAVIRT -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ /* * Used in the idle loop; sti takes one instruction cycle * to complete: @@ -95,7 +95,7 @@ static __always_inline void halt(void) { native_halt(); } -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif /* CONFIG_PARAVIRT */ #ifdef CONFIG_PARAVIRT_XXL diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 9d38ae744a2e..a7294656ad90 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -68,7 +68,7 @@ * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the * CFI symbol layout changes. * - * Without CALL_THUNKS: + * Without CALL_PADDING: * * .align FUNCTION_ALIGNMENT * __cfi_##name: @@ -77,7 +77,7 @@ * .long __kcfi_typeid_##name * name: * - * With CALL_THUNKS: + * With CALL_PADDING: * * .align FUNCTION_ALIGNMENT * __cfi_##name: diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index c55058f3d75e..409981468cba 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -20,7 +20,7 @@ #define PER_CPU_VAR(var) __percpu(var)__percpu_rel -#else /* !__ASSEMBLY__: */ +#else /* !__ASSEMBLER__: */ #include <linux/args.h> #include <linux/bits.h> diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h index e5a13dc8816e..4cd94fdcb45e 100644 --- a/arch/x86/include/asm/runtime-const.h +++ b/arch/x86/include/asm/runtime-const.h @@ -6,7 +6,7 @@ #error "Cannot use runtime-const infrastructure from modules" #endif -#ifdef __ASSEMBLY__ +#ifdef __ASSEMBLER__ .macro RUNTIME_CONST_PTR sym reg movq $0x0123456789abcdef, %\reg @@ -16,7 +16,7 @@ .popsection .endm -#else /* __ASSEMBLY__ */ +#else /* __ASSEMBLER__ */ #define runtime_const_ptr(sym) ({ \ typeof(sym) __ret; \ @@ -74,5 +74,5 @@ static inline void runtime_const_fixup(void (*fn)(void *, unsigned long), } } -#endif /* __ASSEMBLY__ */ +#endif /* __ASSEMBLER__ */ #endif diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 869b88061801..3f24cc472ce9 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -25,6 +25,8 @@ extern int ibt_selftest_noendbr(void); void handle_invalid_op(struct pt_regs *regs); #endif +noinstr bool handle_bug(struct pt_regs *regs); + static inline int get_si_code(unsigned long condition) { if (condition & DR_STEP) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index a888ae0f01fb..e87da25d1236 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -1182,7 +1182,7 @@ void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end) poison_endbr(addr); if (IS_ENABLED(CONFIG_FINEIBT)) - poison_cfi(addr - 16); + poison_cfi(addr - CFI_OFFSET); } } @@ -1389,6 +1389,8 @@ extern u8 fineibt_preamble_end[]; #define fineibt_preamble_ud 0x13 #define fineibt_preamble_hash 5 +#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE) + /* * <fineibt_caller_start>: * 0: b8 78 56 34 12 mov $0x12345678, %eax @@ -1634,7 +1636,7 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end) * have determined there are no indirect calls to it and we * don't need no CFI either. */ - if (!is_endbr(addr + 16)) + if (!is_endbr(addr + CFI_OFFSET)) continue; hash = decode_preamble_hash(addr, &arity); @@ -1642,6 +1644,15 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end) addr, addr, 5, addr)) return -EINVAL; + /* + * FineIBT relies on being at func-16, so if the preamble is + * actually larger than that, place it the tail end. + * + * NOTE: this is possible with things like DEBUG_CALL_THUNKS + * and DEBUG_FORCE_FUNCTION_ALIGN_64B. + */ + addr += CFI_OFFSET - fineibt_prefix_size; + text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size); WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678); text_poke_early(addr + fineibt_preamble_hash, &hash, 4); @@ -1664,10 +1675,10 @@ static void cfi_rewrite_endbr(s32 *start, s32 *end) for (s = start; s < end; s++) { void *addr = (void *)s + *s; - if (!exact_endbr(addr + 16)) + if (!exact_endbr(addr + CFI_OFFSET)) continue; - poison_endbr(addr + 16); + poison_endbr(addr + CFI_OFFSET); } } @@ -1772,7 +1783,8 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, if (FINEIBT_WARN(fineibt_preamble_size, 20) || FINEIBT_WARN(fineibt_preamble_bhi + fineibt_bhi1_size, 20) || FINEIBT_WARN(fineibt_caller_size, 14) || - FINEIBT_WARN(fineibt_paranoid_size, 20)) + FINEIBT_WARN(fineibt_paranoid_size, 20) || + WARN_ON_ONCE(CFI_OFFSET < fineibt_prefix_size)) return; if (cfi_mode == CFI_AUTO) { @@ -1886,6 +1898,11 @@ static void poison_cfi(void *addr) switch (cfi_mode) { case CFI_FINEIBT: /* + * FineIBT preamble is at func-16. + */ + addr += CFI_OFFSET - fineibt_prefix_size; + + /* * FineIBT prefix should start with an ENDBR. */ if (!is_endbr(addr)) @@ -1923,8 +1940,6 @@ static void poison_cfi(void *addr) } } -#define fineibt_prefix_size (fineibt_preamble_size - ENDBR_INSN_SIZE) - /* * When regs->ip points to a 0xD6 byte in the FineIBT preamble, * return true and fill out target and type. diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 5a6a772e0a6c..4dbff8ef9b1c 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -397,7 +397,7 @@ static inline void handle_invalid_op(struct pt_regs *regs) ILL_ILLOPN, error_get_trap_addr(regs)); } -static noinstr bool handle_bug(struct pt_regs *regs) +noinstr bool handle_bug(struct pt_regs *regs) { unsigned long addr = regs->ip; bool handled = false; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index d916bd766c94..801bf9e520db 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -20,7 +20,6 @@ if VIRTUALIZATION config KVM_X86 def_tristate KVM if (KVM_INTEL != n || KVM_AMD != n) select KVM_COMMON - select KVM_GENERIC_MMU_NOTIFIER select KVM_ELIDE_TLB_FLUSH_IF_YOUNG select KVM_MMU_LOCKLESS_AGING select HAVE_KVM_IRQCHIP diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3fb64905d190..a03530795707 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4805,7 +4805,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) #endif case KVM_CAP_NOP_IO_DELAY: case KVM_CAP_MP_STATE: - case KVM_CAP_SYNC_MMU: case KVM_CAP_USER_NMI: case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IOEVENTFD: diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 2fdc1f1f5adb..6b9ff1c6cafa 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -411,14 +411,11 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) return; if (trapnr == X86_TRAP_UD) { - if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { - /* Skip the ud2. */ - regs->ip += LEN_UD2; + if (handle_bug(regs)) return; - } /* - * If this was a BUG and report_bug returns or if this + * If this was a BUG and handle_bug returns or if this * was just a normal #UD, we want to continue onward and * crash. */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8f10080e6fe3..e9b78040d703 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -438,17 +438,8 @@ static void emit_kcfi(u8 **pprog, u32 hash) EMIT1_off32(0xb8, hash); /* movl $hash, %eax */ #ifdef CONFIG_CALL_PADDING - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); - EMIT1(0x90); + for (int i = 0; i < CONFIG_FUNCTION_PADDING_CFI; i++) + EMIT1(0x90); #endif EMIT_ENDBR(); diff --git a/drivers/accel/amdxdna/aie2_ctx.c b/drivers/accel/amdxdna/aie2_ctx.c index 4503c7c77a3e..25845bd5e507 100644 --- a/drivers/accel/amdxdna/aie2_ctx.c +++ b/drivers/accel/amdxdna/aie2_ctx.c @@ -23,9 +23,9 @@ #include "amdxdna_pci_drv.h" #include "amdxdna_pm.h" -static bool force_cmdlist; +static bool force_cmdlist = true; module_param(force_cmdlist, bool, 0600); -MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default false)"); +MODULE_PARM_DESC(force_cmdlist, "Force use command list (Default true)"); #define HWCTX_MAX_TIMEOUT 60000 /* milliseconds */ @@ -53,6 +53,7 @@ static void aie2_hwctx_stop(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwct { drm_sched_stop(&hwctx->priv->sched, bad_job); aie2_destroy_context(xdna->dev_handle, hwctx); + drm_sched_start(&hwctx->priv->sched, 0); } static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hwctx) @@ -80,7 +81,6 @@ static int aie2_hwctx_restart(struct amdxdna_dev *xdna, struct amdxdna_hwctx *hw } out: - drm_sched_start(&hwctx->priv->sched, 0); XDNA_DBG(xdna, "%s restarted, ret %d", hwctx->name, ret); return ret; } @@ -297,19 +297,23 @@ aie2_sched_job_run(struct drm_sched_job *sched_job) struct dma_fence *fence; int ret; - if (!hwctx->priv->mbox_chann) + ret = amdxdna_pm_resume_get(hwctx->client->xdna); + if (ret) + return NULL; + + if (!hwctx->priv->mbox_chann) { + amdxdna_pm_suspend_put(hwctx->client->xdna); return NULL; + } - if (!mmget_not_zero(job->mm)) + if (!mmget_not_zero(job->mm)) { + amdxdna_pm_suspend_put(hwctx->client->xdna); return ERR_PTR(-ESRCH); + } kref_get(&job->refcnt); fence = dma_fence_get(job->fence); - ret = amdxdna_pm_resume_get(hwctx->client->xdna); - if (ret) - goto out; - if (job->drv_cmd) { switch (job->drv_cmd->opcode) { case SYNC_DEBUG_BO: @@ -497,7 +501,7 @@ static void aie2_release_resource(struct amdxdna_hwctx *hwctx) if (AIE2_FEATURE_ON(xdna->dev_handle, AIE2_TEMPORAL_ONLY)) { ret = aie2_destroy_context(xdna->dev_handle, hwctx); - if (ret) + if (ret && ret != -ENODEV) XDNA_ERR(xdna, "Destroy temporal only context failed, ret %d", ret); } else { ret = xrs_release_resource(xdna->xrs_hdl, (uintptr_t)hwctx); @@ -629,7 +633,7 @@ int aie2_hwctx_init(struct amdxdna_hwctx *hwctx) goto free_entity; } - ret = amdxdna_pm_resume_get(xdna); + ret = amdxdna_pm_resume_get_locked(xdna); if (ret) goto free_col_list; @@ -760,7 +764,7 @@ static int aie2_hwctx_cu_config(struct amdxdna_hwctx *hwctx, void *buf, u32 size if (!hwctx->cus) return -ENOMEM; - ret = amdxdna_pm_resume_get(xdna); + ret = amdxdna_pm_resume_get_locked(xdna); if (ret) goto free_cus; @@ -1070,6 +1074,8 @@ void aie2_hmm_invalidate(struct amdxdna_gem_obj *abo, ret = dma_resv_wait_timeout(gobj->resv, DMA_RESV_USAGE_BOOKKEEP, true, MAX_SCHEDULE_TIMEOUT); - if (!ret || ret == -ERESTARTSYS) + if (!ret) XDNA_ERR(xdna, "Failed to wait for bo, ret %ld", ret); + else if (ret == -ERESTARTSYS) + XDNA_DBG(xdna, "Wait for bo interrupted by signal"); } diff --git a/drivers/accel/amdxdna/aie2_message.c b/drivers/accel/amdxdna/aie2_message.c index 7d7dcfeaf794..277a27bce850 100644 --- a/drivers/accel/amdxdna/aie2_message.c +++ b/drivers/accel/amdxdna/aie2_message.c @@ -216,8 +216,10 @@ static int aie2_destroy_context_req(struct amdxdna_dev_hdl *ndev, u32 id) req.context_id = id; ret = aie2_send_mgmt_msg_wait(ndev, &msg); - if (ret) + if (ret && ret != -ENODEV) XDNA_WARN(xdna, "Destroy context failed, ret %d", ret); + else if (ret == -ENODEV) + XDNA_DBG(xdna, "Destroy context: device already stopped"); return ret; } @@ -318,6 +320,9 @@ int aie2_destroy_context(struct amdxdna_dev_hdl *ndev, struct amdxdna_hwctx *hwc struct amdxdna_dev *xdna = ndev->xdna; int ret; + if (!hwctx->priv->mbox_chann) + return 0; + xdna_mailbox_stop_channel(hwctx->priv->mbox_chann); ret = aie2_destroy_context_req(ndev, hwctx->fw_ctx_id); xdna_mailbox_destroy_channel(hwctx->priv->mbox_chann); @@ -694,11 +699,11 @@ aie2_cmdlist_fill_npu_cf(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *siz u32 cmd_len; void *cmd; - memset(npu_slot, 0, sizeof(*npu_slot)); cmd = amdxdna_cmd_get_payload(cmd_bo, &cmd_len); if (*size < sizeof(*npu_slot) + cmd_len) return -EINVAL; + memset(npu_slot, 0, sizeof(*npu_slot)); npu_slot->cu_idx = amdxdna_cmd_get_cu_idx(cmd_bo); if (npu_slot->cu_idx == INVALID_CU_IDX) return -EINVAL; @@ -719,7 +724,6 @@ aie2_cmdlist_fill_npu_dpu(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si u32 cmd_len; u32 arg_sz; - memset(npu_slot, 0, sizeof(*npu_slot)); sn = amdxdna_cmd_get_payload(cmd_bo, &cmd_len); arg_sz = cmd_len - sizeof(*sn); if (cmd_len < sizeof(*sn) || arg_sz > MAX_NPU_ARGS_SIZE) @@ -728,6 +732,7 @@ aie2_cmdlist_fill_npu_dpu(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si if (*size < sizeof(*npu_slot) + arg_sz) return -EINVAL; + memset(npu_slot, 0, sizeof(*npu_slot)); npu_slot->cu_idx = amdxdna_cmd_get_cu_idx(cmd_bo); if (npu_slot->cu_idx == INVALID_CU_IDX) return -EINVAL; @@ -751,7 +756,6 @@ aie2_cmdlist_fill_npu_preempt(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t u32 cmd_len; u32 arg_sz; - memset(npu_slot, 0, sizeof(*npu_slot)); pd = amdxdna_cmd_get_payload(cmd_bo, &cmd_len); arg_sz = cmd_len - sizeof(*pd); if (cmd_len < sizeof(*pd) || arg_sz > MAX_NPU_ARGS_SIZE) @@ -760,6 +764,7 @@ aie2_cmdlist_fill_npu_preempt(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t if (*size < sizeof(*npu_slot) + arg_sz) return -EINVAL; + memset(npu_slot, 0, sizeof(*npu_slot)); npu_slot->cu_idx = amdxdna_cmd_get_cu_idx(cmd_bo); if (npu_slot->cu_idx == INVALID_CU_IDX) return -EINVAL; @@ -787,7 +792,6 @@ aie2_cmdlist_fill_npu_elf(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si u32 cmd_len; u32 arg_sz; - memset(npu_slot, 0, sizeof(*npu_slot)); pd = amdxdna_cmd_get_payload(cmd_bo, &cmd_len); arg_sz = cmd_len - sizeof(*pd); if (cmd_len < sizeof(*pd) || arg_sz > MAX_NPU_ARGS_SIZE) @@ -796,6 +800,7 @@ aie2_cmdlist_fill_npu_elf(struct amdxdna_gem_obj *cmd_bo, void *slot, size_t *si if (*size < sizeof(*npu_slot) + arg_sz) return -EINVAL; + memset(npu_slot, 0, sizeof(*npu_slot)); npu_slot->type = EXEC_NPU_TYPE_ELF; npu_slot->inst_buf_addr = pd->inst_buf; npu_slot->save_buf_addr = pd->save_buf; diff --git a/drivers/accel/amdxdna/aie2_pci.c b/drivers/accel/amdxdna/aie2_pci.c index 2a51b2658bfc..85079b6fc5d9 100644 --- a/drivers/accel/amdxdna/aie2_pci.c +++ b/drivers/accel/amdxdna/aie2_pci.c @@ -32,6 +32,11 @@ static int aie2_max_col = XRS_MAX_COL; module_param(aie2_max_col, uint, 0600); MODULE_PARM_DESC(aie2_max_col, "Maximum column could be used"); +static char *npu_fw[] = { + "npu_7.sbin", + "npu.sbin" +}; + /* * The management mailbox channel is allocated by firmware. * The related register and ring buffer information is on SRAM BAR. @@ -323,6 +328,7 @@ static void aie2_hw_stop(struct amdxdna_dev *xdna) return; } + aie2_runtime_cfg(ndev, AIE2_RT_CFG_CLK_GATING, NULL); aie2_mgmt_fw_fini(ndev); xdna_mailbox_stop_channel(ndev->mgmt_chann); xdna_mailbox_destroy_channel(ndev->mgmt_chann); @@ -406,15 +412,15 @@ static int aie2_hw_start(struct amdxdna_dev *xdna) goto stop_psp; } - ret = aie2_pm_init(ndev); + ret = aie2_mgmt_fw_init(ndev); if (ret) { - XDNA_ERR(xdna, "failed to init pm, ret %d", ret); + XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret); goto destroy_mgmt_chann; } - ret = aie2_mgmt_fw_init(ndev); + ret = aie2_pm_init(ndev); if (ret) { - XDNA_ERR(xdna, "initial mgmt firmware failed, ret %d", ret); + XDNA_ERR(xdna, "failed to init pm, ret %d", ret); goto destroy_mgmt_chann; } @@ -451,7 +457,6 @@ static int aie2_hw_suspend(struct amdxdna_dev *xdna) { struct amdxdna_client *client; - guard(mutex)(&xdna->dev_lock); list_for_each_entry(client, &xdna->client_list, node) aie2_hwctx_suspend(client); @@ -489,6 +494,7 @@ static int aie2_init(struct amdxdna_dev *xdna) struct psp_config psp_conf; const struct firmware *fw; unsigned long bars = 0; + char *fw_full_path; int i, nvec, ret; if (!hypervisor_is_type(X86_HYPER_NATIVE)) { @@ -503,7 +509,19 @@ static int aie2_init(struct amdxdna_dev *xdna) ndev->priv = xdna->dev_info->dev_priv; ndev->xdna = xdna; - ret = request_firmware(&fw, ndev->priv->fw_path, &pdev->dev); + for (i = 0; i < ARRAY_SIZE(npu_fw); i++) { + fw_full_path = kasprintf(GFP_KERNEL, "%s%s", ndev->priv->fw_path, npu_fw[i]); + if (!fw_full_path) + return -ENOMEM; + + ret = firmware_request_nowarn(&fw, fw_full_path, &pdev->dev); + kfree(fw_full_path); + if (!ret) { + XDNA_INFO(xdna, "Load firmware %s%s", ndev->priv->fw_path, npu_fw[i]); + break; + } + } + if (ret) { XDNA_ERR(xdna, "failed to request_firmware %s, ret %d", ndev->priv->fw_path, ret); @@ -951,7 +969,7 @@ static int aie2_get_info(struct amdxdna_client *client, struct amdxdna_drm_get_i if (!drm_dev_enter(&xdna->ddev, &idx)) return -ENODEV; - ret = amdxdna_pm_resume_get(xdna); + ret = amdxdna_pm_resume_get_locked(xdna); if (ret) goto dev_exit; @@ -1044,7 +1062,7 @@ static int aie2_get_array(struct amdxdna_client *client, if (!drm_dev_enter(&xdna->ddev, &idx)) return -ENODEV; - ret = amdxdna_pm_resume_get(xdna); + ret = amdxdna_pm_resume_get_locked(xdna); if (ret) goto dev_exit; @@ -1134,7 +1152,7 @@ static int aie2_set_state(struct amdxdna_client *client, if (!drm_dev_enter(&xdna->ddev, &idx)) return -ENODEV; - ret = amdxdna_pm_resume_get(xdna); + ret = amdxdna_pm_resume_get_locked(xdna); if (ret) goto dev_exit; diff --git a/drivers/accel/amdxdna/aie2_pm.c b/drivers/accel/amdxdna/aie2_pm.c index 579b8be13b18..29bd4403a94d 100644 --- a/drivers/accel/amdxdna/aie2_pm.c +++ b/drivers/accel/amdxdna/aie2_pm.c @@ -31,7 +31,7 @@ int aie2_pm_set_dpm(struct amdxdna_dev_hdl *ndev, u32 dpm_level) { int ret; - ret = amdxdna_pm_resume_get(ndev->xdna); + ret = amdxdna_pm_resume_get_locked(ndev->xdna); if (ret) return ret; diff --git a/drivers/accel/amdxdna/amdxdna_ctx.c b/drivers/accel/amdxdna/amdxdna_ctx.c index 59fa3800b9d3..263d36072540 100644 --- a/drivers/accel/amdxdna/amdxdna_ctx.c +++ b/drivers/accel/amdxdna/amdxdna_ctx.c @@ -104,7 +104,10 @@ void *amdxdna_cmd_get_payload(struct amdxdna_gem_obj *abo, u32 *size) if (size) { count = FIELD_GET(AMDXDNA_CMD_COUNT, cmd->header); - if (unlikely(count <= num_masks)) { + if (unlikely(count <= num_masks || + count * sizeof(u32) + + offsetof(struct amdxdna_cmd, data[0]) > + abo->mem.size)) { *size = 0; return NULL; } @@ -266,9 +269,9 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr struct amdxdna_drm_config_hwctx *args = data; struct amdxdna_dev *xdna = to_xdna_dev(dev); struct amdxdna_hwctx *hwctx; - int ret, idx; u32 buf_size; void *buf; + int ret; u64 val; if (XDNA_MBZ_DBG(xdna, &args->pad, sizeof(args->pad))) @@ -310,20 +313,17 @@ int amdxdna_drm_config_hwctx_ioctl(struct drm_device *dev, void *data, struct dr return -EINVAL; } - mutex_lock(&xdna->dev_lock); - idx = srcu_read_lock(&client->hwctx_srcu); + guard(mutex)(&xdna->dev_lock); hwctx = xa_load(&client->hwctx_xa, args->handle); if (!hwctx) { XDNA_DBG(xdna, "PID %d failed to get hwctx %d", client->pid, args->handle); ret = -EINVAL; - goto unlock_srcu; + goto free_buf; } ret = xdna->dev_info->ops->hwctx_config(hwctx, args->param_type, val, buf, buf_size); -unlock_srcu: - srcu_read_unlock(&client->hwctx_srcu, idx); - mutex_unlock(&xdna->dev_lock); +free_buf: kfree(buf); return ret; } @@ -334,7 +334,7 @@ int amdxdna_hwctx_sync_debug_bo(struct amdxdna_client *client, u32 debug_bo_hdl) struct amdxdna_hwctx *hwctx; struct amdxdna_gem_obj *abo; struct drm_gem_object *gobj; - int ret, idx; + int ret; if (!xdna->dev_info->ops->hwctx_sync_debug_bo) return -EOPNOTSUPP; @@ -345,17 +345,15 @@ int amdxdna_hwctx_sync_debug_bo(struct amdxdna_client *client, u32 debug_bo_hdl) abo = to_xdna_obj(gobj); guard(mutex)(&xdna->dev_lock); - idx = srcu_read_lock(&client->hwctx_srcu); hwctx = xa_load(&client->hwctx_xa, abo->assigned_hwctx); if (!hwctx) { ret = -EINVAL; - goto unlock_srcu; + goto put_obj; } ret = xdna->dev_info->ops->hwctx_sync_debug_bo(hwctx, debug_bo_hdl); -unlock_srcu: - srcu_read_unlock(&client->hwctx_srcu, idx); +put_obj: drm_gem_object_put(gobj); return ret; } diff --git a/drivers/accel/amdxdna/amdxdna_gem.c b/drivers/accel/amdxdna/amdxdna_gem.c index 8c290ddd3251..d60db49ead71 100644 --- a/drivers/accel/amdxdna/amdxdna_gem.c +++ b/drivers/accel/amdxdna/amdxdna_gem.c @@ -21,8 +21,6 @@ #include "amdxdna_pci_drv.h" #include "amdxdna_ubuf.h" -#define XDNA_MAX_CMD_BO_SIZE SZ_32K - MODULE_IMPORT_NS("DMA_BUF"); static int @@ -745,12 +743,6 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev, { struct amdxdna_dev *xdna = to_xdna_dev(dev); struct amdxdna_gem_obj *abo; - int ret; - - if (args->size > XDNA_MAX_CMD_BO_SIZE) { - XDNA_ERR(xdna, "Command bo size 0x%llx too large", args->size); - return ERR_PTR(-EINVAL); - } if (args->size < sizeof(struct amdxdna_cmd)) { XDNA_DBG(xdna, "Command BO size 0x%llx too small", args->size); @@ -764,17 +756,7 @@ amdxdna_drm_create_cmd_bo(struct drm_device *dev, abo->type = AMDXDNA_BO_CMD; abo->client = filp->driver_priv; - ret = amdxdna_gem_obj_vmap(abo, &abo->mem.kva); - if (ret) { - XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret); - goto release_obj; - } - return abo; - -release_obj: - drm_gem_object_put(to_gobj(abo)); - return ERR_PTR(ret); } int amdxdna_drm_create_bo_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) @@ -871,6 +853,7 @@ struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client, struct amdxdna_dev *xdna = client->xdna; struct amdxdna_gem_obj *abo; struct drm_gem_object *gobj; + int ret; gobj = drm_gem_object_lookup(client->filp, bo_hdl); if (!gobj) { @@ -879,9 +862,26 @@ struct amdxdna_gem_obj *amdxdna_gem_get_obj(struct amdxdna_client *client, } abo = to_xdna_obj(gobj); - if (bo_type == AMDXDNA_BO_INVALID || abo->type == bo_type) + if (bo_type != AMDXDNA_BO_INVALID && abo->type != bo_type) + goto put_obj; + + if (bo_type != AMDXDNA_BO_CMD || abo->mem.kva) return abo; + if (abo->mem.size > SZ_32K) { + XDNA_ERR(xdna, "Cmd bo is too big %ld", abo->mem.size); + goto put_obj; + } + + ret = amdxdna_gem_obj_vmap(abo, &abo->mem.kva); + if (ret) { + XDNA_ERR(xdna, "Vmap cmd bo failed, ret %d", ret); + goto put_obj; + } + + return abo; + +put_obj: drm_gem_object_put(gobj); return NULL; } diff --git a/drivers/accel/amdxdna/amdxdna_pci_drv.c b/drivers/accel/amdxdna/amdxdna_pci_drv.c index 4ada45d06fcf..a4384593bdcc 100644 --- a/drivers/accel/amdxdna/amdxdna_pci_drv.c +++ b/drivers/accel/amdxdna/amdxdna_pci_drv.c @@ -23,6 +23,9 @@ MODULE_FIRMWARE("amdnpu/1502_00/npu.sbin"); MODULE_FIRMWARE("amdnpu/17f0_10/npu.sbin"); MODULE_FIRMWARE("amdnpu/17f0_11/npu.sbin"); MODULE_FIRMWARE("amdnpu/17f0_20/npu.sbin"); +MODULE_FIRMWARE("amdnpu/1502_00/npu_7.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_10/npu_7.sbin"); +MODULE_FIRMWARE("amdnpu/17f0_11/npu_7.sbin"); /* * 0.0: Initial version diff --git a/drivers/accel/amdxdna/amdxdna_pm.c b/drivers/accel/amdxdna/amdxdna_pm.c index d024d480521c..b1fafddd7ad5 100644 --- a/drivers/accel/amdxdna/amdxdna_pm.c +++ b/drivers/accel/amdxdna/amdxdna_pm.c @@ -16,6 +16,7 @@ int amdxdna_pm_suspend(struct device *dev) struct amdxdna_dev *xdna = to_xdna_dev(dev_get_drvdata(dev)); int ret = -EOPNOTSUPP; + guard(mutex)(&xdna->dev_lock); if (xdna->dev_info->ops->suspend) ret = xdna->dev_info->ops->suspend(xdna); @@ -28,6 +29,7 @@ int amdxdna_pm_resume(struct device *dev) struct amdxdna_dev *xdna = to_xdna_dev(dev_get_drvdata(dev)); int ret = -EOPNOTSUPP; + guard(mutex)(&xdna->dev_lock); if (xdna->dev_info->ops->resume) ret = xdna->dev_info->ops->resume(xdna); diff --git a/drivers/accel/amdxdna/amdxdna_pm.h b/drivers/accel/amdxdna/amdxdna_pm.h index 77b2d6e45570..3d26b973e0e3 100644 --- a/drivers/accel/amdxdna/amdxdna_pm.h +++ b/drivers/accel/amdxdna/amdxdna_pm.h @@ -15,4 +15,15 @@ void amdxdna_pm_suspend_put(struct amdxdna_dev *xdna); void amdxdna_pm_init(struct amdxdna_dev *xdna); void amdxdna_pm_fini(struct amdxdna_dev *xdna); +static inline int amdxdna_pm_resume_get_locked(struct amdxdna_dev *xdna) +{ + int ret; + + mutex_unlock(&xdna->dev_lock); + ret = amdxdna_pm_resume_get(xdna); + mutex_lock(&xdna->dev_lock); + + return ret; +} + #endif /* _AMDXDNA_PM_H_ */ diff --git a/drivers/accel/amdxdna/amdxdna_ubuf.c b/drivers/accel/amdxdna/amdxdna_ubuf.c index b509f10b155c..fb71d6e3f44d 100644 --- a/drivers/accel/amdxdna/amdxdna_ubuf.c +++ b/drivers/accel/amdxdna/amdxdna_ubuf.c @@ -7,6 +7,7 @@ #include <drm/drm_device.h> #include <drm/drm_print.h> #include <linux/dma-buf.h> +#include <linux/overflow.h> #include <linux/pagemap.h> #include <linux/vmalloc.h> @@ -176,7 +177,10 @@ struct dma_buf *amdxdna_get_ubuf(struct drm_device *dev, goto free_ent; } - exp_info.size += va_ent[i].len; + if (check_add_overflow(exp_info.size, va_ent[i].len, &exp_info.size)) { + ret = -EINVAL; + goto free_ent; + } } ubuf->nr_pages = exp_info.size >> PAGE_SHIFT; diff --git a/drivers/accel/amdxdna/npu1_regs.c b/drivers/accel/amdxdna/npu1_regs.c index 6f36a27b5a02..6e3d3ca69c04 100644 --- a/drivers/accel/amdxdna/npu1_regs.c +++ b/drivers/accel/amdxdna/npu1_regs.c @@ -72,7 +72,7 @@ static const struct aie2_fw_feature_tbl npu1_fw_feature_table[] = { }; static const struct amdxdna_dev_priv npu1_dev_priv = { - .fw_path = "amdnpu/1502_00/npu.sbin", + .fw_path = "amdnpu/1502_00/", .rt_config = npu1_default_rt_cfg, .dpm_clk_tbl = npu1_dpm_clk_table, .fw_feature_tbl = npu1_fw_feature_table, diff --git a/drivers/accel/amdxdna/npu4_regs.c b/drivers/accel/amdxdna/npu4_regs.c index a8d6f76dde5f..ce25eef5fc34 100644 --- a/drivers/accel/amdxdna/npu4_regs.c +++ b/drivers/accel/amdxdna/npu4_regs.c @@ -98,7 +98,7 @@ const struct aie2_fw_feature_tbl npu4_fw_feature_table[] = { }; static const struct amdxdna_dev_priv npu4_dev_priv = { - .fw_path = "amdnpu/17f0_10/npu.sbin", + .fw_path = "amdnpu/17f0_10/", .rt_config = npu4_default_rt_cfg, .dpm_clk_tbl = npu4_dpm_clk_table, .fw_feature_tbl = npu4_fw_feature_table, diff --git a/drivers/accel/amdxdna/npu5_regs.c b/drivers/accel/amdxdna/npu5_regs.c index c0a35cfd886c..c0ac5daf32ee 100644 --- a/drivers/accel/amdxdna/npu5_regs.c +++ b/drivers/accel/amdxdna/npu5_regs.c @@ -63,7 +63,7 @@ #define NPU5_SRAM_BAR_BASE MMNPU_APERTURE1_BASE static const struct amdxdna_dev_priv npu5_dev_priv = { - .fw_path = "amdnpu/17f0_11/npu.sbin", + .fw_path = "amdnpu/17f0_11/", .rt_config = npu4_default_rt_cfg, .dpm_clk_tbl = npu4_dpm_clk_table, .fw_feature_tbl = npu4_fw_feature_table, diff --git a/drivers/accel/amdxdna/npu6_regs.c b/drivers/accel/amdxdna/npu6_regs.c index 1fb07df99186..ce591ed0d483 100644 --- a/drivers/accel/amdxdna/npu6_regs.c +++ b/drivers/accel/amdxdna/npu6_regs.c @@ -63,7 +63,7 @@ #define NPU6_SRAM_BAR_BASE MMNPU_APERTURE1_BASE static const struct amdxdna_dev_priv npu6_dev_priv = { - .fw_path = "amdnpu/17f0_10/npu.sbin", + .fw_path = "amdnpu/17f0_10/", .rt_config = npu4_default_rt_cfg, .dpm_clk_tbl = npu4_dpm_clk_table, .fw_feature_tbl = npu4_fw_feature_table, diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c index 4fbd4bbf2909..668c71d5ff45 100644 --- a/drivers/accel/ethosu/ethosu_gem.c +++ b/drivers/accel/ethosu/ethosu_gem.c @@ -154,7 +154,7 @@ static void cmd_state_init(struct cmd_state *st) static u64 cmd_to_addr(u32 *cmd) { - return ((u64)((cmd[0] & 0xff0000) << 16)) | cmd[1]; + return (((u64)cmd[0] & 0xff0000) << 16) | cmd[1]; } static u64 dma_length(struct ethosu_validated_cmdstream_info *info, diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c index f2c943b934be..9470f1830ff5 100644 --- a/drivers/acpi/osi.c +++ b/drivers/acpi/osi.c @@ -390,6 +390,19 @@ static const struct dmi_system_id acpi_osi_dmi_table[] __initconst = { }, /* + * The screen backlight turns off during udev device creation + * when returning true for _OSI("Windows 2009") + */ + { + .callback = dmi_disable_osi_win7, + .ident = "Acer Aspire One D255", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "AOD255"), + }, + }, + + /* * The wireless hotkey does not work on those machines when * returning true for _OSI("Windows 2012") */ diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 66ec81e306d4..132a9df98471 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -386,6 +386,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "80E1"), }, }, + { + .callback = init_nvs_save_s3, + .ident = "Lenovo G70-35", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_NAME, "80Q5"), + }, + }, /* * ThinkPad X1 Tablet(2016) cannot do suspend-to-idle using * the Low Power S0 Idle firmware interface (see diff --git a/drivers/base/property.c b/drivers/base/property.c index 6a63860579dd..8d9a34be57fb 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -797,7 +797,18 @@ struct fwnode_handle * fwnode_get_next_child_node(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { - return fwnode_call_ptr_op(fwnode, get_next_child_node, child); + struct fwnode_handle *next; + + if (IS_ERR_OR_NULL(fwnode)) + return NULL; + + /* Try to find a child in primary fwnode */ + next = fwnode_call_ptr_op(fwnode, get_next_child_node, child); + if (next) + return next; + + /* When no more children in primary, continue with secondary */ + return fwnode_call_ptr_op(fwnode->secondary, get_next_child_node, child); } EXPORT_SYMBOL_GPL(fwnode_get_next_child_node); @@ -841,19 +852,7 @@ EXPORT_SYMBOL_GPL(fwnode_get_next_available_child_node); struct fwnode_handle *device_get_next_child_node(const struct device *dev, struct fwnode_handle *child) { - const struct fwnode_handle *fwnode = dev_fwnode(dev); - struct fwnode_handle *next; - - if (IS_ERR_OR_NULL(fwnode)) - return NULL; - - /* Try to find a child in primary fwnode */ - next = fwnode_get_next_child_node(fwnode, child); - if (next) - return next; - - /* When no more children in primary, continue with secondary */ - return fwnode_get_next_child_node(fwnode->secondary, child); + return fwnode_get_next_child_node(dev_fwnode(dev), child); } EXPORT_SYMBOL_GPL(device_get_next_child_node); diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c index 742b2908ff68..b3dbf6c76e98 100644 --- a/drivers/block/drbd/drbd_actlog.c +++ b/drivers/block/drbd/drbd_actlog.c @@ -483,38 +483,20 @@ void drbd_al_begin_io(struct drbd_device *device, struct drbd_interval *i) int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval *i) { - struct lru_cache *al = device->act_log; /* for bios crossing activity log extent boundaries, * we may need to activate two extents in one go */ unsigned first = i->sector >> (AL_EXTENT_SHIFT-9); unsigned last = i->size == 0 ? first : (i->sector + (i->size >> 9) - 1) >> (AL_EXTENT_SHIFT-9); - unsigned nr_al_extents; - unsigned available_update_slots; unsigned enr; - D_ASSERT(device, first <= last); - - nr_al_extents = 1 + last - first; /* worst case: all touched extends are cold. */ - available_update_slots = min(al->nr_elements - al->used, - al->max_pending_changes - al->pending_changes); - - /* We want all necessary updates for a given request within the same transaction - * We could first check how many updates are *actually* needed, - * and use that instead of the worst-case nr_al_extents */ - if (available_update_slots < nr_al_extents) { - /* Too many activity log extents are currently "hot". - * - * If we have accumulated pending changes already, - * we made progress. - * - * If we cannot get even a single pending change through, - * stop the fast path until we made some progress, - * or requests to "cold" extents could be starved. */ - if (!al->pending_changes) - __set_bit(__LC_STARVING, &device->act_log->flags); - return -ENOBUFS; + if (i->partially_in_al_next_enr) { + D_ASSERT(device, first < i->partially_in_al_next_enr); + D_ASSERT(device, last >= i->partially_in_al_next_enr); + first = i->partially_in_al_next_enr; } + D_ASSERT(device, first <= last); + /* Is resync active in this area? */ for (enr = first; enr <= last; enr++) { struct lc_element *tmp; @@ -529,14 +511,21 @@ int drbd_al_begin_io_nonblock(struct drbd_device *device, struct drbd_interval * } } - /* Checkout the refcounts. - * Given that we checked for available elements and update slots above, - * this has to be successful. */ + /* Try to checkout the refcounts. */ for (enr = first; enr <= last; enr++) { struct lc_element *al_ext; al_ext = lc_get_cumulative(device->act_log, enr); - if (!al_ext) - drbd_info(device, "LOGIC BUG for enr=%u\n", enr); + + if (!al_ext) { + /* Did not work. We may have exhausted the possible + * changes per transaction. Or raced with someone + * "locking" it against changes. + * Remember where to continue from. + */ + if (enr > first) + i->partially_in_al_next_enr = enr; + return -ENOBUFS; + } } return 0; } @@ -556,7 +545,11 @@ void drbd_al_complete_io(struct drbd_device *device, struct drbd_interval *i) for (enr = first; enr <= last; enr++) { extent = lc_find(device->act_log, enr); - if (!extent) { + /* Yes, this masks a bug elsewhere. However, during normal + * operation this is harmless, so no need to crash the kernel + * by the BUG_ON(refcount == 0) in lc_put(). + */ + if (!extent || extent->refcnt == 0) { drbd_err(device, "al_complete_io() called on inactive extent %u\n", enr); continue; } diff --git a/drivers/block/drbd/drbd_interval.h b/drivers/block/drbd/drbd_interval.h index 366489b72fe9..5d3213b81eed 100644 --- a/drivers/block/drbd/drbd_interval.h +++ b/drivers/block/drbd/drbd_interval.h @@ -8,12 +8,15 @@ struct drbd_interval { struct rb_node rb; sector_t sector; /* start sector of the interval */ - unsigned int size; /* size in bytes */ sector_t end; /* highest interval end in subtree */ + unsigned int size; /* size in bytes */ unsigned int local:1 /* local or remote request? */; unsigned int waiting:1; /* someone is waiting for completion */ unsigned int completed:1; /* this has been completed already; * ignore for conflict detection */ + + /* to resume a partially successful drbd_al_begin_io_nonblock(); */ + unsigned int partially_in_al_next_enr; }; static inline void drbd_clear_interval(struct drbd_interval *i) diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index b8f0eddf7e87..200d464e984b 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -32,6 +32,7 @@ #include <linux/memcontrol.h> #include <linux/mm_inline.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/random.h> #include <linux/reboot.h> #include <linux/notifier.h> @@ -732,9 +733,9 @@ int drbd_send_sync_param(struct drbd_peer_device *peer_device) } if (apv >= 88) - strcpy(p->verify_alg, nc->verify_alg); + strscpy(p->verify_alg, nc->verify_alg); if (apv >= 89) - strcpy(p->csums_alg, nc->csums_alg); + strscpy(p->csums_alg, nc->csums_alg); rcu_read_unlock(); return drbd_send_command(peer_device, sock, cmd, size, NULL, 0); @@ -745,6 +746,7 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm struct drbd_socket *sock; struct p_protocol *p; struct net_conf *nc; + size_t integrity_alg_len; int size, cf; sock = &connection->data; @@ -762,8 +764,10 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm } size = sizeof(*p); - if (connection->agreed_pro_version >= 87) - size += strlen(nc->integrity_alg) + 1; + if (connection->agreed_pro_version >= 87) { + integrity_alg_len = strlen(nc->integrity_alg) + 1; + size += integrity_alg_len; + } p->protocol = cpu_to_be32(nc->wire_protocol); p->after_sb_0p = cpu_to_be32(nc->after_sb_0p); @@ -778,7 +782,7 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm p->conn_flags = cpu_to_be32(cf); if (connection->agreed_pro_version >= 87) - strcpy(p->integrity_alg, nc->integrity_alg); + strscpy(p->integrity_alg, nc->integrity_alg, integrity_alg_len); rcu_read_unlock(); return __conn_send_command(connection, sock, cmd, size, NULL, 0); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 3cfef456a1f3..58b95bf4bdca 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -3801,14 +3801,14 @@ static int receive_SyncParam(struct drbd_connection *connection, struct packet_i *new_net_conf = *old_net_conf; if (verify_tfm) { - strcpy(new_net_conf->verify_alg, p->verify_alg); + strscpy(new_net_conf->verify_alg, p->verify_alg); new_net_conf->verify_alg_len = strlen(p->verify_alg) + 1; crypto_free_shash(peer_device->connection->verify_tfm); peer_device->connection->verify_tfm = verify_tfm; drbd_info(device, "using verify-alg: \"%s\"\n", p->verify_alg); } if (csums_tfm) { - strcpy(new_net_conf->csums_alg, p->csums_alg); + strscpy(new_net_conf->csums_alg, p->csums_alg); new_net_conf->csums_alg_len = strlen(p->csums_alg) + 1; crypto_free_shash(peer_device->connection->csums_tfm); peer_device->connection->csums_tfm = csums_tfm; diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index d15826f6ee81..70f75ef07945 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -621,7 +621,8 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, break; case READ_COMPLETED_WITH_ERROR: - drbd_set_out_of_sync(peer_device, req->i.sector, req->i.size); + drbd_set_out_of_sync(first_peer_device(device), + req->i.sector, req->i.size); drbd_report_io_error(device, req); __drbd_chk_io_error(device, DRBD_READ_ERROR); fallthrough; diff --git a/drivers/block/zloop.c b/drivers/block/zloop.c index 65a40266437c..51c043342127 100644 --- a/drivers/block/zloop.c +++ b/drivers/block/zloop.c @@ -542,6 +542,21 @@ out: zloop_put_cmd(cmd); } +/* + * Sync the entire FS containing the zone files instead of walking all files. + */ +static int zloop_flush(struct zloop_device *zlo) +{ + struct super_block *sb = file_inode(zlo->data_dir)->i_sb; + int ret; + + down_read(&sb->s_umount); + ret = sync_filesystem(sb); + up_read(&sb->s_umount); + + return ret; +} + static void zloop_handle_cmd(struct zloop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); @@ -562,11 +577,7 @@ static void zloop_handle_cmd(struct zloop_cmd *cmd) zloop_rw(cmd); return; case REQ_OP_FLUSH: - /* - * Sync the entire FS containing the zone files instead of - * walking all files - */ - cmd->ret = sync_filesystem(file_inode(zlo->data_dir)->i_sb); + cmd->ret = zloop_flush(zlo); break; case REQ_OP_ZONE_RESET: cmd->ret = zloop_reset_zone(zlo, rq_zone_no(rq)); @@ -981,7 +992,8 @@ static int zloop_ctl_add(struct zloop_options *opts) struct queue_limits lim = { .max_hw_sectors = SZ_1M >> SECTOR_SHIFT, .chunk_sectors = opts->zone_size, - .features = BLK_FEAT_ZONED, + .features = BLK_FEAT_ZONED | BLK_FEAT_WRITE_CACHE, + }; unsigned int nr_zones, i, j; struct zloop_device *zlo; @@ -1162,7 +1174,12 @@ static int zloop_ctl_remove(struct zloop_options *opts) int ret; if (!(opts->mask & ZLOOP_OPT_ID)) { - pr_err("No ID specified\n"); + pr_err("No ID specified for remove\n"); + return -EINVAL; + } + + if (opts->mask & ~ZLOOP_OPT_ID) { + pr_err("Invalid option specified for remove\n"); return -EINVAL; } diff --git a/drivers/char/ipmi/ipmi_ipmb.c b/drivers/char/ipmi/ipmi_ipmb.c index 3a51e58b2487..28818952a7a4 100644 --- a/drivers/char/ipmi/ipmi_ipmb.c +++ b/drivers/char/ipmi/ipmi_ipmb.c @@ -202,11 +202,16 @@ static int ipmi_ipmb_slave_cb(struct i2c_client *client, break; case I2C_SLAVE_READ_REQUESTED: + *val = 0xff; + ipmi_ipmb_check_msg_done(iidev); + break; + case I2C_SLAVE_STOP: ipmi_ipmb_check_msg_done(iidev); break; case I2C_SLAVE_READ_PROCESSED: + *val = 0xff; break; } diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index c530966c4e07..c41f51c82edd 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -602,6 +602,22 @@ static int __ipmi_bmc_register(struct ipmi_smi *intf, static int __scan_channels(struct ipmi_smi *intf, struct ipmi_device_id *id, bool rescan); +static void ipmi_lock_xmit_msgs(struct ipmi_smi *intf, int run_to_completion, + unsigned long *flags) +{ + if (run_to_completion) + return; + spin_lock_irqsave(&intf->xmit_msgs_lock, *flags); +} + +static void ipmi_unlock_xmit_msgs(struct ipmi_smi *intf, int run_to_completion, + unsigned long *flags) +{ + if (run_to_completion) + return; + spin_unlock_irqrestore(&intf->xmit_msgs_lock, *flags); +} + static void free_ipmi_user(struct kref *ref) { struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount); @@ -1869,21 +1885,32 @@ static struct ipmi_smi_msg *smi_add_send_msg(struct ipmi_smi *intf, return smi_msg; } -static void smi_send(struct ipmi_smi *intf, +static int smi_send(struct ipmi_smi *intf, const struct ipmi_smi_handlers *handlers, struct ipmi_smi_msg *smi_msg, int priority) { int run_to_completion = READ_ONCE(intf->run_to_completion); unsigned long flags = 0; + int rv = 0; - if (!run_to_completion) - spin_lock_irqsave(&intf->xmit_msgs_lock, flags); + ipmi_lock_xmit_msgs(intf, run_to_completion, &flags); smi_msg = smi_add_send_msg(intf, smi_msg, priority); - if (!run_to_completion) - spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags); + ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags); - if (smi_msg) - handlers->sender(intf->send_info, smi_msg); + if (smi_msg) { + rv = handlers->sender(intf->send_info, smi_msg); + if (rv) { + ipmi_lock_xmit_msgs(intf, run_to_completion, &flags); + intf->curr_msg = NULL; + ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags); + /* + * Something may have been added to the transmit + * queue, so schedule a check for that. + */ + queue_work(system_wq, &intf->smi_work); + } + } + return rv; } static bool is_maintenance_mode_cmd(struct kernel_ipmi_msg *msg) @@ -2296,6 +2323,7 @@ static int i_ipmi_request(struct ipmi_user *user, struct ipmi_recv_msg *recv_msg; int run_to_completion = READ_ONCE(intf->run_to_completion); int rv = 0; + bool in_seq_table = false; if (supplied_recv) { recv_msg = supplied_recv; @@ -2349,33 +2377,50 @@ static int i_ipmi_request(struct ipmi_user *user, rv = i_ipmi_req_ipmb(intf, addr, msgid, msg, smi_msg, recv_msg, source_address, source_lun, retries, retry_time_ms); + in_seq_table = true; } else if (is_ipmb_direct_addr(addr)) { rv = i_ipmi_req_ipmb_direct(intf, addr, msgid, msg, smi_msg, recv_msg, source_lun); } else if (is_lan_addr(addr)) { rv = i_ipmi_req_lan(intf, addr, msgid, msg, smi_msg, recv_msg, source_lun, retries, retry_time_ms); + in_seq_table = true; } else { - /* Unknown address type. */ + /* Unknown address type. */ ipmi_inc_stat(intf, sent_invalid_commands); rv = -EINVAL; } - if (rv) { -out_err: - if (!supplied_smi) - ipmi_free_smi_msg(smi_msg); - if (!supplied_recv) - ipmi_free_recv_msg(recv_msg); - } else { + if (!rv) { dev_dbg(intf->si_dev, "Send: %*ph\n", smi_msg->data_size, smi_msg->data); - smi_send(intf, intf->handlers, smi_msg, priority); + rv = smi_send(intf, intf->handlers, smi_msg, priority); + if (rv != IPMI_CC_NO_ERROR) + /* smi_send() returns an IPMI err, return a Linux one. */ + rv = -EIO; + if (rv && in_seq_table) { + /* + * If it's in the sequence table, it will be + * retried later, so ignore errors. + */ + rv = 0; + /* But we need to fix the timeout. */ + intf_start_seq_timer(intf, smi_msg->msgid); + ipmi_free_smi_msg(smi_msg); + smi_msg = NULL; + } } +out_err: if (!run_to_completion) mutex_unlock(&intf->users_mutex); + if (rv) { + if (!supplied_smi) + ipmi_free_smi_msg(smi_msg); + if (!supplied_recv) + ipmi_free_recv_msg(recv_msg); + } return rv; } @@ -3949,12 +3994,12 @@ static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf, dev_dbg(intf->si_dev, "Invalid command: %*ph\n", msg->data_size, msg->data); - smi_send(intf, intf->handlers, msg, 0); - /* - * We used the message, so return the value that - * causes it to not be freed or queued. - */ - rv = -1; + if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR) + /* + * We used the message, so return the value that + * causes it to not be freed or queued. + */ + rv = -1; } else if (!IS_ERR(recv_msg)) { /* Extract the source address from the data. */ ipmb_addr = (struct ipmi_ipmb_addr *) &recv_msg->addr; @@ -4028,12 +4073,12 @@ static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf, msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE; msg->data_size = 5; - smi_send(intf, intf->handlers, msg, 0); - /* - * We used the message, so return the value that - * causes it to not be freed or queued. - */ - rv = -1; + if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR) + /* + * We used the message, so return the value that + * causes it to not be freed or queued. + */ + rv = -1; } else if (!IS_ERR(recv_msg)) { /* Extract the source address from the data. */ daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr; @@ -4173,7 +4218,7 @@ static int handle_lan_get_msg_cmd(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { struct cmd_rcvr *rcvr; - int rv = 0; + int rv = 0; /* Free by default */ unsigned char netfn; unsigned char cmd; unsigned char chan; @@ -4226,12 +4271,12 @@ static int handle_lan_get_msg_cmd(struct ipmi_smi *intf, dev_dbg(intf->si_dev, "Invalid command: %*ph\n", msg->data_size, msg->data); - smi_send(intf, intf->handlers, msg, 0); - /* - * We used the message, so return the value that - * causes it to not be freed or queued. - */ - rv = -1; + if (smi_send(intf, intf->handlers, msg, 0) == IPMI_CC_NO_ERROR) + /* + * We used the message, so return the value that + * causes it to not be freed or queued. + */ + rv = -1; } else if (!IS_ERR(recv_msg)) { /* Extract the source address from the data. */ lan_addr = (struct ipmi_lan_addr *) &recv_msg->addr; @@ -4824,8 +4869,7 @@ static void smi_work(struct work_struct *t) * message delivery. */ restart: - if (!run_to_completion) - spin_lock_irqsave(&intf->xmit_msgs_lock, flags); + ipmi_lock_xmit_msgs(intf, run_to_completion, &flags); if (intf->curr_msg == NULL && !intf->in_shutdown) { struct list_head *entry = NULL; @@ -4841,8 +4885,7 @@ restart: intf->curr_msg = newmsg; } } - if (!run_to_completion) - spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags); + ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags); if (newmsg) { cc = intf->handlers->sender(intf->send_info, newmsg); @@ -4850,8 +4893,11 @@ restart: if (newmsg->recv_msg) deliver_err_response(intf, newmsg->recv_msg, cc); - else - ipmi_free_smi_msg(newmsg); + ipmi_lock_xmit_msgs(intf, run_to_completion, &flags); + intf->curr_msg = NULL; + ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags); + ipmi_free_smi_msg(newmsg); + newmsg = NULL; goto restart; } } @@ -4919,16 +4965,14 @@ void ipmi_smi_msg_received(struct ipmi_smi *intf, spin_unlock_irqrestore(&intf->waiting_rcv_msgs_lock, flags); - if (!run_to_completion) - spin_lock_irqsave(&intf->xmit_msgs_lock, flags); + ipmi_lock_xmit_msgs(intf, run_to_completion, &flags); /* * We can get an asynchronous event or receive message in addition * to commands we send. */ if (msg == intf->curr_msg) intf->curr_msg = NULL; - if (!run_to_completion) - spin_unlock_irqrestore(&intf->xmit_msgs_lock, flags); + ipmi_unlock_xmit_msgs(intf, run_to_completion, &flags); if (run_to_completion) smi_work(&intf->smi_work); @@ -5041,7 +5085,12 @@ static void check_msg_timeout(struct ipmi_smi *intf, struct seq_table *ent, ipmi_inc_stat(intf, retransmitted_ipmb_commands); - smi_send(intf, intf->handlers, smi_msg, 0); + /* If this fails we'll retry later or timeout. */ + if (smi_send(intf, intf->handlers, smi_msg, 0) != IPMI_CC_NO_ERROR) { + /* But fix the timeout. */ + intf_start_seq_timer(intf, smi_msg->msgid); + ipmi_free_smi_msg(smi_msg); + } } else ipmi_free_smi_msg(smi_msg); diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 6bdf624c37ce..4a9e9de4d684 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -809,6 +809,12 @@ restart: */ return_hosed_msg(smi_info, IPMI_BUS_ERR); } + if (smi_info->waiting_msg != NULL) { + /* Also handle if there was a message waiting. */ + smi_info->curr_msg = smi_info->waiting_msg; + smi_info->waiting_msg = NULL; + return_hosed_msg(smi_info, IPMI_BUS_ERR); + } smi_mod_timer(smi_info, jiffies + SI_TIMEOUT_HOSED); goto out; } @@ -918,9 +924,14 @@ static int sender(void *send_info, struct ipmi_smi_msg *msg) { struct smi_info *smi_info = send_info; unsigned long flags; + int rv = IPMI_CC_NO_ERROR; debug_timestamp(smi_info, "Enqueue"); + /* + * Check here for run to completion mode. A check under lock is + * later. + */ if (smi_info->si_state == SI_HOSED) return IPMI_BUS_ERR; @@ -934,18 +945,15 @@ static int sender(void *send_info, struct ipmi_smi_msg *msg) } spin_lock_irqsave(&smi_info->si_lock, flags); - /* - * The following two lines don't need to be under the lock for - * the lock's sake, but they do need SMP memory barriers to - * avoid getting things out of order. We are already claiming - * the lock, anyway, so just do it under the lock to avoid the - * ordering problem. - */ - BUG_ON(smi_info->waiting_msg); - smi_info->waiting_msg = msg; - check_start_timer_thread(smi_info); + if (smi_info->si_state == SI_HOSED) { + rv = IPMI_BUS_ERR; + } else { + BUG_ON(smi_info->waiting_msg); + smi_info->waiting_msg = msg; + check_start_timer_thread(smi_info); + } spin_unlock_irqrestore(&smi_info->si_lock, flags); - return IPMI_CC_NO_ERROR; + return rv; } static void set_run_to_completion(void *send_info, bool i_run_to_completion) @@ -1113,7 +1121,9 @@ static void smi_timeout(struct timer_list *t) * SI_USEC_PER_JIFFY); smi_result = smi_event_handler(smi_info, time_diff); - if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) { + if (smi_info->si_state == SI_HOSED) { + timeout = jiffies + SI_TIMEOUT_HOSED; + } else if ((smi_info->io.irq) && (!smi_info->interrupt_disabled)) { /* Running with interrupts, only do long timeouts. */ timeout = jiffies + SI_TIMEOUT_JIFFIES; smi_inc_stat(smi_info, long_timeouts); @@ -2226,7 +2236,8 @@ static void wait_msg_processed(struct smi_info *smi_info) unsigned long jiffies_now; long time_diff; - while (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL)) { + while (smi_info->si_state != SI_HOSED && + (smi_info->curr_msg || (smi_info->si_state != SI_NORMAL))) { jiffies_now = jiffies; time_diff = (((long)jiffies_now - (long)smi_info->last_timeout_jiffies) * SI_USEC_PER_JIFFY); diff --git a/drivers/char/ipmi/ipmi_si_ls2k.c b/drivers/char/ipmi/ipmi_si_ls2k.c index 45442c257efd..4c1da80f256c 100644 --- a/drivers/char/ipmi/ipmi_si_ls2k.c +++ b/drivers/char/ipmi/ipmi_si_ls2k.c @@ -168,7 +168,7 @@ static void ipmi_ls2k_remove(struct platform_device *pdev) ipmi_si_remove_by_dev(&pdev->dev); } -struct platform_driver ipmi_ls2k_platform_driver = { +static struct platform_driver ipmi_ls2k_platform_driver = { .driver = { .name = "ls2k-ipmi-si", }, diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c index 3ae162625bb1..c781425a005e 100644 --- a/drivers/clk/imx/clk-imx8qxp.c +++ b/drivers/clk/imx/clk-imx8qxp.c @@ -346,7 +346,29 @@ static struct platform_driver imx8qxp_clk_driver = { }, .probe = imx8qxp_clk_probe, }; -module_platform_driver(imx8qxp_clk_driver); + +static int __init imx8qxp_clk_init(void) +{ + int ret; + + ret = platform_driver_register(&imx8qxp_clk_driver); + if (ret) + return ret; + + ret = imx_clk_scu_module_init(); + if (ret) + platform_driver_unregister(&imx8qxp_clk_driver); + + return ret; +} +module_init(imx8qxp_clk_init); + +static void __exit imx8qxp_clk_exit(void) +{ + imx_clk_scu_module_exit(); + platform_driver_unregister(&imx8qxp_clk_driver); +} +module_exit(imx8qxp_clk_exit); MODULE_AUTHOR("Aisheng Dong <aisheng.dong@nxp.com>"); MODULE_DESCRIPTION("NXP i.MX8QXP clock driver"); diff --git a/drivers/clk/imx/clk-scu.c b/drivers/clk/imx/clk-scu.c index 33e637ad3579..a85ec48a798b 100644 --- a/drivers/clk/imx/clk-scu.c +++ b/drivers/clk/imx/clk-scu.c @@ -191,6 +191,16 @@ static bool imx_scu_clk_is_valid(u32 rsrc_id) return p != NULL; } +int __init imx_clk_scu_module_init(void) +{ + return platform_driver_register(&imx_clk_scu_driver); +} + +void __exit imx_clk_scu_module_exit(void) +{ + return platform_driver_unregister(&imx_clk_scu_driver); +} + int imx_clk_scu_init(struct device_node *np, const struct imx_clk_scu_rsrc_table *data) { @@ -215,7 +225,7 @@ int imx_clk_scu_init(struct device_node *np, rsrc_table = data; } - return platform_driver_register(&imx_clk_scu_driver); + return 0; } /* diff --git a/drivers/clk/imx/clk-scu.h b/drivers/clk/imx/clk-scu.h index af7b697f51ca..ca82f2cce897 100644 --- a/drivers/clk/imx/clk-scu.h +++ b/drivers/clk/imx/clk-scu.h @@ -25,6 +25,8 @@ extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8dxl; extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8qxp; extern const struct imx_clk_scu_rsrc_table imx_clk_scu_rsrc_imx8qm; +int __init imx_clk_scu_module_init(void); +void __exit imx_clk_scu_module_exit(void); int imx_clk_scu_init(struct device_node *np, const struct imx_clk_scu_rsrc_table *data); struct clk_hw *imx_scu_of_clk_src_get(struct of_phandle_args *clkspec, diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index a48af3540c74..11c58af41900 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1476,13 +1476,13 @@ static void __intel_pstate_update_max_freq(struct cpufreq_policy *policy, refresh_frequency_limits(policy); } -static bool intel_pstate_update_max_freq(struct cpudata *cpudata) +static bool intel_pstate_update_max_freq(int cpu) { - struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpudata->cpu); + struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); if (!policy) return false; - __intel_pstate_update_max_freq(policy, cpudata); + __intel_pstate_update_max_freq(policy, all_cpu_data[cpu]); return true; } @@ -1501,7 +1501,7 @@ static void intel_pstate_update_limits_for_all(void) int cpu; for_each_possible_cpu(cpu) - intel_pstate_update_max_freq(all_cpu_data[cpu]); + intel_pstate_update_max_freq(cpu); mutex_lock(&hybrid_capacity_lock); @@ -1647,8 +1647,8 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b, static void update_cpu_qos_request(int cpu, enum freq_qos_req_type type) { struct cpudata *cpudata = all_cpu_data[cpu]; - unsigned int freq = cpudata->pstate.turbo_freq; struct freq_qos_request *req; + unsigned int freq; struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu); if (!policy) @@ -1661,6 +1661,8 @@ static void update_cpu_qos_request(int cpu, enum freq_qos_req_type type) if (hwp_active) intel_pstate_get_hwp_cap(cpudata); + freq = cpudata->pstate.turbo_freq; + if (type == FREQ_QOS_MIN) { freq = DIV_ROUND_UP(freq * global.min_perf_pct, 100); } else { @@ -1908,7 +1910,7 @@ static void intel_pstate_notify_work(struct work_struct *work) struct cpudata *cpudata = container_of(to_delayed_work(work), struct cpudata, hwp_notify_work); - if (intel_pstate_update_max_freq(cpudata)) { + if (intel_pstate_update_max_freq(cpudata->cpu)) { /* * The driver will not be unregistered while this function is * running, so update the capacity without acquiring the driver diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h index 007b8aff0238..5b0570df0fd9 100644 --- a/drivers/cxl/core/core.h +++ b/drivers/cxl/core/core.h @@ -152,6 +152,24 @@ int cxl_pci_get_bandwidth(struct pci_dev *pdev, struct access_coordinate *c); int cxl_port_get_switch_dport_bandwidth(struct cxl_port *port, struct access_coordinate *c); +static inline struct device *port_to_host(struct cxl_port *port) +{ + struct cxl_port *parent = is_cxl_root(port) ? NULL : + to_cxl_port(port->dev.parent); + + /* + * The host of CXL root port and the first level of ports is + * the platform firmware device, the host of all other ports + * is their parent port. + */ + if (!parent) + return port->uport_dev; + else if (is_cxl_root(parent)) + return parent->uport_dev; + else + return &parent->dev; +} + static inline struct device *dport_to_host(struct cxl_dport *dport) { struct cxl_port *port = dport->port; diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c index e3f0c39e6812..c222e98ae736 100644 --- a/drivers/cxl/core/hdm.c +++ b/drivers/cxl/core/hdm.c @@ -904,7 +904,7 @@ static void cxl_decoder_reset(struct cxl_decoder *cxld) if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0) return; - if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags)) + if (cxld->flags & CXL_DECODER_F_LOCK) return; if (port->commit_end == id) diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index fa6dd0c94656..e7a6452bf544 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -311,6 +311,7 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) * cxl_payload_from_user_allowed() - Check contents of in_payload. * @opcode: The mailbox command opcode. * @payload_in: Pointer to the input payload passed in from user space. + * @in_size: Size of @payload_in in bytes. * * Return: * * true - payload_in passes check for @opcode. @@ -325,12 +326,15 @@ static bool cxl_mem_raw_command_allowed(u16 opcode) * * The specific checks are determined by the opcode. */ -static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in) +static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in, + size_t in_size) { switch (opcode) { case CXL_MBOX_OP_SET_PARTITION_INFO: { struct cxl_mbox_set_partition_info *pi = payload_in; + if (in_size < sizeof(*pi)) + return false; if (pi->flags & CXL_SET_PARTITION_IMMEDIATE_FLAG) return false; break; @@ -338,6 +342,8 @@ static bool cxl_payload_from_user_allowed(u16 opcode, void *payload_in) case CXL_MBOX_OP_CLEAR_LOG: { const uuid_t *uuid = (uuid_t *)payload_in; + if (in_size < sizeof(uuid_t)) + return false; /* * Restrict the ‘Clear log’ action to only apply to * Vendor debug logs. @@ -365,7 +371,8 @@ static int cxl_mbox_cmd_ctor(struct cxl_mbox_cmd *mbox_cmd, if (IS_ERR(mbox_cmd->payload_in)) return PTR_ERR(mbox_cmd->payload_in); - if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in)) { + if (!cxl_payload_from_user_allowed(opcode, mbox_cmd->payload_in, + in_size)) { dev_dbg(cxl_mbox->host, "%s: input payload not allowed\n", cxl_mem_opcode_to_name(opcode)); kvfree(mbox_cmd->payload_in); diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index f547d8ac34c7..273c22118d3d 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -1089,10 +1089,8 @@ static int cxlmd_add(struct cxl_memdev *cxlmd, struct cxl_dev_state *cxlds) DEFINE_FREE(put_cxlmd, struct cxl_memdev *, if (!IS_ERR_OR_NULL(_T)) put_device(&_T->dev)) -static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd) +static bool cxl_memdev_attach_failed(struct cxl_memdev *cxlmd) { - int rc; - /* * If @attach is provided fail if the driver is not attached upon * return. Note that failure here could be the result of a race to @@ -1100,7 +1098,14 @@ static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd) * succeeded and then cxl_mem unbound before the lock is acquired. */ guard(device)(&cxlmd->dev); - if (cxlmd->attach && !cxlmd->dev.driver) { + return (cxlmd->attach && !cxlmd->dev.driver); +} + +static struct cxl_memdev *cxl_memdev_autoremove(struct cxl_memdev *cxlmd) +{ + int rc; + + if (cxl_memdev_attach_failed(cxlmd)) { cxl_memdev_unregister(cxlmd); return ERR_PTR(-ENXIO); } diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index 3c6e76721522..68462e38a977 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -115,15 +115,17 @@ static void unregister_nvb(void *_cxl_nvb) device_unregister(&cxl_nvb->dev); } -/** - * devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology - * @host: platform firmware root device - * @port: CXL port at the root of a CXL topology - * - * Return: bridge device that can host cxl_nvdimm objects - */ -struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, - struct cxl_port *port) +static bool cxl_nvdimm_bridge_failed_attach(struct cxl_nvdimm_bridge *cxl_nvb) +{ + struct device *dev = &cxl_nvb->dev; + + guard(device)(dev); + /* If the device has no driver, then it failed to attach. */ + return dev->driver == NULL; +} + +struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host, + struct cxl_port *port) { struct cxl_nvdimm_bridge *cxl_nvb; struct device *dev; @@ -145,6 +147,11 @@ struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, if (rc) goto err; + if (cxl_nvdimm_bridge_failed_attach(cxl_nvb)) { + unregister_nvb(cxl_nvb); + return ERR_PTR(-ENODEV); + } + rc = devm_add_action_or_reset(host, unregister_nvb, cxl_nvb); if (rc) return ERR_PTR(rc); @@ -155,7 +162,7 @@ err: put_device(dev); return ERR_PTR(rc); } -EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm_bridge, "CXL"); +EXPORT_SYMBOL_FOR_MODULES(__devm_cxl_add_nvdimm_bridge, "cxl_pmem"); static void cxl_nvdimm_release(struct device *dev) { @@ -255,6 +262,21 @@ int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port, if (!cxl_nvb) return -ENODEV; + /* + * Take the uport_dev lock to guard against race of nvdimm_bus object. + * cxl_acpi_probe() registers the nvdimm_bus and is done under the + * root port uport_dev lock. + * + * Take the cxl_nvb device lock to ensure that cxl_nvb driver is in a + * consistent state. And the driver registers nvdimm_bus. + */ + guard(device)(cxl_nvb->port->uport_dev); + guard(device)(&cxl_nvb->dev); + if (!cxl_nvb->nvdimm_bus) { + rc = -ENODEV; + goto err_alloc; + } + cxl_nvd = cxl_nvdimm_alloc(cxl_nvb, cxlmd); if (IS_ERR(cxl_nvd)) { rc = PTR_ERR(cxl_nvd); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index b69c2529744c..0c5957d1d329 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -615,22 +615,8 @@ struct cxl_port *parent_port_of(struct cxl_port *port) static void unregister_port(void *_port) { struct cxl_port *port = _port; - struct cxl_port *parent = parent_port_of(port); - struct device *lock_dev; - /* - * CXL root port's and the first level of ports are unregistered - * under the platform firmware device lock, all other ports are - * unregistered while holding their parent port lock. - */ - if (!parent) - lock_dev = port->uport_dev; - else if (is_cxl_root(parent)) - lock_dev = parent->uport_dev; - else - lock_dev = &parent->dev; - - device_lock_assert(lock_dev); + device_lock_assert(port_to_host(port)); port->dead = true; device_unregister(&port->dev); } @@ -1427,20 +1413,11 @@ static struct device *grandparent(struct device *dev) return NULL; } -static struct device *endpoint_host(struct cxl_port *endpoint) -{ - struct cxl_port *port = to_cxl_port(endpoint->dev.parent); - - if (is_cxl_root(port)) - return port->uport_dev; - return &port->dev; -} - static void delete_endpoint(void *data) { struct cxl_memdev *cxlmd = data; struct cxl_port *endpoint = cxlmd->endpoint; - struct device *host = endpoint_host(endpoint); + struct device *host = port_to_host(endpoint); scoped_guard(device, host) { if (host->driver && !endpoint->dead) { @@ -1456,7 +1433,7 @@ static void delete_endpoint(void *data) int cxl_endpoint_autoremove(struct cxl_memdev *cxlmd, struct cxl_port *endpoint) { - struct device *host = endpoint_host(endpoint); + struct device *host = port_to_host(endpoint); struct device *dev = &cxlmd->dev; get_device(host); @@ -1790,7 +1767,16 @@ static struct cxl_dport *find_or_add_dport(struct cxl_port *port, { struct cxl_dport *dport; - device_lock_assert(&port->dev); + /* + * The port is already visible in CXL hierarchy, but it may still + * be in the process of binding to the CXL port driver at this point. + * + * port creation and driver binding are protected by the port's host + * lock, so acquire the host lock here to ensure the port has completed + * driver binding before proceeding with dport addition. + */ + guard(device)(port_to_host(port)); + guard(device)(&port->dev); dport = cxl_find_dport_by_dev(port, dport_dev); if (!dport) { dport = probe_dport(port, dport_dev); @@ -1857,13 +1843,11 @@ retry: * RP port enumerated by cxl_acpi without dport will * have the dport added here. */ - scoped_guard(device, &port->dev) { - dport = find_or_add_dport(port, dport_dev); - if (IS_ERR(dport)) { - if (PTR_ERR(dport) == -EAGAIN) - goto retry; - return PTR_ERR(dport); - } + dport = find_or_add_dport(port, dport_dev); + if (IS_ERR(dport)) { + if (PTR_ERR(dport) == -EAGAIN) + goto retry; + return PTR_ERR(dport); } rc = cxl_add_ep(dport, &cxlmd->dev); diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index fec37af1dfbf..42874948b589 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -1100,12 +1100,12 @@ static int cxl_rr_assign_decoder(struct cxl_port *port, struct cxl_region *cxlr, static void cxl_region_setup_flags(struct cxl_region *cxlr, struct cxl_decoder *cxld) { - if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags)) { + if (cxld->flags & CXL_DECODER_F_LOCK) { set_bit(CXL_REGION_F_LOCK, &cxlr->flags); clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags); } - if (test_bit(CXL_DECODER_F_NORMALIZED_ADDRESSING, &cxld->flags)) + if (cxld->flags & CXL_DECODER_F_NORMALIZED_ADDRESSING) set_bit(CXL_REGION_F_NORMALIZED_ADDRESSING, &cxlr->flags); } diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index 04c673e7cdb0..9b947286eb9b 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -574,11 +574,16 @@ struct cxl_nvdimm_bridge { #define CXL_DEV_ID_LEN 19 +enum { + CXL_NVD_F_INVALIDATED = 0, +}; + struct cxl_nvdimm { struct device dev; struct cxl_memdev *cxlmd; u8 dev_id[CXL_DEV_ID_LEN]; /* for nvdimm, string of 'serial' */ u64 dirty_shutdowns; + unsigned long flags; }; struct cxl_pmem_region_mapping { @@ -920,6 +925,8 @@ void cxl_driver_unregister(struct cxl_driver *cxl_drv); struct cxl_nvdimm_bridge *to_cxl_nvdimm_bridge(struct device *dev); struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, struct cxl_port *port); +struct cxl_nvdimm_bridge *__devm_cxl_add_nvdimm_bridge(struct device *host, + struct cxl_port *port); struct cxl_nvdimm *to_cxl_nvdimm(struct device *dev); bool is_cxl_nvdimm(struct device *dev); int devm_cxl_add_nvdimm(struct device *host, struct cxl_port *port, diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 6a97e4e490b6..082ec0f1c3a0 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -13,6 +13,20 @@ static __read_mostly DECLARE_BITMAP(exclusive_cmds, CXL_MEM_COMMAND_ID_MAX); +/** + * devm_cxl_add_nvdimm_bridge() - add the root of a LIBNVDIMM topology + * @host: platform firmware root device + * @port: CXL port at the root of a CXL topology + * + * Return: bridge device that can host cxl_nvdimm objects + */ +struct cxl_nvdimm_bridge *devm_cxl_add_nvdimm_bridge(struct device *host, + struct cxl_port *port) +{ + return __devm_cxl_add_nvdimm_bridge(host, port); +} +EXPORT_SYMBOL_NS_GPL(devm_cxl_add_nvdimm_bridge, "CXL"); + static void clear_exclusive(void *mds) { clear_exclusive_cxl_commands(mds, exclusive_cmds); @@ -129,6 +143,9 @@ static int cxl_nvdimm_probe(struct device *dev) struct nvdimm *nvdimm; int rc; + if (test_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags)) + return -EBUSY; + set_exclusive_cxl_commands(mds, exclusive_cmds); rc = devm_add_action_or_reset(dev, clear_exclusive, mds); if (rc) @@ -309,8 +326,10 @@ static int detach_nvdimm(struct device *dev, void *data) scoped_guard(device, dev) { if (dev->driver) { cxl_nvd = to_cxl_nvdimm(dev); - if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) + if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) { release = true; + set_bit(CXL_NVD_F_INVALIDATED, &cxl_nvd->flags); + } } } if (release) @@ -353,6 +372,7 @@ static struct cxl_driver cxl_nvdimm_bridge_driver = { .probe = cxl_nvdimm_bridge_probe, .id = CXL_DEVICE_NVDIMM_BRIDGE, .drv = { + .probe_type = PROBE_FORCE_SYNCHRONOUS, .suppress_bind_attrs = true, }, }; diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 1c868c1e4a49..8153d62c58f0 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -848,7 +848,7 @@ static int ar_context_init(struct ar_context *ctx, struct fw_ohci *ohci, { struct device *dev = ohci->card.device; unsigned int i; - struct page *pages[AR_BUFFERS + AR_WRAPAROUND_PAGES]; + struct page *pages[AR_BUFFERS + AR_WRAPAROUND_PAGES] = { NULL }; dma_addr_t dma_addrs[AR_BUFFERS]; void *vaddr; struct descriptor *d; diff --git a/drivers/gpio/gpiolib-shared.c b/drivers/gpio/gpiolib-shared.c index d2614ace4de1..17a7128b6bd9 100644 --- a/drivers/gpio/gpiolib-shared.c +++ b/drivers/gpio/gpiolib-shared.c @@ -748,14 +748,14 @@ static bool gpio_shared_entry_is_really_shared(struct gpio_shared_entry *entry) static void gpio_shared_free_exclusive(void) { struct gpio_shared_entry *entry, *epos; + struct gpio_shared_ref *ref, *rpos; list_for_each_entry_safe(entry, epos, &gpio_shared_list, list) { if (gpio_shared_entry_is_really_shared(entry)) continue; - gpio_shared_drop_ref(list_first_entry(&entry->refs, - struct gpio_shared_ref, - list)); + list_for_each_entry_safe(ref, rpos, &entry->refs, list) + gpio_shared_drop_ref(ref); gpio_shared_drop_entry(entry); } } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 86a171e96b0e..ada572aaebd6 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -3267,8 +3267,12 @@ static int gpiochip_get(struct gpio_chip *gc, unsigned int offset) /* Make sure this is called after checking for gc->get(). */ ret = gc->get(gc, offset); - if (ret > 1) - ret = -EBADE; + if (ret > 1) { + gpiochip_warn(gc, + "invalid return value from gc->get(): %d, consider fixing the driver\n", + ret); + ret = !!ret; + } return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c index afe5ca81beec..db7858fe0c3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c @@ -641,6 +641,7 @@ static void aca_error_fini(struct aca_error *aerr) aca_bank_error_remove(aerr, bank_error); out_unlock: + mutex_unlock(&aerr->lock); mutex_destroy(&aerr->lock); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d9789e0b5201..3e19b51a2763 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -7059,6 +7059,15 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev) dev_info(adev->dev, "PCI error: slot reset callback!!\n"); memset(&reset_context, 0, sizeof(reset_context)); + INIT_LIST_HEAD(&device_list); + hive = amdgpu_get_xgmi_hive(adev); + if (hive) { + mutex_lock(&hive->hive_lock); + list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) + list_add_tail(&tmp_adev->reset_list, &device_list); + } else { + list_add_tail(&adev->reset_list, &device_list); + } if (adev->pcie_reset_ctx.swus) link_dev = adev->pcie_reset_ctx.swus; @@ -7099,19 +7108,13 @@ pci_ers_result_t amdgpu_pci_slot_reset(struct pci_dev *pdev) reset_context.reset_req_dev = adev; set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags); - INIT_LIST_HEAD(&device_list); - hive = amdgpu_get_xgmi_hive(adev); if (hive) { - mutex_lock(&hive->hive_lock); reset_context.hive = hive; - list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { + list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) tmp_adev->pcie_reset_ctx.in_link_reset = true; - list_add_tail(&tmp_adev->reset_list, &device_list); - } } else { set_bit(AMDGPU_SKIP_HW_RESET, &reset_context.flags); - list_add_tail(&adev->reset_list, &device_list); } r = amdgpu_device_asic_reset(adev, &device_list, &reset_context); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index 6e8aad91bcd3..0d3c18f04ac3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -332,13 +332,13 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size if (!context || !context->initialized) { dev_err(adev->dev, "TA is not initialized\n"); ret = -EINVAL; - goto err_free_shared_buf; + goto free_shared_buf; } if (!psp->ta_funcs || !psp->ta_funcs->fn_ta_invoke) { dev_err(adev->dev, "Unsupported function to invoke TA\n"); ret = -EOPNOTSUPP; - goto err_free_shared_buf; + goto free_shared_buf; } context->session_id = ta_id; @@ -346,7 +346,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size mutex_lock(&psp->ras_context.mutex); ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len); if (ret) - goto err_free_shared_buf; + goto unlock; ret = psp_fn_ta_invoke(psp, cmd_id); if (ret || context->resp_status) { @@ -354,15 +354,17 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size ret, context->resp_status); if (!ret) { ret = -EINVAL; - goto err_free_shared_buf; + goto unlock; } } if (copy_to_user((char *)&buf[copy_pos], context->mem_context.shared_buf, shared_buf_len)) ret = -EFAULT; -err_free_shared_buf: +unlock: mutex_unlock(&psp->ras_context.mutex); + +free_shared_buf: kfree(shared_buf); return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c index 8013260e29dc..7e9cf1868cc9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c @@ -35,6 +35,8 @@ static const struct dma_fence_ops amdgpu_userq_fence_ops; static struct kmem_cache *amdgpu_userq_fence_slab; +#define AMDGPU_USERQ_MAX_HANDLES (1U << 16) + int amdgpu_userq_fence_slab_init(void) { amdgpu_userq_fence_slab = kmem_cache_create("amdgpu_userq_fence", @@ -478,6 +480,11 @@ int amdgpu_userq_signal_ioctl(struct drm_device *dev, void *data, if (!amdgpu_userq_enabled(dev)) return -ENOTSUPP; + if (args->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES || + args->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES || + args->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES) + return -EINVAL; + num_syncobj_handles = args->num_syncobj_handles; syncobj_handles = memdup_user(u64_to_user_ptr(args->syncobj_handles), size_mul(sizeof(u32), num_syncobj_handles)); @@ -664,6 +671,11 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, if (!amdgpu_userq_enabled(dev)) return -ENOTSUPP; + if (wait_info->num_syncobj_handles > AMDGPU_USERQ_MAX_HANDLES || + wait_info->num_bo_write_handles > AMDGPU_USERQ_MAX_HANDLES || + wait_info->num_bo_read_handles > AMDGPU_USERQ_MAX_HANDLES) + return -EINVAL; + num_read_bo_handles = wait_info->num_bo_read_handles; bo_handles_read = memdup_user(u64_to_user_ptr(wait_info->bo_read_handles), size_mul(sizeof(u32), num_read_bo_handles)); @@ -833,7 +845,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, dma_resv_for_each_fence(&resv_cursor, gobj_read[i]->resv, DMA_RESV_USAGE_READ, fence) { - if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) { + if (num_fences >= wait_info->num_fences) { r = -EINVAL; goto free_fences; } @@ -850,7 +862,7 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, dma_resv_for_each_fence(&resv_cursor, gobj_write[i]->resv, DMA_RESV_USAGE_WRITE, fence) { - if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) { + if (num_fences >= wait_info->num_fences) { r = -EINVAL; goto free_fences; } @@ -874,8 +886,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, goto free_fences; dma_fence_unwrap_for_each(f, &iter, fence) { - if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) { + if (num_fences >= wait_info->num_fences) { r = -EINVAL; + dma_fence_put(fence); goto free_fences; } @@ -898,8 +911,9 @@ int amdgpu_userq_wait_ioctl(struct drm_device *dev, void *data, if (r) goto free_fences; - if (WARN_ON_ONCE(num_fences >= wait_info->num_fences)) { + if (num_fences >= wait_info->num_fences) { r = -EINVAL; + dma_fence_put(fence); goto free_fences; } diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 09ebb13ca5e8..a926a330700e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -720,11 +720,6 @@ static int mes_v11_0_set_hw_resources(struct amdgpu_mes *mes) mes_set_hw_res_pkt.enable_reg_active_poll = 1; mes_set_hw_res_pkt.enable_level_process_quantum_check = 1; mes_set_hw_res_pkt.oversubscription_timer = 50; - if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x7f) - mes_set_hw_res_pkt.enable_lr_compute_wa = 1; - else - dev_info_once(mes->adev->dev, - "MES FW version must be >= 0x7f to enable LR compute workaround.\n"); if (amdgpu_mes_log_enable) { mes_set_hw_res_pkt.enable_mes_event_int_logging = 1; diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index b1c864dc79a8..5bfa5d1d0b36 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -779,11 +779,6 @@ static int mes_v12_0_set_hw_resources(struct amdgpu_mes *mes, int pipe) mes_set_hw_res_pkt.use_different_vmid_compute = 1; mes_set_hw_res_pkt.enable_reg_active_poll = 1; mes_set_hw_res_pkt.enable_level_process_quantum_check = 1; - if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) >= 0x82) - mes_set_hw_res_pkt.enable_lr_compute_wa = 1; - else - dev_info_once(adev->dev, - "MES FW version must be >= 0x82 to enable LR compute workaround.\n"); /* * Keep oversubscribe timer for sdma . When we have unmapped doorbell diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c index 0202df5db1e1..6109124f852e 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c @@ -174,6 +174,10 @@ static int vcn_v5_0_0_sw_init(struct amdgpu_ip_block *ip_block) fw_shared->present_flag_0 = cpu_to_le32(AMDGPU_FW_SHARED_FLAG_0_UNIFIED_QUEUE); fw_shared->sq.is_enabled = 1; + fw_shared->present_flag_0 |= cpu_to_le32(AMDGPU_VCN_SMU_DPM_INTERFACE_FLAG); + fw_shared->smu_dpm_interface.smu_interface_type = (adev->flags & AMD_IS_APU) ? + AMDGPU_VCN_SMU_DPM_INTERFACE_APU : AMDGPU_VCN_SMU_DPM_INTERFACE_DGPU; + if (amdgpu_vcnfw_log) amdgpu_vcn_fwlog_init(&adev->vcn.inst[i]); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c index 246893d80f1f..baf820e6eae8 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -170,11 +170,11 @@ struct dc_stream_state *dc_create_stream_for_sink( if (sink == NULL) goto fail; - stream = kzalloc_obj(struct dc_stream_state); + stream = kzalloc_obj(struct dc_stream_state, GFP_ATOMIC); if (stream == NULL) goto fail; - stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_KERNEL); + stream->update_scratch = kzalloc((int32_t) dc_update_scratch_space_size(), GFP_ATOMIC); if (stream->update_scratch == NULL) goto fail; diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c index 930aaa659c97..ec632f268644 100644 --- a/drivers/gpu/drm/bridge/samsung-dsim.c +++ b/drivers/gpu/drm/bridge/samsung-dsim.c @@ -1881,6 +1881,14 @@ static int samsung_dsim_register_te_irq(struct samsung_dsim *dsi, struct device return 0; } +static void samsung_dsim_unregister_te_irq(struct samsung_dsim *dsi) +{ + if (dsi->te_gpio) { + free_irq(gpiod_to_irq(dsi->te_gpio), dsi); + gpiod_put(dsi->te_gpio); + } +} + static int samsung_dsim_host_attach(struct mipi_dsi_host *host, struct mipi_dsi_device *device) { @@ -1961,7 +1969,7 @@ of_find_panel_or_bridge: if (!(device->mode_flags & MIPI_DSI_MODE_VIDEO)) { ret = samsung_dsim_register_te_irq(dsi, &device->dev); if (ret) - return ret; + goto err_remove_bridge; } // The next bridge can be used by host_ops->attach @@ -1982,15 +1990,12 @@ of_find_panel_or_bridge: err_release_next_bridge: drm_bridge_put(dsi->bridge.next_bridge); dsi->bridge.next_bridge = NULL; - return ret; -} -static void samsung_dsim_unregister_te_irq(struct samsung_dsim *dsi) -{ - if (dsi->te_gpio) { - free_irq(gpiod_to_irq(dsi->te_gpio), dsi); - gpiod_put(dsi->te_gpio); - } + if (!(device->mode_flags & MIPI_DSI_MODE_VIDEO)) + samsung_dsim_unregister_te_irq(dsi); +err_remove_bridge: + drm_bridge_remove(&dsi->bridge); + return ret; } static int samsung_dsim_host_detach(struct mipi_dsi_host *host, diff --git a/drivers/gpu/drm/bridge/synopsys/dw-dp.c b/drivers/gpu/drm/bridge/synopsys/dw-dp.c index 4ab6922dd79c..fd23ca2834b0 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-dp.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-dp.c @@ -2049,7 +2049,9 @@ struct dw_dp *dw_dp_bind(struct device *dev, struct drm_encoder *encoder, bridge->type = DRM_MODE_CONNECTOR_DisplayPort; bridge->ycbcr_420_allowed = true; - devm_drm_bridge_add(dev, bridge); + ret = devm_drm_bridge_add(dev, bridge); + if (ret) + return ERR_PTR(ret); dp->aux.dev = dev; dp->aux.drm_dev = encoder->dev; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 276d05d25ad8..98d64ad791d0 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1415,6 +1415,7 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, { struct ti_sn65dsi86 *pdata = dev_get_drvdata(adev->dev.parent); struct device_node *np = pdata->dev->of_node; + const struct i2c_client *client = to_i2c_client(pdata->dev); int ret; pdata->next_bridge = devm_drm_of_get_bridge(&adev->dev, np, 1, 0); @@ -1433,8 +1434,9 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, ? DRM_MODE_CONNECTOR_DisplayPort : DRM_MODE_CONNECTOR_eDP; if (pdata->bridge.type == DRM_MODE_CONNECTOR_DisplayPort) { - pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT | - DRM_BRIDGE_OP_HPD; + pdata->bridge.ops = DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_DETECT; + if (client->irq) + pdata->bridge.ops |= DRM_BRIDGE_OP_HPD; /* * If comms were already enabled they would have been enabled * with the wrong value of HPD_DISABLE. Update it now. Comms diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 262b1b8773c5..bb49b8361271 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -930,7 +930,8 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, mutex_unlock(&client->modeset_mutex); out: kfree(crtcs); - modes_destroy(dev, modes, connector_count); + if (modes) + modes_destroy(dev, modes, connector_count); kfree(modes); kfree(offsets); kfree(enabled); diff --git a/drivers/gpu/drm/drm_gpusvm.c b/drivers/gpu/drm/drm_gpusvm.c index 24180bfdf5a2..9ef9e52c0547 100644 --- a/drivers/gpu/drm/drm_gpusvm.c +++ b/drivers/gpu/drm/drm_gpusvm.c @@ -1338,14 +1338,14 @@ bool drm_gpusvm_range_pages_valid(struct drm_gpusvm *gpusvm, EXPORT_SYMBOL_GPL(drm_gpusvm_range_pages_valid); /** - * drm_gpusvm_range_pages_valid_unlocked() - GPU SVM range pages valid unlocked + * drm_gpusvm_pages_valid_unlocked() - GPU SVM pages valid unlocked * @gpusvm: Pointer to the GPU SVM structure - * @range: Pointer to the GPU SVM range structure + * @svm_pages: Pointer to the GPU SVM pages structure * - * This function determines if a GPU SVM range pages are valid. Expected be - * called without holding gpusvm->notifier_lock. + * This function determines if a GPU SVM pages are valid. Expected be called + * without holding gpusvm->notifier_lock. * - * Return: True if GPU SVM range has valid pages, False otherwise + * Return: True if GPU SVM pages are valid, False otherwise */ static bool drm_gpusvm_pages_valid_unlocked(struct drm_gpusvm *gpusvm, struct drm_gpusvm_pages *svm_pages) diff --git a/drivers/gpu/drm/i915/display/intel_alpm.c b/drivers/gpu/drm/i915/display/intel_alpm.c index 7ce8c674bb03..07ffee38974b 100644 --- a/drivers/gpu/drm/i915/display/intel_alpm.c +++ b/drivers/gpu/drm/i915/display/intel_alpm.c @@ -562,12 +562,7 @@ void intel_alpm_disable(struct intel_dp *intel_dp) mutex_lock(&intel_dp->alpm.lock); intel_de_rmw(display, ALPM_CTL(display, cpu_transcoder), - ALPM_CTL_ALPM_ENABLE | ALPM_CTL_LOBF_ENABLE | - ALPM_CTL_ALPM_AUX_LESS_ENABLE, 0); - - intel_de_rmw(display, - PORT_ALPM_CTL(cpu_transcoder), - PORT_ALPM_CTL_ALPM_AUX_LESS_ENABLE, 0); + ALPM_CTL_ALPM_ENABLE | ALPM_CTL_LOBF_ENABLE, 0); drm_dbg_kms(display->drm, "Disabling ALPM\n"); mutex_unlock(&intel_dp->alpm.lock); diff --git a/drivers/gpu/drm/imx/ipuv3/parallel-display.c b/drivers/gpu/drm/imx/ipuv3/parallel-display.c index dea85577513a..4ce772bc3cb3 100644 --- a/drivers/gpu/drm/imx/ipuv3/parallel-display.c +++ b/drivers/gpu/drm/imx/ipuv3/parallel-display.c @@ -256,7 +256,9 @@ static int imx_pd_probe(struct platform_device *pdev) platform_set_drvdata(pdev, imxpd); - devm_drm_bridge_add(dev, &imxpd->bridge); + ret = devm_drm_bridge_add(dev, &imxpd->bridge); + if (ret) + return ret; return component_add(dev, &imx_pd_ops); } diff --git a/drivers/gpu/drm/logicvc/logicvc_drm.c b/drivers/gpu/drm/logicvc/logicvc_drm.c index 204b0fee55d0..bbebf4fc7f51 100644 --- a/drivers/gpu/drm/logicvc/logicvc_drm.c +++ b/drivers/gpu/drm/logicvc/logicvc_drm.c @@ -92,7 +92,6 @@ static int logicvc_drm_config_parse(struct logicvc_drm *logicvc) struct device *dev = drm_dev->dev; struct device_node *of_node = dev->of_node; struct logicvc_drm_config *config = &logicvc->config; - struct device_node *layers_node; int ret; logicvc_of_property_parse_bool(of_node, LOGICVC_OF_PROPERTY_DITHERING, @@ -128,7 +127,8 @@ static int logicvc_drm_config_parse(struct logicvc_drm *logicvc) if (ret) return ret; - layers_node = of_get_child_by_name(of_node, "layers"); + struct device_node *layers_node __free(device_node) = + of_get_child_by_name(of_node, "layers"); if (!layers_node) { drm_err(drm_dev, "Missing non-optional layers node\n"); return -EINVAL; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c index e10192fe1d0f..0121d5639471 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/gsp.c @@ -737,8 +737,8 @@ r535_gsp_acpi_caps(acpi_handle handle, CAPS_METHOD_DATA *caps) if (!obj) goto done; - if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || - WARN_ON(obj->buffer.length != 4)) + if (obj->type != ACPI_TYPE_BUFFER || + obj->buffer.length != 4) goto done; caps->status = 0; @@ -773,8 +773,8 @@ r535_gsp_acpi_jt(acpi_handle handle, JT_METHOD_DATA *jt) if (!obj) goto done; - if (WARN_ON(obj->type != ACPI_TYPE_BUFFER) || - WARN_ON(obj->buffer.length != 4)) + if (obj->type != ACPI_TYPE_BUFFER || + obj->buffer.length != 4) goto done; jt->status = 0; @@ -861,8 +861,8 @@ r535_gsp_acpi_dod(acpi_handle handle, DOD_METHOD_DATA *dod) _DOD = output.pointer; - if (WARN_ON(_DOD->type != ACPI_TYPE_PACKAGE) || - WARN_ON(_DOD->package.count > ARRAY_SIZE(dod->acpiIdList))) + if (_DOD->type != ACPI_TYPE_PACKAGE || + _DOD->package.count > ARRAY_SIZE(dod->acpiIdList)) return; for (int i = 0; i < _DOD->package.count; i++) { diff --git a/drivers/gpu/drm/tiny/sharp-memory.c b/drivers/gpu/drm/tiny/sharp-memory.c index 64272cd0f6e2..cbf69460ebf3 100644 --- a/drivers/gpu/drm/tiny/sharp-memory.c +++ b/drivers/gpu/drm/tiny/sharp-memory.c @@ -541,8 +541,8 @@ static int sharp_memory_probe(struct spi_device *spi) smd = devm_drm_dev_alloc(dev, &sharp_memory_drm_driver, struct sharp_memory_device, drm); - if (!smd) - return -ENOMEM; + if (IS_ERR(smd)) + return PTR_ERR(smd); spi_set_drvdata(spi, smd); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c index 2170b45c30e9..f45d93e8c1c8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c @@ -105,6 +105,7 @@ struct vmw_cmdbuf_context { * @handle: DMA address handle for the command buffer space if @using_mob is * false. Immutable. * @size: The size of the command buffer space. Immutable. + * @id: Monotonically increasing ID of the last cmdbuf submitted. * @num_contexts: Number of contexts actually enabled. */ struct vmw_cmdbuf_man { @@ -132,6 +133,7 @@ struct vmw_cmdbuf_man { bool has_pool; dma_addr_t handle; size_t size; + u64 id; u32 num_contexts; }; @@ -303,6 +305,8 @@ static int vmw_cmdbuf_header_submit(struct vmw_cmdbuf_header *header) struct vmw_cmdbuf_man *man = header->man; u32 val; + header->cb_header->id = man->id++; + val = upper_32_bits(header->handle); vmw_write(man->dev_priv, SVGA_REG_COMMAND_HIGH, val); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 3057f8baa7d2..e1f18020170a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1143,7 +1143,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo); if (ret != 0) { drm_dbg(&dev_priv->drm, "Could not find or use MOB buffer.\n"); - return PTR_ERR(vmw_bo); + return ret; } vmw_bo_placement_set(vmw_bo, VMW_BO_DOMAIN_MOB, VMW_BO_DOMAIN_MOB); ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo); @@ -1199,7 +1199,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo); if (ret != 0) { drm_dbg(&dev_priv->drm, "Could not find or use GMR region.\n"); - return PTR_ERR(vmw_bo); + return ret; } vmw_bo_placement_set(vmw_bo, VMW_BO_DOMAIN_GMR | VMW_BO_DOMAIN_VRAM, VMW_BO_DOMAIN_GMR | VMW_BO_DOMAIN_VRAM); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c index fd4e76486f2d..45561bc1c9ef 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_page_dirty.c @@ -260,6 +260,13 @@ out_no_dirty: return ret; } +static void vmw_bo_dirty_free(struct kref *kref) +{ + struct vmw_bo_dirty *dirty = container_of(kref, struct vmw_bo_dirty, ref_count); + + kvfree(dirty); +} + /** * vmw_bo_dirty_release - Release a dirty-tracking user from a buffer object * @vbo: The buffer object @@ -274,7 +281,7 @@ void vmw_bo_dirty_release(struct vmw_bo *vbo) { struct vmw_bo_dirty *dirty = vbo->dirty; - if (dirty && kref_put(&dirty->ref_count, (void *)kvfree)) + if (dirty && kref_put(&dirty->ref_count, vmw_bo_dirty_free)) vbo->dirty = NULL; } diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h index 68172b0248a6..dc5a4fafa70c 100644 --- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h +++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h @@ -96,6 +96,12 @@ #define ENABLE_SEMAPHORE_POLL_BIT REG_BIT(13) #define RING_CMD_CCTL(base) XE_REG((base) + 0xc4, XE_REG_OPTION_MASKED) + +#define CS_MMIO_GROUP_INSTANCE_SELECT(base) XE_REG((base) + 0xcc) +#define SELECTIVE_READ_ADDRESSING REG_BIT(30) +#define SELECTIVE_READ_GROUP REG_GENMASK(29, 23) +#define SELECTIVE_READ_INSTANCE REG_GENMASK(22, 16) + /* * CMD_CCTL read/write fields take a MOCS value and _not_ a table index. * The lsb of each can be considered a separate enabling bit for encryption. diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 9d090d0f2438..df6d04704823 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -210,11 +210,15 @@ static int emit_nop_job(struct xe_gt *gt, struct xe_exec_queue *q) return ret; } +/* Dwords required to emit a RMW of a register */ +#define EMIT_RMW_DW 20 + static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q) { - struct xe_reg_sr *sr = &q->hwe->reg_lrc; + struct xe_hw_engine *hwe = q->hwe; + struct xe_reg_sr *sr = &hwe->reg_lrc; struct xe_reg_sr_entry *entry; - int count_rmw = 0, count = 0, ret; + int count_rmw = 0, count_rmw_mcr = 0, count = 0, ret; unsigned long idx; struct xe_bb *bb; size_t bb_len = 0; @@ -224,6 +228,8 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q) xa_for_each(&sr->xa, idx, entry) { if (entry->reg.masked || entry->clr_bits == ~0) ++count; + else if (entry->reg.mcr) + ++count_rmw_mcr; else ++count_rmw; } @@ -231,17 +237,35 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q) if (count) bb_len += count * 2 + 1; - if (count_rmw) - bb_len += count_rmw * 20 + 7; + /* + * RMW of MCR registers is the same as a normal RMW, except an + * additional LRI (3 dwords) is required per register to steer the read + * to a nom-terminated instance. + * + * We could probably shorten the batch slightly by eliding the + * steering for consecutive MCR registers that have the same + * group/instance target, but it's not worth the extra complexity to do + * so. + */ + bb_len += count_rmw * EMIT_RMW_DW; + bb_len += count_rmw_mcr * (EMIT_RMW_DW + 3); + + /* + * After doing all RMW, we need 7 trailing dwords to clean up, + * plus an additional 3 dwords to reset steering if any of the + * registers were MCR. + */ + if (count_rmw || count_rmw_mcr) + bb_len += 7 + (count_rmw_mcr ? 3 : 0); - if (q->hwe->class == XE_ENGINE_CLASS_RENDER) + if (hwe->class == XE_ENGINE_CLASS_RENDER) /* * Big enough to emit all of the context's 3DSTATE via * xe_lrc_emit_hwe_state_instructions() */ - bb_len += xe_gt_lrc_size(gt, q->hwe->class) / sizeof(u32); + bb_len += xe_gt_lrc_size(gt, hwe->class) / sizeof(u32); - xe_gt_dbg(gt, "LRC %s WA job: %zu dwords\n", q->hwe->name, bb_len); + xe_gt_dbg(gt, "LRC %s WA job: %zu dwords\n", hwe->name, bb_len); bb = xe_bb_new(gt, bb_len, false); if (IS_ERR(bb)) @@ -276,13 +300,23 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q) } } - if (count_rmw) { - /* Emit MI_MATH for each RMW reg: 20dw per reg + 7 trailing dw */ - + if (count_rmw || count_rmw_mcr) { xa_for_each(&sr->xa, idx, entry) { if (entry->reg.masked || entry->clr_bits == ~0) continue; + if (entry->reg.mcr) { + struct xe_reg_mcr reg = { .__reg.raw = entry->reg.raw }; + u8 group, instance; + + xe_gt_mcr_get_nonterminated_steering(gt, reg, &group, &instance); + *cs++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1); + *cs++ = CS_MMIO_GROUP_INSTANCE_SELECT(hwe->mmio_base).addr; + *cs++ = SELECTIVE_READ_ADDRESSING | + REG_FIELD_PREP(SELECTIVE_READ_GROUP, group) | + REG_FIELD_PREP(SELECTIVE_READ_INSTANCE, instance); + } + *cs++ = MI_LOAD_REGISTER_REG | MI_LRR_DST_CS_MMIO; *cs++ = entry->reg.addr; *cs++ = CS_GPR_REG(0, 0).addr; @@ -308,8 +342,9 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q) *cs++ = CS_GPR_REG(0, 0).addr; *cs++ = entry->reg.addr; - xe_gt_dbg(gt, "REG[%#x] = ~%#x|%#x\n", - entry->reg.addr, entry->clr_bits, entry->set_bits); + xe_gt_dbg(gt, "REG[%#x] = ~%#x|%#x%s\n", + entry->reg.addr, entry->clr_bits, entry->set_bits, + entry->reg.mcr ? " (MCR)" : ""); } /* reset used GPR */ @@ -321,6 +356,13 @@ static int emit_wa_job(struct xe_gt *gt, struct xe_exec_queue *q) *cs++ = 0; *cs++ = CS_GPR_REG(0, 2).addr; *cs++ = 0; + + /* reset steering */ + if (count_rmw_mcr) { + *cs++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1); + *cs++ = CS_MMIO_GROUP_INSTANCE_SELECT(q->hwe->mmio_base).addr; + *cs++ = 0; + } } cs = xe_lrc_emit_hwe_state_instructions(q, cs); diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c index eb136390dafd..24d6d9af20d6 100644 --- a/drivers/gpu/drm/xe/xe_sync.c +++ b/drivers/gpu/drm/xe/xe_sync.c @@ -146,8 +146,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, if (!signal) { sync->fence = drm_syncobj_fence_get(sync->syncobj); - if (XE_IOCTL_DBG(xe, !sync->fence)) - return -EINVAL; + if (XE_IOCTL_DBG(xe, !sync->fence)) { + err = -EINVAL; + goto free_sync; + } } break; @@ -167,17 +169,21 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, if (signal) { sync->chain_fence = dma_fence_chain_alloc(); - if (!sync->chain_fence) - return -ENOMEM; + if (!sync->chain_fence) { + err = -ENOMEM; + goto free_sync; + } } else { sync->fence = drm_syncobj_fence_get(sync->syncobj); - if (XE_IOCTL_DBG(xe, !sync->fence)) - return -EINVAL; + if (XE_IOCTL_DBG(xe, !sync->fence)) { + err = -EINVAL; + goto free_sync; + } err = dma_fence_chain_find_seqno(&sync->fence, sync_in.timeline_value); if (err) - return err; + goto free_sync; } break; @@ -200,8 +206,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, if (XE_IOCTL_DBG(xe, IS_ERR(sync->ufence))) return PTR_ERR(sync->ufence); sync->ufence_chain_fence = dma_fence_chain_alloc(); - if (!sync->ufence_chain_fence) - return -ENOMEM; + if (!sync->ufence_chain_fence) { + err = -ENOMEM; + goto free_sync; + } sync->ufence_syncobj = ufence_syncobj; } @@ -216,6 +224,10 @@ int xe_sync_entry_parse(struct xe_device *xe, struct xe_file *xef, sync->timeline_value = sync_in.timeline_value; return 0; + +free_sync: + xe_sync_entry_cleanup(sync); + return err; } ALLOW_ERROR_INJECTION(xe_sync_entry_parse, ERRNO); diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig index 794b9778816b..78ac2ff5befd 100644 --- a/drivers/infiniband/Kconfig +++ b/drivers/infiniband/Kconfig @@ -6,6 +6,7 @@ menuconfig INFINIBAND depends on INET depends on m || IPV6 != m depends on !ALPHA + select DMA_SHARED_BUFFER select IRQ_POLL select DIMLIB help diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index b415d4aad04f..ee4a2bc68fb2 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -926,6 +926,13 @@ static int gid_table_setup_one(struct ib_device *ib_dev) if (err) return err; + /* + * Mark the device as ready for GID cache updates. This allows netdev + * event handlers to update the GID cache even before the device is + * fully registered. + */ + ib_device_enable_gid_updates(ib_dev); + rdma_roce_rescan_device(ib_dev); return err; @@ -1637,6 +1644,12 @@ void ib_cache_release_one(struct ib_device *device) void ib_cache_cleanup_one(struct ib_device *device) { + /* + * Clear the GID updates mark first to prevent event handlers from + * accessing the device while it's being torn down. + */ + ib_device_disable_gid_updates(device); + /* The cleanup function waits for all in-progress workqueue * elements and cleans up the GID cache. This function should be * called after the device was removed from the devices list and diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e54c07c74575..9480d1a51c11 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2729,6 +2729,9 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv, *to_destroy = NULL; if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return 0; + if (id_priv->restricted_node_type != RDMA_NODE_UNSPECIFIED && + id_priv->restricted_node_type != cma_dev->device->node_type) + return 0; dev_id_priv = __rdma_create_id(net, cma_listen_handler, id_priv, @@ -2736,6 +2739,7 @@ static int cma_listen_on_dev(struct rdma_id_private *id_priv, if (IS_ERR(dev_id_priv)) return PTR_ERR(dev_id_priv); + dev_id_priv->restricted_node_type = id_priv->restricted_node_type; dev_id_priv->state = RDMA_CM_ADDR_BOUND; memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); @@ -4194,7 +4198,7 @@ int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type) } mutex_lock(&lock); - if (id_priv->cma_dev) + if (READ_ONCE(id_priv->state) != RDMA_CM_IDLE) ret = -EALREADY; else id_priv->restricted_node_type = node_type; diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 05102769a918..a2c36666e6fc 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -100,6 +100,9 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter, roce_netdev_callback cb, void *cookie); +void ib_device_enable_gid_updates(struct ib_device *device); +void ib_device_disable_gid_updates(struct ib_device *device); + typedef int (*nldev_callback)(struct ib_device *device, struct sk_buff *skb, struct netlink_callback *cb, diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 1b5f1ee0a557..558b73940d66 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -93,6 +93,7 @@ static struct workqueue_struct *ib_unreg_wq; static DEFINE_XARRAY_FLAGS(devices, XA_FLAGS_ALLOC); static DECLARE_RWSEM(devices_rwsem); #define DEVICE_REGISTERED XA_MARK_1 +#define DEVICE_GID_UPDATES XA_MARK_2 static u32 highest_client_id; #define CLIENT_REGISTERED XA_MARK_1 @@ -2412,11 +2413,42 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter, unsigned long index; down_read(&devices_rwsem); - xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) + xa_for_each_marked(&devices, index, dev, DEVICE_GID_UPDATES) ib_enum_roce_netdev(dev, filter, filter_cookie, cb, cookie); up_read(&devices_rwsem); } +/** + * ib_device_enable_gid_updates - Mark device as ready for GID cache updates + * @device: Device to mark + * + * Called after GID table is allocated and initialized. After this mark is set, + * netdevice event handlers can update the device's GID cache. This allows + * events that arrive during device registration to be processed, avoiding + * stale GID entries when netdev properties change during the device + * registration process. + */ +void ib_device_enable_gid_updates(struct ib_device *device) +{ + down_write(&devices_rwsem); + xa_set_mark(&devices, device->index, DEVICE_GID_UPDATES); + up_write(&devices_rwsem); +} + +/** + * ib_device_disable_gid_updates - Clear the GID updates mark + * @device: Device to unmark + * + * Called before GID table cleanup to prevent event handlers from accessing + * the device while it's being torn down. + */ +void ib_device_disable_gid_updates(struct ib_device *device) +{ + down_write(&devices_rwsem); + xa_clear_mark(&devices, device->index, DEVICE_GID_UPDATES); + up_write(&devices_rwsem); +} + /* * ib_enum_all_devs - enumerate all ib_devices * @cb: Callback to call for each found ib_device diff --git a/drivers/infiniband/core/umem_dmabuf.c b/drivers/infiniband/core/umem_dmabuf.c index f5298c33e581..d30f24b90bca 100644 --- a/drivers/infiniband/core/umem_dmabuf.c +++ b/drivers/infiniband/core/umem_dmabuf.c @@ -218,13 +218,11 @@ ib_umem_dmabuf_get_pinned_with_dma_device(struct ib_device *device, err = ib_umem_dmabuf_map_pages(umem_dmabuf); if (err) - goto err_unpin; + goto err_release; dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv); return umem_dmabuf; -err_unpin: - dma_buf_unpin(umem_dmabuf->attach); err_release: dma_resv_unlock(umem_dmabuf->attach->dmabuf->resv); ib_umem_release(&umem_dmabuf->umem); diff --git a/drivers/infiniband/core/uverbs_std_types_dmabuf.c b/drivers/infiniband/core/uverbs_std_types_dmabuf.c index dfdfcd1d1a44..4a7f8b6f9dc8 100644 --- a/drivers/infiniband/core/uverbs_std_types_dmabuf.c +++ b/drivers/infiniband/core/uverbs_std_types_dmabuf.c @@ -10,6 +10,8 @@ #include "rdma_core.h" #include "uverbs.h" +MODULE_IMPORT_NS("DMA_BUF"); + static int uverbs_dmabuf_attach(struct dma_buf *dmabuf, struct dma_buf_attachment *attachment) { diff --git a/drivers/infiniband/hw/bng_re/bng_dev.c b/drivers/infiniband/hw/bng_re/bng_dev.c index cf3bf08e5f26..d34b5f88cd40 100644 --- a/drivers/infiniband/hw/bng_re/bng_dev.c +++ b/drivers/infiniband/hw/bng_re/bng_dev.c @@ -54,9 +54,6 @@ static void bng_re_destroy_chip_ctx(struct bng_re_dev *rdev) { struct bng_re_chip_ctx *chip_ctx; - if (!rdev->chip_ctx) - return; - kfree(rdev->dev_attr); rdev->dev_attr = NULL; @@ -124,12 +121,6 @@ static int bng_re_net_ring_free(struct bng_re_dev *rdev, struct bnge_fw_msg fw_msg = {}; int rc = -EINVAL; - if (!rdev) - return rc; - - if (!aux_dev) - return rc; - bng_re_init_hwrm_hdr((void *)&req, HWRM_RING_FREE); req.ring_type = type; req.ring_id = cpu_to_le16(fw_ring_id); @@ -150,10 +141,7 @@ static int bng_re_net_ring_alloc(struct bng_re_dev *rdev, struct hwrm_ring_alloc_input req = {}; struct hwrm_ring_alloc_output resp; struct bnge_fw_msg fw_msg = {}; - int rc = -EINVAL; - - if (!aux_dev) - return rc; + int rc; bng_re_init_hwrm_hdr((void *)&req, HWRM_RING_ALLOC); req.enables = 0; @@ -184,10 +172,7 @@ static int bng_re_stats_ctx_free(struct bng_re_dev *rdev) struct hwrm_stat_ctx_free_input req = {}; struct hwrm_stat_ctx_free_output resp = {}; struct bnge_fw_msg fw_msg = {}; - int rc = -EINVAL; - - if (!aux_dev) - return rc; + int rc; bng_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_FREE); req.stat_ctx_id = cpu_to_le32(rdev->stats_ctx.fw_id); @@ -208,13 +193,10 @@ static int bng_re_stats_ctx_alloc(struct bng_re_dev *rdev) struct hwrm_stat_ctx_alloc_output resp = {}; struct hwrm_stat_ctx_alloc_input req = {}; struct bnge_fw_msg fw_msg = {}; - int rc = -EINVAL; + int rc; stats->fw_id = BNGE_INVALID_STATS_CTX_ID; - if (!aux_dev) - return rc; - bng_re_init_hwrm_hdr((void *)&req, HWRM_STAT_CTX_ALLOC); req.update_period_ms = cpu_to_le32(1000); req.stats_dma_addr = cpu_to_le64(stats->dma_map); @@ -303,7 +285,7 @@ static int bng_re_dev_init(struct bng_re_dev *rdev) if (rc) { ibdev_err(&rdev->ibdev, "Failed to register with netedev: %#x\n", rc); - return -EINVAL; + goto reg_netdev_fail; } set_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags); @@ -312,19 +294,16 @@ static int bng_re_dev_init(struct bng_re_dev *rdev) ibdev_err(&rdev->ibdev, "RoCE requires minimum 2 MSI-X vectors, but only %d reserved\n", rdev->aux_dev->auxr_info->msix_requested); - bnge_unregister_dev(rdev->aux_dev); - clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags); - return -EINVAL; + rc = -EINVAL; + goto msix_ctx_fail; } ibdev_dbg(&rdev->ibdev, "Got %d MSI-X vectors\n", rdev->aux_dev->auxr_info->msix_requested); rc = bng_re_setup_chip_ctx(rdev); if (rc) { - bnge_unregister_dev(rdev->aux_dev); - clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags); ibdev_err(&rdev->ibdev, "Failed to get chip context\n"); - return -EINVAL; + goto msix_ctx_fail; } bng_re_query_hwrm_version(rdev); @@ -333,16 +312,14 @@ static int bng_re_dev_init(struct bng_re_dev *rdev) if (rc) { ibdev_err(&rdev->ibdev, "Failed to allocate RCFW Channel: %#x\n", rc); - goto fail; + goto alloc_fw_chl_fail; } /* Allocate nq record memory */ rdev->nqr = kzalloc_obj(*rdev->nqr); if (!rdev->nqr) { - bng_re_destroy_chip_ctx(rdev); - bnge_unregister_dev(rdev->aux_dev); - clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags); - return -ENOMEM; + rc = -ENOMEM; + goto nq_alloc_fail; } rdev->nqr->num_msix = rdev->aux_dev->auxr_info->msix_requested; @@ -411,9 +388,15 @@ disable_rcfw: free_ring: bng_re_net_ring_free(rdev, rdev->rcfw.creq.ring_id, type); free_rcfw: + kfree(rdev->nqr); +nq_alloc_fail: bng_re_free_rcfw_channel(&rdev->rcfw); -fail: - bng_re_dev_uninit(rdev); +alloc_fw_chl_fail: + bng_re_destroy_chip_ctx(rdev); +msix_ctx_fail: + bnge_unregister_dev(rdev->aux_dev); + clear_bit(BNG_RE_FLAG_NETDEV_REGISTERED, &rdev->flags); +reg_netdev_fail: return rc; } @@ -486,8 +469,7 @@ static void bng_re_remove(struct auxiliary_device *adev) rdev = dev_info->rdev; - if (rdev) - bng_re_remove_device(rdev, adev); + bng_re_remove_device(rdev, adev); kfree(dev_info); } diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c index b5b93b42e6c4..b0aa7c0238ed 100644 --- a/drivers/infiniband/hw/efa/efa_verbs.c +++ b/drivers/infiniband/hw/efa/efa_verbs.c @@ -1661,7 +1661,7 @@ static struct efa_mr *efa_alloc_mr(struct ib_pd *ibpd, int access_flags, struct efa_mr *mr; if (udata && udata->inlen && - !ib_is_udata_cleared(udata, 0, sizeof(udata->inlen))) { + !ib_is_udata_cleared(udata, 0, udata->inlen)) { ibdev_dbg(&dev->ibdev, "Incompatible ABI params, udata not cleared\n"); return ERR_PTR(-EINVAL); diff --git a/drivers/infiniband/hw/ionic/ionic_controlpath.c b/drivers/infiniband/hw/ionic/ionic_controlpath.c index 5b3f40bd98d8..4842931f5316 100644 --- a/drivers/infiniband/hw/ionic/ionic_controlpath.c +++ b/drivers/infiniband/hw/ionic/ionic_controlpath.c @@ -1218,7 +1218,7 @@ int ionic_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, rdma_udata_to_drv_context(udata, struct ionic_ctx, ibctx); struct ionic_vcq *vcq = to_ionic_vcq(ibcq); struct ionic_tbl_buf buf = {}; - struct ionic_cq_resp resp; + struct ionic_cq_resp resp = {}; struct ionic_cq_req req; int udma_idx = 0, rc; diff --git a/drivers/infiniband/hw/ionic/ionic_ibdev.c b/drivers/infiniband/hw/ionic/ionic_ibdev.c index 164046d00e5d..bd4c73e530d0 100644 --- a/drivers/infiniband/hw/ionic/ionic_ibdev.c +++ b/drivers/infiniband/hw/ionic/ionic_ibdev.c @@ -81,6 +81,8 @@ static int ionic_query_port(struct ib_device *ibdev, u32 port, return -EINVAL; ndev = ib_device_get_netdev(ibdev, port); + if (!ndev) + return -ENODEV; if (netif_running(ndev) && netif_carrier_ok(ndev)) { attr->state = IB_PORT_ACTIVE; diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index 15af53237217..7251cd7a2147 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -5212,7 +5212,7 @@ static int irdma_create_user_ah(struct ib_ah *ibah, #define IRDMA_CREATE_AH_MIN_RESP_LEN offsetofend(struct irdma_create_ah_resp, rsvd) struct irdma_ah *ah = container_of(ibah, struct irdma_ah, ibah); struct irdma_device *iwdev = to_iwdev(ibah->pd->device); - struct irdma_create_ah_resp uresp; + struct irdma_create_ah_resp uresp = {}; struct irdma_ah *parent_ah; int err; diff --git a/drivers/infiniband/hw/mthca/mthca_provider.c b/drivers/infiniband/hw/mthca/mthca_provider.c index ef0635064fba..5c182ae4fc2f 100644 --- a/drivers/infiniband/hw/mthca/mthca_provider.c +++ b/drivers/infiniband/hw/mthca/mthca_provider.c @@ -428,6 +428,8 @@ static int mthca_create_srq(struct ib_srq *ibsrq, if (context && ib_copy_to_udata(udata, &srq->srqn, sizeof(__u32))) { mthca_free_srq(to_mdev(ibsrq->device), srq); + mthca_unmap_user_db(to_mdev(ibsrq->device), &context->uar, + context->db_tab, ucmd.db_index); return -EFAULT; } @@ -436,6 +438,7 @@ static int mthca_create_srq(struct ib_srq *ibsrq, static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata) { + mthca_free_srq(to_mdev(srq->device), to_msrq(srq)); if (udata) { struct mthca_ucontext *context = rdma_udata_to_drv_context( @@ -446,8 +449,6 @@ static int mthca_destroy_srq(struct ib_srq *srq, struct ib_udata *udata) mthca_unmap_user_db(to_mdev(srq->device), &context->uar, context->db_tab, to_msrq(srq)->db_index); } - - mthca_free_srq(to_mdev(srq->device), to_msrq(srq)); return 0; } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 30783814f9d9..291d7668cc8d 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -3474,6 +3474,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, int lpi_base; int nr_lpis; int nr_ites; + int id_bits; int sz; if (!its_alloc_device_table(its, dev_id)) @@ -3485,7 +3486,10 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id, /* * Even if the device wants a single LPI, the ITT must be * sized as a power of two (and you need at least one bit...). + * Also honor the ITS's own EID limit. */ + id_bits = FIELD_GET(GITS_TYPER_IDBITS, its->typer) + 1; + nvecs = min_t(unsigned int, nvecs, BIT(id_bits)); nr_ites = max(2, nvecs); sz = nr_ites * (FIELD_GET(GITS_TYPER_ITT_ENTRY_SIZE, its->typer) + 1); sz = max(sz, ITS_ITT_ALIGN); diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c index e518e5dfede7..f3fce0b1e25d 100644 --- a/drivers/irqchip/irq-gic-v5-irs.c +++ b/drivers/irqchip/irq-gic-v5-irs.c @@ -699,7 +699,7 @@ static int __init gicv5_irs_init(struct gicv5_irs_chip_data *irs_data) */ if (list_empty(&irs_nodes)) { idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR0); - gicv5_global_data.virt_capable = !FIELD_GET(GICV5_IRS_IDR0_VIRT, idr); + gicv5_global_data.virt_capable = !!FIELD_GET(GICV5_IRS_IDR0_VIRT, idr); idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR1); irs_setup_pri_bits(idr); diff --git a/drivers/irqchip/irq-ls-extirq.c b/drivers/irqchip/irq-ls-extirq.c index a7e9c3885b09..d724fe843980 100644 --- a/drivers/irqchip/irq-ls-extirq.c +++ b/drivers/irqchip/irq-ls-extirq.c @@ -125,32 +125,45 @@ static const struct irq_domain_ops extirq_domain_ops = { static int ls_extirq_parse_map(struct ls_extirq_data *priv, struct device_node *node) { - struct of_imap_parser imap_parser; - struct of_imap_item imap_item; + const __be32 *map; + u32 mapsize; int ret; - ret = of_imap_parser_init(&imap_parser, node, &imap_item); - if (ret) - return ret; + map = of_get_property(node, "interrupt-map", &mapsize); + if (!map) + return -ENOENT; + if (mapsize % sizeof(*map)) + return -EINVAL; + mapsize /= sizeof(*map); - for_each_of_imap_item(&imap_parser, &imap_item) { + while (mapsize) { struct device_node *ipar; - u32 hwirq; - int i; + u32 hwirq, intsize, j; - hwirq = imap_item.child_imap[0]; - if (hwirq >= MAXIRQ) { - of_node_put(imap_item.parent_args.np); + if (mapsize < 3) + return -EINVAL; + hwirq = be32_to_cpup(map); + if (hwirq >= MAXIRQ) return -EINVAL; - } priv->nirq = max(priv->nirq, hwirq + 1); - ipar = of_node_get(imap_item.parent_args.np); - priv->map[hwirq].fwnode = of_fwnode_handle(ipar); + ipar = of_find_node_by_phandle(be32_to_cpup(map + 2)); + map += 3; + mapsize -= 3; + if (!ipar) + return -EINVAL; + priv->map[hwirq].fwnode = &ipar->fwnode; + ret = of_property_read_u32(ipar, "#interrupt-cells", &intsize); + if (ret) + return ret; - priv->map[hwirq].param_count = imap_item.parent_args.args_count; - for (i = 0; i < priv->map[hwirq].param_count; i++) - priv->map[hwirq].param[i] = imap_item.parent_args.args[i]; + if (intsize > mapsize) + return -EINVAL; + + priv->map[hwirq].param_count = intsize; + for (j = 0; j < intsize; ++j) + priv->map[hwirq].param[j] = be32_to_cpup(map++); + mapsize -= intsize; } return 0; } @@ -177,8 +190,10 @@ static int ls_extirq_probe(struct platform_device *pdev) return dev_err_probe(dev, -ENOMEM, "Failed to allocate memory\n"); priv->intpcr = devm_of_iomap(dev, node, 0, NULL); - if (!priv->intpcr) - return dev_err_probe(dev, -ENOMEM, "Cannot ioremap OF node %pOF\n", node); + if (IS_ERR(priv->intpcr)) { + return dev_err_probe(dev, PTR_ERR(priv->intpcr), + "Cannot ioremap OF node %pOF\n", node); + } ret = ls_extirq_parse_map(priv, node); if (ret) diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 09e640430208..8e210cb451be 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -136,7 +136,7 @@ static void icu_unmask_irq(struct irq_data *d) } } -struct irq_chip icu_irq_chip = { +static const struct irq_chip icu_irq_chip = { .name = "icu_irq", .irq_mask = icu_mask_irq, .irq_mask_ack = icu_mask_ack_irq, diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c index 686d39254426..5b0dac104814 100644 --- a/drivers/irqchip/irq-sifive-plic.c +++ b/drivers/irqchip/irq-sifive-plic.c @@ -172,8 +172,13 @@ static void plic_irq_disable(struct irq_data *d) static void plic_irq_eoi(struct irq_data *d) { struct plic_handler *handler = this_cpu_ptr(&plic_handlers); + u32 __iomem *reg; + bool enabled; + + reg = handler->enable_base + (d->hwirq / 32) * sizeof(u32); + enabled = readl(reg) & BIT(d->hwirq % 32); - if (unlikely(irqd_irq_disabled(d))) { + if (unlikely(!enabled)) { plic_toggle(handler, d->hwirq, 1); writel(d->hwirq, handler->hart_base + CONTEXT_CLAIM); plic_toggle(handler, d->hwirq, 0); diff --git a/drivers/media/dvb-core/dvb_net.c b/drivers/media/dvb-core/dvb_net.c index 8bb8dd34c223..a2159b2bc176 100644 --- a/drivers/media/dvb-core/dvb_net.c +++ b/drivers/media/dvb-core/dvb_net.c @@ -228,6 +228,9 @@ static int handle_one_ule_extension( struct dvb_net_priv *p ) unsigned char hlen = (p->ule_sndu_type & 0x0700) >> 8; unsigned char htype = p->ule_sndu_type & 0x00FF; + if (htype >= ARRAY_SIZE(ule_mandatory_ext_handlers)) + return -1; + /* Discriminate mandatory and optional extension headers. */ if (hlen == 0) { /* Mandatory extension header */ diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c index 4e3423a19bdf..ac069d0c42b2 100644 --- a/drivers/mmc/host/dw_mmc-rockchip.c +++ b/drivers/mmc/host/dw_mmc-rockchip.c @@ -36,6 +36,8 @@ struct dw_mci_rockchip_priv_data { int default_sample_phase; int num_phases; bool internal_phase; + int sample_phase; + int drv_phase; }; /* @@ -573,9 +575,43 @@ static void dw_mci_rockchip_remove(struct platform_device *pdev) dw_mci_pltfm_remove(pdev); } +static int dw_mci_rockchip_runtime_suspend(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct dw_mci *host = platform_get_drvdata(pdev); + struct dw_mci_rockchip_priv_data *priv = host->priv; + + if (priv->internal_phase) { + priv->sample_phase = rockchip_mmc_get_phase(host, true); + priv->drv_phase = rockchip_mmc_get_phase(host, false); + } + + return dw_mci_runtime_suspend(dev); +} + +static int dw_mci_rockchip_runtime_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct dw_mci *host = platform_get_drvdata(pdev); + struct dw_mci_rockchip_priv_data *priv = host->priv; + int ret; + + ret = dw_mci_runtime_resume(dev); + if (ret) + return ret; + + if (priv->internal_phase) { + rockchip_mmc_set_phase(host, true, priv->sample_phase); + rockchip_mmc_set_phase(host, false, priv->drv_phase); + mci_writel(host, MISC_CON, MEM_CLK_AUTOGATE_ENABLE); + } + + return ret; +} + static const struct dev_pm_ops dw_mci_rockchip_dev_pm_ops = { SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume) - RUNTIME_PM_OPS(dw_mci_runtime_suspend, dw_mci_runtime_resume, NULL) + RUNTIME_PM_OPS(dw_mci_rockchip_runtime_suspend, dw_mci_rockchip_runtime_resume, NULL) }; static struct platform_driver dw_mci_rockchip_pltfm_driver = { diff --git a/drivers/mmc/host/mmci_qcom_dml.c b/drivers/mmc/host/mmci_qcom_dml.c index 3da6112fbe39..67371389cc33 100644 --- a/drivers/mmc/host/mmci_qcom_dml.c +++ b/drivers/mmc/host/mmci_qcom_dml.c @@ -109,6 +109,7 @@ static int of_get_dml_pipe_index(struct device_node *np, const char *name) &dma_spec)) return -ENODEV; + of_node_put(dma_spec.np); if (dma_spec.args_count) return dma_spec.args[0]; diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c index c9442499876c..57e45951644e 100644 --- a/drivers/mmc/host/sdhci-brcmstb.c +++ b/drivers/mmc/host/sdhci-brcmstb.c @@ -116,7 +116,7 @@ static void sdhci_brcmstb_restore_regs(struct mmc_host *mmc, enum cfg_core_ver v writel(sr->boot_main_ctl, priv->boot_regs + SDIO_BOOT_MAIN_CTL); if (ver == SDIO_CFG_CORE_V1) { - writel(sr->sd_pin_sel, cr + SDIO_CFG_SD_PIN_SEL); + writel(sr->sd_pin_sel, cr + SDIO_CFG_V1_SD_PIN_SEL); return; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9af7dacae9b3..0ccf928eecde 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -324,7 +324,7 @@ static bool bond_sk_check(struct bonding *bond) } } -bool bond_xdp_check(struct bonding *bond, int mode) +bool __bond_xdp_check(int mode, int xmit_policy) { switch (mode) { case BOND_MODE_ROUNDROBIN: @@ -335,7 +335,7 @@ bool bond_xdp_check(struct bonding *bond, int mode) /* vlan+srcmac is not supported with XDP as in most cases the 802.1q * payload is not in the packet due to hardware offload. */ - if (bond->params.xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) + if (xmit_policy != BOND_XMIT_POLICY_VLAN_SRCMAC) return true; fallthrough; default: @@ -343,6 +343,11 @@ bool bond_xdp_check(struct bonding *bond, int mode) } } +bool bond_xdp_check(struct bonding *bond, int mode) +{ + return __bond_xdp_check(mode, bond->params.xmit_policy); +} + /*---------------------------------- VLAN -----------------------------------*/ /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid, diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index dcee384c2f06..7380cc4ee75a 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1575,6 +1575,8 @@ static int bond_option_fail_over_mac_set(struct bonding *bond, static int bond_option_xmit_hash_policy_set(struct bonding *bond, const struct bond_opt_value *newval) { + if (bond->xdp_prog && !__bond_xdp_check(BOND_MODE(bond), newval->value)) + return -EOPNOTSUPP; netdev_dbg(bond->dev, "Setting xmit hash policy to %s (%llu)\n", newval->string, newval->value); bond->params.xmit_policy = newval->value; diff --git a/drivers/net/can/dummy_can.c b/drivers/net/can/dummy_can.c index 41953655e3d3..cd23de488edc 100644 --- a/drivers/net/can/dummy_can.c +++ b/drivers/net/can/dummy_can.c @@ -241,6 +241,7 @@ static int __init dummy_can_init(void) dev->netdev_ops = &dummy_can_netdev_ops; dev->ethtool_ops = &dummy_can_ethtool_ops; + dev->flags |= IFF_ECHO; /* enable echo handling */ priv = netdev_priv(dev); priv->can.bittiming_const = &dummy_can_bittiming_const; priv->can.bitrate_max = 20 * MEGA /* BPS */; diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index fa97adf25b73..bb7782582f40 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1214,6 +1214,7 @@ static int mcp251x_open(struct net_device *net) { struct mcp251x_priv *priv = netdev_priv(net); struct spi_device *spi = priv->spi; + bool release_irq = false; unsigned long flags = 0; int ret; @@ -1257,12 +1258,24 @@ static int mcp251x_open(struct net_device *net) return 0; out_free_irq: - free_irq(spi->irq, priv); + /* The IRQ handler might be running, and if so it will be waiting + * for the lock. But free_irq() must wait for the handler to finish + * so calling it here would deadlock. + * + * Setting priv->force_quit will let the handler exit right away + * without any access to the hardware. This make it safe to call + * free_irq() after the lock is released. + */ + priv->force_quit = 1; + release_irq = true; + mcp251x_hw_sleep(spi); out_close: mcp251x_power_enable(priv->transceiver, 0); close_candev(net); mutex_unlock(&priv->mcp_lock); + if (release_irq) + free_irq(spi->irq, priv); return ret; } diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 4c219a5b139b..9b25dda7c183 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -445,6 +445,11 @@ static void ems_usb_read_bulk_callback(struct urb *urb) start = CPC_HEADER_SIZE; while (msg_count) { + if (start + CPC_MSG_HEADER_LEN > urb->actual_length) { + netdev_err(netdev, "format error\n"); + break; + } + msg = (struct ems_cpc_msg *)&ibuf[start]; switch (msg->type) { @@ -474,7 +479,7 @@ static void ems_usb_read_bulk_callback(struct urb *urb) start += CPC_MSG_HEADER_LEN + msg->length; msg_count--; - if (start > urb->transfer_buffer_length) { + if (start > urb->actual_length) { netdev_err(netdev, "format error\n"); break; } diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 2892a68f510a..d257440fa01f 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -272,6 +272,9 @@ struct esd_usb { struct usb_anchor rx_submitted; + unsigned int rx_pipe; + unsigned int tx_pipe; + int net_count; u32 version; int rxinitdone; @@ -537,7 +540,7 @@ static void esd_usb_read_bulk_callback(struct urb *urb) } resubmit_urb: - usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 1), + usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe, urb->transfer_buffer, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); @@ -626,9 +629,7 @@ static int esd_usb_send_msg(struct esd_usb *dev, union esd_usb_msg *msg) { int actual_length; - return usb_bulk_msg(dev->udev, - usb_sndbulkpipe(dev->udev, 2), - msg, + return usb_bulk_msg(dev->udev, dev->tx_pipe, msg, msg->hdr.len * sizeof(u32), /* convert to # of bytes */ &actual_length, 1000); @@ -639,12 +640,8 @@ static int esd_usb_wait_msg(struct esd_usb *dev, { int actual_length; - return usb_bulk_msg(dev->udev, - usb_rcvbulkpipe(dev->udev, 1), - msg, - sizeof(*msg), - &actual_length, - 1000); + return usb_bulk_msg(dev->udev, dev->rx_pipe, msg, + sizeof(*msg), &actual_length, 1000); } static int esd_usb_setup_rx_urbs(struct esd_usb *dev) @@ -677,8 +674,7 @@ static int esd_usb_setup_rx_urbs(struct esd_usb *dev) urb->transfer_dma = buf_dma; - usb_fill_bulk_urb(urb, dev->udev, - usb_rcvbulkpipe(dev->udev, 1), + usb_fill_bulk_urb(urb, dev->udev, dev->rx_pipe, buf, ESD_USB_RX_BUFFER_SIZE, esd_usb_read_bulk_callback, dev); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; @@ -903,7 +899,7 @@ static netdev_tx_t esd_usb_start_xmit(struct sk_buff *skb, /* hnd must not be 0 - MSB is stripped in txdone handling */ msg->tx.hnd = BIT(31) | i; /* returned in TX done message */ - usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), buf, + usb_fill_bulk_urb(urb, dev->udev, dev->tx_pipe, buf, msg->hdr.len * sizeof(u32), /* convert to # of bytes */ esd_usb_write_bulk_callback, context); @@ -1298,10 +1294,16 @@ done: static int esd_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_endpoint_descriptor *ep_in, *ep_out; struct esd_usb *dev; union esd_usb_msg *msg; int i, err; + err = usb_find_common_endpoints(intf->cur_altsetting, &ep_in, &ep_out, + NULL, NULL); + if (err) + return err; + dev = kzalloc_obj(*dev); if (!dev) { err = -ENOMEM; @@ -1309,6 +1311,8 @@ static int esd_usb_probe(struct usb_interface *intf, } dev->udev = interface_to_usbdev(intf); + dev->rx_pipe = usb_rcvbulkpipe(dev->udev, ep_in->bEndpointAddress); + dev->tx_pipe = usb_sndbulkpipe(dev->udev, ep_out->bEndpointAddress); init_usb_anchor(&dev->rx_submitted); diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 2d248deb69dc..b259f6109808 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1461,12 +1461,18 @@ static void es58x_read_bulk_callback(struct urb *urb) } resubmit_urb: + usb_anchor_urb(urb, &es58x_dev->rx_urbs); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + + usb_unanchor_urb(urb); + if (ret == -ENODEV) { for (i = 0; i < es58x_dev->num_can_ch; i++) if (es58x_dev->netdev[i]) netif_device_detach(es58x_dev->netdev[i]); - } else if (ret) + } else dev_err_ratelimited(dev, "Failed resubmitting read bulk urb: %pe\n", ERR_PTR(ret)); diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c index 76578063ac82..f12318268e46 100644 --- a/drivers/net/can/usb/f81604.c +++ b/drivers/net/can/usb/f81604.c @@ -413,6 +413,7 @@ static void f81604_read_bulk_callback(struct urb *urb) { struct f81604_can_frame *frame = urb->transfer_buffer; struct net_device *netdev = urb->context; + struct f81604_port_priv *priv = netdev_priv(netdev); int ret; if (!netif_device_present(netdev)) @@ -445,10 +446,15 @@ static void f81604_read_bulk_callback(struct urb *urb) f81604_process_rx_packet(netdev, frame); resubmit_urb: + usb_anchor_urb(urb, &priv->urbs_anchor); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + usb_unanchor_urb(urb); + if (ret == -ENODEV) netif_device_detach(netdev); - else if (ret) + else netdev_err(netdev, "%s: failed to resubmit read bulk urb: %pe\n", __func__, ERR_PTR(ret)); @@ -620,6 +626,12 @@ static void f81604_read_int_callback(struct urb *urb) netdev_info(netdev, "%s: Int URB aborted: %pe\n", __func__, ERR_PTR(urb->status)); + if (urb->actual_length < sizeof(*data)) { + netdev_warn(netdev, "%s: short int URB: %u < %zu\n", + __func__, urb->actual_length, sizeof(*data)); + goto resubmit_urb; + } + switch (urb->status) { case 0: /* success */ break; @@ -646,10 +658,15 @@ static void f81604_read_int_callback(struct urb *urb) f81604_handle_tx(priv, data); resubmit_urb: + usb_anchor_urb(urb, &priv->urbs_anchor); ret = usb_submit_urb(urb, GFP_ATOMIC); + if (!ret) + return; + usb_unanchor_urb(urb); + if (ret == -ENODEV) netif_device_detach(netdev); - else if (ret) + else netdev_err(netdev, "%s: failed to resubmit int urb: %pe\n", __func__, ERR_PTR(ret)); } @@ -874,9 +891,27 @@ static void f81604_write_bulk_callback(struct urb *urb) if (!netif_device_present(netdev)) return; - if (urb->status) - netdev_info(netdev, "%s: Tx URB error: %pe\n", __func__, - ERR_PTR(urb->status)); + if (!urb->status) + return; + + switch (urb->status) { + case -ENOENT: + case -ECONNRESET: + case -ESHUTDOWN: + return; + default: + break; + } + + if (net_ratelimit()) + netdev_err(netdev, "%s: Tx URB error: %pe\n", __func__, + ERR_PTR(urb->status)); + + can_free_echo_skb(netdev, 0, NULL); + netdev->stats.tx_dropped++; + netdev->stats.tx_errors++; + + netif_wake_queue(netdev); } static void f81604_clear_reg_work(struct work_struct *work) diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 9d27d6f0c0b5..ec9a7cbbbc69 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -772,9 +772,8 @@ device_detach: } } -static int gs_usb_set_bittiming(struct net_device *netdev) +static int gs_usb_set_bittiming(struct gs_can *dev) { - struct gs_can *dev = netdev_priv(netdev); struct can_bittiming *bt = &dev->can.bittiming; struct gs_device_bittiming dbt = { .prop_seg = cpu_to_le32(bt->prop_seg), @@ -791,9 +790,8 @@ static int gs_usb_set_bittiming(struct net_device *netdev) GFP_KERNEL); } -static int gs_usb_set_data_bittiming(struct net_device *netdev) +static int gs_usb_set_data_bittiming(struct gs_can *dev) { - struct gs_can *dev = netdev_priv(netdev); struct can_bittiming *bt = &dev->can.fd.data_bittiming; struct gs_device_bittiming dbt = { .prop_seg = cpu_to_le32(bt->prop_seg), @@ -1057,6 +1055,20 @@ static int gs_can_open(struct net_device *netdev) if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) flags |= GS_CAN_MODE_HW_TIMESTAMP; + rc = gs_usb_set_bittiming(dev); + if (rc) { + netdev_err(netdev, "failed to set bittiming: %pe\n", ERR_PTR(rc)); + goto out_usb_kill_anchored_urbs; + } + + if (ctrlmode & CAN_CTRLMODE_FD) { + rc = gs_usb_set_data_bittiming(dev); + if (rc) { + netdev_err(netdev, "failed to set data bittiming: %pe\n", ERR_PTR(rc)); + goto out_usb_kill_anchored_urbs; + } + } + /* finally start device */ dev->can.state = CAN_STATE_ERROR_ACTIVE; dm.flags = cpu_to_le32(flags); @@ -1370,7 +1382,6 @@ static struct gs_can *gs_make_candev(unsigned int channel, dev->can.state = CAN_STATE_STOPPED; dev->can.clock.freq = le32_to_cpu(bt_const.fclk_can); dev->can.bittiming_const = &dev->bt_const; - dev->can.do_set_bittiming = gs_usb_set_bittiming; dev->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC; @@ -1394,7 +1405,6 @@ static struct gs_can *gs_make_candev(unsigned int channel, * GS_CAN_FEATURE_BT_CONST_EXT is set. */ dev->can.fd.data_bittiming_const = &dev->bt_const; - dev->can.fd.do_set_data_bittiming = gs_usb_set_data_bittiming; } if (feature & GS_CAN_FEATURE_TERMINATION) { diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index c79508b1c43e..0ea0ac75e42f 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -748,7 +748,7 @@ static void ucan_read_bulk_callback(struct urb *urb) len = le16_to_cpu(m->len); /* check sanity (length of content) */ - if (urb->actual_length - pos < len) { + if ((len == 0) || (urb->actual_length - pos < len)) { netdev_warn(up->netdev, "invalid message (short; no data; l:%d)\n", urb->actual_length); diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index c575e164368c..f938a3f701cc 100644 --- a/drivers/net/dsa/realtek/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -769,7 +769,7 @@ static int rtl8365mb_phy_ocp_write(struct realtek_priv *priv, int phy, out: rtl83xx_unlock(priv); - return 0; + return ret; } static int rtl8365mb_phy_read(struct realtek_priv *priv, int phy, int regnum) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 57cd8d2e1ad7..c17900a49595 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -431,7 +431,7 @@ #define MAC_SSIR_SSINC_INDEX 16 #define MAC_SSIR_SSINC_WIDTH 8 #define MAC_TCR_SS_INDEX 29 -#define MAC_TCR_SS_WIDTH 2 +#define MAC_TCR_SS_WIDTH 3 #define MAC_TCR_TE_INDEX 0 #define MAC_TCR_TE_WIDTH 1 #define MAC_TCR_VNE_INDEX 24 diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 62bb4b8a68e1..8b79d88480db 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1120,7 +1120,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned long flags; DBGPR("-->xgbe_powerdown\n"); @@ -1131,8 +1130,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) return -EINVAL; } - spin_lock_irqsave(&pdata->lock, flags); - if (caller == XGMAC_DRIVER_CONTEXT) netif_device_detach(netdev); @@ -1148,8 +1145,6 @@ int xgbe_powerdown(struct net_device *netdev, unsigned int caller) pdata->power_down = 1; - spin_unlock_irqrestore(&pdata->lock, flags); - DBGPR("<--xgbe_powerdown\n"); return 0; @@ -1159,7 +1154,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned long flags; DBGPR("-->xgbe_powerup\n"); @@ -1170,8 +1164,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) return -EINVAL; } - spin_lock_irqsave(&pdata->lock, flags); - pdata->power_down = 0; xgbe_napi_enable(pdata, 0); @@ -1186,8 +1178,6 @@ int xgbe_powerup(struct net_device *netdev, unsigned int caller) xgbe_start_timers(pdata); - spin_unlock_irqrestore(&pdata->lock, flags); - DBGPR("<--xgbe_powerup\n"); return 0; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index d1f0419edb23..7d45ea22a02e 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -76,7 +76,6 @@ struct xgbe_prv_data *xgbe_alloc_pdata(struct device *dev) pdata->netdev = netdev; pdata->dev = dev; - spin_lock_init(&pdata->lock); spin_lock_init(&pdata->xpcs_lock); mutex_init(&pdata->rss_mutex); spin_lock_init(&pdata->tstamp_lock); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index f1b2954017e6..4333d269ee84 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1027,9 +1027,6 @@ struct xgbe_prv_data { unsigned int pp3; unsigned int pp4; - /* Overall device lock */ - spinlock_t lock; - /* XPCS indirect addressing lock */ spinlock_t xpcs_lock; unsigned int xpcs_window_def_reg; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c index fc0e0f36186e..52c1cb9cb7e0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c @@ -1533,7 +1533,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) if_id = (status & 0xFFFF0000) >> 16; if (if_id >= ethsw->sw_attr.num_ifs) { dev_err(dev, "Invalid if_id %d in IRQ status\n", if_id); - goto out; + goto out_clear; } port_priv = ethsw->ports[if_id]; @@ -1553,6 +1553,7 @@ static irqreturn_t dpaa2_switch_irq0_handler_thread(int irq_num, void *arg) dpaa2_switch_port_connect_mac(port_priv); } +out_clear: err = dpsw_clear_irq_status(ethsw->mc_io, 0, ethsw->dpsw_handle, DPSW_IRQ_INDEX_IF, status); if (err) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 70768392912c..a146ceaf2ed6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -3467,7 +3467,7 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i, priv->rx_ring[i] = bdr; err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0, - ENETC_RXB_DMA_SIZE_XDP); + ENETC_RXB_TRUESIZE); if (err) goto free_vector; diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index ba331899d186..d4a1041e456d 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -33,6 +33,7 @@ /* Extended Device Control */ #define E1000_CTRL_EXT_LPCD 0x00000004 /* LCD Power Cycle Done */ +#define E1000_CTRL_EXT_DPG_EN 0x00000008 /* Dynamic Power Gating Enable */ #define E1000_CTRL_EXT_SDP3_DATA 0x00000080 /* Value of SW Definable Pin 3 */ #define E1000_CTRL_EXT_FORCE_SMBUS 0x00000800 /* Force SMBus mode */ #define E1000_CTRL_EXT_EE_RST 0x00002000 /* Reinitialize from EEPROM */ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index aa08f397988e..63ebe00376f5 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -117,7 +117,8 @@ enum e1000_boards { board_pch_cnp, board_pch_tgp, board_pch_adp, - board_pch_mtp + board_pch_mtp, + board_pch_ptp }; struct e1000_ps_page { @@ -527,6 +528,7 @@ extern const struct e1000_info e1000_pch_cnp_info; extern const struct e1000_info e1000_pch_tgp_info; extern const struct e1000_info e1000_pch_adp_info; extern const struct e1000_info e1000_pch_mtp_info; +extern const struct e1000_info e1000_pch_ptp_info; extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index fc8ed38aa095..c7ac599e5a7a 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -118,8 +118,6 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_ARL_I219_V24 0x57A1 #define E1000_DEV_ID_PCH_PTP_I219_LM25 0x57B3 #define E1000_DEV_ID_PCH_PTP_I219_V25 0x57B4 -#define E1000_DEV_ID_PCH_PTP_I219_LM26 0x57B5 -#define E1000_DEV_ID_PCH_PTP_I219_V26 0x57B6 #define E1000_DEV_ID_PCH_PTP_I219_LM27 0x57B7 #define E1000_DEV_ID_PCH_PTP_I219_V27 0x57B8 #define E1000_DEV_ID_PCH_NVL_I219_LM29 0x57B9 diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 0ff8688ac3b8..dea208db1be5 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -528,7 +528,7 @@ static s32 e1000_init_phy_params_pchlan(struct e1000_hw *hw) phy->id = e1000_phy_unknown; - if (hw->mac.type == e1000_pch_mtp) { + if (hw->mac.type == e1000_pch_mtp || hw->mac.type == e1000_pch_ptp) { phy->retry_count = 2; e1000e_enable_phy_retry(hw); } @@ -4932,6 +4932,15 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw) reg |= E1000_KABGTXD_BGSQLBIAS; ew32(KABGTXD, reg); + /* The hardware reset value of the DPG_EN bit is 1. + * Clear DPG_EN to prevent unexpected autonomous power gating. + */ + if (hw->mac.type >= e1000_pch_ptp) { + reg = er32(CTRL_EXT); + reg &= ~E1000_CTRL_EXT_DPG_EN; + ew32(CTRL_EXT, reg); + } + return 0; } @@ -6208,3 +6217,23 @@ const struct e1000_info e1000_pch_mtp_info = { .phy_ops = &ich8_phy_ops, .nvm_ops = &spt_nvm_ops, }; + +const struct e1000_info e1000_pch_ptp_info = { + .mac = e1000_pch_ptp, + .flags = FLAG_IS_ICH + | FLAG_HAS_WOL + | FLAG_HAS_HW_TIMESTAMP + | FLAG_HAS_CTRLEXT_ON_LOAD + | FLAG_HAS_AMT + | FLAG_HAS_FLASH + | FLAG_HAS_JUMBO_FRAMES + | FLAG_APME_IN_WUC, + .flags2 = FLAG2_HAS_PHY_STATS + | FLAG2_HAS_EEE, + .pba = 26, + .max_hw_frame_size = 9022, + .get_variants = e1000_get_variants_ich8lan, + .mac_ops = &ich8_mac_ops, + .phy_ops = &ich8_phy_ops, + .nvm_ops = &spt_nvm_ops, +}; diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index fd4b117ed20f..35dab1e3132f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -55,6 +55,7 @@ static const struct e1000_info *e1000_info_tbl[] = { [board_pch_tgp] = &e1000_pch_tgp_info, [board_pch_adp] = &e1000_pch_adp_info, [board_pch_mtp] = &e1000_pch_mtp_info, + [board_pch_ptp] = &e1000_pch_ptp_info, }; struct e1000_reg_info { @@ -7922,14 +7923,12 @@ static const struct pci_device_id e1000_pci_tbl[] = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_LM24), board_pch_mtp }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ARL_I219_V24), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM26), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V26), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_mtp }, - { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_mtp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM25), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V25), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_LM27), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_PTP_I219_V27), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_LM29), board_pch_ptp }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_NVL_I219_V29), board_pch_ptp }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 7b9e147d7365..926d001b2150 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -3569,6 +3569,7 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) u16 pf_q = vsi->base_queue + ring->queue_index; struct i40e_hw *hw = &vsi->back->hw; struct i40e_hmc_obj_rxq rx_ctx; + u32 xdp_frame_sz; int err = 0; bool ok; @@ -3578,49 +3579,47 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) memset(&rx_ctx, 0, sizeof(rx_ctx)); ring->rx_buf_len = vsi->rx_buf_len; + xdp_frame_sz = i40e_rx_pg_size(ring) / 2; /* XDP RX-queue info only needed for RX rings exposed to XDP */ if (ring->vsi->type != I40E_VSI_MAIN) goto skip; - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->queue_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - return err; - } - ring->xsk_pool = i40e_xsk_pool(ring); if (ring->xsk_pool) { - xdp_rxq_info_unreg(&ring->xdp_rxq); + xdp_frame_sz = xsk_pool_get_rx_frag_step(ring->xsk_pool); ring->rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->queue_index, ring->q_vector->napi.napi_id, - ring->rx_buf_len); + xdp_frame_sz); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_XSK_BUFF_POOL, NULL); if (err) - return err; + goto unreg_xdp; dev_info(&vsi->back->pdev->dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->queue_index); } else { + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->queue_index, + ring->q_vector->napi.napi_id, + xdp_frame_sz); + if (err) + return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err) - return err; + goto unreg_xdp; } skip: - xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq); + xdp_init_buff(&ring->xdp, xdp_frame_sz, &ring->xdp_rxq); rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); @@ -3654,7 +3653,8 @@ skip: dev_info(&vsi->back->pdev->dev, "Failed to clear LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n", ring->queue_index, pf_q, err); - return -ENOMEM; + err = -ENOMEM; + goto unreg_xdp; } /* set the context in the HMC */ @@ -3663,7 +3663,8 @@ skip: dev_info(&vsi->back->pdev->dev, "Failed to set LAN Rx queue context on Rx ring %d (pf_q %d), error: %d\n", ring->queue_index, pf_q, err); - return -ENOMEM; + err = -ENOMEM; + goto unreg_xdp; } /* configure Rx buffer alignment */ @@ -3671,7 +3672,8 @@ skip: if (I40E_2K_TOO_SMALL_WITH_PADDING) { dev_info(&vsi->back->pdev->dev, "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n"); - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + goto unreg_xdp; } clear_ring_build_skb_enabled(ring); } else { @@ -3701,6 +3703,11 @@ skip: } return 0; +unreg_xdp: + if (ring->vsi->type == I40E_VSI_MAIN) + xdp_rxq_info_unreg(&ring->xdp_rxq); + + return err; } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index 759f3d1c4c8f..dde0ccd789ed 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -88,7 +88,7 @@ TRACE_EVENT(i40e_napi_poll, __entry->rx_clean_complete = rx_clean_complete; __entry->tx_clean_complete = tx_clean_complete; __entry->irq_num = q->irq_num; - __entry->curr_cpu = get_cpu(); + __entry->curr_cpu = smp_processor_id(); __assign_str(qname); __assign_str(dev_name); __assign_bitmask(irq_affinity, cpumask_bits(&q->affinity_mask), diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 34db7d8866b0..894f2d06d39d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1470,6 +1470,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) return; + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + if (rx_ring->xsk_pool) { i40e_xsk_clean_rx_ring(rx_ring); goto skip_free; @@ -1527,8 +1530,6 @@ skip_free: void i40e_free_rx_resources(struct i40e_ring *rx_ring) { i40e_clean_rx_ring(rx_ring); - if (rx_ring->vsi->type == I40E_VSI_MAIN) - xdp_rxq_info_unreg(&rx_ring->xdp_rxq); rx_ring->xdp_prog = NULL; kfree(rx_ring->rx_bi); rx_ring->rx_bi = NULL; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index bceaf4b1b85d..86c1964f42e1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2793,7 +2793,22 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) netdev->watchdog_timeo = 5 * HZ; netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = LIBIE_MAX_MTU; + + /* PF/VF API: vf_res->max_mtu is max frame size (not MTU). + * Convert to MTU. + */ + if (!adapter->vf_res->max_mtu) { + netdev->max_mtu = LIBIE_MAX_MTU; + } else if (adapter->vf_res->max_mtu < LIBETH_RX_LL_LEN + ETH_MIN_MTU || + adapter->vf_res->max_mtu > + LIBETH_RX_LL_LEN + LIBIE_MAX_MTU) { + netdev_warn_once(adapter->netdev, + "invalid max frame size %d from PF, using default MTU %d", + adapter->vf_res->max_mtu, LIBIE_MAX_MTU); + netdev->max_mtu = LIBIE_MAX_MTU; + } else { + netdev->max_mtu = adapter->vf_res->max_mtu - LIBETH_RX_LL_LEN; + } if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index def7efa15447..2b2b22af42be 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -987,6 +987,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); int ice_plug_aux_dev(struct ice_pf *pf); void ice_unplug_aux_dev(struct ice_pf *pf); +void ice_rdma_finalize_setup(struct ice_pf *pf); int ice_init_rdma(struct ice_pf *pf); void ice_deinit_rdma(struct ice_pf *pf); bool ice_is_wol_supported(struct ice_hw *hw); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index eb77dfa934aa..1667f686ff75 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -124,6 +124,8 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx) if (vsi->type == ICE_VSI_VF) { ice_calc_vf_reg_idx(vsi->vf, q_vector); goto out; + } else if (vsi->type == ICE_VSI_LB) { + goto skip_alloc; } else if (vsi->type == ICE_VSI_CTRL && vsi->vf) { struct ice_vsi *ctrl_vsi = ice_get_vf_ctrl_vsi(pf, vsi); @@ -659,33 +661,22 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); u32 num_bufs = ICE_DESC_UNUSED(ring); - u32 rx_buf_len; int err; - if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) { - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - return err; - } - + if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF || + ring->vsi->type == ICE_VSI_LB) { ice_rx_xsk_pool(ring); err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool); if (err) return err; if (ring->xsk_pool) { - xdp_rxq_info_unreg(&ring->xdp_rxq); - - rx_buf_len = - xsk_pool_get_rx_frame_size(ring->xsk_pool); + u32 frag_size = + xsk_pool_get_rx_frag_step(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id, - rx_buf_len); + frag_size); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -702,14 +693,13 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (err) return err; - if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { - err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index, - ring->q_vector->napi.napi_id, - ring->rx_buf_len); - if (err) - goto err_destroy_fq; - } + err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, + ring->q_index, + ring->q_vector->napi.napi_id, + ring->truesize); + if (err) + goto err_destroy_fq; + xdp_rxq_info_attach_page_pool(&ring->xdp_rxq, ring->pp); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 6cd63190f55d..ce11fea122d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1816,6 +1816,7 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode) case ice_aqc_opc_lldp_stop: case ice_aqc_opc_lldp_start: case ice_aqc_opc_lldp_filter_ctrl: + case ice_aqc_opc_sff_eeprom: return true; } @@ -1841,6 +1842,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, { struct libie_aq_desc desc_cpy; bool is_cmd_for_retry; + u8 *buf_cpy = NULL; u8 idx = 0; u16 opcode; int status; @@ -1850,8 +1852,11 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, memset(&desc_cpy, 0, sizeof(desc_cpy)); if (is_cmd_for_retry) { - /* All retryable cmds are direct, without buf. */ - WARN_ON(buf); + if (buf) { + buf_cpy = kmemdup(buf, buf_size, GFP_KERNEL); + if (!buf_cpy) + return -ENOMEM; + } memcpy(&desc_cpy, desc, sizeof(desc_cpy)); } @@ -1863,12 +1868,14 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY) break; + if (buf_cpy) + memcpy(buf, buf_cpy, buf_size); memcpy(desc, &desc_cpy, sizeof(desc_cpy)); - msleep(ICE_SQ_SEND_DELAY_TIME_MS); } while (++idx < ICE_SQ_SEND_MAX_EXECUTE); + kfree(buf_cpy); return status; } @@ -6391,7 +6398,7 @@ int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add) struct ice_aqc_lldp_filter_ctrl *cmd; struct libie_aq_desc desc; - if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw)) + if (!ice_fw_supports_lldp_fltr_ctrl(hw)) return -EOPNOTSUPP; cmd = libie_aq_raw(&desc); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 0ea64b330614..301947d53ede 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1289,6 +1289,10 @@ static u64 ice_loopback_test(struct net_device *netdev) test_vsi->netdev = netdev; tx_ring = test_vsi->tx_rings[0]; rx_ring = test_vsi->rx_rings[0]; + /* Dummy q_vector and napi. Fill the minimum required for + * ice_rxq_pp_create(). + */ + rx_ring->q_vector->napi.dev = netdev; if (ice_lbtest_prepare_rings(test_vsi)) { ret = 2; @@ -3328,7 +3332,7 @@ process_rx: rx_rings = kzalloc_objs(*rx_rings, vsi->num_rxq); if (!rx_rings) { err = -ENOMEM; - goto done; + goto free_xdp; } ice_for_each_rxq(vsi, i) { @@ -3338,6 +3342,7 @@ process_rx: rx_rings[i].cached_phctime = pf->ptp.cached_phc_time; rx_rings[i].desc = NULL; rx_rings[i].xdp_buf = NULL; + rx_rings[i].xdp_rxq = (struct xdp_rxq_info){ }; /* this is to allow wr32 to have something to write to * during early allocation of Rx buffers @@ -3355,7 +3360,7 @@ rx_unwind: } kfree(rx_rings); err = -ENOMEM; - goto free_tx; + goto free_xdp; } } @@ -3407,6 +3412,13 @@ process_link: } goto done; +free_xdp: + if (xdp_rings) { + ice_for_each_xdp_txq(vsi, i) + ice_free_tx_ring(&xdp_rings[i]); + kfree(xdp_rings); + } + free_tx: /* error cleanup if the Rx allocations failed after getting Tx */ if (tx_rings) { @@ -4505,7 +4517,7 @@ ice_get_module_eeprom(struct net_device *netdev, u8 addr = ICE_I2C_EEPROM_DEV_ADDR; struct ice_hw *hw = &pf->hw; bool is_sfp = false; - unsigned int i, j; + unsigned int i; u16 offset = 0; u8 page = 0; int status; @@ -4547,26 +4559,19 @@ ice_get_module_eeprom(struct net_device *netdev, if (page == 0 || !(data[0x2] & 0x4)) { u32 copy_len; - /* If i2c bus is busy due to slow page change or - * link management access, call can fail. This is normal. - * So we retry this a few times. - */ - for (j = 0; j < 4; j++) { - status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, - !is_sfp, value, - SFF_READ_BLOCK_SIZE, - 0, NULL); - netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%X)\n", - addr, offset, page, is_sfp, - value[0], value[1], value[2], value[3], - value[4], value[5], value[6], value[7], - status); - if (status) { - usleep_range(1500, 2500); - memset(value, 0, SFF_READ_BLOCK_SIZE); - continue; - } - break; + status = ice_aq_sff_eeprom(hw, 0, addr, offset, page, + !is_sfp, value, + SFF_READ_BLOCK_SIZE, + 0, NULL); + netdev_dbg(netdev, "SFF %02X %02X %02X %X = %02X%02X%02X%02X.%02X%02X%02X%02X (%pe)\n", + addr, offset, page, is_sfp, + value[0], value[1], value[2], value[3], + value[4], value[5], value[6], value[7], + ERR_PTR(status)); + if (status) { + netdev_err(netdev, "%s: error reading module EEPROM: status %pe\n", + __func__, ERR_PTR(status)); + return status; } /* Make sure we have enough room for the new block */ diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 3572b0e1d49f..102d63c3018b 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -361,6 +361,39 @@ void ice_unplug_aux_dev(struct ice_pf *pf) } /** + * ice_rdma_finalize_setup - Complete RDMA setup after VSI is ready + * @pf: ptr to ice_pf + * + * Sets VSI-dependent information and plugs aux device. + * Must be called after ice_init_rdma(), ice_vsi_rebuild(), and + * ice_dcb_rebuild() complete. + */ +void ice_rdma_finalize_setup(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + struct iidc_rdma_priv_dev_info *privd; + int ret; + + if (!ice_is_rdma_ena(pf) || !pf->cdev_info) + return; + + privd = pf->cdev_info->iidc_priv; + if (!privd || !pf->vsi || !pf->vsi[0] || !pf->vsi[0]->netdev) + return; + + /* Assign VSI info now that VSI is valid */ + privd->netdev = pf->vsi[0]->netdev; + privd->vport_id = pf->vsi[0]->vsi_num; + + /* Update QoS info after DCB has been rebuilt */ + ice_setup_dcb_qos_info(pf, &privd->qos_info); + + ret = ice_plug_aux_dev(pf); + if (ret) + dev_warn(dev, "Failed to plug RDMA aux device: %d\n", ret); +} + +/** * ice_init_rdma - initializes PF for RDMA use * @pf: ptr to ice_pf */ @@ -398,22 +431,14 @@ int ice_init_rdma(struct ice_pf *pf) } cdev->iidc_priv = privd; - privd->netdev = pf->vsi[0]->netdev; privd->hw_addr = (u8 __iomem *)pf->hw.hw_addr; cdev->pdev = pf->pdev; - privd->vport_id = pf->vsi[0]->vsi_num; pf->cdev_info->rdma_protocol |= IIDC_RDMA_PROTOCOL_ROCEV2; - ice_setup_dcb_qos_info(pf, &privd->qos_info); - ret = ice_plug_aux_dev(pf); - if (ret) - goto err_plug_aux_dev; + return 0; -err_plug_aux_dev: - pf->cdev_info->adev = NULL; - xa_erase(&ice_aux_id, pf->aux_idx); err_alloc_xa: kfree(privd); err_privd_alloc: @@ -432,7 +457,6 @@ void ice_deinit_rdma(struct ice_pf *pf) if (!ice_is_rdma_ena(pf)) return; - ice_unplug_aux_dev(pf); xa_erase(&ice_aux_id, pf->aux_idx); kfree(pf->cdev_info->iidc_priv); kfree(pf->cdev_info); diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f91f8b672b02..689c6025ea82 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -107,10 +107,6 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) if (!vsi->rxq_map) goto err_rxq_map; - /* There is no need to allocate q_vectors for a loopback VSI. */ - if (vsi->type == ICE_VSI_LB) - return 0; - /* allocate memory for q_vector pointers */ vsi->q_vectors = devm_kcalloc(dev, vsi->num_q_vectors, sizeof(*vsi->q_vectors), GFP_KERNEL); @@ -241,6 +237,8 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) case ICE_VSI_LB: vsi->alloc_txq = 1; vsi->alloc_rxq = 1; + /* A dummy q_vector, no actual IRQ. */ + vsi->num_q_vectors = 1; break; default: dev_warn(ice_pf_to_dev(pf), "Unknown VSI type %d\n", vsi_type); @@ -2426,14 +2424,21 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi) } break; case ICE_VSI_LB: - ret = ice_vsi_alloc_rings(vsi); + ret = ice_vsi_alloc_q_vectors(vsi); if (ret) goto unroll_vsi_init; + ret = ice_vsi_alloc_rings(vsi); + if (ret) + goto unroll_alloc_q_vector; + ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + /* Simply map the dummy q_vector to the only rx_ring */ + vsi->rx_rings[0]->q_vector = vsi->q_vectors[0]; + break; default: /* clean up the resources and exit */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index ebf48feffb30..e7308e381e2f 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -5138,6 +5138,9 @@ int ice_load(struct ice_pf *pf) if (err) goto err_init_rdma; + /* Finalize RDMA: VSI already created, assign info and plug device */ + ice_rdma_finalize_setup(pf); + ice_service_task_restart(pf); clear_bit(ICE_DOWN, pf->state); @@ -5169,6 +5172,7 @@ void ice_unload(struct ice_pf *pf) devl_assert_locked(priv_to_devlink(pf)); + ice_unplug_aux_dev(pf); ice_deinit_rdma(pf); ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); @@ -5595,6 +5599,7 @@ static int ice_suspend(struct device *dev) */ disabled = ice_service_task_stop(pf); + ice_unplug_aux_dev(pf); ice_deinit_rdma(pf); /* Already suspended?, then there is nothing to do */ @@ -7859,7 +7864,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_health_clear(pf); - ice_plug_aux_dev(pf); + ice_rdma_finalize_setup(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index a5bbce68f76c..a2cd4cf37734 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -560,7 +560,9 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) i = 0; } - if (rx_ring->vsi->type == ICE_VSI_PF && + if ((rx_ring->vsi->type == ICE_VSI_PF || + rx_ring->vsi->type == ICE_VSI_SF || + rx_ring->vsi->type == ICE_VSI_LB) && xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) { xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq); xdp_rxq_info_unreg(&rx_ring->xdp_rxq); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index c673094663a3..0643017541c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -899,6 +899,9 @@ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) u16 ntc = rx_ring->next_to_clean; u16 ntu = rx_ring->next_to_use; + if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + while (ntc != ntu) { struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc); diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c index 40e08a71d2d3..bb99d9e7c65d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c +++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c @@ -307,9 +307,6 @@ static int idpf_del_flow_steer(struct net_device *netdev, vport_config = vport->adapter->vport_config[np->vport_idx]; user_config = &vport_config->user_config; - if (!idpf_sideband_action_ena(vport, fsp)) - return -EOPNOTSUPP; - rule = kzalloc_flex(*rule, rule_info, 1); if (!rule) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index de3df705a7e6..cf966fe6c759 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -1318,6 +1318,7 @@ static struct idpf_vport *idpf_vport_alloc(struct idpf_adapter *adapter, free_rss_key: kfree(rss_data->rss_key); + rss_data->rss_key = NULL; free_qreg_chunks: idpf_vport_deinit_queue_reg_chunks(adapter->vport_config[idx]); free_vector_idxs: diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 05a162094d10..252259993022 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -1314,6 +1314,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc) struct idpf_txq_group *txq_grp = &rsrc->txq_grps[i]; for (unsigned int j = 0; j < txq_grp->num_txq; j++) { + if (!txq_grp->txqs[j]) + continue; + if (idpf_queue_has(FLOW_SCH_EN, txq_grp->txqs[j])) { kfree(txq_grp->txqs[j]->refillq); txq_grp->txqs[j]->refillq = NULL; @@ -1339,6 +1342,9 @@ static void idpf_txq_group_rel(struct idpf_q_vec_rsrc *rsrc) */ static void idpf_rxq_sw_queue_rel(struct idpf_rxq_group *rx_qgrp) { + if (!rx_qgrp->splitq.bufq_sets) + return; + for (unsigned int i = 0; i < rx_qgrp->splitq.num_bufq_sets; i++) { struct idpf_bufq_set *bufq_set = &rx_qgrp->splitq.bufq_sets[i]; @@ -2336,7 +2342,7 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq) do { struct idpf_splitq_4b_tx_compl_desc *tx_desc; - struct idpf_tx_queue *target; + struct idpf_tx_queue *target = NULL; u32 ctype_gen, id; tx_desc = flow ? &complq->comp[ntc].common : @@ -2356,14 +2362,14 @@ void idpf_wait_for_sw_marker_completion(const struct idpf_tx_queue *txq) target = complq->txq_grp->txqs[id]; idpf_queue_clear(SW_MARKER, target); - if (target == txq) - break; next: if (unlikely(++ntc == complq->desc_count)) { ntc = 0; gen_flag = !gen_flag; } + if (target == txq) + break; } while (time_before(jiffies, timeout)); idpf_queue_assign(GEN_CHK, complq, gen_flag); @@ -4059,7 +4065,7 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport, continue; name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name, if_name, - vec_name, vidx); + vec_name, vector); err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0, name, q_vector); diff --git a/drivers/net/ethernet/intel/idpf/xdp.c b/drivers/net/ethernet/intel/idpf/xdp.c index 6ac9c6624c2a..cbccd4546768 100644 --- a/drivers/net/ethernet/intel/idpf/xdp.c +++ b/drivers/net/ethernet/intel/idpf/xdp.c @@ -47,12 +47,16 @@ static int __idpf_xdp_rxq_info_init(struct idpf_rx_queue *rxq, void *arg) { const struct idpf_vport *vport = rxq->q_vector->vport; const struct idpf_q_vec_rsrc *rsrc; + u32 frag_size = 0; bool split; int err; + if (idpf_queue_has(XSK, rxq)) + frag_size = rxq->bufq_sets[0].bufq.truesize; + err = __xdp_rxq_info_reg(&rxq->xdp_rxq, vport->netdev, rxq->idx, rxq->q_vector->napi.napi_id, - rxq->rx_buf_size); + frag_size); if (err) return err; diff --git a/drivers/net/ethernet/intel/idpf/xsk.c b/drivers/net/ethernet/intel/idpf/xsk.c index 676cbd80774d..d95d3efdfd36 100644 --- a/drivers/net/ethernet/intel/idpf/xsk.c +++ b/drivers/net/ethernet/intel/idpf/xsk.c @@ -403,6 +403,7 @@ int idpf_xskfq_init(struct idpf_buf_queue *bufq) bufq->pending = fq.pending; bufq->thresh = fq.thresh; bufq->rx_buf_size = fq.buf_len; + bufq->truesize = fq.truesize; if (!idpf_xskfq_refill(bufq)) netdev_err(bufq->pool->netdev, diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c index 30ce5fbb5b77..ce4a7b58cad2 100644 --- a/drivers/net/ethernet/intel/igb/igb_xsk.c +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -524,6 +524,16 @@ bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool) return nb_pkts < budget; } +static u32 igb_sw_irq_prep(struct igb_q_vector *q_vector) +{ + u32 eics = 0; + + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; +} + int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct igb_adapter *adapter = netdev_priv(dev); @@ -542,20 +552,32 @@ int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) ring = adapter->tx_ring[qid]; - if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) - return -ENETDOWN; - if (!READ_ONCE(ring->xsk_pool)) return -EINVAL; - if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + if (flags & XDP_WAKEUP_TX) { + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) + return -ENETDOWN; + + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (flags & XDP_WAKEUP_RX) { + /* If IGB_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the TX path, making this RX call a NOP + */ + ring = adapter->rx_ring[qid]; + eics |= igb_sw_irq_prep(ring->q_vector); + } + + if (eics) { /* Cause software interrupt */ - if (adapter->flags & IGB_FLAG_HAS_MSIX) { - eics |= ring->q_vector->eims_value; + if (adapter->flags & IGB_FLAG_HAS_MSIX) wr32(E1000_EICS, eics); - } else { + else wr32(E1000_ICS, E1000_ICS_RXDMT0); - } } return 0; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 27e5c2109138..b2e8d0c0f827 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6906,28 +6906,29 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, return nxmit; } -static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, - struct igc_q_vector *q_vector) +static u32 igc_sw_irq_prep(struct igc_q_vector *q_vector) { - struct igc_hw *hw = &adapter->hw; u32 eics = 0; - eics |= q_vector->eims_value; - wr32(IGC_EICS, eics); + if (!napi_if_scheduled_mark_missed(&q_vector->napi)) + eics = q_vector->eims_value; + + return eics; } int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct igc_adapter *adapter = netdev_priv(dev); - struct igc_q_vector *q_vector; + struct igc_hw *hw = &adapter->hw; struct igc_ring *ring; + u32 eics = 0; if (test_bit(__IGC_DOWN, &adapter->state)) return -ENETDOWN; if (!igc_xdp_is_enabled(adapter)) return -ENXIO; - + /* Check if queue_id is valid. Tx and Rx queue numbers are always same */ if (queue_id >= adapter->num_rx_queues) return -EINVAL; @@ -6936,9 +6937,22 @@ int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) if (!ring->xsk_pool) return -ENXIO; - q_vector = adapter->q_vector[queue_id]; - if (!napi_if_scheduled_mark_missed(&q_vector->napi)) - igc_trigger_rxtxq_interrupt(adapter, q_vector); + if (flags & XDP_WAKEUP_RX) + eics |= igc_sw_irq_prep(ring->q_vector); + + if (flags & XDP_WAKEUP_TX) { + /* If IGC_FLAG_QUEUE_PAIRS is active, the q_vector + * and NAPI is shared between RX and TX. + * If NAPI is already running it would be marked as missed + * from the RX path, making this TX call a NOP + */ + ring = adapter->tx_ring[queue_id]; + eics |= igc_sw_irq_prep(ring->q_vector); + } + + if (eics) + /* Cause software interrupt */ + wr32(IGC_EICS, eics); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 7aae83c108fd..44ee19386766 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -550,7 +550,8 @@ static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter, tstamp->buffer_type = 0; /* Trigger txrx interrupt for transmit completion */ - igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0); + igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, + XDP_WAKEUP_TX); return; } diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 74d320879513..b67b580f7f1c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -852,7 +852,8 @@ static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw, if (!mac->get_link_status) goto out; - if (hw->mac.type == ixgbe_mac_e610_vf) { + if (hw->mac.type == ixgbe_mac_e610_vf && + hw->api_version >= ixgbe_mbox_api_16) { ret_val = ixgbevf_get_pf_link_state(hw, speed, link_up); if (ret_val) goto out; diff --git a/drivers/net/ethernet/intel/libeth/xsk.c b/drivers/net/ethernet/intel/libeth/xsk.c index 846e902e31b6..4882951d5c9c 100644 --- a/drivers/net/ethernet/intel/libeth/xsk.c +++ b/drivers/net/ethernet/intel/libeth/xsk.c @@ -167,6 +167,7 @@ int libeth_xskfq_create(struct libeth_xskfq *fq) fq->pending = fq->count; fq->thresh = libeth_xdp_queue_threshold(fq->count); fq->buf_len = xsk_pool_get_rx_frame_size(fq->pool); + fq->truesize = xsk_pool_get_rx_frag_step(fq->pool); return 0; } diff --git a/drivers/net/ethernet/intel/libie/fwlog.c b/drivers/net/ethernet/intel/libie/fwlog.c index 79020d990859..4d0c8370386b 100644 --- a/drivers/net/ethernet/intel/libie/fwlog.c +++ b/drivers/net/ethernet/intel/libie/fwlog.c @@ -1049,6 +1049,10 @@ void libie_fwlog_deinit(struct libie_fwlog *fwlog) { int status; + /* if FW logging isn't supported it means no configuration was done */ + if (!libie_fwlog_supported(fwlog)) + return; + /* make sure FW logging is disabled to not put the FW in a weird state * for the next driver load */ diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index ec55eb2a6c04..028dd55604ea 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -554,28 +554,43 @@ static void octep_clean_irqs(struct octep_device *oct) } /** - * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * octep_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. * * @iq: Octeon Tx queue data structure. * @oq: Octeon Rx queue data structure. */ -static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq) +static void octep_update_pkt(struct octep_iq *iq, struct octep_oq *oq) { - u32 pkts_pend = oq->pkts_pending; + u32 pkts_pend = READ_ONCE(oq->pkts_pending); + u32 last_pkt_count = READ_ONCE(oq->last_pkt_count); + u32 pkts_processed = READ_ONCE(iq->pkts_processed); + u32 pkt_in_done = READ_ONCE(iq->pkt_in_done); netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); - if (iq->pkts_processed) { - writel(iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed = 0; + if (pkts_processed) { + writel(pkts_processed, iq->inst_cnt_reg); + readl(iq->inst_cnt_reg); + WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed)); + WRITE_ONCE(iq->pkts_processed, 0); } - if (oq->last_pkt_count - pkts_pend) { - writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; + if (last_pkt_count - pkts_pend) { + writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg); + readl(oq->pkts_sent_reg); + WRITE_ONCE(oq->last_pkt_count, pkts_pend); } /* Flush the previous wrties before writing to RESEND bit */ - wmb(); + smp_wmb(); +} + +/** + * octep_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * + * @iq: Octeon Tx queue data structure. + * @oq: Octeon Rx queue data structure. + */ +static void octep_enable_ioq_irq(struct octep_iq *iq, struct octep_oq *oq) +{ writeq(1UL << OCTEP_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg); writeq(1UL << OCTEP_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg); } @@ -601,7 +616,8 @@ static int octep_napi_poll(struct napi_struct *napi, int budget) if (tx_pending || rx_done >= budget) return budget; - napi_complete(napi); + octep_update_pkt(ioq_vector->iq, ioq_vector->oq); + napi_complete_done(napi, rx_done); octep_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq); return rx_done; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c index f2a7c6a76c74..74de19166488 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.c @@ -324,10 +324,16 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, struct octep_oq *oq) { u32 pkt_count, new_pkts; + u32 last_pkt_count, pkts_pending; pkt_count = readl(oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count = READ_ONCE(oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; + if (pkt_count < last_pkt_count) { + dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n", + oq->q_no, pkt_count, last_pkt_count); + } /* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and * reached half its max value. @@ -338,8 +344,9 @@ static int octep_oq_check_hw_for_pkts(struct octep_device *oct, pkt_count = readl(oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; + WRITE_ONCE(oq->last_pkt_count, pkt_count); + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts)); return new_pkts; } @@ -414,7 +421,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, u16 rx_ol_flags; u32 read_idx; - read_idx = oq->host_read_idx; + read_idx = READ_ONCE(oq->host_read_idx); rx_bytes = 0; desc_used = 0; for (pkt = 0; pkt < pkts_to_process; pkt++) { @@ -499,7 +506,7 @@ static int __octep_oq_process_rx(struct octep_device *oct, napi_gro_receive(oq->napi, skb); } - oq->host_read_idx = read_idx; + WRITE_ONCE(oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes; @@ -522,22 +529,26 @@ int octep_oq_process_rx(struct octep_oq *oq, int budget) { u32 pkts_available, pkts_processed, total_pkts_processed; struct octep_device *oct = oq->octep_dev; + u32 pkts_pending; pkts_available = 0; pkts_processed = 0; total_pkts_processed = 0; while (total_pkts_processed < budget) { /* update pending count only when current one exhausted */ - if (oq->pkts_pending == 0) + pkts_pending = READ_ONCE(oq->pkts_pending); + if (pkts_pending == 0) octep_oq_check_hw_for_pkts(oct, oq); + pkts_pending = READ_ONCE(oq->pkts_pending); pkts_available = min(budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending); if (!pkts_available) break; pkts_processed = __octep_oq_process_rx(oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; } diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c index 562fe945b422..7f1b93cffb98 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_main.c @@ -286,28 +286,45 @@ static void octep_vf_clean_irqs(struct octep_vf_device *oct) } /** - * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * octep_vf_update_pkt() - Update IQ/OQ IN/OUT_CNT registers. * * @iq: Octeon Tx queue data structure. * @oq: Octeon Rx queue data structure. */ -static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, struct octep_vf_oq *oq) + +static void octep_vf_update_pkt(struct octep_vf_iq *iq, struct octep_vf_oq *oq) { - u32 pkts_pend = oq->pkts_pending; + u32 pkts_pend = READ_ONCE(oq->pkts_pending); + u32 last_pkt_count = READ_ONCE(oq->last_pkt_count); + u32 pkts_processed = READ_ONCE(iq->pkts_processed); + u32 pkt_in_done = READ_ONCE(iq->pkt_in_done); netdev_dbg(iq->netdev, "enabling intr for Q-%u\n", iq->q_no); - if (iq->pkts_processed) { - writel(iq->pkts_processed, iq->inst_cnt_reg); - iq->pkt_in_done -= iq->pkts_processed; - iq->pkts_processed = 0; + if (pkts_processed) { + writel(pkts_processed, iq->inst_cnt_reg); + readl(iq->inst_cnt_reg); + WRITE_ONCE(iq->pkt_in_done, (pkt_in_done - pkts_processed)); + WRITE_ONCE(iq->pkts_processed, 0); } - if (oq->last_pkt_count - pkts_pend) { - writel(oq->last_pkt_count - pkts_pend, oq->pkts_sent_reg); - oq->last_pkt_count = pkts_pend; + if (last_pkt_count - pkts_pend) { + writel(last_pkt_count - pkts_pend, oq->pkts_sent_reg); + readl(oq->pkts_sent_reg); + WRITE_ONCE(oq->last_pkt_count, pkts_pend); } /* Flush the previous wrties before writing to RESEND bit */ smp_wmb(); +} + +/** + * octep_vf_enable_ioq_irq() - Enable MSI-x interrupt of a Tx/Rx queue. + * + * @iq: Octeon Tx queue data structure. + * @oq: Octeon Rx queue data structure. + */ +static void octep_vf_enable_ioq_irq(struct octep_vf_iq *iq, + struct octep_vf_oq *oq) +{ writeq(1UL << OCTEP_VF_OQ_INTR_RESEND_BIT, oq->pkts_sent_reg); writeq(1UL << OCTEP_VF_IQ_INTR_RESEND_BIT, iq->inst_cnt_reg); } @@ -333,6 +350,7 @@ static int octep_vf_napi_poll(struct napi_struct *napi, int budget) if (tx_pending || rx_done >= budget) return budget; + octep_vf_update_pkt(ioq_vector->iq, ioq_vector->oq); if (likely(napi_complete_done(napi, rx_done))) octep_vf_enable_ioq_irq(ioq_vector->iq, ioq_vector->oq); diff --git a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c index 6f865dbbba6c..b579d5b545c4 100644 --- a/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c +++ b/drivers/net/ethernet/marvell/octeon_ep_vf/octep_vf_rx.c @@ -325,9 +325,16 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, struct octep_vf_oq *oq) { u32 pkt_count, new_pkts; + u32 last_pkt_count, pkts_pending; pkt_count = readl(oq->pkts_sent_reg); - new_pkts = pkt_count - oq->last_pkt_count; + last_pkt_count = READ_ONCE(oq->last_pkt_count); + new_pkts = pkt_count - last_pkt_count; + + if (pkt_count < last_pkt_count) { + dev_err(oq->dev, "OQ-%u pkt_count(%u) < oq->last_pkt_count(%u)\n", + oq->q_no, pkt_count, last_pkt_count); + } /* Clear the hardware packets counter register if the rx queue is * being processed continuously with-in a single interrupt and @@ -339,8 +346,9 @@ static int octep_vf_oq_check_hw_for_pkts(struct octep_vf_device *oct, pkt_count = readl(oq->pkts_sent_reg); new_pkts += pkt_count; } - oq->last_pkt_count = pkt_count; - oq->pkts_pending += new_pkts; + WRITE_ONCE(oq->last_pkt_count, pkt_count); + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending + new_pkts)); return new_pkts; } @@ -369,7 +377,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct, struct sk_buff *skb; u32 read_idx; - read_idx = oq->host_read_idx; + read_idx = READ_ONCE(oq->host_read_idx); rx_bytes = 0; desc_used = 0; for (pkt = 0; pkt < pkts_to_process; pkt++) { @@ -463,7 +471,7 @@ static int __octep_vf_oq_process_rx(struct octep_vf_device *oct, napi_gro_receive(oq->napi, skb); } - oq->host_read_idx = read_idx; + WRITE_ONCE(oq->host_read_idx, read_idx); oq->refill_count += desc_used; oq->stats->packets += pkt; oq->stats->bytes += rx_bytes; @@ -486,22 +494,26 @@ int octep_vf_oq_process_rx(struct octep_vf_oq *oq, int budget) { u32 pkts_available, pkts_processed, total_pkts_processed; struct octep_vf_device *oct = oq->octep_vf_dev; + u32 pkts_pending; pkts_available = 0; pkts_processed = 0; total_pkts_processed = 0; while (total_pkts_processed < budget) { /* update pending count only when current one exhausted */ - if (oq->pkts_pending == 0) + pkts_pending = READ_ONCE(oq->pkts_pending); + if (pkts_pending == 0) octep_vf_oq_check_hw_for_pkts(oct, oq); + pkts_pending = READ_ONCE(oq->pkts_pending); pkts_available = min(budget - total_pkts_processed, - oq->pkts_pending); + pkts_pending); if (!pkts_available) break; pkts_processed = __octep_vf_oq_process_rx(oct, oq, pkts_available); - oq->pkts_pending -= pkts_processed; + pkts_pending = READ_ONCE(oq->pkts_pending); + WRITE_ONCE(oq->pkts_pending, (pkts_pending - pkts_processed)); total_pkts_processed += pkts_processed; } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 1060764b9f17..bb8ced22ca3b 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3770,12 +3770,21 @@ static int mtk_xdp_setup(struct net_device *dev, struct bpf_prog *prog, mtk_stop(dev); old_prog = rcu_replace_pointer(eth->prog, prog, lockdep_rtnl_is_held()); + + if (netif_running(dev) && need_update) { + int err; + + err = mtk_open(dev); + if (err) { + rcu_assign_pointer(eth->prog, old_prog); + + return err; + } + } + if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev) && need_update) - return mtk_open(dev); - return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index a868c28c8280..ea71de39f996 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -1770,8 +1770,14 @@ static void mana_poll_tx_cq(struct mana_cq *cq) ndev = txq->ndev; apc = netdev_priv(ndev); + /* Limit CQEs polled to 4 wraparounds of the CQ to ensure the + * doorbell can be rung in time for the hardware's requirement + * of at least one doorbell ring every 8 wraparounds. + */ comp_read = mana_gd_poll_cq(cq->gdma_cq, completions, - CQE_POLLING_BUFFER); + min((cq->gdma_cq->queue_size / + COMP_ENTRY_SIZE) * 4, + CQE_POLLING_BUFFER)); if (comp_read < 1) return; @@ -2156,7 +2162,14 @@ static void mana_poll_rx_cq(struct mana_cq *cq) struct mana_rxq *rxq = cq->rxq; int comp_read, i; - comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, CQE_POLLING_BUFFER); + /* Limit CQEs polled to 4 wraparounds of the CQ to ensure the + * doorbell can be rung in time for the hardware's requirement + * of at least one doorbell ring every 8 wraparounds. + */ + comp_read = mana_gd_poll_cq(cq->gdma_cq, comp, + min((cq->gdma_cq->queue_size / + COMP_ENTRY_SIZE) * 4, + CQE_POLLING_BUFFER)); WARN_ON_ONCE(comp_read > CQE_POLLING_BUFFER); rxq->xdp_flush = false; @@ -2201,11 +2214,11 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue) mana_gd_ring_cq(gdma_queue, SET_ARM_BIT); cq->work_done_since_doorbell = 0; napi_complete_done(&cq->napi, w); - } else if (cq->work_done_since_doorbell > - cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) { + } else if (cq->work_done_since_doorbell >= + (cq->gdma_cq->queue_size / COMP_ENTRY_SIZE) * 4) { /* MANA hardware requires at least one doorbell ring every 8 * wraparounds of CQ even if there is no need to arm the CQ. - * This driver rings the doorbell as soon as we have exceeded + * This driver rings the doorbell as soon as it has processed * 4 wraparounds. */ mana_gd_ring_cq(gdma_queue, 0); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index e98cb9f3a44c..1fe96cd24b4f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -328,6 +328,7 @@ struct stmmac_priv { void __iomem *ptpaddr; void __iomem *estaddr; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + unsigned int num_double_vlans; int sfty_irq; int sfty_ce_irq; int sfty_ue_irq; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 029e9b518160..f0160ff54a59 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -157,6 +157,7 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue); static void stmmac_flush_tx_descriptors(struct stmmac_priv *priv, int queue); static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, u32 rxmode, u32 chan); +static int stmmac_vlan_restore(struct stmmac_priv *priv); #ifdef CONFIG_DEBUG_FS static const struct net_device_ops stmmac_netdev_ops; @@ -4097,6 +4098,8 @@ static int __stmmac_open(struct net_device *dev, phylink_start(priv->phylink); + stmmac_vlan_restore(priv); + ret = stmmac_request_irq(dev); if (ret) goto irq_error; @@ -6757,6 +6760,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) hash = 0; } + if (!netif_running(priv->dev)) + return 0; + return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double); } @@ -6766,6 +6772,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); + unsigned int num_double_vlans; bool is_double = false; int ret; @@ -6777,7 +6784,8 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid is_double = true; set_bit(vid, priv->active_vlans); - ret = stmmac_vlan_update(priv, is_double); + num_double_vlans = priv->num_double_vlans + is_double; + ret = stmmac_vlan_update(priv, num_double_vlans); if (ret) { clear_bit(vid, priv->active_vlans); goto err_pm_put; @@ -6785,9 +6793,15 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid if (priv->hw->num_vlan) { ret = stmmac_add_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid); - if (ret) + if (ret) { + clear_bit(vid, priv->active_vlans); + stmmac_vlan_update(priv, priv->num_double_vlans); goto err_pm_put; + } } + + priv->num_double_vlans = num_double_vlans; + err_pm_put: pm_runtime_put(priv->device); @@ -6800,6 +6814,7 @@ err_pm_put: static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); + unsigned int num_double_vlans; bool is_double = false; int ret; @@ -6811,14 +6826,23 @@ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vi is_double = true; clear_bit(vid, priv->active_vlans); + num_double_vlans = priv->num_double_vlans - is_double; + ret = stmmac_vlan_update(priv, num_double_vlans); + if (ret) { + set_bit(vid, priv->active_vlans); + goto del_vlan_error; + } if (priv->hw->num_vlan) { ret = stmmac_del_hw_vlan_rx_fltr(priv, ndev, priv->hw, proto, vid); - if (ret) + if (ret) { + set_bit(vid, priv->active_vlans); + stmmac_vlan_update(priv, priv->num_double_vlans); goto del_vlan_error; + } } - ret = stmmac_vlan_update(priv, is_double); + priv->num_double_vlans = num_double_vlans; del_vlan_error: pm_runtime_put(priv->device); @@ -6826,6 +6850,23 @@ del_vlan_error: return ret; } +static int stmmac_vlan_restore(struct stmmac_priv *priv) +{ + int ret; + + if (!(priv->dev->features & NETIF_F_VLAN_FEATURES)) + return 0; + + if (priv->hw->num_vlan) + stmmac_restore_hw_vlan_rx_fltr(priv, priv->dev, priv->hw); + + ret = stmmac_vlan_update(priv, priv->num_double_vlans); + if (ret) + netdev_err(priv->dev, "Failed to restore VLANs\n"); + + return ret; +} + static int stmmac_bpf(struct net_device *dev, struct netdev_bpf *bpf) { struct stmmac_priv *priv = netdev_priv(dev); @@ -8263,10 +8304,10 @@ int stmmac_resume(struct device *dev) stmmac_init_coalesce(priv); phylink_rx_clk_stop_block(priv->phylink); stmmac_set_rx_mode(ndev); - - stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw); phylink_rx_clk_stop_unblock(priv->phylink); + stmmac_vlan_restore(priv); + stmmac_enable_all_queues(priv); stmmac_enable_all_dma_irq(priv); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c index b18404dd5a8b..e24efe3bfedb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c @@ -76,7 +76,9 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev, } hw->vlan_filter[0] = vid; - vlan_write_single(dev, vid); + + if (netif_running(dev)) + vlan_write_single(dev, vid); return 0; } @@ -97,12 +99,15 @@ static int vlan_add_hw_rx_fltr(struct net_device *dev, return -EPERM; } - ret = vlan_write_filter(dev, hw, index, val); + if (netif_running(dev)) { + ret = vlan_write_filter(dev, hw, index, val); + if (ret) + return ret; + } - if (!ret) - hw->vlan_filter[index] = val; + hw->vlan_filter[index] = val; - return ret; + return 0; } static int vlan_del_hw_rx_fltr(struct net_device *dev, @@ -115,7 +120,9 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, if (hw->num_vlan == 1) { if ((hw->vlan_filter[0] & VLAN_TAG_VID) == vid) { hw->vlan_filter[0] = 0; - vlan_write_single(dev, 0); + + if (netif_running(dev)) + vlan_write_single(dev, 0); } return 0; } @@ -124,25 +131,23 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, for (i = 0; i < hw->num_vlan; i++) { if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) && ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) { - ret = vlan_write_filter(dev, hw, i, 0); - if (!ret) - hw->vlan_filter[i] = 0; - else - return ret; + if (netif_running(dev)) { + ret = vlan_write_filter(dev, hw, i, 0); + if (ret) + return ret; + } + + hw->vlan_filter[i] = 0; } } - return ret; + return 0; } static void vlan_restore_hw_rx_fltr(struct net_device *dev, struct mac_device_info *hw) { - void __iomem *ioaddr = hw->pcsr; - u32 value; - u32 hash; - u32 val; int i; /* Single Rx VLAN Filter */ @@ -152,19 +157,8 @@ static void vlan_restore_hw_rx_fltr(struct net_device *dev, } /* Extended Rx VLAN Filter Enable */ - for (i = 0; i < hw->num_vlan; i++) { - if (hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) { - val = hw->vlan_filter[i]; - vlan_write_filter(dev, hw, i, val); - } - } - - hash = readl(ioaddr + VLAN_HASH_TABLE); - if (hash & VLAN_VLHT) { - value = readl(ioaddr + VLAN_TAG); - value |= VLAN_VTHM; - writel(value, ioaddr + VLAN_TAG); - } + for (i = 0; i < hw->num_vlan; i++) + vlan_write_filter(dev, hw, i, hw->vlan_filter[i]); } static void vlan_update_hash(struct mac_device_info *hw, u32 hash, @@ -183,6 +177,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash, value |= VLAN_EDVLP; value |= VLAN_ESVL; value |= VLAN_DOVLTC; + } else { + value &= ~VLAN_EDVLP; + value &= ~VLAN_ESVL; + value &= ~VLAN_DOVLTC; } writel(value, ioaddr + VLAN_TAG); @@ -193,6 +191,10 @@ static void vlan_update_hash(struct mac_device_info *hw, u32 hash, value |= VLAN_EDVLP; value |= VLAN_ESVL; value |= VLAN_DOVLTC; + } else { + value &= ~VLAN_EDVLP; + value &= ~VLAN_ESVL; + value &= ~VLAN_DOVLTC; } writel(value | perfect_match, ioaddr + VLAN_TAG); diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 5924db6be3fe..967918050433 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -391,7 +391,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev) cpsw_ale_set_allmulti(common->ale, ndev->flags & IFF_ALLMULTI, port->port_id); - port_mask = ALE_PORT_HOST; + port_mask = BIT(port->port_id) | ALE_PORT_HOST; /* Clear all mcast from ALE */ cpsw_ale_flush_multicast(common->ale, port_mask, -1); diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index bb969dd435b4..be7b69319221 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -450,14 +450,13 @@ static void cpsw_ale_flush_mcast(struct cpsw_ale *ale, u32 *ale_entry, ale->port_mask_bits); if ((mask & port_mask) == 0) return; /* ports dont intersect, not interested */ - mask &= ~port_mask; + mask &= (~port_mask | ALE_PORT_HOST); - /* free if only remaining port is host port */ - if (mask) + if (mask == 0x0 || mask == ALE_PORT_HOST) + cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); + else cpsw_ale_set_port_mask(ale_entry, mask, ale->port_mask_bits); - else - cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); } int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask, int vid) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 9efa39069c8c..372e55803168 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -279,6 +279,14 @@ static int prueth_emac_common_start(struct prueth *prueth) if (ret) goto disable_class; + /* Reset link state to force reconfiguration in + * emac_adjust_link(). Without this, if the link was already up + * before restart, emac_adjust_link() won't detect any state + * change and will skip critical configuration like writing + * speed to firmware. + */ + emac->link = 0; + mutex_lock(&emac->ndev->phydev->lock); emac_adjust_link(emac->ndev); mutex_unlock(&emac->ndev->phydev->lock); diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 2db116fb1a7c..3c9acd6e49e8 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -617,7 +617,7 @@ static ssize_t sysdata_release_enabled_show(struct config_item *item, bool release_enabled; dynamic_netconsole_mutex_lock(); - release_enabled = !!(nt->sysdata_fields & SYSDATA_TASKNAME); + release_enabled = !!(nt->sysdata_fields & SYSDATA_RELEASE); dynamic_netconsole_mutex_unlock(); return sysfs_emit(buf, "%d\n", release_enabled); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index ea7c1eadc864..3b6d4252d34c 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -10088,6 +10088,7 @@ static const struct usb_device_id rtl8152_table[] = { { USB_DEVICE(VENDOR_ID_DLINK, 0xb301) }, { USB_DEVICE(VENDOR_ID_DELL, 0xb097) }, { USB_DEVICE(VENDOR_ID_ASUS, 0x1976) }, + { USB_DEVICE(VENDOR_ID_TRENDNET, 0xe02b) }, {} }; diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 05558b6afecd..17c941aac32d 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2130,6 +2130,11 @@ static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb) { struct ipv6hdr *pip6; + /* check if nd_tbl is not initiliazed due to + * ipv6.disable=1 set during boot + */ + if (!ipv6_stub->nd_tbl) + return false; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return false; pip6 = ipv6_hdr(skb); diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index 05268d425d6a..af7590639dbf 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -5432,7 +5432,7 @@ int ath12k_mac_op_get_txpower(struct ieee80211_hw *hw, ar->last_tx_power_update)) goto send_tx_power; - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = arvif->vdev_id; params.stats_id = WMI_REQUEST_PDEV_STAT; ret = ath12k_mac_get_fw_stats(ar, ¶ms); @@ -13454,7 +13454,7 @@ void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw, /* TODO: Use real NF instead of default one. */ signal = rate_info.rssi_comb; - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = 0; params.stats_id = WMI_REQUEST_VDEV_STAT; @@ -13582,7 +13582,7 @@ void ath12k_mac_op_link_sta_statistics(struct ieee80211_hw *hw, spin_unlock_bh(&ar->ab->dp->dp_lock); if (!signal && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA) { - params.pdev_id = ar->pdev->pdev_id; + params.pdev_id = ath12k_mac_get_target_pdev_id(ar); params.vdev_id = 0; params.stats_id = WMI_REQUEST_VDEV_STAT; diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index 8e13c3ec1cc7..b93e33edf369 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -8216,8 +8216,6 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab, struct ath12k_fw_stats *stats = parse->stats; struct ath12k *ar; struct ath12k_link_vif *arvif; - struct ieee80211_sta *sta; - struct ath12k_sta *ahsta; struct ath12k_link_sta *arsta; int i, ret = 0; const void *data = ptr; @@ -8253,21 +8251,19 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab, arvif = ath12k_mac_get_arvif(ar, le32_to_cpu(src->vdev_id)); if (arvif) { - sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar), - arvif->bssid, - NULL); - if (sta) { - ahsta = ath12k_sta_to_ahsta(sta); - arsta = &ahsta->deflink; + spin_lock_bh(&ab->base_lock); + arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid); + if (arsta) { arsta->rssi_beacon = le32_to_cpu(src->beacon_snr); ath12k_dbg(ab, ATH12K_DBG_WMI, "wmi stats vdev id %d snr %d\n", src->vdev_id, src->beacon_snr); } else { - ath12k_dbg(ab, ATH12K_DBG_WMI, - "not found station bssid %pM for vdev stat\n", - arvif->bssid); + ath12k_warn(ab, + "not found link sta with bssid %pM for vdev stat\n", + arvif->bssid); } + spin_unlock_bh(&ab->base_lock); } data += sizeof(*src); @@ -8338,8 +8334,6 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab, struct ath12k_fw_stats *stats = parse->stats; struct ath12k_link_vif *arvif; struct ath12k_link_sta *arsta; - struct ieee80211_sta *sta; - struct ath12k_sta *ahsta; struct ath12k *ar; int vdev_id; int j; @@ -8375,19 +8369,15 @@ static int ath12k_wmi_tlv_rssi_chain_parse(struct ath12k_base *ab, "stats bssid %pM vif %p\n", arvif->bssid, arvif->ahvif->vif); - sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar), - arvif->bssid, - NULL); - if (!sta) { - ath12k_dbg(ab, ATH12K_DBG_WMI, - "not found station of bssid %pM for rssi chain\n", - arvif->bssid); + guard(spinlock_bh)(&ab->base_lock); + arsta = ath12k_link_sta_find_by_addr(ab, arvif->bssid); + if (!arsta) { + ath12k_warn(ab, + "not found link sta with bssid %pM for rssi chain\n", + arvif->bssid); return -EPROTO; } - ahsta = ath12k_sta_to_ahsta(sta); - arsta = &ahsta->deflink; - BUILD_BUG_ON(ARRAY_SIZE(arsta->chain_signal) > ARRAY_SIZE(stats_rssi->rssi_avg_beacon)); diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c index 3304b5971be0..b41ca1410da9 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mac.c @@ -413,6 +413,7 @@ mt76_connac2_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 + 1 + 2 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) { u16 capab = le16_to_cpu(mgmt->u.action.u.addba_req.capab); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index 871b67101976..0d9435900423 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -668,6 +668,7 @@ mt7925_mac_write_txwi_80211(struct mt76_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) tid = MT_TX_ADDBA; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 2560e2f46e89..d4f3ee943b47 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -800,6 +800,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi, u32 val; if (ieee80211_is_action(fc) && + skb->len >= IEEE80211_MIN_ACTION_SIZE + 1 && mgmt->u.action.category == WLAN_CATEGORY_BACK && mgmt->u.action.u.addba_req.action_code == WLAN_ACTION_ADDBA_REQ) { if (is_mt7990(&dev->mt76)) diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index 8c8e074a3a70..c7ae8031436a 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -668,7 +668,7 @@ static int rsi_mac80211_config(struct ieee80211_hw *hw, struct rsi_hw *adapter = hw->priv; struct rsi_common *common = adapter->priv; struct ieee80211_conf *conf = &hw->conf; - int status = -EOPNOTSUPP; + int status = 0; mutex_lock(&common->mutex); diff --git a/drivers/net/wireless/st/cw1200/pm.c b/drivers/net/wireless/st/cw1200/pm.c index 120f0379f81d..84eb15d729c7 100644 --- a/drivers/net/wireless/st/cw1200/pm.c +++ b/drivers/net/wireless/st/cw1200/pm.c @@ -264,12 +264,14 @@ int cw1200_wow_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) wiphy_err(priv->hw->wiphy, "PM request failed: %d. WoW is disabled.\n", ret); cw1200_wow_resume(hw); + mutex_unlock(&priv->conf_mutex); return -EBUSY; } /* Force resume if event is coming from the device. */ if (atomic_read(&priv->bh_rx)) { cw1200_wow_resume(hw); + mutex_unlock(&priv->conf_mutex); return -EAGAIN; } diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 17dd417756f2..1c340a4a0930 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -1875,6 +1875,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) wl->wow_enabled); WARN_ON(!wl->wow_enabled); + mutex_lock(&wl->mutex); + ret = pm_runtime_force_resume(wl->dev); if (ret < 0) { wl1271_error("ELP wakeup failure!"); @@ -1891,8 +1893,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) run_irq_work = true; spin_unlock_irqrestore(&wl->wl_lock, flags); - mutex_lock(&wl->mutex); - /* test the recovery flag before calling any SDIO functions */ pending_recovery = test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags); diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 295076cf70de..c57ae4d6c5c0 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -905,6 +905,19 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, * supported, so we avoid reprogramming the region on every MSI, * specifically unmapping immediately after writel(). */ + if (ep->msi_iatu_mapped && (ep->msi_msg_addr != msg_addr || + ep->msi_map_size != map_size)) { + /* + * The host changed the MSI target address or the required + * mapping size changed. Reprogramming the iATU when there are + * operations in flight is unsafe on this controller. However, + * there is no unified way to check if we have operations in + * flight, thus we don't know if we should WARN() or not. + */ + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); + ep->msi_iatu_mapped = false; + } + if (!ep->msi_iatu_mapped) { ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, @@ -915,15 +928,6 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, ep->msi_iatu_mapped = true; ep->msi_msg_addr = msg_addr; ep->msi_map_size = map_size; - } else if (WARN_ON_ONCE(ep->msi_msg_addr != msg_addr || - ep->msi_map_size != map_size)) { - /* - * The host changed the MSI target address or the required - * mapping size changed. Reprogramming the iATU at runtime is - * unsafe on this controller, so bail out instead of trying to - * update the existing region. - */ - return -EINVAL; } writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset); @@ -1010,6 +1014,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, writel(msg_data, ep->msi_mem + offset); + /* flush posted write before unmap */ + readl(ep->msi_mem + offset); + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); return 0; diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c index a8f82104a384..227c37c360e1 100644 --- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c +++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c @@ -574,10 +574,9 @@ static int cs42l43_pin_probe(struct platform_device *pdev) if (child) { ret = devm_add_action_or_reset(&pdev->dev, cs42l43_fwnode_put, child); - if (ret) { - fwnode_handle_put(child); + if (ret) return ret; - } + if (!child->dev) child->dev = priv->dev; fwnode = child; diff --git a/drivers/pinctrl/cix/pinctrl-sky1.c b/drivers/pinctrl/cix/pinctrl-sky1.c index 5d0d8be815b2..938894058d86 100644 --- a/drivers/pinctrl/cix/pinctrl-sky1.c +++ b/drivers/pinctrl/cix/pinctrl-sky1.c @@ -522,11 +522,10 @@ static int __maybe_unused sky1_pinctrl_resume(struct device *dev) return pinctrl_force_default(spctl->pctl); } -const struct dev_pm_ops sky1_pinctrl_pm_ops = { +static const struct dev_pm_ops sky1_pinctrl_pm_ops = { SET_LATE_SYSTEM_SLEEP_PM_OPS(sky1_pinctrl_suspend, sky1_pinctrl_resume) }; -EXPORT_SYMBOL_GPL(sky1_pinctrl_pm_ops); static int sky1_pinctrl_probe(struct platform_device *pdev) { diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c index dfa32b11555c..e2293a872dcb 100644 --- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c +++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c @@ -679,7 +679,6 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev, unsigned int *num_maps) { struct device *dev = pctldev->dev; - struct device_node *pnode; unsigned long *configs = NULL; unsigned int num_configs = 0; struct property *prop; @@ -693,7 +692,7 @@ static int aml_dt_node_to_map_pinmux(struct pinctrl_dev *pctldev, return -ENOENT; } - pnode = of_get_parent(np); + struct device_node *pnode __free(device_node) = of_get_parent(np); if (!pnode) { dev_info(dev, "Missing function node\n"); return -EINVAL; diff --git a/drivers/pinctrl/pinconf-generic.c b/drivers/pinctrl/pinconf-generic.c index 94b1d057197c..2b030bd0e6ad 100644 --- a/drivers/pinctrl/pinconf-generic.c +++ b/drivers/pinctrl/pinconf-generic.c @@ -351,13 +351,13 @@ int pinconf_generic_parse_dt_config(struct device_node *np, ret = parse_dt_cfg(np, dt_params, ARRAY_SIZE(dt_params), cfg, &ncfg); if (ret) - return ret; + goto out; if (pctldev && pctldev->desc->num_custom_params && pctldev->desc->custom_params) { ret = parse_dt_cfg(np, pctldev->desc->custom_params, pctldev->desc->num_custom_params, cfg, &ncfg); if (ret) - return ret; + goto out; } /* no configs found at all */ diff --git a/drivers/pinctrl/pinctrl-amdisp.c b/drivers/pinctrl/pinctrl-amdisp.c index efbf40c776ea..e0874cc086a7 100644 --- a/drivers/pinctrl/pinctrl-amdisp.c +++ b/drivers/pinctrl/pinctrl-amdisp.c @@ -80,7 +80,7 @@ static int amdisp_get_group_pins(struct pinctrl_dev *pctldev, return 0; } -const struct pinctrl_ops amdisp_pinctrl_ops = { +static const struct pinctrl_ops amdisp_pinctrl_ops = { .get_groups_count = amdisp_get_groups_count, .get_group_name = amdisp_get_group_name, .get_group_pins = amdisp_get_group_pins, diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c index a4b04bf6d081..5c055d344ac9 100644 --- a/drivers/pinctrl/pinctrl-cy8c95x0.c +++ b/drivers/pinctrl/pinctrl-cy8c95x0.c @@ -627,7 +627,7 @@ static int cy8c95x0_write_regs_mask(struct cy8c95x0_pinctrl *chip, int reg, bitmap_scatter(tmask, mask, chip->map, MAX_LINE); bitmap_scatter(tval, val, chip->map, MAX_LINE); - for_each_set_clump8(offset, bits, tmask, chip->tpin) { + for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) { unsigned int i = offset / 8; write_val = bitmap_get_value8(tval, offset); @@ -655,7 +655,7 @@ static int cy8c95x0_read_regs_mask(struct cy8c95x0_pinctrl *chip, int reg, bitmap_scatter(tmask, mask, chip->map, MAX_LINE); bitmap_scatter(tval, val, chip->map, MAX_LINE); - for_each_set_clump8(offset, bits, tmask, chip->tpin) { + for_each_set_clump8(offset, bits, tmask, chip->nport * BANK_SZ) { unsigned int i = offset / 8; ret = cy8c95x0_regmap_read_bits(chip, reg, i, bits, &read_val); diff --git a/drivers/pinctrl/pinctrl-equilibrium.c b/drivers/pinctrl/pinctrl-equilibrium.c index 48b55c5bf8d4..ba1c867b7b89 100644 --- a/drivers/pinctrl/pinctrl-equilibrium.c +++ b/drivers/pinctrl/pinctrl-equilibrium.c @@ -23,7 +23,7 @@ #define PIN_NAME_LEN 10 #define PAD_REG_OFF 0x100 -static void eqbr_gpio_disable_irq(struct irq_data *d) +static void eqbr_irq_mask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -36,7 +36,7 @@ static void eqbr_gpio_disable_irq(struct irq_data *d) gpiochip_disable_irq(gc, offset); } -static void eqbr_gpio_enable_irq(struct irq_data *d) +static void eqbr_irq_unmask(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -50,7 +50,7 @@ static void eqbr_gpio_enable_irq(struct irq_data *d) raw_spin_unlock_irqrestore(&gctrl->lock, flags); } -static void eqbr_gpio_ack_irq(struct irq_data *d) +static void eqbr_irq_ack(struct irq_data *d) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -62,10 +62,17 @@ static void eqbr_gpio_ack_irq(struct irq_data *d) raw_spin_unlock_irqrestore(&gctrl->lock, flags); } -static void eqbr_gpio_mask_ack_irq(struct irq_data *d) +static void eqbr_irq_mask_ack(struct irq_data *d) { - eqbr_gpio_disable_irq(d); - eqbr_gpio_ack_irq(d); + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); + unsigned int offset = irqd_to_hwirq(d); + unsigned long flags; + + raw_spin_lock_irqsave(&gctrl->lock, flags); + writel(BIT(offset), gctrl->membase + GPIO_IRNENCLR); + writel(BIT(offset), gctrl->membase + GPIO_IRNCR); + raw_spin_unlock_irqrestore(&gctrl->lock, flags); } static inline void eqbr_cfg_bit(void __iomem *addr, @@ -92,7 +99,7 @@ static int eqbr_irq_type_cfg(struct gpio_irq_type *type, return 0; } -static int eqbr_gpio_set_irq_type(struct irq_data *d, unsigned int type) +static int eqbr_irq_set_type(struct irq_data *d, unsigned int type) { struct gpio_chip *gc = irq_data_get_irq_chip_data(d); struct eqbr_gpio_ctrl *gctrl = gpiochip_get_data(gc); @@ -166,11 +173,11 @@ static void eqbr_irq_handler(struct irq_desc *desc) static const struct irq_chip eqbr_irq_chip = { .name = "gpio_irq", - .irq_mask = eqbr_gpio_disable_irq, - .irq_unmask = eqbr_gpio_enable_irq, - .irq_ack = eqbr_gpio_ack_irq, - .irq_mask_ack = eqbr_gpio_mask_ack_irq, - .irq_set_type = eqbr_gpio_set_irq_type, + .irq_ack = eqbr_irq_ack, + .irq_mask = eqbr_irq_mask, + .irq_mask_ack = eqbr_irq_mask_ack, + .irq_unmask = eqbr_irq_unmask, + .irq_set_type = eqbr_irq_set_type, .flags = IRQCHIP_IMMUTABLE, GPIOCHIP_IRQ_RESOURCE_HELPERS, }; diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index d87c0b1de616..f15b18f334ee 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3640,14 +3640,10 @@ static int rockchip_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, * or the gpio driver hasn't probed yet. */ scoped_guard(mutex, &bank->deferred_lock) { - if (!gpio || !gpio->direction_output) { - rc = rockchip_pinconf_defer_pin(bank, - pin - bank->pin_base, - param, arg); - if (rc) - return rc; - break; - } + if (!gpio || !gpio->direction_output) + return rockchip_pinconf_defer_pin(bank, + pin - bank->pin_base, + param, arg); } } diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c index 4dfa820d4e77..f1c827ddbfbf 100644 --- a/drivers/pinctrl/qcom/pinctrl-qcs615.c +++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c @@ -1067,6 +1067,7 @@ static const struct msm_pinctrl_soc_data qcs615_tlmm = { .ntiles = ARRAY_SIZE(qcs615_tiles), .wakeirq_map = qcs615_pdc_map, .nwakeirq_map = ARRAY_SIZE(qcs615_pdc_map), + .wakeirq_dual_edge_errata = true, }; static const struct of_device_id qcs615_tlmm_of_match[] = { diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c index d93af5f0e8d3..65411abfbfac 100644 --- a/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-sdm660-lpass-lpi.c @@ -76,7 +76,7 @@ static const char * const pdm_clk_groups[] = { "gpio18" }; static const char * const pdm_rx_groups[] = { "gpio21", "gpio23", "gpio25" }; static const char * const pdm_sync_groups[] = { "gpio19" }; -const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = { +static const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = { LPI_PINGROUP_OFFSET(0, LPI_NO_SLEW, _, _, _, _, 0x0000), LPI_PINGROUP_OFFSET(1, LPI_NO_SLEW, _, _, _, _, 0x1000), LPI_PINGROUP_OFFSET(2, LPI_NO_SLEW, _, _, _, _, 0x2000), @@ -113,7 +113,7 @@ const struct lpi_pingroup sdm660_lpi_pinctrl_groups[] = { LPI_PINGROUP_OFFSET(31, LPI_NO_SLEW, _, _, _, _, 0xb010), }; -const struct lpi_function sdm660_lpi_pinctrl_functions[] = { +static const struct lpi_function sdm660_lpi_pinctrl_functions[] = { LPI_FUNCTION(comp_rx), LPI_FUNCTION(dmic1_clk), LPI_FUNCTION(dmic1_data), diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 48434292a39b..c990b6118172 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -204,6 +204,32 @@ sunxi_pinctrl_desc_find_function_by_pin(struct sunxi_pinctrl *pctl, return NULL; } +static struct sunxi_desc_function * +sunxi_pinctrl_desc_find_function_by_pin_and_mux(struct sunxi_pinctrl *pctl, + const u16 pin_num, + const u8 muxval) +{ + for (unsigned int i = 0; i < pctl->desc->npins; i++) { + const struct sunxi_desc_pin *pin = pctl->desc->pins + i; + struct sunxi_desc_function *func = pin->functions; + + if (pin->pin.number != pin_num) + continue; + + if (pin->variant && !(pctl->variant & pin->variant)) + continue; + + while (func->name) { + if (func->muxval == muxval) + return func; + + func++; + } + } + + return NULL; +} + static int sunxi_pctrl_get_groups_count(struct pinctrl_dev *pctldev) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); @@ -930,6 +956,30 @@ static const struct pinmux_ops sunxi_pmx_ops = { .strict = true, }; +static int sunxi_pinctrl_gpio_get_direction(struct gpio_chip *chip, + unsigned int offset) +{ + struct sunxi_pinctrl *pctl = gpiochip_get_data(chip); + const struct sunxi_desc_function *func; + u32 pin = offset + chip->base; + u32 reg, shift, mask; + u8 muxval; + + sunxi_mux_reg(pctl, offset, ®, &shift, &mask); + + muxval = (readl(pctl->membase + reg) & mask) >> shift; + + func = sunxi_pinctrl_desc_find_function_by_pin_and_mux(pctl, pin, muxval); + if (!func) + return -ENODEV; + + if (!strcmp(func->name, "gpio_out")) + return GPIO_LINE_DIRECTION_OUT; + if (!strcmp(func->name, "gpio_in") || !strcmp(func->name, "irq")) + return GPIO_LINE_DIRECTION_IN; + return -EINVAL; +} + static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip, unsigned offset) { @@ -1599,6 +1649,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev, pctl->chip->request = gpiochip_generic_request; pctl->chip->free = gpiochip_generic_free; pctl->chip->set_config = gpiochip_generic_config; + pctl->chip->get_direction = sunxi_pinctrl_gpio_get_direction; pctl->chip->direction_input = sunxi_pinctrl_gpio_direction_input; pctl->chip->direction_output = sunxi_pinctrl_gpio_direction_output; pctl->chip->get = sunxi_pinctrl_gpio_get; diff --git a/drivers/pmdomain/imx/gpcv2.c b/drivers/pmdomain/imx/gpcv2.c index cff738e4d546..a829f8da5be7 100644 --- a/drivers/pmdomain/imx/gpcv2.c +++ b/drivers/pmdomain/imx/gpcv2.c @@ -1416,7 +1416,9 @@ static int imx_pgc_domain_suspend(struct device *dev) static int imx_pgc_domain_resume(struct device *dev) { - return pm_runtime_put(dev); + pm_runtime_put(dev); + + return 0; } #endif diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig index a708fc63f581..d10b6f9243d5 100644 --- a/drivers/regulator/Kconfig +++ b/drivers/regulator/Kconfig @@ -508,7 +508,7 @@ config REGULATOR_FP9931 This driver supports the FP9931/JD9930 voltage regulator chip which is used to provide power to Electronic Paper Displays so it is found in E-Book readers. - If HWWON is enabled, it also provides temperature measurement. + If HWMON is enabled, it also provides temperature measurement. config REGULATOR_LM363X tristate "TI LM363X voltage regulators" diff --git a/drivers/regulator/bq257xx-regulator.c b/drivers/regulator/bq257xx-regulator.c index fc1ccede4468..dab8f1ab4450 100644 --- a/drivers/regulator/bq257xx-regulator.c +++ b/drivers/regulator/bq257xx-regulator.c @@ -115,11 +115,10 @@ static void bq257xx_reg_dt_parse_gpio(struct platform_device *pdev) return; subchild = of_get_child_by_name(child, pdata->desc.of_match); + of_node_put(child); if (!subchild) return; - of_node_put(child); - pdata->otg_en_gpio = devm_fwnode_gpiod_get_index(&pdev->dev, of_fwnode_handle(subchild), "enable", 0, diff --git a/drivers/regulator/fp9931.c b/drivers/regulator/fp9931.c index 7fbcc6327cc6..abea3b69d8a0 100644 --- a/drivers/regulator/fp9931.c +++ b/drivers/regulator/fp9931.c @@ -144,13 +144,12 @@ static int fp9931_hwmon_read(struct device *dev, enum hwmon_sensor_types type, return ret; ret = regmap_read(data->regmap, FP9931_REG_TMST_VALUE, &val); - if (ret) - return ret; + if (!ret) + *temp = (s8)val * 1000; pm_runtime_put_autosuspend(data->dev); - *temp = (s8)val * 1000; - return 0; + return ret; } static umode_t fp9931_hwmon_is_visible(const void *data, diff --git a/drivers/regulator/tps65185.c b/drivers/regulator/tps65185.c index 3286c9ab33d0..786622d8d598 100644 --- a/drivers/regulator/tps65185.c +++ b/drivers/regulator/tps65185.c @@ -332,6 +332,9 @@ static int tps65185_probe(struct i2c_client *client) int i; data = devm_kzalloc(&client->dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + data->regmap = devm_regmap_init_i2c(client, ®map_config); if (IS_ERR(data->regmap)) return dev_err_probe(&client->dev, PTR_ERR(data->regmap), diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 94ad253d65a0..e9d9ac7da485 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -12025,6 +12025,8 @@ lpfc_sli4_pci_mem_unset(struct lpfc_hba *phba) iounmap(phba->sli4_hba.conf_regs_memmap_p); if (phba->sli4_hba.dpp_regs_memmap_p) iounmap(phba->sli4_hba.dpp_regs_memmap_p); + if (phba->sli4_hba.dpp_regs_memmap_wc_p) + iounmap(phba->sli4_hba.dpp_regs_memmap_wc_p); break; case LPFC_SLI_INTF_IF_TYPE_1: break; diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index 1cbfbe44cb7c..303523f754b8 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -15977,6 +15977,32 @@ lpfc_dual_chute_pci_bar_map(struct lpfc_hba *phba, uint16_t pci_barset) return NULL; } +static __maybe_unused void __iomem * +lpfc_dpp_wc_map(struct lpfc_hba *phba, uint8_t dpp_barset) +{ + + /* DPP region is supposed to cover 64-bit BAR2 */ + if (dpp_barset != WQ_PCI_BAR_4_AND_5) { + lpfc_log_msg(phba, KERN_WARNING, LOG_INIT, + "3273 dpp_barset x%x != WQ_PCI_BAR_4_AND_5\n", + dpp_barset); + return NULL; + } + + if (!phba->sli4_hba.dpp_regs_memmap_wc_p) { + void __iomem *dpp_map; + + dpp_map = ioremap_wc(phba->pci_bar2_map, + pci_resource_len(phba->pcidev, + PCI_64BIT_BAR4)); + + if (dpp_map) + phba->sli4_hba.dpp_regs_memmap_wc_p = dpp_map; + } + + return phba->sli4_hba.dpp_regs_memmap_wc_p; +} + /** * lpfc_modify_hba_eq_delay - Modify Delay Multiplier on EQs * @phba: HBA structure that EQs are on. @@ -16940,9 +16966,6 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq, uint8_t dpp_barset; uint32_t dpp_offset; uint8_t wq_create_version; -#ifdef CONFIG_X86 - unsigned long pg_addr; -#endif /* sanity check on queue memory */ if (!wq || !cq) @@ -17128,14 +17151,15 @@ lpfc_wq_create(struct lpfc_hba *phba, struct lpfc_queue *wq, #ifdef CONFIG_X86 /* Enable combined writes for DPP aperture */ - pg_addr = (unsigned long)(wq->dpp_regaddr) & PAGE_MASK; - rc = set_memory_wc(pg_addr, 1); - if (rc) { + bar_memmap_p = lpfc_dpp_wc_map(phba, dpp_barset); + if (!bar_memmap_p) { lpfc_printf_log(phba, KERN_ERR, LOG_INIT, "3272 Cannot setup Combined " "Write on WQ[%d] - disable DPP\n", wq->queue_id); phba->cfg_enable_dpp = 0; + } else { + wq->dpp_regaddr = bar_memmap_p + dpp_offset; } #else phba->cfg_enable_dpp = 0; diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h index ee58383492b2..b6d90604bb61 100644 --- a/drivers/scsi/lpfc/lpfc_sli4.h +++ b/drivers/scsi/lpfc/lpfc_sli4.h @@ -785,6 +785,9 @@ struct lpfc_sli4_hba { void __iomem *dpp_regs_memmap_p; /* Kernel memory mapped address for * dpp registers */ + void __iomem *dpp_regs_memmap_wc_p;/* Kernel memory mapped address for + * dpp registers with write combining + */ union { struct { /* IF Type 0, BAR 0 PCI cfg space reg mem map */ diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 81150bef1145..5875065e2849 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -4807,21 +4807,25 @@ void mpi3mr_memset_buffers(struct mpi3mr_ioc *mrioc) } for (i = 0; i < mrioc->num_queues; i++) { - mrioc->op_reply_qinfo[i].qid = 0; - mrioc->op_reply_qinfo[i].ci = 0; - mrioc->op_reply_qinfo[i].num_replies = 0; - mrioc->op_reply_qinfo[i].ephase = 0; - atomic_set(&mrioc->op_reply_qinfo[i].pend_ios, 0); - atomic_set(&mrioc->op_reply_qinfo[i].in_use, 0); - mpi3mr_memset_op_reply_q_buffers(mrioc, i); - - mrioc->req_qinfo[i].ci = 0; - mrioc->req_qinfo[i].pi = 0; - mrioc->req_qinfo[i].num_requests = 0; - mrioc->req_qinfo[i].qid = 0; - mrioc->req_qinfo[i].reply_qid = 0; - spin_lock_init(&mrioc->req_qinfo[i].q_lock); - mpi3mr_memset_op_req_q_buffers(mrioc, i); + if (mrioc->op_reply_qinfo) { + mrioc->op_reply_qinfo[i].qid = 0; + mrioc->op_reply_qinfo[i].ci = 0; + mrioc->op_reply_qinfo[i].num_replies = 0; + mrioc->op_reply_qinfo[i].ephase = 0; + atomic_set(&mrioc->op_reply_qinfo[i].pend_ios, 0); + atomic_set(&mrioc->op_reply_qinfo[i].in_use, 0); + mpi3mr_memset_op_reply_q_buffers(mrioc, i); + } + + if (mrioc->req_qinfo) { + mrioc->req_qinfo[i].ci = 0; + mrioc->req_qinfo[i].pi = 0; + mrioc->req_qinfo[i].num_requests = 0; + mrioc->req_qinfo[i].qid = 0; + mrioc->req_qinfo[i].reply_qid = 0; + spin_lock_init(&mrioc->req_qinfo[i].q_lock); + mpi3mr_memset_op_req_q_buffers(mrioc, i); + } } atomic_set(&mrioc->pend_large_data_sz, 0); diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index 6a8d35aea93a..645524f3fe2d 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -525,8 +525,9 @@ int pm8001_queue_command(struct sas_task *task, gfp_t gfp_flags) } else { task->task_done(task); } - rc = -ENODEV; - goto err_out; + spin_unlock_irqrestore(&pm8001_ha->lock, flags); + pm8001_dbg(pm8001_ha, IO, "pm8001_task_exec device gone\n"); + return 0; } ccb = pm8001_ccb_alloc(pm8001_ha, pm8001_dev, task); diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 35101e9b7ba7..8e1686358e25 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -528,9 +528,8 @@ struct efd { }; static int ses_enclosure_find_by_addr(struct enclosure_device *edev, - void *data) + struct efd *efd) { - struct efd *efd = data; int i; struct ses_component *scomp; @@ -683,7 +682,7 @@ static void ses_match_to_enclosure(struct enclosure_device *edev, if (efd.addr) { efd.dev = &sdev->sdev_gendev; - enclosure_for_each_device(ses_enclosure_find_by_addr, &efd); + ses_enclosure_find_by_addr(edev, &efd); } } diff --git a/drivers/scsi/snic/vnic_dev.c b/drivers/scsi/snic/vnic_dev.c index c692de061f29..ed7771e62854 100644 --- a/drivers/scsi/snic/vnic_dev.c +++ b/drivers/scsi/snic/vnic_dev.c @@ -42,8 +42,6 @@ struct vnic_dev { struct vnic_devcmd_notify *notify; struct vnic_devcmd_notify notify_copy; dma_addr_t notify_pa; - u32 *linkstatus; - dma_addr_t linkstatus_pa; struct vnic_stats *stats; dma_addr_t stats_pa; struct vnic_devcmd_fw_info *fw_info; @@ -650,8 +648,6 @@ int svnic_dev_init(struct vnic_dev *vdev, int arg) int svnic_dev_link_status(struct vnic_dev *vdev) { - if (vdev->linkstatus) - return *vdev->linkstatus; if (!vnic_dev_notify_ready(vdev)) return 0; @@ -686,11 +682,6 @@ void svnic_dev_unregister(struct vnic_dev *vdev) sizeof(struct vnic_devcmd_notify), vdev->notify, vdev->notify_pa); - if (vdev->linkstatus) - dma_free_coherent(&vdev->pdev->dev, - sizeof(u32), - vdev->linkstatus, - vdev->linkstatus_pa); if (vdev->stats) dma_free_coherent(&vdev->pdev->dev, sizeof(struct vnic_stats), diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 664ad55728b5..ae1abab97835 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1856,8 +1856,9 @@ static enum scsi_qc_status storvsc_queuecommand(struct Scsi_Host *host, cmd_request->payload_sz = payload_sz; /* Invokes the vsc to start an IO */ - ret = storvsc_do_io(dev, cmd_request, get_cpu()); - put_cpu(); + migrate_disable(); + ret = storvsc_do_io(dev, cmd_request, smp_processor_id()); + migrate_enable(); if (ret) scsi_dma_unmap(scmnd); diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c index b99de8c4cc99..33f211e159ef 100644 --- a/drivers/spi/spi-stm32.c +++ b/drivers/spi/spi-stm32.c @@ -1625,6 +1625,9 @@ static int stm32_spi_prepare_rx_dma_mdma_chaining(struct stm32_spi *spi, return -EINVAL; } + *rx_mdma_desc = _mdma_desc; + *rx_dma_desc = _dma_desc; + return 0; } diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 847b55789bb8..899e663fea6e 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -24,6 +24,7 @@ #include <linux/pm_opp.h> #include <linux/regulator/consumer.h> #include <linux/sched/clock.h> +#include <linux/sizes.h> #include <linux/iopoll.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> @@ -517,8 +518,8 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, struct scsi_cmnd *cmd, if (hba->mcq_enabled) { struct ufs_hw_queue *hwq = ufshcd_mcq_req_to_hwq(hba, rq); - - hwq_id = hwq->id; + if (hwq) + hwq_id = hwq->id; } else { doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL); } @@ -4389,14 +4390,6 @@ out_unlock: spin_unlock_irqrestore(hba->host->host_lock, flags); mutex_unlock(&hba->uic_cmd_mutex); - /* - * If the h8 exit fails during the runtime resume process, it becomes - * stuck and cannot be recovered through the error handler. To fix - * this, use link recovery instead of the error handler. - */ - if (ret && hba->pm_op_in_progress) - ret = ufshcd_link_recovery(hba); - return ret; } @@ -5249,6 +5242,25 @@ static void ufshcd_lu_init(struct ufs_hba *hba, struct scsi_device *sdev) hba->dev_info.rpmb_region_size[1] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION1_SIZE]; hba->dev_info.rpmb_region_size[2] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION2_SIZE]; hba->dev_info.rpmb_region_size[3] = desc_buf[RPMB_UNIT_DESC_PARAM_REGION3_SIZE]; + + if (hba->dev_info.wspecversion <= 0x0220) { + /* + * These older spec chips have only one RPMB region, + * sized between 128 kB minimum and 16 MB maximum. + * No per region size fields are provided (respective + * REGIONX_SIZE fields always contain zeros), so get + * it from the logical block count and size fields for + * compatibility + * + * (See JESD220C-2_2 Section 14.1.4.6 + * RPMB Unit Descriptor,* offset 13h, 4 bytes) + */ + hba->dev_info.rpmb_region_size[0] = + (get_unaligned_be64(desc_buf + + RPMB_UNIT_DESC_PARAM_LOGICAL_BLK_COUNT) + << desc_buf[RPMB_UNIT_DESC_PARAM_LOGICAL_BLK_SIZE]) + / SZ_128K; + } } @@ -5963,6 +5975,7 @@ static int ufshcd_disable_auto_bkops(struct ufs_hba *hba) hba->auto_bkops_enabled = false; trace_ufshcd_auto_bkops_state(hba, "Disabled"); + hba->urgent_bkops_lvl = BKOPS_STATUS_PERF_IMPACT; hba->is_urgent_bkops_lvl_checked = false; out: return err; @@ -6066,7 +6079,7 @@ static void ufshcd_bkops_exception_event_handler(struct ufs_hba *hba) * impacted or critical. Handle these device by determining their urgent * bkops status at runtime. */ - if (curr_status < BKOPS_STATUS_PERF_IMPACT) { + if ((curr_status > BKOPS_STATUS_NO_OP) && (curr_status < BKOPS_STATUS_PERF_IMPACT)) { dev_err(hba->dev, "%s: device raised urgent BKOPS exception for bkops status %d\n", __func__, curr_status); /* update the current status as the urgent bkops level */ @@ -7097,7 +7110,7 @@ static irqreturn_t ufshcd_handle_mcq_cq_events(struct ufs_hba *hba) ret = ufshcd_vops_get_outstanding_cqs(hba, &outstanding_cqs); if (ret) - outstanding_cqs = (1U << hba->nr_hw_queues) - 1; + outstanding_cqs = (1ULL << hba->nr_hw_queues) - 1; /* Exclude the poll queues */ nr_queues = hba->nr_hw_queues - hba->nr_queues[HCTX_TYPE_POLL]; @@ -10179,7 +10192,15 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) } else { dev_err(hba->dev, "%s: hibern8 exit failed %d\n", __func__, ret); - goto vendor_suspend; + /* + * If the h8 exit fails during the runtime resume + * process, it becomes stuck and cannot be recovered + * through the error handler. To fix this, use link + * recovery instead of the error handler. + */ + ret = ufshcd_link_recovery(hba); + if (ret) + goto vendor_suspend; } } else if (ufshcd_is_link_off(hba)) { /* diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 8e89cc5b2820..fb857faaf0d6 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -47,6 +47,7 @@ #include <linux/dax.h> #include <linux/uaccess.h> #include <uapi/linux/rseq.h> +#include <linux/rseq.h> #include <asm/param.h> #include <asm/page.h> @@ -286,7 +287,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, } #ifdef CONFIG_RSEQ NEW_AUX_ENT(AT_RSEQ_FEATURE_SIZE, offsetof(struct rseq, end)); - NEW_AUX_ENT(AT_RSEQ_ALIGN, __alignof__(struct rseq)); + NEW_AUX_ENT(AT_RSEQ_ALIGN, rseq_alloc_align()); #endif #undef NEW_AUX_ENT /* AT_NULL is zero; clear the rest too */ diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c284f48cfae4..2a886bece810 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -3340,7 +3340,6 @@ again: btrfs_abort_transaction(trans, ret); goto out_put; } - WARN_ON(ret); /* We've already setup this transaction, go ahead and exit */ if (block_group->cache_generation == trans->transid && diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index d97bbbd045e0..56ff8afe9a22 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1657,7 +1657,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, if (unlikely(ret)) { btrfs_err(trans->fs_info, "failed to add delayed dir index item, root: %llu, inode: %llu, index: %llu, error: %d", - index, btrfs_root_id(node->root), node->inode_id, ret); + btrfs_root_id(node->root), node->inode_id, index, ret); btrfs_delayed_item_release_metadata(dir->root, item); btrfs_release_delayed_item(item); } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f6fa15a1193f..e4fad777b034 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1994,7 +1994,7 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, int level = btrfs_super_log_root_level(disk_super); if (unlikely(fs_devices->rw_devices == 0)) { - btrfs_warn(fs_info, "log replay required on RO media"); + btrfs_err(fs_info, "log replay required on RO media"); return -EIO; } @@ -2008,9 +2008,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, check.owner_root = BTRFS_TREE_LOG_OBJECTID; log_tree_root->node = read_tree_block(fs_info, bytenr, &check); if (IS_ERR(log_tree_root->node)) { - btrfs_warn(fs_info, "failed to read log tree"); ret = PTR_ERR(log_tree_root->node); log_tree_root->node = NULL; + btrfs_err(fs_info, "failed to read log tree with error: %d", ret); btrfs_put_root(log_tree_root); return ret; } @@ -2023,9 +2023,9 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info, /* returns with log_tree_root freed on success */ ret = btrfs_recover_log_trees(log_tree_root); btrfs_put_root(log_tree_root); - if (ret) { - btrfs_handle_fs_error(fs_info, ret, - "Failed to recover log tree"); + if (unlikely(ret)) { + ASSERT(BTRFS_FS_ERROR(fs_info) != 0); + btrfs_err(fs_info, "failed to recover log trees with error: %d", ret); return ret; } @@ -2972,7 +2972,6 @@ static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info) task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid"); if (IS_ERR(task)) { /* fs_info->update_uuid_tree_gen remains 0 in all error case */ - btrfs_warn(fs_info, "failed to start uuid_rescan task"); up(&fs_info->uuid_tree_rescan_sem); return PTR_ERR(task); } @@ -3188,7 +3187,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) if (incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP) { btrfs_err(fs_info, "cannot mount because of unknown incompat features (0x%llx)", - incompat); + incompat & ~BTRFS_FEATURE_INCOMPAT_SUPP); return -EINVAL; } @@ -3220,7 +3219,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) if (compat_ro_unsupp && is_rw_mount) { btrfs_err(fs_info, "cannot mount read-write because of unknown compat_ro features (0x%llx)", - compat_ro); + compat_ro_unsupp); return -EINVAL; } @@ -3233,7 +3232,7 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) !btrfs_test_opt(fs_info, NOLOGREPLAY)) { btrfs_err(fs_info, "cannot replay dirty log with unsupported compat_ro features (0x%llx), try rescue=nologreplay", - compat_ro); + compat_ro_unsupp); return -EINVAL; } @@ -3642,7 +3641,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true); if (IS_ERR(fs_info->fs_root)) { ret = PTR_ERR(fs_info->fs_root); - btrfs_warn(fs_info, "failed to read fs tree: %d", ret); + btrfs_err(fs_info, "failed to read fs tree: %d", ret); fs_info->fs_root = NULL; goto fail_qgroup; } @@ -3663,8 +3662,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device btrfs_info(fs_info, "checking UUID tree"); ret = btrfs_check_uuid_tree(fs_info); if (ret) { - btrfs_warn(fs_info, - "failed to check the UUID tree: %d", ret); + btrfs_err(fs_info, "failed to check the UUID tree: %d", ret); close_ctree(fs_info); return ret; } @@ -4399,9 +4397,17 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ btrfs_flush_workqueue(fs_info->delayed_workers); - ret = btrfs_commit_super(fs_info); - if (ret) - btrfs_err(fs_info, "commit super ret %d", ret); + /* + * If the filesystem is shutdown, then an attempt to commit the + * super block (or any write) will just fail. Since we freeze + * the filesystem before shutting it down, the filesystem is in + * a consistent state and we don't need to commit super blocks. + */ + if (!btrfs_is_shutdown(fs_info)) { + ret = btrfs_commit_super(fs_info); + if (ret) + btrfs_err(fs_info, "commit super block returned %d", ret); + } } kthread_stop(fs_info->transaction_kthread); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 03cf9f242c70..b0d9baf5b412 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2933,9 +2933,15 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans) while (!TRANS_ABORTED(trans) && cached_state) { struct extent_state *next_state; - if (btrfs_test_opt(fs_info, DISCARD_SYNC)) + if (btrfs_test_opt(fs_info, DISCARD_SYNC)) { ret = btrfs_discard_extent(fs_info, start, end + 1 - start, NULL, true); + if (ret) { + btrfs_warn(fs_info, + "discard failed for extent [%llu, %llu]: errno=%d %s", + start, end, ret, btrfs_decode_error(ret)); + } + } next_state = btrfs_next_extent_state(unpin, cached_state); btrfs_clear_extent_dirty(unpin, start, end, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6efb543f1c24..a11fcc9e9f50 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1392,10 +1392,25 @@ static int cow_one_range(struct btrfs_inode *inode, struct folio *locked_folio, return ret; free_reserved: + /* + * If we have reserved an extent for the current range and failed to + * create the respective extent map or ordered extent, it means that + * when we reserved the extent we decremented the extent's size from + * the data space_info's bytes_may_use counter and + * incremented the space_info's bytes_reserved counter by the same + * amount. + * + * We must make sure extent_clear_unlock_delalloc() does not try + * to decrement again the data space_info's bytes_may_use counter, which + * will be handled by btrfs_free_reserved_extent(). + * + * Therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV, but only + * EXTENT_CLEAR_META_RESV. + */ extent_clear_unlock_delalloc(inode, file_offset, cur_end, locked_folio, cached, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW | - EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, + EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV, PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK); btrfs_qgroup_free_data(inode, NULL, file_offset, cur_len, NULL); @@ -4764,7 +4779,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry) spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu with active swapfile", - btrfs_root_id(root)); + btrfs_root_id(dest)); ret = -EPERM; goto out_up_write; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index ae2173235c4d..a1fd44c44ecf 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4581,7 +4581,7 @@ static int btrfs_uring_read_extent(struct kiocb *iocb, struct iov_iter *iter, { struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp)); struct extent_io_tree *io_tree = &inode->io_tree; - struct page **pages; + struct page **pages = NULL; struct btrfs_uring_priv *priv = NULL; unsigned long nr_pages; int ret; @@ -4639,6 +4639,11 @@ out_fail: btrfs_unlock_extent(io_tree, start, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); kfree(priv); + for (int i = 0; i < nr_pages; i++) { + if (pages[i]) + __free_page(pages[i]); + } + kfree(pages); return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 3cdd9755dc52..3b2a6517d0b5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -370,7 +370,7 @@ static bool squota_check_parent_usage(struct btrfs_fs_info *fs_info, struct btrf nr_members++; } mismatch = (parent->excl != excl_sum || parent->rfer != rfer_sum || - parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != excl_cmpr_sum); + parent->excl_cmpr != excl_cmpr_sum || parent->rfer_cmpr != rfer_cmpr_sum); WARN(mismatch, "parent squota qgroup %hu/%llu has mismatched usage from its %d members. " diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 95db7c48fbad..a330d8624b83 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4723,6 +4723,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map, ret = btrfs_remove_dev_extents(trans, chunk_map); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); return ret; } @@ -4732,6 +4733,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map, if (unlikely(ret)) { mutex_unlock(&trans->fs_info->chunk_mutex); btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); return ret; } } @@ -4750,6 +4752,7 @@ int btrfs_last_identity_remap_gone(struct btrfs_chunk_map *chunk_map, ret = remove_chunk_stripes(trans, chunk_map, path); if (unlikely(ret)) { btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); return ret; } @@ -5982,6 +5985,9 @@ static int remove_range_from_remap_tree(struct btrfs_trans_handle *trans, struct btrfs_block_group *dest_bg; dest_bg = btrfs_lookup_block_group(fs_info, new_addr); + if (unlikely(!dest_bg)) + return -EUCLEAN; + adjust_block_group_remap_bytes(trans, dest_bg, -overlap_length); btrfs_put_block_group(dest_bg); ret = btrfs_add_to_free_space_tree(trans, diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 81022d912abb..bc94bbc00772 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -743,7 +743,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr btrfs_warn_rl(fs_info, "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU", logical, stripe->mirror_num, - header->fsid, fs_info->fs_devices->fsid); + header->fsid, fs_info->fs_devices->metadata_uuid); return; } if (memcmp(header->chunk_tree_uuid, fs_info->chunk_tree_uuid, diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 452394b34d01..ac4c4573ee39 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1740,7 +1740,7 @@ static int check_extent_data_ref(struct extent_buffer *leaf, objectid > BTRFS_LAST_FREE_OBJECTID)) { extent_err(leaf, slot, "invalid extent data backref objectid value %llu", - root); + objectid); return -EUCLEAN; } if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) { @@ -1921,7 +1921,7 @@ static int check_dev_extent_item(const struct extent_buffer *leaf, if (unlikely(prev_key->offset + prev_len > key->offset)) { generic_err(leaf, slot, "dev extent overlap, prev offset %llu len %llu current offset %llu", - prev_key->objectid, prev_len, key->offset); + prev_key->offset, prev_len, key->offset); return -EUCLEAN; } } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6fb0c4cd50ff..648bb09fc416 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6907,7 +6907,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, ret = btrfs_translate_remap(fs_info, &new_logical, length); if (ret) - return ret; + goto out; if (new_logical != logical) { btrfs_free_chunk_map(map); @@ -6921,8 +6921,10 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, } num_copies = btrfs_chunk_map_num_copies(map); - if (io_geom.mirror_num > num_copies) - return -EINVAL; + if (io_geom.mirror_num > num_copies) { + ret = -EINVAL; + goto out; + } map_offset = logical - map->start; io_geom.raid56_full_stripe_start = (u64)-1; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index bc82083e420a..00f0efaf12b2 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -80,18 +80,27 @@ static void iomap_set_range_uptodate(struct folio *folio, size_t off, { struct iomap_folio_state *ifs = folio->private; unsigned long flags; - bool uptodate = true; + bool mark_uptodate = true; if (folio_test_uptodate(folio)) return; if (ifs) { spin_lock_irqsave(&ifs->state_lock, flags); - uptodate = ifs_set_range_uptodate(folio, ifs, off, len); + /* + * If a read with bytes pending is in progress, we must not call + * folio_mark_uptodate(). The read completion path + * (iomap_read_end()) will call folio_end_read(), which uses XOR + * semantics to set the uptodate bit. If we set it here, the XOR + * in folio_end_read() will clear it, leaving the folio not + * uptodate. + */ + mark_uptodate = ifs_set_range_uptodate(folio, ifs, off, len) && + !ifs->read_bytes_pending; spin_unlock_irqrestore(&ifs->state_lock, flags); } - if (uptodate) + if (mark_uptodate) folio_mark_uptodate(folio); } diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 95254aa1b654..e911daedff65 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -87,6 +87,19 @@ static inline enum fserror_type iomap_dio_err_type(const struct iomap_dio *dio) return FSERR_DIRECTIO_READ; } +static inline bool should_report_dio_fserror(const struct iomap_dio *dio) +{ + switch (dio->error) { + case 0: + case -EAGAIN: + case -ENOTBLK: + /* don't send fsnotify for success or magic retry codes */ + return false; + default: + return true; + } +} + ssize_t iomap_dio_complete(struct iomap_dio *dio) { const struct iomap_dio_ops *dops = dio->dops; @@ -96,7 +109,7 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio) if (dops && dops->end_io) ret = dops->end_io(iocb, dio->size, ret, dio->flags); - if (dio->error) + if (should_report_dio_fserror(dio)) fserror_report_io(file_inode(iocb->ki_filp), iomap_dio_err_type(dio), offset, dio->size, dio->error, GFP_NOFS); diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c index 4d1ef8a2cee9..60546fa14dfe 100644 --- a/fs/iomap/ioend.c +++ b/fs/iomap/ioend.c @@ -215,17 +215,18 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, WARN_ON_ONCE(!folio->private && map_len < dirty_len); switch (wpc->iomap.type) { - case IOMAP_INLINE: - WARN_ON_ONCE(1); - return -EIO; + case IOMAP_UNWRITTEN: + ioend_flags |= IOMAP_IOEND_UNWRITTEN; + break; + case IOMAP_MAPPED: + break; case IOMAP_HOLE: return map_len; default: - break; + WARN_ON_ONCE(1); + return -EIO; } - if (wpc->iomap.type == IOMAP_UNWRITTEN) - ioend_flags |= IOMAP_IOEND_UNWRITTEN; if (wpc->iomap.flags & IOMAP_F_SHARED) ioend_flags |= IOMAP_IOEND_SHARED; if (folio_test_dropbehind(folio)) diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index a9d1c3b2c084..dd1451bf7543 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -10,6 +10,202 @@ #include "internal.h" /* + * Perform the cleanup rituals after an unbuffered write is complete. + */ +static void netfs_unbuffered_write_done(struct netfs_io_request *wreq) +{ + struct netfs_inode *ictx = netfs_inode(wreq->inode); + + _enter("R=%x", wreq->debug_id); + + /* Okay, declare that all I/O is complete. */ + trace_netfs_rreq(wreq, netfs_rreq_trace_write_done); + + if (!wreq->error) + netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); + + if (wreq->origin == NETFS_DIO_WRITE && + wreq->mapping->nrpages) { + /* mmap may have got underfoot and we may now have folios + * locally covering the region we just wrote. Attempt to + * discard the folios, but leave in place any modified locally. + * ->write_iter() is prevented from interfering by the DIO + * counter. + */ + pgoff_t first = wreq->start >> PAGE_SHIFT; + pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT; + + invalidate_inode_pages2_range(wreq->mapping, first, last); + } + + if (wreq->origin == NETFS_DIO_WRITE) + inode_dio_end(wreq->inode); + + _debug("finished"); + netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip); + /* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */ + + if (wreq->iocb) { + size_t written = umin(wreq->transferred, wreq->len); + + wreq->iocb->ki_pos += written; + if (wreq->iocb->ki_complete) { + trace_netfs_rreq(wreq, netfs_rreq_trace_ki_complete); + wreq->iocb->ki_complete(wreq->iocb, wreq->error ?: written); + } + wreq->iocb = VFS_PTR_POISON; + } + + netfs_clear_subrequests(wreq); +} + +/* + * Collect the subrequest results of unbuffered write subrequests. + */ +static void netfs_unbuffered_write_collect(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + struct netfs_io_subrequest *subreq) +{ + trace_netfs_collect_sreq(wreq, subreq); + + spin_lock(&wreq->lock); + list_del_init(&subreq->rreq_link); + spin_unlock(&wreq->lock); + + wreq->transferred += subreq->transferred; + iov_iter_advance(&wreq->buffer.iter, subreq->transferred); + + stream->collected_to = subreq->start + subreq->transferred; + wreq->collected_to = stream->collected_to; + netfs_put_subrequest(subreq, netfs_sreq_trace_put_done); + + trace_netfs_collect_stream(wreq, stream); + trace_netfs_collect_state(wreq, wreq->collected_to, 0); +} + +/* + * Write data to the server without going through the pagecache and without + * writing it to the local cache. We dispatch the subrequests serially and + * wait for each to complete before dispatching the next, lest we leave a gap + * in the data written due to a failure such as ENOSPC. We could, however + * attempt to do preparation such as content encryption for the next subreq + * whilst the current is in progress. + */ +static int netfs_unbuffered_write(struct netfs_io_request *wreq) +{ + struct netfs_io_subrequest *subreq = NULL; + struct netfs_io_stream *stream = &wreq->io_streams[0]; + int ret; + + _enter("%llx", wreq->len); + + if (wreq->origin == NETFS_DIO_WRITE) + inode_dio_begin(wreq->inode); + + stream->collected_to = wreq->start; + + for (;;) { + bool retry = false; + + if (!subreq) { + netfs_prepare_write(wreq, stream, wreq->start + wreq->transferred); + subreq = stream->construct; + stream->construct = NULL; + stream->front = NULL; + } + + /* Check if (re-)preparation failed. */ + if (unlikely(test_bit(NETFS_SREQ_FAILED, &subreq->flags))) { + netfs_write_subrequest_terminated(subreq, subreq->error); + wreq->error = subreq->error; + break; + } + + iov_iter_truncate(&subreq->io_iter, wreq->len - wreq->transferred); + if (!iov_iter_count(&subreq->io_iter)) + break; + + subreq->len = netfs_limit_iter(&subreq->io_iter, 0, + stream->sreq_max_len, + stream->sreq_max_segs); + iov_iter_truncate(&subreq->io_iter, subreq->len); + stream->submit_extendable_to = subreq->len; + + trace_netfs_sreq(subreq, netfs_sreq_trace_submit); + stream->issue_write(subreq); + + /* Async, need to wait. */ + netfs_wait_for_in_progress_stream(wreq, stream); + + if (test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) { + retry = true; + } else if (test_bit(NETFS_SREQ_FAILED, &subreq->flags)) { + ret = subreq->error; + wreq->error = ret; + netfs_see_subrequest(subreq, netfs_sreq_trace_see_failed); + subreq = NULL; + break; + } + ret = 0; + + if (!retry) { + netfs_unbuffered_write_collect(wreq, stream, subreq); + subreq = NULL; + if (wreq->transferred >= wreq->len) + break; + if (!wreq->iocb && signal_pending(current)) { + ret = wreq->transferred ? -EINTR : -ERESTARTSYS; + trace_netfs_rreq(wreq, netfs_rreq_trace_intr); + break; + } + continue; + } + + /* We need to retry the last subrequest, so first reset the + * iterator, taking into account what, if anything, we managed + * to transfer. + */ + subreq->error = -EAGAIN; + trace_netfs_sreq(subreq, netfs_sreq_trace_retry); + if (subreq->transferred > 0) + iov_iter_advance(&wreq->buffer.iter, subreq->transferred); + + if (stream->source == NETFS_UPLOAD_TO_SERVER && + wreq->netfs_ops->retry_request) + wreq->netfs_ops->retry_request(wreq, stream); + + __clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags); + __clear_bit(NETFS_SREQ_BOUNDARY, &subreq->flags); + __clear_bit(NETFS_SREQ_FAILED, &subreq->flags); + subreq->io_iter = wreq->buffer.iter; + subreq->start = wreq->start + wreq->transferred; + subreq->len = wreq->len - wreq->transferred; + subreq->transferred = 0; + subreq->retry_count += 1; + stream->sreq_max_len = UINT_MAX; + stream->sreq_max_segs = INT_MAX; + + netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit); + stream->prepare_write(subreq); + + __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); + netfs_stat(&netfs_n_wh_retry_write_subreq); + } + + netfs_unbuffered_write_done(wreq); + _leave(" = %d", ret); + return ret; +} + +static void netfs_unbuffered_write_async(struct work_struct *work) +{ + struct netfs_io_request *wreq = container_of(work, struct netfs_io_request, work); + + netfs_unbuffered_write(wreq); + netfs_put_request(wreq, netfs_rreq_trace_put_complete); +} + +/* * Perform an unbuffered write where we may have to do an RMW operation on an * encrypted file. This can also be used for direct I/O writes. */ @@ -70,35 +266,35 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter * */ wreq->buffer.iter = *iter; } + + wreq->len = iov_iter_count(&wreq->buffer.iter); } __set_bit(NETFS_RREQ_USE_IO_ITER, &wreq->flags); - if (async) - __set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags); /* Copy the data into the bounce buffer and encrypt it. */ // TODO /* Dispatch the write. */ __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags); - if (async) - wreq->iocb = iocb; - wreq->len = iov_iter_count(&wreq->buffer.iter); - ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len); - if (ret < 0) { - _debug("begin = %zd", ret); - goto out; - } - if (!async) { - ret = netfs_wait_for_write(wreq); - if (ret > 0) - iocb->ki_pos += ret; - } else { + if (async) { + INIT_WORK(&wreq->work, netfs_unbuffered_write_async); + wreq->iocb = iocb; + queue_work(system_dfl_wq, &wreq->work); ret = -EIOCBQUEUED; + } else { + ret = netfs_unbuffered_write(wreq); + if (ret < 0) { + _debug("begin = %zd", ret); + } else { + iocb->ki_pos += wreq->transferred; + ret = wreq->transferred ?: wreq->error; + } + + netfs_put_request(wreq, netfs_rreq_trace_put_complete); } -out: netfs_put_request(wreq, netfs_rreq_trace_put_return); return ret; diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index 4319611f5354..d436e20d3418 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -198,6 +198,9 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping, struct file *file, loff_t start, enum netfs_io_origin origin); +void netfs_prepare_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start); void netfs_reissue_write(struct netfs_io_stream *stream, struct netfs_io_subrequest *subreq, struct iov_iter *source); @@ -212,7 +215,6 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c struct folio **writethrough_cache); ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_control *wbc, struct folio *writethrough_cache); -int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len); /* * write_retry.c diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index 61eab34ea67e..83eb3dc1adf8 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -399,27 +399,6 @@ bool netfs_write_collection(struct netfs_io_request *wreq) ictx->ops->invalidate_cache(wreq); } - if ((wreq->origin == NETFS_UNBUFFERED_WRITE || - wreq->origin == NETFS_DIO_WRITE) && - !wreq->error) - netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred); - - if (wreq->origin == NETFS_DIO_WRITE && - wreq->mapping->nrpages) { - /* mmap may have got underfoot and we may now have folios - * locally covering the region we just wrote. Attempt to - * discard the folios, but leave in place any modified locally. - * ->write_iter() is prevented from interfering by the DIO - * counter. - */ - pgoff_t first = wreq->start >> PAGE_SHIFT; - pgoff_t last = (wreq->start + wreq->transferred - 1) >> PAGE_SHIFT; - invalidate_inode_pages2_range(wreq->mapping, first, last); - } - - if (wreq->origin == NETFS_DIO_WRITE) - inode_dio_end(wreq->inode); - _debug("finished"); netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip); /* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */ diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 34894da5a23e..437268f65640 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -154,9 +154,9 @@ EXPORT_SYMBOL(netfs_prepare_write_failed); * Prepare a write subrequest. We need to allocate a new subrequest * if we don't have one. */ -static void netfs_prepare_write(struct netfs_io_request *wreq, - struct netfs_io_stream *stream, - loff_t start) +void netfs_prepare_write(struct netfs_io_request *wreq, + struct netfs_io_stream *stream, + loff_t start) { struct netfs_io_subrequest *subreq; struct iov_iter *wreq_iter = &wreq->buffer.iter; @@ -699,41 +699,6 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c } /* - * Write data to the server without going through the pagecache and without - * writing it to the local cache. - */ -int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t len) -{ - struct netfs_io_stream *upload = &wreq->io_streams[0]; - ssize_t part; - loff_t start = wreq->start; - int error = 0; - - _enter("%zx", len); - - if (wreq->origin == NETFS_DIO_WRITE) - inode_dio_begin(wreq->inode); - - while (len) { - // TODO: Prepare content encryption - - _debug("unbuffered %zx", len); - part = netfs_advance_write(wreq, upload, start, len, false); - start += part; - len -= part; - rolling_buffer_advance(&wreq->buffer, part); - if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) - netfs_wait_for_paused_write(wreq); - if (test_bit(NETFS_RREQ_FAILED, &wreq->flags)) - break; - } - - netfs_end_issue_write(wreq); - _leave(" = %d", error); - return error; -} - -/* * Write some of a pending folio data back to the server and/or the cache. */ static int netfs_write_folio_single(struct netfs_io_request *wreq, diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index e9acd2cd602c..4cc8a58fa56a 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -377,15 +377,15 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) } /* - * write_threads - Start NFSD, or report the current number of running threads + * write_threads - Start NFSD, or report the configured number of threads * * Input: * buf: ignored * size: zero * Output: * On success: passed-in buffer filled with '\n'-terminated C - * string numeric value representing the number of - * running NFSD threads; + * string numeric value representing the configured + * number of NFSD threads; * return code is the size in bytes of the string * On error: return code is zero * @@ -399,8 +399,8 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) * Output: * On success: NFS service is started; * passed-in buffer filled with '\n'-terminated C - * string numeric value representing the number of - * running NFSD threads; + * string numeric value representing the configured + * number of NFSD threads; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ @@ -430,7 +430,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) } /* - * write_pool_threads - Set or report the current number of threads per pool + * write_pool_threads - Set or report the configured number of threads per pool * * Input: * buf: ignored @@ -447,7 +447,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) * Output: * On success: passed-in buffer filled with '\n'-terminated C * string containing integer values representing the - * number of NFSD threads in each pool; + * configured number of NFSD threads in each pool; * return code is the size in bytes of the string * On error: return code is zero or a negative errno value */ @@ -1647,7 +1647,7 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info) if (attr) nn->min_threads = nla_get_u32(attr); - ret = nfsd_svc(nrpools, nthreads, net, get_current_cred(), scope); + ret = nfsd_svc(nrpools, nthreads, net, current_cred(), scope); if (ret > 0) ret = 0; out_unlock: @@ -1657,7 +1657,7 @@ out_unlock: } /** - * nfsd_nl_threads_get_doit - get the number of running threads + * nfsd_nl_threads_get_doit - get the maximum number of running threads * @skb: reply buffer * @info: netlink metadata and command arguments * @@ -1700,7 +1700,7 @@ int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info) struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i]; err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, - sp->sp_nrthreads); + sp->sp_nrthrmax); if (err) goto err_unlock; } @@ -2000,7 +2000,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info) } ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0, - get_current_cred()); + current_cred()); /* always save the latest error */ if (ret < 0) err = ret; diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 0887ee601d3c..4a04208393b8 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -239,12 +239,13 @@ static void nfsd_net_free(struct percpu_ref *ref) int nfsd_nrthreads(struct net *net) { - int rv = 0; + int i, rv = 0; struct nfsd_net *nn = net_generic(net, nfsd_net_id); mutex_lock(&nfsd_mutex); if (nn->nfsd_serv) - rv = nn->nfsd_serv->sv_nrthreads; + for (i = 0; i < nn->nfsd_serv->sv_nrpools; ++i) + rv += nn->nfsd_serv->sv_pools[i].sp_nrthrmax; mutex_unlock(&nfsd_mutex); return rv; } @@ -659,7 +660,7 @@ int nfsd_get_nrthreads(int n, int *nthreads, struct net *net) if (serv) for (i = 0; i < serv->sv_nrpools && i < n; i++) - nthreads[i] = serv->sv_pools[i].sp_nrthreads; + nthreads[i] = serv->sv_pools[i].sp_nrthrmax; return 0; } diff --git a/fs/nsfs.c b/fs/nsfs.c index db91de208645..c215878d55e8 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -199,6 +199,17 @@ static bool nsfs_ioctl_valid(unsigned int cmd) return false; } +static bool may_use_nsfs_ioctl(unsigned int cmd) +{ + switch (_IOC_NR(cmd)) { + case _IOC_NR(NS_MNT_GET_NEXT): + fallthrough; + case _IOC_NR(NS_MNT_GET_PREV): + return may_see_all_namespaces(); + } + return true; +} + static long ns_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -214,6 +225,8 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, if (!nsfs_ioctl_valid(ioctl)) return -ENOIOCTLCMD; + if (!may_use_nsfs_ioctl(ioctl)) + return -EPERM; ns = get_proc_ns(file_inode(filp)); switch (ioctl) { @@ -614,7 +627,7 @@ static struct dentry *nsfs_fh_to_dentry(struct super_block *sb, struct fid *fh, return ERR_PTR(-EOPNOTSUPP); } - if (owning_ns && !ns_capable(owning_ns, CAP_SYS_ADMIN)) { + if (owning_ns && !may_see_all_namespaces()) { ns->ops->put(ns); return ERR_PTR(-EPERM); } diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index c327c246a9b4..04bb95091f49 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -118,7 +118,7 @@ static const char *path_no_prefix(struct cifs_sb_info *cifs_sb, if (!*path) return path; - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && + if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH) && cifs_sb->prepath) { len = strlen(cifs_sb->prepath) + 1; if (unlikely(len > strlen(path))) diff --git a/fs/smb/client/cifs_fs_sb.h b/fs/smb/client/cifs_fs_sb.h index 5e8d163cb5f8..84e7e366b0ff 100644 --- a/fs/smb/client/cifs_fs_sb.h +++ b/fs/smb/client/cifs_fs_sb.h @@ -55,7 +55,7 @@ struct cifs_sb_info { struct nls_table *local_nls; struct smb3_fs_context *ctx; atomic_t active; - unsigned int mnt_cifs_flags; + atomic_t mnt_cifs_flags; struct delayed_work prune_tlinks; struct rcu_head rcu; diff --git a/fs/smb/client/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h index b51ce64fcccf..147496ac9f9f 100644 --- a/fs/smb/client/cifs_ioctl.h +++ b/fs/smb/client/cifs_ioctl.h @@ -122,11 +122,3 @@ struct smb3_notify_info { #define CIFS_GOING_FLAGS_DEFAULT 0x0 /* going down */ #define CIFS_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */ #define CIFS_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */ - -static inline bool cifs_forced_shutdown(struct cifs_sb_info *sbi) -{ - if (CIFS_MOUNT_SHUTDOWN & sbi->mnt_cifs_flags) - return true; - else - return false; -} diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c index e7891b4406f2..e2edc207cef2 100644 --- a/fs/smb/client/cifs_unicode.c +++ b/fs/smb/client/cifs_unicode.c @@ -11,20 +11,6 @@ #include "cifsglob.h" #include "cifs_debug.h" -int cifs_remap(struct cifs_sb_info *cifs_sb) -{ - int map_type; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR) - map_type = SFM_MAP_UNI_RSVD; - else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR) - map_type = SFU_MAP_UNI_RSVD; - else - map_type = NO_MAP_UNI_RSVD; - - return map_type; -} - /* Convert character using the SFU - "Services for Unix" remapping range */ static bool convert_sfu_char(const __u16 src_char, char *target) diff --git a/fs/smb/client/cifs_unicode.h b/fs/smb/client/cifs_unicode.h index 9249db3b78c3..3e9cd9acf0a9 100644 --- a/fs/smb/client/cifs_unicode.h +++ b/fs/smb/client/cifs_unicode.h @@ -22,6 +22,7 @@ #include <linux/types.h> #include <linux/nls.h> #include "../../nls/nls_ucs2_utils.h" +#include "cifsglob.h" /* * Macs use an older "SFM" mapping of the symbols above. Fortunately it does @@ -65,10 +66,21 @@ char *cifs_strndup_from_utf16(const char *src, const int maxlen, const struct nls_table *codepage); int cifsConvertToUTF16(__le16 *target, const char *source, int srclen, const struct nls_table *cp, int map_chars); -int cifs_remap(struct cifs_sb_info *cifs_sb); __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len, const struct nls_table *cp, int remap); wchar_t cifs_toupper(wchar_t in); +static inline int cifs_remap(const struct cifs_sb_info *cifs_sb) +{ + unsigned int sbflags = cifs_sb_flags(cifs_sb); + + if (sbflags & CIFS_MOUNT_MAP_SFM_CHR) + return SFM_MAP_UNI_RSVD; + if (sbflags & CIFS_MOUNT_MAP_SPECIAL_CHR) + return SFU_MAP_UNI_RSVD; + + return NO_MAP_UNI_RSVD; +} + #endif /* _CIFS_UNICODE_H */ diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c index 6fa12c901c14..f4cb3018a358 100644 --- a/fs/smb/client/cifsacl.c +++ b/fs/smb/client/cifsacl.c @@ -356,7 +356,7 @@ sid_to_id(struct cifs_sb_info *cifs_sb, struct smb_sid *psid, psid->num_subauth, SID_MAX_SUB_AUTHORITIES); } - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) || + if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_UID_FROM_ACL) || (cifs_sb_master_tcon(cifs_sb)->posix_extensions)) { uint32_t unix_id; bool is_group; @@ -1612,7 +1612,8 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, struct smb_acl *dacl_ptr = NULL; struct smb_ntsd *pntsd = NULL; /* acl obtained from server */ struct smb_ntsd *pnntsd = NULL; /* modified acl to be sent to server */ - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); + unsigned int sbflags; struct tcon_link *tlink; struct smb_version_operations *ops; bool mode_from_sid, id_from_sid; @@ -1643,15 +1644,9 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode, return rc; } - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) - mode_from_sid = true; - else - mode_from_sid = false; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) - id_from_sid = true; - else - id_from_sid = false; + sbflags = cifs_sb_flags(cifs_sb); + mode_from_sid = sbflags & CIFS_MOUNT_MODE_FROM_SID; + id_from_sid = sbflags & CIFS_MOUNT_UID_FROM_ACL; /* Potentially, five new ACEs can be added to the ACL for U,G,O mapping */ if (pnmode && *pnmode != NO_CHANGE_64) { /* chmod */ diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 99b04234a08e..427558404aa5 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -226,16 +226,18 @@ cifs_sb_deactive(struct super_block *sb) static int cifs_read_super(struct super_block *sb) { - struct inode *inode; struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; + unsigned int sbflags; struct timespec64 ts; + struct inode *inode; int rc = 0; cifs_sb = CIFS_SB(sb); tcon = cifs_sb_master_tcon(cifs_sb); + sbflags = cifs_sb_flags(cifs_sb); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL) + if (sbflags & CIFS_MOUNT_POSIXACL) sb->s_flags |= SB_POSIXACL; if (tcon->snapshot_time) @@ -311,7 +313,7 @@ cifs_read_super(struct super_block *sb) } #ifdef CONFIG_CIFS_NFSD_EXPORT - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { + if (sbflags & CIFS_MOUNT_SERVER_INUM) { cifs_dbg(FYI, "export ops supported\n"); sb->s_export_op = &cifs_export_ops; } @@ -389,8 +391,7 @@ statfs_out: static long cifs_fallocate(struct file *file, int mode, loff_t off, loff_t len) { - struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); - struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + struct cifs_tcon *tcon = cifs_sb_master_tcon(CIFS_SB(file)); struct TCP_Server_Info *server = tcon->ses->server; struct inode *inode = file_inode(file); int rc; @@ -418,11 +419,9 @@ out_unlock: static int cifs_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { - struct cifs_sb_info *cifs_sb; + unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode)); - cifs_sb = CIFS_SB(inode->i_sb); - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) { + if (sbflags & CIFS_MOUNT_NO_PERM) { if ((mask & MAY_EXEC) && !execute_ok(inode)) return -EACCES; else @@ -568,15 +567,17 @@ cifs_show_security(struct seq_file *s, struct cifs_ses *ses) static void cifs_show_cache_flavor(struct seq_file *s, struct cifs_sb_info *cifs_sb) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); + seq_puts(s, ",cache="); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) + if (sbflags & CIFS_MOUNT_STRICT_IO) seq_puts(s, "strict"); - else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) + else if (sbflags & CIFS_MOUNT_DIRECT_IO) seq_puts(s, "none"); - else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE) + else if (sbflags & CIFS_MOUNT_RW_CACHE) seq_puts(s, "singleclient"); /* assume only one client access */ - else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) + else if (sbflags & CIFS_MOUNT_RO_CACHE) seq_puts(s, "ro"); /* read only caching assumed */ else seq_puts(s, "loose"); @@ -637,6 +638,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root) struct cifs_sb_info *cifs_sb = CIFS_SB(root->d_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct sockaddr *srcaddr; + unsigned int sbflags; + srcaddr = (struct sockaddr *)&tcon->ses->server->srcaddr; seq_show_option(s, "vers", tcon->ses->server->vals->version_string); @@ -670,16 +673,17 @@ cifs_show_options(struct seq_file *s, struct dentry *root) (int)(srcaddr->sa_family)); } + sbflags = cifs_sb_flags(cifs_sb); seq_printf(s, ",uid=%u", from_kuid_munged(&init_user_ns, cifs_sb->ctx->linux_uid)); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) + if (sbflags & CIFS_MOUNT_OVERR_UID) seq_puts(s, ",forceuid"); else seq_puts(s, ",noforceuid"); seq_printf(s, ",gid=%u", from_kgid_munged(&init_user_ns, cifs_sb->ctx->linux_gid)); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) + if (sbflags & CIFS_MOUNT_OVERR_GID) seq_puts(s, ",forcegid"); else seq_puts(s, ",noforcegid"); @@ -722,53 +726,53 @@ cifs_show_options(struct seq_file *s, struct dentry *root) seq_puts(s, ",unix"); else seq_puts(s, ",nounix"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) + if (sbflags & CIFS_MOUNT_NO_DFS) seq_puts(s, ",nodfs"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) + if (sbflags & CIFS_MOUNT_POSIX_PATHS) seq_puts(s, ",posixpaths"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) + if (sbflags & CIFS_MOUNT_SET_UID) seq_puts(s, ",setuids"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) + if (sbflags & CIFS_MOUNT_UID_FROM_ACL) seq_puts(s, ",idsfromsid"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) + if (sbflags & CIFS_MOUNT_SERVER_INUM) seq_puts(s, ",serverino"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) + if (sbflags & CIFS_MOUNT_RWPIDFORWARD) seq_puts(s, ",rwpidforward"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) + if (sbflags & CIFS_MOUNT_NOPOSIXBRL) seq_puts(s, ",forcemand"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) + if (sbflags & CIFS_MOUNT_NO_XATTR) seq_puts(s, ",nouser_xattr"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR) + if (sbflags & CIFS_MOUNT_MAP_SPECIAL_CHR) seq_puts(s, ",mapchars"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR) + if (sbflags & CIFS_MOUNT_MAP_SFM_CHR) seq_puts(s, ",mapposix"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) + if (sbflags & CIFS_MOUNT_UNX_EMUL) seq_puts(s, ",sfu"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) + if (sbflags & CIFS_MOUNT_NO_BRL) seq_puts(s, ",nobrl"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_HANDLE_CACHE) + if (sbflags & CIFS_MOUNT_NO_HANDLE_CACHE) seq_puts(s, ",nohandlecache"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) + if (sbflags & CIFS_MOUNT_MODE_FROM_SID) seq_puts(s, ",modefromsid"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) + if (sbflags & CIFS_MOUNT_CIFS_ACL) seq_puts(s, ",cifsacl"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) + if (sbflags & CIFS_MOUNT_DYNPERM) seq_puts(s, ",dynperm"); if (root->d_sb->s_flags & SB_POSIXACL) seq_puts(s, ",acl"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) + if (sbflags & CIFS_MOUNT_MF_SYMLINKS) seq_puts(s, ",mfsymlinks"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE) + if (sbflags & CIFS_MOUNT_FSCACHE) seq_puts(s, ",fsc"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC) + if (sbflags & CIFS_MOUNT_NOSSYNC) seq_puts(s, ",nostrictsync"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) + if (sbflags & CIFS_MOUNT_NO_PERM) seq_puts(s, ",noperm"); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID) + if (sbflags & CIFS_MOUNT_CIFS_BACKUPUID) seq_printf(s, ",backupuid=%u", from_kuid_munged(&init_user_ns, cifs_sb->ctx->backupuid)); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID) + if (sbflags & CIFS_MOUNT_CIFS_BACKUPGID) seq_printf(s, ",backupgid=%u", from_kgid_munged(&init_user_ns, cifs_sb->ctx->backupgid)); @@ -909,10 +913,10 @@ static int cifs_write_inode(struct inode *inode, struct writeback_control *wbc) static int cifs_drop_inode(struct inode *inode) { - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode)); /* no serverino => unconditional eviction */ - return !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) || + return !(sbflags & CIFS_MOUNT_SERVER_INUM) || inode_generic_drop(inode); } @@ -950,7 +954,7 @@ cifs_get_root(struct smb3_fs_context *ctx, struct super_block *sb) char *s, *p; char sep; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH) return dget(sb->s_root); full_path = cifs_build_path_to_root(ctx, cifs_sb, diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 080ea601c209..6f9b6c72962b 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -1580,24 +1580,59 @@ CIFS_I(struct inode *inode) return container_of(inode, struct cifsInodeInfo, netfs.inode); } -static inline struct cifs_sb_info * -CIFS_SB(struct super_block *sb) +static inline void *cinode_to_fsinfo(struct cifsInodeInfo *cinode) +{ + return cinode->netfs.inode.i_sb->s_fs_info; +} + +static inline void *super_to_fsinfo(struct super_block *sb) { return sb->s_fs_info; } -static inline struct cifs_sb_info * -CIFS_FILE_SB(struct file *file) +static inline void *inode_to_fsinfo(struct inode *inode) +{ + return inode->i_sb->s_fs_info; +} + +static inline void *file_to_fsinfo(struct file *file) +{ + return file_inode(file)->i_sb->s_fs_info; +} + +static inline void *dentry_to_fsinfo(struct dentry *dentry) +{ + return dentry->d_sb->s_fs_info; +} + +static inline void *const_dentry_to_fsinfo(const struct dentry *dentry) { - return CIFS_SB(file_inode(file)->i_sb); + return dentry->d_sb->s_fs_info; +} + +#define CIFS_SB(_ptr) \ + ((struct cifs_sb_info *) \ + _Generic((_ptr), \ + struct cifsInodeInfo * : cinode_to_fsinfo, \ + const struct dentry * : const_dentry_to_fsinfo, \ + struct super_block * : super_to_fsinfo, \ + struct dentry * : dentry_to_fsinfo, \ + struct inode * : inode_to_fsinfo, \ + struct file * : file_to_fsinfo)(_ptr)) + +/* + * Use atomic_t for @cifs_sb->mnt_cifs_flags as it is currently accessed + * locklessly and may be changed concurrently by mount/remount and reconnect + * paths. + */ +static inline unsigned int cifs_sb_flags(const struct cifs_sb_info *cifs_sb) +{ + return atomic_read(&cifs_sb->mnt_cifs_flags); } static inline char CIFS_DIR_SEP(const struct cifs_sb_info *cifs_sb) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) - return '/'; - else - return '\\'; + return (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS) ? '/' : '\\'; } static inline void @@ -2314,9 +2349,8 @@ static inline bool __cifs_cache_state_check(struct cifsInodeInfo *cinode, unsigned int oplock_flags, unsigned int sb_flags) { - struct cifs_sb_info *cifs_sb = CIFS_SB(cinode->netfs.inode.i_sb); + unsigned int sflags = cifs_sb_flags(CIFS_SB(cinode)); unsigned int oplock = READ_ONCE(cinode->oplock); - unsigned int sflags = cifs_sb->mnt_cifs_flags; return (oplock & oplock_flags) || (sflags & sb_flags); } @@ -2336,4 +2370,9 @@ static inline void cifs_reset_oplock(struct cifsInodeInfo *cinode) WRITE_ONCE(cinode->oplock, 0); } +static inline bool cifs_forced_shutdown(const struct cifs_sb_info *sbi) +{ + return cifs_sb_flags(sbi) & CIFS_MOUNT_SHUTDOWN; +} + #endif /* _CIFS_GLOB_H */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 33dfe116ca52..3bad2c5c523d 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -2167,9 +2167,6 @@ void __cifs_put_smb_ses(struct cifs_ses *ses) #ifdef CONFIG_KEYS -/* strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1 */ -#define CIFSCREDS_DESC_SIZE (7 + CIFS_MAX_DOMAINNAME_LEN + 1) - /* Populate username and pw fields from keyring if possible */ static int cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) @@ -2177,6 +2174,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) int rc = 0; int is_domain = 0; const char *delim, *payload; + size_t desc_sz; char *desc; ssize_t len; struct key *key; @@ -2185,7 +2183,9 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) struct sockaddr_in6 *sa6; const struct user_key_payload *upayload; - desc = kmalloc(CIFSCREDS_DESC_SIZE, GFP_KERNEL); + /* "cifs:a:" and "cifs:d:" are the same length; +1 for NUL terminator */ + desc_sz = strlen("cifs:a:") + CIFS_MAX_DOMAINNAME_LEN + 1; + desc = kmalloc(desc_sz, GFP_KERNEL); if (!desc) return -ENOMEM; @@ -2193,11 +2193,11 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) switch (server->dstaddr.ss_family) { case AF_INET: sa = (struct sockaddr_in *)&server->dstaddr; - sprintf(desc, "cifs:a:%pI4", &sa->sin_addr.s_addr); + snprintf(desc, desc_sz, "cifs:a:%pI4", &sa->sin_addr.s_addr); break; case AF_INET6: sa6 = (struct sockaddr_in6 *)&server->dstaddr; - sprintf(desc, "cifs:a:%pI6c", &sa6->sin6_addr.s6_addr); + snprintf(desc, desc_sz, "cifs:a:%pI6c", &sa6->sin6_addr.s6_addr); break; default: cifs_dbg(FYI, "Bad ss_family (%hu)\n", @@ -2216,7 +2216,7 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) } /* didn't work, try to find a domain key */ - sprintf(desc, "cifs:d:%s", ses->domainName); + snprintf(desc, desc_sz, "cifs:d:%s", ses->domainName); cifs_dbg(FYI, "%s: desc=%s\n", __func__, desc); key = request_key(&key_type_logon, desc, ""); if (IS_ERR(key)) { @@ -2236,7 +2236,6 @@ cifs_set_cifscreds(struct smb3_fs_context *ctx, struct cifs_ses *ses) /* find first : in payload */ payload = upayload->data; delim = strnchr(payload, upayload->datalen, ':'); - cifs_dbg(FYI, "payload=%s\n", payload); if (!delim) { cifs_dbg(FYI, "Unable to find ':' in payload (datalen=%d)\n", upayload->datalen); @@ -2915,8 +2914,8 @@ compare_mount_options(struct super_block *sb, struct cifs_mnt_data *mnt_data) { struct cifs_sb_info *old = CIFS_SB(sb); struct cifs_sb_info *new = mnt_data->cifs_sb; - unsigned int oldflags = old->mnt_cifs_flags & CIFS_MOUNT_MASK; - unsigned int newflags = new->mnt_cifs_flags & CIFS_MOUNT_MASK; + unsigned int oldflags = cifs_sb_flags(old) & CIFS_MOUNT_MASK; + unsigned int newflags = cifs_sb_flags(new) & CIFS_MOUNT_MASK; if ((sb->s_flags & CIFS_MS_MASK) != (mnt_data->flags & CIFS_MS_MASK)) return 0; @@ -2971,9 +2970,9 @@ static int match_prepath(struct super_block *sb, struct smb3_fs_context *ctx = mnt_data->ctx; struct cifs_sb_info *old = CIFS_SB(sb); struct cifs_sb_info *new = mnt_data->cifs_sb; - bool old_set = (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && + bool old_set = (cifs_sb_flags(old) & CIFS_MOUNT_USE_PREFIX_PATH) && old->prepath; - bool new_set = (new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) && + bool new_set = (cifs_sb_flags(new) & CIFS_MOUNT_USE_PREFIX_PATH) && new->prepath; if (tcon->origin_fullpath && @@ -3004,7 +3003,7 @@ cifs_match_super(struct super_block *sb, void *data) cifs_sb = CIFS_SB(sb); /* We do not want to use a superblock that has been shutdown */ - if (CIFS_MOUNT_SHUTDOWN & cifs_sb->mnt_cifs_flags) { + if (cifs_forced_shutdown(cifs_sb)) { spin_unlock(&cifs_tcp_ses_lock); return 0; } @@ -3469,6 +3468,8 @@ ip_connect(struct TCP_Server_Info *server) int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) { struct smb3_fs_context *ctx = cifs_sb->ctx; + unsigned int sbflags; + int rc = 0; INIT_DELAYED_WORK(&cifs_sb->prune_tlinks, cifs_prune_tlinks); INIT_LIST_HEAD(&cifs_sb->tcon_sb_link); @@ -3493,17 +3494,16 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) } ctx->local_nls = cifs_sb->local_nls; - smb3_update_mnt_flags(cifs_sb); + sbflags = smb3_update_mnt_flags(cifs_sb); if (ctx->direct_io) cifs_dbg(FYI, "mounting share using direct i/o\n"); if (ctx->cache_ro) { cifs_dbg(VFS, "mounting share with read only caching. Ensure that the share will not be modified while in use.\n"); - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RO_CACHE; + sbflags |= CIFS_MOUNT_RO_CACHE; } else if (ctx->cache_rw) { cifs_dbg(VFS, "mounting share in single client RW caching mode. Ensure that no other systems will be accessing the share.\n"); - cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_RO_CACHE | - CIFS_MOUNT_RW_CACHE); + sbflags |= CIFS_MOUNT_RO_CACHE | CIFS_MOUNT_RW_CACHE; } if ((ctx->cifs_acl) && (ctx->dynperm)) @@ -3512,16 +3512,19 @@ int cifs_setup_cifs_sb(struct cifs_sb_info *cifs_sb) if (ctx->prepath) { cifs_sb->prepath = kstrdup(ctx->prepath, GFP_KERNEL); if (cifs_sb->prepath == NULL) - return -ENOMEM; - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + rc = -ENOMEM; + else + sbflags |= CIFS_MOUNT_USE_PREFIX_PATH; } - return 0; + atomic_set(&cifs_sb->mnt_cifs_flags, sbflags); + return rc; } /* Release all succeed connections */ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) { + struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb; int rc = 0; if (mnt_ctx->tcon) @@ -3533,7 +3536,7 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx) mnt_ctx->ses = NULL; mnt_ctx->tcon = NULL; mnt_ctx->server = NULL; - mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS; + atomic_andnot(CIFS_MOUNT_POSIX_PATHS, &cifs_sb->mnt_cifs_flags); free_xid(mnt_ctx->xid); } @@ -3587,19 +3590,23 @@ out: int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx) { struct TCP_Server_Info *server; + struct cifs_tcon *tcon = NULL; struct cifs_sb_info *cifs_sb; struct smb3_fs_context *ctx; - struct cifs_tcon *tcon = NULL; + unsigned int sbflags; int rc = 0; - if (WARN_ON_ONCE(!mnt_ctx || !mnt_ctx->server || !mnt_ctx->ses || !mnt_ctx->fs_ctx || - !mnt_ctx->cifs_sb)) { - rc = -EINVAL; - goto out; + if (WARN_ON_ONCE(!mnt_ctx)) + return -EINVAL; + if (WARN_ON_ONCE(!mnt_ctx->server || !mnt_ctx->ses || + !mnt_ctx->fs_ctx || !mnt_ctx->cifs_sb)) { + mnt_ctx->tcon = NULL; + return -EINVAL; } server = mnt_ctx->server; ctx = mnt_ctx->fs_ctx; cifs_sb = mnt_ctx->cifs_sb; + sbflags = cifs_sb_flags(cifs_sb); /* search for existing tcon to this server share */ tcon = cifs_get_tcon(mnt_ctx->ses, ctx); @@ -3614,9 +3621,9 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx) * path (i.e., do not remap / and \ and do not map any special characters) */ if (tcon->posix_extensions) { - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS; - cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MAP_SFM_CHR | - CIFS_MOUNT_MAP_SPECIAL_CHR); + sbflags |= CIFS_MOUNT_POSIX_PATHS; + sbflags &= ~(CIFS_MOUNT_MAP_SFM_CHR | + CIFS_MOUNT_MAP_SPECIAL_CHR); } #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY @@ -3643,12 +3650,11 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx) /* do not care if a following call succeed - informational */ if (!tcon->pipe && server->ops->qfs_tcon) { server->ops->qfs_tcon(mnt_ctx->xid, tcon, cifs_sb); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RO_CACHE) { + if (sbflags & CIFS_MOUNT_RO_CACHE) { if (tcon->fsDevInfo.DeviceCharacteristics & cpu_to_le32(FILE_READ_ONLY_DEVICE)) cifs_dbg(VFS, "mounted to read only share\n"); - else if ((cifs_sb->mnt_cifs_flags & - CIFS_MOUNT_RW_CACHE) == 0) + else if (!(sbflags & CIFS_MOUNT_RW_CACHE)) cifs_dbg(VFS, "read only mount of RW share\n"); /* no need to log a RW mount of a typical RW share */ } @@ -3660,11 +3666,12 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx) * Inside cifs_fscache_get_super_cookie it checks * that we do not get super cookie twice. */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_FSCACHE) + if (sbflags & CIFS_MOUNT_FSCACHE) cifs_fscache_get_super_cookie(tcon); out: mnt_ctx->tcon = tcon; + atomic_set(&cifs_sb->mnt_cifs_flags, sbflags); return rc; } @@ -3783,7 +3790,8 @@ int cifs_is_path_remote(struct cifs_mount_ctx *mnt_ctx) cifs_sb, full_path, tcon->Flags & SMB_SHARE_IS_IN_DFS); if (rc != 0) { cifs_server_dbg(VFS, "cannot query dirs between root and final path, enabling CIFS_MOUNT_USE_PREFIX_PATH\n"); - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, + &cifs_sb->mnt_cifs_flags); rc = 0; } } @@ -3863,7 +3871,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx) * Force the use of prefix path to support failover on DFS paths that resolve to targets * that have different prefix paths. */ - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags); kfree(cifs_sb->prepath); cifs_sb->prepath = ctx->prepath; ctx->prepath = NULL; @@ -4357,7 +4365,7 @@ cifs_sb_tlink(struct cifs_sb_info *cifs_sb) kuid_t fsuid = current_fsuid(); int err; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER)) return cifs_get_tlink(cifs_sb_master_tlink(cifs_sb)); spin_lock(&cifs_sb->tlink_tree_lock); diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 983132735d72..83f8cf2f8d2b 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1333,7 +1333,7 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb) * Force the use of prefix path to support failover on DFS paths that resolve to targets * that have different prefix paths. */ - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags); refresh_tcon_referral(tcon, true); return 0; diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c index cb10088197d2..953f1fee8cb8 100644 --- a/fs/smb/client/dir.c +++ b/fs/smb/client/dir.c @@ -82,10 +82,11 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa const char *tree, int tree_len, bool prefix) { - int dfsplen; - int pplen = 0; - struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry); + unsigned int sbflags = cifs_sb_flags(cifs_sb); char dirsep = CIFS_DIR_SEP(cifs_sb); + int pplen = 0; + int dfsplen; char *s; if (unlikely(!page)) @@ -96,7 +97,7 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa else dfsplen = 0; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) + if (sbflags & CIFS_MOUNT_USE_PREFIX_PATH) pplen = cifs_sb->prepath ? strlen(cifs_sb->prepath) + 1 : 0; s = dentry_path_raw(direntry, page, PATH_MAX); @@ -123,7 +124,7 @@ char *__build_path_from_dentry_optional_prefix(struct dentry *direntry, void *pa if (dfsplen) { s -= dfsplen; memcpy(s, tree, dfsplen); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) { + if (sbflags & CIFS_MOUNT_POSIX_PATHS) { int i; for (i = 0; i < dfsplen; i++) { if (s[i] == '\\') @@ -152,7 +153,7 @@ char *build_path_from_dentry_optional_prefix(struct dentry *direntry, void *page static int check_name(struct dentry *direntry, struct cifs_tcon *tcon) { - struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(direntry); int i; if (unlikely(tcon->fsAttrInfo.MaxPathNameComponentLength && @@ -160,7 +161,7 @@ check_name(struct dentry *direntry, struct cifs_tcon *tcon) le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength))) return -ENAMETOOLONG; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS)) { for (i = 0; i < direntry->d_name.len; i++) { if (direntry->d_name.name[i] == '\\') { cifs_dbg(FYI, "Invalid file name\n"); @@ -181,11 +182,12 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned int rc = -ENOENT; int create_options = CREATE_NOT_DIR; int desired_access; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); struct cifs_tcon *tcon = tlink_tcon(tlink); const char *full_path; void *page = alloc_dentry_path(); struct inode *newinode = NULL; + unsigned int sbflags; int disposition; struct TCP_Server_Info *server = tcon->ses->server; struct cifs_open_parms oparms; @@ -365,6 +367,7 @@ retry_open: * If Open reported that we actually created a file then we now have to * set the mode if possible. */ + sbflags = cifs_sb_flags(cifs_sb); if ((tcon->unix_ext) && (*oplock & CIFS_CREATE_ACTION)) { struct cifs_unix_set_info_args args = { .mode = mode, @@ -374,7 +377,7 @@ retry_open: .device = 0, }; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { + if (sbflags & CIFS_MOUNT_SET_UID) { args.uid = current_fsuid(); if (inode->i_mode & S_ISGID) args.gid = inode->i_gid; @@ -411,9 +414,9 @@ cifs_create_get_file_info: if (server->ops->set_lease_key) server->ops->set_lease_key(newinode, fid); if ((*oplock & CIFS_CREATE_ACTION) && S_ISREG(newinode->i_mode)) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) + if (sbflags & CIFS_MOUNT_DYNPERM) newinode->i_mode = mode; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { + if (sbflags & CIFS_MOUNT_SET_UID) { newinode->i_uid = current_fsuid(); if (inode->i_mode & S_ISGID) newinode->i_gid = inode->i_gid; @@ -458,18 +461,20 @@ int cifs_atomic_open(struct inode *inode, struct dentry *direntry, struct file *file, unsigned int oflags, umode_t mode) { - int rc; - unsigned int xid; - struct tcon_link *tlink; - struct cifs_tcon *tcon; + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); + struct cifs_open_info_data buf = {}; struct TCP_Server_Info *server; - struct cifs_fid fid = {}; + struct cifsFileInfo *file_info; struct cifs_pending_open open; + struct cifs_fid fid = {}; + struct tcon_link *tlink; + struct cifs_tcon *tcon; + unsigned int sbflags; + unsigned int xid; __u32 oplock; - struct cifsFileInfo *file_info; - struct cifs_open_info_data buf = {}; + int rc; - if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb)))) + if (unlikely(cifs_forced_shutdown(cifs_sb))) return smb_EIO(smb_eio_trace_forced_shutdown); /* @@ -499,7 +504,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n", inode, direntry, direntry); - tlink = cifs_sb_tlink(CIFS_SB(inode->i_sb)); + tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) { rc = PTR_ERR(tlink); goto out_free_xid; @@ -536,13 +541,13 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, goto out; } - if (file->f_flags & O_DIRECT && - CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) { - if (CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) + sbflags = cifs_sb_flags(cifs_sb); + if ((file->f_flags & O_DIRECT) && (sbflags & CIFS_MOUNT_STRICT_IO)) { + if (sbflags & CIFS_MOUNT_NO_BRL) file->f_op = &cifs_file_direct_nobrl_ops; else file->f_op = &cifs_file_direct_ops; - } + } file_info = cifs_new_fileinfo(&fid, file, tlink, oplock, buf.symlink_target); if (file_info == NULL) { diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 18f31d4eb98d..f3ddcdf406c8 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -270,7 +270,7 @@ static void cifs_begin_writeback(struct netfs_io_request *wreq) static int cifs_init_request(struct netfs_io_request *rreq, struct file *file) { struct cifs_io_request *req = container_of(rreq, struct cifs_io_request, rreq); - struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode); struct cifsFileInfo *open_file = NULL; rreq->rsize = cifs_sb->ctx->rsize; @@ -281,7 +281,7 @@ static int cifs_init_request(struct netfs_io_request *rreq, struct file *file) open_file = file->private_data; rreq->netfs_priv = file->private_data; req->cfile = cifsFileInfo_get(open_file); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RWPIDFORWARD) req->pid = req->cfile->pid; } else if (rreq->origin != NETFS_WRITEBACK) { WARN_ON_ONCE(1); @@ -906,7 +906,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, * close because it may cause a error when we open this file * again and get at least level II oplock. */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_STRICT_IO) set_bit(CIFS_INO_INVALID_MAPPING, &cifsi->flags); cifs_set_oplock_level(cifsi, 0); } @@ -955,11 +955,11 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, int cifs_file_flush(const unsigned int xid, struct inode *inode, struct cifsFileInfo *cfile) { - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); struct cifs_tcon *tcon; int rc; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOSSYNC) return 0; if (cfile && (OPEN_FMODE(cfile->f_flags) & FMODE_WRITE)) { @@ -1015,24 +1015,24 @@ static int cifs_do_truncate(const unsigned int xid, struct dentry *dentry) int cifs_open(struct inode *inode, struct file *file) { + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); + struct cifs_open_info_data data = {}; + struct cifsFileInfo *cfile = NULL; + struct TCP_Server_Info *server; + struct cifs_pending_open open; + bool posix_open_ok = false; + struct cifs_fid fid = {}; + struct tcon_link *tlink; + struct cifs_tcon *tcon; + const char *full_path; + unsigned int sbflags; int rc = -EACCES; unsigned int xid; __u32 oplock; - struct cifs_sb_info *cifs_sb; - struct TCP_Server_Info *server; - struct cifs_tcon *tcon; - struct tcon_link *tlink; - struct cifsFileInfo *cfile = NULL; void *page; - const char *full_path; - bool posix_open_ok = false; - struct cifs_fid fid = {}; - struct cifs_pending_open open; - struct cifs_open_info_data data = {}; xid = get_xid(); - cifs_sb = CIFS_SB(inode->i_sb); if (unlikely(cifs_forced_shutdown(cifs_sb))) { free_xid(xid); return smb_EIO(smb_eio_trace_forced_shutdown); @@ -1056,9 +1056,9 @@ int cifs_open(struct inode *inode, struct file *file) cifs_dbg(FYI, "inode = 0x%p file flags are 0x%x for %s\n", inode, file->f_flags, full_path); - if (file->f_flags & O_DIRECT && - cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) + sbflags = cifs_sb_flags(cifs_sb); + if ((file->f_flags & O_DIRECT) && (sbflags & CIFS_MOUNT_STRICT_IO)) { + if (sbflags & CIFS_MOUNT_NO_BRL) file->f_op = &cifs_file_direct_nobrl_ops; else file->f_op = &cifs_file_direct_ops; @@ -1209,7 +1209,7 @@ cifs_relock_file(struct cifsFileInfo *cfile) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY - struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(cinode); #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING); @@ -1222,7 +1222,7 @@ cifs_relock_file(struct cifsFileInfo *cfile) #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) + ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0)) rc = cifs_push_posix_locks(cfile); else #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ @@ -2011,7 +2011,7 @@ cifs_push_locks(struct cifsFileInfo *cfile) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); int rc = 0; #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY - struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(cinode); #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ /* we are going to update can_cache_brlcks here - need a write access */ @@ -2024,7 +2024,7 @@ cifs_push_locks(struct cifsFileInfo *cfile) #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) + ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0)) rc = cifs_push_posix_locks(cfile); else #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ @@ -2428,11 +2428,11 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl) cifs_read_flock(fl, &type, &lock, &unlock, &wait_flag, tcon->ses->server); - cifs_sb = CIFS_FILE_SB(file); + cifs_sb = CIFS_SB(file); if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) + ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0)) posix_lck = true; if (!lock && !unlock) { @@ -2455,14 +2455,14 @@ int cifs_flock(struct file *file, int cmd, struct file_lock *fl) int cifs_lock(struct file *file, int cmd, struct file_lock *flock) { - int rc, xid; + struct cifs_sb_info *cifs_sb = CIFS_SB(file); + struct cifsFileInfo *cfile; int lock = 0, unlock = 0; bool wait_flag = false; bool posix_lck = false; - struct cifs_sb_info *cifs_sb; struct cifs_tcon *tcon; - struct cifsFileInfo *cfile; __u32 type; + int rc, xid; rc = -EACCES; xid = get_xid(); @@ -2477,12 +2477,11 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag, tcon->ses->server); - cifs_sb = CIFS_FILE_SB(file); set_bit(CIFS_INO_CLOSE_ON_LOCK, &CIFS_I(d_inode(cfile->dentry))->flags); if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) + ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0)) posix_lck = true; /* * BB add code here to normalize offset and length to account for @@ -2532,11 +2531,11 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, bool fsuid_only) { + struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode); struct cifsFileInfo *open_file = NULL; - struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb); /* only filter by fsuid on multiuser mounts */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER)) fsuid_only = false; spin_lock(&cifs_inode->open_file_lock); @@ -2589,10 +2588,10 @@ cifs_get_writable_file(struct cifsInodeInfo *cifs_inode, int flags, return rc; } - cifs_sb = CIFS_SB(cifs_inode->netfs.inode.i_sb); + cifs_sb = CIFS_SB(cifs_inode); /* only filter by fsuid on multiuser mounts */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MULTIUSER)) fsuid_only = false; spin_lock(&cifs_inode->open_file_lock); @@ -2787,7 +2786,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) struct TCP_Server_Info *server; struct cifsFileInfo *smbfile = file->private_data; struct inode *inode = file_inode(file); - struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); + struct cifs_sb_info *cifs_sb = CIFS_SB(file); rc = file_write_and_wait_range(file, start, end); if (rc) { @@ -2801,7 +2800,7 @@ int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) file, datasync); tcon = tlink_tcon(smbfile->tlink); - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) { + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOSSYNC)) { server = tcon->ses->server; if (server->ops->flush == NULL) { rc = -ENOSYS; @@ -2853,7 +2852,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file->f_mapping->host; struct cifsInodeInfo *cinode = CIFS_I(inode); struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); ssize_t rc; rc = netfs_start_io_write(inode); @@ -2870,7 +2869,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from) if (rc <= 0) goto out; - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) && + if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) && (cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from), server->vals->exclusive_lock_type, 0, NULL, CIFS_WRITE_OP))) { @@ -2893,7 +2892,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); struct cifsInodeInfo *cinode = CIFS_I(inode); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); struct cifsFileInfo *cfile = (struct cifsFileInfo *) iocb->ki_filp->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); @@ -2906,7 +2905,7 @@ cifs_strict_writev(struct kiocb *iocb, struct iov_iter *from) if (CIFS_CACHE_WRITE(cinode)) { if (cap_unix(tcon->ses) && (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && - ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) { + ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0)) { written = netfs_file_write_iter(iocb, from); goto out; } @@ -2994,7 +2993,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to) { struct inode *inode = file_inode(iocb->ki_filp); struct cifsInodeInfo *cinode = CIFS_I(inode); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); struct cifsFileInfo *cfile = (struct cifsFileInfo *) iocb->ki_filp->private_data; struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); @@ -3011,7 +3010,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to) if (!CIFS_CACHE_READ(cinode)) return netfs_unbuffered_read_iter(iocb, to); - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) { + if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NOPOSIXBRL) == 0) { if (iocb->ki_flags & IOCB_DIRECT) return netfs_unbuffered_read_iter(iocb, to); return netfs_buffered_read_iter(iocb, to); @@ -3130,10 +3129,9 @@ bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file, if (is_inode_writable(cifsInode) || ((cifsInode->oplock & CIFS_CACHE_RW_FLG) != 0 && from_readdir)) { /* This inode is open for write at least once */ - struct cifs_sb_info *cifs_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(cifsInode); - cifs_sb = CIFS_SB(cifsInode->netfs.inode.i_sb); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) { + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_DIRECT_IO) { /* since no page cache to corrupt on directio we can change size safely */ return true; @@ -3181,7 +3179,7 @@ void cifs_oplock_break(struct work_struct *work) server = tcon->ses->server; scoped_guard(spinlock, &cinode->open_file_lock) { - unsigned int sbflags = cifs_sb->mnt_cifs_flags; + unsigned int sbflags = cifs_sb_flags(cifs_sb); server->ops->downgrade_oplock(server, cinode, cfile->oplock_level, cfile->oplock_epoch, &purge_cache); diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index 09fe749e97ee..54090739535f 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -2062,161 +2062,160 @@ smb3_cleanup_fs_context(struct smb3_fs_context *ctx) kfree(ctx); } -void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb) +unsigned int smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct smb3_fs_context *ctx = cifs_sb->ctx; if (ctx->nodfs) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_DFS; + sbflags |= CIFS_MOUNT_NO_DFS; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_DFS; + sbflags &= ~CIFS_MOUNT_NO_DFS; if (ctx->noperm) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM; + sbflags |= CIFS_MOUNT_NO_PERM; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_PERM; + sbflags &= ~CIFS_MOUNT_NO_PERM; if (ctx->setuids) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SET_UID; + sbflags |= CIFS_MOUNT_SET_UID; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SET_UID; + sbflags &= ~CIFS_MOUNT_SET_UID; if (ctx->setuidfromacl) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UID_FROM_ACL; + sbflags |= CIFS_MOUNT_UID_FROM_ACL; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UID_FROM_ACL; + sbflags &= ~CIFS_MOUNT_UID_FROM_ACL; if (ctx->server_ino) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM; + sbflags |= CIFS_MOUNT_SERVER_INUM; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; + sbflags &= ~CIFS_MOUNT_SERVER_INUM; if (ctx->remap) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SFM_CHR; + sbflags |= CIFS_MOUNT_MAP_SFM_CHR; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SFM_CHR; + sbflags &= ~CIFS_MOUNT_MAP_SFM_CHR; if (ctx->sfu_remap) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SPECIAL_CHR; + sbflags |= CIFS_MOUNT_MAP_SPECIAL_CHR; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MAP_SPECIAL_CHR; + sbflags &= ~CIFS_MOUNT_MAP_SPECIAL_CHR; if (ctx->no_xattr) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_XATTR; + sbflags |= CIFS_MOUNT_NO_XATTR; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_XATTR; + sbflags &= ~CIFS_MOUNT_NO_XATTR; if (ctx->sfu_emul) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL; + sbflags |= CIFS_MOUNT_UNX_EMUL; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_UNX_EMUL; + sbflags &= ~CIFS_MOUNT_UNX_EMUL; if (ctx->nobrl) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL; + sbflags |= CIFS_MOUNT_NO_BRL; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_BRL; + sbflags &= ~CIFS_MOUNT_NO_BRL; if (ctx->nohandlecache) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_HANDLE_CACHE; + sbflags |= CIFS_MOUNT_NO_HANDLE_CACHE; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NO_HANDLE_CACHE; + sbflags &= ~CIFS_MOUNT_NO_HANDLE_CACHE; if (ctx->nostrictsync) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOSSYNC; + sbflags |= CIFS_MOUNT_NOSSYNC; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOSSYNC; + sbflags &= ~CIFS_MOUNT_NOSSYNC; if (ctx->mand_lock) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NOPOSIXBRL; + sbflags |= CIFS_MOUNT_NOPOSIXBRL; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_NOPOSIXBRL; + sbflags &= ~CIFS_MOUNT_NOPOSIXBRL; if (ctx->rwpidforward) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_RWPIDFORWARD; + sbflags |= CIFS_MOUNT_RWPIDFORWARD; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_RWPIDFORWARD; + sbflags &= ~CIFS_MOUNT_RWPIDFORWARD; if (ctx->mode_ace) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MODE_FROM_SID; + sbflags |= CIFS_MOUNT_MODE_FROM_SID; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MODE_FROM_SID; + sbflags &= ~CIFS_MOUNT_MODE_FROM_SID; if (ctx->cifs_acl) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL; + sbflags |= CIFS_MOUNT_CIFS_ACL; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_ACL; + sbflags &= ~CIFS_MOUNT_CIFS_ACL; if (ctx->backupuid_specified) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPUID; + sbflags |= CIFS_MOUNT_CIFS_BACKUPUID; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPUID; + sbflags &= ~CIFS_MOUNT_CIFS_BACKUPUID; if (ctx->backupgid_specified) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_BACKUPGID; + sbflags |= CIFS_MOUNT_CIFS_BACKUPGID; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_CIFS_BACKUPGID; + sbflags &= ~CIFS_MOUNT_CIFS_BACKUPGID; if (ctx->override_uid) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID; + sbflags |= CIFS_MOUNT_OVERR_UID; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_UID; + sbflags &= ~CIFS_MOUNT_OVERR_UID; if (ctx->override_gid) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_GID; + sbflags |= CIFS_MOUNT_OVERR_GID; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_OVERR_GID; + sbflags &= ~CIFS_MOUNT_OVERR_GID; if (ctx->dynperm) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM; + sbflags |= CIFS_MOUNT_DYNPERM; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DYNPERM; + sbflags &= ~CIFS_MOUNT_DYNPERM; if (ctx->fsc) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_FSCACHE; + sbflags |= CIFS_MOUNT_FSCACHE; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_FSCACHE; + sbflags &= ~CIFS_MOUNT_FSCACHE; if (ctx->multiuser) - cifs_sb->mnt_cifs_flags |= (CIFS_MOUNT_MULTIUSER | - CIFS_MOUNT_NO_PERM); + sbflags |= CIFS_MOUNT_MULTIUSER | CIFS_MOUNT_NO_PERM; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MULTIUSER; + sbflags &= ~CIFS_MOUNT_MULTIUSER; if (ctx->strict_io) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_STRICT_IO; + sbflags |= CIFS_MOUNT_STRICT_IO; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_STRICT_IO; + sbflags &= ~CIFS_MOUNT_STRICT_IO; if (ctx->direct_io) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO; + sbflags |= CIFS_MOUNT_DIRECT_IO; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_DIRECT_IO; + sbflags &= ~CIFS_MOUNT_DIRECT_IO; if (ctx->mfsymlinks) - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MF_SYMLINKS; + sbflags |= CIFS_MOUNT_MF_SYMLINKS; else - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_MF_SYMLINKS; - if (ctx->mfsymlinks) { - if (ctx->sfu_emul) { - /* - * Our SFU ("Services for Unix") emulation allows now - * creating new and reading existing SFU symlinks. - * Older Linux kernel versions were not able to neither - * read existing nor create new SFU symlinks. But - * creating and reading SFU style mknod and FIFOs was - * supported for long time. When "mfsymlinks" and - * "sfu" are both enabled at the same time, it allows - * reading both types of symlinks, but will only create - * them with mfsymlinks format. This allows better - * Apple compatibility, compatibility with older Linux - * kernel clients (probably better for Samba too) - * while still recognizing old Windows style symlinks. - */ - cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n"); - } - } - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SHUTDOWN; + sbflags &= ~CIFS_MOUNT_MF_SYMLINKS; - return; + if (ctx->mfsymlinks && ctx->sfu_emul) { + /* + * Our SFU ("Services for Unix") emulation allows now + * creating new and reading existing SFU symlinks. + * Older Linux kernel versions were not able to neither + * read existing nor create new SFU symlinks. But + * creating and reading SFU style mknod and FIFOs was + * supported for long time. When "mfsymlinks" and + * "sfu" are both enabled at the same time, it allows + * reading both types of symlinks, but will only create + * them with mfsymlinks format. This allows better + * Apple compatibility, compatibility with older Linux + * kernel clients (probably better for Samba too) + * while still recognizing old Windows style symlinks. + */ + cifs_dbg(VFS, "mount options mfsymlinks and sfu both enabled\n"); + } + sbflags &= ~CIFS_MOUNT_SHUTDOWN; + atomic_set(&cifs_sb->mnt_cifs_flags, sbflags); + return sbflags; } diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h index 49b2a6f09ca2..0b64fcb5d302 100644 --- a/fs/smb/client/fs_context.h +++ b/fs/smb/client/fs_context.h @@ -374,7 +374,7 @@ int smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx); int smb3_sync_session_ctx_passwords(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses); -void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); +unsigned int smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); /* * max deferred close timeout (jiffies) - 2^30 diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index d4d3cfeb6c90..3e844c55ab8a 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -40,32 +40,33 @@ static void cifs_set_netfs_context(struct inode *inode) static void cifs_set_ops(struct inode *inode) { - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); + struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct netfs_inode *ictx = netfs_inode(inode); + unsigned int sbflags = cifs_sb_flags(cifs_sb); switch (inode->i_mode & S_IFMT) { case S_IFREG: inode->i_op = &cifs_file_inode_ops; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) { + if (sbflags & CIFS_MOUNT_DIRECT_IO) { set_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) + if (sbflags & CIFS_MOUNT_NO_BRL) inode->i_fop = &cifs_file_direct_nobrl_ops; else inode->i_fop = &cifs_file_direct_ops; - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) + } else if (sbflags & CIFS_MOUNT_STRICT_IO) { + if (sbflags & CIFS_MOUNT_NO_BRL) inode->i_fop = &cifs_file_strict_nobrl_ops; else inode->i_fop = &cifs_file_strict_ops; - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_BRL) + } else if (sbflags & CIFS_MOUNT_NO_BRL) inode->i_fop = &cifs_file_nobrl_ops; else { /* not direct, send byte range locks */ inode->i_fop = &cifs_file_ops; } /* check if server can support readahead */ - if (cifs_sb_master_tcon(cifs_sb)->ses->server->max_read < - PAGE_SIZE + MAX_CIFS_HDR_SIZE) + if (tcon->ses->server->max_read < PAGE_SIZE + MAX_CIFS_HDR_SIZE) inode->i_data.a_ops = &cifs_addr_ops_smallbuf; else inode->i_data.a_ops = &cifs_addr_ops; @@ -194,8 +195,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, inode->i_gid = fattr->cf_gid; /* if dynperm is set, don't clobber existing mode */ - if (inode_state_read(inode) & I_NEW || - !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) + if ((inode_state_read(inode) & I_NEW) || + !(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_DYNPERM)) inode->i_mode = fattr->cf_mode; cifs_i->cifsAttrs = fattr->cf_cifsattrs; @@ -248,10 +249,8 @@ cifs_fill_uniqueid(struct super_block *sb, struct cifs_fattr *fattr) { struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) - return; - - fattr->cf_uniqueid = iunique(sb, ROOT_I); + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM)) + fattr->cf_uniqueid = iunique(sb, ROOT_I); } /* Fill a cifs_fattr struct with info from FILE_UNIX_BASIC_INFO. */ @@ -259,6 +258,8 @@ void cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info, struct cifs_sb_info *cifs_sb) { + unsigned int sbflags; + memset(fattr, 0, sizeof(*fattr)); fattr->cf_uniqueid = le64_to_cpu(info->UniqueId); fattr->cf_bytes = le64_to_cpu(info->NumOfBytes); @@ -317,8 +318,9 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info, break; } + sbflags = cifs_sb_flags(cifs_sb); fattr->cf_uid = cifs_sb->ctx->linux_uid; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)) { + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) { u64 id = le64_to_cpu(info->Uid); if (id < ((uid_t)-1)) { kuid_t uid = make_kuid(&init_user_ns, id); @@ -328,7 +330,7 @@ cifs_unix_basic_to_fattr(struct cifs_fattr *fattr, FILE_UNIX_BASIC_INFO *info, } fattr->cf_gid = cifs_sb->ctx->linux_gid; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) { + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) { u64 id = le64_to_cpu(info->Gid); if (id < ((gid_t)-1)) { kgid_t gid = make_kgid(&init_user_ns, id); @@ -382,7 +384,7 @@ static int update_inode_info(struct super_block *sb, * * If file type or uniqueid is different, return error. */ - if (unlikely((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) && + if (unlikely((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM) && CIFS_I(*inode)->uniqueid != fattr->cf_uniqueid)) { CIFS_I(*inode)->time = 0; /* force reval */ return -ESTALE; @@ -468,7 +470,7 @@ static int cifs_get_unix_fattr(const unsigned char *full_path, cifs_fill_uniqueid(sb, fattr); /* check for Minshall+French symlinks */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MF_SYMLINKS) { tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path); cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc); } @@ -1081,7 +1083,7 @@ cifs_backup_query_path_info(int xid, else if ((tcon->ses->capabilities & tcon->ses->server->vals->cap_nt_find) == 0) info.info_level = SMB_FIND_FILE_INFO_STANDARD; - else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) + else if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM) info.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; else /* no srvino useful for fallback to some netapp */ info.info_level = SMB_FIND_FILE_DIRECTORY_INFO; @@ -1109,7 +1111,7 @@ static void cifs_set_fattr_ino(int xid, struct cifs_tcon *tcon, struct super_blo struct TCP_Server_Info *server = tcon->ses->server; int rc; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) { + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM)) { if (*inode) fattr->cf_uniqueid = CIFS_I(*inode)->uniqueid; else @@ -1263,14 +1265,15 @@ static int cifs_get_fattr(struct cifs_open_info_data *data, struct inode **inode, const char *full_path) { + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_open_info_data tmp_data = {}; - struct cifs_tcon *tcon; + void *smb1_backup_rsp_buf = NULL; struct TCP_Server_Info *server; + struct cifs_tcon *tcon; struct tcon_link *tlink; - struct cifs_sb_info *cifs_sb = CIFS_SB(sb); - void *smb1_backup_rsp_buf = NULL; - int rc = 0; + unsigned int sbflags; int tmprc = 0; + int rc = 0; tlink = cifs_sb_tlink(cifs_sb); if (IS_ERR(tlink)) @@ -1370,16 +1373,17 @@ static int cifs_get_fattr(struct cifs_open_info_data *data, #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY handle_mnt_opt: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ + sbflags = cifs_sb_flags(cifs_sb); /* query for SFU type info if supported and needed */ if ((fattr->cf_cifsattrs & ATTR_SYSTEM) && - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) { + (sbflags & CIFS_MOUNT_UNX_EMUL)) { tmprc = cifs_sfu_type(fattr, full_path, cifs_sb, xid); if (tmprc) cifs_dbg(FYI, "cifs_sfu_type failed: %d\n", tmprc); } /* fill in 0777 bits from ACL */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) { + if (sbflags & CIFS_MOUNT_MODE_FROM_SID) { rc = cifs_acl_to_fattr(cifs_sb, fattr, *inode, true, full_path, fid); if (rc == -EREMOTE) @@ -1389,7 +1393,7 @@ handle_mnt_opt: __func__, rc); goto out; } - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) { + } else if (sbflags & CIFS_MOUNT_CIFS_ACL) { rc = cifs_acl_to_fattr(cifs_sb, fattr, *inode, false, full_path, fid); if (rc == -EREMOTE) @@ -1399,7 +1403,7 @@ handle_mnt_opt: __func__, rc); goto out; } - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) + } else if (sbflags & CIFS_MOUNT_UNX_EMUL) /* fill in remaining high mode bits e.g. SUID, VTX */ cifs_sfu_mode(fattr, full_path, cifs_sb, xid); else if (!(tcon->posix_extensions)) @@ -1409,7 +1413,7 @@ handle_mnt_opt: /* check for Minshall+French symlinks */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + if (sbflags & CIFS_MOUNT_MF_SYMLINKS) { tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path); cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc); } @@ -1509,7 +1513,7 @@ static int smb311_posix_get_fattr(struct cifs_open_info_data *data, * 3. Tweak fattr based on mount options */ /* check for Minshall+French symlinks */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_MF_SYMLINKS) { tmprc = check_mf_symlink(xid, tcon, cifs_sb, fattr, full_path); cifs_dbg(FYI, "check_mf_symlink: %d\n", tmprc); } @@ -1660,7 +1664,7 @@ struct inode *cifs_root_iget(struct super_block *sb) int len; int rc; - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) + if ((cifs_sb_flags(cifs_sb) & CIFS_MOUNT_USE_PREFIX_PATH) && cifs_sb->prepath) { len = strlen(cifs_sb->prepath); path = kzalloc(len + 2 /* leading sep + null */, GFP_KERNEL); @@ -2098,8 +2102,9 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, const char *full_path, struct cifs_sb_info *cifs_sb, struct cifs_tcon *tcon, const unsigned int xid) { - int rc = 0; struct inode *inode = NULL; + unsigned int sbflags; + int rc = 0; if (tcon->posix_extensions) { rc = smb311_posix_get_inode_info(&inode, full_path, @@ -2139,6 +2144,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, if (parent->i_mode & S_ISGID) mode |= S_ISGID; + sbflags = cifs_sb_flags(cifs_sb); #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY if (tcon->unix_ext) { struct cifs_unix_set_info_args args = { @@ -2148,7 +2154,7 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, .mtime = NO_CHANGE_64, .device = 0, }; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { + if (sbflags & CIFS_MOUNT_SET_UID) { args.uid = current_fsuid(); if (parent->i_mode & S_ISGID) args.gid = parent->i_gid; @@ -2166,14 +2172,14 @@ cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, { #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ struct TCP_Server_Info *server = tcon->ses->server; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) && + if (!(sbflags & CIFS_MOUNT_CIFS_ACL) && (mode & S_IWUGO) == 0 && server->ops->mkdir_setinfo) server->ops->mkdir_setinfo(inode, full_path, cifs_sb, tcon, xid); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) + if (sbflags & CIFS_MOUNT_DYNPERM) inode->i_mode = (mode | S_IFDIR); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { + if (sbflags & CIFS_MOUNT_SET_UID) { inode->i_uid = current_fsuid(); if (inode->i_mode & S_ISGID) inode->i_gid = parent->i_gid; @@ -2686,7 +2692,7 @@ cifs_dentry_needs_reval(struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct cifsInodeInfo *cifs_i = CIFS_I(inode); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct cached_fid *cfid = NULL; @@ -2727,7 +2733,7 @@ cifs_dentry_needs_reval(struct dentry *dentry) } /* hardlinked files w/ noserverino get "special" treatment */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) && + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM) && S_ISREG(inode->i_mode) && inode->i_nlink != 1) return true; @@ -2752,10 +2758,10 @@ cifs_wait_bit_killable(struct wait_bit_key *key, int mode) int cifs_revalidate_mapping(struct inode *inode) { - int rc; struct cifsInodeInfo *cifs_inode = CIFS_I(inode); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); unsigned long *flags = &cifs_inode->flags; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + int rc; /* swapfiles are not supposed to be shared */ if (IS_SWAPFILE(inode)) @@ -2768,7 +2774,7 @@ cifs_revalidate_mapping(struct inode *inode) if (test_and_clear_bit(CIFS_INO_INVALID_MAPPING, flags)) { /* for cache=singleclient, do not invalidate */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RW_CACHE) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RW_CACHE) goto skip_invalidate; cifs_inode->netfs.zero_point = cifs_inode->netfs.remote_i_size; @@ -2892,10 +2898,11 @@ int cifs_revalidate_dentry(struct dentry *dentry) int cifs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int flags) { - struct dentry *dentry = path->dentry; - struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(path->dentry); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); + struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); + unsigned int sbflags; int rc; if (unlikely(cifs_forced_shutdown(CIFS_SB(inode->i_sb)))) @@ -2952,12 +2959,13 @@ int cifs_getattr(struct mnt_idmap *idmap, const struct path *path, * enabled, and the admin hasn't overridden them, set the ownership * to the fsuid/fsgid of the current process. */ - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER) && - !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) && + sbflags = cifs_sb_flags(cifs_sb); + if ((sbflags & CIFS_MOUNT_MULTIUSER) && + !(sbflags & CIFS_MOUNT_CIFS_ACL) && !tcon->unix_ext) { - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)) + if (!(sbflags & CIFS_MOUNT_OVERR_UID)) stat->uid = current_fsuid(); - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)) + if (!(sbflags & CIFS_MOUNT_OVERR_GID)) stat->gid = current_fsgid(); } return 0; @@ -3102,7 +3110,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) void *page = alloc_dentry_path(); struct inode *inode = d_inode(direntry); struct cifsInodeInfo *cifsInode = CIFS_I(inode); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); struct tcon_link *tlink; struct cifs_tcon *pTcon; struct cifs_unix_set_info_args *args = NULL; @@ -3113,7 +3121,7 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) xid = get_xid(); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs); @@ -3266,26 +3274,26 @@ out: static int cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) { - unsigned int xid; - kuid_t uid = INVALID_UID; - kgid_t gid = INVALID_GID; struct inode *inode = d_inode(direntry); - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cifsInode = CIFS_I(inode); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct cifsFileInfo *cfile = NULL; - const char *full_path; void *page = alloc_dentry_path(); - int rc = -EACCES; - __u32 dosattr = 0; __u64 mode = NO_CHANGE_64; - bool posix = cifs_sb_master_tcon(cifs_sb)->posix_extensions; + kuid_t uid = INVALID_UID; + kgid_t gid = INVALID_GID; + const char *full_path; + __u32 dosattr = 0; + int rc = -EACCES; + unsigned int xid; xid = get_xid(); cifs_dbg(FYI, "setattr on file %pd attrs->ia_valid 0x%x\n", direntry, attrs->ia_valid); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) + if (sbflags & CIFS_MOUNT_NO_PERM) attrs->ia_valid |= ATTR_FORCE; rc = setattr_prepare(&nop_mnt_idmap, direntry, attrs); @@ -3346,8 +3354,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (attrs->ia_valid & ATTR_GID) gid = attrs->ia_gid; - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) || - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)) { + if (sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) { if (uid_valid(uid) || gid_valid(gid)) { mode = NO_CHANGE_64; rc = id_mode_to_cifs_acl(inode, full_path, &mode, @@ -3358,9 +3365,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) goto cifs_setattr_exit; } } - } else - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) + } else if (!(sbflags & CIFS_MOUNT_SET_UID)) { attrs->ia_valid &= ~(ATTR_UID | ATTR_GID); + } /* skip mode change if it's just for clearing setuid/setgid */ if (attrs->ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) @@ -3369,9 +3376,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) if (attrs->ia_valid & ATTR_MODE) { mode = attrs->ia_mode; rc = 0; - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) || - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) || - posix) { + if ((sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) || + cifs_sb_master_tcon(cifs_sb)->posix_extensions) { rc = id_mode_to_cifs_acl(inode, full_path, &mode, INVALID_UID, INVALID_GID); if (rc) { @@ -3393,7 +3399,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) dosattr = cifsInode->cifsAttrs | ATTR_READONLY; /* fix up mode if we're not using dynperm */ - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM) == 0) + if ((sbflags & CIFS_MOUNT_DYNPERM) == 0) attrs->ia_mode = inode->i_mode & ~S_IWUGO; } else if ((mode & S_IWUGO) && (cifsInode->cifsAttrs & ATTR_READONLY)) { @@ -3404,7 +3410,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) dosattr |= ATTR_NORMAL; /* reset local inode permissions to normal */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) { + if (!(sbflags & CIFS_MOUNT_DYNPERM)) { attrs->ia_mode &= ~(S_IALLUGO); if (S_ISDIR(inode->i_mode)) attrs->ia_mode |= @@ -3413,7 +3419,7 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) attrs->ia_mode |= cifs_sb->ctx->file_mode; } - } else if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DYNPERM)) { + } else if (!(sbflags & CIFS_MOUNT_DYNPERM)) { /* ignore mode change - ATTR_READONLY hasn't changed */ attrs->ia_valid &= ~ATTR_MODE; } diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 8dc2651e237f..9afab3237e54 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -216,7 +216,7 @@ static int cifs_shutdown(struct super_block *sb, unsigned long arg) */ case CIFS_GOING_FLAGS_LOGFLUSH: case CIFS_GOING_FLAGS_NOLOGFLUSH: - sbi->mnt_cifs_flags |= CIFS_MOUNT_SHUTDOWN; + atomic_or(CIFS_MOUNT_SHUTDOWN, &sbi->mnt_cifs_flags); goto shutdown_good; default: rc = -EINVAL; diff --git a/fs/smb/client/link.c b/fs/smb/client/link.c index a2f7bfa8ad1e..434e8fe74080 100644 --- a/fs/smb/client/link.c +++ b/fs/smb/client/link.c @@ -544,14 +544,15 @@ int cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, struct dentry *direntry, const char *symname) { - int rc = -EOPNOTSUPP; - unsigned int xid; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); + struct inode *newinode = NULL; struct tcon_link *tlink; struct cifs_tcon *pTcon; const char *full_path; + int rc = -EOPNOTSUPP; + unsigned int sbflags; + unsigned int xid; void *page; - struct inode *newinode = NULL; if (unlikely(cifs_forced_shutdown(cifs_sb))) return smb_EIO(smb_eio_trace_forced_shutdown); @@ -580,6 +581,7 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, cifs_dbg(FYI, "symname is %s\n", symname); /* BB what if DFS and this volume is on different share? BB */ + sbflags = cifs_sb_flags(cifs_sb); rc = -EOPNOTSUPP; switch (cifs_symlink_type(cifs_sb)) { case CIFS_SYMLINK_TYPE_UNIX: @@ -594,14 +596,14 @@ cifs_symlink(struct mnt_idmap *idmap, struct inode *inode, break; case CIFS_SYMLINK_TYPE_MFSYMLINKS: - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) { + if (sbflags & CIFS_MOUNT_MF_SYMLINKS) { rc = create_mf_symlink(xid, pTcon, cifs_sb, full_path, symname); } break; case CIFS_SYMLINK_TYPE_SFU: - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { + if (sbflags & CIFS_MOUNT_UNX_EMUL) { rc = __cifs_sfu_make_node(xid, inode, direntry, pTcon, full_path, S_IFLNK, 0, symname); diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c index 22cde46309fe..bc24c92b8b95 100644 --- a/fs/smb/client/misc.c +++ b/fs/smb/client/misc.c @@ -275,13 +275,15 @@ dump_smb(void *buf, int smb_buf_length) void cifs_autodisable_serverino(struct cifs_sb_info *cifs_sb) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); + + if (sbflags & CIFS_MOUNT_SERVER_INUM) { struct cifs_tcon *tcon = NULL; if (cifs_sb->master_tlink) tcon = cifs_sb_master_tcon(cifs_sb); - cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_SERVER_INUM; + atomic_andnot(CIFS_MOUNT_SERVER_INUM, &cifs_sb->mnt_cifs_flags); cifs_sb->mnt_cifs_serverino_autodisabled = true; cifs_dbg(VFS, "Autodisabling the use of server inode numbers on %s\n", tcon ? tcon->tree_name : "new server"); @@ -382,11 +384,13 @@ void cifs_done_oplock_break(struct cifsInodeInfo *cinode) bool backup_cred(struct cifs_sb_info *cifs_sb) { - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPUID) { + unsigned int sbflags = cifs_sb_flags(cifs_sb); + + if (sbflags & CIFS_MOUNT_CIFS_BACKUPUID) { if (uid_eq(cifs_sb->ctx->backupuid, current_fsuid())) return true; } - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_BACKUPGID) { + if (sbflags & CIFS_MOUNT_CIFS_BACKUPGID) { if (in_group_p(cifs_sb->ctx->backupgid)) return true; } @@ -955,7 +959,7 @@ int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix) convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb)); } - cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH; + atomic_or(CIFS_MOUNT_USE_PREFIX_PATH, &cifs_sb->mnt_cifs_flags); return 0; } @@ -984,7 +988,7 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid, * look up or tcon is not DFS. */ if (strlen(full_path) < 2 || !cifs_sb || - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS) || + (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_DFS) || !is_tcon_dfs(tcon)) return 0; diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index 8615a8747b7f..be22bbc4a65a 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -121,7 +121,7 @@ retry: * want to clobber the existing one with the one that * the readdir code created. */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_SERVER_INUM)) fattr->cf_uniqueid = CIFS_I(inode)->uniqueid; /* @@ -177,6 +177,7 @@ cifs_fill_common_info(struct cifs_fattr *fattr, struct cifs_sb_info *cifs_sb) struct cifs_open_info_data data = { .reparse = { .tag = fattr->cf_cifstag, }, }; + unsigned int sbflags; fattr->cf_uid = cifs_sb->ctx->linux_uid; fattr->cf_gid = cifs_sb->ctx->linux_gid; @@ -215,12 +216,12 @@ out_reparse: * may look wrong since the inodes may not have timed out by the time * "ls" does a stat() call on them. */ - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_CIFS_ACL) || - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID)) + sbflags = cifs_sb_flags(cifs_sb); + if (sbflags & (CIFS_MOUNT_CIFS_ACL | CIFS_MOUNT_MODE_FROM_SID)) fattr->cf_flags |= CIFS_FATTR_NEED_REVAL; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL && - fattr->cf_cifsattrs & ATTR_SYSTEM) { + if ((sbflags & CIFS_MOUNT_UNX_EMUL) && + (fattr->cf_cifsattrs & ATTR_SYSTEM)) { if (fattr->cf_eof == 0) { fattr->cf_mode &= ~S_IFMT; fattr->cf_mode |= S_IFIFO; @@ -345,13 +346,14 @@ static int _initiate_cifs_search(const unsigned int xid, struct file *file, const char *full_path) { - __u16 search_flags; - int rc = 0; - struct cifsFileInfo *cifsFile; - struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); + struct cifs_sb_info *cifs_sb = CIFS_SB(file); struct tcon_link *tlink = NULL; - struct cifs_tcon *tcon; struct TCP_Server_Info *server; + struct cifsFileInfo *cifsFile; + struct cifs_tcon *tcon; + unsigned int sbflags; + __u16 search_flags; + int rc = 0; if (file->private_data == NULL) { tlink = cifs_sb_tlink(cifs_sb); @@ -385,6 +387,7 @@ _initiate_cifs_search(const unsigned int xid, struct file *file, cifs_dbg(FYI, "Full path: %s start at: %lld\n", full_path, file->f_pos); ffirst_retry: + sbflags = cifs_sb_flags(cifs_sb); /* test for Unix extensions */ /* but now check for them on the share/mount not on the SMB session */ /* if (cap_unix(tcon->ses) { */ @@ -395,7 +398,7 @@ ffirst_retry: else if ((tcon->ses->capabilities & tcon->ses->server->vals->cap_nt_find) == 0) { cifsFile->srch_inf.info_level = SMB_FIND_FILE_INFO_STANDARD; - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM) { + } else if (sbflags & CIFS_MOUNT_SERVER_INUM) { cifsFile->srch_inf.info_level = SMB_FIND_FILE_ID_FULL_DIR_INFO; } else /* not srvinos - BB fixme add check for backlevel? */ { cifsFile->srch_inf.info_level = SMB_FIND_FILE_FULL_DIRECTORY_INFO; @@ -411,8 +414,7 @@ ffirst_retry: if (rc == 0) { cifsFile->invalidHandle = false; - } else if ((rc == -EOPNOTSUPP) && - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) { + } else if (rc == -EOPNOTSUPP && (sbflags & CIFS_MOUNT_SERVER_INUM)) { cifs_autodisable_serverino(cifs_sb); goto ffirst_retry; } @@ -690,7 +692,7 @@ find_cifs_entry(const unsigned int xid, struct cifs_tcon *tcon, loff_t pos, loff_t first_entry_in_buffer; loff_t index_to_find = pos; struct cifsFileInfo *cfile = file->private_data; - struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); + struct cifs_sb_info *cifs_sb = CIFS_SB(file); struct TCP_Server_Info *server = tcon->ses->server; /* check if index in the buffer */ @@ -955,6 +957,7 @@ static int cifs_filldir(char *find_entry, struct file *file, struct cifs_sb_info *cifs_sb = CIFS_SB(sb); struct cifs_dirent de = { NULL, }; struct cifs_fattr fattr; + unsigned int sbflags; struct qstr name; int rc = 0; @@ -1019,15 +1022,15 @@ static int cifs_filldir(char *find_entry, struct file *file, break; } - if (de.ino && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SERVER_INUM)) { + sbflags = cifs_sb_flags(cifs_sb); + if (de.ino && (sbflags & CIFS_MOUNT_SERVER_INUM)) { fattr.cf_uniqueid = de.ino; } else { fattr.cf_uniqueid = iunique(sb, ROOT_I); cifs_autodisable_serverino(cifs_sb); } - if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MF_SYMLINKS) && - couldbe_mf_symlink(&fattr)) + if ((sbflags & CIFS_MOUNT_MF_SYMLINKS) && couldbe_mf_symlink(&fattr)) /* * trying to get the type and mode can be slow, * so just call those regular files for now, and mark @@ -1058,7 +1061,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx) const char *full_path; void *page = alloc_dentry_path(); struct cached_fid *cfid = NULL; - struct cifs_sb_info *cifs_sb = CIFS_FILE_SB(file); + struct cifs_sb_info *cifs_sb = CIFS_SB(file); xid = get_xid(); diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index ce9b923498b5..cd1e1eaee67a 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -55,17 +55,18 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, const char *full_path, const char *symname) { struct reparse_symlink_data_buffer *buf = NULL; - struct cifs_open_info_data data = {}; - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); const char *symroot = cifs_sb->ctx->symlinkroot; + struct cifs_open_info_data data = {}; + char sep = CIFS_DIR_SEP(cifs_sb); + char *symlink_target = NULL; + u16 len, plen, poff, slen; + unsigned int sbflags; + __le16 *path = NULL; struct inode *new; + char *sym = NULL; struct kvec iov; - __le16 *path = NULL; bool directory; - char *symlink_target = NULL; - char *sym = NULL; - char sep = CIFS_DIR_SEP(cifs_sb); - u16 len, plen, poff, slen; int rc = 0; if (strlen(symname) > REPARSE_SYM_PATH_MAX) @@ -83,8 +84,8 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, .symlink_target = symlink_target, }; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && - symroot && symname[0] == '/') { + sbflags = cifs_sb_flags(cifs_sb); + if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symroot && symname[0] == '/') { /* * This is a request to create an absolute symlink on the server * which does not support POSIX paths, and expects symlink in @@ -164,7 +165,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, * mask these characters in NT object prefix by '_' and then change * them back. */ - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') + if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') sym[0] = sym[1] = sym[2] = sym[5] = '_'; path = cifs_convert_path_to_utf16(sym, cifs_sb); @@ -173,7 +174,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, goto out; } - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { sym[0] = '\\'; sym[1] = sym[2] = '?'; sym[5] = ':'; @@ -197,7 +198,7 @@ static int create_native_symlink(const unsigned int xid, struct inode *inode, slen = 2 * UniStrnlen((wchar_t *)path, REPARSE_SYM_PATH_MAX); poff = 0; plen = slen; - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { + if (!(sbflags & CIFS_MOUNT_POSIX_PATHS) && symname[0] == '/') { /* * For absolute NT symlinks skip leading "\\??\\" in PrintName as * PrintName is user visible location in DOS/Win32 format (not in NT format). @@ -824,7 +825,7 @@ int smb2_parse_native_symlink(char **target, const char *buf, unsigned int len, goto out; } - if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) && + if (!(cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS) && symroot && !relative) { /* * This is an absolute symlink from the server which does not diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h index 570b0d25aeba..0164dc47bdfd 100644 --- a/fs/smb/client/reparse.h +++ b/fs/smb/client/reparse.h @@ -33,7 +33,7 @@ static inline kuid_t wsl_make_kuid(struct cifs_sb_info *cifs_sb, { u32 uid = le32_to_cpu(*(__le32 *)ptr); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_UID) return cifs_sb->ctx->linux_uid; return make_kuid(current_user_ns(), uid); } @@ -43,7 +43,7 @@ static inline kgid_t wsl_make_kgid(struct cifs_sb_info *cifs_sb, { u32 gid = le32_to_cpu(*(__le32 *)ptr); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_OVERR_GID) return cifs_sb->ctx->linux_gid; return make_kgid(current_user_ns(), gid); } diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index aed49aaef8c4..9643eca0cb70 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -49,6 +49,7 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, if (!CIFSSMBQFSUnixInfo(xid, tcon)) { __u64 cap = le64_to_cpu(tcon->fsUnixInfo.Capability); + unsigned int sbflags; cifs_dbg(FYI, "unix caps which server supports %lld\n", cap); /* @@ -75,14 +76,16 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, if (cap & CIFS_UNIX_TRANSPORT_ENCRYPTION_MANDATORY_CAP) cifs_dbg(VFS, "per-share encryption not supported yet\n"); + if (cifs_sb) + sbflags = cifs_sb_flags(cifs_sb); + cap &= CIFS_UNIX_CAP_MASK; if (ctx && ctx->no_psx_acl) cap &= ~CIFS_UNIX_POSIX_ACL_CAP; else if (CIFS_UNIX_POSIX_ACL_CAP & cap) { cifs_dbg(FYI, "negotiated posix acl support\n"); if (cifs_sb) - cifs_sb->mnt_cifs_flags |= - CIFS_MOUNT_POSIXACL; + sbflags |= CIFS_MOUNT_POSIXACL; } if (ctx && ctx->posix_paths == 0) @@ -90,10 +93,12 @@ void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon, else if (cap & CIFS_UNIX_POSIX_PATHNAMES_CAP) { cifs_dbg(FYI, "negotiate posix pathnames\n"); if (cifs_sb) - cifs_sb->mnt_cifs_flags |= - CIFS_MOUNT_POSIX_PATHS; + sbflags |= CIFS_MOUNT_POSIX_PATHS; } + if (cifs_sb) + atomic_set(&cifs_sb->mnt_cifs_flags, sbflags); + cifs_dbg(FYI, "Negotiate caps 0x%x\n", (int)cap); #ifdef CONFIG_CIFS_DEBUG2 if (cap & CIFS_UNIX_FCNTL_CAP) @@ -1147,7 +1152,7 @@ static int cifs_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode, unsigned int oplock) { - unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags; + unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode)); __u8 op; op = !!((oplock & CIFS_CACHE_READ_FLG) || (sbflags & CIFS_MOUNT_RO_CACHE)); @@ -1282,7 +1287,8 @@ cifs_make_node(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, umode_t mode, dev_t dev) { - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + struct cifs_sb_info *cifs_sb = CIFS_SB(inode); + unsigned int sbflags = cifs_sb_flags(cifs_sb); struct inode *newinode = NULL; int rc; @@ -1298,7 +1304,7 @@ cifs_make_node(unsigned int xid, struct inode *inode, .mtime = NO_CHANGE_64, .device = dev, }; - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { + if (sbflags & CIFS_MOUNT_SET_UID) { args.uid = current_fsuid(); args.gid = current_fsgid(); } else { @@ -1317,7 +1323,7 @@ cifs_make_node(unsigned int xid, struct inode *inode, if (rc == 0) d_instantiate(dentry, newinode); return rc; - } else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { + } else if (sbflags & CIFS_MOUNT_UNX_EMUL) { /* * Check if mounted with mount parm 'sfu' mount parm. * SFU emulation should work with all servers diff --git a/fs/smb/client/smb2file.c b/fs/smb/client/smb2file.c index 1ab41de2b634..ed651c946251 100644 --- a/fs/smb/client/smb2file.c +++ b/fs/smb/client/smb2file.c @@ -72,7 +72,7 @@ int smb2_fix_symlink_target_type(char **target, bool directory, struct cifs_sb_i * POSIX server does not distinguish between symlinks to file and * symlink directory. So nothing is needed to fix on the client side. */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_POSIX_PATHS) return 0; if (!*target) diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index e19674d9b92b..973fce3c959c 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -455,17 +455,8 @@ calc_size_exit: __le16 * cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb) { - int len; const char *start_of_path; - __le16 *to; - int map_type; - - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR) - map_type = SFM_MAP_UNI_RSVD; - else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR) - map_type = SFU_MAP_UNI_RSVD; - else - map_type = NO_MAP_UNI_RSVD; + int len; /* Windows doesn't allow paths beginning with \ */ if (from[0] == '\\') @@ -479,14 +470,13 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb) } else start_of_path = from; - to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len, - cifs_sb->local_nls, map_type); - return to; + return cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len, + cifs_sb->local_nls, cifs_remap(cifs_sb)); } __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode, unsigned int oplock) { - unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags; + unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode)); __le32 lease = 0; if ((oplock & CIFS_CACHE_WRITE_FLG) || (sbflags & CIFS_MOUNT_RW_CACHE)) diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index fea9a35caa57..7f2d3459cbf9 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -986,7 +986,7 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, rc = -EREMOTE; } if (rc == -EREMOTE && IS_ENABLED(CONFIG_CIFS_DFS_UPCALL) && - (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_DFS)) + (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_DFS)) rc = -EOPNOTSUPP; goto out; } @@ -2691,7 +2691,7 @@ static int smb2_oplock_response(struct cifs_tcon *tcon, __u64 persistent_fid, __u64 volatile_fid, __u16 net_fid, struct cifsInodeInfo *cinode, unsigned int oplock) { - unsigned int sbflags = CIFS_SB(cinode->netfs.inode.i_sb)->mnt_cifs_flags; + unsigned int sbflags = cifs_sb_flags(CIFS_SB(cinode)); __u8 op; if (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING) @@ -5332,7 +5332,7 @@ static int smb2_make_node(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, umode_t mode, dev_t dev) { - struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); + unsigned int sbflags = cifs_sb_flags(CIFS_SB(inode)); int rc = -EOPNOTSUPP; /* @@ -5341,7 +5341,7 @@ static int smb2_make_node(unsigned int xid, struct inode *inode, * supports block and char device, socket & fifo, * and was used by default in earlier versions of Windows */ - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL) { + if (sbflags & CIFS_MOUNT_UNX_EMUL) { rc = cifs_sfu_make_node(xid, inode, dentry, tcon, full_path, mode, dev); } else if (CIFS_REPARSE_SUPPORT(tcon)) { diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index ef655acf673d..04e361ed2356 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -1714,19 +1714,17 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) is_binding = (ses->ses_status == SES_GOOD); spin_unlock(&ses->ses_lock); - /* keep session key if binding */ - if (!is_binding) { - kfree_sensitive(ses->auth_key.response); - ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, - GFP_KERNEL); - if (!ses->auth_key.response) { - cifs_dbg(VFS, "Kerberos can't allocate (%u bytes) memory\n", - msg->sesskey_len); - rc = -ENOMEM; - goto out_put_spnego_key; - } - ses->auth_key.len = msg->sesskey_len; + kfree_sensitive(ses->auth_key.response); + ses->auth_key.response = kmemdup(msg->data, + msg->sesskey_len, + GFP_KERNEL); + if (!ses->auth_key.response) { + cifs_dbg(VFS, "%s: can't allocate (%u bytes) memory\n", + __func__, msg->sesskey_len); + rc = -ENOMEM; + goto out_put_spnego_key; } + ses->auth_key.len = msg->sesskey_len; sess_data->iov[1].iov_base = msg->data + msg->sesskey_len; sess_data->iov[1].iov_len = msg->secblob_len; @@ -3182,22 +3180,19 @@ SMB2_open_init(struct cifs_tcon *tcon, struct TCP_Server_Info *server, } if ((oparms->disposition != FILE_OPEN) && (oparms->cifs_sb)) { + unsigned int sbflags = cifs_sb_flags(oparms->cifs_sb); bool set_mode; bool set_owner; - if ((oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MODE_FROM_SID) && - (oparms->mode != ACL_NO_MODE)) + if ((sbflags & CIFS_MOUNT_MODE_FROM_SID) && + oparms->mode != ACL_NO_MODE) { set_mode = true; - else { + } else { set_mode = false; oparms->mode = ACL_NO_MODE; } - if (oparms->cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UID_FROM_ACL) - set_owner = true; - else - set_owner = false; - + set_owner = sbflags & CIFS_MOUNT_UID_FROM_ACL; if (set_owner | set_mode) { cifs_dbg(FYI, "add sd with mode 0x%x\n", oparms->mode); rc = add_sd_context(iov, &n_iov, oparms->mode, set_owner); diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c index 75697f6d2566..05f8099047e1 100644 --- a/fs/smb/client/transport.c +++ b/fs/smb/client/transport.c @@ -807,16 +807,21 @@ cifs_cancelled_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid) } /* - * Return a channel (master if none) of @ses that can be used to send - * regular requests. + * cifs_pick_channel - pick an eligible channel for network operations * - * If we are currently binding a new channel (negprot/sess.setup), - * return the new incomplete channel. + * @ses: session reference + * + * Select an eligible channel (not terminating and not marked as needing + * reconnect), preferring the least loaded one. If no eligible channel is + * found, fall back to the primary channel (index 0). + * + * Return: TCP_Server_Info pointer for the chosen channel, or NULL if @ses is + * NULL. */ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) { uint index = 0; - unsigned int min_in_flight = UINT_MAX, max_in_flight = 0; + unsigned int min_in_flight = UINT_MAX; struct TCP_Server_Info *server = NULL; int i, start, cur; @@ -846,14 +851,8 @@ struct TCP_Server_Info *cifs_pick_channel(struct cifs_ses *ses) min_in_flight = server->in_flight; index = cur; } - if (server->in_flight > max_in_flight) - max_in_flight = server->in_flight; } - /* if all channels are equally loaded, fall back to round-robin */ - if (min_in_flight == max_in_flight) - index = (uint)start % ses->chan_count; - server = ses->chans[index].server; spin_unlock(&ses->chan_lock); diff --git a/fs/smb/client/xattr.c b/fs/smb/client/xattr.c index e1a7d9a10a53..23227f2f9428 100644 --- a/fs/smb/client/xattr.c +++ b/fs/smb/client/xattr.c @@ -149,7 +149,7 @@ static int cifs_xattr_set(const struct xattr_handler *handler, break; } - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR) goto out; if (pTcon->ses->server->ops->set_EA) { @@ -309,7 +309,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler, break; } - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR) goto out; if (pTcon->ses->server->ops->query_all_EAs) @@ -398,7 +398,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size) if (unlikely(cifs_forced_shutdown(cifs_sb))) return smb_EIO(smb_eio_trace_forced_shutdown); - if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_XATTR) + if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_NO_XATTR) return -EOPNOTSUPP; tlink = cifs_sb_tlink(cifs_sb); diff --git a/fs/smb/server/Kconfig b/fs/smb/server/Kconfig index 2775162c535c..12594879cb64 100644 --- a/fs/smb/server/Kconfig +++ b/fs/smb/server/Kconfig @@ -13,6 +13,7 @@ config SMB_SERVER select CRYPTO_LIB_MD5 select CRYPTO_LIB_SHA256 select CRYPTO_LIB_SHA512 + select CRYPTO_LIB_UTILS select CRYPTO_CMAC select CRYPTO_AEAD2 select CRYPTO_CCM diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index 580c4d303dc3..5fe8c667c6b1 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -15,6 +15,7 @@ #include <crypto/aead.h> #include <crypto/md5.h> #include <crypto/sha2.h> +#include <crypto/utils.h> #include <linux/random.h> #include <linux/scatterlist.h> @@ -165,7 +166,8 @@ int ksmbd_auth_ntlmv2(struct ksmbd_conn *conn, struct ksmbd_session *sess, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE, sess->sess_key); - if (memcmp(ntlmv2->ntlmv2_hash, ntlmv2_rsp, CIFS_HMAC_MD5_HASH_SIZE) != 0) + if (crypto_memneq(ntlmv2->ntlmv2_hash, ntlmv2_rsp, + CIFS_HMAC_MD5_HASH_SIZE)) return -EINVAL; return 0; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 95901a78951c..743c629fe7ec 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -4,6 +4,7 @@ * Copyright (C) 2018 Samsung Electronics Co., Ltd. */ +#include <crypto/utils.h> #include <linux/inetdevice.h> #include <net/addrconf.h> #include <linux/syscalls.h> @@ -8880,7 +8881,7 @@ int smb2_check_sign_req(struct ksmbd_work *work) ksmbd_sign_smb2_pdu(work->conn, work->sess->sess_key, iov, 1, signature); - if (memcmp(signature, signature_req, SMB2_SIGNATURE_SIZE)) { + if (crypto_memneq(signature, signature_req, SMB2_SIGNATURE_SIZE)) { pr_err("bad smb2 signature\n"); return 0; } @@ -8968,7 +8969,7 @@ int smb3_check_sign_req(struct ksmbd_work *work) if (ksmbd_sign_smb3_pdu(conn, signing_key, iov, 1, signature)) return 0; - if (memcmp(signature, signature_req, SMB2_SIGNATURE_SIZE)) { + if (crypto_memneq(signature, signature_req, SMB2_SIGNATURE_SIZE)) { pr_err("bad smb2 signature\n"); return 0; } diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 7c53b78b818e..188572491d53 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -2540,9 +2540,9 @@ static int smb_direct_prepare(struct ksmbd_transport *t) goto put; req = (struct smbdirect_negotiate_req *)recvmsg->packet; - sp->max_recv_size = min_t(int, sp->max_recv_size, + sp->max_recv_size = min_t(u32, sp->max_recv_size, le32_to_cpu(req->preferred_send_size)); - sp->max_send_size = min_t(int, sp->max_send_size, + sp->max_send_size = min_t(u32, sp->max_send_size, le32_to_cpu(req->max_receive_size)); sp->max_fragmented_send_size = le32_to_cpu(req->max_fragmented_size); diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c index 8e958db5f786..67abd4dff222 100644 --- a/fs/squashfs/cache.c +++ b/fs/squashfs/cache.c @@ -344,6 +344,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer, if (unlikely(length < 0)) return -EIO; + if (unlikely(*offset < 0 || *offset >= SQUASHFS_METADATA_SIZE)) + return -EIO; + while (length) { entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0); if (entry->error) { diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 9c6765cc2d44..bd8fbb40b49e 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -872,6 +872,34 @@ resv_err: return err2; } +void +xfs_growfs_compute_deltas( + struct xfs_mount *mp, + xfs_rfsblock_t nb, + int64_t *deltap, + xfs_agnumber_t *nagcountp) +{ + xfs_rfsblock_t nb_div, nb_mod; + int64_t delta; + xfs_agnumber_t nagcount; + + nb_div = nb; + nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); + if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS) + nb_div++; + else if (nb_mod) + nb = nb_div * mp->m_sb.sb_agblocks; + + if (nb_div > XFS_MAX_AGNUMBER + 1) { + nb_div = XFS_MAX_AGNUMBER + 1; + nb = nb_div * mp->m_sb.sb_agblocks; + } + nagcount = nb_div; + delta = nb - mp->m_sb.sb_dblocks; + *deltap = delta; + *nagcountp = nagcount; +} + /* * Extent the AG indicated by the @id by the length passed in */ diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 1f24cfa27321..3cd4790768ff 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -331,6 +331,9 @@ struct aghdr_init_data { int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id); int xfs_ag_shrink_space(struct xfs_perag *pag, struct xfs_trans **tpp, xfs_extlen_t delta); +void +xfs_growfs_compute_deltas(struct xfs_mount *mp, xfs_rfsblock_t nb, + int64_t *deltap, xfs_agnumber_t *nagcountp); int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp, xfs_extlen_t len); int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index a017016e9075..3794e5412eba 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -268,6 +268,10 @@ xfs_inode_from_disk( } if (xfs_is_reflink_inode(ip)) xfs_ifork_init_cow(ip); + if (xfs_is_metadir_inode(ip)) { + XFS_STATS_DEC(ip->i_mount, xs_inodes_active); + XFS_STATS_INC(ip->i_mount, xs_inodes_meta); + } return 0; out_destroy_data_fork: diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c index cf239f862212..71f004e9dc64 100644 --- a/fs/xfs/libxfs/xfs_metafile.c +++ b/fs/xfs/libxfs/xfs_metafile.c @@ -61,6 +61,9 @@ xfs_metafile_set_iflag( ip->i_diflags2 |= XFS_DIFLAG2_METADATA; ip->i_metatype = metafile_type; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + + XFS_STATS_DEC(ip->i_mount, xs_inodes_active); + XFS_STATS_INC(ip->i_mount, xs_inodes_meta); } /* Clear the metadata directory inode flag. */ @@ -74,6 +77,8 @@ xfs_metafile_clear_iflag( ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + XFS_STATS_INC(ip->i_mount, xs_inodes_active); + XFS_STATS_DEC(ip->i_mount, xs_inodes_meta); } /* diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h index 2e9715cc1641..23cde1248f01 100644 --- a/fs/xfs/libxfs/xfs_ondisk.h +++ b/fs/xfs/libxfs/xfs_ondisk.h @@ -73,7 +73,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_free_hdr, 64); XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf, 64); XFS_CHECK_STRUCT_SIZE(struct xfs_dir3_leaf_hdr, 64); - XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_entry, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_hdr, 32); XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_map, 4); XFS_CHECK_STRUCT_SIZE(struct xfs_attr_leaf_name_local, 4); @@ -116,7 +116,7 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_da_intnode, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_entry, 8); XFS_CHECK_STRUCT_SIZE(struct xfs_da_node_hdr, 16); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free, 4); XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr, 16); XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, freetag, 0); XFS_CHECK_OFFSET(struct xfs_dir2_data_unused, length, 2); @@ -136,16 +136,7 @@ xfs_check_ondisk_structs(void) /* ondisk dir/attr structures from xfs/122 */ XFS_CHECK_STRUCT_SIZE(struct xfs_attr_sf_entry, 3); XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_free, 4); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_hdr, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_data_unused, 6); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free, 16); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_free_hdr, 16); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf, 16); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_entry, 8); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_hdr, 16); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_leaf_tail, 4); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_entry, 3); - XFS_CHECK_STRUCT_SIZE(struct xfs_dir2_sf_hdr, 10); /* log structures */ XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88); @@ -217,11 +208,6 @@ xfs_check_ondisk_structs(void) XFS_CHECK_OFFSET(struct xfs_dir3_free, hdr.hdr.magic, 0); XFS_CHECK_OFFSET(struct xfs_attr3_leafblock, hdr.info.hdr, 0); - XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat, 192); - XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers, 24); - XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req, 64); - XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req, 64); - /* * Make sure the incore inode timestamp range corresponds to hand * converted values based on the ondisk format specification. @@ -301,6 +287,40 @@ xfs_check_ondisk_structs(void) XFS_CHECK_SB_OFFSET(sb_pad, 281); XFS_CHECK_SB_OFFSET(sb_rtstart, 288); XFS_CHECK_SB_OFFSET(sb_rtreserved, 296); + + /* + * ioctl UABI + * + * Due to different padding/alignment requirements across + * different architectures, some structures are ommited from + * the size checks. In addition, structures with architecture + * dependent size fields are also ommited (e.g. __kernel_long_t). + */ + XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat, 192); + XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers, 24); + XFS_CHECK_STRUCT_SIZE(struct xfs_bulkstat_req, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_inumbers_req, 64); + XFS_CHECK_STRUCT_SIZE(struct dioattr, 12); + XFS_CHECK_STRUCT_SIZE(struct getbmap, 32); + XFS_CHECK_STRUCT_SIZE(struct getbmapx, 48); + XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist_cursor, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_attrlist_ent, 4); + XFS_CHECK_STRUCT_SIZE(struct xfs_ag_geometry, 128); + XFS_CHECK_STRUCT_SIZE(struct xfs_rtgroup_geometry, 128); + XFS_CHECK_STRUCT_SIZE(struct xfs_error_injection, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_geom, 256); + XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_geom_v4, 112); + XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_counts, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_fsop_resblks, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_growfs_log, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_bulk_ireq, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_fs_eofblocks, 128); + XFS_CHECK_STRUCT_SIZE(struct xfs_fsid, 8); + XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_metadata, 64); + XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_vec, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_scrub_vec_head, 40); } #endif /* __XFS_ONDISK_H */ diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index 38d16fe1f6d8..47322adb7690 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -1347,6 +1347,9 @@ xfs_log_sb( * feature was introduced. This counter can go negative due to the way * we handle nearly-lockless reservations, so we must use the _positive * variant here to avoid writing out nonsense frextents. + * + * RT groups are only supported on v5 file systems, which always + * have lazy SB counters. */ if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) { mp->m_sb.sb_frextents = diff --git a/fs/xfs/scrub/dir_repair.c b/fs/xfs/scrub/dir_repair.c index 9dc55c918c78..23b80c54aa60 100644 --- a/fs/xfs/scrub/dir_repair.c +++ b/fs/xfs/scrub/dir_repair.c @@ -177,7 +177,7 @@ xrep_dir_teardown( rd->dir_names = NULL; if (rd->dir_entries) xfarray_destroy(rd->dir_entries); - rd->dir_names = NULL; + rd->dir_entries = NULL; } /* Set up for a directory repair. */ diff --git a/fs/xfs/scrub/orphanage.c b/fs/xfs/scrub/orphanage.c index 52a108f6d5f4..33c6db6b4498 100644 --- a/fs/xfs/scrub/orphanage.c +++ b/fs/xfs/scrub/orphanage.c @@ -442,6 +442,11 @@ xrep_adoption_check_dcache( return 0; d_child = try_lookup_noperm(&qname, d_orphanage); + if (IS_ERR(d_child)) { + dput(d_orphanage); + return PTR_ERR(d_child); + } + if (d_child) { trace_xrep_adoption_check_child(sc->mp, d_child); @@ -479,7 +484,7 @@ xrep_adoption_zap_dcache( return; d_child = try_lookup_noperm(&qname, d_orphanage); - while (d_child != NULL) { + while (!IS_ERR_OR_NULL(d_child)) { trace_xrep_adoption_invalidate_child(sc->mp, d_child); ASSERT(d_is_negative(d_child)); diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 17255c41786b..8d64d904d73c 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -95,18 +95,17 @@ xfs_growfs_data_private( struct xfs_growfs_data *in) /* growfs data input struct */ { xfs_agnumber_t oagcount = mp->m_sb.sb_agcount; + xfs_rfsblock_t nb = in->newblocks; struct xfs_buf *bp; int error; xfs_agnumber_t nagcount; xfs_agnumber_t nagimax = 0; - xfs_rfsblock_t nb, nb_div, nb_mod; int64_t delta; bool lastag_extended = false; struct xfs_trans *tp; struct aghdr_init_data id = {}; struct xfs_perag *last_pag; - nb = in->newblocks; error = xfs_sb_validate_fsb_count(&mp->m_sb, nb); if (error) return error; @@ -125,20 +124,8 @@ xfs_growfs_data_private( mp->m_sb.sb_rextsize); if (error) return error; + xfs_growfs_compute_deltas(mp, nb, &delta, &nagcount); - nb_div = nb; - nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks); - if (nb_mod && nb_mod >= XFS_MIN_AG_BLOCKS) - nb_div++; - else if (nb_mod) - nb = nb_div * mp->m_sb.sb_agblocks; - - if (nb_div > XFS_MAX_AGNUMBER + 1) { - nb_div = XFS_MAX_AGNUMBER + 1; - nb = nb_div * mp->m_sb.sb_agblocks; - } - nagcount = nb_div; - delta = nb - mp->m_sb.sb_dblocks; /* * Reject filesystems with a single AG because they are not * supported, and reject a shrink operation that would cause a diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c index 169123772cb3..239b843e83d4 100644 --- a/fs/xfs/xfs_health.c +++ b/fs/xfs/xfs_health.c @@ -314,6 +314,22 @@ xfs_rgno_mark_sick( xfs_rtgroup_put(rtg); } +static inline void xfs_inode_report_fserror(struct xfs_inode *ip) +{ + /* + * Do not report inodes being constructed or freed, or metadata inodes, + * to fsnotify. + */ + if (xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIM) || + xfs_is_internal_inode(ip)) { + fserror_report_metadata(ip->i_mount->m_super, -EFSCORRUPTED, + GFP_NOFS); + return; + } + + fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS); +} + /* Mark the unhealthy parts of an inode. */ void xfs_inode_mark_sick( @@ -339,7 +355,7 @@ xfs_inode_mark_sick( inode_state_clear(VFS_I(ip), I_DONTCACHE); spin_unlock(&VFS_I(ip)->i_lock); - fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS); + xfs_inode_report_fserror(ip); if (mask) xfs_healthmon_report_inode(ip, XFS_HEALTHMON_SICK, old_mask, mask); @@ -371,7 +387,7 @@ xfs_inode_mark_corrupt( inode_state_clear(VFS_I(ip), I_DONTCACHE); spin_unlock(&VFS_I(ip)->i_lock); - fserror_report_file_metadata(VFS_I(ip), -EFSCORRUPTED, GFP_NOFS); + xfs_inode_report_fserror(ip); if (mask) xfs_healthmon_report_inode(ip, XFS_HEALTHMON_CORRUPT, old_mask, mask); diff --git a/fs/xfs/xfs_healthmon.c b/fs/xfs/xfs_healthmon.c index e37c18cec372..4a06d6632f65 100644 --- a/fs/xfs/xfs_healthmon.c +++ b/fs/xfs/xfs_healthmon.c @@ -69,7 +69,7 @@ xfs_healthmon_get( struct xfs_healthmon *hm; rcu_read_lock(); - hm = mp->m_healthmon; + hm = rcu_dereference(mp->m_healthmon); if (hm && !refcount_inc_not_zero(&hm->ref)) hm = NULL; rcu_read_unlock(); @@ -110,13 +110,13 @@ xfs_healthmon_attach( struct xfs_healthmon *hm) { spin_lock(&xfs_healthmon_lock); - if (mp->m_healthmon != NULL) { + if (rcu_access_pointer(mp->m_healthmon) != NULL) { spin_unlock(&xfs_healthmon_lock); return -EEXIST; } refcount_inc(&hm->ref); - mp->m_healthmon = hm; + rcu_assign_pointer(mp->m_healthmon, hm); hm->mount_cookie = (uintptr_t)mp->m_super; spin_unlock(&xfs_healthmon_lock); @@ -128,13 +128,16 @@ STATIC void xfs_healthmon_detach( struct xfs_healthmon *hm) { + struct xfs_mount *mp; + spin_lock(&xfs_healthmon_lock); if (hm->mount_cookie == DETACHED_MOUNT_COOKIE) { spin_unlock(&xfs_healthmon_lock); return; } - XFS_M((struct super_block *)hm->mount_cookie)->m_healthmon = NULL; + mp = XFS_M((struct super_block *)hm->mount_cookie); + rcu_assign_pointer(mp->m_healthmon, NULL); hm->mount_cookie = DETACHED_MOUNT_COOKIE; spin_unlock(&xfs_healthmon_lock); diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index dbaab4ae709f..a7a09e7eec81 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -106,7 +106,7 @@ xfs_inode_alloc( mapping_set_folio_min_order(VFS_I(ip)->i_mapping, M_IGEO(mp)->min_folio_order); - XFS_STATS_INC(mp, vn_active); + XFS_STATS_INC(mp, xs_inodes_active); ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(ip->i_ino == 0); @@ -172,7 +172,10 @@ __xfs_inode_free( /* asserts to verify all state is correct here */ ASSERT(atomic_read(&ip->i_pincount) == 0); ASSERT(!ip->i_itemp || list_empty(&ip->i_itemp->ili_item.li_bio_list)); - XFS_STATS_DEC(ip->i_mount, vn_active); + if (xfs_is_metadir_inode(ip)) + XFS_STATS_DEC(ip->i_mount, xs_inodes_meta); + else + XFS_STATS_DEC(ip->i_mount, xs_inodes_active); call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback); } @@ -636,6 +639,14 @@ xfs_iget_cache_miss( if (!ip) return -ENOMEM; + /* + * Set XFS_INEW as early as possible so that the health code won't pass + * the inode to the fserror code if the ondisk inode cannot be loaded. + * We're going to free the xfs_inode immediately if that happens, which + * would lead to UAF problems. + */ + xfs_iflags_set(ip, XFS_INEW); + error = xfs_imap(pag, tp, ip->i_ino, &ip->i_imap, flags); if (error) goto out_destroy; @@ -713,7 +724,6 @@ xfs_iget_cache_miss( ip->i_udquot = NULL; ip->i_gdquot = NULL; ip->i_pdquot = NULL; - xfs_iflags_set(ip, XFS_INEW); /* insert the new inode */ spin_lock(&pag->pag_ici_lock); @@ -2234,7 +2244,7 @@ xfs_inode_mark_reclaimable( struct xfs_mount *mp = ip->i_mount; bool need_inactive; - XFS_STATS_INC(mp, vn_reclaim); + XFS_STATS_INC(mp, xs_inode_mark_reclaimable); /* * We should never get here with any of the reclaim flags already set. diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 61c71128d171..ddd4028be8d6 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -345,7 +345,7 @@ typedef struct xfs_mount { struct xfs_hooks m_dir_update_hooks; /* Private data referring to a health monitor object. */ - struct xfs_healthmon *m_healthmon; + struct xfs_healthmon __rcu *m_healthmon; } xfs_mount_t; #define M_IGEO(mp) (&(mp)->m_ino_geo) diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 6be19fa1ebe2..64c8afb935c2 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -304,7 +304,7 @@ xfs_dax_notify_dev_failure( error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); if (error) { - xfs_perag_put(pag); + xfs_perag_rele(pag); break; } @@ -340,7 +340,7 @@ xfs_dax_notify_dev_failure( if (rtg) xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); if (error) { - xfs_group_put(xg); + xfs_group_rele(xg); break; } } diff --git a/fs/xfs/xfs_platform.h b/fs/xfs/xfs_platform.h index 1e59bf94d1f2..59a33c60e0ca 100644 --- a/fs/xfs/xfs_platform.h +++ b/fs/xfs/xfs_platform.h @@ -235,6 +235,10 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, #ifdef XFS_WARN +/* + * Please note that this ASSERT doesn't kill the kernel. It will if the kernel + * has panic_on_warn set. + */ #define ASSERT(expr) \ (likely(expr) ? (void)0 : asswarn(NULL, #expr, __FILE__, __LINE__)) @@ -245,6 +249,11 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count, #endif /* XFS_WARN */ #endif /* DEBUG */ +/* + * Use this to catch metadata corruptions that are not caught by block or + * structure verifiers. The reason is that the verifiers check corruptions only + * within the scope of the object being verified. + */ #define XFS_IS_CORRUPT(mp, expr) \ (unlikely(expr) ? xfs_corruption_error(#expr, XFS_ERRLEVEL_LOW, (mp), \ NULL, 0, __FILE__, __LINE__, \ diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 90a94a5b6f7e..153f3c378f9f 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -112,6 +112,10 @@ xfs_rtcopy_summary( error = xfs_rtget_summary(oargs, log, bbno, &sum); if (error) goto out; + if (XFS_IS_CORRUPT(oargs->mp, sum < 0)) { + error = -EFSCORRUPTED; + goto out; + } if (sum == 0) continue; error = xfs_rtmodify_summary(oargs, log, bbno, -sum); @@ -120,7 +124,6 @@ xfs_rtcopy_summary( error = xfs_rtmodify_summary(nargs, log, bbno, sum); if (error) goto out; - ASSERT(sum > 0); } } error = 0; @@ -1047,6 +1050,15 @@ xfs_growfs_rt_bmblock( */ xfs_trans_resv_calc(mp, &mp->m_resv); + /* + * Sync sb counters now to reflect the updated values. Lazy counters are + * not always updated and in order to avoid inconsistencies between + * frextents and rtextents, it is better to sync the counters. + */ + + if (xfs_has_lazysbcount(mp)) + xfs_log_sb(args.tp); + error = xfs_trans_commit(args.tp); if (error) goto out_free; @@ -1079,17 +1091,27 @@ xfs_last_rtgroup_extents( } /* - * Calculate the last rbmblock currently used. + * This will return the bitmap block number (indexed at 0) that will be + * extended/modified. There are 2 cases here: + * 1. The size of the rtg is such that it is a multiple of + * xfs_rtbitmap_rtx_per_rbmblock() i.e, an integral number of bitmap blocks + * are completely filled up. In this case, we should return + * 1 + (the last used bitmap block number). + * 2. The size of the rtg is not an multiple of xfs_rtbitmap_rtx_per_rbmblock(). + * Here we will return the block number of last used block number. In this + * case, we will modify the last used bitmap block to extend the size of the + * rtgroup. * * This also deals with the case where there were no rtextents before. */ static xfs_fileoff_t -xfs_last_rt_bmblock( +xfs_last_rt_bmblock_to_extend( struct xfs_rtgroup *rtg) { struct xfs_mount *mp = rtg_mount(rtg); xfs_rgnumber_t rgno = rtg_rgno(rtg); xfs_fileoff_t bmbno = 0; + unsigned int mod = 0; ASSERT(!mp->m_sb.sb_rgcount || rgno >= mp->m_sb.sb_rgcount - 1); @@ -1097,9 +1119,16 @@ xfs_last_rt_bmblock( xfs_rtxnum_t nrext = xfs_last_rtgroup_extents(mp); /* Also fill up the previous block if not entirely full. */ - bmbno = xfs_rtbitmap_blockcount_len(mp, nrext); - if (xfs_rtx_to_rbmword(mp, nrext) != 0) - bmbno--; + /* We are doing a -1 to convert it to a 0 based index */ + bmbno = xfs_rtbitmap_blockcount_len(mp, nrext) - 1; + div_u64_rem(nrext, xfs_rtbitmap_rtx_per_rbmblock(mp), &mod); + /* + * mod = 0 means that all the current blocks are full. So + * return the next block number to be used for the rtgroup + * growth. + */ + if (mod == 0) + bmbno++; } return bmbno; @@ -1204,7 +1233,8 @@ xfs_growfs_rtg( goto out_rele; } - for (bmbno = xfs_last_rt_bmblock(rtg); bmbno < bmblocks; bmbno++) { + for (bmbno = xfs_last_rt_bmblock_to_extend(rtg); bmbno < bmblocks; + bmbno++) { error = xfs_growfs_rt_bmblock(rtg, nrblocks, rextsize, bmbno); if (error) goto out_error; diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c index 017db0361cd8..c13d600732c9 100644 --- a/fs/xfs/xfs_stats.c +++ b/fs/xfs/xfs_stats.c @@ -42,7 +42,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) { "xstrat", xfsstats_offset(xs_write_calls) }, { "rw", xfsstats_offset(xs_attr_get) }, { "attr", xfsstats_offset(xs_iflush_count)}, - { "icluster", xfsstats_offset(vn_active) }, + { "icluster", xfsstats_offset(xs_inodes_active) }, { "vnodes", xfsstats_offset(xb_get) }, { "buf", xfsstats_offset(xs_abtb_2) }, { "abtb2", xfsstats_offset(xs_abtc_2) }, @@ -59,7 +59,8 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) { "rtrefcntbt", xfsstats_offset(xs_qm_dqreclaims)}, /* we print both series of quota information together */ { "qm", xfsstats_offset(xs_gc_read_calls)}, - { "zoned", xfsstats_offset(__pad1)}, + { "zoned", xfsstats_offset(xs_inodes_meta)}, + { "metafile", xfsstats_offset(xs_xstrat_bytes)}, }; /* Loop over all stats groups */ @@ -99,16 +100,20 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf) void xfs_stats_clearall(struct xfsstats __percpu *stats) { + uint32_t xs_inodes_active, xs_inodes_meta; int c; - uint32_t vn_active; xfs_notice(NULL, "Clearing xfsstats"); for_each_possible_cpu(c) { preempt_disable(); - /* save vn_active, it's a universal truth! */ - vn_active = per_cpu_ptr(stats, c)->s.vn_active; + /* + * Save the active / meta inode counters, as they are stateful. + */ + xs_inodes_active = per_cpu_ptr(stats, c)->s.xs_inodes_active; + xs_inodes_meta = per_cpu_ptr(stats, c)->s.xs_inodes_meta; memset(per_cpu_ptr(stats, c), 0, sizeof(*stats)); - per_cpu_ptr(stats, c)->s.vn_active = vn_active; + per_cpu_ptr(stats, c)->s.xs_inodes_active = xs_inodes_active; + per_cpu_ptr(stats, c)->s.xs_inodes_meta = xs_inodes_meta; preempt_enable(); } } diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h index 153d2381d0a8..57c32b86c358 100644 --- a/fs/xfs/xfs_stats.h +++ b/fs/xfs/xfs_stats.h @@ -100,14 +100,14 @@ struct __xfsstats { uint32_t xs_iflush_count; uint32_t xs_icluster_flushcnt; uint32_t xs_icluster_flushinode; - uint32_t vn_active; /* # vnodes not on free lists */ - uint32_t vn_alloc; /* # times vn_alloc called */ - uint32_t vn_get; /* # times vn_get called */ - uint32_t vn_hold; /* # times vn_hold called */ - uint32_t vn_rele; /* # times vn_rele called */ - uint32_t vn_reclaim; /* # times vn_reclaim called */ - uint32_t vn_remove; /* # times vn_remove called */ - uint32_t vn_free; /* # times vn_free called */ + uint32_t xs_inodes_active; + uint32_t __unused_vn_alloc; + uint32_t __unused_vn_get; + uint32_t __unused_vn_hold; + uint32_t xs_inode_destroy; + uint32_t xs_inode_destroy2; /* same as xs_inode_destroy */ + uint32_t xs_inode_mark_reclaimable; + uint32_t __unused_vn_free; uint32_t xb_get; uint32_t xb_create; uint32_t xb_get_locked; @@ -142,7 +142,8 @@ struct __xfsstats { uint32_t xs_gc_read_calls; uint32_t xs_gc_write_calls; uint32_t xs_gc_zone_reset_calls; - uint32_t __pad1; +/* Metafile counters */ + uint32_t xs_inodes_meta; /* Extra precision counters */ uint64_t xs_xstrat_bytes; uint64_t xs_write_bytes; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index abc45f860a73..f8de44443e81 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -712,8 +712,8 @@ xfs_fs_destroy_inode( trace_xfs_destroy_inode(ip); ASSERT(!rwsem_is_locked(&inode->i_rwsem)); - XFS_STATS_INC(ip->i_mount, vn_rele); - XFS_STATS_INC(ip->i_mount, vn_remove); + XFS_STATS_INC(ip->i_mount, xs_inode_destroy); + XFS_STATS_INC(ip->i_mount, xs_inode_destroy2); xfs_inode_mark_reclaimable(ip); } diff --git a/fs/xfs/xfs_verify_media.c b/fs/xfs/xfs_verify_media.c index 069cd371619d..8bbd4ec567f8 100644 --- a/fs/xfs/xfs_verify_media.c +++ b/fs/xfs/xfs_verify_media.c @@ -122,7 +122,7 @@ xfs_verify_report_losses( error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); if (error) { - xfs_perag_put(pag); + xfs_perag_rele(pag); break; } @@ -158,7 +158,7 @@ xfs_verify_report_losses( if (rtg) xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP); if (error) { - xfs_group_put(xg); + xfs_group_rele(xg); break; } } diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 67e0c8f5800f..e3d19b6dc64a 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -78,7 +78,7 @@ xfs_zone_account_reclaimable( struct xfs_rtgroup *rtg, uint32_t freed) { - struct xfs_group *xg = &rtg->rtg_group; + struct xfs_group *xg = rtg_group(rtg); struct xfs_mount *mp = rtg_mount(rtg); struct xfs_zone_info *zi = mp->m_zone_info; uint32_t used = rtg_rmap(rtg)->i_used_blocks; @@ -759,7 +759,7 @@ xfs_zone_alloc_blocks( trace_xfs_zone_alloc_blocks(oz, allocated, count_fsb); - *sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0); + *sector = xfs_gbno_to_daddr(rtg_group(rtg), 0); *is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *sector); if (!*is_seq) *sector += XFS_FSB_TO_BB(mp, allocated); @@ -1080,7 +1080,7 @@ xfs_init_zone( if (write_pointer == 0) { /* zone is empty */ atomic_inc(&zi->zi_nr_free_zones); - xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE); + xfs_group_set_mark(rtg_group(rtg), XFS_RTG_FREE); iz->available += rtg_blocks(rtg); } else if (write_pointer < rtg_blocks(rtg)) { /* zone is open */ diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index 48c6cf584447..7efeecd2d85f 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -627,7 +627,7 @@ xfs_zone_gc_alloc_blocks( if (!*count_fsb) return NULL; - *daddr = xfs_gbno_to_daddr(&oz->oz_rtg->rtg_group, 0); + *daddr = xfs_gbno_to_daddr(rtg_group(oz->oz_rtg), 0); *is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *daddr); if (!*is_seq) *daddr += XFS_FSB_TO_BB(mp, oz->oz_allocated); @@ -702,7 +702,7 @@ xfs_zone_gc_start_chunk( chunk->data = data; chunk->oz = oz; chunk->victim_rtg = iter->victim_rtg; - atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref); + atomic_inc(&rtg_group(chunk->victim_rtg)->xg_active_ref); atomic_inc(&chunk->victim_rtg->rtg_gccount); bio->bi_iter.bi_sector = xfs_rtb_to_daddr(mp, chunk->old_startblock); @@ -788,7 +788,7 @@ xfs_zone_gc_split_write( atomic_inc(&chunk->oz->oz_ref); split_chunk->victim_rtg = chunk->victim_rtg; - atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref); + atomic_inc(&rtg_group(chunk->victim_rtg)->xg_active_ref); atomic_inc(&chunk->victim_rtg->rtg_gccount); chunk->offset += split_len; @@ -888,7 +888,7 @@ xfs_zone_gc_finish_reset( goto out; } - xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE); + xfs_group_set_mark(rtg_group(rtg), XFS_RTG_FREE); atomic_inc(&zi->zi_nr_free_zones); xfs_zoned_add_available(mp, rtg_blocks(rtg)); @@ -917,7 +917,7 @@ xfs_submit_zone_reset_bio( XFS_STATS_INC(mp, xs_gc_zone_reset_calls); - bio->bi_iter.bi_sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0); + bio->bi_iter.bi_sector = xfs_gbno_to_daddr(rtg_group(rtg), 0); if (!bdev_zone_is_seq(bio->bi_bdev, bio->bi_iter.bi_sector)) { /* * Also use the bio to drive the state machine when neither diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b78b53198a2e..05b34a6355b0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -124,7 +124,7 @@ struct bpf_map_ops { u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); - int (*map_check_btf)(const struct bpf_map *map, + int (*map_check_btf)(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); @@ -656,7 +656,7 @@ static inline bool bpf_map_support_seq_show(const struct bpf_map *map) map->ops->map_seq_show_elem; } -int map_check_no_btf(const struct bpf_map *map, +int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 85efa9772530..8157e8da61d4 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -176,7 +176,7 @@ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage); void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache); -int bpf_local_storage_map_check_btf(const struct bpf_map *map, +int bpf_local_storage_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index e45162ef59bb..4ce0d27f8ea2 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -14,6 +14,8 @@ struct bpf_mem_alloc { struct obj_cgroup *objcg; bool percpu; struct work_struct work; + void (*dtor_ctx_free)(void *ctx); + void *dtor_ctx; }; /* 'size != 0' is for bpf_mem_alloc which manages fixed-size objects. @@ -32,6 +34,10 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg /* The percpu allocation with a specific unit size. */ int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size); void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma); +void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma, + void (*dtor)(void *obj, void *ctx), + void (*dtor_ctx_free)(void *ctx), + void *ctx); /* Check the allocation size for kmalloc equivalent allocator */ int bpf_mem_alloc_check_size(bool percpu, size_t size); diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 90536b2bc42e..51ef13ed756e 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -339,8 +339,11 @@ static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int orde { return folio_alloc_noprof(gfp, order); } -#define vma_alloc_folio_noprof(gfp, order, vma, addr) \ - folio_alloc_noprof(gfp, order) +static inline struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, + struct vm_area_struct *vma, unsigned long addr) +{ + return folio_alloc_noprof(gfp, order); +} #endif #define alloc_pages(...) alloc_hooks(alloc_pages_noprof(__VA_ARGS__)) diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 814bb2892f99..6c75df30a281 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -139,6 +139,8 @@ enum { * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. * * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension. + * mark_obj_codetag_empty() should be called upon freeing for objects allocated + * with this flag to indicate that their NULL tags are expected and normal. */ #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) #define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h index 35227d47cfc9..dc272b514a01 100644 --- a/include/linux/indirect_call_wrapper.h +++ b/include/linux/indirect_call_wrapper.h @@ -16,22 +16,26 @@ */ #define INDIRECT_CALL_1(f, f1, ...) \ ({ \ - likely(f == f1) ? f1(__VA_ARGS__) : f(__VA_ARGS__); \ + typeof(f) __f1 = (f); \ + likely(__f1 == f1) ? f1(__VA_ARGS__) : __f1(__VA_ARGS__); \ }) #define INDIRECT_CALL_2(f, f2, f1, ...) \ ({ \ - likely(f == f2) ? f2(__VA_ARGS__) : \ - INDIRECT_CALL_1(f, f1, __VA_ARGS__); \ + typeof(f) __f2 = (f); \ + likely(__f2 == f2) ? f2(__VA_ARGS__) : \ + INDIRECT_CALL_1(__f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_3(f, f3, f2, f1, ...) \ ({ \ - likely(f == f3) ? f3(__VA_ARGS__) : \ - INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__); \ + typeof(f) __f3 = (f); \ + likely(__f3 == f3) ? f3(__VA_ARGS__) : \ + INDIRECT_CALL_2(__f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALL_4(f, f4, f3, f2, f1, ...) \ ({ \ - likely(f == f4) ? f4(__VA_ARGS__) : \ - INDIRECT_CALL_3(f, f3, f2, f1, __VA_ARGS__); \ + typeof(f) __f4 = (f); \ + likely(__f4 == f4) ? f4(__VA_ARGS__) : \ + INDIRECT_CALL_3(__f4, f3, f2, f1, __VA_ARGS__); \ }) #define INDIRECT_CALLABLE_DECLARE(f) f diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 70c0948f978e..0225121f3013 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -394,6 +394,7 @@ #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 #define GITS_TYPER_ITT_ENTRY_SIZE GENMASK_ULL(7, 4) +#define GITS_TYPER_IDBITS GENMASK_ULL(12, 8) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS GENMASK_ULL(17, 13) diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index fdef2c155c27..d1c3d4941854 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -434,8 +434,44 @@ extern unsigned long preset_lpj; /* * Convert various time units to each other: */ -extern unsigned int jiffies_to_msecs(const unsigned long j); -extern unsigned int jiffies_to_usecs(const unsigned long j); + +#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) +/** + * jiffies_to_msecs - Convert jiffies to milliseconds + * @j: jiffies value + * + * This inline version takes care of HZ in {100,250,1000}. + * + * Return: milliseconds value + */ +static inline unsigned int jiffies_to_msecs(const unsigned long j) +{ + return (MSEC_PER_SEC / HZ) * j; +} +#else +unsigned int jiffies_to_msecs(const unsigned long j); +#endif + +#if !(USEC_PER_SEC % HZ) +/** + * jiffies_to_usecs - Convert jiffies to microseconds + * @j: jiffies value + * + * Return: microseconds value + */ +static inline unsigned int jiffies_to_usecs(const unsigned long j) +{ + /* + * Hz usually doesn't go much further MSEC_PER_SEC. + * jiffies_to_usecs() and usecs_to_jiffies() depend on that. + */ + BUILD_BUG_ON(HZ > USEC_PER_SEC); + + return (USEC_PER_SEC / HZ) * j; +} +#else +unsigned int jiffies_to_usecs(const unsigned long j); +#endif /** * jiffies_to_nsecs - Convert jiffies to nanoseconds diff --git a/include/linux/kthread.h b/include/linux/kthread.h index c92c1149ee6e..a01a474719a7 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -7,6 +7,24 @@ struct mm_struct; +/* opaque kthread data */ +struct kthread; + +/* + * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will + * always remain a kthread. For kthreads p->worker_private always + * points to a struct kthread. For tasks that are not kthreads + * p->worker_private is used to point to other things. + * + * Return NULL for any task that is not a kthread. + */ +static inline struct kthread *tsk_is_kthread(struct task_struct *p) +{ + if (p->flags & PF_KTHREAD) + return p->worker_private; + return NULL; +} + __printf(4, 5) struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), void *data, @@ -98,9 +116,10 @@ void *kthread_probe_data(struct task_struct *k); int kthread_park(struct task_struct *k); void kthread_unpark(struct task_struct *k); void kthread_parkme(void); -void kthread_exit(long result) __noreturn; +#define kthread_exit(result) do_exit(result) void kthread_complete_and_exit(struct completion *, long) __noreturn; int kthreads_update_housekeeping(void); +void kthread_do_exit(struct kthread *, long); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index dde605cb894e..34759a262b28 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -253,7 +253,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu); #endif -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER union kvm_mmu_notifier_arg { unsigned long attributes; }; @@ -275,7 +274,6 @@ struct kvm_gfn_range { bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range); -#endif enum { OUTSIDE_GUEST_MODE, @@ -849,13 +847,12 @@ struct kvm { struct hlist_head irq_ack_notifier_list; #endif -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER struct mmu_notifier mmu_notifier; unsigned long mmu_invalidate_seq; long mmu_invalidate_in_progress; gfn_t mmu_invalidate_range_start; gfn_t mmu_invalidate_range_end; -#endif + struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; @@ -2118,7 +2115,6 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[]; extern const struct kvm_stats_header kvm_vcpu_stats_header; extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[]; -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq) { if (unlikely(kvm->mmu_invalidate_in_progress)) @@ -2196,7 +2192,6 @@ static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm, return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq; } -#endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h index fe82a6c3005f..dd11fdc76a5f 100644 --- a/include/linux/liveupdate.h +++ b/include/linux/liveupdate.h @@ -23,8 +23,11 @@ struct file; /** * struct liveupdate_file_op_args - Arguments for file operation callbacks. * @handler: The file handler being called. - * @retrieved: The retrieve status for the 'can_finish / finish' - * operation. + * @retrieve_status: The retrieve status for the 'can_finish / finish' + * operation. A value of 0 means the retrieve has not been + * attempted, a positive value means the retrieve was + * successful, and a negative value means the retrieve failed, + * and the value is the error code of the call. * @file: The file object. For retrieve: [OUT] The callback sets * this to the new file. For other ops: [IN] The caller sets * this to the file being operated on. @@ -40,7 +43,7 @@ struct file; */ struct liveupdate_file_op_args { struct liveupdate_file_handler *handler; - bool retrieved; + int retrieve_status; struct file *file; u64 serialized_data; void *private_data; diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h index e0e2c265e5d1..ba84f02c2a10 100644 --- a/include/linux/mmc/host.h +++ b/include/linux/mmc/host.h @@ -486,14 +486,12 @@ struct mmc_host { struct mmc_ios ios; /* current io bus settings */ + bool claimed; /* host exclusively claimed */ + /* group bitfields together to minimize padding */ unsigned int use_spi_crc:1; - unsigned int claimed:1; /* host exclusively claimed */ unsigned int doing_init_tune:1; /* initial tuning in progress */ - unsigned int can_retune:1; /* re-tuning can be used */ unsigned int doing_retune:1; /* re-tuning in progress */ - unsigned int retune_now:1; /* do re-tuning at next req */ - unsigned int retune_paused:1; /* re-tuning is temporarily disabled */ unsigned int retune_crc_disable:1; /* don't trigger retune upon crc */ unsigned int can_dma_map_merge:1; /* merging can be used */ unsigned int vqmmc_enabled:1; /* vqmmc regulator is enabled */ @@ -508,6 +506,9 @@ struct mmc_host { int rescan_disable; /* disable card detection */ int rescan_entered; /* used with nonremovable devices */ + bool can_retune; /* re-tuning can be used */ + bool retune_now; /* do re-tuning at next req */ + bool retune_paused; /* re-tuning is temporarily disabled */ int need_retune; /* re-tuning is needed */ int hold_retune; /* hold off re-tuning */ unsigned int retune_period; /* re-tuning period in secs */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d4e6e00bb90a..67e25f6d15a4 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4711,7 +4711,7 @@ static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } @@ -4729,7 +4729,7 @@ static inline void __netif_tx_release(struct netdev_queue *txq) static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } @@ -4738,7 +4738,7 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; @@ -4746,14 +4746,14 @@ static inline bool __netif_tx_trylock(struct netdev_queue *txq) static inline void __netif_tx_unlock(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { - /* Pairs with READ_ONCE() in __dev_queue_xmit() */ + /* Pairs with READ_ONCE() in netif_tx_owned() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } @@ -4846,6 +4846,23 @@ static inline void netif_tx_disable(struct net_device *dev) local_bh_enable(); } +#ifndef CONFIG_PREEMPT_RT +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + /* Other cpus might concurrently change txq->xmit_lock_owner + * to -1 or to their cpu id, but not to our id. + */ + return READ_ONCE(txq->xmit_lock_owner) == cpu; +} + +#else +static inline bool netif_tx_owned(struct netdev_queue *txq, unsigned int cpu) +{ + return rt_mutex_owner(&txq->_xmit_lock.lock) == current; +} + +#endif + static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index 825f5865bfc5..c8e227a3f9e2 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -55,6 +55,8 @@ static __always_inline bool is_ns_init_id(const struct ns_common *ns) #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) +bool may_see_all_namespaces(void); + static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) { return atomic_read(&ns->__ns_ref_active); diff --git a/include/linux/overflow.h b/include/linux/overflow.h index eddd987a8513..a8cb6319b4fb 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -42,7 +42,7 @@ * both the type-agnostic benefits of the macros while also being able to * enforce that the return value is, in fact, checked. */ -static inline bool __must_check __must_check_overflow(bool overflow) +static __always_inline bool __must_check __must_check_overflow(bool overflow) { return unlikely(overflow); } @@ -327,7 +327,7 @@ static inline bool __must_check __must_check_overflow(bool overflow) * with any overflow causing the return value to be SIZE_MAX. The * lvalue must be size_t to avoid implicit type conversion. */ -static inline size_t __must_check size_mul(size_t factor1, size_t factor2) +static __always_inline size_t __must_check size_mul(size_t factor1, size_t factor2) { size_t bytes; @@ -346,7 +346,7 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2) * with any overflow causing the return value to be SIZE_MAX. The * lvalue must be size_t to avoid implicit type conversion. */ -static inline size_t __must_check size_add(size_t addend1, size_t addend2) +static __always_inline size_t __must_check size_add(size_t addend1, size_t addend2) { size_t bytes; @@ -367,7 +367,7 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2) * argument may be SIZE_MAX (or the result with be forced to SIZE_MAX). * The lvalue must be size_t to avoid implicit type conversion. */ -static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) +static __always_inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) { size_t bytes; diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 41037c513f06..64921b10ac74 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -545,22 +545,10 @@ static inline int pm_runtime_resume_and_get(struct device *dev) * * Decrement the runtime PM usage counter of @dev and if it turns out to be * equal to 0, queue up a work item for @dev like in pm_request_idle(). - * - * Return: - * * 1: Success. Usage counter dropped to zero, but device was already suspended. - * * 0: Success. - * * -EINVAL: Runtime PM error. - * * -EACCES: Runtime PM disabled. - * * -EAGAIN: Runtime PM usage counter became non-zero or Runtime PM status - * change ongoing. - * * -EBUSY: Runtime PM child_count non-zero. - * * -EPERM: Device PM QoS resume latency 0. - * * -EINPROGRESS: Suspend already in progress. - * * -ENOSYS: CONFIG_PM not enabled. */ -static inline int pm_runtime_put(struct device *dev) +static inline void pm_runtime_put(struct device *dev) { - return __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); + __pm_runtime_idle(dev, RPM_GET_PUT | RPM_ASYNC); } /** diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 876358cfe1b1..d862fa610270 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -248,6 +248,7 @@ int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node); int ring_buffer_map(struct trace_buffer *buffer, int cpu, struct vm_area_struct *vma); +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu); int ring_buffer_unmap(struct trace_buffer *buffer, int cpu); int ring_buffer_map_get_reader(struct trace_buffer *buffer, int cpu); #endif /* _LINUX_RING_BUFFER_H */ diff --git a/include/linux/rseq.h b/include/linux/rseq.h index 7a01a0760405..b9d62fc2140d 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -146,6 +146,18 @@ static inline void rseq_fork(struct task_struct *t, u64 clone_flags) t->rseq = current->rseq; } +/* + * Value returned by getauxval(AT_RSEQ_ALIGN) and expected by rseq + * registration. This is the active rseq area size rounded up to next + * power of 2, which guarantees that the rseq structure will always be + * aligned on the nearest power of two large enough to contain it, even + * as it grows. + */ +static inline unsigned int rseq_alloc_align(void) +{ + return 1U << get_count_order(offsetof(struct rseq, end)); +} + #else /* CONFIG_RSEQ */ static inline void rseq_handle_slowpath(struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h index cbc4a791618b..c6831c93cd6e 100644 --- a/include/linux/rseq_entry.h +++ b/include/linux/rseq_entry.h @@ -216,10 +216,10 @@ efault: } #else /* CONFIG_RSEQ_SLICE_EXTENSION */ -static inline bool rseq_slice_extension_enabled(void) { return false; } -static inline bool rseq_arm_slice_extension_timer(void) { return false; } -static inline void rseq_slice_clear_grant(struct task_struct *t) { } -static inline bool rseq_grant_slice_extension(bool work_pending) { return false; } +static __always_inline bool rseq_slice_extension_enabled(void) { return false; } +static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; } +static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { } +static __always_inline bool rseq_grant_slice_extension(bool work_pending) { return false; } #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */ bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); diff --git a/include/linux/sched.h b/include/linux/sched.h index 074ad4ef3d81..a7b4a980eb2f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -579,6 +579,7 @@ struct sched_entity { u64 deadline; u64 min_vruntime; u64 min_slice; + u64 max_slice; struct list_head group_node; unsigned char on_rq; diff --git a/include/linux/slab.h b/include/linux/slab.h index a5a5e4108ae5..15a60b501b95 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -517,18 +517,6 @@ void kfree_sensitive(const void *objp); DEFINE_FREE(kfree, void *, if (!IS_ERR_OR_NULL(_T)) kfree(_T)) DEFINE_FREE(kfree_sensitive, void *, if (_T) kfree_sensitive(_T)) -/** - * ksize - Report actual allocation size of associated object - * - * @objp: Pointer returned from a prior kmalloc()-family allocation. - * - * This should not be used for writing beyond the originally requested - * allocation size. Either use krealloc() or round up the allocation size - * with kmalloc_size_roundup() prior to allocation. If this is used to - * access beyond the originally requested allocation size, UBSAN_BOUNDS - * and/or FORTIFY_SOURCE may trip, since they only know about the - * originally allocated size via the __alloc_size attribute. - */ size_t ksize(const void *objp); #ifdef CONFIG_PRINTK diff --git a/include/linux/tnum.h b/include/linux/tnum.h index fa4654ffb621..ca2cfec8de08 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -131,4 +131,7 @@ static inline bool tnum_subreg_is_const(struct tnum a) return !(tnum_subreg(a)).mask; } +/* Returns the smallest member of t larger than z */ +u64 tnum_step(struct tnum t, u64 z); + #endif /* _LINUX_TNUM_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1f3804245c06..809e4f7dfdbd 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -647,36 +647,22 @@ static inline void user_access_restore(unsigned long flags) { } /* Define RW variant so the below _mode macro expansion works */ #define masked_user_rw_access_begin(u) masked_user_access_begin(u) #define user_rw_access_begin(u, s) user_access_begin(u, s) -#define user_rw_access_end() user_access_end() /* Scoped user access */ -#define USER_ACCESS_GUARD(_mode) \ -static __always_inline void __user * \ -class_user_##_mode##_begin(void __user *ptr) \ -{ \ - return ptr; \ -} \ - \ -static __always_inline void \ -class_user_##_mode##_end(void __user *ptr) \ -{ \ - user_##_mode##_access_end(); \ -} \ - \ -DEFINE_CLASS(user_ ##_mode## _access, void __user *, \ - class_user_##_mode##_end(_T), \ - class_user_##_mode##_begin(ptr), void __user *ptr) \ - \ -static __always_inline class_user_##_mode##_access_t \ -class_user_##_mode##_access_ptr(void __user *scope) \ -{ \ - return scope; \ -} -USER_ACCESS_GUARD(read) -USER_ACCESS_GUARD(write) -USER_ACCESS_GUARD(rw) -#undef USER_ACCESS_GUARD +/* Cleanup wrapper functions */ +static __always_inline void __scoped_user_read_access_end(const void *p) +{ + user_read_access_end(); +}; +static __always_inline void __scoped_user_write_access_end(const void *p) +{ + user_write_access_end(); +}; +static __always_inline void __scoped_user_rw_access_end(const void *p) +{ + user_access_end(); +}; /** * __scoped_user_access_begin - Start a scoped user access @@ -750,13 +736,13 @@ USER_ACCESS_GUARD(rw) * * Don't use directly. Use scoped_masked_user_$MODE_access() instead. */ -#define __scoped_user_access(mode, uptr, size, elbl) \ -for (bool done = false; !done; done = true) \ - for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ - !done; done = true) \ - for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true) \ - /* Force modified pointer usage within the scope */ \ - for (const typeof(uptr) uptr = _tmpptr; !done; done = true) +#define __scoped_user_access(mode, uptr, size, elbl) \ +for (bool done = false; !done; done = true) \ + for (auto _tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ + !done; done = true) \ + /* Force modified pointer usage within the scope */ \ + for (const auto uptr __cleanup(__scoped_user_##mode##_access_end) = \ + _tmpptr; !done; done = true) /** * scoped_user_read_access_size - Start a scoped user read access with given size diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h index 2ca60828f28b..1502b2a355f9 100644 --- a/include/linux/usb/r8152.h +++ b/include/linux/usb/r8152.h @@ -32,6 +32,7 @@ #define VENDOR_ID_DLINK 0x2001 #define VENDOR_ID_DELL 0x413c #define VENDOR_ID_ASUS 0x0b05 +#define VENDOR_ID_TRENDNET 0x20f4 #if IS_REACHABLE(CONFIG_USB_RTL8152) extern u8 rtl8152_get_version(struct usb_interface *intf); diff --git a/include/net/act_api.h b/include/net/act_api.h index e1e8f0f7dacb..d11b79107930 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -70,6 +70,7 @@ struct tc_action { #define TCA_ACT_FLAGS_REPLACE (1U << (TCA_ACT_FLAGS_USER_BITS + 2)) #define TCA_ACT_FLAGS_NO_RTNL (1U << (TCA_ACT_FLAGS_USER_BITS + 3)) #define TCA_ACT_FLAGS_AT_INGRESS (1U << (TCA_ACT_FLAGS_USER_BITS + 4)) +#define TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT (1U << (TCA_ACT_FLAGS_USER_BITS + 5)) /* Update lastuse only if needed, to avoid dirtying a cache line. * We use a temp variable to avoid fetching jiffies twice. diff --git a/include/net/bonding.h b/include/net/bonding.h index 7f8fda2fdfcb..d3520ecfa7f0 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -699,6 +699,7 @@ void bond_debug_register(struct bonding *bond); void bond_debug_unregister(struct bonding *bond); void bond_debug_reregister(struct bonding *bond); const char *bond_mode_name(int mode); +bool __bond_xdp_check(int mode, int xmit_policy); bool bond_xdp_check(struct bonding *bond, int mode); void bond_setup(struct net_device *bond_dev); unsigned int bond_get_num_tx_queues(void); diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h index 282e29237d93..c16de5b7963f 100644 --- a/include/net/inet6_hashtables.h +++ b/include/net/inet6_hashtables.h @@ -175,7 +175,7 @@ static inline bool inet6_match(const struct net *net, const struct sock *sk, { if (!net_eq(sock_net(sk), net) || sk->sk_family != AF_INET6 || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || !ipv6_addr_equal(&sk->sk_v6_daddr, saddr) || !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return false; diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index 8bddf58b1a85..1a47e7ed371a 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -344,7 +344,7 @@ static inline bool inet_match(const struct net *net, const struct sock *sk, int dif, int sdif) { if (!net_eq(sock_net(sk), net) || - sk->sk_portpair != ports || + READ_ONCE(sk->sk_portpair) != ports || sk->sk_addrpair != cookie) return false; diff --git a/include/net/ip.h b/include/net/ip.h index 52264c459357..f39a3787fedd 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -101,7 +101,7 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm, ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if); ipcm->addr = inet->inet_saddr; - ipcm->protocol = inet->inet_num; + ipcm->protocol = READ_ONCE(inet->inet_num); } #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index b4495c38e0a0..318593743b6e 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -559,7 +559,7 @@ static inline u32 fib_multipath_hash_from_keys(const struct net *net, siphash_aligned_key_t hash_key; u32 mp_seed; - mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed).mp_seed; + mp_seed = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed); fib_multipath_hash_construct_key(&hash_key, mp_seed); return flow_hash_from_keys_seed(keys, &hash_key); diff --git a/include/net/libeth/xsk.h b/include/net/libeth/xsk.h index 481a7b28e6f2..82b5d21aae87 100644 --- a/include/net/libeth/xsk.h +++ b/include/net/libeth/xsk.h @@ -597,6 +597,7 @@ __libeth_xsk_run_pass(struct libeth_xdp_buff *xdp, * @pending: current number of XSkFQEs to refill * @thresh: threshold below which the queue is refilled * @buf_len: HW-writeable length per each buffer + * @truesize: step between consecutive buffers, 0 if none exists * @nid: ID of the closest NUMA node with memory */ struct libeth_xskfq { @@ -614,6 +615,8 @@ struct libeth_xskfq { u32 thresh; u32 buf_len; + u32 truesize; + int nid; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 40e8106e71f0..acfa2ceef9c0 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -309,11 +309,13 @@ static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) * @NFT_ITER_UNSPEC: unspecified, to catch errors * @NFT_ITER_READ: read-only iteration over set elements * @NFT_ITER_UPDATE: iteration under mutex to update set element state + * @NFT_ITER_UPDATE_CLONE: clone set before iteration under mutex to update element */ enum nft_iter_type { NFT_ITER_UNSPEC, NFT_ITER_READ, NFT_ITER_UPDATE, + NFT_ITER_UPDATE_CLONE, }; struct nft_set; @@ -1845,6 +1847,11 @@ struct nft_trans_gc { struct rcu_head rcu; }; +static inline int nft_trans_gc_space(const struct nft_trans_gc *trans) +{ + return NFT_TRANS_GC_BATCHCOUNT - trans->count; +} + static inline void nft_ctx_update(struct nft_ctx *ctx, const struct nft_trans *trans) { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 31c25a6d6acc..c355300893a3 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -781,13 +781,23 @@ static inline bool skb_skip_tc_classify(struct sk_buff *skb) static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) { struct Qdisc *qdisc; + bool nolock; for (; i < dev->num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc); if (qdisc) { + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) { + clear_bit(__QDISC_STATE_MISSED, &qdisc->state); + clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); + spin_unlock_bh(&qdisc->seqlock); + } } } } diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h index cddebafb9f77..6f996229167b 100644 --- a/include/net/secure_seq.h +++ b/include/net/secure_seq.h @@ -5,16 +5,47 @@ #include <linux/types.h> struct net; +extern struct net init_net; + +union tcp_seq_and_ts_off { + struct { + u32 seq; + u32 ts_off; + }; + u64 hash64; +}; u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport); -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport); -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr); -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport); -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr); +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport); + +static inline u32 secure_tcp_seq(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcp_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + + return ts.seq; +} + +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, + __be16 sport, __be16 dport); + +static inline u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, + __be16 sport, __be16 dport) +{ + union tcp_seq_and_ts_off ts; + + ts = secure_tcpv6_seq_and_ts_off(&init_net, saddr, daddr, + sport, dport); + return ts.seq; +} #endif /* _NET_SECURE_SEQ */ diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h index b147a3bb1a46..e0fded18e18c 100644 --- a/include/net/tc_act/tc_gate.h +++ b/include/net/tc_act/tc_gate.h @@ -32,6 +32,7 @@ struct tcf_gate_params { s32 tcfg_clockid; size_t num_entries; struct list_head entries; + struct rcu_head rcu; }; #define GATE_ACT_GATE_OPEN BIT(0) @@ -39,7 +40,7 @@ struct tcf_gate_params { struct tcf_gate { struct tc_action common; - struct tcf_gate_params param; + struct tcf_gate_params __rcu *param; u8 current_gate_status; ktime_t current_close_time; u32 current_entry_octets; @@ -51,47 +52,65 @@ struct tcf_gate { #define to_gate(a) ((struct tcf_gate *)a) +static inline struct tcf_gate_params *tcf_gate_params_locked(const struct tc_action *a) +{ + struct tcf_gate *gact = to_gate(a); + + return rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); +} + static inline s32 tcf_gate_prio(const struct tc_action *a) { + struct tcf_gate_params *p; s32 tcfg_prio; - tcfg_prio = to_gate(a)->param.tcfg_priority; + p = tcf_gate_params_locked(a); + tcfg_prio = p->tcfg_priority; return tcfg_prio; } static inline u64 tcf_gate_basetime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_basetime; - tcfg_basetime = to_gate(a)->param.tcfg_basetime; + p = tcf_gate_params_locked(a); + tcfg_basetime = p->tcfg_basetime; return tcfg_basetime; } static inline u64 tcf_gate_cycletime(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletime; - tcfg_cycletime = to_gate(a)->param.tcfg_cycletime; + p = tcf_gate_params_locked(a); + tcfg_cycletime = p->tcfg_cycletime; return tcfg_cycletime; } static inline u64 tcf_gate_cycletimeext(const struct tc_action *a) { + struct tcf_gate_params *p; u64 tcfg_cycletimeext; - tcfg_cycletimeext = to_gate(a)->param.tcfg_cycletime_ext; + p = tcf_gate_params_locked(a); + tcfg_cycletimeext = p->tcfg_cycletime_ext; return tcfg_cycletimeext; } static inline u32 tcf_gate_num_entries(const struct tc_action *a) { + struct tcf_gate_params *p; u32 num_entries; - num_entries = to_gate(a)->param.num_entries; + p = tcf_gate_params_locked(a); + num_entries = p->num_entries; return num_entries; } @@ -105,7 +124,7 @@ static inline struct action_gate_entry u32 num_entries; int i = 0; - p = &to_gate(a)->param; + p = tcf_gate_params_locked(a); num_entries = p->num_entries; list_for_each_entry(entry, &p->entries, list) diff --git a/include/net/tc_act/tc_ife.h b/include/net/tc_act/tc_ife.h index c7f24a2da1ca..24d4d5a62b3c 100644 --- a/include/net/tc_act/tc_ife.h +++ b/include/net/tc_act/tc_ife.h @@ -13,15 +13,13 @@ struct tcf_ife_params { u8 eth_src[ETH_ALEN]; u16 eth_type; u16 flags; - + struct list_head metalist; struct rcu_head rcu; }; struct tcf_ife_info { struct tc_action common; struct tcf_ife_params __rcu *params; - /* list of metaids allowed */ - struct list_head metalist; }; #define to_ife(a) ((struct tcf_ife_info *)a) diff --git a/include/net/tcp.h b/include/net/tcp.h index fea6081cf6c7..3f1fe954e6aa 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -43,6 +43,7 @@ #include <net/dst.h> #include <net/mptcp.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -2477,8 +2478,9 @@ struct tcp_request_sock_ops { struct flowi *fl, struct request_sock *req, u32 tw_isn); - u32 (*init_seq)(const struct sk_buff *skb); - u32 (*init_ts_off)(const struct net *net, const struct sk_buff *skb); + union tcp_seq_and_ts_off (*init_seq_and_ts_off)( + const struct net *net, + const struct sk_buff *skb); int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 242e34f771cc..6b9ebae2dc95 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -51,6 +51,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return xsk_pool_get_chunk_size(pool) - xsk_pool_get_headroom(pool); } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return pool->unaligned ? 0 : xsk_pool_get_chunk_size(pool); +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { @@ -122,7 +127,7 @@ static inline void xsk_buff_free(struct xdp_buff *xdp) goto out; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { - list_del(&pos->list_node); + list_del_init(&pos->list_node); xp_free(pos); } @@ -157,7 +162,7 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first) frag = list_first_entry_or_null(&xskb->pool->xskb_list, struct xdp_buff_xsk, list_node); if (frag) { - list_del(&frag->list_node); + list_del_init(&frag->list_node); ret = &frag->xdp; } @@ -168,7 +173,7 @@ static inline void xsk_buff_del_frag(struct xdp_buff *xdp) { struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp); - list_del(&xskb->list_node); + list_del_init(&xskb->list_node); } static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first) @@ -337,6 +342,11 @@ static inline u32 xsk_pool_get_rx_frame_size(struct xsk_buff_pool *pool) return 0; } +static inline u32 xsk_pool_get_rx_frag_step(struct xsk_buff_pool *pool) +{ + return 0; +} + static inline void xsk_pool_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq) { diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h index 6de6fd8bd15e..d639ff889e64 100644 --- a/include/rdma/rdma_cm.h +++ b/include/rdma/rdma_cm.h @@ -181,7 +181,7 @@ void rdma_destroy_id(struct rdma_cm_id *id); * * It needs to be called before the RDMA identifier is bound * to an device, which mean it should be called before - * rdma_bind_addr(), rdma_bind_addr() and rdma_listen(). + * rdma_bind_addr(), rdma_resolve_addr() and rdma_listen(). */ int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type); diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h index 7f93e754da5c..cd7920c81f85 100644 --- a/include/trace/events/kmem.h +++ b/include/trace/events/kmem.h @@ -440,7 +440,13 @@ TRACE_EVENT(rss_stat, TP_fast_assign( __entry->mm_id = mm_ptr_to_hash(mm); - __entry->curr = !!(current->mm == mm); + /* + * curr is true if the mm matches the current task's mm_struct. + * Since kthreads (PF_KTHREAD) have no mm_struct of their own + * but can borrow one via kthread_use_mm(), we must filter them + * out to avoid incorrectly attributing the RSS update to them. + */ + __entry->curr = current->mm == mm && !(current->flags & PF_KTHREAD); __entry->member = member; __entry->size = (percpu_counter_sum_positive(&mm->rss_stat[member]) << PAGE_SHIFT); diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 64a382fbc31a..2d366be46a1c 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -57,6 +57,7 @@ EM(netfs_rreq_trace_done, "DONE ") \ EM(netfs_rreq_trace_end_copy_to_cache, "END-C2C") \ EM(netfs_rreq_trace_free, "FREE ") \ + EM(netfs_rreq_trace_intr, "INTR ") \ EM(netfs_rreq_trace_ki_complete, "KI-CMPL") \ EM(netfs_rreq_trace_recollect, "RECLLCT") \ EM(netfs_rreq_trace_redirty, "REDIRTY") \ @@ -169,7 +170,8 @@ EM(netfs_sreq_trace_put_oom, "PUT OOM ") \ EM(netfs_sreq_trace_put_wip, "PUT WIP ") \ EM(netfs_sreq_trace_put_work, "PUT WORK ") \ - E_(netfs_sreq_trace_put_terminated, "PUT TERM ") + EM(netfs_sreq_trace_put_terminated, "PUT TERM ") \ + E_(netfs_sreq_trace_see_failed, "SEE FAILED ") #define netfs_folio_traces \ EM(netfs_folio_is_uptodate, "mod-uptodate") \ diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index e527b24bd824..c89aede3cb12 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -401,8 +401,8 @@ extern "C" { * implementation can multiply the values by 2^6=64. For that reason the padding * must only contain zeros. * index 0 = Y plane, [15:0] z:Y [6:10] little endian - * index 1 = Cr plane, [15:0] z:Cr [6:10] little endian - * index 2 = Cb plane, [15:0] z:Cb [6:10] little endian + * index 1 = Cb plane, [15:0] z:Cb [6:10] little endian + * index 2 = Cr plane, [15:0] z:Cr [6:10] little endian */ #define DRM_FORMAT_S010 fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */ #define DRM_FORMAT_S210 fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */ @@ -414,8 +414,8 @@ extern "C" { * implementation can multiply the values by 2^4=16. For that reason the padding * must only contain zeros. * index 0 = Y plane, [15:0] z:Y [4:12] little endian - * index 1 = Cr plane, [15:0] z:Cr [4:12] little endian - * index 2 = Cb plane, [15:0] z:Cb [4:12] little endian + * index 1 = Cb plane, [15:0] z:Cb [4:12] little endian + * index 2 = Cr plane, [15:0] z:Cr [4:12] little endian */ #define DRM_FORMAT_S012 fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */ #define DRM_FORMAT_S212 fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */ @@ -424,8 +424,8 @@ extern "C" { /* * 3 plane YCbCr * index 0 = Y plane, [15:0] Y little endian - * index 1 = Cr plane, [15:0] Cr little endian - * index 2 = Cb plane, [15:0] Cb little endian + * index 1 = Cb plane, [15:0] Cb little endian + * index 2 = Cr plane, [15:0] Cr little endian */ #define DRM_FORMAT_S016 fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */ #define DRM_FORMAT_S216 fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index ec1c54b5a310..14f634ab9350 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -712,7 +712,7 @@ #define PCI_EXP_LNKCTL2_HASD 0x0020 /* HW Autonomous Speed Disable */ #define PCI_EXP_LNKSTA2 0x32 /* Link Status 2 */ #define PCI_EXP_LNKSTA2_FLIT 0x0400 /* Flit Mode Status */ -#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x32 /* end of v2 EPs w/ link */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 0x34 /* end of v2 EPs w/ link */ #define PCI_EXP_SLTCAP2 0x34 /* Slot Capabilities 2 */ #define PCI_EXP_SLTCAP2_IBPD 0x00000001 /* In-band PD Disable Supported */ #define PCI_EXP_SLTCTL2 0x38 /* Slot Control 2 */ diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index 863c4a00a66b..f69344fe6c08 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -87,10 +87,17 @@ struct rseq_slice_ctrl { }; /* - * struct rseq is aligned on 4 * 8 bytes to ensure it is always - * contained within a single cache-line. + * The original size and alignment of the allocation for struct rseq is + * 32 bytes. * - * A single struct rseq per thread is allowed. + * The allocation size needs to be greater or equal to + * max(getauxval(AT_RSEQ_FEATURE_SIZE), 32), and the allocation needs to + * be aligned on max(getauxval(AT_RSEQ_ALIGN), 32). + * + * As an alternative, userspace is allowed to use both the original size + * and alignment of 32 bytes for backward compatibility. + * + * A single active struct rseq registration per thread is allowed. */ struct rseq { /* @@ -181,9 +188,20 @@ struct rseq { struct rseq_slice_ctrl slice_ctrl; /* + * Before rseq became extensible, its original size was 32 bytes even + * though the active rseq area was only 20 bytes. + * Exposing a 32 bytes feature size would make life needlessly painful + * for userspace. Therefore, add a reserved byte after byte 32 + * to bump the rseq feature size from 32 to 33. + * The next field to be added to the rseq area will be larger + * than one byte, and will replace this reserved byte. + */ + __u8 __reserved; + + /* * Flexible array member at end of structure, after last feature field. */ char end[]; -} __attribute__((aligned(4 * sizeof(__u64)))); +} __attribute__((aligned(32))); #endif /* _UAPI_LINUX_RSEQ_H */ diff --git a/init/Kconfig b/init/Kconfig index c25869cf59c1..b55deae9256c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -153,7 +153,7 @@ config CC_HAS_COUNTED_BY_PTR config CC_HAS_BROKEN_COUNTED_BY_REF bool # https://github.com/llvm/llvm-project/issues/182575 - default y if CC_IS_CLANG && CLANG_VERSION < 220000 + default y if CC_IS_CLANG && CLANG_VERSION < 220100 config CC_HAS_MULTIDIMENSIONAL_NONSTRING def_bool $(success,echo 'char tag[][4] __attribute__((__nonstring__)) = { };' | $(CC) $(CLANG_FLAGS) -x c - -c -o /dev/null -Werror) diff --git a/io_uring/cmd_net.c b/io_uring/cmd_net.c index 57ddaf874611..125a81c520a6 100644 --- a/io_uring/cmd_net.c +++ b/io_uring/cmd_net.c @@ -146,7 +146,7 @@ static int io_uring_cmd_getsockname(struct socket *sock, return -EINVAL; uaddr = u64_to_user_ptr(READ_ONCE(sqe->addr)); - ulen = u64_to_user_ptr(sqe->addr3); + ulen = u64_to_user_ptr(READ_ONCE(sqe->addr3)); peer = READ_ONCE(sqe->optlen); if (peer > 1) return -EINVAL; diff --git a/io_uring/timeout.c b/io_uring/timeout.c index 84dda24f3eb2..cb61d4862fc6 100644 --- a/io_uring/timeout.c +++ b/io_uring/timeout.c @@ -462,7 +462,7 @@ int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) tr->ltimeout = true; if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS)) return -EINVAL; - if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2))) + if (get_timespec64(&tr->ts, u64_to_user_ptr(READ_ONCE(sqe->addr2)))) return -EFAULT; if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0) return -EINVAL; @@ -557,7 +557,7 @@ static int __io_timeout_prep(struct io_kiocb *req, data->req = req; data->flags = flags; - if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr))) + if (get_timespec64(&data->ts, u64_to_user_ptr(READ_ONCE(sqe->addr)))) return -EFAULT; if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0) diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 144f30e740e8..f355cf1c1a16 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -303,7 +303,7 @@ static long arena_map_update_elem(struct bpf_map *map, void *key, return -EOPNOTSUPP; } -static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf, +static int arena_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { return 0; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 26763df6134a..33de68c95ad8 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -548,7 +548,7 @@ static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } -static int array_map_check_btf(const struct bpf_map *map, +static int array_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c index 35e1ddca74d2..b73336c976b7 100644 --- a/kernel/bpf/bloom_filter.c +++ b/kernel/bpf/bloom_filter.c @@ -180,7 +180,7 @@ static long bloom_map_update_elem(struct bpf_map *map, void *key, return -EINVAL; } -static int bloom_map_check_btf(const struct bpf_map *map, +static int bloom_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/bpf_insn_array.c b/kernel/bpf/bpf_insn_array.c index c0286f25ca3c..a2f84afe6f7c 100644 --- a/kernel/bpf/bpf_insn_array.c +++ b/kernel/bpf/bpf_insn_array.c @@ -98,7 +98,7 @@ static long insn_array_delete_elem(struct bpf_map *map, void *key) return -EINVAL; } -static int insn_array_check_btf(const struct bpf_map *map, +static int insn_array_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index b28f07d3a0db..9c96a4477f81 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -107,14 +107,12 @@ static void __bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; - /* If RCU Tasks Trace grace period implies RCU grace period, do - * kfree(), else do kfree_rcu(). + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. */ local_storage = container_of(rcu, struct bpf_local_storage, rcu); - if (rcu_trace_implies_rcu_gp()) - kfree(local_storage); - else - kfree_rcu(local_storage, rcu); + kfree(local_storage); } /* Handle use_kmalloc_nolock == false */ @@ -138,10 +136,11 @@ static void bpf_local_storage_free_rcu(struct rcu_head *rcu) static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { - if (rcu_trace_implies_rcu_gp()) - bpf_local_storage_free_rcu(rcu); - else - call_rcu(rcu, bpf_local_storage_free_rcu); + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. + */ + bpf_local_storage_free_rcu(rcu); } static void bpf_local_storage_free(struct bpf_local_storage *local_storage, @@ -164,16 +163,29 @@ static void bpf_local_storage_free(struct bpf_local_storage *local_storage, bpf_local_storage_free_trace_rcu); } -/* rcu tasks trace callback for use_kmalloc_nolock == false */ -static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) +/* rcu callback for use_kmalloc_nolock == false */ +static void __bpf_selem_free_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); - if (rcu_trace_implies_rcu_gp()) - kfree(selem); - else - kfree_rcu(selem, rcu); + /* bpf_selem_unlink_nofail may have already cleared smap and freed fields. */ + smap = rcu_dereference_check(SDATA(selem)->smap, 1); + + if (smap) + bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); + kfree(selem); +} + +/* rcu tasks trace callback for use_kmalloc_nolock == false */ +static void __bpf_selem_free_trace_rcu(struct rcu_head *rcu) +{ + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. + */ + __bpf_selem_free_rcu(rcu); } /* Handle use_kmalloc_nolock == false */ @@ -181,7 +193,7 @@ static void __bpf_selem_free(struct bpf_local_storage_elem *selem, bool vanilla_rcu) { if (vanilla_rcu) - kfree_rcu(selem, rcu); + call_rcu(&selem->rcu, __bpf_selem_free_rcu); else call_rcu_tasks_trace(&selem->rcu, __bpf_selem_free_trace_rcu); } @@ -195,37 +207,29 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) /* The bpf_local_storage_map_free will wait for rcu_barrier */ smap = rcu_dereference_check(SDATA(selem)->smap, 1); - if (smap) { - migrate_disable(); + if (smap) bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); - migrate_enable(); - } kfree_nolock(selem); } static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { - if (rcu_trace_implies_rcu_gp()) - bpf_selem_free_rcu(rcu); - else - call_rcu(rcu, bpf_selem_free_rcu); + /* + * RCU Tasks Trace grace period implies RCU grace period, do + * kfree() directly. + */ + bpf_selem_free_rcu(rcu); } void bpf_selem_free(struct bpf_local_storage_elem *selem, bool reuse_now) { - struct bpf_local_storage_map *smap; - - smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); - if (!selem->use_kmalloc_nolock) { /* * No uptr will be unpin even when reuse_now == false since uptr * is only supported in task local storage, where * smap->use_kmalloc_nolock == true. */ - if (smap) - bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); __bpf_selem_free(selem, reuse_now); return; } @@ -797,7 +801,7 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr) return 0; } -int bpf_local_storage_map_check_btf(const struct bpf_map *map, +int bpf_local_storage_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) @@ -958,10 +962,9 @@ restart: */ synchronize_rcu(); - if (smap->use_kmalloc_nolock) { - rcu_barrier_tasks_trace(); - rcu_barrier(); - } + /* smap remains in use regardless of kmalloc_nolock, so wait unconditionally. */ + rcu_barrier_tasks_trace(); + rcu_barrier(); kvfree(smap->buckets); bpf_map_area_free(smap); } diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 04171fbc39cb..32b43cb9061b 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -29,6 +29,7 @@ #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/kthread.h> +#include <linux/local_lock.h> #include <linux/completion.h> #include <trace/events/xdp.h> #include <linux/btf_ids.h> @@ -52,6 +53,7 @@ struct xdp_bulk_queue { struct list_head flush_node; struct bpf_cpu_map_entry *obj; unsigned int count; + local_lock_t bq_lock; }; /* Struct for every remote "destination" CPU in map */ @@ -451,6 +453,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, for_each_possible_cpu(i) { bq = per_cpu_ptr(rcpu->bulkq, i); bq->obj = rcpu; + local_lock_init(&bq->bq_lock); } /* Alloc queue */ @@ -722,6 +725,8 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq) struct ptr_ring *q; int i; + lockdep_assert_held(&bq->bq_lock); + if (unlikely(!bq->count)) return; @@ -749,11 +754,15 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq) } /* Runs under RCU-read-side, plus in softirq under NAPI protection. - * Thus, safe percpu variable access. + * Thus, safe percpu variable access. PREEMPT_RT relies on + * local_lock_nested_bh() to serialise access to the per-CPU bq. */ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { - struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); + struct xdp_bulk_queue *bq; + + local_lock_nested_bh(&rcpu->bulkq->bq_lock); + bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) bq_flush_to_queue(bq); @@ -774,6 +783,8 @@ static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) list_add(&bq->flush_node, flush_list); } + + local_unlock_nested_bh(&rcpu->bulkq->bq_lock); } int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, @@ -810,7 +821,9 @@ void __cpu_map_flush(struct list_head *flush_list) struct xdp_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { + local_lock_nested_bh(&bq->obj->bulkq->bq_lock); bq_flush_to_queue(bq); + local_unlock_nested_bh(&bq->obj->bulkq->bq_lock); /* If already running, costs spin_lock_irqsave + smb_mb */ wake_up_process(bq->obj->kthread); diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2625601de76e..3d619d01088e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -45,6 +45,7 @@ * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> +#include <linux/local_lock.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> @@ -60,6 +61,7 @@ struct xdp_dev_bulk_queue { struct net_device *dev_rx; struct bpf_prog *xdp_prog; unsigned int count; + local_lock_t bq_lock; }; struct bpf_dtab_netdev { @@ -381,6 +383,8 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) int to_send = cnt; int i; + lockdep_assert_held(&bq->bq_lock); + if (unlikely(!cnt)) return; @@ -425,10 +429,12 @@ void __dev_flush(struct list_head *flush_list) struct xdp_dev_bulk_queue *bq, *tmp; list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { + local_lock_nested_bh(&bq->dev->xdp_bulkq->bq_lock); bq_xmit_all(bq, XDP_XMIT_FLUSH); bq->dev_rx = NULL; bq->xdp_prog = NULL; __list_del_clearprev(&bq->flush_node); + local_unlock_nested_bh(&bq->dev->xdp_bulkq->bq_lock); } } @@ -451,12 +457,16 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) /* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu * variable access, and map elements stick around. See comment above - * xdp_do_flush() in filter.c. + * xdp_do_flush() in filter.c. PREEMPT_RT relies on local_lock_nested_bh() + * to serialise access to the per-CPU bq. */ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); + struct xdp_dev_bulk_queue *bq; + + local_lock_nested_bh(&dev->xdp_bulkq->bq_lock); + bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) bq_xmit_all(bq, 0); @@ -477,6 +487,8 @@ static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, } bq->q[bq->count++] = xdpf; + + local_unlock_nested_bh(&dev->xdp_bulkq->bq_lock); } static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, @@ -588,18 +600,22 @@ static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifin } /* Get ifindex of each upper device. 'indexes' must be able to hold at - * least MAX_NEST_DEV elements. - * Returns the number of ifindexes added. + * least 'max' elements. + * Returns the number of ifindexes added, or -EOVERFLOW if there are too + * many upper devices. */ -static int get_upper_ifindexes(struct net_device *dev, int *indexes) +static int get_upper_ifindexes(struct net_device *dev, int *indexes, int max) { struct net_device *upper; struct list_head *iter; int n = 0; netdev_for_each_upper_dev_rcu(dev, upper, iter) { + if (n >= max) + return -EOVERFLOW; indexes[n++] = upper->ifindex; } + return n; } @@ -615,7 +631,11 @@ int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, int err; if (exclude_ingress) { - num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); + num_excluded = get_upper_ifindexes(dev_rx, excluded_devices, + ARRAY_SIZE(excluded_devices) - 1); + if (num_excluded < 0) + return num_excluded; + excluded_devices[num_excluded++] = dev_rx->ifindex; } @@ -733,7 +753,11 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, int err; if (exclude_ingress) { - num_excluded = get_upper_ifindexes(dev, excluded_devices); + num_excluded = get_upper_ifindexes(dev, excluded_devices, + ARRAY_SIZE(excluded_devices) - 1); + if (num_excluded < 0) + return num_excluded; + excluded_devices[num_excluded++] = dev->ifindex; } @@ -1115,8 +1139,13 @@ static int dev_map_notification(struct notifier_block *notifier, if (!netdev->xdp_bulkq) return NOTIFY_BAD; - for_each_possible_cpu(cpu) - per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; + for_each_possible_cpu(cpu) { + struct xdp_dev_bulk_queue *bq; + + bq = per_cpu_ptr(netdev->xdp_bulkq, cpu); + bq->dev = netdev; + local_lock_init(&bq->bq_lock); + } break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 3b9d297a53be..bc6bc8bb871d 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -125,6 +125,11 @@ struct htab_elem { char key[] __aligned(8); }; +struct htab_btf_record { + struct btf_record *record; + u32 key_size; +}; + static inline bool htab_is_prealloc(const struct bpf_htab *htab) { return !(htab->map.map_flags & BPF_F_NO_PREALLOC); @@ -457,6 +462,83 @@ static int htab_map_alloc_check(union bpf_attr *attr) return 0; } +static void htab_mem_dtor(void *obj, void *ctx) +{ + struct htab_btf_record *hrec = ctx; + struct htab_elem *elem = obj; + void *map_value; + + if (IS_ERR_OR_NULL(hrec->record)) + return; + + map_value = htab_elem_value(elem, hrec->key_size); + bpf_obj_free_fields(hrec->record, map_value); +} + +static void htab_pcpu_mem_dtor(void *obj, void *ctx) +{ + void __percpu *pptr = *(void __percpu **)obj; + struct htab_btf_record *hrec = ctx; + int cpu; + + if (IS_ERR_OR_NULL(hrec->record)) + return; + + for_each_possible_cpu(cpu) + bpf_obj_free_fields(hrec->record, per_cpu_ptr(pptr, cpu)); +} + +static void htab_dtor_ctx_free(void *ctx) +{ + struct htab_btf_record *hrec = ctx; + + btf_record_free(hrec->record); + kfree(ctx); +} + +static int htab_set_dtor(struct bpf_htab *htab, void (*dtor)(void *, void *)) +{ + u32 key_size = htab->map.key_size; + struct bpf_mem_alloc *ma; + struct htab_btf_record *hrec; + int err; + + /* No need for dtors. */ + if (IS_ERR_OR_NULL(htab->map.record)) + return 0; + + hrec = kzalloc(sizeof(*hrec), GFP_KERNEL); + if (!hrec) + return -ENOMEM; + hrec->key_size = key_size; + hrec->record = btf_record_dup(htab->map.record); + if (IS_ERR(hrec->record)) { + err = PTR_ERR(hrec->record); + kfree(hrec); + return err; + } + ma = htab_is_percpu(htab) ? &htab->pcpu_ma : &htab->ma; + bpf_mem_alloc_set_dtor(ma, dtor, htab_dtor_ctx_free, hrec); + return 0; +} + +static int htab_map_check_btf(struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, const struct btf_type *value_type) +{ + struct bpf_htab *htab = container_of(map, struct bpf_htab, map); + + if (htab_is_prealloc(htab)) + return 0; + /* + * We must set the dtor using this callback, as map's BTF record is not + * populated in htab_map_alloc(), so it will always appear as NULL. + */ + if (htab_is_percpu(htab)) + return htab_set_dtor(htab, htab_pcpu_mem_dtor); + else + return htab_set_dtor(htab, htab_mem_dtor); +} + static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || @@ -2281,6 +2363,7 @@ const struct bpf_map_ops htab_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab), .map_btf_id = &htab_map_btf_ids[0], @@ -2303,6 +2386,7 @@ const struct bpf_map_ops htab_lru_map_ops = { .map_seq_show_elem = htab_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru), .map_btf_id = &htab_map_btf_ids[0], @@ -2482,6 +2566,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_percpu), .map_btf_id = &htab_map_btf_ids[0], @@ -2502,6 +2587,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_seq_show_elem = htab_percpu_map_seq_show_elem, .map_set_for_each_callback_args = map_set_for_each_callback_args, .map_for_each_callback = bpf_for_each_hash_elem, + .map_check_btf = htab_map_check_btf, .map_mem_usage = htab_map_mem_usage, BATCH_OPS(htab_lru_percpu), .map_btf_id = &htab_map_btf_ids[0], diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 1ccbf28b2ad9..8fca0c64f7b1 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -364,7 +364,7 @@ static long cgroup_storage_delete_elem(struct bpf_map *map, void *key) return -EINVAL; } -static int cgroup_storage_check_btf(const struct bpf_map *map, +static int cgroup_storage_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1adeb4d3b8cf..0f57608b385d 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -751,7 +751,7 @@ free_stack: return err; } -static int trie_check_btf(const struct bpf_map *map, +static int trie_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index bd45dda9dc35..682a9f34214b 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -102,6 +102,8 @@ struct bpf_mem_cache { int percpu_size; bool draining; struct bpf_mem_cache *tgt; + void (*dtor)(void *obj, void *ctx); + void *dtor_ctx; /* list of objects to be freed after RCU GP */ struct llist_head free_by_rcu; @@ -260,12 +262,14 @@ static void free_one(void *obj, bool percpu) kfree(obj); } -static int free_all(struct llist_node *llnode, bool percpu) +static int free_all(struct bpf_mem_cache *c, struct llist_node *llnode, bool percpu) { struct llist_node *pos, *t; int cnt = 0; llist_for_each_safe(pos, t, llnode) { + if (c->dtor) + c->dtor((void *)pos + LLIST_NODE_SZ, c->dtor_ctx); free_one(pos, percpu); cnt++; } @@ -276,7 +280,7 @@ static void __free_rcu(struct rcu_head *head) { struct bpf_mem_cache *c = container_of(head, struct bpf_mem_cache, rcu_ttrace); - free_all(llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); + free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), !!c->percpu_size); atomic_set(&c->call_rcu_ttrace_in_progress, 0); } @@ -308,7 +312,7 @@ static void do_call_rcu_ttrace(struct bpf_mem_cache *c) if (atomic_xchg(&c->call_rcu_ttrace_in_progress, 1)) { if (unlikely(READ_ONCE(c->draining))) { llnode = llist_del_all(&c->free_by_rcu_ttrace); - free_all(llnode, !!c->percpu_size); + free_all(c, llnode, !!c->percpu_size); } return; } @@ -417,7 +421,7 @@ static void check_free_by_rcu(struct bpf_mem_cache *c) dec_active(c, &flags); if (unlikely(READ_ONCE(c->draining))) { - free_all(llist_del_all(&c->waiting_for_gp), !!c->percpu_size); + free_all(c, llist_del_all(&c->waiting_for_gp), !!c->percpu_size); atomic_set(&c->call_rcu_in_progress, 0); } else { call_rcu_hurry(&c->rcu, __free_by_rcu); @@ -635,13 +639,13 @@ static void drain_mem_cache(struct bpf_mem_cache *c) * Except for waiting_for_gp_ttrace list, there are no concurrent operations * on these lists, so it is safe to use __llist_del_all(). */ - free_all(llist_del_all(&c->free_by_rcu_ttrace), percpu); - free_all(llist_del_all(&c->waiting_for_gp_ttrace), percpu); - free_all(__llist_del_all(&c->free_llist), percpu); - free_all(__llist_del_all(&c->free_llist_extra), percpu); - free_all(__llist_del_all(&c->free_by_rcu), percpu); - free_all(__llist_del_all(&c->free_llist_extra_rcu), percpu); - free_all(llist_del_all(&c->waiting_for_gp), percpu); + free_all(c, llist_del_all(&c->free_by_rcu_ttrace), percpu); + free_all(c, llist_del_all(&c->waiting_for_gp_ttrace), percpu); + free_all(c, __llist_del_all(&c->free_llist), percpu); + free_all(c, __llist_del_all(&c->free_llist_extra), percpu); + free_all(c, __llist_del_all(&c->free_by_rcu), percpu); + free_all(c, __llist_del_all(&c->free_llist_extra_rcu), percpu); + free_all(c, llist_del_all(&c->waiting_for_gp), percpu); } static void check_mem_cache(struct bpf_mem_cache *c) @@ -680,6 +684,9 @@ static void check_leaked_objs(struct bpf_mem_alloc *ma) static void free_mem_alloc_no_barrier(struct bpf_mem_alloc *ma) { + /* We can free dtor ctx only once all callbacks are done using it. */ + if (ma->dtor_ctx_free) + ma->dtor_ctx_free(ma->dtor_ctx); check_leaked_objs(ma); free_percpu(ma->cache); free_percpu(ma->caches); @@ -1014,3 +1021,32 @@ int bpf_mem_alloc_check_size(bool percpu, size_t size) return 0; } + +void bpf_mem_alloc_set_dtor(struct bpf_mem_alloc *ma, void (*dtor)(void *obj, void *ctx), + void (*dtor_ctx_free)(void *ctx), void *ctx) +{ + struct bpf_mem_caches *cc; + struct bpf_mem_cache *c; + int cpu, i; + + ma->dtor_ctx_free = dtor_ctx_free; + ma->dtor_ctx = ctx; + + if (ma->cache) { + for_each_possible_cpu(cpu) { + c = per_cpu_ptr(ma->cache, cpu); + c->dtor = dtor; + c->dtor_ctx = ctx; + } + } + if (ma->caches) { + for_each_possible_cpu(cpu) { + cc = per_cpu_ptr(ma->caches, cpu); + for (i = 0; i < NUM_CACHES; i++) { + c = &cc->cache[i]; + c->dtor = dtor; + c->dtor_ctx = ctx; + } + } + } +} diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0378e83b4099..274039e36465 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1234,7 +1234,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) } EXPORT_SYMBOL_GPL(bpf_obj_name_cpy); -int map_check_no_btf(const struct bpf_map *map, +int map_check_no_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index 26fbfbb01700..4abc359b3db0 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -269,3 +269,59 @@ struct tnum tnum_bswap64(struct tnum a) { return TNUM(swab64(a.value), swab64(a.mask)); } + +/* Given tnum t, and a number z such that tmin <= z < tmax, where tmin + * is the smallest member of the t (= t.value) and tmax is the largest + * member of t (= t.value | t.mask), returns the smallest member of t + * larger than z. + * + * For example, + * t = x11100x0 + * z = 11110001 (241) + * result = 11110010 (242) + * + * Note: if this function is called with z >= tmax, it just returns + * early with tmax; if this function is called with z < tmin, the + * algorithm already returns tmin. + */ +u64 tnum_step(struct tnum t, u64 z) +{ + u64 tmax, j, p, q, r, s, v, u, w, res; + u8 k; + + tmax = t.value | t.mask; + + /* if z >= largest member of t, return largest member of t */ + if (z >= tmax) + return tmax; + + /* if z < smallest member of t, return smallest member of t */ + if (z < t.value) + return t.value; + + /* keep t's known bits, and match all unknown bits to z */ + j = t.value | (z & t.mask); + + if (j > z) { + p = ~z & t.value & ~t.mask; + k = fls64(p); /* k is the most-significant 0-to-1 flip */ + q = U64_MAX << k; + r = q & z; /* positions > k matched to z */ + s = ~q & t.value; /* positions <= k matched to t.value */ + v = r | s; + res = v; + } else { + p = z & ~t.value & ~t.mask; + k = fls64(p); /* k is the most-significant 1-to-0 flip */ + q = U64_MAX << k; + r = q & t.mask & z; /* unknown positions > k, matched to z */ + s = q & ~t.mask; /* known positions > k, set to 1 */ + v = r | s; + /* add 1 to unknown positions > k to make value greater than z */ + u = v + (1ULL << k); + /* extract bits in unknown positions > k from u, rest from t.value */ + w = (u & t.mask) | t.value; + res = w; + } + return res; +} diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bb12ba020649..401d6c4960ec 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2379,6 +2379,9 @@ static void __update_reg32_bounds(struct bpf_reg_state *reg) static void __update_reg64_bounds(struct bpf_reg_state *reg) { + u64 tnum_next, tmax; + bool umin_in_tnum; + /* min signed is max(sign bit) | min(other bits) */ reg->smin_value = max_t(s64, reg->smin_value, reg->var_off.value | (reg->var_off.mask & S64_MIN)); @@ -2388,6 +2391,33 @@ static void __update_reg64_bounds(struct bpf_reg_state *reg) reg->umin_value = max(reg->umin_value, reg->var_off.value); reg->umax_value = min(reg->umax_value, reg->var_off.value | reg->var_off.mask); + + /* Check if u64 and tnum overlap in a single value */ + tnum_next = tnum_step(reg->var_off, reg->umin_value); + umin_in_tnum = (reg->umin_value & ~reg->var_off.mask) == reg->var_off.value; + tmax = reg->var_off.value | reg->var_off.mask; + if (umin_in_tnum && tnum_next > reg->umax_value) { + /* The u64 range and the tnum only overlap in umin. + * u64: ---[xxxxxx]----- + * tnum: --xx----------x- + */ + ___mark_reg_known(reg, reg->umin_value); + } else if (!umin_in_tnum && tnum_next == tmax) { + /* The u64 range and the tnum only overlap in the maximum value + * represented by the tnum, called tmax. + * u64: ---[xxxxxx]----- + * tnum: xx-----x-------- + */ + ___mark_reg_known(reg, tmax); + } else if (!umin_in_tnum && tnum_next <= reg->umax_value && + tnum_step(reg->var_off, tnum_next) > reg->umax_value) { + /* The u64 range and the tnum only overlap in between umin + * (excluded) and umax. + * u64: ---[xxxxxx]----- + * tnum: xx----x-------x- + */ + ___mark_reg_known(reg, tnum_next); + } } static void __update_reg_bounds(struct bpf_reg_state *reg) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c22cda7766d8..be1d71dda317 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2608,6 +2608,7 @@ static void cgroup_migrate_add_task(struct task_struct *task, mgctx->tset.nr_tasks++; + css_set_skip_task_iters(cset, task); list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 9faf34377a88..e200de7c60b6 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -62,6 +62,75 @@ static const char * const perr_strings[] = { }; /* + * CPUSET Locking Convention + * ------------------------- + * + * Below are the four global/local locks guarding cpuset structures in lock + * acquisition order: + * - cpuset_top_mutex + * - cpu_hotplug_lock (cpus_read_lock/cpus_write_lock) + * - cpuset_mutex + * - callback_lock (raw spinlock) + * + * As cpuset will now indirectly flush a number of different workqueues in + * housekeeping_update() to update housekeeping cpumasks when the set of + * isolated CPUs is going to be changed, it may be vulnerable to deadlock + * if we hold cpus_read_lock while calling into housekeeping_update(). + * + * The first cpuset_top_mutex will be held except when calling into + * cpuset_handle_hotplug() from the CPU hotplug code where cpus_write_lock + * and cpuset_mutex will be held instead. The main purpose of this mutex + * is to prevent regular cpuset control file write actions from interfering + * with the call to housekeeping_update(), though CPU hotplug operation can + * still happen in parallel. This mutex also provides protection for some + * internal variables. + * + * A task must hold all the remaining three locks to modify externally visible + * or used fields of cpusets, though some of the internally used cpuset fields + * and internal variables can be modified without holding callback_lock. If only + * reliable read access of the externally used fields are needed, a task can + * hold either cpuset_mutex or callback_lock which are exposed to other + * external subsystems. + * + * If a task holds cpu_hotplug_lock and cpuset_mutex, it blocks others, + * ensuring that it is the only task able to also acquire callback_lock and + * be able to modify cpusets. It can perform various checks on the cpuset + * structure first, knowing nothing will change. It can also allocate memory + * without holding callback_lock. While it is performing these checks, various + * callback routines can briefly acquire callback_lock to query cpusets. Once + * it is ready to make the changes, it takes callback_lock, blocking everyone + * else. + * + * Calls to the kernel memory allocator cannot be made while holding + * callback_lock which is a spinlock, as the memory allocator may sleep or + * call back into cpuset code and acquire callback_lock. + * + * Now, the task_struct fields mems_allowed and mempolicy may be changed + * by other task, we use alloc_lock in the task_struct fields to protect + * them. + * + * The cpuset_common_seq_show() handlers only hold callback_lock across + * small pieces of code, such as when reading out possibly multi-word + * cpumasks and nodemasks. + */ + +static DEFINE_MUTEX(cpuset_top_mutex); +static DEFINE_MUTEX(cpuset_mutex); + +/* + * File level internal variables below follow one of the following exclusion + * rules. + * + * RWCS: Read/write-able by holding either cpus_write_lock (and optionally + * cpuset_mutex) or both cpus_read_lock and cpuset_mutex. + * + * CSCB: Readable by holding either cpuset_mutex or callback_lock. Writable + * by holding both cpuset_mutex and callback_lock. + * + * T: Read/write-able by holding the cpuset_top_mutex. + */ + +/* * For local partitions, update to subpartitions_cpus & isolated_cpus is done * in update_parent_effective_cpumask(). For remote partitions, it is done in * the remote_partition_*() and remote_cpus_update() helpers. @@ -70,19 +139,22 @@ static const char * const perr_strings[] = { * Exclusive CPUs distributed out to local or remote sub-partitions of * top_cpuset */ -static cpumask_var_t subpartitions_cpus; +static cpumask_var_t subpartitions_cpus; /* RWCS */ + +/* + * Exclusive CPUs in isolated partitions (shown in cpuset.cpus.isolated) + */ +static cpumask_var_t isolated_cpus; /* CSCB */ /* - * Exclusive CPUs in isolated partitions + * Set if housekeeping cpumasks are to be updated. */ -static cpumask_var_t isolated_cpus; +static bool update_housekeeping; /* RWCS */ /* - * isolated_cpus updating flag (protected by cpuset_mutex) - * Set if isolated_cpus is going to be updated in the current - * cpuset_mutex crtical section. + * Copy of isolated_cpus to be passed to housekeeping_update() */ -static bool isolated_cpus_updating; +static cpumask_var_t isolated_hk_cpus; /* T */ /* * A flag to force sched domain rebuild at the end of an operation. @@ -98,7 +170,7 @@ static bool isolated_cpus_updating; * Note that update_relax_domain_level() in cpuset-v1.c can still call * rebuild_sched_domains_locked() directly without using this flag. */ -static bool force_sd_rebuild; +static bool force_sd_rebuild; /* RWCS */ /* * Partition root states: @@ -218,42 +290,6 @@ struct cpuset top_cpuset = { .partition_root_state = PRS_ROOT, }; -/* - * There are two global locks guarding cpuset structures - cpuset_mutex and - * callback_lock. The cpuset code uses only cpuset_mutex. Other kernel - * subsystems can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset - * structures. Note that cpuset_mutex needs to be a mutex as it is used in - * paths that rely on priority inheritance (e.g. scheduler - on RT) for - * correctness. - * - * A task must hold both locks to modify cpusets. If a task holds - * cpuset_mutex, it blocks others, ensuring that it is the only task able to - * also acquire callback_lock and be able to modify cpusets. It can perform - * various checks on the cpuset structure first, knowing nothing will change. - * It can also allocate memory while just holding cpuset_mutex. While it is - * performing these checks, various callback routines can briefly acquire - * callback_lock to query cpusets. Once it is ready to make the changes, it - * takes callback_lock, blocking everyone else. - * - * Calls to the kernel memory allocator can not be made while holding - * callback_lock, as that would risk double tripping on callback_lock - * from one of the callbacks into the cpuset code from within - * __alloc_pages(). - * - * If a task is only holding callback_lock, then it has read-only - * access to cpusets. - * - * Now, the task_struct fields mems_allowed and mempolicy may be changed - * by other task, we use alloc_lock in the task_struct fields to protect - * them. - * - * The cpuset_common_seq_show() handlers only hold callback_lock across - * small pieces of code, such as when reading out possibly multi-word - * cpumasks and nodemasks. - */ - -static DEFINE_MUTEX(cpuset_mutex); - /** * cpuset_lock - Acquire the global cpuset mutex * @@ -283,6 +319,7 @@ void lockdep_assert_cpuset_lock_held(void) */ void cpuset_full_lock(void) { + mutex_lock(&cpuset_top_mutex); cpus_read_lock(); mutex_lock(&cpuset_mutex); } @@ -291,12 +328,14 @@ void cpuset_full_unlock(void) { mutex_unlock(&cpuset_mutex); cpus_read_unlock(); + mutex_unlock(&cpuset_top_mutex); } #ifdef CONFIG_LOCKDEP bool lockdep_is_cpuset_held(void) { - return lockdep_is_held(&cpuset_mutex); + return lockdep_is_held(&cpuset_mutex) || + lockdep_is_held(&cpuset_top_mutex); } #endif @@ -961,7 +1000,7 @@ void rebuild_sched_domains_locked(void) * offline CPUs, a warning is emitted and we return directly to * prevent the panic. */ - for (i = 0; i < ndoms; ++i) { + for (i = 0; doms && i < ndoms; i++) { if (WARN_ON_ONCE(!cpumask_subset(doms[i], cpu_active_mask))) return; } @@ -1161,12 +1200,18 @@ static void reset_partition_data(struct cpuset *cs) static void isolated_cpus_update(int old_prs, int new_prs, struct cpumask *xcpus) { WARN_ON_ONCE(old_prs == new_prs); - if (new_prs == PRS_ISOLATED) + lockdep_assert_held(&callback_lock); + lockdep_assert_held(&cpuset_mutex); + if (new_prs == PRS_ISOLATED) { + if (cpumask_subset(xcpus, isolated_cpus)) + return; cpumask_or(isolated_cpus, isolated_cpus, xcpus); - else + } else { + if (!cpumask_intersects(xcpus, isolated_cpus)) + return; cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); - - isolated_cpus_updating = true; + } + update_housekeeping = true; } /* @@ -1219,8 +1264,8 @@ static void partition_xcpus_del(int old_prs, struct cpuset *parent, isolated_cpus_update(old_prs, parent->partition_root_state, xcpus); - cpumask_and(xcpus, xcpus, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, xcpus); + cpumask_and(parent->effective_cpus, parent->effective_cpus, cpu_active_mask); } /* @@ -1284,22 +1329,43 @@ static bool prstate_housekeeping_conflict(int prstate, struct cpumask *new_cpus) } /* - * update_isolation_cpumasks - Update external isolation related CPU masks + * update_hk_sched_domains - Update HK cpumasks & rebuild sched domains * - * The following external CPU masks will be updated if necessary: - * - workqueue unbound cpumask + * Update housekeeping cpumasks and rebuild sched domains if necessary. + * This should be called at the end of cpuset or hotplug actions. */ -static void update_isolation_cpumasks(void) +static void update_hk_sched_domains(void) { - int ret; - - if (!isolated_cpus_updating) - return; + if (update_housekeeping) { + /* Updating HK cpumasks implies rebuild sched domains */ + update_housekeeping = false; + force_sd_rebuild = true; + cpumask_copy(isolated_hk_cpus, isolated_cpus); - ret = housekeeping_update(isolated_cpus); - WARN_ON_ONCE(ret < 0); + /* + * housekeeping_update() is now called without holding + * cpus_read_lock and cpuset_mutex. Only cpuset_top_mutex + * is still being held for mutual exclusion. + */ + mutex_unlock(&cpuset_mutex); + cpus_read_unlock(); + WARN_ON_ONCE(housekeeping_update(isolated_hk_cpus)); + cpus_read_lock(); + mutex_lock(&cpuset_mutex); + } + /* force_sd_rebuild will be cleared in rebuild_sched_domains_locked() */ + if (force_sd_rebuild) + rebuild_sched_domains_locked(); +} - isolated_cpus_updating = false; +/* + * Work function to invoke update_hk_sched_domains() + */ +static void hk_sd_workfn(struct work_struct *work) +{ + cpuset_full_lock(); + update_hk_sched_domains(); + cpuset_full_unlock(); } /** @@ -1450,7 +1516,6 @@ static int remote_partition_enable(struct cpuset *cs, int new_prs, cs->remote_partition = true; cpumask_copy(cs->effective_xcpus, tmp->new_cpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); cs->prs_err = 0; @@ -1495,7 +1560,6 @@ static void remote_partition_disable(struct cpuset *cs, struct tmpmasks *tmp) compute_excpus(cs, cs->effective_xcpus); reset_partition_data(cs); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); cpuset_force_rebuild(); /* @@ -1566,7 +1630,6 @@ static void remote_cpus_update(struct cpuset *cs, struct cpumask *xcpus, if (xcpus) cpumask_copy(cs->exclusive_cpus, xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if (adding || deleting) cpuset_force_rebuild(); @@ -1910,7 +1973,6 @@ write_error: partition_xcpus_add(new_prs, parent, tmp->delmask); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); if ((old_prs != new_prs) && (cmd == partcmd_update)) update_partition_exclusive_flag(cs, new_prs); @@ -2155,7 +2217,7 @@ get_css: WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); - cpuset_update_tasks_cpumask(cp, cp->effective_cpus); + cpuset_update_tasks_cpumask(cp, tmp->new_cpus); /* * On default hierarchy, inherit the CS_SCHED_LOAD_BALANCE @@ -2878,7 +2940,6 @@ out: else if (isolcpus_updated) isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); - update_isolation_cpumasks(); /* Force update if switching back to member & update effective_xcpus */ update_cpumasks_hier(cs, &tmpmask, !new_prs); @@ -3168,9 +3229,8 @@ ssize_t cpuset_write_resmask(struct kernfs_open_file *of, } free_cpuset(trialcs); - if (force_sd_rebuild) - rebuild_sched_domains_locked(); out_unlock: + update_hk_sched_domains(); cpuset_full_unlock(); if (of_cft(of)->private == FILE_MEMLIST) schedule_flush_migrate_mm(); @@ -3278,6 +3338,7 @@ static ssize_t cpuset_partition_write(struct kernfs_open_file *of, char *buf, cpuset_full_lock(); if (is_cpuset_online(cs)) retval = update_prstate(cs, val); + update_hk_sched_domains(); cpuset_full_unlock(); return retval ?: nbytes; } @@ -3452,6 +3513,7 @@ static void cpuset_css_killed(struct cgroup_subsys_state *css) /* Reset valid partition back to member */ if (is_partition_valid(cs)) update_prstate(cs, PRS_MEMBER); + update_hk_sched_domains(); cpuset_full_unlock(); } @@ -3607,6 +3669,7 @@ int __init cpuset_init(void) BUG_ON(!alloc_cpumask_var(&top_cpuset.exclusive_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&subpartitions_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&isolated_cpus, GFP_KERNEL)); + BUG_ON(!zalloc_cpumask_var(&isolated_hk_cpus, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); nodes_setall(top_cpuset.mems_allowed); @@ -3778,6 +3841,7 @@ unlock: */ static void cpuset_handle_hotplug(void) { + static DECLARE_WORK(hk_sd_work, hk_sd_workfn); static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; @@ -3859,9 +3923,21 @@ static void cpuset_handle_hotplug(void) rcu_read_unlock(); } - /* rebuild sched domains if necessary */ - if (force_sd_rebuild) - rebuild_sched_domains_cpuslocked(); + + /* + * Queue a work to call housekeeping_update() & rebuild_sched_domains() + * There will be a slight delay before the HK_TYPE_DOMAIN housekeeping + * cpumask can correctly reflect what is in isolated_cpus. + * + * We rely on WORK_STRUCT_PENDING_BIT to not requeue a work item that + * is still pending. Before the pending bit is cleared, the work data + * is copied out and work item dequeued. So it is possible to queue + * the work again before the hk_sd_workfn() is invoked to process the + * previously queued work. Since hk_sd_workfn() doesn't use the work + * item at all, this is not a problem. + */ + if (update_housekeeping || force_sd_rebuild) + queue_work(system_unbound_wq, &hk_sd_work); free_tmpmasks(ptmp); } diff --git a/kernel/dma/direct.h b/kernel/dma/direct.h index f476c63b668c..e89f175e9c2d 100644 --- a/kernel/dma/direct.h +++ b/kernel/dma/direct.h @@ -85,7 +85,7 @@ static inline dma_addr_t dma_direct_map_phys(struct device *dev, if (is_swiotlb_force_bounce(dev)) { if (attrs & DMA_ATTR_MMIO) - goto err_overflow; + return DMA_MAPPING_ERROR; return swiotlb_map(dev, phys, size, dir, attrs); } diff --git a/kernel/events/core.c b/kernel/events/core.c index ac70d68217b6..1f5699b339ec 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4138,7 +4138,8 @@ static int merge_sched_in(struct perf_event *event, void *data) if (*perf_event_fasync(event)) event->pending_kill = POLL_ERR; - perf_event_wakeup(event); + event->pending_wakeup = 1; + irq_work_queue(&event->pending_irq); } else { struct perf_cpu_pmu_context *cpc = this_cpc(event->pmu_ctx->pmu); @@ -7464,28 +7465,28 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) ret = perf_mmap_aux(vma, event, nr_pages); if (ret) return ret; - } - /* - * Since pinned accounting is per vm we cannot allow fork() to copy our - * vma. - */ - vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); - vma->vm_ops = &perf_mmap_vmops; + /* + * Since pinned accounting is per vm we cannot allow fork() to copy our + * vma. + */ + vm_flags_set(vma, VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP); + vma->vm_ops = &perf_mmap_vmops; - mapped = get_mapped(event, event_mapped); - if (mapped) - mapped(event, vma->vm_mm); + mapped = get_mapped(event, event_mapped); + if (mapped) + mapped(event, vma->vm_mm); - /* - * Try to map it into the page table. On fail, invoke - * perf_mmap_close() to undo the above, as the callsite expects - * full cleanup in this case and therefore does not invoke - * vmops::close(). - */ - ret = map_range(event->rb, vma); - if (ret) - perf_mmap_close(vma); + /* + * Try to map it into the page table. On fail, invoke + * perf_mmap_close() to undo the above, as the callsite expects + * full cleanup in this case and therefore does not invoke + * vmops::close(). + */ + ret = map_range(event->rb, vma); + if (ret) + perf_mmap_close(vma); + } return ret; } @@ -10776,6 +10777,13 @@ int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { + /* + * Entry point from hardware PMI, interrupts should be disabled here. + * This serializes us against perf_event_remove_from_context() in + * things like perf_event_release_kernel(). + */ + lockdep_assert_irqs_disabled(); + return __perf_event_overflow(event, 1, data, regs); } @@ -10852,6 +10860,19 @@ static void perf_swevent_event(struct perf_event *event, u64 nr, { struct hw_perf_event *hwc = &event->hw; + /* + * This is: + * - software preempt + * - tracepoint preempt + * - tp_target_task irq (ctx->lock) + * - uprobes preempt/irq + * - kprobes preempt/irq + * - hw_breakpoint irq + * + * Any of these are sufficient to hold off RCU and thus ensure @event + * exists. + */ + lockdep_assert_preemption_disabled(); local64_add(nr, &event->count); if (!regs) @@ -10860,6 +10881,16 @@ static void perf_swevent_event(struct perf_event *event, u64 nr, if (!is_sampling_event(event)) return; + /* + * Serialize against event_function_call() IPIs like normal overflow + * event handling. Specifically, must not allow + * perf_event_release_kernel() -> perf_remove_from_context() to make + * progress and 'release' the event from under us. + */ + guard(irqsave)(); + if (event->state != PERF_EVENT_STATE_ACTIVE) + return; + if ((event->attr.sample_type & PERF_SAMPLE_PERIOD) && !event->attr.freq) { data->period = nr; return perf_swevent_overflow(event, 1, data, regs); @@ -11358,6 +11389,11 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct perf_sample_data data; struct perf_event *event; + /* + * Per being a tracepoint, this runs with preemption disabled. + */ + lockdep_assert_preemption_disabled(); + struct perf_raw_record raw = { .frag = { .size = entry_size, @@ -11690,6 +11726,11 @@ void perf_bp_event(struct perf_event *bp, void *data) struct perf_sample_data sample; struct pt_regs *regs = data; + /* + * Exception context, will have interrupts disabled. + */ + lockdep_assert_irqs_disabled(); + perf_sample_data_init(&sample, bp->attr.bp_addr, 0); if (!bp->hw.state && !perf_exclude_event(bp, regs)) @@ -12154,7 +12195,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) if (regs && !perf_exclude_event(event, regs)) { if (!(event->attr.exclude_idle && is_idle_task(current))) - if (__perf_event_overflow(event, 1, &data, regs)) + if (perf_event_overflow(event, &data, regs)) ret = HRTIMER_NORESTART; } diff --git a/kernel/exit.c b/kernel/exit.c index 8a87021211ae..ede3117fa7d4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -896,11 +896,16 @@ static void synchronize_group_exit(struct task_struct *tsk, long code) void __noreturn do_exit(long code) { struct task_struct *tsk = current; + struct kthread *kthread; int group_dead; WARN_ON(irqs_disabled()); WARN_ON(tsk->plug); + kthread = tsk_is_kthread(tsk); + if (unlikely(kthread)) + kthread_do_exit(kthread, code); + kcov_task_exit(tsk); kmsan_task_exit(tsk); @@ -1013,6 +1018,7 @@ void __noreturn do_exit(long code) lockdep_free_task(tsk); do_task_dead(); } +EXPORT_SYMBOL(do_exit); void __noreturn make_task_dead(int signr) { diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index 79e655ea4ca1..ae758150ccb9 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -168,7 +168,7 @@ static bool __report_matches(const struct expect_report *r) if (!report_available()) return false; - expect = kmalloc_obj(observed.lines); + expect = (typeof(expect))kmalloc_obj(observed.lines); if (WARN_ON(!expect)) return false; diff --git a/kernel/kthread.c b/kernel/kthread.c index 20451b624b67..791210daf8b4 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -85,24 +85,6 @@ static inline struct kthread *to_kthread(struct task_struct *k) return k->worker_private; } -/* - * Variant of to_kthread() that doesn't assume @p is a kthread. - * - * When "(p->flags & PF_KTHREAD)" is set the task is a kthread and will - * always remain a kthread. For kthreads p->worker_private always - * points to a struct kthread. For tasks that are not kthreads - * p->worker_private is used to point to other things. - * - * Return NULL for any task that is not a kthread. - */ -static inline struct kthread *__to_kthread(struct task_struct *p) -{ - void *kthread = p->worker_private; - if (kthread && !(p->flags & PF_KTHREAD)) - kthread = NULL; - return kthread; -} - void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) { struct kthread *kthread = to_kthread(tsk); @@ -193,7 +175,7 @@ EXPORT_SYMBOL_GPL(kthread_should_park); bool kthread_should_stop_or_park(void) { - struct kthread *kthread = __to_kthread(current); + struct kthread *kthread = tsk_is_kthread(current); if (!kthread) return false; @@ -234,7 +216,7 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); */ void *kthread_func(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); if (kthread) return kthread->threadfn; return NULL; @@ -266,7 +248,7 @@ EXPORT_SYMBOL_GPL(kthread_data); */ void *kthread_probe_data(struct task_struct *task) { - struct kthread *kthread = __to_kthread(task); + struct kthread *kthread = tsk_is_kthread(task); void *data = NULL; if (kthread) @@ -309,19 +291,8 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); -/** - * kthread_exit - Cause the current kthread return @result to kthread_stop(). - * @result: The integer value to return to kthread_stop(). - * - * While kthread_exit can be called directly, it exists so that - * functions which do some additional work in non-modular code such as - * module_put_and_kthread_exit can be implemented. - * - * Does not return. - */ -void __noreturn kthread_exit(long result) +void kthread_do_exit(struct kthread *kthread, long result) { - struct kthread *kthread = to_kthread(current); kthread->result = result; if (!list_empty(&kthread->affinity_node)) { mutex_lock(&kthread_affinity_lock); @@ -333,9 +304,7 @@ void __noreturn kthread_exit(long result) kthread->preferred_affinity = NULL; } } - do_exit(0); } -EXPORT_SYMBOL(kthread_exit); /** * kthread_complete_and_exit - Exit the current kthread. @@ -683,7 +652,7 @@ void kthread_set_per_cpu(struct task_struct *k, int cpu) bool kthread_is_per_cpu(struct task_struct *p) { - struct kthread *kthread = __to_kthread(p); + struct kthread *kthread = tsk_is_kthread(p); if (!kthread) return false; diff --git a/kernel/liveupdate/luo_file.c b/kernel/liveupdate/luo_file.c index 8c79058253e1..5acee4174bf0 100644 --- a/kernel/liveupdate/luo_file.c +++ b/kernel/liveupdate/luo_file.c @@ -134,9 +134,12 @@ static LIST_HEAD(luo_file_handler_list); * state that is not preserved. Set by the handler's .preserve() * callback, and must be freed in the handler's .unpreserve() * callback. - * @retrieved: A flag indicating whether a user/kernel in the new kernel has + * @retrieve_status: Status code indicating whether a user/kernel in the new kernel has * successfully called retrieve() on this file. This prevents - * multiple retrieval attempts. + * multiple retrieval attempts. A value of 0 means a retrieve() + * has not been attempted, a positive value means the retrieve() + * was successful, and a negative value means the retrieve() + * failed, and the value is the error code of the call. * @mutex: A mutex that protects the fields of this specific instance * (e.g., @retrieved, @file), ensuring that operations like * retrieving or finishing a file are atomic. @@ -161,7 +164,7 @@ struct luo_file { struct file *file; u64 serialized_data; void *private_data; - bool retrieved; + int retrieve_status; struct mutex mutex; struct list_head list; u64 token; @@ -298,7 +301,6 @@ int luo_preserve_file(struct luo_file_set *file_set, u64 token, int fd) luo_file->file = file; luo_file->fh = fh; luo_file->token = token; - luo_file->retrieved = false; mutex_init(&luo_file->mutex); args.handler = fh; @@ -577,7 +579,12 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token, return -ENOENT; guard(mutex)(&luo_file->mutex); - if (luo_file->retrieved) { + if (luo_file->retrieve_status < 0) { + /* Retrieve was attempted and it failed. Return the error code. */ + return luo_file->retrieve_status; + } + + if (luo_file->retrieve_status > 0) { /* * Someone is asking for this file again, so get a reference * for them. @@ -590,16 +597,19 @@ int luo_retrieve_file(struct luo_file_set *file_set, u64 token, args.handler = luo_file->fh; args.serialized_data = luo_file->serialized_data; err = luo_file->fh->ops->retrieve(&args); - if (!err) { - luo_file->file = args.file; - - /* Get reference so we can keep this file in LUO until finish */ - get_file(luo_file->file); - *filep = luo_file->file; - luo_file->retrieved = true; + if (err) { + /* Keep the error code for later use. */ + luo_file->retrieve_status = err; + return err; } - return err; + luo_file->file = args.file; + /* Get reference so we can keep this file in LUO until finish */ + get_file(luo_file->file); + *filep = luo_file->file; + luo_file->retrieve_status = 1; + + return 0; } static int luo_file_can_finish_one(struct luo_file_set *file_set, @@ -615,7 +625,7 @@ static int luo_file_can_finish_one(struct luo_file_set *file_set, args.handler = luo_file->fh; args.file = luo_file->file; args.serialized_data = luo_file->serialized_data; - args.retrieved = luo_file->retrieved; + args.retrieve_status = luo_file->retrieve_status; can_finish = luo_file->fh->ops->can_finish(&args); } @@ -632,7 +642,7 @@ static void luo_file_finish_one(struct luo_file_set *file_set, args.handler = luo_file->fh; args.file = luo_file->file; args.serialized_data = luo_file->serialized_data; - args.retrieved = luo_file->retrieved; + args.retrieve_status = luo_file->retrieve_status; luo_file->fh->ops->finish(&args); luo_flb_file_finish(luo_file->fh); @@ -788,7 +798,6 @@ int luo_file_deserialize(struct luo_file_set *file_set, luo_file->file = NULL; luo_file->serialized_data = file_ser[i].data; luo_file->token = file_ser[i].token; - luo_file->retrieved = false; mutex_init(&luo_file->mutex); list_add_tail(&luo_file->list, &file_set->files_list); } diff --git a/kernel/module/Kconfig b/kernel/module/Kconfig index be74917802ad..43b1bb01fd27 100644 --- a/kernel/module/Kconfig +++ b/kernel/module/Kconfig @@ -169,9 +169,10 @@ config MODVERSIONS make them incompatible with the kernel you are running. If unsure, say N. +if MODVERSIONS + choice prompt "Module versioning implementation" - depends on MODVERSIONS help Select the tool used to calculate symbol versions for modules. @@ -206,7 +207,7 @@ endchoice config ASM_MODVERSIONS bool - default HAVE_ASM_MODVERSIONS && MODVERSIONS + default HAVE_ASM_MODVERSIONS help This enables module versioning for exported symbols also from assembly. This can be enabled only when the target architecture @@ -214,7 +215,6 @@ config ASM_MODVERSIONS config EXTENDED_MODVERSIONS bool "Extended Module Versioning Support" - depends on MODVERSIONS help This enables extended MODVERSIONs support, allowing long symbol names to be versioned. @@ -224,7 +224,6 @@ config EXTENDED_MODVERSIONS config BASIC_MODVERSIONS bool "Basic Module Versioning Support" - depends on MODVERSIONS default y help This enables basic MODVERSIONS support, allowing older tools or @@ -237,6 +236,8 @@ config BASIC_MODVERSIONS This is enabled by default when MODVERSIONS are enabled. If unsure, say Y. +endif # MODVERSIONS + config MODULE_SRCVERSION_ALL bool "Source checksum for all modules" help @@ -277,10 +278,11 @@ config MODULE_SIG_FORCE Reject unsigned modules or signed modules for which we don't have a key. Without this, such modules will simply taint the kernel. +if MODULE_SIG || IMA_APPRAISE_MODSIG + config MODULE_SIG_ALL bool "Automatically sign all modules" default y - depends on MODULE_SIG || IMA_APPRAISE_MODSIG help Sign all modules during make modules_install. Without this option, modules must be signed manually, using the scripts/sign-file tool. @@ -290,7 +292,6 @@ comment "Do not forget to sign required modules with scripts/sign-file" choice prompt "Hash algorithm to sign modules" - depends on MODULE_SIG || IMA_APPRAISE_MODSIG default MODULE_SIG_SHA512 help This determines which sort of hashing algorithm will be used during @@ -327,7 +328,6 @@ endchoice config MODULE_SIG_HASH string - depends on MODULE_SIG || IMA_APPRAISE_MODSIG default "sha256" if MODULE_SIG_SHA256 default "sha384" if MODULE_SIG_SHA384 default "sha512" if MODULE_SIG_SHA512 @@ -335,6 +335,8 @@ config MODULE_SIG_HASH default "sha3-384" if MODULE_SIG_SHA3_384 default "sha3-512" if MODULE_SIG_SHA3_512 +endif # MODULE_SIG || IMA_APPRAISE_MODSIG + config MODULE_COMPRESS bool "Module compression" help @@ -350,9 +352,10 @@ config MODULE_COMPRESS If unsure, say N. +if MODULE_COMPRESS + choice prompt "Module compression type" - depends on MODULE_COMPRESS help Choose the supported algorithm for module compression. @@ -379,7 +382,6 @@ endchoice config MODULE_COMPRESS_ALL bool "Automatically compress all modules" default y - depends on MODULE_COMPRESS help Compress all modules during 'make modules_install'. @@ -389,7 +391,6 @@ config MODULE_COMPRESS_ALL config MODULE_DECOMPRESS bool "Support in-kernel module decompression" - depends on MODULE_COMPRESS select ZLIB_INFLATE if MODULE_COMPRESS_GZIP select XZ_DEC if MODULE_COMPRESS_XZ select ZSTD_DECOMPRESS if MODULE_COMPRESS_ZSTD @@ -400,6 +401,8 @@ config MODULE_DECOMPRESS If unsure, say N. +endif # MODULE_COMPRESS + config MODULE_ALLOW_MISSING_NAMESPACE_IMPORTS bool "Allow loading of modules with missing namespace imports" help diff --git a/kernel/module/main.c b/kernel/module/main.c index 2bac4c7cd019..c3ce106c70af 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -1568,6 +1568,13 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) break; default: + if (sym[i].st_shndx >= info->hdr->e_shnum) { + pr_err("%s: Symbol %s has an invalid section index %u (max %u)\n", + mod->name, name, sym[i].st_shndx, info->hdr->e_shnum - 1); + ret = -ENOEXEC; + break; + } + /* Divert to percpu allocation if a percpu var. */ if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); @@ -3544,12 +3551,6 @@ static int load_module(struct load_info *info, const char __user *uargs, mutex_unlock(&module_mutex); free_module: mod_stat_bump_invalid(info, flags); - /* Free lock-classes; relies on the preceding sync_rcu() */ - for_class_mod_mem_type(type, core_data) { - lockdep_free_key_range(mod->mem[type].base, - mod->mem[type].size); - } - module_memory_restore_rox(mod); module_deallocate(mod, info); free_copy: diff --git a/kernel/nscommon.c b/kernel/nscommon.c index bdc3c86231d3..3166c1fd844a 100644 --- a/kernel/nscommon.c +++ b/kernel/nscommon.c @@ -309,3 +309,9 @@ void __ns_ref_active_get(struct ns_common *ns) return; } } + +bool may_see_all_namespaces(void) +{ + return (task_active_pid_ns(current) == &init_pid_ns) && + ns_capable_noaudit(init_pid_ns.user_ns, CAP_SYS_ADMIN); +} diff --git a/kernel/nstree.c b/kernel/nstree.c index f36c59e6951d..6d12e5900ac0 100644 --- a/kernel/nstree.c +++ b/kernel/nstree.c @@ -515,32 +515,11 @@ static inline bool __must_check ns_requested(const struct klistns *kls, static inline bool __must_check may_list_ns(const struct klistns *kls, struct ns_common *ns) { - if (kls->user_ns) { - if (kls->userns_capable) - return true; - } else { - struct ns_common *owner; - struct user_namespace *user_ns; - - owner = ns_owner(ns); - if (owner) - user_ns = to_user_ns(owner); - else - user_ns = &init_user_ns; - if (ns_capable_noaudit(user_ns, CAP_SYS_ADMIN)) - return true; - } - - if (is_current_namespace(ns)) + if (kls->user_ns && kls->userns_capable) return true; - - if (ns->ns_type != CLONE_NEWUSER) - return false; - - if (ns_capable_noaudit(to_user_ns(ns), CAP_SYS_ADMIN)) + if (is_current_namespace(ns)) return true; - - return false; + return may_see_all_namespaces(); } static inline void ns_put(struct ns_common *ns) @@ -600,7 +579,7 @@ static ssize_t do_listns_userns(struct klistns *kls) ret = 0; head = &to_ns_common(kls->user_ns)->ns_owner_root.ns_list_head; - kls->userns_capable = ns_capable_noaudit(kls->user_ns, CAP_SYS_ADMIN); + kls->userns_capable = may_see_all_namespaces(); rcu_read_lock(); diff --git a/kernel/rseq.c b/kernel/rseq.c index b0973d19f366..38d3ef540760 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -80,6 +80,7 @@ #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/types.h> +#include <linux/rseq.h> #include <asm/ptrace.h> #define CREATE_TRACE_POINTS @@ -449,13 +450,14 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32 * auxiliary vector AT_RSEQ_ALIGN. If rseq_len is the original rseq * size, the required alignment is the original struct rseq alignment. * - * In order to be valid, rseq_len is either the original rseq size, or - * large enough to contain all supported fields, as communicated to + * The rseq_len is required to be greater or equal to the original rseq + * size. In order to be valid, rseq_len is either the original rseq size, + * or large enough to contain all supported fields, as communicated to * user-space through the ELF auxiliary vector AT_RSEQ_FEATURE_SIZE. */ if (rseq_len < ORIG_RSEQ_SIZE || (rseq_len == ORIG_RSEQ_SIZE && !IS_ALIGNED((unsigned long)rseq, ORIG_RSEQ_SIZE)) || - (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, __alignof__(*rseq)) || + (rseq_len != ORIG_RSEQ_SIZE && (!IS_ALIGNED((unsigned long)rseq, rseq_alloc_align()) || rseq_len < offsetof(struct rseq, end)))) return -EINVAL; if (!access_ok(rseq, rseq_len)) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 759777694c78..b7f77c165a6e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6830,6 +6830,7 @@ static void __sched notrace __schedule(int sched_mode) /* SCX must consult the BPF scheduler to tell if rq is empty */ if (!rq->nr_running && !scx_enabled()) { next = prev; + rq->next_class = &idle_sched_class; goto picked; } } else if (!preempt && prev_state) { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 62b1f3ac5630..1594987d637b 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -976,8 +976,12 @@ static bool scx_dsq_priq_less(struct rb_node *node_a, static void dsq_mod_nr(struct scx_dispatch_q *dsq, s32 delta) { - /* scx_bpf_dsq_nr_queued() reads ->nr without locking, use WRITE_ONCE() */ - WRITE_ONCE(dsq->nr, dsq->nr + delta); + /* + * scx_bpf_dsq_nr_queued() reads ->nr without locking. Use READ_ONCE() + * on the read side and WRITE_ONCE() on the write side to properly + * annotate the concurrent lockless access and avoid KCSAN warnings. + */ + WRITE_ONCE(dsq->nr, READ_ONCE(dsq->nr) + delta); } static void refill_task_slice_dfl(struct scx_sched *sch, struct task_struct *p) @@ -2460,7 +2464,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) /* see kick_cpus_irq_workfn() */ smp_store_release(&rq->scx.kick_sync, rq->scx.kick_sync + 1); - rq->next_class = &ext_sched_class; + rq_modified_begin(rq, &ext_sched_class); rq_unpin_lock(rq, rf); balance_one(rq, prev); @@ -2475,7 +2479,7 @@ do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) * If @force_scx is true, always try to pick a SCHED_EXT task, * regardless of any higher-priority sched classes activity. */ - if (!force_scx && sched_class_above(rq->next_class, &ext_sched_class)) + if (!force_scx && rq_modified_above(rq, &ext_sched_class)) return RETRY_TASK; keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP; @@ -2735,7 +2739,7 @@ static bool check_rq_for_timeouts(struct rq *rq) unsigned long last_runnable = p->scx.runnable_at; if (unlikely(time_after(jiffies, - last_runnable + scx_watchdog_timeout))) { + last_runnable + READ_ONCE(scx_watchdog_timeout)))) { u32 dur_ms = jiffies_to_msecs(jiffies - last_runnable); scx_exit(sch, SCX_EXIT_ERROR_STALL, 0, @@ -2763,7 +2767,7 @@ static void scx_watchdog_workfn(struct work_struct *work) cond_resched(); } queue_delayed_work(system_unbound_wq, to_delayed_work(work), - scx_watchdog_timeout / 2); + READ_ONCE(scx_watchdog_timeout) / 2); } void scx_tick(struct rq *rq) @@ -3585,7 +3589,6 @@ static int scx_cgroup_init(struct scx_sched *sch) ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init, NULL, css->cgroup, &args); if (ret) { - css_put(css); scx_error(sch, "ops.cgroup_init() failed (%d)", ret); return ret; } @@ -3708,7 +3711,9 @@ static void scx_kobj_release(struct kobject *kobj) static ssize_t scx_attr_ops_show(struct kobject *kobj, struct kobj_attribute *ka, char *buf) { - return sysfs_emit(buf, "%s\n", scx_root->ops.name); + struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); + + return sysfs_emit(buf, "%s\n", sch->ops.name); } SCX_ATTR(ops); @@ -3752,7 +3757,9 @@ static const struct kobj_type scx_ktype = { static int scx_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { - return add_uevent_var(env, "SCXOPS=%s", scx_root->ops.name); + const struct scx_sched *sch = container_of(kobj, struct scx_sched, kobj); + + return add_uevent_var(env, "SCXOPS=%s", sch->ops.name); } static const struct kset_uevent_ops scx_uevent_ops = { @@ -4423,10 +4430,19 @@ done: scx_bypass(false); } +/* + * Claim the exit on @sch. The caller must ensure that the helper kthread work + * is kicked before the current task can be preempted. Once exit_kind is + * claimed, scx_error() can no longer trigger, so if the current task gets + * preempted and the BPF scheduler fails to schedule it back, the helper work + * will never be kicked and the whole system can wedge. + */ static bool scx_claim_exit(struct scx_sched *sch, enum scx_exit_kind kind) { int none = SCX_EXIT_NONE; + lockdep_assert_preemption_disabled(); + if (!atomic_try_cmpxchg(&sch->exit_kind, &none, kind)) return false; @@ -4449,6 +4465,7 @@ static void scx_disable(enum scx_exit_kind kind) rcu_read_lock(); sch = rcu_dereference(scx_root); if (sch) { + guard(preempt)(); scx_claim_exit(sch, kind); kthread_queue_work(sch->helper, &sch->disable_work); } @@ -4771,6 +4788,8 @@ static bool scx_vexit(struct scx_sched *sch, { struct scx_exit_info *ei = sch->exit_info; + guard(preempt)(); + if (!scx_claim_exit(sch, kind)) return false; @@ -4955,20 +4974,30 @@ static int validate_ops(struct scx_sched *sch, const struct sched_ext_ops *ops) return 0; } -static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) +/* + * scx_enable() is offloaded to a dedicated system-wide RT kthread to avoid + * starvation. During the READY -> ENABLED task switching loop, the calling + * thread's sched_class gets switched from fair to ext. As fair has higher + * priority than ext, the calling thread can be indefinitely starved under + * fair-class saturation, leading to a system hang. + */ +struct scx_enable_cmd { + struct kthread_work work; + struct sched_ext_ops *ops; + int ret; +}; + +static void scx_enable_workfn(struct kthread_work *work) { + struct scx_enable_cmd *cmd = + container_of(work, struct scx_enable_cmd, work); + struct sched_ext_ops *ops = cmd->ops; struct scx_sched *sch; struct scx_task_iter sti; struct task_struct *p; unsigned long timeout; int i, cpu, ret; - if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), - cpu_possible_mask)) { - pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); - return -EINVAL; - } - mutex_lock(&scx_enable_mutex); if (scx_enable_state() != SCX_DISABLED) { @@ -5060,7 +5089,7 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) WRITE_ONCE(scx_watchdog_timeout, timeout); WRITE_ONCE(scx_watchdog_timestamp, jiffies); queue_delayed_work(system_unbound_wq, &scx_watchdog_work, - scx_watchdog_timeout / 2); + READ_ONCE(scx_watchdog_timeout) / 2); /* * Once __scx_enabled is set, %current can be switched to SCX anytime. @@ -5185,13 +5214,15 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) atomic_long_inc(&scx_enable_seq); - return 0; + cmd->ret = 0; + return; err_free_ksyncs: free_kick_syncs(); err_unlock: mutex_unlock(&scx_enable_mutex); - return ret; + cmd->ret = ret; + return; err_disable_unlock_all: scx_cgroup_unlock(); @@ -5210,7 +5241,41 @@ err_disable: */ scx_error(sch, "scx_enable() failed (%d)", ret); kthread_flush_work(&sch->disable_work); - return 0; + cmd->ret = 0; +} + +static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link) +{ + static struct kthread_worker *helper; + static DEFINE_MUTEX(helper_mutex); + struct scx_enable_cmd cmd; + + if (!cpumask_equal(housekeeping_cpumask(HK_TYPE_DOMAIN), + cpu_possible_mask)) { + pr_err("sched_ext: Not compatible with \"isolcpus=\" domain isolation\n"); + return -EINVAL; + } + + if (!READ_ONCE(helper)) { + mutex_lock(&helper_mutex); + if (!helper) { + helper = kthread_run_worker(0, "scx_enable_helper"); + if (IS_ERR_OR_NULL(helper)) { + helper = NULL; + mutex_unlock(&helper_mutex); + return -ENOMEM; + } + sched_set_fifo(helper->task); + } + mutex_unlock(&helper_mutex); + } + + kthread_init_work(&cmd.work, scx_enable_workfn); + cmd.ops = ops; + + kthread_queue_work(READ_ONCE(helper), &cmd.work); + kthread_flush_work(&cmd.work); + return cmd.ret; } diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index c5a3b0bac7c3..ba298ac3ce6c 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -663,9 +663,8 @@ void scx_idle_init_masks(void) BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.cpu, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&scx_idle_global_masks.smt, GFP_KERNEL)); - /* Allocate per-node idle cpumasks */ - scx_idle_node_masks = kzalloc_objs(*scx_idle_node_masks, - num_possible_nodes()); + /* Allocate per-node idle cpumasks (use nr_node_ids for non-contiguous NUMA nodes) */ + scx_idle_node_masks = kzalloc_objs(*scx_idle_node_masks, nr_node_ids); BUG_ON(!scx_idle_node_masks); for_each_node(i) { diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h index 386c677e4c9a..11ebb744d893 100644 --- a/kernel/sched/ext_internal.h +++ b/kernel/sched/ext_internal.h @@ -74,7 +74,7 @@ enum scx_exit_flags { * info communication. The following flag indicates whether ops.init() * finished successfully. */ - SCX_EFLAG_INITIALIZED, + SCX_EFLAG_INITIALIZED = 1LLU << 0, }; /* diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index eea99ec01a3f..bf948db905ed 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -589,6 +589,21 @@ static inline bool entity_before(const struct sched_entity *a, return vruntime_cmp(a->deadline, "<", b->deadline); } +/* + * Per avg_vruntime() below, cfs_rq::zero_vruntime is only slightly stale + * and this value should be no more than two lag bounds. Which puts it in the + * general order of: + * + * (slice + TICK_NSEC) << NICE_0_LOAD_SHIFT + * + * which is around 44 bits in size (on 64bit); that is 20 for + * NICE_0_LOAD_SHIFT, another 20 for NSEC_PER_MSEC and then a handful for + * however many msec the actual slice+tick ends up begin. + * + * (disregarding the actual divide-by-weight part makes for the worst case + * weight of 2, which nicely cancels vs the fuzz in zero_vruntime not actually + * being the zero-lag point). + */ static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se) { return vruntime_op(se->vruntime, "-", cfs_rq->zero_vruntime); @@ -676,41 +691,65 @@ sum_w_vruntime_sub(struct cfs_rq *cfs_rq, struct sched_entity *se) } static inline -void sum_w_vruntime_update(struct cfs_rq *cfs_rq, s64 delta) +void update_zero_vruntime(struct cfs_rq *cfs_rq, s64 delta) { /* - * v' = v + d ==> sum_w_vruntime' = sum_runtime - d*sum_weight + * v' = v + d ==> sum_w_vruntime' = sum_w_vruntime - d*sum_weight */ cfs_rq->sum_w_vruntime -= cfs_rq->sum_weight * delta; + cfs_rq->zero_vruntime += delta; } /* - * Specifically: avg_runtime() + 0 must result in entity_eligible() := true + * Specifically: avg_vruntime() + 0 must result in entity_eligible() := true * For this to be so, the result of this function must have a left bias. + * + * Called in: + * - place_entity() -- before enqueue + * - update_entity_lag() -- before dequeue + * - entity_tick() + * + * This means it is one entry 'behind' but that puts it close enough to where + * the bound on entity_key() is at most two lag bounds. */ u64 avg_vruntime(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; - s64 avg = cfs_rq->sum_w_vruntime; - long load = cfs_rq->sum_weight; + long weight = cfs_rq->sum_weight; + s64 delta = 0; - if (curr && curr->on_rq) { - unsigned long weight = scale_load_down(curr->load.weight); + if (curr && !curr->on_rq) + curr = NULL; - avg += entity_key(cfs_rq, curr) * weight; - load += weight; - } + if (weight) { + s64 runtime = cfs_rq->sum_w_vruntime; + + if (curr) { + unsigned long w = scale_load_down(curr->load.weight); + + runtime += entity_key(cfs_rq, curr) * w; + weight += w; + } - if (load) { /* sign flips effective floor / ceiling */ - if (avg < 0) - avg -= (load - 1); - avg = div_s64(avg, load); + if (runtime < 0) + runtime -= (weight - 1); + + delta = div_s64(runtime, weight); + } else if (curr) { + /* + * When there is but one element, it is the average. + */ + delta = curr->vruntime - cfs_rq->zero_vruntime; } - return cfs_rq->zero_vruntime + avg; + update_zero_vruntime(cfs_rq, delta); + + return cfs_rq->zero_vruntime; } +static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq); + /* * lag_i = S - s_i = w_i * (V - v_i) * @@ -724,17 +763,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq) * EEVDF gives the following limit for a steady state system: * * -r_max < lag < max(r_max, q) - * - * XXX could add max_slice to the augmented data to track this. */ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se) { + u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC; s64 vlag, limit; WARN_ON_ONCE(!se->on_rq); vlag = avg_vruntime(cfs_rq) - se->vruntime; - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se); + limit = calc_delta_fair(max_slice, se); se->vlag = clamp(vlag, -limit, limit); } @@ -777,16 +815,6 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se) return vruntime_eligible(cfs_rq, se->vruntime); } -static void update_zero_vruntime(struct cfs_rq *cfs_rq) -{ - u64 vruntime = avg_vruntime(cfs_rq); - s64 delta = vruntime_op(vruntime, "-", cfs_rq->zero_vruntime); - - sum_w_vruntime_update(cfs_rq, delta); - - cfs_rq->zero_vruntime = vruntime; -} - static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) { struct sched_entity *root = __pick_root_entity(cfs_rq); @@ -802,6 +830,21 @@ static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq) return min_slice; } +static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq) +{ + struct sched_entity *root = __pick_root_entity(cfs_rq); + struct sched_entity *curr = cfs_rq->curr; + u64 max_slice = 0ULL; + + if (curr && curr->on_rq) + max_slice = curr->slice; + + if (root) + max_slice = max(max_slice, root->max_slice); + + return max_slice; +} + static inline bool __entity_less(struct rb_node *a, const struct rb_node *b) { return entity_before(__node_2_se(a), __node_2_se(b)); @@ -826,6 +869,15 @@ static inline void __min_slice_update(struct sched_entity *se, struct rb_node *n } } +static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node) +{ + if (node) { + struct sched_entity *rse = __node_2_se(node); + if (rse->max_slice > se->max_slice) + se->max_slice = rse->max_slice; + } +} + /* * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime) */ @@ -833,6 +885,7 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) { u64 old_min_vruntime = se->min_vruntime; u64 old_min_slice = se->min_slice; + u64 old_max_slice = se->max_slice; struct rb_node *node = &se->run_node; se->min_vruntime = se->vruntime; @@ -843,8 +896,13 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit) __min_slice_update(se, node->rb_right); __min_slice_update(se, node->rb_left); + se->max_slice = se->slice; + __max_slice_update(se, node->rb_right); + __max_slice_update(se, node->rb_left); + return se->min_vruntime == old_min_vruntime && - se->min_slice == old_min_slice; + se->min_slice == old_min_slice && + se->max_slice == old_max_slice; } RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, @@ -856,7 +914,6 @@ RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity, static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { sum_w_vruntime_add(cfs_rq, se); - update_zero_vruntime(cfs_rq); se->min_vruntime = se->vruntime; se->min_slice = se->slice; rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, @@ -868,7 +925,6 @@ static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline, &min_vruntime_cb); sum_w_vruntime_sub(cfs_rq, se); - update_zero_vruntime(cfs_rq); } struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq) @@ -3790,6 +3846,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { bool curr = cfs_rq->curr == se; + bool rel_vprot = false; + u64 vprot; if (se->on_rq) { /* commit outstanding execution time */ @@ -3797,6 +3855,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, update_entity_lag(cfs_rq, se); se->deadline -= se->vruntime; se->rel_deadline = 1; + if (curr && protect_slice(se)) { + vprot = se->vprot - se->vruntime; + rel_vprot = true; + } + cfs_rq->nr_queued--; if (!curr) __dequeue_entity(cfs_rq, se); @@ -3812,6 +3875,9 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, if (se->rel_deadline) se->deadline = div_s64(se->deadline * se->load.weight, weight); + if (rel_vprot) + vprot = div_s64(vprot * se->load.weight, weight); + update_load_set(&se->load, weight); do { @@ -3823,6 +3889,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, enqueue_load_avg(cfs_rq, se); if (se->on_rq) { place_entity(cfs_rq, se, 0); + if (rel_vprot) + se->vprot = se->vruntime + vprot; update_load_add(&cfs_rq->load, se->load.weight); if (!curr) __enqueue_entity(cfs_rq, se); @@ -5420,7 +5488,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) } static void -set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, bool first) { clear_buddies(cfs_rq, se); @@ -5435,7 +5503,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) __dequeue_entity(cfs_rq, se); update_load_avg(cfs_rq, se, UPDATE_TG); - set_protect_slice(cfs_rq, se); + if (first) + set_protect_slice(cfs_rq, se); } update_stats_curr_start(cfs_rq, se); @@ -5524,6 +5593,11 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) update_load_avg(cfs_rq, curr, UPDATE_TG); update_cfs_group(curr); + /* + * Pulls along cfs_rq::zero_vruntime. + */ + avg_vruntime(cfs_rq); + #ifdef CONFIG_SCHED_HRTICK /* * queued ticks are scheduled to match the slice, so don't bother @@ -8948,13 +9022,13 @@ again: pse = parent_entity(pse); } if (se_depth >= pse_depth) { - set_next_entity(cfs_rq_of(se), se); + set_next_entity(cfs_rq_of(se), se, true); se = parent_entity(se); } } put_prev_entity(cfs_rq, pse); - set_next_entity(cfs_rq, se); + set_next_entity(cfs_rq, se, true); __set_next_task_fair(rq, p, true); } @@ -12908,7 +12982,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) t0 = sched_clock_cpu(this_cpu); __sched_balance_update_blocked_averages(this_rq); - this_rq->next_class = &fair_sched_class; + rq_modified_begin(this_rq, &fair_sched_class); raw_spin_rq_unlock(this_rq); for_each_domain(this_cpu, sd) { @@ -12975,7 +13049,7 @@ static int sched_balance_newidle(struct rq *this_rq, struct rq_flags *rf) pulled_task = 1; /* If a higher prio class was modified, restart the pick */ - if (sched_class_above(this_rq->next_class, &fair_sched_class)) + if (rq_modified_above(this_rq, &fair_sched_class)) pulled_task = -1; out: @@ -13568,7 +13642,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - set_next_entity(cfs_rq, se); + set_next_entity(cfs_rq, se, first); /* ensure bandwidth has been allocated on our new cfs_rq */ account_cfs_rq_runtime(cfs_rq, 0); } diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 3b725d39c06e..ef152d401fe2 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -123,8 +123,6 @@ int housekeeping_update(struct cpumask *isol_mask) struct cpumask *trial, *old = NULL; int err; - lockdep_assert_cpus_held(); - trial = kmalloc(cpumask_size(), GFP_KERNEL); if (!trial) return -ENOMEM; @@ -136,7 +134,7 @@ int housekeeping_update(struct cpumask *isol_mask) } if (!housekeeping.flags) - static_branch_enable_cpuslocked(&housekeeping_overridden); + static_branch_enable(&housekeeping_overridden); if (housekeeping.flags & HK_FLAG_DOMAIN) old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b82fb70a9d54..43bbf0693cca 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2748,6 +2748,17 @@ static inline const struct sched_class *next_active_class(const struct sched_cla #define sched_class_above(_a, _b) ((_a) < (_b)) +static inline void rq_modified_begin(struct rq *rq, const struct sched_class *class) +{ + if (sched_class_above(rq->next_class, class)) + rq->next_class = class; +} + +static inline bool rq_modified_above(struct rq *rq, const struct sched_class *class) +{ + return sched_class_above(rq->next_class, class); +} + static inline bool sched_stop_runnable(struct rq *rq) { return rq->stop && task_on_rq_queued(rq->stop); diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a5c7d15fce72..9daf8c5d9687 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies); int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ) - return -EINVAL; return proc_dointvec_conv(table, dir, buffer, lenp, ppos, do_proc_int_conv_userhz_jiffies); } diff --git a/kernel/time/time.c b/kernel/time/time.c index 0ba8e3c50d62..36fd2313ae7e 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -365,20 +365,16 @@ SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) } #endif +#if HZ > MSEC_PER_SEC || (MSEC_PER_SEC % HZ) /** * jiffies_to_msecs - Convert jiffies to milliseconds * @j: jiffies value * - * Avoid unnecessary multiplications/divisions in the - * two most common HZ cases. - * * Return: milliseconds value */ unsigned int jiffies_to_msecs(const unsigned long j) { -#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) - return (MSEC_PER_SEC / HZ) * j; -#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) +#if HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC); #else # if BITS_PER_LONG == 32 @@ -390,7 +386,9 @@ unsigned int jiffies_to_msecs(const unsigned long j) #endif } EXPORT_SYMBOL(jiffies_to_msecs); +#endif +#if (USEC_PER_SEC % HZ) /** * jiffies_to_usecs - Convert jiffies to microseconds * @j: jiffies value @@ -405,17 +403,14 @@ unsigned int jiffies_to_usecs(const unsigned long j) */ BUILD_BUG_ON(HZ > USEC_PER_SEC); -#if !(USEC_PER_SEC % HZ) - return (USEC_PER_SEC / HZ) * j; -#else -# if BITS_PER_LONG == 32 +#if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; -# else +#else return (j * HZ_TO_USEC_NUM) / HZ_TO_USEC_DEN; -# endif #endif } EXPORT_SYMBOL(jiffies_to_usecs); +#endif /** * mktime64 - Converts date to seconds. diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index c1ed0d5e8de6..155eeaea4113 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL; int cpu; - lockdep_assert_cpus_held(); - if (!works) return -ENOMEM; if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) @@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) * First set previously isolated CPUs as available (unisolate). * This cpumask contains only CPUs that switched to available now. */ + guard(cpus_read_lock)(); cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); @@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void) cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); /* Protect against RCU torture hotplug testing */ - guard(cpus_read_lock)(); return tmigr_isolated_exclude_cpumask(cpumask); } late_initcall(tmigr_init_isolation); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 9bc0dfd235af..0b040a417442 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -2454,8 +2454,10 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_kprobe_multi_link *kmulti_link; + bool has_cookies; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); + has_cookies = !!kmulti_link->cookies; seq_printf(seq, "kprobe_cnt:\t%u\n" @@ -2467,7 +2469,7 @@ static void bpf_kprobe_multi_show_fdinfo(const struct bpf_link *link, for (int i = 0; i < kmulti_link->cnt; i++) { seq_printf(seq, "%llu\t %pS\n", - kmulti_link->cookies[i], + has_cookies ? kmulti_link->cookies[i] : 0, (void *)kmulti_link->addrs[i]); } } diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 827fb9a0bf0d..2f72af0357e5 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -8611,6 +8611,7 @@ ftrace_pid_follow_sched_process_fork(void *data, struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, self, task); @@ -8624,6 +8625,7 @@ ftrace_pid_follow_sched_process_exit(void *data, struct task_struct *task) struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->function_pids); trace_filter_add_remove_task(pid_list, NULL, task); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f16f053ef77d..17d0ea0cc3e6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7310,6 +7310,27 @@ int ring_buffer_map(struct trace_buffer *buffer, int cpu, return err; } +/* + * This is called when a VMA is duplicated (e.g., on fork()) to increment + * the user_mapped counter without remapping pages. + */ +void ring_buffer_map_dup(struct trace_buffer *buffer, int cpu) +{ + struct ring_buffer_per_cpu *cpu_buffer; + + if (WARN_ON(!cpumask_test_cpu(cpu, buffer->cpumask))) + return; + + cpu_buffer = buffer->buffers[cpu]; + + guard(mutex)(&cpu_buffer->mapping_lock); + + if (cpu_buffer->user_mapped) + __rb_inc_dec_mapped(cpu_buffer, true); + else + WARN(1, "Unexpected buffer stat, it should be mapped"); +} + int ring_buffer_unmap(struct trace_buffer *buffer, int cpu) { struct ring_buffer_per_cpu *cpu_buffer; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 23de3719f495..1e7c032a72d2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8213,6 +8213,18 @@ static inline int get_snapshot_map(struct trace_array *tr) { return 0; } static inline void put_snapshot_map(struct trace_array *tr) { } #endif +/* + * This is called when a VMA is duplicated (e.g., on fork()) to increment + * the user_mapped counter without remapping pages. + */ +static void tracing_buffers_mmap_open(struct vm_area_struct *vma) +{ + struct ftrace_buffer_info *info = vma->vm_file->private_data; + struct trace_iterator *iter = &info->iter; + + ring_buffer_map_dup(iter->array_buffer->buffer, iter->cpu_file); +} + static void tracing_buffers_mmap_close(struct vm_area_struct *vma) { struct ftrace_buffer_info *info = vma->vm_file->private_data; @@ -8232,6 +8244,7 @@ static int tracing_buffers_may_split(struct vm_area_struct *vma, unsigned long a } static const struct vm_operations_struct tracing_buffers_vmops = { + .open = tracing_buffers_mmap_open, .close = tracing_buffers_mmap_close, .may_split = tracing_buffers_may_split, }; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9928da636c9d..b7343fdfd7b0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task) struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_raw(tr->filtered_pids); trace_filter_add_remove_task(pid_list, NULL, task); @@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data, struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->filtered_pids); trace_filter_add_remove_task(pid_list, self, task); @@ -4668,26 +4670,22 @@ static __init int event_trace_memsetup(void) return 0; } -__init void -early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +/* + * Helper function to enable or disable a comma-separated list of events + * from the bootup buffer. + */ +static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable) { char *token; - int ret; - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; + while ((token = strsep(&buf, ","))) { if (*token) { - /* Restarting syscalls requires that we stop them first */ - if (disable_first) + if (enable) { + if (ftrace_set_clr_event(tr, token, 1)) + pr_warn("Failed to enable trace event: %s\n", token); + } else { ftrace_set_clr_event(tr, token, 0); - - ret = ftrace_set_clr_event(tr, token, 1); - if (ret) - pr_warn("Failed to enable trace event: %s\n", token); + } } /* Put back the comma to allow this to be called again */ @@ -4696,6 +4694,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first) } } +/** + * early_enable_events - enable events from the bootup buffer + * @tr: The trace array to enable the events in + * @buf: The buffer containing the comma separated list of events + * @disable_first: If true, disable all events in @buf before enabling them + * + * This function enables events from the bootup buffer. If @disable_first + * is true, it will first disable all events in the buffer before enabling + * them. + * + * For syscall events, which rely on a global refcount to register the + * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must + * ensure the refcount hits zero before re-enabling them. A simple + * "disable then enable" per-event is not enough if multiple syscalls are + * used, as the refcount will stay above zero. Thus, we need a two-phase + * approach: disable all, then enable all. + */ +__init void +early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +{ + if (disable_first) + __early_set_events(tr, buf, false); + + __early_set_events(tr, buf, true); +} + static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 3d8239fee004..0d2d3a2ea7dd 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -400,14 +400,19 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops, struct ftrace_regs *fregs) { + unsigned long *task_var = fgraph_get_task_var(gops); struct fgraph_times *ftimes; struct trace_array *tr; + unsigned int trace_ctx; + u64 calltime, rettime; int size; + rettime = trace_clock_local(); + ftrace_graph_addr_finish(gops, trace); - if (trace_recursion_test(TRACE_GRAPH_NOTRACE_BIT)) { - trace_recursion_clear(TRACE_GRAPH_NOTRACE_BIT); + if (*task_var & TRACE_GRAPH_NOTRACE) { + *task_var &= ~TRACE_GRAPH_NOTRACE; return; } @@ -418,11 +423,13 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace, tr = gops->private; handle_nosleeptime(tr, trace, ftimes, size); - if (tracing_thresh && - (trace_clock_local() - ftimes->calltime < tracing_thresh)) + calltime = ftimes->calltime; + + if (tracing_thresh && (rettime - calltime < tracing_thresh)) return; - else - trace_graph_return(trace, gops, fregs); + + trace_ctx = tracing_gen_ctx(); + __trace_graph_return(tr, trace, trace_ctx, calltime, rettime); } static struct fgraph_ops funcgraph_ops = { diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 318df4c75454..93f356d2b3d9 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -630,7 +630,7 @@ config DEBUG_FORCE_WEAK_PER_CPU config WARN_CONTEXT_ANALYSIS bool "Compiler context-analysis warnings" - depends on CC_IS_CLANG && CLANG_VERSION >= 220000 + depends on CC_IS_CLANG && CLANG_VERSION >= 220100 # Branch profiling re-defines "if", which messes with the compiler's # ability to analyze __cond_acquires(..), resulting in false positives. depends on !TRACE_BRANCH_PROFILING @@ -641,7 +641,7 @@ config WARN_CONTEXT_ANALYSIS and releasing user-definable "context locks". Clang's name of the feature is "Thread Safety Analysis". Requires - Clang 22 or later. + Clang 22.1.0 or later. Produces warnings by default. Select CONFIG_WERROR if you wish to turn these warnings into errors. @@ -760,6 +760,7 @@ source "mm/Kconfig.debug" config DEBUG_OBJECTS bool "Debug object operations" + depends on PREEMPT_COUNT || !DEFERRED_STRUCT_PAGE_INIT depends on DEBUG_KERNEL help If you say Y here, additional code will be inserted into the diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 89a1d6745dc2..12f50de85b62 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -398,9 +398,26 @@ static void fill_pool(void) atomic_inc(&cpus_allocating); while (pool_should_refill(&pool_global)) { + gfp_t gfp = __GFP_HIGH | __GFP_NOWARN; HLIST_HEAD(head); - if (!kmem_alloc_batch(&head, obj_cache, __GFP_HIGH | __GFP_NOWARN)) + /* + * Allow reclaim only in preemptible context and during + * early boot. If not preemptible, the caller might hold + * locks causing a deadlock in the allocator. + * + * If the reclaim flag is not set during early boot then + * allocations, which happen before deferred page + * initialization has completed, will fail. + * + * In preemptible context the flag is harmless and not a + * performance issue as that's usually invoked from slow + * path initialization context. + */ + if (preemptible() || system_state < SYSTEM_SCHEDULING) + gfp |= __GFP_KSWAPD_RECLAIM; + + if (!kmem_alloc_batch(&head, obj_cache, gfp)) break; guard(raw_spinlock_irqsave)(&pool_lock); diff --git a/mm/damon/core.c b/mm/damon/core.c index 01eba1a547d4..adfc52fee9dc 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1252,6 +1252,9 @@ int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src) { int err; + if (!is_power_of_2(src->min_region_sz)) + return -EINVAL; + err = damon_commit_schemes(dst, src); if (err) return err; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index d4ca8cfd7f9d..8e2746ea74ad 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -94,6 +94,9 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma) inode = file_inode(vma->vm_file); + if (IS_ANON_FILE(inode)) + return false; + return !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode); } diff --git a/mm/kfence/core.c b/mm/kfence/core.c index b4ea3262c925..7393957f9a20 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -13,6 +13,7 @@ #include <linux/hash.h> #include <linux/irq_work.h> #include <linux/jhash.h> +#include <linux/kasan-enabled.h> #include <linux/kcsan-checks.h> #include <linux/kfence.h> #include <linux/kmemleak.h> @@ -917,6 +918,20 @@ void __init kfence_alloc_pool_and_metadata(void) return; /* + * If KASAN hardware tags are enabled, disable KFENCE, because it + * does not support MTE yet. + */ + if (kasan_hw_tags_enabled()) { + pr_info("disabled as KASAN HW tags are enabled\n"); + if (__kfence_pool) { + memblock_free(__kfence_pool, KFENCE_POOL_SIZE); + __kfence_pool = NULL; + } + kfence_sample_interval = 0; + return; + } + + /* * If the pool has already been initialized by arch, there is no need to * re-allocate the memory pool. */ @@ -989,14 +1004,14 @@ static int kfence_init_late(void) #ifdef CONFIG_CONTIG_ALLOC struct page *pages; - pages = alloc_contig_pages(nr_pages_pool, GFP_KERNEL, first_online_node, - NULL); + pages = alloc_contig_pages(nr_pages_pool, GFP_KERNEL | __GFP_SKIP_KASAN, + first_online_node, NULL); if (!pages) return -ENOMEM; __kfence_pool = page_to_virt(pages); - pages = alloc_contig_pages(nr_pages_meta, GFP_KERNEL, first_online_node, - NULL); + pages = alloc_contig_pages(nr_pages_meta, GFP_KERNEL | __GFP_SKIP_KASAN, + first_online_node, NULL); if (pages) kfence_metadata_init = page_to_virt(pages); #else @@ -1006,11 +1021,13 @@ static int kfence_init_late(void) return -EINVAL; } - __kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE, GFP_KERNEL); + __kfence_pool = alloc_pages_exact(KFENCE_POOL_SIZE, + GFP_KERNEL | __GFP_SKIP_KASAN); if (!__kfence_pool) return -ENOMEM; - kfence_metadata_init = alloc_pages_exact(KFENCE_METADATA_SIZE, GFP_KERNEL); + kfence_metadata_init = alloc_pages_exact(KFENCE_METADATA_SIZE, + GFP_KERNEL | __GFP_SKIP_KASAN); #endif if (!kfence_metadata_init) diff --git a/mm/memfd_luo.c b/mm/memfd_luo.c index 5c17da3880c5..e485b828d173 100644 --- a/mm/memfd_luo.c +++ b/mm/memfd_luo.c @@ -326,7 +326,12 @@ static void memfd_luo_finish(struct liveupdate_file_op_args *args) struct memfd_luo_folio_ser *folios_ser; struct memfd_luo_ser *ser; - if (args->retrieved) + /* + * If retrieve was successful, nothing to do. If it failed, retrieve() + * already cleaned up everything it could. So nothing to do there + * either. Only need to clean up when retrieve was not called. + */ + if (args->retrieve_status) return; ser = phys_to_virt(args->serialized_data); diff --git a/mm/mm_init.c b/mm/mm_init.c index 61d983d23f55..df34797691bd 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1896,7 +1896,11 @@ static void __init free_area_init(void) for_each_node(nid) { pg_data_t *pgdat; - if (!node_online(nid)) + /* + * If an architecture has not allocated node data for + * this node, presume the node is memoryless or offline. + */ + if (!NODE_DATA(nid)) alloc_offline_node_data(nid); pgdat = NODE_DATA(nid); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fcc32737f451..2d4b6f1a554e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6928,7 +6928,8 @@ static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask) { const gfp_t reclaim_mask = __GFP_IO | __GFP_FS | __GFP_RECLAIM; const gfp_t action_mask = __GFP_COMP | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | - __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO; + __GFP_ZERO | __GFP_ZEROTAGS | __GFP_SKIP_ZERO | + __GFP_SKIP_KASAN; const gfp_t cc_action_mask = __GFP_RETRY_MAYFAIL | __GFP_NOWARN; /* diff --git a/mm/slab.h b/mm/slab.h index 71c7261bf822..f6ef862b60ef 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -290,14 +290,14 @@ static inline void *nearest_obj(struct kmem_cache *cache, /* Determine object index from a given position */ static inline unsigned int __obj_to_index(const struct kmem_cache *cache, - void *addr, void *obj) + void *addr, const void *obj) { return reciprocal_divide(kasan_reset_tag(obj) - addr, cache->reciprocal_size); } static inline unsigned int obj_to_index(const struct kmem_cache *cache, - const struct slab *slab, void *obj) + const struct slab *slab, const void *obj) { if (is_kfence_address(obj)) return 0; diff --git a/mm/slub.c b/mm/slub.c index 862642c165ed..0c906fefc31b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2041,18 +2041,18 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, #ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG -static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) +static inline void mark_obj_codetag_empty(const void *obj) { - struct slab *obj_exts_slab; + struct slab *obj_slab; unsigned long slab_exts; - obj_exts_slab = virt_to_slab(obj_exts); - slab_exts = slab_obj_exts(obj_exts_slab); + obj_slab = virt_to_slab(obj); + slab_exts = slab_obj_exts(obj_slab); if (slab_exts) { get_slab_obj_exts(slab_exts); - unsigned int offs = obj_to_index(obj_exts_slab->slab_cache, - obj_exts_slab, obj_exts); - struct slabobj_ext *ext = slab_obj_ext(obj_exts_slab, + unsigned int offs = obj_to_index(obj_slab->slab_cache, + obj_slab, obj); + struct slabobj_ext *ext = slab_obj_ext(obj_slab, slab_exts, offs); if (unlikely(is_codetag_empty(&ext->ref))) { @@ -2090,7 +2090,7 @@ static inline void handle_failed_objexts_alloc(unsigned long obj_exts, #else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */ -static inline void mark_objexts_empty(struct slabobj_ext *obj_exts) {} +static inline void mark_obj_codetag_empty(const void *obj) {} static inline bool mark_failed_objexts_alloc(struct slab *slab) { return false; } static inline void handle_failed_objexts_alloc(unsigned long obj_exts, struct slabobj_ext *vec, unsigned int objects) {} @@ -2196,7 +2196,6 @@ int alloc_slab_obj_exts(struct slab *slab, struct kmem_cache *s, retry: old_exts = READ_ONCE(slab->obj_exts); handle_failed_objexts_alloc(old_exts, vec, objects); - slab_set_stride(slab, sizeof(struct slabobj_ext)); if (new_slab) { /* @@ -2211,7 +2210,7 @@ retry: * assign slabobj_exts in parallel. In this case the existing * objcg vector should be reused. */ - mark_objexts_empty(vec); + mark_obj_codetag_empty(vec); if (unlikely(!allow_spin)) kfree_nolock(vec); else @@ -2254,7 +2253,7 @@ static inline void free_slab_obj_exts(struct slab *slab, bool allow_spin) * NULL, therefore replace NULL with CODETAG_EMPTY to indicate that * the extension for obj_exts is expected to be NULL. */ - mark_objexts_empty(obj_exts); + mark_obj_codetag_empty(obj_exts); if (allow_spin) kfree(obj_exts); else @@ -2272,6 +2271,9 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab) void *addr; unsigned long obj_exts; + /* Initialize stride early to avoid memory ordering issues */ + slab_set_stride(slab, sizeof(struct slabobj_ext)); + if (!need_slab_obj_exts(s)) return; @@ -2288,7 +2290,6 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab) obj_exts |= MEMCG_DATA_OBJEXTS; #endif slab->obj_exts = obj_exts; - slab_set_stride(slab, sizeof(struct slabobj_ext)); } else if (s->flags & SLAB_OBJ_EXT_IN_OBJ) { unsigned int offset = obj_exts_offset_in_object(s); @@ -2312,6 +2313,10 @@ static void alloc_slab_obj_exts_early(struct kmem_cache *s, struct slab *slab) #else /* CONFIG_SLAB_OBJ_EXT */ +static inline void mark_obj_codetag_empty(const void *obj) +{ +} + static inline void init_slab_obj_exts(struct slab *slab) { } @@ -2783,6 +2788,15 @@ static inline struct slab_sheaf *alloc_empty_sheaf(struct kmem_cache *s, static void free_empty_sheaf(struct kmem_cache *s, struct slab_sheaf *sheaf) { + /* + * If the sheaf was created with __GFP_NO_OBJ_EXT flag then its + * corresponding extension is NULL and alloc_tag_sub() will throw a + * warning, therefore replace NULL with CODETAG_EMPTY to indicate + * that the extension for this sheaf is expected to be NULL. + */ + if (s->flags & SLAB_KMALLOC) + mark_obj_codetag_empty(sheaf); + kfree(sheaf); stat(s, SHEAF_FREE); @@ -2822,7 +2836,7 @@ static struct slab_sheaf *alloc_full_sheaf(struct kmem_cache *s, gfp_t gfp) if (!sheaf) return NULL; - if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC)) { + if (refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) { free_empty_sheaf(s, sheaf); return NULL; } @@ -4575,7 +4589,7 @@ __pcs_replace_empty_main(struct kmem_cache *s, struct slub_percpu_sheaves *pcs, return NULL; if (empty) { - if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC)) { + if (!refill_sheaf(s, empty, gfp | __GFP_NOMEMALLOC | __GFP_NOWARN)) { full = empty; } else { /* @@ -4890,9 +4904,14 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_noprof); static int __prefill_sheaf_pfmemalloc(struct kmem_cache *s, struct slab_sheaf *sheaf, gfp_t gfp) { - int ret = 0; + gfp_t gfp_nomemalloc; + int ret; + + gfp_nomemalloc = gfp | __GFP_NOMEMALLOC; + if (gfp_pfmemalloc_allowed(gfp)) + gfp_nomemalloc |= __GFP_NOWARN; - ret = refill_sheaf(s, sheaf, gfp | __GFP_NOMEMALLOC); + ret = refill_sheaf(s, sheaf, gfp_nomemalloc); if (likely(!ret || !gfp_pfmemalloc_allowed(gfp))) return ret; diff --git a/net/atm/lec.c b/net/atm/lec.c index a107375c0629..fb93c6e1c329 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1260,24 +1260,28 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); struct net_device *dev = (struct net_device *)vcc->proto_data; - vcc->pop = vpriv->old_pop; - if (vpriv->xoff) - netif_wake_queue(dev); - kfree(vpriv); - vcc->user_back = NULL; - vcc->push = entry->old_push; - vcc_release_async(vcc, -EPIPE); + if (vpriv) { + vcc->pop = vpriv->old_pop; + if (vpriv->xoff) + netif_wake_queue(dev); + kfree(vpriv); + vcc->user_back = NULL; + vcc->push = entry->old_push; + vcc_release_async(vcc, -EPIPE); + } entry->vcc = NULL; } if (entry->recv_vcc) { struct atm_vcc *vcc = entry->recv_vcc; struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); - kfree(vpriv); - vcc->user_back = NULL; + if (vpriv) { + kfree(vpriv); + vcc->user_back = NULL; - entry->recv_vcc->push = entry->old_recv_push; - vcc_release_async(entry->recv_vcc, -EPIPE); + entry->recv_vcc->push = entry->old_recv_push; + vcc_release_async(entry->recv_vcc, -EPIPE); + } entry->recv_vcc = NULL; } } diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2ce4e5bf9292..fdc2abe96d77 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -111,7 +111,15 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh, /* unsupported WiFi driver version */ goto default_throughput; - real_netdev = batadv_get_real_netdev(hard_iface->net_dev); + /* only use rtnl_trylock because the elp worker will be cancelled while + * the rntl_lock is held. the cancel_delayed_work_sync() would otherwise + * wait forever when the elp work_item was started and it is then also + * trying to rtnl_lock + */ + if (!rtnl_trylock()) + return false; + real_netdev = __batadv_get_real_netdev(hard_iface->net_dev); + rtnl_unlock(); if (!real_netdev) goto default_throughput; diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 7b7640f3ffe2..d6732c34aeaf 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -204,7 +204,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) } /** - * batadv_get_real_netdevice() - check if the given netdev struct is a virtual + * __batadv_get_real_netdev() - check if the given netdev struct is a virtual * interface on top of another 'real' interface * @netdev: the device to check * @@ -214,7 +214,7 @@ static bool batadv_is_valid_iface(const struct net_device *net_dev) * Return: the 'real' net device or the original net device and NULL in case * of an error. */ -static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) +struct net_device *__batadv_get_real_netdev(struct net_device *netdev) { struct batadv_hard_iface *hard_iface = NULL; struct net_device *real_netdev = NULL; @@ -267,7 +267,7 @@ struct net_device *batadv_get_real_netdev(struct net_device *net_device) struct net_device *real_netdev; rtnl_lock(); - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); rtnl_unlock(); return real_netdev; @@ -336,7 +336,7 @@ static u32 batadv_wifi_flags_evaluate(struct net_device *net_device) if (batadv_is_cfg80211_netdev(net_device)) wifi_flags |= BATADV_HARDIF_WIFI_CFG80211_DIRECT; - real_netdev = batadv_get_real_netdevice(net_device); + real_netdev = __batadv_get_real_netdev(net_device); if (!real_netdev) return wifi_flags; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 9db8a310961e..9ba8fb2bdceb 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -67,6 +67,7 @@ enum batadv_hard_if_bcast { extern struct notifier_block batadv_hard_if_notifier; +struct net_device *__batadv_get_real_netdev(struct net_device *net_device); struct net_device *batadv_get_real_netdev(struct net_device *net_device); bool batadv_is_cfg80211_hardif(struct batadv_hard_iface *hard_iface); bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface); diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index ee01122f466f..f7502e62dd35 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -74,7 +74,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) eth_hdr(skb)->h_proto == htons(ETH_P_RARP)) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED)) { br_do_proxy_suppress_arp(skb, br, vid, NULL); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 1405f1061a54..2cbae0f9ae1f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -170,7 +170,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb (skb->protocol == htons(ETH_P_ARP) || skb->protocol == htons(ETH_P_RARP))) { br_do_proxy_suppress_arp(skb, br, vid, p); - } else if (IS_ENABLED(CONFIG_IPV6) && + } else if (ipv6_mod_enabled() && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index b9b2981c4841..9b55d38ea9ed 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -1345,6 +1345,16 @@ br_multicast_ctx_options_equal(const struct net_bridge_mcast *brmctx1, } static inline bool +br_multicast_port_ctx_options_equal(const struct net_bridge_mcast_port *pmctx1, + const struct net_bridge_mcast_port *pmctx2) +{ + return br_multicast_ngroups_get(pmctx1) == + br_multicast_ngroups_get(pmctx2) && + br_multicast_ngroups_get_max(pmctx1) == + br_multicast_ngroups_get_max(pmctx2); +} + +static inline bool br_multicast_ctx_matches_vlan_snooping(const struct net_bridge_mcast *brmctx) { bool vlan_snooping_enabled; diff --git a/net/bridge/br_vlan_options.c b/net/bridge/br_vlan_options.c index 8fa89b04ee94..5514e1fc8d1f 100644 --- a/net/bridge/br_vlan_options.c +++ b/net/bridge/br_vlan_options.c @@ -43,9 +43,29 @@ bool br_vlan_opts_eq_range(const struct net_bridge_vlan *v_curr, u8 range_mc_rtr = br_vlan_multicast_router(range_end); u8 curr_mc_rtr = br_vlan_multicast_router(v_curr); - return v_curr->state == range_end->state && - __vlan_tun_can_enter_range(v_curr, range_end) && - curr_mc_rtr == range_mc_rtr; + if (v_curr->state != range_end->state) + return false; + + if (!__vlan_tun_can_enter_range(v_curr, range_end)) + return false; + + if (curr_mc_rtr != range_mc_rtr) + return false; + + /* Check user-visible priv_flags that affect output */ + if ((v_curr->priv_flags ^ range_end->priv_flags) & + (BR_VLFLAG_NEIGH_SUPPRESS_ENABLED | BR_VLFLAG_MCAST_ENABLED)) + return false; + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (!br_vlan_is_master(v_curr) && + !br_multicast_port_ctx_vlan_disabled(&v_curr->port_mcast_ctx) && + !br_multicast_port_ctx_options_equal(&v_curr->port_mcast_ctx, + &range_end->port_mcast_ctx)) + return false; +#endif + + return true; } bool br_vlan_opts_fill(struct sk_buff *skb, const struct net_bridge_vlan *v, diff --git a/net/can/bcm.c b/net/can/bcm.c index b7324e9c955b..fd9fa072881e 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1176,6 +1176,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, if (!op) return -ENOMEM; + spin_lock_init(&op->bcm_tx_lock); op->can_id = msg_head->can_id; op->nframes = msg_head->nframes; op->cfsiz = CFSIZ(msg_head->flags); diff --git a/net/core/dev.c b/net/core/dev.c index b470487788a2..203dc36aaed5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3987,7 +3987,7 @@ static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, if (shinfo->nr_frags > 0) { niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); if (net_is_devmem_iov(niov) && - net_devmem_iov_binding(niov)->dev != dev) + READ_ONCE(net_devmem_iov_binding(niov)->dev) != dev) goto out_free; } @@ -4818,10 +4818,7 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ - /* Other cpus might concurrently change txq->xmit_lock_owner - * to -1 or to their cpu id, but not to our id. - */ - if (READ_ONCE(txq->xmit_lock_owner) != cpu) { + if (!netif_tx_owned(txq, cpu)) { bool is_list = false; if (dev_xmit_recursion()) @@ -7807,11 +7804,12 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) +static void napi_threaded_poll_loop(struct napi_struct *napi, + unsigned long *busy_poll_last_qs) { + unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; - unsigned long last_qs = jiffies; for (;;) { bool repoll = false; @@ -7840,12 +7838,12 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) /* When busy poll is enabled, the old packets are not flushed in * napi_complete_done. So flush them here. */ - if (busy_poll) + if (busy_poll_last_qs) gro_flush_normal(&napi->gro, HZ >= 1000); local_bh_enable(); /* Call cond_resched here to avoid watchdog warnings. */ - if (repoll || busy_poll) { + if (repoll || busy_poll_last_qs) { rcu_softirq_qs_periodic(last_qs); cond_resched(); } @@ -7853,11 +7851,15 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) if (!repoll) break; } + + if (busy_poll_last_qs) + *busy_poll_last_qs = last_qs; } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; + unsigned long last_qs = jiffies; bool want_busy_poll; bool in_busy_poll; unsigned long val; @@ -7875,7 +7877,7 @@ static int napi_threaded_poll(void *data) assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state, want_busy_poll); - napi_threaded_poll_loop(napi, want_busy_poll); + napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL); } return 0; @@ -13189,7 +13191,7 @@ static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); - napi_threaded_poll_loop(&sd->backlog, false); + napi_threaded_poll_loop(&sd->backlog, NULL); } static void backlog_napi_setup(unsigned int cpu) diff --git a/net/core/devmem.c b/net/core/devmem.c index 8c9aad776bf4..69d79aee07ef 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -396,7 +396,8 @@ struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk, * net_device. */ dst_dev = dst_dev_rcu(dst); - if (unlikely(!dst_dev) || unlikely(dst_dev != binding->dev)) { + if (unlikely(!dst_dev) || + unlikely(dst_dev != READ_ONCE(binding->dev))) { err = -ENODEV; goto out_unlock; } @@ -513,7 +514,8 @@ static void mp_dmabuf_devmem_uninstall(void *mp_priv, xa_erase(&binding->bound_rxqs, xa_idx); if (xa_empty(&binding->bound_rxqs)) { mutex_lock(&binding->lock); - binding->dev = NULL; + ASSERT_EXCLUSIVE_WRITER(binding->dev); + WRITE_ONCE(binding->dev, NULL); mutex_unlock(&binding->lock); } break; diff --git a/net/core/filter.c b/net/core/filter.c index 0d5d5a17acb2..a77d23fe2359 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4150,12 +4150,14 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset) struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1]; struct xdp_rxq_info *rxq = xdp->rxq; - unsigned int tailroom; + int tailroom; if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz) return -EOPNOTSUPP; - tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag); + tailroom = rxq->frag_size - skb_frag_size(frag) - + skb_frag_off(frag) % rxq->frag_size; + WARN_ON_ONCE(tailroom < 0); if (unlikely(offset > tailroom)) return -EINVAL; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index a8558a52884f..cd74beffd209 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -132,7 +132,7 @@ static int netif_local_xmit_active(struct net_device *dev) for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - if (READ_ONCE(txq->xmit_lock_owner) == smp_processor_id()) + if (netif_tx_owned(txq, smp_processor_id())) return 1; } diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 9a3965680451..6a6f2cda5aae 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -20,7 +20,6 @@ #include <net/tcp.h> static siphash_aligned_key_t net_secret; -static siphash_aligned_key_t ts_secret; #define EPHEMERAL_PORT_SHUFFLE_PERIOD (10 * HZ) @@ -28,11 +27,6 @@ static __always_inline void net_secret_init(void) { net_get_random_once(&net_secret, sizeof(net_secret)); } - -static __always_inline void ts_secret_init(void) -{ - net_get_random_once(&ts_secret, sizeof(ts_secret)); -} #endif #ifdef CONFIG_INET @@ -53,28 +47,9 @@ static u32 seq_scale(u32 seq) #endif #if IS_ENABLED(CONFIG_IPV6) -u32 secure_tcpv6_ts_off(const struct net *net, - const __be32 *saddr, const __be32 *daddr) -{ - const struct { - struct in6_addr saddr; - struct in6_addr daddr; - } __aligned(SIPHASH_ALIGNMENT) combined = { - .saddr = *(struct in6_addr *)saddr, - .daddr = *(struct in6_addr *)daddr, - }; - - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash(&combined, offsetofend(typeof(combined), daddr), - &ts_secret); -} -EXPORT_IPV6_MOD(secure_tcpv6_ts_off); - -u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcpv6_seq_and_ts_off(const struct net *net, const __be32 *saddr, + const __be32 *daddr, __be16 sport, __be16 dport) { const struct { struct in6_addr saddr; @@ -87,14 +62,20 @@ u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr, .sport = sport, .dport = dport }; - u32 hash; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash(&combined, offsetofend(typeof(combined), dport), - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash(&combined, offsetofend(typeof(combined), dport), + &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL(secure_tcpv6_seq); +EXPORT_SYMBOL(secure_tcpv6_seq_and_ts_off); u64 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, __be16 dport) @@ -118,33 +99,30 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #endif #ifdef CONFIG_INET -u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) -{ - if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) - return 0; - - ts_secret_init(); - return siphash_2u32((__force u32)saddr, (__force u32)daddr, - &ts_secret); -} - /* secure_tcp_seq_and_tsoff(a, b, 0, d) == secure_ipv4_port_ephemeral(a, b, d), * but fortunately, `sport' cannot be 0 in any circumstances. If this changes, * it would be easy enough to have the former function use siphash_4u32, passing * the arguments as separate u32. */ -u32 secure_tcp_seq(__be32 saddr, __be32 daddr, - __be16 sport, __be16 dport) +union tcp_seq_and_ts_off +secure_tcp_seq_and_ts_off(const struct net *net, __be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) { - u32 hash; + u32 ports = (__force u32)sport << 16 | (__force u32)dport; + union tcp_seq_and_ts_off st; net_secret_init(); - hash = siphash_3u32((__force u32)saddr, (__force u32)daddr, - (__force u32)sport << 16 | (__force u32)dport, - &net_secret); - return seq_scale(hash); + + st.hash64 = siphash_3u32((__force u32)saddr, (__force u32)daddr, + ports, &net_secret); + + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) + st.ts_off = 0; + + st.seq = seq_scale(st.seq); + return st; } -EXPORT_SYMBOL_GPL(secure_tcp_seq); +EXPORT_SYMBOL_GPL(secure_tcp_seq_and_ts_off); u64 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 2e26174c9919..3261793abe83 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1205,8 +1205,8 @@ void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_strp_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_strp_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) @@ -1216,8 +1216,8 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; - psock->saved_data_ready = NULL; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); + WRITE_ONCE(psock->saved_data_ready, NULL); strp_stop(&psock->strp); } @@ -1296,8 +1296,8 @@ void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) return; psock->saved_data_ready = sk->sk_data_ready; - sk->sk_data_ready = sk_psock_verdict_data_ready; - sk->sk_write_space = sk_psock_write_space; + WRITE_ONCE(sk->sk_data_ready, sk_psock_verdict_data_ready); + WRITE_ONCE(sk->sk_write_space, sk_psock_write_space); } void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) @@ -1308,6 +1308,6 @@ void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) if (!psock->saved_data_ready) return; - sk->sk_data_ready = psock->saved_data_ready; + WRITE_ONCE(sk->sk_data_ready, psock->saved_data_ready); psock->saved_data_ready = NULL; } diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index b71c22475c51..df922f9f5289 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -748,6 +748,7 @@ config TCP_SIGPOOL config TCP_AO bool "TCP: Authentication Option (RFC5925)" select CRYPTO + select CRYPTO_LIB_UTILS select TCP_SIGPOOL depends on 64BIT && IPV6 != m # seq-number extension needs WRITE_ONCE(u64) help @@ -761,6 +762,7 @@ config TCP_AO config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" select CRYPTO_LIB_MD5 + select CRYPTO_LIB_UTILS help RFC2385 specifies a method of giving MD5 protection to TCP sessions. Its main (only?) use is to protect BGP sessions between core routers diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 52847950b28a..61e654b395be 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -200,7 +200,7 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, struct inet_bind2_bucket *tb2, unsigned short port) { - inet_sk(sk)->inet_num = port; + WRITE_ONCE(inet_sk(sk)->inet_num, port); inet_csk(sk)->icsk_bind_hash = tb; inet_csk(sk)->icsk_bind2_hash = tb2; sk_add_bind_node(sk, &tb2->owners); @@ -224,7 +224,7 @@ static void __inet_put_port(struct sock *sk) spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; inet_csk(sk)->icsk_bind_hash = NULL; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); sk->sk_userlocks &= ~SOCK_CONNECT_BIND; spin_lock(&head2->lock); @@ -352,7 +352,7 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && sk->sk_num == hnum && + if (net_eq(sock_net(sk), net) && READ_ONCE(sk->sk_num) == hnum && !ipv6_only_sock(sk)) { if (sk->sk_rcv_saddr != daddr) return -1; @@ -1206,7 +1206,7 @@ error: sk->sk_hash = 0; inet_sk(sk)->inet_sport = 0; - inet_sk(sk)->inet_num = 0; + WRITE_ONCE(inet_sk(sk)->inet_num, 0); if (tw) inet_twsk_bind_unhash(tw, hinfo); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 061751aabc8e..fc3affd9c801 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -378,9 +378,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcp_ts_off(net, - ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr); + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 643763bc2142..5654cc9c8a0b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -486,7 +486,8 @@ static void proc_fib_multipath_hash_set_seed(struct net *net, u32 user_seed) proc_fib_multipath_hash_rand_seed), }; - WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed, new); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.user_seed, new.user_seed); + WRITE_ONCE(net->ipv4.sysctl_fib_multipath_hash_seed.mp_seed, new.mp_seed); } static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write, @@ -500,7 +501,7 @@ static int proc_fib_multipath_hash_seed(const struct ctl_table *table, int write int ret; mphs = &net->ipv4.sysctl_fib_multipath_hash_seed; - user_seed = mphs->user_seed; + user_seed = READ_ONCE(mphs->user_seed); tmp = *table; tmp.data = &user_seed; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1c8be22a361e..ed6f6712f060 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -244,6 +244,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/md5.h> +#include <crypto/utils.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> @@ -1446,7 +1447,7 @@ out_err: err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } if (binding) @@ -4163,7 +4164,7 @@ ao_parse: break; case TCP_NOTSENT_LOWAT: WRITE_ONCE(tp->notsent_lowat, val); - sk->sk_write_space(sk); + READ_ONCE(sk->sk_write_space)(sk); break; case TCP_INQ: if (val > 1 || val < 0) @@ -4952,7 +4953,7 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); - if (memcmp(hash_location, newhash, 16) != 0) { + if (crypto_memneq(hash_location, newhash, 16)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 4980caddb0fc..a97cdf3e6af4 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -10,6 +10,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <crypto/hash.h> +#include <crypto/utils.h> #include <linux/inetdevice.h> #include <linux/tcp.h> @@ -922,7 +923,7 @@ tcp_ao_verify_hash(const struct sock *sk, const struct sk_buff *skb, /* XXX: make it per-AF callback? */ tcp_ao_hash_skb(family, hash_buf, key, sk, skb, traffic_key, (phash - (u8 *)th), sne); - if (memcmp(phash, hash_buf, maclen)) { + if (crypto_memneq(phash, hash_buf, maclen)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAOBAD); atomic64_inc(&info->counters.pkt_bad); atomic64_inc(&key->pkt_bad); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index a0215a2da324..cc0bd73f36b6 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -724,7 +724,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash); tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } else { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); /* Pairs with lockless read in sk_clone_lock() */ sock_replace_proto(sk, psock->sk_proto); } diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index d83efd91f461..7935702e394b 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -509,7 +509,7 @@ next_chunk: if (r->sdiag_family != AF_UNSPEC && sk->sk_family != r->sdiag_family) goto next_normal; - if (r->id.idiag_sport != htons(sk->sk_num) && + if (r->id.idiag_sport != htons(READ_ONCE(sk->sk_num)) && r->id.idiag_sport) goto next_normal; if (r->id.idiag_dport != sk->sk_dport && diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c27d11c3470b..71ac69b7b75e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5320,25 +5320,11 @@ static void tcp_ofo_queue(struct sock *sk) static bool tcp_prune_ofo_queue(struct sock *sk, const struct sk_buff *in_skb); static int tcp_prune_queue(struct sock *sk, const struct sk_buff *in_skb); -/* Check if this incoming skb can be added to socket receive queues - * while satisfying sk->sk_rcvbuf limit. - * - * In theory we should use skb->truesize, but this can cause problems - * when applications use too small SO_RCVBUF values. - * When LRO / hw gro is used, the socket might have a high tp->scaling_ratio, - * allowing RWIN to be close to available space. - * Whenever the receive queue gets full, we can receive a small packet - * filling RWIN, but with a high skb->truesize, because most NIC use 4K page - * plus sk_buff metadata even when receiving less than 1500 bytes of payload. - * - * Note that we use skb->len to decide to accept or drop this packet, - * but sk->sk_rmem_alloc is the sum of all skb->truesize. - */ static bool tcp_can_ingest(const struct sock *sk, const struct sk_buff *skb) { unsigned int rmem = atomic_read(&sk->sk_rmem_alloc); - return rmem + skb->len <= sk->sk_rcvbuf; + return rmem <= sk->sk_rcvbuf; } static int tcp_try_rmem_schedule(struct sock *sk, const struct sk_buff *skb, @@ -5371,7 +5357,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM); return; } @@ -5581,7 +5567,7 @@ err: void tcp_data_ready(struct sock *sk) { if (tcp_epollin_ready(sk, sk->sk_rcvlowat) || sock_flag(sk, SOCK_DONE)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) @@ -5637,7 +5623,7 @@ queue_and_out: inet_csk(sk)->icsk_ack.pending |= (ICSK_ACK_NOMEM | ICSK_ACK_NOW); inet_csk_schedule_ack(sk); - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); if (skb_queue_len(&sk->sk_receive_queue) && skb->len) { reason = SKB_DROP_REASON_PROTO_MEM; @@ -6060,7 +6046,9 @@ static void tcp_new_space(struct sock *sk) tp->snd_cwnd_stamp = tcp_jiffies32; } - INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); + INDIRECT_CALL_1(READ_ONCE(sk->sk_write_space), + sk_stream_write_space, + sk); } /* Caller made space either from: @@ -6271,7 +6259,7 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, const struct tcphdr *t BUG(); WRITE_ONCE(tp->urg_data, TCP_URG_VALID | tmp); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); } } } @@ -7604,6 +7592,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct sock *fastopen_sk = NULL; + union tcp_seq_and_ts_off st; struct request_sock *req; bool want_cookie = false; struct dst_entry *dst; @@ -7673,9 +7662,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (!dst) goto drop_and_free; + if (tmp_opt.tstamp_ok || (!want_cookie && !isn)) + st = af_ops->init_seq_and_ts_off(net, skb); + if (tmp_opt.tstamp_ok) { tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); - tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); + tcp_rsk(req)->ts_off = st.ts_off; } if (!want_cookie && !isn) { int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); @@ -7697,7 +7689,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop_and_release; } - isn = af_ops->init_seq(skb); + isn = st.seq; } tcp_ecn_create_request(req, skb, sk, dst); @@ -7738,7 +7730,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); goto drop_and_free; } - sk->sk_data_ready(sk); + READ_ONCE(sk->sk_data_ready)(sk); bh_unlock_sock(fastopen_sk); sock_put(fastopen_sk); } else { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9dc75ba73eff..190e8a238876 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -88,6 +88,7 @@ #include <linux/skbuff_ref.h> #include <crypto/md5.h> +#include <crypto/utils.h> #include <trace/events/tcp.h> @@ -104,17 +105,14 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = { static DEFINE_MUTEX(tcp_exit_batch_mutex); -static u32 tcp_v4_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v4_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcp_seq(ip_hdr(skb)->daddr, - ip_hdr(skb)->saddr, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); + return secure_tcp_seq_and_ts_off(net, + ip_hdr(skb)->daddr, + ip_hdr(skb)->saddr, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) @@ -326,15 +324,16 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len rt = NULL; if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcp_seq_and_ts_off(net, + inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port)); - WRITE_ONCE(tp->tsoffset, - secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr)); + WRITE_ONCE(tp->write_seq, st.seq); + WRITE_ONCE(tp->tsoffset, st.ts_off); } atomic_set(&inet->inet_id, get_random_u16()); @@ -821,7 +820,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, goto out; tcp_v4_md5_hash_skb(newhash, key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } @@ -1658,8 +1657,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, - .init_seq = tcp_v4_init_seq, - .init_ts_off = tcp_v4_init_ts_off, + .init_seq_and_ts_off = tcp_v4_init_seq_and_ts_off, .send_synack = tcp_v4_send_synack, }; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index d9c5a43bd281..dafb63b923d0 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -1004,7 +1004,7 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, reason = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) - parent->sk_data_ready(parent); + READ_ONCE(parent->sk_data_ready)(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 27384024ebc0..668a0284c3d5 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1787,7 +1787,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * using prepare_to_wait_exclusive(). */ while (nb) { - INDIRECT_CALL_1(sk->sk_data_ready, + INDIRECT_CALL_1(READ_ONCE(sk->sk_data_ready), sock_def_readable, sk); nb--; } @@ -2286,7 +2286,6 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) udp_sk(sk)->udp_port_hash); hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); nhslot2 = udp_hashslot2(udptable, newhash); - udp_sk(sk)->udp_portaddr_hash = newhash; if (hslot2 != nhslot2 || rcu_access_pointer(sk->sk_reuseport_cb)) { @@ -2320,19 +2319,25 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) if (udp_hashed4(sk)) { spin_lock_bh(&hslot->lock); - udp_rehash4(udptable, sk, newhash4); - if (hslot2 != nhslot2) { - spin_lock(&hslot2->lock); - udp_hash4_dec(hslot2); - spin_unlock(&hslot2->lock); - - spin_lock(&nhslot2->lock); - udp_hash4_inc(nhslot2); - spin_unlock(&nhslot2->lock); + if (inet_rcv_saddr_any(sk)) { + udp_unhash4(udptable, sk); + } else { + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); + } } spin_unlock_bh(&hslot->lock); } + + udp_sk(sk)->udp_portaddr_hash = newhash; } } EXPORT_IPV6_MOD(udp_lib_rehash); diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index 912f0bfef4af..d328a3078ae0 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -158,7 +158,7 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6; if (restore) { - sk->sk_write_space = psock->saved_write_space; + WRITE_ONCE(sk->sk_write_space, psock->saved_write_space); sock_replace_proto(sk, psock->sk_proto); return 0; } diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 5e1da088d8e1..182d38e6d6d8 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -95,7 +95,8 @@ static inline int compute_score(struct sock *sk, const struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && + if (net_eq(sock_net(sk), net) && + READ_ONCE(inet_sk(sk)->inet_num) == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 85df25c36409..08cd86f49bf9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1063,7 +1063,8 @@ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) - dev = l3mdev_master_dev_rcu(dev); + dev = l3mdev_master_dev_rcu(dev) ? : + dev_net(dev)->loopback_dev; else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which @@ -3582,7 +3583,6 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; - int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; @@ -3624,11 +3624,10 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, fib6_nh->fib_nh_weight = 1; - /* We cannot add true routes via loopback here, - * they would result in kernel looping; promote them to reject routes + /* Reset the nexthop device to the loopback device in case of reject + * routes. */ - addr_type = ipv6_addr_type(&cfg->fc_dst); - if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { + if (cfg->fc_flags & RTF_REJECT) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7e007f013ec8..4f6f0d751d6c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -151,9 +151,14 @@ static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk, tcp_parse_options(net, skb, &tcp_opt, 0, NULL); if (tcp_opt.saw_tstamp && tcp_opt.rcv_tsecr) { - tsoff = secure_tcpv6_ts_off(net, - ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); + tsoff = st.ts_off; tcp_opt.rcv_tsecr -= tsoff; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c2816048007d..a62dd2999aec 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -68,6 +68,7 @@ #include <linux/seq_file.h> #include <crypto/md5.h> +#include <crypto/utils.h> #include <trace/events/tcp.h> @@ -104,18 +105,14 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) } } -static u32 tcp_v6_init_seq(const struct sk_buff *skb) +static union tcp_seq_and_ts_off +tcp_v6_init_seq_and_ts_off(const struct net *net, const struct sk_buff *skb) { - return secure_tcpv6_seq(ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32, - tcp_hdr(skb)->dest, - tcp_hdr(skb)->source); -} - -static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) -{ - return secure_tcpv6_ts_off(net, ipv6_hdr(skb)->daddr.s6_addr32, - ipv6_hdr(skb)->saddr.s6_addr32); + return secure_tcpv6_seq_and_ts_off(net, + ipv6_hdr(skb)->daddr.s6_addr32, + ipv6_hdr(skb)->saddr.s6_addr32, + tcp_hdr(skb)->dest, + tcp_hdr(skb)->source); } static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, @@ -319,14 +316,16 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, sk_set_txhash(sk); if (likely(!tp->repair)) { + union tcp_seq_and_ts_off st; + + st = secure_tcpv6_seq_and_ts_off(net, + np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); if (!tp->write_seq) - WRITE_ONCE(tp->write_seq, - secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport)); - tp->tsoffset = secure_tcpv6_ts_off(net, np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32); + WRITE_ONCE(tp->write_seq, st.seq); + tp->tsoffset = st.ts_off; } if (tcp_fastopen_defer_connect(sk, &err)) @@ -831,8 +830,7 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .cookie_init_seq = cookie_v6_init_sequence, #endif .route_req = tcp_v6_route_req, - .init_seq = tcp_v6_init_seq, - .init_ts_off = tcp_v6_init_ts_off, + .init_seq_and_ts_off = tcp_v6_init_seq_and_ts_off, .send_synack = tcp_v6_send_synack, }; @@ -1063,7 +1061,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, key.type = TCP_KEY_MD5; tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); - if (memcmp(md5_hash_location, newhash, 16) != 0) + if (crypto_memneq(md5_hash_location, newhash, 16)) goto out; } #endif diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c index 75096b2195d2..078e1e23d8d1 100644 --- a/net/mac80211/eht.c +++ b/net/mac80211/eht.c @@ -154,6 +154,7 @@ void ieee80211_rx_eml_op_mode_notif(struct ieee80211_sub_if_data *sdata, u8 *ptr = mgmt->u.action.u.eml_omn.variable; struct ieee80211_eml_params eml_params = { .link_id = status->link_id, + .control = control, }; struct sta_info *sta; int opt_len = 0; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 7298836469b3..57a456690406 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -212,9 +212,24 @@ void mptcp_pm_send_ack(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); } -void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +static bool subflow_in_rm_list(const struct mptcp_subflow_context *subflow, + const struct mptcp_rm_list *rm_list) +{ + u8 i, id = subflow_get_local_id(subflow); + + for (i = 0; i < rm_list->nr; i++) { + if (rm_list->ids[i] == id) + return true; + } + + return false; +} + +static void +mptcp_pm_addr_send_ack_avoid_list(struct mptcp_sock *msk, + const struct mptcp_rm_list *rm_list) { - struct mptcp_subflow_context *subflow, *alt = NULL; + struct mptcp_subflow_context *subflow, *stale = NULL, *same_id = NULL; msk_owned_by_me(msk); lockdep_assert_held(&msk->pm.lock); @@ -224,19 +239,35 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) return; mptcp_for_each_subflow(msk, subflow) { - if (__mptcp_subflow_active(subflow)) { - if (!subflow->stale) { - mptcp_pm_send_ack(msk, subflow, false, false); - return; - } + if (!__mptcp_subflow_active(subflow)) + continue; - if (!alt) - alt = subflow; + if (unlikely(subflow->stale)) { + if (!stale) + stale = subflow; + } else if (unlikely(rm_list && + subflow_in_rm_list(subflow, rm_list))) { + if (!same_id) + same_id = subflow; + } else { + goto send_ack; } } - if (alt) - mptcp_pm_send_ack(msk, alt, false, false); + if (same_id) + subflow = same_id; + else if (stale) + subflow = stale; + else + return; + +send_ack: + mptcp_pm_send_ack(msk, subflow, false, false); +} + +void mptcp_pm_addr_send_ack(struct mptcp_sock *msk) +{ + mptcp_pm_addr_send_ack_avoid_list(msk, NULL); } int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk, @@ -470,7 +501,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ msk->pm.rm_list_tx = *rm_list; rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL); WRITE_ONCE(msk->pm.addr_signal, rm_addr); - mptcp_pm_addr_send_ack(msk); + mptcp_pm_addr_send_ack_avoid_list(msk, rm_list); return 0; } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index b5316a6c7d1b..b2b9df43960e 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -418,6 +418,15 @@ subflow: } exit: + /* If an endpoint has both the signal and subflow flags, but it is not + * possible to create subflows -- the 'while' loop body above never + * executed -- then still mark the endp as used, which is somehow the + * case. This avoids issues later when removing the endpoint and calling + * __mark_subflow_endp_available(), which expects the increment here. + */ + if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id) + msk->pm.local_addr_used++; + mptcp_pm_nl_check_work_pending(msk); } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ae97e4d2c1af..e72a9da85e29 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -833,6 +833,11 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, } } +/* Use NFT_ITER_UPDATE iterator even if this may be called from the preparation + * phase, the set clone might already exist from a previous command, or it might + * be a set that is going away and does not require a clone. The netns and + * netlink release paths also need to work on the live set. + */ static void nft_map_deactivate(const struct nft_ctx *ctx, struct nft_set *set) { struct nft_set_iter iter = { @@ -7110,6 +7115,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; + bool set_full = false; u64 expiration; u64 timeout; int err, i; @@ -7401,10 +7407,18 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_elem_free; + if (!(flags & NFT_SET_ELEM_CATCHALL)) { + unsigned int max = nft_set_maxsize(set), nelems; + + nelems = atomic_inc_return(&set->nelems); + if (nelems > max) + set_full = true; + } + trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); if (trans == NULL) { err = -ENOMEM; - goto err_elem_free; + goto err_set_size; } ext->genmask = nft_genmask_cur(ctx->net); @@ -7456,7 +7470,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ue->priv = elem_priv; nft_trans_commit_list_add_elem(ctx->net, trans); - goto err_elem_free; + goto err_set_size; } } } @@ -7474,23 +7488,16 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, goto err_element_clash; } - if (!(flags & NFT_SET_ELEM_CATCHALL)) { - unsigned int max = nft_set_maxsize(set); - - if (!atomic_add_unless(&set->nelems, 1, max)) { - err = -ENFILE; - goto err_set_full; - } - } - nft_trans_container_elem(trans)->elems[0].priv = elem.priv; nft_trans_commit_list_add_elem(ctx->net, trans); - return 0; -err_set_full: - nft_setelem_remove(ctx->net, set, elem.priv); + return set_full ? -ENFILE : 0; + err_element_clash: kfree(trans); +err_set_size: + if (!(flags & NFT_SET_ELEM_CATCHALL)) + atomic_dec(&set->nelems); err_elem_free: nf_tables_set_elem_destroy(ctx, set, elem.priv); err_parse_data: @@ -7841,9 +7848,12 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, static int nft_set_flush(struct nft_ctx *ctx, struct nft_set *set, u8 genmask) { + /* The set backend might need to clone the set, do it now from the + * preparation phase, use NFT_ITER_UPDATE_CLONE iterator type. + */ struct nft_set_iter iter = { .genmask = genmask, - .type = NFT_ITER_UPDATE, + .type = NFT_ITER_UPDATE_CLONE, .fn = nft_setelem_flush, }; @@ -10407,11 +10417,6 @@ static void nft_trans_gc_queue_work(struct nft_trans_gc *trans) schedule_work(&trans_gc_work); } -static int nft_trans_gc_space(struct nft_trans_gc *trans) -{ - return NFT_TRANS_GC_BATCHCOUNT - trans->count; -} - struct nft_trans_gc *nft_trans_gc_queue_async(struct nft_trans_gc *gc, unsigned int gc_seq, gfp_t gfp) { diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 739b992bde59..b0e571c8e3f3 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -374,6 +374,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, { switch (iter->type) { case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: /* only relevant for netlink dumps which use READ type */ WARN_ON_ONCE(iter->skip != 0); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 7ef4b44471d3..a34632ae6048 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1680,11 +1680,11 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, } /** - * pipapo_gc() - Drop expired entries from set, destroy start and end elements + * pipapo_gc_scan() - Drop expired entries from set and link them to gc list * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) +static void pipapo_gc_scan(struct nft_set *set, struct nft_pipapo_match *m) { struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); @@ -1697,6 +1697,8 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) if (!gc) return; + list_add(&gc->list, &priv->gc_head); + while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const struct nft_pipapo_field *f; @@ -1724,9 +1726,13 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) * NFT_SET_ELEM_DEAD_BIT. */ if (__nft_set_elem_expired(&e->ext, tstamp)) { - gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); - if (!gc) - return; + if (!nft_trans_gc_space(gc)) { + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); + if (!gc) + return; + + list_add(&gc->list, &priv->gc_head); + } nft_pipapo_gc_deactivate(net, set, e); pipapo_drop(m, rulemap); @@ -1740,10 +1746,30 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) } } - gc = nft_trans_gc_catchall_sync(gc); + priv->last_gc = jiffies; +} + +/** + * pipapo_gc_queue() - Free expired elements + * @set: nftables API set representation + */ +static void pipapo_gc_queue(struct nft_set *set) +{ + struct nft_pipapo *priv = nft_set_priv(set); + struct nft_trans_gc *gc, *next; + + /* always do a catchall cycle: */ + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (gc) { + gc = nft_trans_gc_catchall_sync(gc); + if (gc) + nft_trans_gc_queue_sync_done(gc); + } + + /* always purge queued gc elements. */ + list_for_each_entry_safe(gc, next, &priv->gc_head, list) { + list_del(&gc->list); nft_trans_gc_queue_sync_done(gc); - priv->last_gc = jiffies; } } @@ -1797,6 +1823,10 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * * We also need to create a new working copy for subsequent insertions and * deletions. + * + * After the live copy has been replaced by the clone, we can safely queue + * expired elements that have been collected by pipapo_gc_scan() for + * memory reclaim. */ static void nft_pipapo_commit(struct nft_set *set) { @@ -1807,7 +1837,7 @@ static void nft_pipapo_commit(struct nft_set *set) return; if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) - pipapo_gc(set, priv->clone); + pipapo_gc_scan(set, priv->clone); old = rcu_replace_pointer(priv->match, priv->clone, nft_pipapo_transaction_mutex_held(set)); @@ -1815,6 +1845,8 @@ static void nft_pipapo_commit(struct nft_set *set) if (old) call_rcu(&old->rcu, pipapo_reclaim_match); + + pipapo_gc_queue(set); } static void nft_pipapo_abort(const struct nft_set *set) @@ -2144,13 +2176,20 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_pipapo_match *m; switch (iter->type) { - case NFT_ITER_UPDATE: + case NFT_ITER_UPDATE_CLONE: m = pipapo_maybe_clone(set); if (!m) { iter->err = -ENOMEM; return; } - + nft_pipapo_do_walk(ctx, set, m, iter); + break; + case NFT_ITER_UPDATE: + if (priv->clone) + m = priv->clone; + else + m = rcu_dereference_protected(priv->match, + nft_pipapo_transaction_mutex_held(set)); nft_pipapo_do_walk(ctx, set, m, iter); break; case NFT_ITER_READ: @@ -2272,6 +2311,7 @@ static int nft_pipapo_init(const struct nft_set *set, f->mt = NULL; } + INIT_LIST_HEAD(&priv->gc_head); rcu_assign_pointer(priv->match, m); return 0; @@ -2321,6 +2361,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; + WARN_ON_ONCE(!list_empty(&priv->gc_head)); + m = rcu_dereference_protected(priv->match, true); if (priv->clone) { diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index eaab422aa56a..9aee9a9eaeb7 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -156,12 +156,14 @@ struct nft_pipapo_match { * @clone: Copy where pending insertions and deletions are kept * @width: Total bytes to be matched for one packet, including padding * @last_gc: Timestamp of last garbage collection run, jiffies + * @gc_head: list of nft_trans_gc to queue up for mem reclaim */ struct nft_pipapo { struct nft_pipapo_match __rcu *match; struct nft_pipapo_match *clone; int width; unsigned long last_gc; + struct list_head gc_head; }; struct nft_pipapo_elem; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index e90c5b8b4d5e..e42905376654 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -856,13 +856,15 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, struct nft_rbtree *priv = nft_set_priv(set); switch (iter->type) { - case NFT_ITER_UPDATE: - lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); - + case NFT_ITER_UPDATE_CLONE: if (nft_array_may_resize(set) < 0) { iter->err = -ENOMEM; break; } + fallthrough; + case NFT_ITER_UPDATE: + lockdep_assert_held(&nft_pernet(ctx->net)->commit_mutex); + nft_rbtree_do_walk(ctx, set, iter); break; case NFT_ITER_READ: diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index 3670bb33732e..7cb1e6aaae90 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -707,8 +707,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, int rc; data_exch = kzalloc_obj(*data_exch); - if (!data_exch) + if (!data_exch) { + kfree_skb(skb); return -ENOMEM; + } data_exch->cb = cb; data_exch->cb_context = cb_context; @@ -731,8 +733,10 @@ static int digital_in_send(struct nfc_dev *nfc_dev, struct nfc_target *target, data_exch); exit: - if (rc) + if (rc) { + kfree_skb(skb); kfree(data_exch); + } return rc; } diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 6e9b76e2cc56..43d871525dbc 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -567,6 +567,10 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); timer_delete_sync(&ndev->data_timer); + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, + ndev->cur_conn_id, + -ENODEV); mutex_unlock(&ndev->req_lock); return 0; } @@ -598,6 +602,11 @@ static int nci_close_device(struct nci_dev *ndev) flush_workqueue(ndev->cmd_wq); timer_delete_sync(&ndev->cmd_timer); + timer_delete_sync(&ndev->data_timer); + + if (test_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + nci_data_exchange_complete(ndev, NULL, ndev->cur_conn_id, + -ENODEV); /* Clear flags except NCI_UNREG */ ndev->flags &= BIT(NCI_UNREG); @@ -1035,18 +1044,23 @@ static int nci_transceive(struct nfc_dev *nfc_dev, struct nfc_target *target, struct nci_conn_info *conn_info; conn_info = ndev->rf_conn_info; - if (!conn_info) + if (!conn_info) { + kfree_skb(skb); return -EPROTO; + } pr_debug("target_idx %d, len %d\n", target->idx, skb->len); if (!ndev->target_active_prot) { pr_err("unable to exchange data, no active target\n"); + kfree_skb(skb); return -EINVAL; } - if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) + if (test_and_set_bit(NCI_DATA_EXCHANGE, &ndev->flags)) { + kfree_skb(skb); return -EBUSY; + } /* store cb and context to be used on receiving data */ conn_info->data_exchange_cb = cb; @@ -1482,10 +1496,20 @@ static bool nci_valid_size(struct sk_buff *skb) unsigned int hdr_size = NCI_CTRL_HDR_SIZE; if (skb->len < hdr_size || - !nci_plen(skb->data) || skb->len < hdr_size + nci_plen(skb->data)) { return false; } + + if (!nci_plen(skb->data)) { + /* Allow zero length in proprietary notifications (0x20 - 0x3F). */ + if (nci_opcode_oid(nci_opcode(skb->data)) >= 0x20 && + nci_mt(skb->data) == NCI_MT_NTF_PKT) + return true; + + /* Disallow zero length otherwise. */ + return false; + } + return true; } diff --git a/net/nfc/nci/data.c b/net/nfc/nci/data.c index 78f4131af3cf..5f98c73db5af 100644 --- a/net/nfc/nci/data.c +++ b/net/nfc/nci/data.c @@ -33,7 +33,8 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, conn_info = nci_get_conn_info_by_conn_id(ndev, conn_id); if (!conn_info) { kfree_skb(skb); - goto exit; + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + return; } cb = conn_info->data_exchange_cb; @@ -45,6 +46,12 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, timer_delete_sync(&ndev->data_timer); clear_bit(NCI_DATA_EXCHANGE_TO, &ndev->flags); + /* Mark the exchange as done before calling the callback. + * The callback (e.g. rawsock_data_exchange_complete) may + * want to immediately queue another data exchange. + */ + clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); + if (cb) { /* forward skb to nfc core */ cb(cb_context, skb, err); @@ -54,9 +61,6 @@ void nci_data_exchange_complete(struct nci_dev *ndev, struct sk_buff *skb, /* no waiting callback, free skb */ kfree_skb(skb); } - -exit: - clear_bit(NCI_DATA_EXCHANGE, &ndev->flags); } /* ----------------- NCI TX Data ----------------- */ diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index b049022399ae..f7d7a599fade 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -67,6 +67,17 @@ static int rawsock_release(struct socket *sock) if (sock->type == SOCK_RAW) nfc_sock_unlink(&raw_sk_list, sk); + if (sk->sk_state == TCP_ESTABLISHED) { + /* Prevent rawsock_tx_work from starting new transmits and + * wait for any in-progress work to finish. This must happen + * before the socket is orphaned to avoid a race where + * rawsock_tx_work runs after the NCI device has been freed. + */ + sk->sk_shutdown |= SEND_SHUTDOWN; + cancel_work_sync(&nfc_rawsock(sk)->tx_work); + rawsock_write_queue_purge(sk); + } + sock_orphan(sk); sock_put(sk); diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 04f310255692..654e23d13e3d 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -490,18 +490,24 @@ bool rds_tcp_tune(struct socket *sock) struct rds_tcp_net *rtn; tcp_sock_set_nodelay(sock->sk); - lock_sock(sk); /* TCP timer functions might access net namespace even after * a process which created this net namespace terminated. */ if (!sk->sk_net_refcnt) { - if (!maybe_get_net(net)) { - release_sock(sk); + if (!maybe_get_net(net)) return false; - } + /* + * sk_net_refcnt_upgrade() must be called before lock_sock() + * because it does a GFP_KERNEL allocation, which can trigger + * fs_reclaim and create a circular lock dependency with the + * socket lock. The fields it modifies (sk_net_refcnt, + * ns_tracker) are not accessed by any concurrent code path + * at this point. + */ sk_net_refcnt_upgrade(sk); put_net(net); } + lock_sock(sk); rtn = net_generic(net, rds_tcp_netid); if (rtn->sndbuf_size > 0) { sk->sk_sndbuf = rtn->sndbuf_size; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index bd51522c7953..7d5e50c921a0 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1360,6 +1360,12 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, return -EINVAL; } + if (bind && !(flags & TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT)) { + NL_SET_ERR_MSG_MOD(extack, + "Attaching ct to a non ingress/clsact qdisc is unsupported"); + return -EOPNOTSUPP; + } + err = nla_parse_nested(tb, TCA_CT_MAX, nla, ct_policy, extack); if (err < 0) return err; diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 686eaed81b81..fdbfcaa3e2ab 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -32,9 +32,12 @@ static ktime_t gate_get_time(struct tcf_gate *gact) return KTIME_MAX; } -static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start) +static void tcf_gate_params_free_rcu(struct rcu_head *head); + +static void gate_get_start_time(struct tcf_gate *gact, + const struct tcf_gate_params *param, + ktime_t *start) { - struct tcf_gate_params *param = &gact->param; ktime_t now, base, cycle; u64 n; @@ -69,12 +72,14 @@ static enum hrtimer_restart gate_timer_func(struct hrtimer *timer) { struct tcf_gate *gact = container_of(timer, struct tcf_gate, hitimer); - struct tcf_gate_params *p = &gact->param; struct tcfg_gate_entry *next; + struct tcf_gate_params *p; ktime_t close_time, now; spin_lock(&gact->tcf_lock); + p = rcu_dereference_protected(gact->param, + lockdep_is_held(&gact->tcf_lock)); next = gact->next_entry; /* cycle start, clear pending bit, clear total octets */ @@ -225,6 +230,35 @@ static void release_entry_list(struct list_head *entries) } } +static int tcf_gate_copy_entries(struct tcf_gate_params *dst, + const struct tcf_gate_params *src, + struct netlink_ext_ack *extack) +{ + struct tcfg_gate_entry *entry; + int i = 0; + + list_for_each_entry(entry, &src->entries, list) { + struct tcfg_gate_entry *new; + + new = kzalloc(sizeof(*new), GFP_ATOMIC); + if (!new) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + new->index = entry->index; + new->gate_state = entry->gate_state; + new->interval = entry->interval; + new->ipv = entry->ipv; + new->maxoctets = entry->maxoctets; + list_add_tail(&new->list, &dst->entries); + i++; + } + + dst->num_entries = i; + return 0; +} + static int parse_gate_list(struct nlattr *list_attr, struct tcf_gate_params *sched, struct netlink_ext_ack *extack) @@ -270,24 +304,44 @@ release_list: return err; } -static void gate_setup_timer(struct tcf_gate *gact, u64 basetime, - enum tk_offsets tko, s32 clockid, - bool do_init) +static bool gate_timer_needs_cancel(u64 basetime, u64 old_basetime, + enum tk_offsets tko, + enum tk_offsets old_tko, + s32 clockid, s32 old_clockid) { - if (!do_init) { - if (basetime == gact->param.tcfg_basetime && - tko == gact->tk_offset && - clockid == gact->param.tcfg_clockid) - return; + return basetime != old_basetime || + clockid != old_clockid || + tko != old_tko; +} - spin_unlock_bh(&gact->tcf_lock); - hrtimer_cancel(&gact->hitimer); - spin_lock_bh(&gact->tcf_lock); +static int gate_clock_resolve(s32 clockid, enum tk_offsets *tko, + struct netlink_ext_ack *extack) +{ + switch (clockid) { + case CLOCK_REALTIME: + *tko = TK_OFFS_REAL; + return 0; + case CLOCK_MONOTONIC: + *tko = TK_OFFS_MAX; + return 0; + case CLOCK_BOOTTIME: + *tko = TK_OFFS_BOOT; + return 0; + case CLOCK_TAI: + *tko = TK_OFFS_TAI; + return 0; + default: + NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); + return -EINVAL; } - gact->param.tcfg_basetime = basetime; - gact->param.tcfg_clockid = clockid; - gact->tk_offset = tko; - hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, HRTIMER_MODE_ABS_SOFT); +} + +static void gate_setup_timer(struct tcf_gate *gact, s32 clockid, + enum tk_offsets tko) +{ + WRITE_ONCE(gact->tk_offset, tko); + hrtimer_setup(&gact->hitimer, gate_timer_func, clockid, + HRTIMER_MODE_ABS_SOFT); } static int tcf_gate_init(struct net *net, struct nlattr *nla, @@ -296,15 +350,22 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_gate_ops.net_id); - enum tk_offsets tk_offset = TK_OFFS_TAI; + u64 cycletime = 0, basetime = 0, cycletime_ext = 0; + struct tcf_gate_params *p = NULL, *old_p = NULL; + enum tk_offsets old_tk_offset = TK_OFFS_TAI; + const struct tcf_gate_params *cur_p = NULL; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_GATE_MAX + 1]; + enum tk_offsets tko = TK_OFFS_TAI; struct tcf_chain *goto_ch = NULL; - u64 cycletime = 0, basetime = 0; - struct tcf_gate_params *p; + s32 timer_clockid = CLOCK_TAI; + bool use_old_entries = false; + s32 old_clockid = CLOCK_TAI; + bool need_cancel = false; s32 clockid = CLOCK_TAI; struct tcf_gate *gact; struct tc_gate *parm; + u64 old_basetime = 0; int ret = 0, err; u32 gflags = 0; s32 prio = -1; @@ -321,26 +382,8 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (!tb[TCA_GATE_PARMS]) return -EINVAL; - if (tb[TCA_GATE_CLOCKID]) { + if (tb[TCA_GATE_CLOCKID]) clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]); - switch (clockid) { - case CLOCK_REALTIME: - tk_offset = TK_OFFS_REAL; - break; - case CLOCK_MONOTONIC: - tk_offset = TK_OFFS_MAX; - break; - case CLOCK_BOOTTIME: - tk_offset = TK_OFFS_BOOT; - break; - case CLOCK_TAI: - tk_offset = TK_OFFS_TAI; - break; - default: - NL_SET_ERR_MSG(extack, "Invalid 'clockid'"); - return -EINVAL; - } - } parm = nla_data(tb[TCA_GATE_PARMS]); index = parm->index; @@ -366,6 +409,60 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, return -EEXIST; } + gact = to_gate(*a); + + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); + if (err < 0) + goto release_idr; + + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) { + err = -ENOMEM; + goto chain_put; + } + INIT_LIST_HEAD(&p->entries); + + use_old_entries = !tb[TCA_GATE_ENTRY_LIST]; + if (!use_old_entries) { + err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); + if (err < 0) + goto err_free; + use_old_entries = !err; + } + + if (ret == ACT_P_CREATED && use_old_entries) { + NL_SET_ERR_MSG(extack, "The entry list is empty"); + err = -EINVAL; + goto err_free; + } + + if (ret != ACT_P_CREATED) { + rcu_read_lock(); + cur_p = rcu_dereference(gact->param); + + old_basetime = cur_p->tcfg_basetime; + old_clockid = cur_p->tcfg_clockid; + old_tk_offset = READ_ONCE(gact->tk_offset); + + basetime = old_basetime; + cycletime_ext = cur_p->tcfg_cycletime_ext; + prio = cur_p->tcfg_priority; + gflags = cur_p->tcfg_flags; + + if (!tb[TCA_GATE_CLOCKID]) + clockid = old_clockid; + + err = 0; + if (use_old_entries) { + err = tcf_gate_copy_entries(p, cur_p, extack); + if (!err && !tb[TCA_GATE_CYCLE_TIME]) + cycletime = cur_p->tcfg_cycletime; + } + rcu_read_unlock(); + if (err) + goto err_free; + } + if (tb[TCA_GATE_PRIORITY]) prio = nla_get_s32(tb[TCA_GATE_PRIORITY]); @@ -375,25 +472,26 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (tb[TCA_GATE_FLAGS]) gflags = nla_get_u32(tb[TCA_GATE_FLAGS]); - gact = to_gate(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&gact->param.entries); + if (tb[TCA_GATE_CYCLE_TIME]) + cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); - err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); - if (err < 0) - goto release_idr; + if (tb[TCA_GATE_CYCLE_TIME_EXT]) + cycletime_ext = nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); - spin_lock_bh(&gact->tcf_lock); - p = &gact->param; + err = gate_clock_resolve(clockid, &tko, extack); + if (err) + goto err_free; + timer_clockid = clockid; - if (tb[TCA_GATE_CYCLE_TIME]) - cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]); + need_cancel = ret != ACT_P_CREATED && + gate_timer_needs_cancel(basetime, old_basetime, + tko, old_tk_offset, + timer_clockid, old_clockid); - if (tb[TCA_GATE_ENTRY_LIST]) { - err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack); - if (err < 0) - goto chain_put; - } + if (need_cancel) + hrtimer_cancel(&gact->hitimer); + + spin_lock_bh(&gact->tcf_lock); if (!cycletime) { struct tcfg_gate_entry *entry; @@ -402,22 +500,20 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, list_for_each_entry(entry, &p->entries, list) cycle = ktime_add_ns(cycle, entry->interval); cycletime = cycle; - if (!cycletime) { - err = -EINVAL; - goto chain_put; - } } p->tcfg_cycletime = cycletime; + p->tcfg_cycletime_ext = cycletime_ext; - if (tb[TCA_GATE_CYCLE_TIME_EXT]) - p->tcfg_cycletime_ext = - nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]); - - gate_setup_timer(gact, basetime, tk_offset, clockid, - ret == ACT_P_CREATED); + if (need_cancel || ret == ACT_P_CREATED) + gate_setup_timer(gact, timer_clockid, tko); p->tcfg_priority = prio; p->tcfg_flags = gflags; - gate_get_start_time(gact, &start); + p->tcfg_basetime = basetime; + p->tcfg_clockid = timer_clockid; + gate_get_start_time(gact, p, &start); + + old_p = rcu_replace_pointer(gact->param, p, + lockdep_is_held(&gact->tcf_lock)); gact->current_close_time = start; gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING; @@ -434,11 +530,15 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); + if (old_p) + call_rcu(&old_p->rcu, tcf_gate_params_free_rcu); + return ret; +err_free: + release_entry_list(&p->entries); + kfree(p); chain_put: - spin_unlock_bh(&gact->tcf_lock); - if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: @@ -446,21 +546,29 @@ release_idr: * without taking tcf_lock. */ if (ret == ACT_P_CREATED) - gate_setup_timer(gact, gact->param.tcfg_basetime, - gact->tk_offset, gact->param.tcfg_clockid, - true); + gate_setup_timer(gact, timer_clockid, tko); + tcf_idr_release(*a, bind); return err; } +static void tcf_gate_params_free_rcu(struct rcu_head *head) +{ + struct tcf_gate_params *p = container_of(head, struct tcf_gate_params, rcu); + + release_entry_list(&p->entries); + kfree(p); +} + static void tcf_gate_cleanup(struct tc_action *a) { struct tcf_gate *gact = to_gate(a); struct tcf_gate_params *p; - p = &gact->param; hrtimer_cancel(&gact->hitimer); - release_entry_list(&p->entries); + p = rcu_dereference_protected(gact->param, 1); + if (p) + call_rcu(&p->rcu, tcf_gate_params_free_rcu); } static int dumping_entry(struct sk_buff *skb, @@ -509,10 +617,9 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, struct nlattr *entry_list; struct tcf_t t; - spin_lock_bh(&gact->tcf_lock); - opt.action = gact->tcf_action; - - p = &gact->param; + rcu_read_lock(); + opt.action = READ_ONCE(gact->tcf_action); + p = rcu_dereference(gact->param); if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -552,12 +659,12 @@ static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &gact->tcf_tm); if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD)) goto nla_put_failure; - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); return skb->len; nla_put_failure: - spin_unlock_bh(&gact->tcf_lock); + rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 79df81d12894..d5e8a91bb4eb 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -293,8 +293,8 @@ static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) /* called when adding new meta information */ static int __add_metainfo(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic, bool exists) + struct tcf_ife_params *p, u32 metaid, void *metaval, + int len, bool atomic) { struct tcf_meta_info *mi = NULL; int ret = 0; @@ -313,45 +313,40 @@ static int __add_metainfo(const struct tcf_meta_ops *ops, } } - if (exists) - spin_lock_bh(&ife->tcf_lock); - list_add_tail(&mi->metalist, &ife->metalist); - if (exists) - spin_unlock_bh(&ife->tcf_lock); + list_add_tail(&mi->metalist, &p->metalist); return ret; } static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, - struct tcf_ife_info *ife, u32 metaid, - bool exists) + struct tcf_ife_params *p, u32 metaid) { int ret; if (!try_module_get(ops->owner)) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + ret = __add_metainfo(ops, p, metaid, NULL, 0, true); if (ret) module_put(ops->owner); return ret; } -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool exists) +static int add_metainfo(struct tcf_ife_params *p, u32 metaid, void *metaval, + int len) { const struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret; if (!ops) return -ENOENT; - ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + ret = __add_metainfo(ops, p, metaid, metaval, len, false); if (ret) /*put back what find_ife_oplist took */ module_put(ops->owner); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife, bool exists) +static int use_all_metadata(struct tcf_ife_params *p) { struct tcf_meta_ops *o; int rc = 0; @@ -359,7 +354,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); + rc = add_metainfo_and_get_ops(o, p, o->metaid); if (rc == 0) installed += 1; } @@ -371,7 +366,7 @@ static int use_all_metadata(struct tcf_ife_info *ife, bool exists) return -EINVAL; } -static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) +static int dump_metalist(struct sk_buff *skb, struct tcf_ife_params *p) { struct tcf_meta_info *e; struct nlattr *nest; @@ -379,14 +374,14 @@ static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) int total_encoded = 0; /*can only happen on decode */ - if (list_empty(&ife->metalist)) + if (list_empty(&p->metalist)) return 0; nest = nla_nest_start_noflag(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry(e, &p->metalist, metalist) { if (!e->ops->get(skb, e)) total_encoded += 1; } @@ -403,13 +398,11 @@ out_nlmsg_trim: return -1; } -/* under ife->tcf_lock */ -static void _tcf_ife_cleanup(struct tc_action *a) +static void __tcf_ife_cleanup(struct tcf_ife_params *p) { - struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_safe(e, n, &p->metalist, metalist) { list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -422,18 +415,23 @@ static void _tcf_ife_cleanup(struct tc_action *a) } } +static void tcf_ife_cleanup_params(struct rcu_head *head) +{ + struct tcf_ife_params *p = container_of(head, struct tcf_ife_params, + rcu); + + __tcf_ife_cleanup(p); + kfree(p); +} + static void tcf_ife_cleanup(struct tc_action *a) { struct tcf_ife_info *ife = to_ife(a); struct tcf_ife_params *p; - spin_lock_bh(&ife->tcf_lock); - _tcf_ife_cleanup(a); - spin_unlock_bh(&ife->tcf_lock); - p = rcu_dereference_protected(ife->params, 1); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); } static int load_metalist(struct nlattr **tb, bool rtnl_held) @@ -455,8 +453,7 @@ static int load_metalist(struct nlattr **tb, bool rtnl_held) return 0; } -static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, - bool exists, bool rtnl_held) +static int populate_metalist(struct tcf_ife_params *p, struct nlattr **tb) { int len = 0; int rc = 0; @@ -468,7 +465,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = add_metainfo(ife, i, val, len, exists); + rc = add_metainfo(p, i, val, len); if (rc) return rc; } @@ -523,6 +520,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p = kzalloc_obj(*p); if (!p) return -ENOMEM; + INIT_LIST_HEAD(&p->metalist); if (tb[TCA_IFE_METALST]) { err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, @@ -567,8 +565,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } ife = to_ife(*a); - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&ife->metalist); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) @@ -600,8 +596,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = populate_metalist(ife, tb2, exists, - !(flags & TCA_ACT_FLAGS_NO_RTNL)); + err = populate_metalist(p, tb2); if (err) goto metadata_parse_err; } else { @@ -610,7 +605,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife, exists); + err = use_all_metadata(p); if (err) goto metadata_parse_err; } @@ -626,13 +621,14 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); if (p) - kfree_rcu(p, rcu); + call_rcu(&p->rcu, tcf_ife_cleanup_params); return ret; metadata_parse_err: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: + __tcf_ife_cleanup(p); kfree(p); tcf_idr_release(*a, bind); return err; @@ -679,7 +675,7 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, if (nla_put(skb, TCA_IFE_TYPE, 2, &p->eth_type)) goto nla_put_failure; - if (dump_metalist(skb, ife)) { + if (dump_metalist(skb, p)) { /*ignore failure to dump metalist */ pr_info("Failed to dump metalist\n"); } @@ -693,13 +689,13 @@ nla_put_failure: return -1; } -static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, +static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_params *p, u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; /* XXX: use hash to speed up */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (metaid == e->metaid) { if (e->ops) { /* We check for decode presence already */ @@ -716,10 +712,13 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; + struct tcf_ife_params *p; u8 *ifehdr_end; u8 *tlv_data; u16 metalen; + p = rcu_dereference_bh(ife->params); + bstats_update(this_cpu_ptr(ife->common.cpu_bstats), skb); tcf_lastuse_update(&ife->tcf_tm); @@ -745,7 +744,7 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, return TC_ACT_SHOT; } - if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { + if (find_decode_metaid(skb, p, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ @@ -769,12 +768,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, /*XXX: check if we can do this at install time instead of current * send data path **/ -static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) +static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_params *p) { - struct tcf_meta_info *e, *n; + struct tcf_meta_info *e; int tot_run_sz = 0, run_sz = 0; - list_for_each_entry_safe(e, n, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->check_presence) { run_sz = e->ops->check_presence(skb, e); tot_run_sz += run_sz; @@ -795,7 +794,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA where ORIGDATA = original ethernet header ... */ - u16 metalen = ife_get_sz(skb, ife); + u16 metalen = ife_get_sz(skb, p); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = 0; int new_len = skb->len + hdrm; @@ -833,25 +832,21 @@ drop: if (!ife_meta) goto drop; - spin_lock(&ife->tcf_lock); - /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... */ - list_for_each_entry(e, &ife->metalist, metalist) { + list_for_each_entry_rcu(e, &p->metalist, metalist) { if (e->ops->encode) { err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { /* too corrupt to keep around if overwritten */ - spin_unlock(&ife->tcf_lock); goto drop; } skboff += err; } - spin_unlock(&ife->tcf_lock); oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(p->eth_src)) diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 343309e9009b..4829c27446e3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2228,6 +2228,11 @@ static bool is_qdisc_ingress(__u32 classid) return (TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS)); } +static bool is_ingress_or_clsact(struct tcf_block *block, struct Qdisc *q) +{ + return tcf_block_shared(block) || (q && !!(q->flags & TCQ_F_INGRESS)); +} + static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { @@ -2420,6 +2425,8 @@ replay: flags |= TCA_ACT_FLAGS_NO_RTNL; if (is_qdisc_ingress(parent)) flags |= TCA_ACT_FLAGS_AT_INGRESS; + if (is_ingress_or_clsact(block, q)) + flags |= TCA_ACT_FLAGS_AT_INGRESS_OR_CLSACT; err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, flags, extack); if (err == 0) { diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index a64d27476231..ffea9fbd522d 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -391,8 +391,8 @@ static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = { 1239850263, 1191209601, 1147878294, 1108955788 }; -static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, - u64 target_ns, u64 rtt_est_ns); +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust); + /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2) * @@ -2013,7 +2013,8 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) u64 delay; u32 len; - if (q->config->is_shared && now - q->last_checked_active >= q->config->sync_time) { + if (q->config->is_shared && q->rate_ns && + now - q->last_checked_active >= q->config->sync_time) { struct net_device *dev = qdisc_dev(sch); struct cake_sched_data *other_priv; u64 new_rate = q->config->rate_bps; @@ -2039,12 +2040,9 @@ static struct sk_buff *cake_dequeue(struct Qdisc *sch) if (num_active_qs > 1) new_rate = div64_u64(q->config->rate_bps, num_active_qs); - /* mtu = 0 is used to only update the rate and not mess with cobalt params */ - cake_set_rate(b, new_rate, 0, 0, 0); + cake_configure_rates(sch, new_rate, true); q->last_checked_active = now; q->active_queues = num_active_qs; - q->rate_ns = b->tin_rate_ns; - q->rate_shft = b->tin_rate_shft; } begin: @@ -2361,12 +2359,10 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu, b->cparams.p_dec = 1 << 20; /* 1/4096 */ } -static int cake_config_besteffort(struct Qdisc *sch) +static int cake_config_besteffort(struct Qdisc *sch, u64 rate, u32 mtu) { struct cake_sched_data *q = qdisc_priv(sch); struct cake_tin_data *b = &q->tins[0]; - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; q->tin_cnt = 1; @@ -2380,12 +2376,10 @@ static int cake_config_besteffort(struct Qdisc *sch) return 0; } -static int cake_config_precedence(struct Qdisc *sch) +static int cake_config_precedence(struct Qdisc *sch, u64 rate, u32 mtu) { /* convert high-level (user visible) parameters into internal format */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2456,7 +2450,7 @@ static int cake_config_precedence(struct Qdisc *sch) * Total 12 traffic classes. */ -static int cake_config_diffserv8(struct Qdisc *sch) +static int cake_config_diffserv8(struct Qdisc *sch, u64 rate, u32 mtu) { /* Pruned list of traffic classes for typical applications: * @@ -2473,8 +2467,6 @@ static int cake_config_diffserv8(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 256; u32 i; @@ -2504,7 +2496,7 @@ static int cake_config_diffserv8(struct Qdisc *sch) return 0; } -static int cake_config_diffserv4(struct Qdisc *sch) +static int cake_config_diffserv4(struct Qdisc *sch, u64 rate, u32 mtu) { /* Further pruned list of traffic classes for four-class system: * @@ -2517,8 +2509,6 @@ static int cake_config_diffserv4(struct Qdisc *sch) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 4; @@ -2546,7 +2536,7 @@ static int cake_config_diffserv4(struct Qdisc *sch) return 0; } -static int cake_config_diffserv3(struct Qdisc *sch) +static int cake_config_diffserv3(struct Qdisc *sch, u64 rate, u32 mtu) { /* Simplified Diffserv structure with 3 tins. * Latency Sensitive (CS7, CS6, EF, VA, TOS4) @@ -2554,8 +2544,6 @@ static int cake_config_diffserv3(struct Qdisc *sch) * Low Priority (LE, CS1) */ struct cake_sched_data *q = qdisc_priv(sch); - u32 mtu = psched_mtu(qdisc_dev(sch)); - u64 rate = q->config->rate_bps; u32 quantum = 1024; q->tin_cnt = 3; @@ -2580,32 +2568,33 @@ static int cake_config_diffserv3(struct Qdisc *sch) return 0; } -static void cake_reconfigure(struct Qdisc *sch) +static void cake_configure_rates(struct Qdisc *sch, u64 rate, bool rate_adjust) { + u32 mtu = likely(rate_adjust) ? 0 : psched_mtu(qdisc_dev(sch)); struct cake_sched_data *qd = qdisc_priv(sch); struct cake_sched_config *q = qd->config; int c, ft; switch (q->tin_mode) { case CAKE_DIFFSERV_BESTEFFORT: - ft = cake_config_besteffort(sch); + ft = cake_config_besteffort(sch, rate, mtu); break; case CAKE_DIFFSERV_PRECEDENCE: - ft = cake_config_precedence(sch); + ft = cake_config_precedence(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV8: - ft = cake_config_diffserv8(sch); + ft = cake_config_diffserv8(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV4: - ft = cake_config_diffserv4(sch); + ft = cake_config_diffserv4(sch, rate, mtu); break; case CAKE_DIFFSERV_DIFFSERV3: default: - ft = cake_config_diffserv3(sch); + ft = cake_config_diffserv3(sch, rate, mtu); break; } @@ -2616,6 +2605,14 @@ static void cake_reconfigure(struct Qdisc *sch) qd->rate_ns = qd->tins[ft].tin_rate_ns; qd->rate_shft = qd->tins[ft].tin_rate_shft; +} + +static void cake_reconfigure(struct Qdisc *sch) +{ + struct cake_sched_data *qd = qdisc_priv(sch); + struct cake_sched_config *q = qd->config; + + cake_configure_rates(sch, qd->config->rate_bps, false); if (q->buffer_config_limit) { qd->buffer_limit = q->buffer_config_limit; diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c index 306e046276d4..a4b07b661b77 100644 --- a/net/sched/sch_ets.c +++ b/net/sched/sch_ets.c @@ -115,12 +115,12 @@ static void ets_offload_change(struct Qdisc *sch) struct ets_sched *q = qdisc_priv(sch); struct tc_ets_qopt_offload qopt; unsigned int w_psum_prev = 0; - unsigned int q_psum = 0; - unsigned int q_sum = 0; unsigned int quantum; unsigned int w_psum; unsigned int weight; unsigned int i; + u64 q_psum = 0; + u64 q_sum = 0; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; @@ -138,8 +138,12 @@ static void ets_offload_change(struct Qdisc *sch) for (i = 0; i < q->nbands; i++) { quantum = q->classes[i].quantum; - q_psum += quantum; - w_psum = quantum ? q_psum * 100 / q_sum : 0; + if (quantum) { + q_psum += quantum; + w_psum = div64_u64(q_psum * 100, q_sum); + } else { + w_psum = 0; + } weight = w_psum - w_psum_prev; w_psum_prev = w_psum; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 9a550f832d78..f2edcf872981 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -823,6 +823,7 @@ static void fq_reset(struct Qdisc *sch) for (idx = 0; idx < FQ_BANDS; idx++) { q->band_flows[idx].new_flows.first = NULL; q->band_flows[idx].old_flows.first = NULL; + q->band_pkt_count[idx] = 0; } q->delayed = RB_ROOT; q->flows = 0; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3a7e00c063c3..cd83d11bc8e4 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1785,7 +1785,7 @@ restart: __skb_queue_tail(&other->sk_receive_queue, skb); spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); return 0; @@ -2278,7 +2278,7 @@ restart_locked: scm_stat_add(other, skb); skb_queue_tail(&other->sk_receive_queue, skb); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sock_put(other); scm_destroy(&scm); return len; @@ -2351,7 +2351,7 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other, sk_send_sigurg(other); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); return 0; out_unlock: @@ -2477,7 +2477,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, spin_unlock(&other->sk_receive_queue.lock); unix_state_unlock(other); - other->sk_data_ready(other); + READ_ONCE(other->sk_data_ready)(other); sent += size; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 3b46bc635c43..6149f6a79897 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -167,26 +167,32 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) struct xdp_buff_xsk *pos, *tmp; struct list_head *xskb_list; u32 contd = 0; + u32 num_desc; int err; - if (frags) - contd = XDP_PKT_CONTD; + if (likely(!frags)) { + err = __xsk_rcv_zc(xs, xskb, len, contd); + if (err) + goto err; + return 0; + } - err = __xsk_rcv_zc(xs, xskb, len, contd); - if (err) + contd = XDP_PKT_CONTD; + num_desc = xdp_get_shared_info_from_buff(xdp)->nr_frags + 1; + if (xskq_prod_nb_free(xs->rx, num_desc) < num_desc) { + xs->rx_queue_full++; + err = -ENOBUFS; goto err; - if (likely(!frags)) - return 0; + } + __xsk_rcv_zc(xs, xskb, len, contd); xskb_list = &xskb->pool->xskb_list; list_for_each_entry_safe(pos, tmp, xskb_list, list_node) { if (list_is_singular(xskb_list)) contd = 0; len = pos->xdp.data_end - pos->xdp.data; - err = __xsk_rcv_zc(xs, pos, len, contd); - if (err) - goto err; - list_del(&pos->list_node); + __xsk_rcv_zc(xs, pos, len, contd); + list_del_init(&pos->list_node); } return 0; diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs index c1cca7b438c3..e5fba6bf6db0 100644 --- a/rust/kernel/io.rs +++ b/rust/kernel/io.rs @@ -139,9 +139,9 @@ pub struct Mmio<const SIZE: usize = 0>(MmioRaw<SIZE>); /// Internal helper macros used to invoke C MMIO read functions. /// -/// This macro is intended to be used by higher-level MMIO access macros (define_read) and provides -/// a unified expansion for infallible vs. fallible read semantics. It emits a direct call into the -/// corresponding C helper and performs the required cast to the Rust return type. +/// This macro is intended to be used by higher-level MMIO access macros (io_define_read) and +/// provides a unified expansion for infallible vs. fallible read semantics. It emits a direct call +/// into the corresponding C helper and performs the required cast to the Rust return type. /// /// # Parameters /// @@ -166,9 +166,9 @@ macro_rules! call_mmio_read { /// Internal helper macros used to invoke C MMIO write functions. /// -/// This macro is intended to be used by higher-level MMIO access macros (define_write) and provides -/// a unified expansion for infallible vs. fallible write semantics. It emits a direct call into the -/// corresponding C helper and performs the required cast to the Rust return type. +/// This macro is intended to be used by higher-level MMIO access macros (io_define_write) and +/// provides a unified expansion for infallible vs. fallible write semantics. It emits a direct call +/// into the corresponding C helper and performs the required cast to the Rust return type. /// /// # Parameters /// @@ -193,7 +193,30 @@ macro_rules! call_mmio_write { }}; } -macro_rules! define_read { +/// Generates an accessor method for reading from an I/O backend. +/// +/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked +/// (infallible) or runtime bounds-checked (fallible) read methods. It abstracts the address +/// calculation and bounds checking, and delegates the actual I/O read operation to a specified +/// helper macro, making it generic over different I/O backends. +/// +/// # Parameters +/// +/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on +/// `IoKnownSize` for compile-time checks and returns the value directly. `fallible` performs +/// runtime checks against `maxsize()` and returns a `Result<T>`. +/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g., +/// `#[cfg(CONFIG_64BIT)]` or inline directives). +/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`). +/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `read32`, +/// `try_read8`). +/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call +/// (e.g., `call_mmio_read`). +/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the +/// `$call_macro`. +/// * `$type_name:ty` - The Rust type of the value being read (e.g., `u8`, `u32`). +#[macro_export] +macro_rules! io_define_read { (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) -> $type_name:ty) => { /// Read IO data from a given offset known at compile time. @@ -226,9 +249,33 @@ macro_rules! define_read { } }; } -pub(crate) use define_read; +pub use io_define_read; -macro_rules! define_write { +/// Generates an accessor method for writing to an I/O backend. +/// +/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked +/// (infallible) or runtime bounds-checked (fallible) write methods. It abstracts the address +/// calculation and bounds checking, and delegates the actual I/O write operation to a specified +/// helper macro, making it generic over different I/O backends. +/// +/// # Parameters +/// +/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on +/// `IoKnownSize` for compile-time checks and returns `()`. `fallible` performs runtime checks +/// against `maxsize()` and returns a `Result`. +/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g., +/// `#[cfg(CONFIG_64BIT)]` or inline directives). +/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`). +/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `write32`, +/// `try_write8`). +/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call +/// (e.g., `call_mmio_write`). +/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the +/// `$call_macro`. +/// * `$type_name:ty` - The Rust type of the value being written (e.g., `u8`, `u32`). Note the use +/// of `<-` before the type to denote a write operation. +#[macro_export] +macro_rules! io_define_write { (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) <- $type_name:ty) => { /// Write IO data from a given offset known at compile time. @@ -259,7 +306,7 @@ macro_rules! define_write { } }; } -pub(crate) use define_write; +pub use io_define_write; /// Checks whether an access of type `U` at the given `offset` /// is valid within this region. @@ -509,40 +556,40 @@ impl<const SIZE: usize> Io for Mmio<SIZE> { self.0.maxsize() } - define_read!(fallible, try_read8, call_mmio_read(readb) -> u8); - define_read!(fallible, try_read16, call_mmio_read(readw) -> u16); - define_read!(fallible, try_read32, call_mmio_read(readl) -> u32); - define_read!( + io_define_read!(fallible, try_read8, call_mmio_read(readb) -> u8); + io_define_read!(fallible, try_read16, call_mmio_read(readw) -> u16); + io_define_read!(fallible, try_read32, call_mmio_read(readl) -> u32); + io_define_read!( fallible, #[cfg(CONFIG_64BIT)] try_read64, call_mmio_read(readq) -> u64 ); - define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8); - define_write!(fallible, try_write16, call_mmio_write(writew) <- u16); - define_write!(fallible, try_write32, call_mmio_write(writel) <- u32); - define_write!( + io_define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8); + io_define_write!(fallible, try_write16, call_mmio_write(writew) <- u16); + io_define_write!(fallible, try_write32, call_mmio_write(writel) <- u32); + io_define_write!( fallible, #[cfg(CONFIG_64BIT)] try_write64, call_mmio_write(writeq) <- u64 ); - define_read!(infallible, read8, call_mmio_read(readb) -> u8); - define_read!(infallible, read16, call_mmio_read(readw) -> u16); - define_read!(infallible, read32, call_mmio_read(readl) -> u32); - define_read!( + io_define_read!(infallible, read8, call_mmio_read(readb) -> u8); + io_define_read!(infallible, read16, call_mmio_read(readw) -> u16); + io_define_read!(infallible, read32, call_mmio_read(readl) -> u32); + io_define_read!( infallible, #[cfg(CONFIG_64BIT)] read64, call_mmio_read(readq) -> u64 ); - define_write!(infallible, write8, call_mmio_write(writeb) <- u8); - define_write!(infallible, write16, call_mmio_write(writew) <- u16); - define_write!(infallible, write32, call_mmio_write(writel) <- u32); - define_write!( + io_define_write!(infallible, write8, call_mmio_write(writeb) <- u8); + io_define_write!(infallible, write16, call_mmio_write(writew) <- u16); + io_define_write!(infallible, write32, call_mmio_write(writel) <- u32); + io_define_write!( infallible, #[cfg(CONFIG_64BIT)] write64, @@ -566,40 +613,40 @@ impl<const SIZE: usize> Mmio<SIZE> { unsafe { &*core::ptr::from_ref(raw).cast() } } - define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8); - define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16); - define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32); - define_read!( + io_define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8); + io_define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16); + io_define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32); + io_define_read!( infallible, #[cfg(CONFIG_64BIT)] pub read64_relaxed, call_mmio_read(readq_relaxed) -> u64 ); - define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8); - define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16); - define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32); - define_read!( + io_define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8); + io_define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16); + io_define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32); + io_define_read!( fallible, #[cfg(CONFIG_64BIT)] pub try_read64_relaxed, call_mmio_read(readq_relaxed) -> u64 ); - define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8); - define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16); - define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32); - define_write!( + io_define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8); + io_define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16); + io_define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32); + io_define_write!( infallible, #[cfg(CONFIG_64BIT)] pub write64_relaxed, call_mmio_write(writeq_relaxed) <- u64 ); - define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8); - define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16); - define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32); - define_write!( + io_define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8); + io_define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16); + io_define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32); + io_define_write!( fallible, #[cfg(CONFIG_64BIT)] pub try_write64_relaxed, diff --git a/rust/kernel/pci/io.rs b/rust/kernel/pci/io.rs index 6ca4cf75594c..fb6edab2aea7 100644 --- a/rust/kernel/pci/io.rs +++ b/rust/kernel/pci/io.rs @@ -8,8 +8,8 @@ use crate::{ device, devres::Devres, io::{ - define_read, - define_write, + io_define_read, + io_define_write, Io, IoCapable, IoKnownSize, @@ -88,7 +88,7 @@ pub struct ConfigSpace<'a, S: ConfigSpaceKind = Extended> { /// Internal helper macros used to invoke C PCI configuration space read functions. /// /// This macro is intended to be used by higher-level PCI configuration space access macros -/// (define_read) and provides a unified expansion for infallible vs. fallible read semantics. It +/// (io_define_read) and provides a unified expansion for infallible vs. fallible read semantics. It /// emits a direct call into the corresponding C helper and performs the required cast to the Rust /// return type. /// @@ -117,9 +117,9 @@ macro_rules! call_config_read { /// Internal helper macros used to invoke C PCI configuration space write functions. /// /// This macro is intended to be used by higher-level PCI configuration space access macros -/// (define_write) and provides a unified expansion for infallible vs. fallible read semantics. It -/// emits a direct call into the corresponding C helper and performs the required cast to the Rust -/// return type. +/// (io_define_write) and provides a unified expansion for infallible vs. fallible read semantics. +/// It emits a direct call into the corresponding C helper and performs the required cast to the +/// Rust return type. /// /// # Parameters /// @@ -163,13 +163,13 @@ impl<'a, S: ConfigSpaceKind> Io for ConfigSpace<'a, S> { // PCI configuration space does not support fallible operations. // The default implementations from the Io trait are not used. - define_read!(infallible, read8, call_config_read(pci_read_config_byte) -> u8); - define_read!(infallible, read16, call_config_read(pci_read_config_word) -> u16); - define_read!(infallible, read32, call_config_read(pci_read_config_dword) -> u32); + io_define_read!(infallible, read8, call_config_read(pci_read_config_byte) -> u8); + io_define_read!(infallible, read16, call_config_read(pci_read_config_word) -> u16); + io_define_read!(infallible, read32, call_config_read(pci_read_config_dword) -> u32); - define_write!(infallible, write8, call_config_write(pci_write_config_byte) <- u8); - define_write!(infallible, write16, call_config_write(pci_write_config_word) <- u16); - define_write!(infallible, write32, call_config_write(pci_write_config_dword) <- u32); + io_define_write!(infallible, write8, call_config_write(pci_write_config_byte) <- u8); + io_define_write!(infallible, write16, call_config_write(pci_write_config_word) <- u16); + io_define_write!(infallible, write32, call_config_write(pci_write_config_dword) <- u32); } impl<'a, S: ConfigSpaceKind> IoKnownSize for ConfigSpace<'a, S> { diff --git a/sound/hda/codecs/realtek/alc269.c b/sound/hda/codecs/realtek/alc269.c index 36053042ca77..86bb22d19629 100644 --- a/sound/hda/codecs/realtek/alc269.c +++ b/sound/hda/codecs/realtek/alc269.c @@ -1017,6 +1017,24 @@ static int alc269_resume(struct hda_codec *codec) return 0; } +#define STARLABS_STARFIGHTER_SHUTUP_DELAY_MS 30 + +static void starlabs_starfighter_shutup(struct hda_codec *codec) +{ + if (snd_hda_gen_shutup_speakers(codec)) + msleep(STARLABS_STARFIGHTER_SHUTUP_DELAY_MS); +} + +static void alc233_fixup_starlabs_starfighter(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) + spec->shutup = starlabs_starfighter_shutup; +} + static void alc269_fixup_pincfg_no_hp_to_lineout(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4040,6 +4058,7 @@ enum { ALC245_FIXUP_CLEVO_NOISY_MIC, ALC269_FIXUP_VAIO_VJFH52_MIC_NO_PRESENCE, ALC233_FIXUP_MEDION_MTL_SPK, + ALC233_FIXUP_STARLABS_STARFIGHTER, ALC294_FIXUP_BASS_SPEAKER_15, ALC283_FIXUP_DELL_HP_RESUME, ALC294_FIXUP_ASUS_CS35L41_SPI_2, @@ -4056,6 +4075,7 @@ enum { ALC236_FIXUP_HP_MUTE_LED_MICMUTE_GPIO, ALC233_FIXUP_LENOVO_GPIO2_MIC_HOTKEY, ALC245_FIXUP_BASS_HP_DAC, + ALC245_FIXUP_ACER_MICMUTE_LED, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -6499,6 +6519,10 @@ static const struct hda_fixup alc269_fixups[] = { { } }, }, + [ALC233_FIXUP_STARLABS_STARFIGHTER] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc233_fixup_starlabs_starfighter, + }, [ALC294_FIXUP_BASS_SPEAKER_15] = { .type = HDA_FIXUP_FUNC, .v.func = alc294_fixup_bass_speaker_15, @@ -6576,6 +6600,12 @@ static const struct hda_fixup alc269_fixups[] = { /* Borrow the DAC routing selected for those Thinkpads */ .v.func = alc285_fixup_thinkpad_x1_gen7, }, + [ALC245_FIXUP_ACER_MICMUTE_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_coef_micmute_led, + .chained = true, + .chain_id = ALC2XX_FIXUP_HEADSET_MIC, + } }; static const struct hda_quirk alc269_fixup_tbl[] = { @@ -6591,6 +6621,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF), + SND_PCI_QUIRK(0x1025, 0x0943, "Acer Aspire V3-572G", ALC269_FIXUP_ASPIRE_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK), SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), @@ -6627,6 +6658,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x159c, "Acer Nitro 5 AN515-58", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x1597, "Acer Nitro 5 AN517-55", ALC2XX_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1025, 0x169a, "Acer Swift SFG16", ALC256_FIXUP_ACER_SFG16_MICMUTE_LED), + SND_PCI_QUIRK(0x1025, 0x171e, "Acer Nitro ANV15-51", ALC245_FIXUP_ACER_MICMUTE_LED), SND_PCI_QUIRK(0x1025, 0x1826, "Acer Helios ZPC", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x182c, "Acer Helios ZPD", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), SND_PCI_QUIRK(0x1025, 0x1844, "Acer Helios ZPS", ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2), @@ -7311,7 +7343,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP), - SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP), + SND_PCI_QUIRK(0x144d, 0xc188, "Samsung Galaxy Book Flex (NT950QCT-A38A)", ALC298_FIXUP_SAMSUNG_AMP), + SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Book Flex (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP), SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP), @@ -7651,6 +7684,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX), SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME), SND_PCI_QUIRK(0x2782, 0x4900, "MEDION E15443", ALC233_FIXUP_MEDION_MTL_SPK), + SND_PCI_QUIRK(0x7017, 0x2014, "Star Labs StarFighter", ALC233_FIXUP_STARLABS_STARFIGHTER), SND_PCI_QUIRK(0x8086, 0x2074, "Intel NUC 8", ALC233_FIXUP_INTEL_NUC8_DMIC), SND_PCI_QUIRK(0x8086, 0x2080, "Intel NUC 8 Rugged", ALC256_FIXUP_INTEL_NUC8_RUGGED), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", ALC256_FIXUP_INTEL_NUC10), @@ -7747,6 +7781,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC298_FIXUP_TPT470_DOCK_FIX, .name = "tpt470-dock-fix"}, {.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"}, {.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"}, + {.id = ALC233_FIXUP_STARLABS_STARFIGHTER, .name = "starlabs-starfighter"}, {.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"}, {.id = ALC269_FIXUP_SONY_VAIO, .name = "vaio"}, {.id = ALC269_FIXUP_DELL_M101Z, .name = "dell-m101z"}, diff --git a/sound/hda/codecs/side-codecs/cs35l56_hda.c b/sound/hda/codecs/side-codecs/cs35l56_hda.c index cfc8de2ae499..1ace4beef508 100644 --- a/sound/hda/codecs/side-codecs/cs35l56_hda.c +++ b/sound/hda/codecs/side-codecs/cs35l56_hda.c @@ -249,7 +249,7 @@ static int cs35l56_hda_posture_put(struct snd_kcontrol *kcontrol, struct snd_ctl_elem_value *ucontrol) { struct cs35l56_hda *cs35l56 = snd_kcontrol_chip(kcontrol); - unsigned long pos = ucontrol->value.integer.value[0]; + long pos = ucontrol->value.integer.value[0]; bool changed; int ret; @@ -403,10 +403,6 @@ static void cs35l56_hda_remove_controls(struct cs35l56_hda *cs35l56) snd_ctl_remove(cs35l56->codec->card, cs35l56->volume_ctl); } -static const struct cs_dsp_client_ops cs35l56_hda_client_ops = { - /* cs_dsp requires the client to provide this even if it is empty */ -}; - static int cs35l56_hda_request_firmware_file(struct cs35l56_hda *cs35l56, const struct firmware **firmware, char **filename, const char *base_name, const char *system_name, @@ -1149,7 +1145,6 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id) cs35l56->base.cal_index = cs35l56->index; cs35l56_init_cs_dsp(&cs35l56->base, &cs35l56->cs_dsp); - cs35l56->cs_dsp.client_ops = &cs35l56_hda_client_ops; if (cs35l56->base.reset_gpio) { dev_dbg(cs35l56->base.dev, "Hard reset\n"); diff --git a/sound/hda/controllers/intel.c b/sound/hda/controllers/intel.c index 6fddf400c4a3..3f434994c18d 100644 --- a/sound/hda/controllers/intel.c +++ b/sound/hda/controllers/intel.c @@ -1751,6 +1751,8 @@ static int default_bdl_pos_adj(struct azx *chip) return 1; case AZX_DRIVER_ZHAOXINHDMI: return 128; + case AZX_DRIVER_NVIDIA: + return 64; default: return 32; } diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index f1a63475100d..7af4daeb4c6f 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -703,6 +703,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Vivobook_ASUSLaptop M6501RR_M6501RR"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ASUS EXPERTBOOK BM1503CDA"), + } + }, {} }; diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c index b83bc4de1301..3e04e6897b14 100644 --- a/sound/soc/codecs/cs42l43-jack.c +++ b/sound/soc/codecs/cs42l43-jack.c @@ -699,6 +699,7 @@ static int cs42l43_run_type_detect(struct cs42l43_codec *priv) switch (type & CS42L43_HSDET_TYPE_STS_MASK) { case 0x0: // CTIA case 0x1: // OMTP + case 0x4: return cs42l43_run_load_detect(priv, true); case 0x2: // 3-pole return cs42l43_run_load_detect(priv, false); diff --git a/sound/soc/sdca/sdca_interrupts.c b/sound/soc/sdca/sdca_interrupts.c index d9e22cf40f77..95b1ab4ba1b0 100644 --- a/sound/soc/sdca/sdca_interrupts.c +++ b/sound/soc/sdca/sdca_interrupts.c @@ -265,9 +265,9 @@ static int sdca_irq_request_locked(struct device *dev, } /** - * sdca_request_irq - request an individual SDCA interrupt + * sdca_irq_request - request an individual SDCA interrupt * @dev: Pointer to the struct device against which things should be allocated. - * @interrupt_info: Pointer to the interrupt information structure. + * @info: Pointer to the interrupt information structure. * @sdca_irq: SDCA interrupt position. * @name: Name to be given to the IRQ. * @handler: A callback thread function to be called for the IRQ. diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c index 73bce9712dbd..bf4401aba76c 100644 --- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -160,8 +160,8 @@ int snd_usb_endpoint_implicit_feedback_sink(struct snd_usb_endpoint *ep) * This won't be used for implicit feedback which takes the packet size * returned from the sync source */ -static int slave_next_packet_size(struct snd_usb_endpoint *ep, - unsigned int avail) +static int synced_next_packet_size(struct snd_usb_endpoint *ep, + unsigned int avail) { unsigned int phase; int ret; @@ -221,13 +221,14 @@ int snd_usb_endpoint_next_packet_size(struct snd_usb_endpoint *ep, packet = ctx->packet_size[idx]; if (packet) { + packet = min(packet, ep->maxframesize); if (avail && packet >= avail) return -EAGAIN; return packet; } if (ep->sync_source) - return slave_next_packet_size(ep, avail); + return synced_next_packet_size(ep, avail); else return next_packet_size(ep, avail); } @@ -1378,6 +1379,9 @@ int snd_usb_endpoint_set_params(struct snd_usb_audio *chip, return -EINVAL; } + ep->packsize[0] = min(ep->packsize[0], ep->maxframesize); + ep->packsize[1] = min(ep->packsize[1], ep->maxframesize); + /* calculate the frequency in 16.16 format */ ep->freqm = ep->freqn; ep->freqshift = INT_MIN; diff --git a/sound/usb/format.c b/sound/usb/format.c index 64cfe4a9d8cd..1207c507882a 100644 --- a/sound/usb/format.c +++ b/sound/usb/format.c @@ -305,17 +305,48 @@ static bool s1810c_valid_sample_rate(struct audioformat *fp, } /* - * Many Focusrite devices supports a limited set of sampling rates per - * altsetting. Maximum rate is exposed in the last 4 bytes of Format Type - * descriptor which has a non-standard bLength = 10. + * Focusrite devices use rate pairs: 44100/48000, 88200/96000, and + * 176400/192000. Return true if rate is in the pair for max_rate. + */ +static bool focusrite_rate_pair(unsigned int rate, + unsigned int max_rate) +{ + switch (max_rate) { + case 48000: return rate == 44100 || rate == 48000; + case 96000: return rate == 88200 || rate == 96000; + case 192000: return rate == 176400 || rate == 192000; + default: return true; + } +} + +/* + * Focusrite devices report all supported rates in a single clock + * source but only a subset is valid per altsetting. + * + * Detection uses two descriptor features: + * + * 1. Format Type descriptor bLength == 10: non-standard extension + * with max sample rate in bytes 6..9. + * + * 2. bmControls VAL_ALT_SETTINGS readable bit: when set, the device + * only supports the highest rate pair for that altsetting, and when + * clear, all rates up to max_rate are valid. + * + * For devices without the bLength == 10 extension but with + * VAL_ALT_SETTINGS readable and multiple altsettings (only seen in + * Scarlett 18i8 3rd Gen playback), fall back to the Focusrite + * convention: alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz. */ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip, struct audioformat *fp, unsigned int rate) { + struct usb_interface *iface; struct usb_host_interface *alts; + struct uac2_as_header_descriptor *as; unsigned char *fmt; unsigned int max_rate; + bool val_alt; alts = snd_usb_get_host_interface(chip, fp->iface, fp->altsetting); if (!alts) @@ -326,9 +357,21 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip, if (!fmt) return true; + as = snd_usb_find_csint_desc(alts->extra, alts->extralen, + NULL, UAC_AS_GENERAL); + if (!as) + return true; + + val_alt = uac_v2v3_control_is_readable(as->bmControls, + UAC2_AS_VAL_ALT_SETTINGS); + if (fmt[0] == 10) { /* bLength */ max_rate = combine_quad(&fmt[6]); + if (val_alt) + return focusrite_rate_pair(rate, max_rate); + + /* No val_alt: rates fall through from higher */ switch (max_rate) { case 192000: if (rate == 176400 || rate == 192000) @@ -344,12 +387,29 @@ static bool focusrite_valid_sample_rate(struct snd_usb_audio *chip, usb_audio_info(chip, "%u:%d : unexpected max rate: %u\n", fp->iface, fp->altsetting, max_rate); - return true; } } - return true; + if (!val_alt) + return true; + + /* Multi-altsetting device with val_alt but no max_rate + * in the format descriptor. Use Focusrite convention: + * alt 1 = 48kHz, alt 2 = 96kHz, alt 3 = 192kHz. + */ + iface = usb_ifnum_to_if(chip->dev, fp->iface); + if (!iface || iface->num_altsetting <= 2) + return true; + + switch (fp->altsetting) { + case 1: max_rate = 48000; break; + case 2: max_rate = 96000; break; + case 3: max_rate = 192000; break; + default: return true; + } + + return focusrite_rate_pair(rate, max_rate); } /* diff --git a/sound/usb/mixer_s1810c.c b/sound/usb/mixer_s1810c.c index 473cb29efa7f..7eac7d1bce64 100644 --- a/sound/usb/mixer_s1810c.c +++ b/sound/usb/mixer_s1810c.c @@ -71,7 +71,7 @@ * * e I guess the same as with mixer * */ -/** struct s1810c_ctl_packet - basic vendor request +/* struct s1810c_ctl_packet - basic vendor request * @selector: device/mixer/output * @b: request-dependant field b * @tag: fixed value identifying type of request @@ -94,14 +94,14 @@ struct s1810c_ctl_packet { __le32 e; }; -/** selectors for CMD request +/* selectors for CMD request */ #define SC1810C_SEL_DEVICE 0 #define SC1810C_SEL_MIXER 0x64 #define SC1810C_SEL_OUTPUT 0x65 -/** control ids */ +/* control ids */ #define SC1810C_CTL_LINE_SW 0 #define SC1810C_CTL_MUTE_SW 1 #define SC1824C_CTL_MONO_SW 2 @@ -127,7 +127,7 @@ struct s1810c_ctl_packet { #define SC1810C_GET_STATE_TAG SC1810C_SET_STATE_TAG #define SC1810C_GET_STATE_LEN SC1810C_SET_STATE_LEN -/** Mixer levels normally range from 0 (off) to 0x0100 0000 (0 dB). +/* Mixer levels normally range from 0 (off) to 0x0100 0000 (0 dB). * raw_level = 2^24 * 10^(db_level / 20), thus * -3dB = 0xb53bf0 (technically, half-power -3.01...dB would be 0xb504f3) * -96dB = 0x109 @@ -145,7 +145,7 @@ struct s1810c_ctl_packet { #define MIXER_LEVEL_N3DB 0xb53bf0 #define MIXER_LEVEL_0DB 0x1000000 -/** +/* * This packet includes mixer volumes and * various other fields, it's an extended * version of ctl_packet, with a and b @@ -155,7 +155,7 @@ struct s1810c_state_packet { __le32 fields[63]; }; -/** indices into s1810c_state_packet.fields[] +/* indices into s1810c_state_packet.fields[] */ #define SC1810C_STATE_TAG_IDX 2 #define SC1810C_STATE_LEN_IDX 3 diff --git a/sound/usb/mixer_scarlett2.c b/sound/usb/mixer_scarlett2.c index 85a0316889d4..ef3150581eab 100644 --- a/sound/usb/mixer_scarlett2.c +++ b/sound/usb/mixer_scarlett2.c @@ -1328,8 +1328,6 @@ struct scarlett2_data { struct snd_kcontrol *mux_ctls[SCARLETT2_MUX_MAX]; struct snd_kcontrol *mix_ctls[SCARLETT2_MIX_MAX]; struct snd_kcontrol *compressor_ctls[SCARLETT2_COMPRESSOR_CTLS_MAX]; - struct snd_kcontrol *precomp_flt_ctls[SCARLETT2_PRECOMP_FLT_CTLS_MAX]; - struct snd_kcontrol *peq_flt_ctls[SCARLETT2_PEQ_FLT_CTLS_MAX]; struct snd_kcontrol *precomp_flt_switch_ctls[SCARLETT2_DSP_SWITCH_MAX]; struct snd_kcontrol *peq_flt_switch_ctls[SCARLETT2_DSP_SWITCH_MAX]; struct snd_kcontrol *direct_monitor_ctl; @@ -3447,7 +3445,6 @@ static int scarlett2_update_autogain(struct usb_mixer_interface *mixer) private->autogain_status[i] = private->num_autogain_status_texts - 1; - for (i = 0; i < SCARLETT2_AG_TARGET_COUNT; i++) if (scarlett2_has_config_item(private, scarlett2_ag_target_configs[i])) { @@ -5372,8 +5369,7 @@ static int scarlett2_update_filter_values(struct usb_mixer_interface *mixer) err = scarlett2_usb_get_config( mixer, SCARLETT2_CONFIG_PEQ_FLT_SWITCH, - info->dsp_input_count * info->peq_flt_count, - private->peq_flt_switch); + info->dsp_input_count, private->peq_flt_switch); if (err < 0) return err; @@ -6546,7 +6542,7 @@ static int scarlett2_add_dsp_ctls(struct usb_mixer_interface *mixer, int i) err = scarlett2_add_new_ctl( mixer, &scarlett2_precomp_flt_ctl, i * info->precomp_flt_count + j, - 1, s, &private->precomp_flt_switch_ctls[j]); + 1, s, NULL); if (err < 0) return err; } @@ -6556,7 +6552,7 @@ static int scarlett2_add_dsp_ctls(struct usb_mixer_interface *mixer, int i) err = scarlett2_add_new_ctl( mixer, &scarlett2_peq_flt_ctl, i * info->peq_flt_count + j, - 1, s, &private->peq_flt_switch_ctls[j]); + 1, s, NULL); if (err < 0) return err; } diff --git a/sound/usb/qcom/qc_audio_offload.c b/sound/usb/qcom/qc_audio_offload.c index 01e6063c2207..510b68cced33 100644 --- a/sound/usb/qcom/qc_audio_offload.c +++ b/sound/usb/qcom/qc_audio_offload.c @@ -1007,7 +1007,7 @@ put_suspend: /** * uaudio_transfer_buffer_setup() - fetch and populate xfer buffer params * @subs: usb substream - * @xfer_buf: xfer buf to be allocated + * @xfer_buf_cpu: xfer buf to be allocated * @xfer_buf_len: size of allocation * @mem_info: QMI response info * diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 4cac0dfb0094..c6a78efbcaa3 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2365,6 +2365,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x2040, 0x7281, /* Hauppauge HVR-950Q-MXL */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), + DEVICE_FLG(0x20b1, 0x2009, /* XMOS Ltd DIYINHK USB Audio 2.0 */ + QUIRK_FLAG_SKIP_IMPLICIT_FB | QUIRK_FLAG_DSD_RAW), DEVICE_FLG(0x2040, 0x8200, /* Hauppauge Woodbury */ QUIRK_FLAG_SHARE_MEDIA_DEVICE | QUIRK_FLAG_ALIGN_TRANSFER), DEVICE_FLG(0x21b4, 0x0081, /* AudioQuest DragonFly */ @@ -2424,7 +2426,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { VENDOR_FLG(0x07fd, /* MOTU */ QUIRK_FLAG_VALIDATE_RATES), VENDOR_FLG(0x1235, /* Focusrite Novation */ - QUIRK_FLAG_VALIDATE_RATES), + QUIRK_FLAG_SKIP_CLOCK_SELECTOR | + QUIRK_FLAG_SKIP_IFACE_SETUP), VENDOR_FLG(0x1511, /* AURALiC */ QUIRK_FLAG_DSD_RAW), VENDOR_FLG(0x152a, /* Thesycon devices */ @@ -2506,6 +2509,7 @@ static const char *const snd_usb_audio_quirk_flag_names[] = { QUIRK_STRING_ENTRY(MIC_RES_384), QUIRK_STRING_ENTRY(MIXER_PLAYBACK_MIN_MUTE), QUIRK_STRING_ENTRY(MIXER_CAPTURE_MIN_MUTE), + QUIRK_STRING_ENTRY(SKIP_IFACE_SETUP), NULL }; diff --git a/sound/usb/stream.c b/sound/usb/stream.c index ac4d92065dd9..d38c39e28f38 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -1259,6 +1259,9 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, set_iface_first = true; /* try to set the interface... */ + if (chip->quirk_flags & QUIRK_FLAG_SKIP_IFACE_SETUP) + continue; + usb_set_interface(chip->dev, iface_no, 0); if (set_iface_first) usb_set_interface(chip->dev, iface_no, altno); diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h index 79978cae9799..085530cf62d9 100644 --- a/sound/usb/usbaudio.h +++ b/sound/usb/usbaudio.h @@ -224,6 +224,10 @@ extern bool snd_usb_skip_validation; * playback value represents muted state instead of minimum audible volume * QUIRK_FLAG_MIXER_CAPTURE_MIN_MUTE * Similar to QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE, but for capture streams + * QUIRK_FLAG_SKIP_IFACE_SETUP + * Skip the probe-time interface setup (usb_set_interface, + * init_pitch, init_sample_rate); redundant with + * snd_usb_endpoint_prepare() at stream-open time */ enum { @@ -253,6 +257,7 @@ enum { QUIRK_TYPE_MIC_RES_384 = 23, QUIRK_TYPE_MIXER_PLAYBACK_MIN_MUTE = 24, QUIRK_TYPE_MIXER_CAPTURE_MIN_MUTE = 25, + QUIRK_TYPE_SKIP_IFACE_SETUP = 26, /* Please also edit snd_usb_audio_quirk_flag_names */ }; @@ -284,5 +289,6 @@ enum { #define QUIRK_FLAG_MIC_RES_384 QUIRK_FLAG(MIC_RES_384) #define QUIRK_FLAG_MIXER_PLAYBACK_MIN_MUTE QUIRK_FLAG(MIXER_PLAYBACK_MIN_MUTE) #define QUIRK_FLAG_MIXER_CAPTURE_MIN_MUTE QUIRK_FLAG(MIXER_CAPTURE_MIN_MUTE) +#define QUIRK_FLAG_SKIP_IFACE_SETUP QUIRK_FLAG(SKIP_IFACE_SETUP) #endif /* __USBAUDIO_H */ diff --git a/sound/usb/usx2y/us144mkii.c b/sound/usb/usx2y/us144mkii.c index bc71968df8e2..0cf4fa74e210 100644 --- a/sound/usb/usx2y/us144mkii.c +++ b/sound/usb/usx2y/us144mkii.c @@ -10,8 +10,8 @@ MODULE_AUTHOR("Šerif Rami <ramiserifpersia@gmail.com>"); MODULE_DESCRIPTION("ALSA Driver for TASCAM US-144MKII"); MODULE_LICENSE("GPL"); -/** - * @brief Module parameters for ALSA card instantiation. +/* + * Module parameters for ALSA card instantiation. * * These parameters allow users to configure how the ALSA sound card * for the TASCAM US-144MKII is instantiated. @@ -269,7 +269,7 @@ void tascam_stop_work_handler(struct work_struct *work) atomic_set(&tascam->active_urbs, 0); } -/** +/* * tascam_card_private_free() - Frees private data associated with the sound * card. * @card: Pointer to the ALSA sound card instance. @@ -291,7 +291,7 @@ static void tascam_card_private_free(struct snd_card *card) } } -/** +/* * tascam_suspend() - Handles device suspension. * @intf: The USB interface being suspended. * @message: Power management message. @@ -332,7 +332,7 @@ static int tascam_suspend(struct usb_interface *intf, pm_message_t message) return 0; } -/** +/* * tascam_resume() - Handles device resumption from suspend. * @intf: The USB interface being resumed. * @@ -390,7 +390,7 @@ static void tascam_error_timer(struct timer_list *t) schedule_work(&tascam->midi_out_work); } -/** +/* * tascam_probe() - Probes for the TASCAM US-144MKII device. * @intf: The USB interface being probed. * @usb_id: The USB device ID. @@ -565,7 +565,7 @@ free_card: return err; } -/** +/* * tascam_disconnect() - Disconnects the TASCAM US-144MKII device. * @intf: The USB interface being disconnected. * diff --git a/sound/usb/usx2y/us144mkii_capture.c b/sound/usb/usx2y/us144mkii_capture.c index 00188ff6cd51..af120bf62173 100644 --- a/sound/usb/usx2y/us144mkii_capture.c +++ b/sound/usb/usx2y/us144mkii_capture.c @@ -3,7 +3,7 @@ #include "us144mkii.h" -/** +/* * tascam_capture_open() - Opens the PCM capture substream. * @substream: The ALSA PCM substream to open. * @@ -23,7 +23,7 @@ static int tascam_capture_open(struct snd_pcm_substream *substream) return 0; } -/** +/* * tascam_capture_close() - Closes the PCM capture substream. * @substream: The ALSA PCM substream to close. * @@ -41,7 +41,7 @@ static int tascam_capture_close(struct snd_pcm_substream *substream) return 0; } -/** +/* * tascam_capture_prepare() - Prepares the PCM capture substream for use. * @substream: The ALSA PCM substream to prepare. * @@ -62,7 +62,7 @@ static int tascam_capture_prepare(struct snd_pcm_substream *substream) return 0; } -/** +/* * tascam_capture_pointer() - Returns the current capture pointer position. * @substream: The ALSA PCM substream. * @@ -91,7 +91,7 @@ tascam_capture_pointer(struct snd_pcm_substream *substream) return do_div(pos, runtime->buffer_size); } -/** +/* * tascam_capture_ops - ALSA PCM operations for capture. * * This structure defines the callback functions for capture stream operations, @@ -109,7 +109,7 @@ const struct snd_pcm_ops tascam_capture_ops = { .pointer = tascam_capture_pointer, }; -/** +/* * decode_tascam_capture_block() - Decodes a raw 512-byte block from the device. * @src_block: Pointer to the 512-byte raw source block. * @dst_block: Pointer to the destination buffer for decoded audio frames. diff --git a/sound/usb/usx2y/us144mkii_controls.c b/sound/usb/usx2y/us144mkii_controls.c index 62055fb8e7ba..81ded11e3709 100644 --- a/sound/usb/usx2y/us144mkii_controls.c +++ b/sound/usb/usx2y/us144mkii_controls.c @@ -3,8 +3,8 @@ #include "us144mkii.h" -/** - * @brief Text descriptions for playback output source options. +/* + * Text descriptions for playback output source options. * * Used by ALSA kcontrol elements to provide user-friendly names for * the playback routing options (e.g., "Playback 1-2", "Playback 3-4"). @@ -12,15 +12,15 @@ static const char *const playback_source_texts[] = { "Playback 1-2", "Playback 3-4" }; -/** - * @brief Text descriptions for capture input source options. +/* + * Text descriptions for capture input source options. * * Used by ALSA kcontrol elements to provide user-friendly names for * the capture routing options (e.g., "Analog In", "Digital In"). */ static const char *const capture_source_texts[] = { "Analog In", "Digital In" }; -/** +/* * tascam_playback_source_info() - ALSA control info callback for playback * source. * @kcontrol: The ALSA kcontrol instance. @@ -38,7 +38,7 @@ static int tascam_playback_source_info(struct snd_kcontrol *kcontrol, return snd_ctl_enum_info(uinfo, 1, 2, playback_source_texts); } -/** +/* * tascam_line_out_get() - ALSA control get callback for Line Outputs Source. * @kcontrol: The ALSA kcontrol instance. * @ucontrol: The ALSA control element value structure to fill. @@ -60,7 +60,7 @@ static int tascam_line_out_get(struct snd_kcontrol *kcontrol, return 0; } -/** +/* * tascam_line_out_put() - ALSA control put callback for Line Outputs Source. * @kcontrol: The ALSA kcontrol instance. * @ucontrol: The ALSA control element value structure containing the new value. @@ -89,7 +89,7 @@ static int tascam_line_out_put(struct snd_kcontrol *kcontrol, return changed; } -/** +/* * tascam_line_out_control - ALSA kcontrol definition for Line Outputs Source. * * This defines a new ALSA mixer control named "Line OUTPUTS Source" that allows @@ -106,7 +106,7 @@ static const struct snd_kcontrol_new tascam_line_out_control = { .put = tascam_line_out_put, }; -/** +/* * tascam_digital_out_get() - ALSA control get callback for Digital Outputs * Source. * @kcontrol: The ALSA kcontrol instance. @@ -129,7 +129,7 @@ static int tascam_digital_out_get(struct snd_kcontrol *kcontrol, return 0; } -/** +/* * tascam_digital_out_put() - ALSA control put callback for Digital Outputs * Source. * @kcontrol: The ALSA kcontrol instance. @@ -159,7 +159,7 @@ static int tascam_digital_out_put(struct snd_kcontrol *kcontrol, return changed; } -/** +/* * tascam_digital_out_control - ALSA kcontrol definition for Digital Outputs * Source. * @@ -177,7 +177,7 @@ static const struct snd_kcontrol_new tascam_digital_out_control = { .put = tascam_digital_out_put, }; -/** +/* * tascam_capture_source_info() - ALSA control info callback for capture source. * @kcontrol: The ALSA kcontrol instance. * @uinfo: The ALSA control element info structure to fill. @@ -194,7 +194,7 @@ static int tascam_capture_source_info(struct snd_kcontrol *kcontrol, return snd_ctl_enum_info(uinfo, 1, 2, capture_source_texts); } -/** +/* * tascam_capture_12_get() - ALSA control get callback for Capture channels 1 * and 2 Source. * @kcontrol: The ALSA kcontrol instance. @@ -217,7 +217,7 @@ static int tascam_capture_12_get(struct snd_kcontrol *kcontrol, return 0; } -/** +/* * tascam_capture_12_put() - ALSA control put callback for Capture channels 1 * and 2 Source. * @kcontrol: The ALSA kcontrol instance. @@ -247,7 +247,7 @@ static int tascam_capture_12_put(struct snd_kcontrol *kcontrol, return changed; } -/** +/* * tascam_capture_12_control - ALSA kcontrol definition for Capture channels 1 * and 2 Source. * @@ -265,7 +265,7 @@ static const struct snd_kcontrol_new tascam_capture_12_control = { .put = tascam_capture_12_put, }; -/** +/* * tascam_capture_34_get() - ALSA control get callback for Capture channels 3 * and 4 Source. * @kcontrol: The ALSA kcontrol instance. @@ -288,7 +288,7 @@ static int tascam_capture_34_get(struct snd_kcontrol *kcontrol, return 0; } -/** +/* * tascam_capture_34_put() - ALSA control put callback for Capture channels 3 * and 4 Source. * @kcontrol: The ALSA kcontrol instance. @@ -318,7 +318,7 @@ static int tascam_capture_34_put(struct snd_kcontrol *kcontrol, return changed; } -/** +/* * tascam_capture_34_control - ALSA kcontrol definition for Capture channels 3 * and 4 Source. * @@ -336,7 +336,7 @@ static const struct snd_kcontrol_new tascam_capture_34_control = { .put = tascam_capture_34_put, }; -/** +/* * tascam_samplerate_info() - ALSA control info callback for Sample Rate. * @kcontrol: The ALSA kcontrol instance. * @uinfo: The ALSA control element info structure to fill. @@ -356,7 +356,7 @@ static int tascam_samplerate_info(struct snd_kcontrol *kcontrol, return 0; } -/** +/* * tascam_samplerate_get() - ALSA control get callback for Sample Rate. * @kcontrol: The ALSA kcontrol instance. * @ucontrol: The ALSA control element value structure to fill. @@ -400,7 +400,7 @@ static int tascam_samplerate_get(struct snd_kcontrol *kcontrol, return 0; } -/** +/* * tascam_samplerate_control - ALSA kcontrol definition for Sample Rate. * * This defines a new ALSA mixer control named "Sample Rate" that displays diff --git a/sound/usb/usx2y/us144mkii_midi.c b/sound/usb/usx2y/us144mkii_midi.c index ed2afec2a89a..4871797b1670 100644 --- a/sound/usb/usx2y/us144mkii_midi.c +++ b/sound/usb/usx2y/us144mkii_midi.c @@ -3,7 +3,7 @@ #include "us144mkii.h" -/** +/* * tascam_midi_in_work_handler() - Deferred work for processing MIDI input. * @work: The work_struct instance. * @@ -75,7 +75,7 @@ out: usb_put_urb(urb); } -/** +/* * tascam_midi_in_open() - Opens the MIDI input substream. * @substream: The ALSA rawmidi substream to open. * @@ -92,7 +92,7 @@ static int tascam_midi_in_open(struct snd_rawmidi_substream *substream) return 0; } -/** +/* * tascam_midi_in_close() - Closes the MIDI input substream. * @substream: The ALSA rawmidi substream to close. * @@ -103,7 +103,7 @@ static int tascam_midi_in_close(struct snd_rawmidi_substream *substream) return 0; } -/** +/* * tascam_midi_in_trigger() - Triggers MIDI input stream activity. * @substream: The ALSA rawmidi substream. * @up: Boolean indicating whether to start (1) or stop (0) the stream. @@ -150,7 +150,7 @@ static void tascam_midi_in_trigger(struct snd_rawmidi_substream *substream, } } -/** +/* * tascam_midi_in_ops - ALSA rawmidi operations for MIDI input. * * This structure defines the callback functions for MIDI input stream @@ -205,7 +205,7 @@ out: usb_put_urb(urb); } -/** +/* * tascam_midi_out_work_handler() - Deferred work for sending MIDI data * @work: The work_struct instance. * @@ -282,7 +282,7 @@ static void tascam_midi_out_work_handler(struct work_struct *work) } } -/** +/* * tascam_midi_out_open() - Opens the MIDI output substream. * @substream: The ALSA rawmidi substream to open. * @@ -301,7 +301,7 @@ static int tascam_midi_out_open(struct snd_rawmidi_substream *substream) return 0; } -/** +/* * tascam_midi_out_close() - Closes the MIDI output substream. * @substream: The ALSA rawmidi substream to close. * @@ -312,7 +312,7 @@ static int tascam_midi_out_close(struct snd_rawmidi_substream *substream) return 0; } -/** +/* * tascam_midi_out_drain() - Drains the MIDI output stream. * @substream: The ALSA rawmidi substream. * @@ -340,7 +340,7 @@ static void tascam_midi_out_drain(struct snd_rawmidi_substream *substream) usb_kill_anchored_urbs(&tascam->midi_out_anchor); } -/** +/* * tascam_midi_out_trigger() - Triggers MIDI output stream activity. * @substream: The ALSA rawmidi substream. * @up: Boolean indicating whether to start (1) or stop (0) the stream. @@ -361,7 +361,7 @@ static void tascam_midi_out_trigger(struct snd_rawmidi_substream *substream, } } -/** +/* * tascam_midi_out_ops - ALSA rawmidi operations for MIDI output. * * This structure defines the callback functions for MIDI output stream diff --git a/sound/usb/usx2y/us144mkii_playback.c b/sound/usb/usx2y/us144mkii_playback.c index 0cb9699ec211..7efaca0a6489 100644 --- a/sound/usb/usx2y/us144mkii_playback.c +++ b/sound/usb/usx2y/us144mkii_playback.c @@ -3,7 +3,7 @@ #include "us144mkii.h" -/** +/* * tascam_playback_open() - Opens the PCM playback substream. * @substream: The ALSA PCM substream to open. * @@ -23,7 +23,7 @@ static int tascam_playback_open(struct snd_pcm_substream *substream) return 0; } -/** +/* * tascam_playback_close() - Closes the PCM playback substream. * @substream: The ALSA PCM substream to close. * @@ -41,7 +41,7 @@ static int tascam_playback_close(struct snd_pcm_substream *substream) return 0; } -/** +/* * tascam_playback_prepare() - Prepares the PCM playback substream for use. * @substream: The ALSA PCM substream to prepare. * @@ -108,7 +108,7 @@ static int tascam_playback_prepare(struct snd_pcm_substream *substream) return 0; } -/** +/* * tascam_playback_pointer() - Returns the current playback pointer position. * @substream: The ALSA PCM substream. * @@ -137,7 +137,7 @@ tascam_playback_pointer(struct snd_pcm_substream *substream) return do_div(pos, runtime->buffer_size); } -/** +/* * tascam_playback_ops - ALSA PCM operations for playback. * * This structure defines the callback functions for playback stream operations, diff --git a/sound/usb/validate.c b/sound/usb/validate.c index 4bb4893f6e74..f62b7cc041dc 100644 --- a/sound/usb/validate.c +++ b/sound/usb/validate.c @@ -281,7 +281,7 @@ static const struct usb_desc_validator audio_validators[] = { /* UAC_VERSION_2, UAC2_SAMPLE_RATE_CONVERTER: not implemented yet */ /* UAC3 */ - FIXED(UAC_VERSION_2, UAC_HEADER, struct uac3_ac_header_descriptor), + FIXED(UAC_VERSION_3, UAC_HEADER, struct uac3_ac_header_descriptor), FIXED(UAC_VERSION_3, UAC_INPUT_TERMINAL, struct uac3_input_terminal_descriptor), FIXED(UAC_VERSION_3, UAC_OUTPUT_TERMINAL, diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index 1733a6e93a07..ef083602b73a 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -65,6 +65,9 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OU LIBELF_FLAGS := $(shell $(HOSTPKG_CONFIG) libelf --cflags 2>/dev/null) LIBELF_LIBS := $(shell $(HOSTPKG_CONFIG) libelf --libs 2>/dev/null || echo -lelf) +ZLIB_LIBS := $(shell $(HOSTPKG_CONFIG) zlib --libs 2>/dev/null || echo -lz) +ZSTD_LIBS := $(shell $(HOSTPKG_CONFIG) libzstd --libs 2>/dev/null || echo -lzstd) + HOSTCFLAGS_resolve_btfids += -g \ -I$(srctree)/tools/include \ -I$(srctree)/tools/include/uapi \ @@ -73,7 +76,7 @@ HOSTCFLAGS_resolve_btfids += -g \ $(LIBELF_FLAGS) \ -Wall -Werror -LIBS = $(LIBELF_LIBS) -lz +LIBS = $(LIBELF_LIBS) $(ZLIB_LIBS) $(ZSTD_LIBS) export srctree OUTPUT HOSTCFLAGS_resolve_btfids Q HOSTCC HOSTLD HOSTAR include $(srctree)/tools/build/Makefile.include @@ -83,7 +86,7 @@ $(BINARY_IN): fixdep FORCE prepare | $(OUTPUT) $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN) $(call msg,LINK,$@) - $(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) + $(Q)$(HOSTCC) $(BINARY_IN) $(KBUILD_HOSTLDFLAGS) $(EXTRA_LDFLAGS) -o $@ $(BPFOBJ) $(SUBCMDOBJ) $(LIBS) clean_objects := $(wildcard $(OUTPUT)/*.o \ $(OUTPUT)/.*.o.cmd \ diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index ca7fcd03efb6..5208f650080f 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -226,7 +226,7 @@ static struct btf_id *btf_id__find(struct rb_root *root, const char *name) } static struct btf_id *__btf_id__add(struct rb_root *root, - char *name, + const char *name, enum btf_id_kind kind, bool unique) { @@ -250,7 +250,11 @@ static struct btf_id *__btf_id__add(struct rb_root *root, id = zalloc(sizeof(*id)); if (id) { pr_debug("adding symbol %s\n", name); - id->name = name; + id->name = strdup(name); + if (!id->name) { + free(id); + return NULL; + } id->kind = kind; rb_link_node(&id->rb_node, parent, p); rb_insert_color(&id->rb_node, root); @@ -258,17 +262,21 @@ static struct btf_id *__btf_id__add(struct rb_root *root, return id; } -static inline struct btf_id *btf_id__add(struct rb_root *root, char *name, enum btf_id_kind kind) +static inline struct btf_id *btf_id__add(struct rb_root *root, + const char *name, + enum btf_id_kind kind) { return __btf_id__add(root, name, kind, false); } -static inline struct btf_id *btf_id__add_unique(struct rb_root *root, char *name, enum btf_id_kind kind) +static inline struct btf_id *btf_id__add_unique(struct rb_root *root, + const char *name, + enum btf_id_kind kind) { return __btf_id__add(root, name, kind, true); } -static char *get_id(const char *prefix_end) +static int get_id(const char *prefix_end, char *buf, size_t buf_sz) { /* * __BTF_ID__func__vfs_truncate__0 @@ -277,28 +285,28 @@ static char *get_id(const char *prefix_end) */ int len = strlen(prefix_end); int pos = sizeof("__") - 1; - char *p, *id; + char *p; if (pos >= len) - return NULL; + return -1; - id = strdup(prefix_end + pos); - if (id) { - /* - * __BTF_ID__func__vfs_truncate__0 - * id = ^ - * - * cut the unique id part - */ - p = strrchr(id, '_'); - p--; - if (*p != '_') { - free(id); - return NULL; - } - *p = '\0'; - } - return id; + if (len - pos >= buf_sz) + return -1; + + strcpy(buf, prefix_end + pos); + /* + * __BTF_ID__func__vfs_truncate__0 + * buf = ^ + * + * cut the unique id part + */ + p = strrchr(buf, '_'); + p--; + if (*p != '_') + return -1; + *p = '\0'; + + return 0; } static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind kind) @@ -335,10 +343,9 @@ static struct btf_id *add_set(struct object *obj, char *name, enum btf_id_kind k static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) { - char *id; + char id[KSYM_NAME_LEN]; - id = get_id(name + size); - if (!id) { + if (get_id(name + size, id, sizeof(id))) { pr_err("FAILED to parse symbol name: %s\n", name); return NULL; } @@ -346,6 +353,21 @@ static struct btf_id *add_symbol(struct rb_root *root, char *name, size_t size) return btf_id__add(root, id, BTF_ID_KIND_SYM); } +static void btf_id__free_all(struct rb_root *root) +{ + struct rb_node *next; + struct btf_id *id; + + next = rb_first(root); + while (next) { + id = rb_entry(next, struct btf_id, rb_node); + next = rb_next(&id->rb_node); + rb_erase(&id->rb_node, root); + free(id->name); + free(id); + } +} + static void bswap_32_data(void *data, u32 nr_bytes) { u32 cnt, i; @@ -1547,6 +1569,11 @@ dump_btf: out: btf__free(obj.base_btf); btf__free(obj.btf); + btf_id__free_all(&obj.structs); + btf_id__free_all(&obj.unions); + btf_id__free_all(&obj.typedefs); + btf_id__free_all(&obj.funcs); + btf_id__free_all(&obj.sets); if (obj.efile.elf) { elf_end(obj.efile.elf); close(obj.efile.fd); diff --git a/tools/include/linux/args.h b/tools/include/linux/args.h index 2e8e65d975c7..14b268f2389a 100644 --- a/tools/include/linux/args.h +++ b/tools/include/linux/args.h @@ -22,7 +22,11 @@ #define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0) /* Concatenate two parameters, but allow them to be expanded beforehand. */ +#ifndef __CONCAT #define __CONCAT(a, b) a ## b +#endif +#ifndef CONCATENATE #define CONCATENATE(a, b) __CONCAT(a, b) +#endif #endif /* _LINUX_ARGS_H */ diff --git a/tools/sched_ext/Kconfig b/tools/sched_ext/Kconfig new file mode 100644 index 000000000000..275bd97ae62b --- /dev/null +++ b/tools/sched_ext/Kconfig @@ -0,0 +1,61 @@ +# sched-ext mandatory options +# +CONFIG_BPF=y +CONFIG_BPF_SYSCALL=y +CONFIG_BPF_JIT=y +CONFIG_DEBUG_INFO_BTF=y +CONFIG_BPF_JIT_ALWAYS_ON=y +CONFIG_BPF_JIT_DEFAULT_ON=y +CONFIG_SCHED_CLASS_EXT=y + +# Required by some rust schedulers (e.g. scx_p2dq) +# +CONFIG_KALLSYMS_ALL=y + +# Required on arm64 +# +# CONFIG_DEBUG_INFO_REDUCED is not set + +# LAVD tracks futex to give an additional time slice for futex holder +# (i.e., avoiding lock holder preemption) for better system-wide progress. +# LAVD first tries to use ftrace to trace futex function calls. +# If that is not available, it tries to use a tracepoint. +CONFIG_FUNCTION_TRACER=y + +# Enable scheduling debugging +# +CONFIG_SCHED_DEBUG=y + +# Enable extra scheduling features (for a better code coverage while testing +# the schedulers) +# +CONFIG_SCHED_AUTOGROUP=y +CONFIG_SCHED_CORE=y +CONFIG_SCHED_MC=y + +# Enable fully preemptible kernel for a better test coverage of the schedulers +# +# CONFIG_PREEMPT_NONE is not set +# CONFIG_PREEMPT_VOLUNTARY is not set +CONFIG_PREEMPT=y +CONFIG_PREEMPT_DYNAMIC=y + +# Additional debugging information (useful to catch potential locking issues) +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_PROVE_LOCKING=y + +# Bpftrace headers (for additional debug info) +CONFIG_BPF_EVENTS=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_DYNAMIC_FTRACE=y +CONFIG_KPROBES=y +CONFIG_KPROBE_EVENTS=y +CONFIG_UPROBES=y +CONFIG_UPROBE_EVENTS=y +CONFIG_DEBUG_FS=y + +# Enable access to kernel configuration and headers at runtime +CONFIG_IKHEADERS=y +CONFIG_IKCONFIG_PROC=y +CONFIG_IKCONFIG=y diff --git a/tools/sched_ext/Makefile b/tools/sched_ext/Makefile index 47ad7444677e..21554f089692 100644 --- a/tools/sched_ext/Makefile +++ b/tools/sched_ext/Makefile @@ -122,6 +122,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ -I../../include \ $(call get_sys_includes,$(CLANG)) \ -Wall -Wno-compare-distinct-pointer-types \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ -O2 -mcpu=v3 # sort removes libbpf duplicates when not cross-building diff --git a/tools/sched_ext/README.md b/tools/sched_ext/README.md index 56a9d1557ac4..6e282bce453c 100644 --- a/tools/sched_ext/README.md +++ b/tools/sched_ext/README.md @@ -58,14 +58,8 @@ CONFIG_SCHED_CLASS_EXT=y CONFIG_BPF_SYSCALL=y CONFIG_BPF_JIT=y CONFIG_DEBUG_INFO_BTF=y -``` - -It's also recommended that you also include the following Kconfig options: - -``` CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT_DEFAULT_ON=y -CONFIG_PAHOLE_HAS_BTF_TAG=y ``` There is a `Kconfig` file in this directory whose contents you can append to diff --git a/tools/sched_ext/include/scx/compat.h b/tools/sched_ext/include/scx/compat.h index 8b4897fc8b99..edccc99c7294 100644 --- a/tools/sched_ext/include/scx/compat.h +++ b/tools/sched_ext/include/scx/compat.h @@ -125,6 +125,7 @@ static inline long scx_hotplug_seq(void) { int fd; char buf[32]; + char *endptr; ssize_t len; long val; @@ -137,8 +138,10 @@ static inline long scx_hotplug_seq(void) buf[len] = 0; close(fd); - val = strtoul(buf, NULL, 10); - SCX_BUG_ON(val < 0, "invalid num hotplug events: %lu", val); + errno = 0; + val = strtoul(buf, &endptr, 10); + SCX_BUG_ON(errno == ERANGE || endptr == buf || + (*endptr != '\n' && *endptr != '\0'), "invalid num hotplug events: %ld", val); return val; } diff --git a/tools/sched_ext/scx_central.c b/tools/sched_ext/scx_central.c index 2a805f1d6c8f..710fa03376e2 100644 --- a/tools/sched_ext/scx_central.c +++ b/tools/sched_ext/scx_central.c @@ -66,7 +66,7 @@ restart: assert(skel->rodata->nr_cpu_ids > 0); assert(skel->rodata->nr_cpu_ids <= INT32_MAX); - while ((opt = getopt(argc, argv, "s:c:pvh")) != -1) { + while ((opt = getopt(argc, argv, "s:c:vh")) != -1) { switch (opt) { case 's': skel->rodata->slice_ns = strtoull(optarg, NULL, 0) * 1000; diff --git a/tools/sched_ext/scx_sdt.c b/tools/sched_ext/scx_sdt.c index d8ca9aa316a5..a36405d8df30 100644 --- a/tools/sched_ext/scx_sdt.c +++ b/tools/sched_ext/scx_sdt.c @@ -54,7 +54,7 @@ restart: optind = 1; skel = SCX_OPS_OPEN(sdt_ops, scx_sdt); - while ((opt = getopt(argc, argv, "fvh")) != -1) { + while ((opt = getopt(argc, argv, "vh")) != -1) { switch (opt) { case 'v': verbose = true; diff --git a/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c new file mode 100644 index 000000000000..2259f454a202 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/gcs_prot_none_fault.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2026 ARM Limited + */ + +#include <errno.h> +#include <signal.h> +#include <unistd.h> + +#include <sys/mman.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +static uint64_t *gcs_page; +static bool post_mprotect; + +#ifndef __NR_map_shadow_stack +#define __NR_map_shadow_stack 453 +#endif + +static bool alloc_gcs(struct tdescr *td) +{ + long page_size = sysconf(_SC_PAGE_SIZE); + + gcs_page = (void *)syscall(__NR_map_shadow_stack, 0, + page_size, 0); + if (gcs_page == MAP_FAILED) { + fprintf(stderr, "Failed to map %ld byte GCS: %d\n", + page_size, errno); + return false; + } + + return true; +} + +static int gcs_prot_none_fault_trigger(struct tdescr *td) +{ + /* Verify that the page is readable (ie, not completely unmapped) */ + fprintf(stderr, "Read value 0x%lx\n", gcs_page[0]); + + if (mprotect(gcs_page, sysconf(_SC_PAGE_SIZE), PROT_NONE) != 0) { + fprintf(stderr, "mprotect(PROT_NONE) failed: %d\n", errno); + return 0; + } + post_mprotect = true; + + /* This should trigger a fault if PROT_NONE is honoured for the GCS page */ + fprintf(stderr, "Read value after mprotect(PROT_NONE) 0x%lx\n", gcs_page[0]); + return 0; +} + +static int gcs_prot_none_fault_signal(struct tdescr *td, siginfo_t *si, + ucontext_t *uc) +{ + ASSERT_GOOD_CONTEXT(uc); + + /* A fault before mprotect(PROT_NONE) is unexpected. */ + if (!post_mprotect) + return 0; + + return 1; +} + +struct tdescr tde = { + .name = "GCS PROT_NONE fault", + .descr = "Read from GCS after mprotect(PROT_NONE) segfaults", + .feats_required = FEAT_GCS, + .timeout = 3, + .sig_ok = SIGSEGV, + .sanity_disabled = true, + .init = alloc_gcs, + .trigger = gcs_prot_none_fault_trigger, + .run = gcs_prot_none_fault_signal, +}; diff --git a/tools/testing/selftests/bpf/DENYLIST.asan b/tools/testing/selftests/bpf/DENYLIST.asan new file mode 100644 index 000000000000..d7fe372a2293 --- /dev/null +++ b/tools/testing/selftests/bpf/DENYLIST.asan @@ -0,0 +1,3 @@ +*arena* +task_local_data +uprobe_multi_test diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 6776158f1f3e..72a9ba41f95e 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -27,7 +27,11 @@ ifneq ($(wildcard $(GENHDR)),) endif BPF_GCC ?= $(shell command -v bpf-gcc;) +ifdef ASAN +SAN_CFLAGS ?= -fsanitize=address -fno-omit-frame-pointer +else SAN_CFLAGS ?= +endif SAN_LDFLAGS ?= $(SAN_CFLAGS) RELEASE ?= OPT_FLAGS ?= $(if $(RELEASE),-O2,-O0) @@ -326,8 +330,8 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ ARCH= CROSS_COMPILE= CC="$(HOSTCC)" LD="$(HOSTLD)" \ - EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)' \ - EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)' \ + EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \ OUTPUT=$(HOST_BUILD_DIR)/bpftool/ \ LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/ \ LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/ \ @@ -338,8 +342,8 @@ $(CROSS_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) \ $(BPFOBJ) | $(BUILD_DIR)/bpftool $(Q)$(MAKE) $(submake_extras) -C $(BPFTOOLDIR) \ ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) \ - EXTRA_CFLAGS='-g $(OPT_FLAGS) $(EXTRA_CFLAGS)' \ - EXTRA_LDFLAGS='$(EXTRA_LDFLAGS)' \ + EXTRA_CFLAGS='-g $(OPT_FLAGS) $(SAN_CFLAGS) $(EXTRA_CFLAGS)' \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \ OUTPUT=$(BUILD_DIR)/bpftool/ \ LIBBPF_OUTPUT=$(BUILD_DIR)/libbpf/ \ LIBBPF_DESTDIR=$(SCRATCH_DIR)/ \ @@ -404,6 +408,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids \ $(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids \ CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)" \ LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \ + EXTRA_LDFLAGS='$(SAN_LDFLAGS) $(EXTRA_LDFLAGS)' \ OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ) # Get Clang's default includes on this system, as opposed to those seen by diff --git a/tools/testing/selftests/bpf/benchs/bench_trigger.c b/tools/testing/selftests/bpf/benchs/bench_trigger.c index aeec9edd3851..f74b313d6ae4 100644 --- a/tools/testing/selftests/bpf/benchs/bench_trigger.c +++ b/tools/testing/selftests/bpf/benchs/bench_trigger.c @@ -230,8 +230,8 @@ static void trigger_fentry_setup(void) static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); - char **syms = NULL; - size_t cnt = 0; + struct bpf_link *link = NULL; + struct ksyms *ksyms = NULL; /* Some recursive functions will be skipped in * bpf_get_ksyms -> skip_entry, as they can introduce sufficient @@ -241,16 +241,18 @@ static void attach_ksyms_all(struct bpf_program *empty, bool kretprobe) * So, don't run the kprobe-multi-all and kretprobe-multi-all on * a debug kernel. */ - if (bpf_get_ksyms(&syms, &cnt, true)) { + if (bpf_get_ksyms(&ksyms, true)) { fprintf(stderr, "failed to get ksyms\n"); exit(1); } - opts.syms = (const char **) syms; - opts.cnt = cnt; + opts.syms = (const char **)ksyms->filtered_syms; + opts.cnt = ksyms->filtered_cnt; opts.retprobe = kretprobe; /* attach empty to all the kernel functions except bpf_get_numa_node_id. */ - if (!bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts)) { + link = bpf_program__attach_kprobe_multi_opts(empty, NULL, &opts); + free_kallsyms_local(ksyms); + if (!link) { fprintf(stderr, "failed to attach bpf_program__attach_kprobe_multi_opts to all\n"); exit(1); } diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 4bc2d25f33e1..6cb56501a505 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -8,6 +8,7 @@ #include <errno.h> #include <syscall.h> #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */ +#include <linux/args.h> static inline unsigned int bpf_num_possible_cpus(void) { @@ -21,25 +22,43 @@ static inline unsigned int bpf_num_possible_cpus(void) return possible_cpus; } -/* Copy up to sz - 1 bytes from zero-terminated src string and ensure that dst - * is zero-terminated string no matter what (unless sz == 0, in which case - * it's a no-op). It's conceptually close to FreeBSD's strlcpy(), but differs - * in what is returned. Given this is internal helper, it's trivial to extend - * this, when necessary. Use this instead of strncpy inside libbpf source code. +/* + * Simplified strscpy() implementation. The kernel one is in lib/string.c */ -static inline void bpf_strlcpy(char *dst, const char *src, size_t sz) +static inline ssize_t sized_strscpy(char *dest, const char *src, size_t count) { - size_t i; + long res = 0; - if (sz == 0) - return; + if (count == 0) + return -E2BIG; - sz--; - for (i = 0; i < sz && src[i]; i++) - dst[i] = src[i]; - dst[i] = '\0'; + while (count > 1) { + char c; + + c = src[res]; + dest[res] = c; + if (!c) + return res; + res++; + count--; + } + + /* Force NUL-termination. */ + dest[res] = '\0'; + + /* Return E2BIG if the source didn't stop */ + return src[res] ? -E2BIG : res; } +#define __strscpy0(dst, src, ...) \ + sized_strscpy(dst, src, sizeof(dst)) +#define __strscpy1(dst, src, size) \ + sized_strscpy(dst, src, size) + +#undef strscpy /* Redefine the placeholder from tools/include/linux/string.h */ +#define strscpy(dst, src, ...) \ + CONCATENATE(__strscpy, COUNT_ARGS(__VA_ARGS__))(dst, src, __VA_ARGS__) + #define __bpf_percpu_val_align __attribute__((__aligned__(8))) #define BPF_DECLARE_PERCPU(type, name) \ diff --git a/tools/testing/selftests/bpf/bpftool_helpers.c b/tools/testing/selftests/bpf/bpftool_helpers.c index a5824945a4a5..929fc257f431 100644 --- a/tools/testing/selftests/bpf/bpftool_helpers.c +++ b/tools/testing/selftests/bpf/bpftool_helpers.c @@ -1,24 +1,37 @@ // SPDX-License-Identifier: GPL-2.0-only -#include "bpftool_helpers.h" #include <unistd.h> #include <string.h> #include <stdbool.h> +#include "bpf_util.h" +#include "bpftool_helpers.h" + #define BPFTOOL_PATH_MAX_LEN 64 #define BPFTOOL_FULL_CMD_MAX_LEN 512 #define BPFTOOL_DEFAULT_PATH "tools/sbin/bpftool" -static int detect_bpftool_path(char *buffer) +static int detect_bpftool_path(char *buffer, size_t size) { char tmp[BPFTOOL_PATH_MAX_LEN]; + const char *env_path; + + /* First, check if BPFTOOL environment variable is set */ + env_path = getenv("BPFTOOL"); + if (env_path && access(env_path, X_OK) == 0) { + strscpy(buffer, env_path, size); + return 0; + } else if (env_path) { + fprintf(stderr, "bpftool '%s' doesn't exist or is not executable\n", env_path); + return 1; + } /* Check default bpftool location (will work if we are running the * default flavor of test_progs) */ snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "./%s", BPFTOOL_DEFAULT_PATH); if (access(tmp, X_OK) == 0) { - strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN); + strscpy(buffer, tmp, size); return 0; } @@ -27,11 +40,11 @@ static int detect_bpftool_path(char *buffer) */ snprintf(tmp, BPFTOOL_PATH_MAX_LEN, "../%s", BPFTOOL_DEFAULT_PATH); if (access(tmp, X_OK) == 0) { - strncpy(buffer, tmp, BPFTOOL_PATH_MAX_LEN); + strscpy(buffer, tmp, size); return 0; } - /* Failed to find bpftool binary */ + fprintf(stderr, "Failed to detect bpftool path, use BPFTOOL env var to override\n"); return 1; } @@ -44,7 +57,7 @@ static int run_command(char *args, char *output_buf, size_t output_max_len) int ret; /* Detect and cache bpftool binary location */ - if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path)) + if (bpftool_path[0] == 0 && detect_bpftool_path(bpftool_path, sizeof(bpftool_path))) return 1; ret = snprintf(command, BPFTOOL_FULL_CMD_MAX_LEN, "%s %s%s", diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c index 20cede4db3ce..45cd0b479fe3 100644 --- a/tools/testing/selftests/bpf/cgroup_helpers.c +++ b/tools/testing/selftests/bpf/cgroup_helpers.c @@ -86,7 +86,7 @@ static int __enable_controllers(const char *cgroup_path, const char *controllers enable[len] = 0; close(fd); } else { - bpf_strlcpy(enable, controllers, sizeof(enable)); + strscpy(enable, controllers); } snprintf(path, sizeof(path), "%s/cgroup.subtree_control", cgroup_path); diff --git a/tools/testing/selftests/bpf/jit_disasm_helpers.c b/tools/testing/selftests/bpf/jit_disasm_helpers.c index febd6b12e372..364c557c5115 100644 --- a/tools/testing/selftests/bpf/jit_disasm_helpers.c +++ b/tools/testing/selftests/bpf/jit_disasm_helpers.c @@ -122,15 +122,15 @@ static int disasm_one_func(FILE *text_out, uint8_t *image, __u32 len) pc += cnt; } qsort(labels.pcs, labels.cnt, sizeof(*labels.pcs), cmp_u32); - for (i = 0; i < labels.cnt; ++i) - /* gcc is unable to infer upper bound for labels.cnt and assumes - * it to be U32_MAX. U32_MAX takes 10 decimal digits. - * snprintf below prints into labels.names[*], - * which has space only for two digits and a letter. - * To avoid truncation warning use (i % MAX_LOCAL_LABELS), - * which informs gcc about printed value upper bound. - */ - snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i % MAX_LOCAL_LABELS); + /* gcc is unable to infer upper bound for labels.cnt and + * assumes it to be U32_MAX. U32_MAX takes 10 decimal digits. + * snprintf below prints into labels.names[*], which has space + * only for two digits and a letter. To avoid truncation + * warning use (i < MAX_LOCAL_LABELS), which informs gcc about + * printed value upper bound. + */ + for (i = 0; i < labels.cnt && i < MAX_LOCAL_LABELS; ++i) + snprintf(labels.names[i], sizeof(labels.names[i]), "L%d", i); /* now print with labels */ labels.print_phase = true; diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 0a6a5561bed3..b82f572641b7 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -432,7 +432,7 @@ int make_sockaddr(int family, const char *addr_str, __u16 port, memset(addr, 0, sizeof(*sun)); sun->sun_family = family; sun->sun_path[0] = 0; - strcpy(sun->sun_path + 1, addr_str); + strscpy(sun->sun_path + 1, addr_str, sizeof(sun->sun_path) - 1); if (len) *len = offsetof(struct sockaddr_un, sun_path) + 1 + strlen(addr_str); return 0; @@ -581,8 +581,7 @@ int open_tuntap(const char *dev_name, bool need_mac) return -1; ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN); - strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1); - ifr.ifr_name[IFNAMSIZ - 1] = '\0'; + strscpy(ifr.ifr_name, dev_name); err = ioctl(fd, TUNSETIFF, &ifr); if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) { diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 5225d69bf79b..c69080ca14f5 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -346,8 +346,7 @@ static void test_task_sleepable(void) close(finish_pipe[1]); test_data = malloc(sizeof(char) * 10); - strncpy(test_data, "test_data", 10); - test_data[9] = '\0'; + strscpy(test_data, "test_data", 10); test_data_long = malloc(sizeof(char) * 5000); for (int i = 0; i < 5000; ++i) { diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index b7d1b52309d0..f829b6f09bc9 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -281,7 +281,7 @@ static void test_dctcp_fallback(void) dctcp_skel = bpf_dctcp__open(); if (!ASSERT_OK_PTR(dctcp_skel, "dctcp_skel")) return; - strcpy(dctcp_skel->rodata->fallback_cc, "cubic"); + strscpy(dctcp_skel->rodata->fallback_cc, "cubic"); if (!ASSERT_OK(bpf_dctcp__load(dctcp_skel), "bpf_dctcp__load")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c index 9015e2c2ab12..478a77cb67e6 100644 --- a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c @@ -202,7 +202,7 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id) iter_fd = bpf_iter_create(bpf_link__fd(link)); if (!ASSERT_GE(iter_fd, 0, "iter_create")) - goto out; + goto out_link; /* trigger the program run */ (void)read(iter_fd, buf, sizeof(buf)); @@ -210,6 +210,8 @@ static void test_cgroup_iter_sleepable(int cgroup_fd, __u64 cgroup_id) ASSERT_EQ(skel->bss->cgroup_id, cgroup_id, "cgroup_id"); close(iter_fd); +out_link: + bpf_link__destroy(link); out: cgrp_ls_sleepable__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c index dd75ccb03770..469e92869523 100644 --- a/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c +++ b/tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c @@ -308,8 +308,10 @@ static int find_field_offset(struct btf *btf, char *pattern, regmatch_t *matches return -1; } - strncpy(type_str, type, type_sz); - strncpy(field_str, field, field_sz); + memcpy(type_str, type, type_sz); + type_str[type_sz] = '\0'; + memcpy(field_str, field, field_sz); + field_str[field_sz] = '\0'; btf_id = btf__find_by_name(btf, type_str); if (btf_id < 0) { PRINT_FAIL("No BTF info for type %s\n", type_str); diff --git a/tools/testing/selftests/bpf/prog_tests/dynptr.c b/tools/testing/selftests/bpf/prog_tests/dynptr.c index b9f86cb91e81..5fda11590708 100644 --- a/tools/testing/selftests/bpf/prog_tests/dynptr.c +++ b/tools/testing/selftests/bpf/prog_tests/dynptr.c @@ -137,11 +137,14 @@ static void verify_success(const char *prog_name, enum test_setup_type setup_typ ); link = bpf_program__attach(prog); - if (!ASSERT_OK_PTR(link, "bpf_program__attach")) + if (!ASSERT_OK_PTR(link, "bpf_program__attach")) { + bpf_object__close(obj); goto cleanup; + } err = bpf_prog_test_run_opts(aux_prog_fd, &topts); bpf_link__destroy(link); + bpf_object__close(obj); if (!ASSERT_OK(err, "test_run")) goto cleanup; diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c index c534b4d5f9da..3078d8264deb 100644 --- a/tools/testing/selftests/bpf/prog_tests/fd_array.c +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -412,8 +412,8 @@ static void check_fd_array_cnt__fd_array_too_big(void) ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG"); cleanup_fds: - while (i > 0) - Close(extra_fds[--i]); + while (i-- > 0) + Close(extra_fds[i]); } void test_fd_array_cnt(void) diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index 08bae13248c4..fb4892681464 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -570,7 +570,7 @@ static int create_tap(const char *ifname) }; int fd, ret; - strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + strscpy(ifr.ifr_name, ifname); fd = open("/dev/net/tun", O_RDWR); if (fd < 0) @@ -599,7 +599,7 @@ static int ifup(const char *ifname) struct ifreq ifr = {}; int sk, ret; - strncpy(ifr.ifr_name, ifname, sizeof(ifr.ifr_name)); + strscpy(ifr.ifr_name, ifname); sk = socket(PF_INET, SOCK_DGRAM, 0); if (sk < 0) diff --git a/tools/testing/selftests/bpf/prog_tests/htab_update.c b/tools/testing/selftests/bpf/prog_tests/htab_update.c index d0b405eb2966..ea1a6766fbe9 100644 --- a/tools/testing/selftests/bpf/prog_tests/htab_update.c +++ b/tools/testing/selftests/bpf/prog_tests/htab_update.c @@ -61,6 +61,7 @@ static void test_reenter_update(void) ASSERT_EQ(skel->bss->update_err, -EDEADLK, "no reentrancy"); out: + free(value); htab_update__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c index 6e35e13c2022..399fe9103f83 100644 --- a/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/kmem_cache_iter.c @@ -104,11 +104,8 @@ void test_kmem_cache_iter(void) if (!ASSERT_GE(iter_fd, 0, "iter_create")) goto destroy; - memset(buf, 0, sizeof(buf)); - while (read(iter_fd, buf, sizeof(buf)) > 0) { - /* Read out all contents */ - printf("%s", buf); - } + while (read(iter_fd, buf, sizeof(buf)) > 0) + ; /* Read out all contents */ /* Next reads should return 0 */ ASSERT_EQ(read(iter_fd, buf, sizeof(buf)), 0, "read"); diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 9caef222e528..f81dcd609ee9 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -456,25 +456,23 @@ static void test_kprobe_multi_bench_attach(bool kernel) { LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); struct kprobe_multi_empty *skel = NULL; - char **syms = NULL; - size_t cnt = 0; + struct ksyms *ksyms = NULL; - if (!ASSERT_OK(bpf_get_ksyms(&syms, &cnt, kernel), "bpf_get_ksyms")) + if (!ASSERT_OK(bpf_get_ksyms(&ksyms, kernel), "bpf_get_ksyms")) return; skel = kprobe_multi_empty__open_and_load(); if (!ASSERT_OK_PTR(skel, "kprobe_multi_empty__open_and_load")) goto cleanup; - opts.syms = (const char **) syms; - opts.cnt = cnt; + opts.syms = (const char **)ksyms->filtered_syms; + opts.cnt = ksyms->filtered_cnt; do_bench_test(skel, &opts); cleanup: kprobe_multi_empty__destroy(skel); - if (syms) - free(syms); + free_kallsyms_local(ksyms); } static void test_kprobe_multi_bench_attach_addr(bool kernel) diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c index 3bc730b7c7fa..1b25d5c5f8fb 100644 --- a/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c +++ b/tools/testing/selftests/bpf/prog_tests/lwt_seg6local.c @@ -117,7 +117,7 @@ void test_lwt_seg6local(void) const char *ns1 = NETNS_BASE "1"; const char *ns6 = NETNS_BASE "6"; struct nstoken *nstoken = NULL; - const char *foobar = "foobar"; + const char foobar[] = "foobar"; ssize_t bytes; int sfd, cfd; char buf[7]; diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c new file mode 100644 index 000000000000..506ed55e8528 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/map_kptr_race.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ +#include <test_progs.h> +#include <network_helpers.h> + +#include "map_kptr_race.skel.h" + +static int get_map_id(int map_fd) +{ + struct bpf_map_info info = {}; + __u32 len = sizeof(info); + + if (!ASSERT_OK(bpf_map_get_info_by_fd(map_fd, &info, &len), "get_map_info")) + return -1; + return info.id; +} + +static int read_refs(struct map_kptr_race *skel) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts); + int ret; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.count_ref), &opts); + if (!ASSERT_OK(ret, "count_ref run")) + return -1; + if (!ASSERT_OK(opts.retval, "count_ref retval")) + return -1; + return skel->bss->num_of_refs; +} + +static void test_htab_leak(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct map_kptr_race *skel, *watcher; + int ret, map_id; + + skel = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_htab_leak), &opts); + if (!ASSERT_OK(ret, "test_htab_leak run")) + goto out_skel; + if (!ASSERT_OK(opts.retval, "test_htab_leak retval")) + goto out_skel; + + map_id = get_map_id(bpf_map__fd(skel->maps.race_hash_map)); + if (!ASSERT_GE(map_id, 0, "map_id")) + goto out_skel; + + watcher = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(watcher, "watcher open_and_load")) + goto out_skel; + + watcher->bss->target_map_id = map_id; + watcher->links.map_put = bpf_program__attach(watcher->progs.map_put); + if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry")) + goto out_watcher; + watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free); + if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit")) + goto out_watcher; + + map_kptr_race__destroy(skel); + skel = NULL; + + kern_sync_rcu(); + + while (!READ_ONCE(watcher->bss->map_freed)) + sched_yield(); + + ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed"); + ASSERT_EQ(read_refs(watcher), 2, "htab refcount"); + +out_watcher: + map_kptr_race__destroy(watcher); +out_skel: + map_kptr_race__destroy(skel); +} + +static void test_percpu_htab_leak(void) +{ + LIBBPF_OPTS(bpf_test_run_opts, opts, + .data_in = &pkt_v4, + .data_size_in = sizeof(pkt_v4), + .repeat = 1, + ); + struct map_kptr_race *skel, *watcher; + int ret, map_id; + + skel = map_kptr_race__open(); + if (!ASSERT_OK_PTR(skel, "open")) + return; + + skel->rodata->nr_cpus = libbpf_num_possible_cpus(); + if (skel->rodata->nr_cpus > 16) + skel->rodata->nr_cpus = 16; + + ret = map_kptr_race__load(skel); + if (!ASSERT_OK(ret, "load")) + goto out_skel; + + ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.test_percpu_htab_leak), &opts); + if (!ASSERT_OK(ret, "test_percpu_htab_leak run")) + goto out_skel; + if (!ASSERT_OK(opts.retval, "test_percpu_htab_leak retval")) + goto out_skel; + + map_id = get_map_id(bpf_map__fd(skel->maps.race_percpu_hash_map)); + if (!ASSERT_GE(map_id, 0, "map_id")) + goto out_skel; + + watcher = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(watcher, "watcher open_and_load")) + goto out_skel; + + watcher->bss->target_map_id = map_id; + watcher->links.map_put = bpf_program__attach(watcher->progs.map_put); + if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry")) + goto out_watcher; + watcher->links.htab_map_free = bpf_program__attach(watcher->progs.htab_map_free); + if (!ASSERT_OK_PTR(watcher->links.htab_map_free, "attach fexit")) + goto out_watcher; + + map_kptr_race__destroy(skel); + skel = NULL; + + kern_sync_rcu(); + + while (!READ_ONCE(watcher->bss->map_freed)) + sched_yield(); + + ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed"); + ASSERT_EQ(read_refs(watcher), 2, "percpu_htab refcount"); + +out_watcher: + map_kptr_race__destroy(watcher); +out_skel: + map_kptr_race__destroy(skel); +} + +static void test_sk_ls_leak(void) +{ + struct map_kptr_race *skel, *watcher; + int listen_fd = -1, client_fd = -1, map_id; + + skel = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + if (!ASSERT_OK(map_kptr_race__attach(skel), "attach")) + goto out_skel; + + listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0); + if (!ASSERT_GE(listen_fd, 0, "start_server")) + goto out_skel; + + client_fd = connect_to_fd(listen_fd, 0); + if (!ASSERT_GE(client_fd, 0, "connect_to_fd")) + goto out_skel; + + if (!ASSERT_EQ(skel->bss->sk_ls_leak_done, 1, "sk_ls_leak_done")) + goto out_skel; + + close(client_fd); + client_fd = -1; + close(listen_fd); + listen_fd = -1; + + map_id = get_map_id(bpf_map__fd(skel->maps.race_sk_ls_map)); + if (!ASSERT_GE(map_id, 0, "map_id")) + goto out_skel; + + watcher = map_kptr_race__open_and_load(); + if (!ASSERT_OK_PTR(watcher, "watcher open_and_load")) + goto out_skel; + + watcher->bss->target_map_id = map_id; + watcher->links.map_put = bpf_program__attach(watcher->progs.map_put); + if (!ASSERT_OK_PTR(watcher->links.map_put, "attach fentry")) + goto out_watcher; + watcher->links.sk_map_free = bpf_program__attach(watcher->progs.sk_map_free); + if (!ASSERT_OK_PTR(watcher->links.sk_map_free, "attach fexit")) + goto out_watcher; + + map_kptr_race__destroy(skel); + skel = NULL; + + kern_sync_rcu(); + + while (!READ_ONCE(watcher->bss->map_freed)) + sched_yield(); + + ASSERT_EQ(watcher->bss->map_freed, 1, "map_freed"); + ASSERT_EQ(read_refs(watcher), 2, "sk_ls refcount"); + +out_watcher: + map_kptr_race__destroy(watcher); +out_skel: + if (client_fd >= 0) + close(client_fd); + if (listen_fd >= 0) + close(listen_fd); + map_kptr_race__destroy(skel); +} + +void serial_test_map_kptr_race(void) +{ + if (test__start_subtest("htab_leak")) + test_htab_leak(); + if (test__start_subtest("percpu_htab_leak")) + test_percpu_htab_leak(); + if (test__start_subtest("sk_ls_leak")) + test_sk_ls_leak(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c index a043af9cd6d9..41441325e179 100644 --- a/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c +++ b/tools/testing/selftests/bpf/prog_tests/queue_stack_map.c @@ -28,9 +28,9 @@ static void test_queue_stack_map_by_type(int type) vals[i] = rand(); if (type == QUEUE) - strncpy(file, "./test_queue_map.bpf.o", sizeof(file)); + strscpy(file, "./test_queue_map.bpf.o"); else if (type == STACK) - strncpy(file, "./test_stack_map.bpf.o", sizeof(file)); + strscpy(file, "./test_stack_map.bpf.o"); else return; diff --git a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c index d93a0c7b1786..0322f817d07b 100644 --- a/tools/testing/selftests/bpf/prog_tests/reg_bounds.c +++ b/tools/testing/selftests/bpf/prog_tests/reg_bounds.c @@ -2091,7 +2091,7 @@ static struct subtest_case crafted_cases[] = { {U64, S64, {0, 0xffffffffULL}, {0x7fffffff, 0x7fffffff}}, {U64, U32, {0, 0x100000000}, {0, 0}}, - {U64, U32, {0xfffffffe, 0x100000000}, {0x80000000, 0x80000000}}, + {U64, U32, {0xfffffffe, 0x300000000}, {0x80000000, 0x80000000}}, {U64, S32, {0, 0xffffffff00000000ULL}, {0, 0}}, /* these are tricky cases where lower 32 bits allow to tighten 64 diff --git a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c index e4dac529d424..77fe1bfb7504 100644 --- a/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/setget_sockopt.c @@ -212,7 +212,7 @@ void test_setget_sockopt(void) if (!ASSERT_OK_PTR(skel, "open skel")) goto done; - strcpy(skel->rodata->veth, "binddevtest1"); + strscpy(skel->rodata->veth, "binddevtest1"); skel->rodata->veth_ifindex = if_nametoindex("binddevtest1"); if (!ASSERT_GT(skel->rodata->veth_ifindex, 0, "if_nametoindex")) goto done; diff --git a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c index 3eefdfed1db9..657d897958b6 100644 --- a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c +++ b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c @@ -34,7 +34,7 @@ void test_skc_to_unix_sock(void) memset(&sockaddr, 0, sizeof(sockaddr)); sockaddr.sun_family = AF_UNIX; - strncpy(sockaddr.sun_path, sock_path, strlen(sock_path)); + strscpy(sockaddr.sun_path, sock_path); sockaddr.sun_path[0] = '\0'; err = bind(sockfd, (struct sockaddr *)&sockaddr, sizeof(sockaddr)); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 256707e7d20d..dd3c757859f6 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -204,7 +204,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type) /* Fail since bpf_link for the same prog type has been created. */ link2 = bpf_program__attach_sockmap(prog_clone, map); if (!ASSERT_ERR_PTR(link2, "bpf_program__attach_sockmap")) { - bpf_link__detach(link2); + bpf_link__destroy(link2); goto out; } @@ -230,7 +230,7 @@ static void test_skmsg_helpers_with_link(enum bpf_map_type map_type) if (!ASSERT_OK(err, "bpf_link_update")) goto out; out: - bpf_link__detach(link); + bpf_link__destroy(link); test_skmsg_load_helpers__destroy(skel); } @@ -417,7 +417,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void) if (!ASSERT_OK_PTR(link, "bpf_program__attach_sockmap")) goto out; - bpf_link__detach(link); + bpf_link__destroy(link); err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0); if (!ASSERT_OK(err, "bpf_prog_attach")) @@ -426,7 +426,7 @@ static void test_sockmap_skb_verdict_attach_with_link(void) /* Fail since attaching with the same prog/map has been done. */ link = bpf_program__attach_sockmap(prog, map); if (!ASSERT_ERR_PTR(link, "bpf_program__attach_sockmap")) - bpf_link__detach(link); + bpf_link__destroy(link); err = bpf_prog_detach2(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT); if (!ASSERT_OK(err, "bpf_prog_detach2")) @@ -747,13 +747,13 @@ static void test_sockmap_skb_verdict_peek_with_link(void) test_sockmap_skb_verdict_peek_helper(map); ASSERT_EQ(pass->bss->clone_called, 1, "clone_called"); out: - bpf_link__detach(link); + bpf_link__destroy(link); test_sockmap_pass_prog__destroy(pass); } static void test_sockmap_unconnected_unix(void) { - int err, map, stream = 0, dgram = 0, zero = 0; + int err, map, stream = -1, dgram = -1, zero = 0; struct test_sockmap_pass_prog *skel; skel = test_sockmap_pass_prog__open_and_load(); @@ -764,22 +764,22 @@ static void test_sockmap_unconnected_unix(void) stream = xsocket(AF_UNIX, SOCK_STREAM, 0); if (stream < 0) - return; + goto out; dgram = xsocket(AF_UNIX, SOCK_DGRAM, 0); - if (dgram < 0) { - close(stream); - return; - } + if (dgram < 0) + goto out; err = bpf_map_update_elem(map, &zero, &stream, BPF_ANY); - ASSERT_ERR(err, "bpf_map_update_elem(stream)"); + if (!ASSERT_ERR(err, "bpf_map_update_elem(stream)")) + goto out; err = bpf_map_update_elem(map, &zero, &dgram, BPF_ANY); ASSERT_OK(err, "bpf_map_update_elem(dgram)"); - +out: close(stream); close(dgram); + test_sockmap_pass_prog__destroy(skel); } static void test_sockmap_many_socket(void) @@ -1027,7 +1027,7 @@ static void test_sockmap_skb_verdict_vsock_poll(void) if (xrecv_nonblock(conn, &buf, 1, 0) != 1) FAIL("xrecv_nonblock"); detach: - bpf_link__detach(link); + bpf_link__destroy(link); close: xclose(conn); xclose(peer); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index f1bdccc7e4e7..cc0c68bab907 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -899,7 +899,7 @@ static void test_msg_redir_to_listening_with_link(struct test_sockmap_listen *sk redir_to_listening(family, sotype, sock_map, verdict_map, REDIR_EGRESS); - bpf_link__detach(link); + bpf_link__destroy(link); } static void redir_partial(int family, int sotype, int sock_map, int parser_map) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index ba6b3ec1156a..53637431ec5d 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -142,7 +142,7 @@ static int getsetsockopt(void) /* TCP_CONGESTION can extend the string */ - strcpy(buf.cc, "nv"); + strscpy(buf.cc, "nv"); err = setsockopt(fd, SOL_TCP, TCP_CONGESTION, &buf, strlen("nv")); if (err) { log_err("Failed to call setsockopt(TCP_CONGESTION)"); diff --git a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c index 4006879ca3fe..d42123a0fb16 100644 --- a/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c +++ b/tools/testing/selftests/bpf/prog_tests/struct_ops_private_stack.c @@ -54,9 +54,7 @@ static void test_private_stack_fail(void) } err = struct_ops_private_stack_fail__load(skel); - if (!ASSERT_ERR(err, "struct_ops_private_stack_fail__load")) - goto cleanup; - return; + ASSERT_ERR(err, "struct_ops_private_stack_fail__load"); cleanup: struct_ops_private_stack_fail__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_data.h b/tools/testing/selftests/bpf/prog_tests/task_local_data.h index 0f86b9275cf9..8342e2fe5260 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_local_data.h +++ b/tools/testing/selftests/bpf/prog_tests/task_local_data.h @@ -262,7 +262,7 @@ retry: if (!atomic_compare_exchange_strong(&tld_meta_p->cnt, &cnt, cnt + 1)) goto retry; - strncpy(tld_meta_p->metadata[i].name, name, TLD_NAME_LEN); + strscpy(tld_meta_p->metadata[i].name, name); atomic_store(&tld_meta_p->metadata[i].size, size); return (tld_key_t){(__s16)off}; } diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index dd7a138d8c3d..2955750ddada 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -1360,10 +1360,8 @@ static void test_tc_opts_dev_cleanup_target(int target) assert_mprog_count_ifindex(ifindex, target, 4); - ASSERT_OK(system("ip link del dev tcx_opts1"), "del veth"); - ASSERT_EQ(if_nametoindex("tcx_opts1"), 0, "dev1_removed"); - ASSERT_EQ(if_nametoindex("tcx_opts2"), 0, "dev2_removed"); - return; + goto cleanup; + cleanup3: err = bpf_prog_detach_opts(fd3, loopback, target, &optd); ASSERT_OK(err, "prog_detach"); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 76d72a59365e..64fbda082309 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -1095,7 +1095,7 @@ static int tun_open(char *name) ifr.ifr_flags = IFF_TUN | IFF_NO_PI; if (*name) - strncpy(ifr.ifr_name, name, IFNAMSIZ); + strscpy(ifr.ifr_name, name); err = ioctl(fd, TUNSETIFF, &ifr); if (!ASSERT_OK(err, "ioctl TUNSETIFF")) diff --git a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c index 273dd41ca09e..2a1ff821bc97 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_sysctl.c +++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c @@ -27,6 +27,7 @@ struct sysctl_test { OP_EPERM, SUCCESS, } result; + struct bpf_object *obj; }; static struct sysctl_test tests[] = { @@ -1471,6 +1472,7 @@ static int load_sysctl_prog_file(struct sysctl_test *test) return -1; } + test->obj = obj; return prog_fd; } @@ -1573,6 +1575,7 @@ out: /* Detaching w/o checking return code: best effort attempt. */ if (progfd != -1) bpf_prog_detach(cgfd, atype); + bpf_object__close(test->obj); close(progfd); printf("[%s]\n", err ? "FAIL" : "PASS"); return err; diff --git a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c index 0fe0a8f62486..7fc4d7dd70ef 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c +++ b/tools/testing/selftests/bpf/prog_tests/test_tc_tunnel.c @@ -699,7 +699,7 @@ void test_tc_tunnel(void) return; if (!ASSERT_OK(setup(), "global setup")) - return; + goto out; for (i = 0; i < ARRAY_SIZE(subtests_cfg); i++) { cfg = &subtests_cfg[i]; @@ -711,4 +711,7 @@ void test_tc_tunnel(void) subtest_cleanup(cfg); } cleanup(); + +out: + test_tc_tunnel__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c index b38c16b4247f..9aff08ac55c0 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c +++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c @@ -24,9 +24,9 @@ static struct fixture *init_fixture(void) /* for no_alu32 and cpuv4 veristat is in parent folder */ if (access("./veristat", F_OK) == 0) - strcpy(fix->veristat, "./veristat"); + strscpy(fix->veristat, "./veristat"); else if (access("../veristat", F_OK) == 0) - strcpy(fix->veristat, "../veristat"); + strscpy(fix->veristat, "../veristat"); else PRINT_FAIL("Can't find veristat binary"); diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c index bab4a31621c7..7e38ec6e656b 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c +++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c @@ -2003,9 +2003,17 @@ int testapp_stats_tx_invalid_descs(struct test_spec *test) int testapp_stats_rx_full(struct test_spec *test) { - if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE)) + struct pkt_stream *tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); + if (!tmp) + return TEST_FAILURE; + test->ifobj_tx->xsk->pkt_stream = tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + if (!tmp) return TEST_FAILURE; - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + test->ifobj_rx->xsk->pkt_stream = tmp; test->ifobj_rx->xsk->rxqsize = DEFAULT_UMEM_BUFFERS; test->ifobj_rx->release_rx = false; @@ -2015,9 +2023,17 @@ int testapp_stats_rx_full(struct test_spec *test) int testapp_stats_fill_empty(struct test_spec *test) { - if (pkt_stream_replace(test, DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE)) + struct pkt_stream *tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS + DEFAULT_UMEM_BUFFERS / 2, MIN_PKT_SIZE); + if (!tmp) + return TEST_FAILURE; + test->ifobj_tx->xsk->pkt_stream = tmp; + + tmp = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + if (!tmp) return TEST_FAILURE; - test->ifobj_rx->xsk->pkt_stream = pkt_stream_generate(DEFAULT_UMEM_BUFFERS, MIN_PKT_SIZE); + test->ifobj_rx->xsk->pkt_stream = tmp; test->ifobj_rx->use_fill_ring = false; test->ifobj_rx->validation_func = validate_fill_empty; diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c index 2ee17ef1dae2..56cbea280fbd 100644 --- a/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/uprobe_multi_test.c @@ -62,8 +62,10 @@ static void release_child(struct child *child) return; close(child->go[1]); close(child->go[0]); - if (child->thread) + if (child->thread) { pthread_join(child->thread, NULL); + child->thread = 0; + } close(child->c2p[0]); close(child->c2p[1]); if (child->pid > 0) @@ -331,6 +333,8 @@ test_attach_api(const char *binary, const char *pattern, struct bpf_uprobe_multi { static struct child child; + memset(&child, 0, sizeof(child)); + /* no pid filter */ __test_attach_api(binary, pattern, opts, NULL); diff --git a/tools/testing/selftests/bpf/prog_tests/verifier_log.c b/tools/testing/selftests/bpf/prog_tests/verifier_log.c index 8337c6bc5b95..aaa2854974c0 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier_log.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier_log.c @@ -47,7 +47,7 @@ static int load_prog(struct bpf_prog_load_opts *opts, bool expect_load_error) static void verif_log_subtest(const char *name, bool expect_load_error, int log_level) { LIBBPF_OPTS(bpf_prog_load_opts, opts); - char *exp_log, prog_name[16], op_name[32]; + char *exp_log, prog_name[24], op_name[32]; struct test_log_buf *skel; struct bpf_program *prog; size_t fixed_log_sz; diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index fb952703653e..e8ea26464349 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -610,6 +610,61 @@ out: system("ip link del bond"); } +/* + * Test that changing xmit_hash_policy to vlan+srcmac is rejected when a + * native XDP program is loaded on a bond in 802.3ad or balance-xor mode. + * These modes support XDP only when xmit_hash_policy != vlan+srcmac; freely + * changing the policy creates an inconsistency that triggers a WARNING in + * dev_xdp_uninstall() during device teardown. + */ +static void test_xdp_bonding_xmit_policy_compat(struct skeletons *skeletons) +{ + struct nstoken *nstoken = NULL; + int bond_ifindex = -1; + int xdp_fd, err; + + SYS(out, "ip netns add ns_xmit_policy"); + nstoken = open_netns("ns_xmit_policy"); + if (!ASSERT_OK_PTR(nstoken, "open ns_xmit_policy")) + goto out; + + /* 802.3ad with layer2+3 policy: native XDP is supported */ + SYS(out, "ip link add bond0 type bond mode 802.3ad xmit_hash_policy layer2+3"); + SYS(out, "ip link add veth0 type veth peer name veth0p"); + SYS(out, "ip link set veth0 master bond0"); + SYS(out, "ip link set bond0 up"); + + bond_ifindex = if_nametoindex("bond0"); + if (!ASSERT_GT(bond_ifindex, 0, "bond0 ifindex")) + goto out; + + xdp_fd = bpf_program__fd(skeletons->xdp_dummy->progs.xdp_dummy_prog); + if (!ASSERT_GE(xdp_fd, 0, "xdp_dummy fd")) + goto out; + + err = bpf_xdp_attach(bond_ifindex, xdp_fd, XDP_FLAGS_DRV_MODE, NULL); + if (!ASSERT_OK(err, "attach XDP to bond0")) + goto out; + + /* With XDP loaded, switching to vlan+srcmac must be rejected */ + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_NEQ(err, 0, "vlan+srcmac change with XDP loaded should fail"); + + /* Detach XDP first, then the same change must succeed */ + ASSERT_OK(bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL), + "detach XDP from bond0"); + + bond_ifindex = -1; + err = system("ip link set bond0 type bond xmit_hash_policy vlan+srcmac 2>/dev/null"); + ASSERT_OK(err, "vlan+srcmac change without XDP should succeed"); + +out: + if (bond_ifindex > 0) + bpf_xdp_detach(bond_ifindex, XDP_FLAGS_DRV_MODE, NULL); + close_netns(nstoken); + SYS_NOFAIL("ip netns del ns_xmit_policy"); +} + static int libbpf_debug_print(enum libbpf_print_level level, const char *format, va_list args) { @@ -677,6 +732,9 @@ void serial_test_xdp_bonding(void) test_case->xmit_policy); } + if (test__start_subtest("xdp_bonding_xmit_policy_compat")) + test_xdp_bonding_xmit_policy_compat(&skeletons); + if (test__start_subtest("xdp_bonding_redirect_multi")) test_xdp_bonding_redirect_multi(&skeletons); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c index 3f9146d83d79..325e0b64dc35 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c @@ -67,7 +67,7 @@ void test_xdp_flowtable(void) struct nstoken *tok = NULL; int iifindex, stats_fd; __u32 value, key = 0; - struct bpf_link *link; + struct bpf_link *link = NULL; if (SYS_NOFAIL("nft -v")) { fprintf(stdout, "Missing required nft tool\n"); @@ -160,6 +160,7 @@ void test_xdp_flowtable(void) ASSERT_GE(value, N_PACKETS - 2, "bpf_xdp_flow_lookup failed"); out: + bpf_link__destroy(link); xdp_flowtable__destroy(skel); if (tok) close_netns(tok); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index 19f92affc2da..5c31054ad4a4 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -126,10 +126,10 @@ static int open_xsk(int ifindex, struct xsk *xsk) static void close_xsk(struct xsk *xsk) { - if (xsk->umem) - xsk_umem__delete(xsk->umem); if (xsk->socket) xsk_socket__delete(xsk->socket); + if (xsk->umem) + xsk_umem__delete(xsk->umem); munmap(xsk->umem_area, UMEM_SIZE); } diff --git a/tools/testing/selftests/bpf/progs/dmabuf_iter.c b/tools/testing/selftests/bpf/progs/dmabuf_iter.c index 13cdb11fdeb2..9cbb7442646e 100644 --- a/tools/testing/selftests/bpf/progs/dmabuf_iter.c +++ b/tools/testing/selftests/bpf/progs/dmabuf_iter.c @@ -48,7 +48,7 @@ int dmabuf_collector(struct bpf_iter__dmabuf *ctx) /* Buffers are not required to be named */ if (pname) { - if (bpf_probe_read_kernel(name, sizeof(name), pname)) + if (bpf_probe_read_kernel_str(name, sizeof(name), pname) < 0) return 1; /* Name strings can be provided by userspace */ diff --git a/tools/testing/selftests/bpf/progs/map_kptr_race.c b/tools/testing/selftests/bpf/progs/map_kptr_race.c new file mode 100644 index 000000000000..f6f136cd8f60 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/map_kptr_race.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "../test_kmods/bpf_testmod_kfunc.h" + +struct map_value { + struct prog_test_ref_kfunc __kptr *ref_ptr; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} race_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, 1); +} race_percpu_hash_map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_SK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct map_value); +} race_sk_ls_map SEC(".maps"); + +int num_of_refs; +int sk_ls_leak_done; +int target_map_id; +int map_freed; +const volatile int nr_cpus; + +SEC("tc") +int test_htab_leak(struct __sk_buff *skb) +{ + struct prog_test_ref_kfunc *p, *old; + struct map_value val = {}; + struct map_value *v; + int key = 0; + + if (bpf_map_update_elem(&race_hash_map, &key, &val, BPF_ANY)) + return 1; + + v = bpf_map_lookup_elem(&race_hash_map, &key); + if (!v) + return 2; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 3; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + bpf_map_delete_elem(&race_hash_map, &key); + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 4; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + return 0; +} + +static int fill_percpu_kptr(struct map_value *v) +{ + struct prog_test_ref_kfunc *p, *old; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 1; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + return 0; +} + +SEC("tc") +int test_percpu_htab_leak(struct __sk_buff *skb) +{ + struct map_value *v, *arr[16] = {}; + struct map_value val = {}; + int key = 0; + int err = 0; + + if (bpf_map_update_elem(&race_percpu_hash_map, &key, &val, BPF_ANY)) + return 1; + + for (int i = 0; i < nr_cpus; i++) { + v = bpf_map_lookup_percpu_elem(&race_percpu_hash_map, &key, i); + if (!v) + return 2; + arr[i] = v; + } + + bpf_map_delete_elem(&race_percpu_hash_map, &key); + + for (int i = 0; i < nr_cpus; i++) { + v = arr[i]; + err = fill_percpu_kptr(v); + if (err) + return 3; + } + + return 0; +} + +SEC("tp_btf/inet_sock_set_state") +int BPF_PROG(test_sk_ls_leak, struct sock *sk, int oldstate, int newstate) +{ + struct prog_test_ref_kfunc *p, *old; + struct map_value *v; + + if (newstate != BPF_TCP_SYN_SENT) + return 0; + + if (sk_ls_leak_done) + return 0; + + v = bpf_sk_storage_get(&race_sk_ls_map, sk, NULL, + BPF_SK_STORAGE_GET_F_CREATE); + if (!v) + return 0; + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 0; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + bpf_sk_storage_delete(&race_sk_ls_map, sk); + + p = bpf_kfunc_call_test_acquire(&(unsigned long){0}); + if (!p) + return 0; + old = bpf_kptr_xchg(&v->ref_ptr, p); + if (old) + bpf_kfunc_call_test_release(old); + + sk_ls_leak_done = 1; + return 0; +} + +long target_map_ptr; + +SEC("fentry/bpf_map_put") +int BPF_PROG(map_put, struct bpf_map *map) +{ + if (target_map_id && map->id == (u32)target_map_id) + target_map_ptr = (long)map; + return 0; +} + +SEC("fexit/htab_map_free") +int BPF_PROG(htab_map_free, struct bpf_map *map) +{ + if (target_map_ptr && (long)map == target_map_ptr) + map_freed = 1; + return 0; +} + +SEC("fexit/bpf_sk_storage_map_free") +int BPF_PROG(sk_map_free, struct bpf_map *map) +{ + if (target_map_ptr && (long)map == target_map_ptr) + map_freed = 1; + return 0; +} + +SEC("syscall") +int count_ref(void *ctx) +{ + struct prog_test_ref_kfunc *p; + unsigned long arg = 0; + + p = bpf_kfunc_call_test_acquire(&arg); + if (!p) + return 1; + + num_of_refs = p->cnt.refs.counter; + + bpf_kfunc_call_test_release(p); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index 560531404bce..97065a26cf70 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1863,4 +1863,141 @@ l1_%=: r0 = 1; \ : __clobber_all); } +/* This test covers the bounds deduction when the u64 range and the tnum + * overlap only at umax. After instruction 3, the ranges look as follows: + * + * 0 umin=0xe01 umax=0xf00 U64_MAX + * | [xxxxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * | x x | tnum values + * + * The verifier can therefore deduce that the R0=0xf0=240. + */ +SEC("socket") +__description("bounds refinement with single-value tnum on umax") +__msg("3: (15) if r0 == 0xe0 {{.*}} R0=240") +__success __log_level(2) +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void bounds_refinement_tnum_umax(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + r0 |= 0xe0; \ + r0 &= 0xf0; \ + if r0 == 0xe0 goto +2; \ + if r0 == 0xf0 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test covers the bounds deduction when the u64 range and the tnum + * overlap only at umin. After instruction 3, the ranges look as follows: + * + * 0 umin=0xe00 umax=0xeff U64_MAX + * | [xxxxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * | x x | tnum values + * + * The verifier can therefore deduce that the R0=0xe0=224. + */ +SEC("socket") +__description("bounds refinement with single-value tnum on umin") +__msg("3: (15) if r0 == 0xf0 {{.*}} R0=224") +__success __log_level(2) +__flag(BPF_F_TEST_REG_INVARIANTS) +__naked void bounds_refinement_tnum_umin(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + r0 |= 0xe0; \ + r0 &= 0xf0; \ + if r0 == 0xf0 goto +2; \ + if r0 == 0xe0 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test covers the bounds deduction when the only possible tnum value is + * in the middle of the u64 range. After instruction 3, the ranges look as + * follows: + * + * 0 umin=0x7cf umax=0x7df U64_MAX + * | [xxxxxxxxxxxx] | + * |----------------------------|------------------------------| + * | x x x x x | tnum values + * | +--- 0x7e0 + * +--- 0x7d0 + * + * Since the lower four bits are zero, the tnum and the u64 range only overlap + * in R0=0x7d0=2000. Instruction 5 is therefore dead code. + */ +SEC("socket") +__description("bounds refinement with single-value tnum in middle of range") +__msg("3: (a5) if r0 < 0x7cf {{.*}} R0=2000") +__success __log_level(2) +__naked void bounds_refinement_tnum_middle(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + if r0 & 0x0f goto +4; \ + if r0 > 0x7df goto +3; \ + if r0 < 0x7cf goto +2; \ + if r0 == 0x7d0 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test cover the negative case for the tnum/u64 overlap. Since + * they contain the same two values (i.e., {0, 1}), we can't deduce + * anything more. + */ +SEC("socket") +__description("bounds refinement: several overlaps between tnum and u64") +__msg("2: (25) if r0 > 0x1 {{.*}} R0=scalar(smin=smin32=0,smax=umax=smax32=umax32=1,var_off=(0x0; 0x1))") +__failure __log_level(2) +__naked void bounds_refinement_several_overlaps(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + if r0 < 0 goto +3; \ + if r0 > 1 goto +2; \ + if r0 == 1 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + +/* This test cover the negative case for the tnum/u64 overlap. Since + * they overlap in the two values contained by the u64 range (i.e., + * {0xf, 0x10}), we can't deduce anything more. + */ +SEC("socket") +__description("bounds refinement: multiple overlaps between tnum and u64") +__msg("2: (25) if r0 > 0x10 {{.*}} R0=scalar(smin=umin=smin32=umin32=15,smax=umax=smax32=umax32=16,var_off=(0x0; 0x1f))") +__failure __log_level(2) +__naked void bounds_refinement_multiple_overlaps(void *ctx) +{ + asm volatile(" \ + call %[bpf_get_prandom_u32]; \ + if r0 < 0xf goto +3; \ + if r0 > 0x10 goto +2; \ + if r0 == 0x10 goto +1; \ + r10 = 0; \ + exit; \ +" : + : __imm(bpf_get_prandom_u32) + : __clobber_all); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 02a85dda30e6..0929f4a7bda4 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1261,14 +1261,8 @@ int get_bpf_max_tramp_links(void) return ret; } -#define MAX_BACKTRACE_SZ 128 -void crash_handler(int signum) +static void dump_crash_log(void) { - void *bt[MAX_BACKTRACE_SZ]; - size_t sz; - - sz = backtrace(bt, ARRAY_SIZE(bt)); - fflush(stdout); stdout = env.stdout_saved; stderr = env.stderr_saved; @@ -1277,12 +1271,32 @@ void crash_handler(int signum) env.test_state->error_cnt++; dump_test_log(env.test, env.test_state, true, false, NULL); } +} + +#define MAX_BACKTRACE_SZ 128 + +void crash_handler(int signum) +{ + void *bt[MAX_BACKTRACE_SZ]; + size_t sz; + + sz = backtrace(bt, ARRAY_SIZE(bt)); + + dump_crash_log(); + if (env.worker_id != -1) fprintf(stderr, "[%d]: ", env.worker_id); fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum); backtrace_symbols_fd(bt, sz, STDERR_FILENO); } +#ifdef __SANITIZE_ADDRESS__ +void __asan_on_error(void) +{ + dump_crash_log(); +} +#endif + void hexdump(const char *prefix, const void *buf, size_t len) { for (int i = 0; i < len; i++) { @@ -1799,7 +1813,7 @@ static int worker_main_send_subtests(int sock, struct test_state *state) msg.subtest_done.num = i; - strncpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME); + strscpy(msg.subtest_done.name, subtest_state->name, MAX_SUBTEST_NAME); msg.subtest_done.error_cnt = subtest_state->error_cnt; msg.subtest_done.skipped = subtest_state->skipped; @@ -1944,13 +1958,15 @@ int main(int argc, char **argv) .parser = parse_arg, .doc = argp_program_doc, }; + int err, i; + +#ifndef __SANITIZE_ADDRESS__ struct sigaction sigact = { .sa_handler = crash_handler, .sa_flags = SA_RESETHAND, - }; - int err, i; - + }; sigaction(SIGSEGV, &sigact, NULL); +#endif env.stdout_saved = stdout; env.stderr_saved = stderr; diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 27db34ecf3f5..a8ae03c57bba 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1320,7 +1320,7 @@ static bool cmp_str_seq(const char *log, const char *exp) printf("FAIL\nTestcase bug\n"); return false; } - strncpy(needle, exp, len); + memcpy(needle, exp, len); needle[len] = 0; q = strstr(log, needle); if (!q) { diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c index 16eb37e5bad6..66af0d13751a 100644 --- a/tools/testing/selftests/bpf/testing_helpers.c +++ b/tools/testing/selftests/bpf/testing_helpers.c @@ -212,6 +212,7 @@ int parse_test_list_file(const char *path, break; } + free(buf); fclose(f); return err; } diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index eeaab7013ca2..0e63daf83ed5 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -24,12 +24,6 @@ #define TRACEFS_PIPE "/sys/kernel/tracing/trace_pipe" #define DEBUGFS_PIPE "/sys/kernel/debug/tracing/trace_pipe" -struct ksyms { - struct ksym *syms; - size_t sym_cap; - size_t sym_cnt; -}; - static struct ksyms *ksyms; static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER; @@ -54,6 +48,8 @@ void free_kallsyms_local(struct ksyms *ksyms) if (!ksyms) return; + free(ksyms->filtered_syms); + if (!ksyms->syms) { free(ksyms); return; @@ -610,7 +606,7 @@ static int search_kallsyms_compare(const void *p1, const struct ksym *p2) return compare_name(p1, p2->name); } -int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) +int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel) { size_t cap = 0, cnt = 0; char *name = NULL, *ksym_name, **syms = NULL; @@ -637,8 +633,10 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) else f = fopen("/sys/kernel/debug/tracing/available_filter_functions", "r"); - if (!f) + if (!f) { + free_kallsyms_local(ksyms); return -EINVAL; + } map = hashmap__new(symbol_hash, symbol_equal, NULL); if (IS_ERR(map)) { @@ -679,15 +677,18 @@ int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel) syms[cnt++] = ksym_name; } - *symsp = syms; - *cntp = cnt; + ksyms->filtered_syms = syms; + ksyms->filtered_cnt = cnt; + *ksymsp = ksyms; error: free(name); fclose(f); hashmap__free(map); - if (err) + if (err) { free(syms); + free_kallsyms_local(ksyms); + } return err; } diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h index a5576b2dfc26..d5bf1433675d 100644 --- a/tools/testing/selftests/bpf/trace_helpers.h +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -23,7 +23,14 @@ struct ksym { long addr; char *name; }; -struct ksyms; + +struct ksyms { + struct ksym *syms; + size_t sym_cap; + size_t sym_cnt; + char **filtered_syms; + size_t filtered_cnt; +}; typedef int (*ksym_cmp_t)(const void *p1, const void *p2); typedef int (*ksym_search_cmp_t)(const void *p1, const struct ksym *p2); @@ -53,7 +60,7 @@ ssize_t get_rel_offset(uintptr_t addr); int read_build_id(const char *path, char *build_id, size_t size); -int bpf_get_ksyms(char ***symsp, size_t *cntp, bool kernel); +int bpf_get_ksyms(struct ksyms **ksymsp, bool kernel); int bpf_get_addrs(unsigned long **addrsp, size_t *cntp, bool kernel); #endif diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index 1be1e353d40a..75f85e0362f5 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -3378,6 +3378,8 @@ int main(int argc, char **argv) } } free(env.presets[i].atoms); + if (env.presets[i].value.type == ENUMERATOR) + free(env.presets[i].value.svalue); } free(env.presets); return -err; diff --git a/tools/testing/selftests/bpf/xdp_features.c b/tools/testing/selftests/bpf/xdp_features.c index 595c79141cf3..a27ed663967c 100644 --- a/tools/testing/selftests/bpf/xdp_features.c +++ b/tools/testing/selftests/bpf/xdp_features.c @@ -16,6 +16,7 @@ #include <network_helpers.h> +#include "bpf_util.h" #include "xdp_features.skel.h" #include "xdp_features.h" @@ -212,7 +213,7 @@ static void set_env_default(void) env.feature.drv_feature = NETDEV_XDP_ACT_NDO_XMIT; env.feature.action = -EINVAL; env.ifindex = -ENODEV; - strcpy(env.ifname, "unknown"); + strscpy(env.ifname, "unknown"); make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_CTRL_PORT, &env.dut_ctrl_addr, NULL); make_sockaddr(AF_INET6, "::ffff:127.0.0.1", DUT_ECHO_PORT, diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 3d8de0d4c96a..6db3b5555a22 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -550,7 +550,7 @@ static int rxq_num(const char *ifname) struct ifreq ifr = { .ifr_data = (void *)&ch, }; - strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); + strscpy(ifr.ifr_name, ifname); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); @@ -571,7 +571,7 @@ static void hwtstamp_ioctl(int op, const char *ifname, struct hwtstamp_config *c struct ifreq ifr = { .ifr_data = (void *)cfg, }; - strncpy(ifr.ifr_name, ifname, IF_NAMESIZE - 1); + strscpy(ifr.ifr_name, ifname); int fd, ret; fd = socket(AF_UNIX, SOCK_DGRAM, 0); diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 5dff3ad53867..a56f4153c64d 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -196,7 +196,6 @@ test_add_proc() # P<v> = set cpus.partition (0:member, 1:root, 2:isolated) # C<l> = add cpu-list to cpuset.cpus # X<l> = add cpu-list to cpuset.cpus.exclusive -# S<p> = use prefix in subtree_control # T = put a task into cgroup # CX<l> = add cpu-list to both cpuset.cpus and cpuset.cpus.exclusive # O<c>=<v> = Write <v> to CPU online file of <c> @@ -209,44 +208,46 @@ test_add_proc() # sched-debug matching which includes offline CPUs and single-CPU partitions # while the second one is for matching cpuset.cpus.isolated. # -SETUP_A123_PARTITIONS="C1-3:P1:S+ C2-3:P1:S+ C3:P1" +SETUP_A123_PARTITIONS="C1-3:P1 C2-3:P1 C3:P1" TEST_MATRIX=( # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- - " C0-1 . . C2-3 S+ C4-5 . . 0 A2:0-1" + " C0-1 . . C2-3 . C4-5 . . 0 A2:0-1" " C0-1 . . C2-3 P1 . . . 0 " - " C0-1 . . C2-3 P1:S+ C0-1:P1 . . 0 " - " C0-1 . . C2-3 P1:S+ C1:P1 . . 0 " - " C0-1:S+ . . C2-3 . . . P1 0 " - " C0-1:P1 . . C2-3 S+ C1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . . 0 " - " C0-1:P1 . . C2-3 S+ C1:P1 . P1 0 " + " C0-1 . . C2-3 P1 C0-1:P1 . . 0 " + " C0-1 . . C2-3 P1 C1:P1 . . 0 " + " C0-1 . . C2-3 . . . P1 0 " + " C0-1:P1 . . C2-3 . C1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . . 0 " + " C0-1:P1 . . C2-3 . C1:P1 . P1 0 " " C0-1:P1 . . C2-3 C4-5 . . . 0 A1:4-5" - " C0-1:P1 . . C2-3 S+:C4-5 . . . 0 A1:4-5" " C0-1 . . C2-3:P1 . . . C2 0 " " C0-1 . . C2-3:P1 . . . C4-5 0 B1:4-5" - "C0-3:P1:S+ C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" - "C0-3:P1:S+ C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" - "C2-3:P1:S+ C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" - "C2-3:P1:S+ C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" - "C2-3:P1:S+ C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" + " C0-3:P1 C2-3:P1 . . . . . . 0 A1:0-1|A2:2-3|XA2:2-3" + " C0-3:P1 C2-3:P1 . . C1-3 . . . 0 A1:1|A2:2-3|XA2:2-3" + " C2-3:P1 C3:P1 . . C3 . . . 0 A1:|A2:3|XA2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . C3 P0 . . 0 A1:3|A2:3 A1:P1|A2:P0" + " C2-3:P1 C2:P1 . . C2-4 . . . 0 A1:3-4|A2:2" + " C2-3:P1 C3:P1 . . C3 . . C0-2 0 A1:|B1:0-2 A1:P1|A2:P1" "$SETUP_A123_PARTITIONS . C2-3 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" # CPU offlining cases: - " C0-1 . . C2-3 S+ C4-5 . O2=0 0 A1:0-1|B1:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" - "C0-3:P1:S+ C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" - "C0-3:P1:S+ C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" - "C2-3:P1:S+ C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" - "C2-3:P1:S+ C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" - "C2-3:P1:S+ C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" - "C2-3:P1:S+ C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C0-1 . . C2-3 . C4-5 . O2=0 0 A1:0-1|B1:3" + " C0-3:P1 C2-3:P1 . . O2=0 . . . 0 A1:0-1|A2:3" + " C0-3:P1 C2-3:P1 . . O2=0 O2=1 . . 0 A1:0-1|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 . . . 0 A1:0|A2:2-3" + " C0-3:P1 C2-3:P1 . . O1=0 O1=1 . . 0 A1:0-1|A2:2-3" + " C2-3:P1 C3:P1 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O3=0 O3=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P2 . . O2=0 O2=1 . . 0 A1:2|A2:3 A1:P1|A2:P2" + " C2-3:P1 C3:P1 . . O2=0 . . . 0 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O3=0 . . . 0 A1:2|A2: A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . . T:O3=0 . . 0 A1:2|A2:2 A1:P1|A2:P-1" + " C2-3:P1 C3:P2 . . T:O2=0 . . . 0 A1:3|A2:3 A1:P1|A2:P-2" + " C1-3:P1 C3:P2 . . . T:O3=0 . . 0 A1:1-2|A2:1-2 A1:P1|A2:P-2 3|" + " C1-3:P1 C3:P2 . . . T:O3=0 O3=1 . 0 A1:1-2|A2:3 A1:P1|A2:P2 3" "$SETUP_A123_PARTITIONS . O1=0 . . . 0 A1:|A2:2|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O2=0 . . . 0 A1:1|A2:|A3:3 A1:P1|A2:P1|A3:P1" "$SETUP_A123_PARTITIONS . O3=0 . . . 0 A1:1|A2:2|A3: A1:P1|A2:P1|A3:P1" @@ -264,88 +265,87 @@ TEST_MATRIX=( # # Remote partition and cpuset.cpus.exclusive tests # - " C0-3:S+ C1-3:S+ C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" - " C0-3:S+ C1-3:S+ C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" - " C0-3:S+ C1-3:S+ C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" - " C4:X0-3:S+ X1-3:S+ X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" - " C4:X0-3:S+ X1-3:S+ X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3:P2 . . 0 A1:0-1|A2:2-3|A3:2-3 A1:P0|A2:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X3:P2 . . 0 A1:0-2|A2:3|A3:3 A1:P0|A2:P2 3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:C3 . 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 C2-3 . . . P2 0 A1:0-1|A2:1|A3:1|B1:2-3 A1:P0|A3:P0|B1:P2" + " C0-3 C1-3 C2-3 C4-5 . . . P2 0 B1:4-5 B1:P2 4-5" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2:C1-3 P2 0 A3:2-3|B1:4 A3:P2|B1:P2 2-4" + " C0-3 C1-3 C2-3 C4 X1-3 X1-3:P2 P2 . 0 A2:1|A3:2-3 A2:P2|A3:P2 1-3" + " C0-3 C1-3 C2-3 C4 X2-3 X2-3 X2-3:P2 P2:C4-5 0 A3:2-3|B1:4-5 A3:P2|B1:P2 2-5" + " C4:X0-3 X1-3 X2-3 . . P2 . . 0 A1:4|A2:1-3|A3:1-3 A2:P2 1-3" + " C4:X0-3 X1-3 X2-3 . . . P2 . 0 A1:4|A2:4|A3:2-3 A3:P2 2-3" # Nested remote/local partition tests - " C0-3:S+ C1-3:S+ C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ + " C0-3 C1-3 C2-3 C4-5 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4-5 \ A1:P0|A2:P1|A3:P2|B1:P1 2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|2-3" - " C0-3:S+ C1-3:S+ C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ + " C0-3 C1-3 C2-3 C4 X2-3 X2-3:P1 . P1 0 A1:0-1|A2:2-3|A3:2-3|B1:4 \ A1:P0|A2:P1|A3:P0|B1:P1" - " C0-3:S+ C1-3:S+ C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ + " C0-3 C1-3 C3 C4 X2-3 X2-3:P1 P2 P1 0 A1:0-1|A2:2|A3:3|B1:4 \ A1:P0|A2:P1|A3:P2|B1:P1 2-4|3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X4:P1 . 0 A1:0-1|A2:2-3|A3:4 \ A1:P0|A2:P2|A3:P1 2-4|2-3" - " C0-4:S+ C1-4:S+ C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ + " C0-4 C1-4 C2-4 . X2-4 X2-4:P2 X3-4:P1 . 0 A1:0-1|A2:2|A3:3-4 \ A1:P0|A2:P2|A3:P1 2" - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . X5 . . 0 A1:0-4|A2:1-4|A3:2-4 \ A1:P0|A2:P-2|A3:P-1 ." - " C0-4:X2-4:S+ C1-4:X2-4:S+:P2 C2-4:X4:P1 \ + " C0-4:X2-4 C1-4:X2-4:P2 C2-4:X4:P1 \ . . . X1 . 0 A1:0-1|A2:2-4|A3:2-4 \ A1:P0|A2:P2|A3:P-1 2-4" # Remote partition offline tests - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" - " C0-3:S+ C1-3:S+ C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 . 0 A1:0-1|A2:1|A3:3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C2-3 . X2-3 X2-3 X2-3:P2:O2=0 O2=1 0 A1:0-1|A2:1|A3:2-3 A1:P0|A3:P2 2-3" + " C0-3 C1-3 C3 . X2-3 X2-3 P2:O3=0 . 0 A1:0-2|A2:1-2|A3: A1:P0|A3:P2 3" + " C0-3 C1-3 C3 . X2-3 X2-3 T:P2:O3=0 . 0 A1:0-2|A2:1-2|A3:1-2 A1:P0|A3:P-2 3|" # An invalidated remote partition cannot self-recover from hotplug - " C0-3:S+ C1-3:S+ C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." + " C0-3 C1-3 C2 . X2-3 X2-3 T:P2:O2=0 O2=1 0 A1:0-3|A2:1-3|A3:2 A1:P0|A3:P-2 ." # cpus.exclusive.effective clearing test - " C0-3:S+ C1-3:S+ C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" + " C0-3 C1-3 C2 . X2-3:X . . . 0 A1:0-3|A2:1-3|A3:2|XA1:" # Invalid to valid remote partition transition test - " C0-3:S+ C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." - " C0-3:S+ C1-3:X3:P2 - . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" + " C0-3 C1-3 . . . X3:P2 . . 0 A1:0-3|A2:1-3|XA2: A2:P-2 ." + " C0-3 C1-3:X3:P2 . . X2-3 P2 . . 0 A1:0-2|A2:3|XA2:3 A2:P2 3" # Invalid to valid local partition direct transition tests - " C1-3:S+:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" - " C1-3:S+:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" - " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" - " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" + " C1-3:P2 X4:P2 . . . . . . 0 A1:1-3|XA1:1-3|A2:1-3:XA2: A1:P2|A2:P-2 1-3" + " C1-3:P2 X4:P2 . . . X3:P2 . . 0 A1:1-2|XA1:1-3|A2:3:XA2:3 A1:P2|A2:P2 1-3" + " C0-3:P2 . . C4-6 C0-4 . . . 0 A1:0-4|B1:5-6 A1:P2|B1:P0" + " C0-3:P2 . . C4-6 C0-4:C0-3 . . . 0 A1:0-3|B1:4-6 A1:P2|B1:P0 0-3" # Local partition invalidation tests - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . . . . 0 A1:1|A2:2|A3:3 A1:P2|A2:P2|A3:P2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . X4 . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" - " C0-3:X1-3:S+:P2 C1-3:X2-3:S+:P2 C2-3:X3:P2 \ + " C0-3:X1-3:P2 C1-3:X2-3:P2 C2-3:X3:P2 \ . . C4:X . . 0 A1:1-3|A2:1-3|A3:2-3|XA2:|XA3: A1:P2|A2:P-2|A3:P-2 1-3" # Local partition CPU change tests - " C0-5:S+:P2 C4-5:S+:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" - " C0-5:S+:P2 C4-5:S+:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" + " C0-5:P2 C4-5:P1 . . . C3-5 . . 0 A1:0-2|A2:3-5 A1:P2|A2:P1 0-2" + " C0-5:P2 C4-5:P1 . . C1-5 . . . 0 A1:1-3|A2:4-5 A1:P2|A2:P1 1-3" # cpus_allowed/exclusive_cpus update tests - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X:C4 . P2 . 0 A1:4|A2:4|XA2:|XA3:|A3:4 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . X1 . P2 . 0 A1:0-3|A2:1-3|XA1:1|XA2:|XA3:|A3:2-3 \ A1:P0|A3:P-2 ." - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3 \ . . X3 P2 . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . . X3 . . 0 A1:0-2|A2:1-2|XA2:3|XA3:3|A3:3|XA3:3 \ A1:P0|A3:P2 3" - " C0-3:X2-3:S+ C1-3:X2-3:S+ C2-3:X2-3:P2 \ + " C0-3:X2-3 C1-3:X2-3 C2-3:X2-3:P2 \ . X4 . . . 0 A1:0-3|A2:1-3|A3:2-3|XA1:4|XA2:|XA3 \ A1:P0|A3:P-2" @@ -356,37 +356,37 @@ TEST_MATRIX=( # # Adding CPUs to partition root that are not in parent's # cpuset.cpus is allowed, but those extra CPUs are ignored. - "C2-3:P1:S+ C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . . C2-4 . . 0 A1:|A2:2-3 A1:P1|A2:P1" # Taking away all CPUs from parent or itself if there are tasks # will make the partition invalid. - "C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" - " C3:P1:S+ C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" + " C2-3:P1 C3:P1 . . T C2-3 . . 0 A1:2-3|A2:2-3 A1:P1|A2:P-1" + " C3:P1 C3 . . T P1 . . 0 A1:3|A2:3 A1:P1|A2:P-1" "$SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P-1|A3:P-1" "$SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1|A2:2|A3:3 A1:P1|A2:P1|A3:P1" # Changing a partition root to member makes child partitions invalid - "C2-3:P1:S+ C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" + " C2-3:P1 C3:P1 . . P0 . . . 0 A1:2-3|A2:3 A1:P0|A2:P-1" "$SETUP_A123_PARTITIONS . C2-3 P0 . . 0 A1:2-3|A2:2-3|A3:3 A1:P1|A2:P0|A3:P-1" # cpuset.cpus can contains cpus not in parent's cpuset.cpus as long # as they overlap. - "C2-3:P1:S+ . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" + " C2-3:P1 . . . . C3-4:P1 . . 0 A1:2|A2:3 A1:P1|A2:P1" # Deletion of CPUs distributed to child cgroup is allowed. - "C0-1:P1:S+ C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5" + " C0-1:P1 C1 . C2-3 C4-5 . . . 0 A1:4-5|A2:4-5" # To become a valid partition root, cpuset.cpus must overlap parent's # cpuset.cpus. - " C0-1:P1 . . C2-3 S+ C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" + " C0-1:P1 . . C2-3 . C4-5:P1 . . 0 A1:0-1|A2:0-1 A1:P1|A2:P-1" # Enabling partition with child cpusets is allowed - " C0-1:S+ C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1" + " C0-1 C1 . C2-3 P1 . . . 0 A1:0-1|A2:1 A1:P1" # A partition root with non-partition root parent is invalid| but it # can be made valid if its parent becomes a partition root too. - " C0-1:S+ C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" - " C0-1:S+ C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" + " C0-1 C1 . C2-3 . P2 . . 0 A1:0-1|A2:1 A1:P0|A2:P-2" + " C0-1 C1:P2 . C2-3 P1 . . . 0 A1:0|A2:1 A1:P1|A2:P2 0-1|1" # A non-exclusive cpuset.cpus change will not invalidate its siblings partition. " C0-1:P1 . . C2-3 C0-2 . . . 0 A1:0-2|B1:3 A1:P1|B1:P0" @@ -398,23 +398,23 @@ TEST_MATRIX=( # Child partition root that try to take all CPUs from parent partition # with tasks will remain invalid. - " C1-4:P1:S+ P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" - " C1-4:P1:S+ P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" - " C1-4:P1:S+ P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . . . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" + " C1-4:P1 P1 . . . C1-4 . . 0 A1|A2:1-4 A1:P1|A2:P1" + " C1-4:P1 P1 . . T C1-4 . . 0 A1:1-4|A2:1-4 A1:P1|A2:P-1" # Clearing of cpuset.cpus with a preset cpuset.cpus.exclusive shouldn't # affect cpuset.cpus.exclusive.effective. - " C1-4:X3:S+ C1:X3 . . . C . . 0 A2:1-4|XA2:3" + " C1-4:X3 C1:X3 . . . C . . 0 A2:1-4|XA2:3" # cpuset.cpus can contain CPUs that overlap a sibling cpuset with cpus.exclusive # but creating a local partition out of it is not allowed. Similarly and change # in cpuset.cpus of a local partition that overlaps sibling exclusive CPUs will # invalidate it. - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1 0 A1:1|A2:2-4|B1:5-6|XB1:5-6 \ A1:P0|A2:P2:B1:P1 2-4" - " CX1-4:S+ CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C3-6 . . . P1 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" - " CX1-4:S+ CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ + " CX1-4 CX2-4:P2 . C5-6 . . . P1:C3-6 0 A1:1|A2:2-4|B1:5-6 \ A1:P0|A2:P2:B1:P-1 2-4" # When multiple partitions with conflicting cpuset.cpus are created, the @@ -426,14 +426,14 @@ TEST_MATRIX=( " C1-3:X1-3 . . C4-5 . . . C1-2 0 A1:1-3|B1:1-2" # cpuset.cpus can become empty with task in it as it inherits parent's effective CPUs - " C1-3:S+ C2 . . . T:C . . 0 A1:1-3|A2:1-3" + " C1-3 C2 . . . T:C . . 0 A1:1-3|A2:1-3" # old-A1 old-A2 old-A3 old-B1 new-A1 new-A2 new-A3 new-B1 fail ECPUs Pstate ISOLCPUS # ------ ------ ------ ------ ------ ------ ------ ------ ---- ----- ------ -------- # Failure cases: # A task cannot be added to a partition with no cpu - "C2-3:P1:S+ C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" + " C2-3:P1 C3:P1 . . O2=0:T . . . 1 A1:|A2:3 A1:P1|A2:P1" # Changes to cpuset.cpus.exclusive that violate exclusivity rule is rejected " C0-3 . . C4-5 X0-3 . . X3-5 1 A1:0-3|B1:4-5" @@ -465,31 +465,31 @@ REMOTE_TEST_MATRIX=( # old-p1 old-p2 old-c11 old-c12 old-c21 old-c22 # new-p1 new-p2 new-c11 new-c12 new-c21 new-c22 ECPUs Pstate ISOLCPUS # ------ ------ ------- ------- ------- ------- ----- ------ -------- - " X1-3:S+ X4-6:S+ X1-2 X3 X4-5 X6 \ + " X1-3 X4-6 X1-2 X3 X4-5 X6 \ . . P2 P2 P2 P2 c11:1-2|c12:3|c21:4-5|c22:6 \ c11:P2|c12:P2|c21:P2|c22:P2 1-6" - " CX1-4:S+ . X1-2:P2 C3 . . \ + " CX1-4 . X1-2:P2 C3 . . \ . . . C3-4 . . p1:3-4|c11:1-2|c12:3-4 \ p1:P0|c11:P2|c12:P0 1-2" - " CX1-4:S+ . X1-2:P2 . . . \ + " CX1-4 . X1-2:P2 . . . \ X2-4 . . . . . p1:1,3-4|c11:2 \ p1:P0|c11:P2 2" - " CX1-5:S+ . X1-2:P2 X3-5:P1 . . \ + " CX1-5 . X1-2:P2 X3-5:P1 . . \ X2-4 . . . . . p1:1,5|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X2 . . . p1:1|c11:2|c12:3-4 \ p1:P0|c11:P2|c12:P1 2" # p1 as member, will get its effective CPUs from its parent rtest - " CX1-4:S+ . X1-2:P2 X3-4:P1 . . \ + " CX1-4 . X1-2:P2 X3-4:P1 . . \ . . X1 CX2-4 . . p1:5-7|c11:1|c12:2-4 \ p1:P0|c11:P2|c12:P1 1" - " CX1-4:S+ X5-6:P1:S+ . . . . \ - . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ + " CX1-4 X5-6:P1 . . . . \ + . . X1-2:P2 X4-5:P1 . X1-7:P2 p1:3|c11:1-2|c12:4:c22:5-6 \ p1:P0|p2:P1|c11:P2|c12:P1|c22:P2 \ 1-2,4-6|1-2,5-6" # c12 whose cpuset.cpus CPUs are all granted to c11 will become invalid partition - " C1-5:P1:S+ . C1-4:P1 C2-3 . . \ + " C1-5:P1 . C1-4:P1 C2-3 . . \ . . . P1 . . p1:5|c11:1-4|c12:5 \ p1:P1|c11:P1|c12:P-1" ) @@ -530,7 +530,6 @@ set_ctrl_state() CGRP=$1 STATE=$2 SHOWERR=${3} - CTRL=${CTRL:=$CONTROLLER} HASERR=0 REDIRECT="2> $TMPMSG" [[ -z "$STATE" || "$STATE" = '.' ]] && return 0 @@ -540,15 +539,16 @@ set_ctrl_state() for CMD in $(echo $STATE | sed -e "s/:/ /g") do TFILE=$CGRP/cgroup.procs - SFILE=$CGRP/cgroup.subtree_control PFILE=$CGRP/cpuset.cpus.partition CFILE=$CGRP/cpuset.cpus XFILE=$CGRP/cpuset.cpus.exclusive - case $CMD in - S*) PREFIX=${CMD#?} - COMM="echo ${PREFIX}${CTRL} > $SFILE" + + # Enable cpuset controller if not enabled yet + [[ -f $CFILE ]] || { + COMM="echo +cpuset > $CGRP/../cgroup.subtree_control" eval $COMM $REDIRECT - ;; + } + case $CMD in X*) CPUS=${CMD#?} COMM="echo $CPUS > $XFILE" @@ -764,7 +764,7 @@ check_cgroup_states() # only CPUs in isolated partitions as well as those that are isolated at # boot time. # -# $1 - expected isolated cpu list(s) <isolcpus1>{,<isolcpus2>} +# $1 - expected isolated cpu list(s) <isolcpus1>{|<isolcpus2>} # <isolcpus1> - expected sched/domains value # <isolcpus2> - cpuset.cpus.isolated value = <isolcpus1> if not defined # @@ -773,6 +773,7 @@ check_isolcpus() EXPECTED_ISOLCPUS=$1 ISCPUS=${CGROUP2}/cpuset.cpus.isolated ISOLCPUS=$(cat $ISCPUS) + HKICPUS=$(cat /sys/devices/system/cpu/isolated) LASTISOLCPU= SCHED_DOMAINS=/sys/kernel/debug/sched/domains if [[ $EXPECTED_ISOLCPUS = . ]] @@ -811,6 +812,11 @@ check_isolcpus() EXPECTED_ISOLCPUS=$EXPECTED_SDOMAIN # + # The inverse of HK_TYPE_DOMAIN cpumask in $HKICPUS should match $ISOLCPUS + # + [[ "$ISOLCPUS" != "$HKICPUS" ]] && return 1 + + # # Use the sched domain in debugfs to check isolated CPUs, if available # [[ -d $SCHED_DOMAINS ]] || return 0 @@ -947,7 +953,6 @@ check_test_results() run_state_test() { TEST=$1 - CONTROLLER=cpuset CGROUP_LIST=". A1 A1/A2 A1/A2/A3 B1" RESET_LIST="A1/A2/A3 A1/A2 A1 B1" I=0 @@ -1003,7 +1008,6 @@ run_state_test() run_remote_state_test() { TEST=$1 - CONTROLLER=cpuset [[ -d rtest ]] || mkdir rtest cd rtest echo +cpuset > cgroup.subtree_control diff --git a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c index 61e55dfbf121..e19ff8168baf 100644 --- a/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c +++ b/tools/testing/selftests/filesystems/nsfs/iterate_mntns.c @@ -37,17 +37,20 @@ FIXTURE(iterate_mount_namespaces) { __u64 mnt_ns_id[MNT_NS_COUNT]; }; +static inline bool mntns_in_list(__u64 *mnt_ns_id, struct mnt_ns_info *info) +{ + for (int i = 0; i < MNT_NS_COUNT; i++) { + if (mnt_ns_id[i] == info->mnt_ns_id) + return true; + } + return false; +} + FIXTURE_SETUP(iterate_mount_namespaces) { for (int i = 0; i < MNT_NS_COUNT; i++) self->fd_mnt_ns[i] = -EBADF; - /* - * Creating a new user namespace let's us guarantee that we only see - * mount namespaces that we did actually create. - */ - ASSERT_EQ(unshare(CLONE_NEWUSER), 0); - for (int i = 0; i < MNT_NS_COUNT; i++) { struct mnt_ns_info info = {}; @@ -75,13 +78,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_forward) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[0], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_next; fd_mnt_ns_next = ioctl(fd_mnt_ns_cur, NS_MNT_GET_NEXT, &info); if (fd_mnt_ns_next < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; @@ -96,13 +101,15 @@ TEST_F(iterate_mount_namespaces, iterate_all_backwards) fd_mnt_ns_cur = fcntl(self->fd_mnt_ns[MNT_NS_LAST_INDEX], F_DUPFD_CLOEXEC); ASSERT_GE(fd_mnt_ns_cur, 0); - for (;; count++) { + for (;;) { struct mnt_ns_info info = {}; int fd_mnt_ns_prev; fd_mnt_ns_prev = ioctl(fd_mnt_ns_cur, NS_MNT_GET_PREV, &info); if (fd_mnt_ns_prev < 0 && errno == ENOENT) break; + if (mntns_in_list(self->mnt_ns_id, &info)) + count++; ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; @@ -125,7 +132,6 @@ TEST_F(iterate_mount_namespaces, iterate_forward) ASSERT_GE(fd_mnt_ns_next, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_next; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } @@ -144,7 +150,6 @@ TEST_F(iterate_mount_namespaces, iterate_backward) ASSERT_GE(fd_mnt_ns_prev, 0); ASSERT_EQ(close(fd_mnt_ns_cur), 0); fd_mnt_ns_cur = fd_mnt_ns_prev; - ASSERT_EQ(info.mnt_ns_id, self->mnt_ns_id[i]); } } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index 16a119a4656c..4afaef01c22e 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -76,6 +76,9 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) memset(s, c, n); } +#define KSELFTEST_PRIO_TEST_F 20000 +#define KSELFTEST_PRIO_XFAIL 20001 + #define TEST_TIMEOUT_DEFAULT 30 /* Utilities exposed to the test definitions */ @@ -465,7 +468,7 @@ static inline void __kselftest_memset_safe(void *s, int c, size_t n) fixture_name##_teardown(_metadata, self, variant); \ } \ static struct __test_metadata *_##fixture_name##_##test_name##_object; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_TEST_F))) \ _register_##fixture_name##_##test_name(void) \ { \ struct __test_metadata *object = mmap(NULL, sizeof(*object), \ @@ -880,7 +883,7 @@ struct __test_xfail { .fixture = &_##fixture_name##_fixture_object, \ .variant = &_##fixture_name##_##variant_name##_object, \ }; \ - static void __attribute__((constructor)) \ + static void __attribute__((constructor(KSELFTEST_PRIO_XFAIL))) \ _register_##fixture_name##_##variant_name##_##test_name##_xfail(void) \ { \ _##fixture_name##_##variant_name##_##test_name##_xfail.test = \ diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 997056697ec8..a24ea64e2ae8 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -15,6 +15,7 @@ TEST_PROGS := \ big_tcp.sh \ bind_bhash.sh \ bpf_offload.py \ + bridge_vlan_dump.sh \ broadcast_ether_dst.sh \ broadcast_pmtu.sh \ busy_poll_test.sh \ diff --git a/tools/testing/selftests/net/bridge_vlan_dump.sh b/tools/testing/selftests/net/bridge_vlan_dump.sh new file mode 100755 index 000000000000..ad66731d2a6f --- /dev/null +++ b/tools/testing/selftests/net/bridge_vlan_dump.sh @@ -0,0 +1,204 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bridge VLAN range grouping. VLANs are collapsed into a range entry in +# the dump if they have the same per-VLAN options. These tests verify that +# VLANs with different per-VLAN option values are not grouped together. + +# shellcheck disable=SC1091,SC2034,SC2154,SC2317 +source lib.sh + +ALL_TESTS=" + vlan_range_neigh_suppress + vlan_range_mcast_max_groups + vlan_range_mcast_n_groups + vlan_range_mcast_enabled +" + +setup_prepare() +{ + setup_ns NS + defer cleanup_all_ns + + ip -n "$NS" link add name br0 type bridge vlan_filtering 1 \ + vlan_default_pvid 0 mcast_snooping 1 mcast_vlan_snooping 1 + ip -n "$NS" link set dev br0 up + + ip -n "$NS" link add name dummy0 type dummy + ip -n "$NS" link set dev dummy0 master br0 + ip -n "$NS" link set dev dummy0 up +} + +vlan_range_neigh_suppress() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different neigh_suppress values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress off + check_err $? "Failed to set neigh_suppress for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different neigh_suppress incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same neigh_suppress value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 neigh_suppress on + check_err $? "Failed to set neigh_suppress for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same neigh_suppress not grouped" + + log_test "VLAN range grouping with neigh_suppress" +} + +vlan_range_mcast_max_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_max_groups values and verify no range grouping + bridge -n "$NS" vlan set vid 10 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 10" + + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 200 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + # Verify VLANs are not shown as a range, but individual entries exist + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_max_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_max_groups value and verify range grouping + bridge -n "$NS" vlan set vid 11 dev dummy0 mcast_max_groups 100 + check_err $? "Failed to set mcast_max_groups for VLAN 11" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_max_groups not grouped" + + log_test "VLAN range grouping with mcast_max_groups" +} + +vlan_range_mcast_n_groups() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Add different numbers of multicast groups to each VLAN + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 10 + check_err $? "Failed to add mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 10 + check_err $? "Failed to add second mdb entry to VLAN 10" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 10 + + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.1 vid 11 + check_err $? "Failed to add mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.1 vid 11 + + # Verify VLANs are not shown as a range due to different mcast_n_groups + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_n_groups incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Add another group to VLAN 11 to match VLAN 10's count + bridge -n "$NS" mdb add dev br0 port dummy0 grp 239.1.1.2 vid 11 + check_err $? "Failed to add second mdb entry to VLAN 11" + defer bridge -n "$NS" mdb del dev br0 port dummy0 grp 239.1.1.2 vid 11 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_n_groups not grouped" + + log_test "VLAN range grouping with mcast_n_groups" +} + +vlan_range_mcast_enabled() +{ + RET=0 + + # Add two new consecutive VLANs for range grouping test + bridge -n "$NS" vlan add vid 10 dev br0 self + defer bridge -n "$NS" vlan del vid 10 dev br0 self + + bridge -n "$NS" vlan add vid 11 dev br0 self + defer bridge -n "$NS" vlan del vid 11 dev br0 self + + bridge -n "$NS" vlan add vid 10 dev dummy0 + defer bridge -n "$NS" vlan del vid 10 dev dummy0 + + bridge -n "$NS" vlan add vid 11 dev dummy0 + defer bridge -n "$NS" vlan del vid 11 dev dummy0 + + # Configure different mcast_snooping for bridge VLANs + # Port VLANs inherit BR_VLFLAG_MCAST_ENABLED from bridge VLANs + bridge -n "$NS" vlan global set dev br0 vid 10 mcast_snooping 1 + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 0 + + # Verify port VLANs are not grouped due to different mcast_enabled + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_fail $? "VLANs with different mcast_enabled incorrectly grouped" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+10$|^\s+10$" + check_err $? "VLAN 10 individual entry not found" + + bridge -n "$NS" -d vlan show dev dummy0 | grep -Eq "^\S+\s+11$|^\s+11$" + check_err $? "VLAN 11 individual entry not found" + + # Configure same mcast_snooping and verify range grouping + bridge -n "$NS" vlan global set dev br0 vid 11 mcast_snooping 1 + + bridge -n "$NS" -d vlan show dev dummy0 | grep -q "10-11" + check_err $? "VLANs with same mcast_enabled not grouped" + + log_test "VLAN range grouping with mcast_enabled" +} + +# Verify the newest tested option is supported +if ! bridge vlan help 2>&1 | grep -q "neigh_suppress"; then + echo "SKIP: iproute2 too old, missing per-VLAN neighbor suppression support" + exit "$ksft_skip" +fi + +trap defer_scopes_cleanup EXIT +setup_prepare +tests_run + +exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index 21026b667667..6eb7f95e70e1 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -1672,6 +1672,17 @@ ipv4_withv6_fcnal() run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1" log_test $? 2 "IPv4 route with invalid IPv6 gateway" + + # Test IPv4 route with loopback IPv6 nexthop + # Regression test: loopback IPv6 nexthop was misclassified as reject + # route, skipping nhc_pcpu_rth_output allocation, causing panic when + # an IPv4 route references it and triggers __mkroute_output(). + run_cmd "$IP -6 nexthop add id 20 dev lo" + run_cmd "$IP ro add 172.20.20.0/24 nhid 20" + run_cmd "ip netns exec $me ping -c1 -W1 172.20.20.1" + log_test $? 1 "IPv4 route with loopback IPv6 nexthop (no crash)" + run_cmd "$IP ro del 172.20.20.0/24" + run_cmd "$IP nexthop del id 20" } ipv4_fcnal_runtime() diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index dc1f200aaa81..a3144d7298a5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -104,6 +104,24 @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, 6 0 0 65535, 6 0 0 0" +# IPv4: TCP hdr of 48B, a first suboption of 12B (DACK8), the RM_ADDR suboption +# generated using "nfbpf_compile '(ip[32] & 0xf0) == 0xc0 && ip[53] == 0x0c && +# (ip[66] & 0xf0) == 0x40'" +CBPF_MPTCP_SUBOPTION_RM_ADDR="13, + 48 0 0 0, + 84 0 0 240, + 21 0 9 64, + 48 0 0 32, + 84 0 0 240, + 21 0 6 192, + 48 0 0 53, + 21 0 4 12, + 48 0 0 66, + 84 0 0 240, + 21 0 1 64, + 6 0 0 65535, + 6 0 0 0" + init_partial() { capout=$(mktemp) @@ -2608,6 +2626,19 @@ remove_tests() chk_rst_nr 0 0 fi + # signal+subflow with limits, remove + if reset "remove signal+subflow with limits"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,subflow + pm_nl_set_limits $ns2 0 0 + addr_nr_ns1=-1 speed=slow \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + chk_rm_nr 1 0 invert + chk_rst_nr 0 0 + fi + # addresses remove if reset "remove addresses"; then pm_nl_set_limits $ns1 3 3 @@ -4217,6 +4248,14 @@ endpoint_tests() chk_subflow_nr "after no reject" 3 chk_mptcp_info subflows 2 subflows 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns2}" ${iptables} -I OUTPUT -s "10.0.1.2" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 local i for i in $(seq 3); do pm_nl_del_endpoint $ns2 1 10.0.1.2 @@ -4229,6 +4268,7 @@ endpoint_tests() chk_subflow_nr "after re-add id 0 ($i)" 3 chk_mptcp_info subflows 3 subflows 3 done + [ ${ipt} = 1 ] && ip netns exec "${ns2}" ${iptables} -D OUTPUT 1 mptcp_lib_kill_group_wait $tests_pid @@ -4288,11 +4328,20 @@ endpoint_tests() chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + # To make sure RM_ADDR are sent over a different subflow, but + # allow the rest to quickly and cleanly close the subflow + local ipt=1 + ip netns exec "${ns1}" ${iptables} -I OUTPUT -s "10.0.1.1" \ + -p tcp -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_RM_ADDR" \ + -j DROP || ipt=0 pm_nl_del_endpoint $ns1 42 10.0.1.1 sleep 0.5 chk_subflow_nr "after delete ID 0" 2 chk_mptcp_info subflows 2 subflows 2 chk_mptcp_info add_addr_signal 2 add_addr_accepted 2 + [ ${ipt} = 1 ] && ip netns exec "${ns1}" ${iptables} -D OUTPUT 1 pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal wait_mpj 4 diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 806aaa7d2d61..d11a8b949aab 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -237,10 +237,13 @@ run_test() for dev in ns2eth1 ns2eth2; do tc -n $ns2 qdisc del dev $dev root >/dev/null 2>&1 done - tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 - tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 - tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 + + # keep the queued pkts number low, or the RTT estimator will see + # increasing latency over time. + tc -n $ns1 qdisc add dev ns1eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns1 qdisc add dev ns1eth2 root netem rate ${rate2}mbit $delay2 limit 50 + tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1 limit 50 + tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2 limit 50 # time is measured in ms, account for transfer size, aggregated link speed # and header overhead (10%) diff --git a/tools/testing/selftests/net/netfilter/nf_queue.c b/tools/testing/selftests/net/netfilter/nf_queue.c index 9e56b9d47037..116c0ca0eabb 100644 --- a/tools/testing/selftests/net/netfilter/nf_queue.c +++ b/tools/testing/selftests/net/netfilter/nf_queue.c @@ -18,6 +18,7 @@ struct options { bool count_packets; bool gso_enabled; + bool failopen; int verbose; unsigned int queue_num; unsigned int timeout; @@ -30,7 +31,7 @@ static struct options opts; static void help(const char *p) { - printf("Usage: %s [-c|-v [-vv] ] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); + printf("Usage: %s [-c|-v [-vv] ] [-o] [-t timeout] [-q queue_num] [-Qdst_queue ] [ -d ms_delay ] [-G]\n", p); } static int parse_attr_cb(const struct nlattr *attr, void *data) @@ -236,6 +237,8 @@ struct mnl_socket *open_queue(void) flags = opts.gso_enabled ? NFQA_CFG_F_GSO : 0; flags |= NFQA_CFG_F_UID_GID; + if (opts.failopen) + flags |= NFQA_CFG_F_FAIL_OPEN; mnl_attr_put_u32(nlh, NFQA_CFG_FLAGS, htonl(flags)); mnl_attr_put_u32(nlh, NFQA_CFG_MASK, htonl(flags)); @@ -329,7 +332,7 @@ static void parse_opts(int argc, char **argv) { int c; - while ((c = getopt(argc, argv, "chvt:q:Q:d:G")) != -1) { + while ((c = getopt(argc, argv, "chvot:q:Q:d:G")) != -1) { switch (c) { case 'c': opts.count_packets = true; @@ -366,6 +369,9 @@ static void parse_opts(int argc, char **argv) case 'G': opts.gso_enabled = false; break; + case 'o': + opts.failopen = true; + break; case 'v': opts.verbose++; break; diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh index 139bc1211878..ea766bdc5d04 100755 --- a/tools/testing/selftests/net/netfilter/nft_queue.sh +++ b/tools/testing/selftests/net/netfilter/nft_queue.sh @@ -591,6 +591,7 @@ EOF test_udp_gro_ct() { local errprefix="FAIL: test_udp_gro_ct:" + local timeout=5 ip netns exec "$nsrouter" conntrack -F 2>/dev/null @@ -630,10 +631,10 @@ table inet udpq { } } EOF - timeout 10 ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & + timeout "$timeout" ip netns exec "$ns2" socat UDP-LISTEN:12346,fork,pf=ipv4 OPEN:"$TMPFILE1",trunc & local rpid=$! - ip netns exec "$nsrouter" ./nf_queue -G -c -q 1 -t 2 > "$TMPFILE2" & + ip netns exec "$nsrouter" nice -n -19 ./nf_queue -G -c -q 1 -o -t 2 > "$TMPFILE2" & local nfqpid=$! ip netns exec "$nsrouter" ethtool -K "veth0" rx-udp-gro-forwarding on rx-gro-list on generic-receive-offload on @@ -643,8 +644,12 @@ EOF local bs=512 local count=$(((32 * 1024 * 1024) / bs)) - dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 16); do - timeout 5 ip netns exec "$ns1" \ + + local nprocs=$(nproc) + [ $nprocs -gt 1 ] && nprocs=$((nprocs - 1)) + + dd if=/dev/zero bs="$bs" count="$count" 2>/dev/null | for i in $(seq 1 $nprocs); do + timeout "$timeout" nice -n 19 ip netns exec "$ns1" \ socat -u -b 512 STDIN UDP-DATAGRAM:10.0.2.99:12346,reuseport,bind=0.0.0.0:55221 & done diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt index 3848b419e68c..6c0f32c40f19 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_rcv_big_endseq.pkt @@ -38,7 +38,7 @@ // If queue is empty, accept a packet even if its end_seq is above wup + rcv_wnd +0 < P. 4001:54001(50000) ack 1 win 257 - +0 > . 1:1(0) ack 54001 win 0 + * > . 1:1(0) ack 54001 win 0 // Check LINUX_MIB_BEYOND_WINDOW has been incremented 3 times. +0 `nstat | grep TcpExtBeyondWindow | grep -q " 3 "` diff --git a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt b/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt deleted file mode 100644 index f575c0ff89da..000000000000 --- a/tools/testing/selftests/net/packetdrill/tcp_rcv_toobig.pkt +++ /dev/null @@ -1,33 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - ---mss=1000 - -`./defaults.sh` - - 0 `nstat -n` - -// Establish a connection. - +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 - +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 - +0 setsockopt(3, SOL_SOCKET, SO_RCVBUF, [20000], 4) = 0 - +0 bind(3, ..., ...) = 0 - +0 listen(3, 1) = 0 - - +0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7> - +0 > S. 0:0(0) ack 1 win 18980 <mss 1460,nop,wscale 0> - +.1 < . 1:1(0) ack 1 win 257 - - +0 accept(3, ..., ...) = 4 - - +0 < P. 1:20001(20000) ack 1 win 257 - +.04 > . 1:1(0) ack 20001 win 18000 - - +0 setsockopt(4, SOL_SOCKET, SO_RCVBUF, [12000], 4) = 0 - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 20001 win 18000 - - +0 read(4, ..., 20000) = 20000 -// A too big packet is accepted if the receive queue is empty - +0 < P. 20001:80001(60000) ack 1 win 257 - +0 > . 1:1(0) ack 80001 win 0 - diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c index 8a5cd5cb5472..cf106a49b55e 100644 --- a/tools/testing/selftests/net/tun.c +++ b/tools/testing/selftests/net/tun.c @@ -944,8 +944,8 @@ TEST_F(tun_vnet_udptnl, send_gso_packet) ASSERT_EQ(ret, off); ret = receive_gso_packet_from_tunnel(self, variant, &r_num_mss); - ASSERT_EQ(ret, variant->data_size); - ASSERT_EQ(r_num_mss, variant->r_num_mss); + EXPECT_EQ(ret, variant->data_size); + EXPECT_EQ(r_num_mss, variant->r_num_mss); } TEST_F(tun_vnet_udptnl, recv_gso_packet) @@ -955,18 +955,18 @@ TEST_F(tun_vnet_udptnl, recv_gso_packet) int ret, gso_type = VIRTIO_NET_HDR_GSO_UDP_L4; ret = send_gso_packet_into_tunnel(self, variant); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); memset(&vnet_hdr, 0, sizeof(vnet_hdr)); ret = receive_gso_packet_from_tun(self, variant, &vnet_hdr); - ASSERT_EQ(ret, variant->data_size); + EXPECT_EQ(ret, variant->data_size); if (!variant->no_gso) { - ASSERT_EQ(vh->gso_size, variant->gso_size); + EXPECT_EQ(vh->gso_size, variant->gso_size); gso_type |= (variant->tunnel_type & UDP_TUNNEL_OUTER_IPV4) ? (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4) : (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6); - ASSERT_EQ(vh->gso_type, gso_type); + EXPECT_EQ(vh->gso_type, gso_type); } } diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile index 2c601a7eaff5..006300ac6dff 100644 --- a/tools/testing/selftests/sched_ext/Makefile +++ b/tools/testing/selftests/sched_ext/Makefile @@ -93,6 +93,8 @@ BPF_CFLAGS = -g -D__TARGET_ARCH_$(SRCARCH) \ $(CLANG_SYS_INCLUDES) \ -Wall -Wno-compare-distinct-pointer-types \ -Wno-incompatible-function-pointer-types \ + -Wno-microsoft-anon-tag \ + -fms-extensions \ -O2 -mcpu=v3 # sort removes libbpf duplicates when not cross-building diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index 82c71653977b..44577e30e764 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -57,7 +57,8 @@ static enum scx_test_status run_test(bool global) char buf; close(pipe_fds[1]); - read(pipe_fds[0], &buf, 1); + if (read(pipe_fds[0], &buf, 1) < 0) + exit(1); close(pipe_fds[0]); exit(0); } diff --git a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c index a3faf5bb49d6..784f2f6c1af9 100644 --- a/tools/testing/selftests/sched_ext/peek_dsq.bpf.c +++ b/tools/testing/selftests/sched_ext/peek_dsq.bpf.c @@ -58,14 +58,14 @@ static void record_peek_result(long pid) { u32 slot_key; long *slot_pid_ptr; - int ix; + u32 ix; if (pid <= 0) return; /* Find an empty slot or one with the same PID */ bpf_for(ix, 0, 10) { - slot_key = (pid + ix) % MAX_SAMPLES; + slot_key = ((u64)pid + ix) % MAX_SAMPLES; slot_pid_ptr = bpf_map_lookup_elem(&peek_results, &slot_key); if (!slot_pid_ptr) continue; diff --git a/tools/testing/selftests/sched_ext/rt_stall.c b/tools/testing/selftests/sched_ext/rt_stall.c index ab772e336f86..81ea9b4883e5 100644 --- a/tools/testing/selftests/sched_ext/rt_stall.c +++ b/tools/testing/selftests/sched_ext/rt_stall.c @@ -15,7 +15,6 @@ #include <signal.h> #include <bpf/bpf.h> #include <scx/common.h> -#include <unistd.h> #include "rt_stall.bpf.skel.h" #include "scx_test.h" #include "../kselftest.h" diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c index 5748d2c69903..761c21f96404 100644 --- a/tools/testing/selftests/sched_ext/runner.c +++ b/tools/testing/selftests/sched_ext/runner.c @@ -166,6 +166,9 @@ int main(int argc, char **argv) enum scx_test_status status; struct scx_test *test = &__scx_tests[i]; + if (exit_req) + break; + if (list) { printf("%s\n", test->name); if (i == (__scx_num_tests - 1)) diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json index 7d07c55bb668..33bb8f3ff8ed 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ct.json @@ -505,5 +505,164 @@ "teardown": [ "$TC qdisc del dev $DEV1 ingress" ] + }, + { + "id": "8883", + "name": "Try to attach act_ct to an ets qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 root handle 1: ets bands 2" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 parent 1: prio 1 protocol ip matchall action ct index 42", + "expExitCode": "2", + "verifyCmd": "$TC -j filter ls dev $DEV1 parent 1: prio 1 protocol ip", + "matchJSON": [], + "teardown": [ + "$TC qdisc del dev $DEV1 root" + ] + }, + { + "id": "3b10", + "name": "Attach act_ct to an ingress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 ingress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 ingress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress" + ] + }, + { + "id": "0337", + "name": "Attach act_ct to a clsact/egress qdisc", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 clsact" + ], + "cmdUnderTest": "$TC filter add dev $DEV1 egress prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls dev $DEV1 egress prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 clsact" + ] + }, + { + "id": "4f60", + "name": "Attach act_ct to a shared block", + "category": [ + "actions", + "ct" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ct", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress_block 21 clsact" + ], + "cmdUnderTest": "$TC filter add block 21 prio 1 protocol ip matchall action ct index 42", + "expExitCode": "0", + "verifyCmd": "$TC -j filter ls block 21 prio 1 protocol ip", + "matchJSON": [ + { + "kind": "matchall" + }, + { + "options": { + "actions": [ + { + "order": 1, + "kind": "ct", + "index": 42, + "ref": 1, + "bind": 1 + } + ] + } + } + ], + "teardown": [ + "$TC qdisc del dev $DEV1 ingress_block 21 clsact" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index f587a32e44c4..808aef4afe22 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1279,5 +1279,104 @@ "teardown": [ "$TC actions flush action ife" ] + }, + { + "id": "f2a0", + "name": "Update decode ife action with encode metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d352", + "name": "Update decode ife action into encode with multiple metadata", + "category": [ + "actions", + "ife" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ], + "$TC actions add action ife decode index 10" + ], + "cmdUnderTest": "$TC actions replace action ife encode use tcindex 1 use mark 22 index 10", + "expExitCode": "0", + "verifyCmd": "$TC -j actions get action ife index 10", + "matchJSON": [ + { + "total acts": 0 + }, + { + "actions": [ + { + "order": 1, + "kind": "ife", + "mode": "encode", + "control_action": { + "type": "pipe" + }, + "type": "0xed3e", + "tcindex": 1, + "mark": 22, + "index": 10, + "ref": 1, + "bind": 0, + "not_in_hw": true + } + ] + } + ], + "teardown": [ + "$TC actions flush action ife" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tdc_helper.py b/tools/testing/selftests/tc-testing/tdc_helper.py index e06f03c0fb5d..adb52fe3acc1 100644 --- a/tools/testing/selftests/tc-testing/tdc_helper.py +++ b/tools/testing/selftests/tc-testing/tdc_helper.py @@ -38,10 +38,14 @@ def list_test_cases(testlist): def list_categories(testlist): - """ Show all categories that are present in a test case file. """ - categories = set(map(lambda x: x['category'], testlist)) + """Show all unique categories present in the test cases.""" + categories = set() + for t in testlist: + if 'category' in t: + categories.update(t['category']) + print("Available categories:") - print(", ".join(str(s) for s in categories)) + print(", ".join(sorted(categories))) print("") diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 267c7369c765..794976b88c6f 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -5,6 +5,7 @@ config KVM_COMMON bool select EVENTFD select INTERVAL_TREE + select MMU_NOTIFIER select PREEMPT_NOTIFIERS config HAVE_KVM_PFNCACHE @@ -93,24 +94,16 @@ config HAVE_KVM_PM_NOTIFIER config KVM_GENERIC_HARDWARE_ENABLING bool -config KVM_GENERIC_MMU_NOTIFIER - select MMU_NOTIFIER - bool - config KVM_ELIDE_TLB_FLUSH_IF_YOUNG - depends on KVM_GENERIC_MMU_NOTIFIER bool config KVM_MMU_LOCKLESS_AGING - depends on KVM_GENERIC_MMU_NOTIFIER bool config KVM_GENERIC_MEMORY_ATTRIBUTES - depends on KVM_GENERIC_MMU_NOTIFIER bool config KVM_GUEST_MEMFD - depends on KVM_GENERIC_MMU_NOTIFIER select XARRAY_MULTI bool diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 22f8a672e1fd..1bc1da66b4b0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -502,7 +502,6 @@ void kvm_destroy_vcpus(struct kvm *kvm) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_destroy_vcpus); -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) { return container_of(mn, struct kvm, mmu_notifier); @@ -901,15 +900,6 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) return mmu_notifier_register(&kvm->mmu_notifier, current->mm); } -#else /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */ - -static int kvm_init_mmu_notifier(struct kvm *kvm) -{ - return 0; -} - -#endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */ - #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_pm_notifier_call(struct notifier_block *bl, unsigned long state, @@ -1226,10 +1216,8 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) out_err_no_debugfs: kvm_coalesced_mmio_free(kvm); out_no_coalesced_mmio: -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER if (kvm->mmu_notifier.ops) mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); -#endif out_err_no_mmu_notifier: kvm_disable_virtualization(); out_err_no_disable: @@ -1292,7 +1280,6 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); -#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); /* * At this point, pending calls to invalidate_range_start() @@ -1311,9 +1298,6 @@ static void kvm_destroy_vm(struct kvm *kvm) kvm->mn_active_invalidate_count = 0; else WARN_ON(kvm->mmu_invalidate_in_progress); -#else - kvm_flush_shadow_all(kvm); -#endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { @@ -4886,6 +4870,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) { switch (arg) { + case KVM_CAP_SYNC_MMU: case KVM_CAP_USER_MEMORY: case KVM_CAP_USER_MEMORY2: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: |