diff --git a/.mailmap b/.mailmap index bd6a72f29d9c..99dba08041fa 100644 --- a/.mailmap +++ b/.mailmap @@ -584,6 +584,8 @@ Mayuresh Janorkar Md Sadre Alam Miaoqing Pan Michael Buesch +Michal Grzeschik +Michal Grzeschik Michael Riesch Michal Simek Michel Dänzer diff --git a/Documentation/.renames.txt b/Documentation/.renames.txt index 43d44753ab93..aa7e5aa4a81b 100644 --- a/Documentation/.renames.txt +++ b/Documentation/.renames.txt @@ -786,6 +786,7 @@ networking/altera_tse networking/device_drivers/ethernet/altera/altera_tse networking/bpf_flow_dissector bpf/prog_flow_dissector networking/cxacru networking/device_drivers/atm/cxacru networking/defza networking/device_drivers/fddi/defza +networking/device_drivers/3com/3c509 networking/device_drivers/ethernet/3com/3c509 networking/device_drivers/3com/vortex networking/device_drivers/ethernet/3com/vortex networking/device_drivers/amazon/ena networking/device_drivers/ethernet/amazon/ena networking/device_drivers/aquantia/atlantic networking/device_drivers/ethernet/aquantia/atlantic diff --git a/Documentation/crypto/krb5.rst b/Documentation/crypto/krb5.rst index beffa0133446..f62e07ac6811 100644 --- a/Documentation/crypto/krb5.rst +++ b/Documentation/crypto/krb5.rst @@ -158,13 +158,22 @@ returned. When a message has been received, the location and size of the data with the message can be determined by calling:: - void crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, - enum krb5_crypto_mode mode, - size_t *_offset, size_t *_len); + int crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t *_offset, size_t *_len); The caller provides the offset and length of the message to the function, which then alters those values to indicate the region containing the data (plus any -padding). It is up to the caller to determine how much padding there is. +padding). It is up to the caller to determine how much padding there is. The +function returns an error if the length is too small or if the mode is +unsupported. An additional function:: + + int crypto_krb5_check_data_len(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t len, size_t min_content); + +is provided to just do a basic check that the decrypted/verified message would +have a sufficient minimum payload. Preparation Functions --------------------- diff --git a/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml b/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml index 91e8cd1db67b..b66ae6300faf 100644 --- a/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml +++ b/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml @@ -73,6 +73,15 @@ properties: HSP CSR is to control and get status of different high-speed peripherals (such as Ethernet, USB, SATA, etc.) via register, which can tune board-level's parameters of PHY, etc. + + Additional background information about the High-Speed Subsystem + and the HSP CSR block is available in Chapter 10 ("High-Speed Interface") + of the EIC7700X SoC Technical Reference Manual, Part 4 + (EIC7700X_SoC_Technical_Reference_Manual_Part4.pdf). The manual is + publicly available at + https://github.com/eswincomputing/EIC7700X-SoC-Technical-Reference-Manual/releases + + This reference is provided for background information only. $ref: /schemas/types.yaml#/definitions/phandle-array items: - items: @@ -82,6 +91,8 @@ properties: - description: Offset of AXI clock controller Low-Power request register - description: Offset of register controlling TX/RX clock delay + - description: Optional offset of register controlling TXD delay + - description: Optional offset of register controlling RXD delay required: - compatible @@ -116,7 +127,7 @@ examples: reset-names = "stmmaceth"; rx-internal-delay-ps = <200>; tx-internal-delay-ps = <200>; - eswin,hsp-sp-csr = <&hsp_sp_csr 0x100 0x108 0x118>; + eswin,hsp-sp-csr = <&hsp_sp_csr 0x100 0x108 0x118 0x114 0x11c>; snps,axi-config = <&stmmac_axi_setup>; snps,aal; snps,fixed-burst; diff --git a/Documentation/networking/device_drivers/ethernet/3com/3c509.rst b/Documentation/networking/device_drivers/ethernet/3com/3c509.rst new file mode 100644 index 000000000000..a8c5e5e6841d --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/3com/3c509.rst @@ -0,0 +1,249 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================================================================= +Linux and the 3Com EtherLink III Series Ethercards (driver v1.18c and higher) +============================================================================= + +This file contains the instructions and caveats for v1.18c and higher versions +of the 3c509 driver. You should not use the driver without reading this file. + +release 1.0 + +28 February 2002 + +Current maintainer (corrections to): + Maciej W. Rozycki + +Introduction +============ + +The following are notes and information on using the 3Com EtherLink III series +ethercards in Linux. These cards are commonly known by the most widely-used +card's 3Com model number, 3c509. They are all 10mb/s ISA-bus cards and shouldn't +be (but sometimes are) confused with the similarly-numbered PCI-bus "3c905" +(aka "Vortex" or "Boomerang") series. Kernel support for the 3c509 family is +provided by the module 3c509.c, which has code to support all of the following +models: + + - 3c509 (original ISA card) + - 3c509B (later revision of the ISA card; supports full-duplex) + - 3c589 (PCMCIA) + - 3c589B (later revision of the 3c589; supports full-duplex) + - 3c579 (EISA) + +Large portions of this documentation were heavily borrowed from the guide +written the original author of the 3c509 driver, Donald Becker. The master +copy of that document, which contains notes on older versions of the driver, +currently resides on Scyld web server: http://www.scyld.com/. + + +Special Driver Features +======================= + +Overriding card settings + +The driver allows boot- or load-time overriding of the card's detected IOADDR, +IRQ, and transceiver settings, although this capability shouldn't generally be +needed except to enable full-duplex mode (see below). An example of the syntax +for LILO parameters for doing this:: + + ether=10,0x310,3,0x3c509,eth0 + +This configures the first found 3c509 card for IRQ 10, base I/O 0x310, and +transceiver type 3 (10base2). The flag "0x3c509" must be set to avoid conflicts +with other card types when overriding the I/O address. When the driver is +loaded as a module, only the IRQ may be overridden. For example, +setting two cards to IRQ10 and IRQ11 is done by using the irq module +option:: + + options 3c509 irq=10,11 + + +Full-duplex mode +================ + +The v1.18c driver added support for the 3c509B's full-duplex capabilities. +In order to enable and successfully use full-duplex mode, three conditions +must be met: + +(a) You must have a Etherlink III card model whose hardware supports full- +duplex operations. Currently, the only members of the 3c509 family that are +positively known to support full-duplex are the 3c509B (ISA bus) and 3c589B +(PCMCIA) cards. Cards without the "B" model designation do *not* support +full-duplex mode; these include the original 3c509 (no "B"), the original +3c589, the 3c529 (MCA bus), and the 3c579 (EISA bus). + +(b) You must be using your card's 10baseT transceiver (i.e., the RJ-45 +connector), not its AUI (thick-net) or 10base2 (thin-net/coax) interfaces. +AUI and 10base2 network cabling is physically incapable of full-duplex +operation. + +(c) Most importantly, your 3c509B must be connected to a link partner that is +itself full-duplex capable. This is almost certainly one of two things: a full- +duplex-capable Ethernet switch (*not* a hub), or a full-duplex-capable NIC on +another system that's connected directly to the 3c509B via a crossover cable. + +Full-duplex mode can be enabled using 'ethtool'. + +.. warning:: + + Extremely important caution concerning full-duplex mode + + Understand that the 3c509B's hardware's full-duplex support is much more + limited than that provide by more modern network interface cards. Although + at the physical layer of the network it fully supports full-duplex operation, + the card was designed before the current Ethernet auto-negotiation (N-way) + spec was written. This means that the 3c509B family ***cannot and will not + auto-negotiate a full-duplex connection with its link partner under any + circumstances, no matter how it is initialized***. If the full-duplex mode + of the 3c509B is enabled, its link partner will very likely need to be + independently _forced_ into full-duplex mode as well; otherwise various nasty + failures will occur - at the very least, you'll see massive numbers of packet + collisions. This is one of very rare circumstances where disabling auto- + negotiation and forcing the duplex mode of a network interface card or switch + would ever be necessary or desirable. + + +Available Transceiver Types +=========================== + +For versions of the driver v1.18c and above, the available transceiver types are: + +== ========================================================================= +0 transceiver type from EEPROM config (normally 10baseT); force half-duplex +1 AUI (thick-net / DB15 connector) +2 (undefined) +3 10base2 (thin-net == coax / BNC connector) +4 10baseT (RJ-45 connector); force half-duplex mode +8 transceiver type and duplex mode taken from card's EEPROM config settings +12 10baseT (RJ-45 connector); force full-duplex mode +== ========================================================================= + +Prior to driver version 1.18c, only transceiver codes 0-4 were supported. Note +that the new transceiver codes 8 and 12 are the *only* ones that will enable +full-duplex mode, no matter what the card's detected EEPROM settings might be. +This insured that merely upgrading the driver from an earlier version would +never automatically enable full-duplex mode in an existing installation; +it must always be explicitly enabled via one of these code in order to be +activated. + +The transceiver type can be changed using 'ethtool'. + + +Interpretation of error messages and common problems +---------------------------------------------------- + +Error Messages +^^^^^^^^^^^^^^ + +eth0: Infinite loop in interrupt, status 2011. +These are "mostly harmless" message indicating that the driver had too much +work during that interrupt cycle. With a status of 0x2011 you are receiving +packets faster than they can be removed from the card. This should be rare +or impossible in normal operation. Possible causes of this error report are: + + - a "green" mode enabled that slows the processor down when there is no + keyboard activity. + + - some other device or device driver hogging the bus or disabling interrupts. + Check /proc/interrupts for excessive interrupt counts. The timer tick + interrupt should always be incrementing faster than the others. + +No received packets +^^^^^^^^^^^^^^^^^^^ + +If a 3c509, 3c562 or 3c589 can successfully transmit packets, but never +receives packets (as reported by /proc/net/dev or 'ifconfig') you likely +have an interrupt line problem. Check /proc/interrupts to verify that the +card is actually generating interrupts. If the interrupt count is not +increasing you likely have a physical conflict with two devices trying to +use the same ISA IRQ line. The common conflict is with a sound card on IRQ10 +or IRQ5, and the easiest solution is to move the 3c509 to a different +interrupt line. If the device is receiving packets but 'ping' doesn't work, +you have a routing problem. + +Tx Carrier Errors Reported in /proc/net/dev +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + + +If an EtherLink III appears to transmit packets, but the "Tx carrier errors" +field in /proc/net/dev increments as quickly as the Tx packet count, you +likely have an unterminated network or the incorrect media transceiver selected. + +3c509B card is not detected on machines with an ISA PnP BIOS. +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +While the updated driver works with most PnP BIOS programs, it does not work +with all. This can be fixed by disabling PnP support using the 3Com-supplied +setup program. + +3c509 card is not detected on overclocked machines +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Increase the delay time in id_read_eeprom() from the current value, 500, +to an absurdly high value, such as 5000. + + +Decoding Status and Error Messages +---------------------------------- + + +The bits in the main status register are: + +===== ====================================== +value description +===== ====================================== +0x01 Interrupt latch +0x02 Tx overrun, or Rx underrun +0x04 Tx complete +0x08 Tx FIFO room available +0x10 A complete Rx packet has arrived +0x20 A Rx packet has started to arrive +0x40 The driver has requested an interrupt +0x80 Statistics counter nearly full +===== ====================================== + +The bits in the transmit (Tx) status word are: + +===== ============================================ +value description +===== ============================================ +0x02 Out-of-window collision. +0x04 Status stack overflow (normally impossible). +0x08 16 collisions. +0x10 Tx underrun (not enough PCI bus bandwidth). +0x20 Tx jabber. +0x40 Tx interrupt requested. +0x80 Status is valid (this should always be set). +===== ============================================ + + +When a transmit error occurs the driver produces a status message such as:: + + eth0: Transmit error, Tx status register 82 + +The two values typically seen here are: + +0x82 +^^^^ + +Out of window collision. This typically occurs when some other Ethernet +host is incorrectly set to full duplex on a half duplex network. + +0x88 +^^^^ + +16 collisions. This typically occurs when the network is exceptionally busy +or when another host doesn't correctly back off after a collision. If this +error is mixed with 0x82 errors it is the result of a host incorrectly set +to full duplex (see above). + +Both of these errors are the result of network problems that should be +corrected. They do not represent driver malfunction. + + +Revision history (this file) +============================ + +28Feb02 v1.0 DR New; major portions based on Becker original 3c509 docs + diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst index 64621c21fd78..1d25be493ae9 100644 --- a/Documentation/networking/device_drivers/ethernet/index.rst +++ b/Documentation/networking/device_drivers/ethernet/index.rst @@ -10,6 +10,7 @@ Contents: .. toctree:: :maxdepth: 2 + 3com/3c509 3com/vortex amazon/ena altera/altera_tse diff --git a/MAINTAINERS b/MAINTAINERS index c2c6d79275c6..8d173418d483 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2064,7 +2064,7 @@ F: Documentation/devicetree/bindings/display/snps,arcpgu.txt F: drivers/gpu/drm/tiny/arcpgu.c ARCNET NETWORK LAYER -M: Michael Grzeschik +M: Michael Grzeschik L: netdev@vger.kernel.org S: Maintained F: drivers/net/arcnet/ @@ -3367,7 +3367,9 @@ F: drivers/irqchip/irq-rda-intc.c F: drivers/tty/serial/rda-uart.c ARM/REALTEK ARCHITECTURE -M: Andreas Färber +M: James Tai +M: Yu-Chun Lin +R: Andreas Färber L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-realtek-soc@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -3375,6 +3377,7 @@ F: Documentation/devicetree/bindings/arm/realtek.yaml F: arch/arm/boot/dts/realtek/ F: arch/arm/mach-realtek/ F: arch/arm64/boot/dts/realtek/ +F: drivers/pinctrl/realtek/ ARM/RISC-V/RENESAS ARCHITECTURE M: Geert Uytterhoeven @@ -13869,6 +13872,7 @@ M: Pratyush Yadav R: Dave Young L: kexec@lists.infradead.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/liveupdate/linux.git F: Documentation/admin-guide/kdump/ F: fs/proc/vmcore.c F: include/linux/crash_core.h @@ -14186,6 +14190,7 @@ M: Pasha Tatashin M: Pratyush Yadav L: kexec@lists.infradead.org W: http://kernel.org/pub/linux/utils/kernel/kexec/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/liveupdate/linux.git F: include/linux/kexec.h F: include/uapi/linux/kexec.h F: kernel/kexec* @@ -14902,6 +14907,7 @@ LIVE UPDATE M: Pasha Tatashin M: Mike Rapoport M: Pratyush Yadav +L: kexec@lists.infradead.org L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/liveupdate/linux.git @@ -18632,6 +18638,7 @@ F: tools/testing/selftests/net/ X: Documentation/networking/mac80211-injection.rst X: Documentation/networking/mac80211_hwsim/ X: Documentation/networking/regulatory.rst +X: include/net/bluetooth/ X: include/net/cfg80211.h X: include/net/ieee80211_radiotap.h X: include/net/iw_handler.h @@ -20737,15 +20744,13 @@ F: Documentation/devicetree/bindings/pci/intel,keembay-pcie* F: drivers/pci/controller/dwc/pcie-keembay.c PCIE DRIVER FOR INTEL LGM GW SOC -M: Chuanhua Lei L: linux-pci@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/devicetree/bindings/pci/intel-gw-pcie.yaml F: drivers/pci/controller/dwc/pcie-intel-gw.c PCIE DRIVER FOR MEDIATEK M: Ryder Lee -M: Jianjun Wang L: linux-pci@vger.kernel.org L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) S: Supported diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild index 483965c5a4de..b154b4e3dfa8 100644 --- a/arch/alpha/include/asm/Kbuild +++ b/arch/alpha/include/asm/Kbuild @@ -5,4 +5,5 @@ generic-y += agp.h generic-y += asm-offsets.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild index 4c69522e0328..483caacc6988 100644 --- a/arch/arc/include/asm/Kbuild +++ b/arch/arc/include/asm/Kbuild @@ -5,5 +5,6 @@ generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += user.h generic-y += text-patching.h diff --git a/arch/arm/boot/dts/renesas/r7s72100-genmai.dts b/arch/arm/boot/dts/renesas/r7s72100-genmai.dts index 3c3756509714..da552a66615e 100644 --- a/arch/arm/boot/dts/renesas/r7s72100-genmai.dts +++ b/arch/arm/boot/dts/renesas/r7s72100-genmai.dts @@ -34,9 +34,6 @@ flash@18000000 { clocks = <&mstp9_clks R7S72100_CLK_SPIBSC0>; power-domains = <&cpg_clocks>; - #address-cells = <1>; - #size-cells = <1>; - partitions { compatible = "fixed-partitions"; #address-cells = <1>; diff --git a/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts b/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts index 91178fb9e721..3306bc9b7bc3 100644 --- a/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts +++ b/arch/arm/boot/dts/renesas/r7s72100-rskrza1.dts @@ -36,8 +36,6 @@ flash@18000000 { power-domains = <&cpg_clocks>; bank-width = <4>; device-width = <1>; - #address-cells = <1>; - #size-cells = <1>; partitions { compatible = "fixed-partitions"; diff --git a/arch/arm/boot/dts/renesas/r7s72100.dtsi b/arch/arm/boot/dts/renesas/r7s72100.dtsi index 245c26bb8e03..6ec57ffa72e8 100644 --- a/arch/arm/boot/dts/renesas/r7s72100.dtsi +++ b/arch/arm/boot/dts/renesas/r7s72100.dtsi @@ -37,7 +37,7 @@ b_clk: b { clock-div = <3>; }; - bsc: bus { + bsc: bus@0 { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/renesas/r8a7778.dtsi b/arch/arm/boot/dts/renesas/r8a7778.dtsi index 859dd29dfce3..7db456b19795 100644 --- a/arch/arm/boot/dts/renesas/r8a7778.dtsi +++ b/arch/arm/boot/dts/renesas/r8a7778.dtsi @@ -40,7 +40,7 @@ aliases { spi2 = &hspi2; }; - lbsc: bus { + lbsc: bus@0 { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/renesas/r8a7779.dtsi b/arch/arm/boot/dts/renesas/r8a7779.dtsi index e437c22f452d..9e8a7e190c89 100644 --- a/arch/arm/boot/dts/renesas/r8a7779.dtsi +++ b/arch/arm/boot/dts/renesas/r8a7779.dtsi @@ -704,7 +704,7 @@ R8A7779_CLK_MMC1 R8A7779_CLK_MMC0 }; }; - lbsc: bus { + lbsc: bus@0 { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/renesas/r8a7792.dtsi b/arch/arm/boot/dts/renesas/r8a7792.dtsi index 9e0de69ac3a3..fbdbcff1cbed 100644 --- a/arch/arm/boot/dts/renesas/r8a7792.dtsi +++ b/arch/arm/boot/dts/renesas/r8a7792.dtsi @@ -86,7 +86,7 @@ extal_clk: extal { bootph-all; }; - lbsc: bus { + lbsc: bus@0 { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index 03657ff8fbe3..decad5f2c826 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += early_ioremap.h generic-y += extable.h generic-y += flat.h generic-y += parport.h +generic-y += ring_buffer.h generated-y += mach-types.h generated-y += unistd-nr.h diff --git a/arch/arm/mach-versatile/integrator_cp.c b/arch/arm/mach-versatile/integrator_cp.c index 2ed4ded56b3f..03dfb5f720b7 100644 --- a/arch/arm/mach-versatile/integrator_cp.c +++ b/arch/arm/mach-versatile/integrator_cp.c @@ -86,14 +86,6 @@ static u64 notrace intcp_read_sched_clock(void) return val; } -static void __init intcp_init_early(void) -{ - cm_map = syscon_regmap_lookup_by_compatible("arm,core-module-integrator"); - if (IS_ERR(cm_map)) - return; - sched_clock_register(intcp_read_sched_clock, 32, 24000000); -} - static void __init intcp_init_irq_of(void) { cm_init(); @@ -119,6 +111,10 @@ static void __init intcp_init_of(void) { struct device_node *cpcon; + cm_map = syscon_regmap_lookup_by_compatible("arm,core-module-integrator"); + if (!IS_ERR(cm_map)) + sched_clock_register(intcp_read_sched_clock, 32, 24000000); + cpcon = of_find_matching_node(NULL, intcp_syscon_match); if (!cpcon) return; @@ -138,7 +134,6 @@ static const char * intcp_dt_board_compat[] = { DT_MACHINE_START(INTEGRATOR_CP_DT, "ARM Integrator/CP (Device Tree)") .reserve = integrator_reserve, .map_io = intcp_map_io, - .init_early = intcp_init_early, .init_irq = intcp_init_irq_of, .init_machine = intcp_init_of, .dt_compat = intcp_dt_board_compat, diff --git a/arch/arm64/boot/dts/renesas/draak-ebisu-panel-aa104xd12.dtso b/arch/arm64/boot/dts/renesas/draak-ebisu-panel-aa104xd12.dtso index 258f8668ca36..90767d74e21b 100644 --- a/arch/arm64/boot/dts/renesas/draak-ebisu-panel-aa104xd12.dtso +++ b/arch/arm64/boot/dts/renesas/draak-ebisu-panel-aa104xd12.dtso @@ -27,7 +27,12 @@ &lvds1 { status = "okay"; ports { + #address-cells = <1>; + #size-cells = <0>; + port@1 { + reg = <1>; + lvds1_out: endpoint { remote-endpoint = <&panel_in>; }; diff --git a/arch/arm64/boot/dts/renesas/r8a78000.dtsi b/arch/arm64/boot/dts/renesas/r8a78000.dtsi index 3e1c98903cea..3ec1b53d2782 100644 --- a/arch/arm64/boot/dts/renesas/r8a78000.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a78000.dtsi @@ -699,7 +699,7 @@ scif0: serial@c0700000 { "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0700000 0 0x40>; interrupts = ; - clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; + clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; }; @@ -709,7 +709,7 @@ scif1: serial@c0704000 { "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0704000 0 0x40>; interrupts = ; - clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; + clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; }; @@ -719,7 +719,7 @@ scif3: serial@c0708000 { "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc0708000 0 0x40>; interrupts = ; - clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; + clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; }; @@ -729,7 +729,7 @@ scif4: serial@c070c000 { "renesas,rcar-gen5-scif", "renesas,scif"; reg = <0 0xc070c000 0 0x40>; interrupts = ; - clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd16>, <&scif_clk>; + clocks = <&dummy_clk_sgasyncd16>, <&dummy_clk_sgasyncd4>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/renesas/r9a09g056.dtsi b/arch/arm64/boot/dts/renesas/r9a09g056.dtsi index 40525470194e..7ccddd6a4a9a 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g056.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g056.dtsi @@ -1327,6 +1327,7 @@ usb20phyrst: usb20phy-reset@15830000 { resets = <&cpg 0xaf>; power-domains = <&cpg>; #reset-cells = <0>; + #mux-state-cells = <1>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi index 9581af58024e..6f6fe5f36bef 100644 --- a/arch/arm64/boot/dts/renesas/r9a09g057.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a09g057.dtsi @@ -1345,6 +1345,7 @@ usb20phyrst: usb20phy-reset@15830000 { resets = <&cpg 0xaf>; power-domains = <&cpg>; #reset-cells = <0>; + #mux-state-cells = <1>; status = "disabled"; }; @@ -1355,6 +1356,7 @@ usb21phyrst: usb21phy-reset@15840000 { resets = <&cpg 0xaf>; power-domains = <&cpg>; #reset-cells = <0>; + #mux-state-cells = <1>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/renesas/rz-smarc-cru-csi-ov5645.dtsi b/arch/arm64/boot/dts/renesas/rz-smarc-cru-csi-ov5645.dtsi index 4d2b0655859a..3feffa4f16a9 100644 --- a/arch/arm64/boot/dts/renesas/rz-smarc-cru-csi-ov5645.dtsi +++ b/arch/arm64/boot/dts/renesas/rz-smarc-cru-csi-ov5645.dtsi @@ -46,7 +46,12 @@ &csi2 { status = "okay"; ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + csi2_in: endpoint { clock-lanes = <0>; data-lanes = <1 2>; diff --git a/arch/arm64/boot/dts/renesas/rz-smarc-du-adv7513.dtsi b/arch/arm64/boot/dts/renesas/rz-smarc-du-adv7513.dtsi index 36707576030d..f5412578ee65 100644 --- a/arch/arm64/boot/dts/renesas/rz-smarc-du-adv7513.dtsi +++ b/arch/arm64/boot/dts/renesas/rz-smarc-du-adv7513.dtsi @@ -26,7 +26,12 @@ &du { status = "okay"; ports { + #address-cells = <1>; + #size-cells = <0>; + port@0 { + reg = <0>; + du_out_rgb: endpoint { remote-endpoint = <&adv7513_in>; }; diff --git a/arch/arm64/boot/dts/renesas/salvator-panel-aa104xd12.dtso b/arch/arm64/boot/dts/renesas/salvator-panel-aa104xd12.dtso index c83a30adc6ad..7807c3f80409 100644 --- a/arch/arm64/boot/dts/renesas/salvator-panel-aa104xd12.dtso +++ b/arch/arm64/boot/dts/renesas/salvator-panel-aa104xd12.dtso @@ -27,7 +27,12 @@ &lvds0 { status = "okay"; ports { + #address-cells = <1>; + #size-cells = <0>; + port@1 { + reg = <1>; + lvds0_out: endpoint { remote-endpoint = <&panel_in>; }; diff --git a/arch/arm64/include/asm/page.h b/arch/arm64/include/asm/page.h index e25d0d18f6d7..58200de8a221 100644 --- a/arch/arm64/include/asm/page.h +++ b/arch/arm64/include/asm/page.h @@ -33,7 +33,7 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr); #define vma_alloc_zeroed_movable_folio vma_alloc_zeroed_movable_folio -bool tag_clear_highpages(struct page *to, int numpages); +bool tag_clear_highpages(struct page *to, int numpages, bool clear_pages); #define __HAVE_ARCH_TAG_CLEAR_HIGHPAGES #define copy_user_page(to, from, vaddr, pg) copy_page(to, from) diff --git a/arch/arm64/include/asm/ring_buffer.h b/arch/arm64/include/asm/ring_buffer.h new file mode 100644 index 000000000000..62316c406888 --- /dev/null +++ b/arch/arm64/include/asm/ring_buffer.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_ARM64_RING_BUFFER_H +#define _ASM_ARM64_RING_BUFFER_H + +#include + +/* Flush D-cache on persistent ring buffer */ +#define arch_ring_buffer_flush_range(start, end) dcache_clean_pop(start, end) + +#endif /* _ASM_ARM64_RING_BUFFER_H */ diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 0f3c5c7ca054..739800835920 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -1018,7 +1018,7 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, return vma_alloc_folio(flags, 0, vma, vaddr); } -bool tag_clear_highpages(struct page *page, int numpages) +bool tag_clear_highpages(struct page *page, int numpages, bool clear_pages) { /* * Check if MTE is supported and fall back to clear_highpage(). @@ -1026,13 +1026,16 @@ bool tag_clear_highpages(struct page *page, int numpages) * post_alloc_hook() will invoke tag_clear_highpages(). */ if (!system_supports_mte()) - return false; + return clear_pages; /* Newly allocated pages, shouldn't have been tagged yet */ for (int i = 0; i < numpages; i++, page++) { WARN_ON_ONCE(!try_page_mte_tagging(page)); - mte_zero_clear_page_tags(page_address(page)); + if (clear_pages) + mte_zero_clear_page_tags(page_address(page)); + else + mte_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } - return true; + return false; } diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild index 3a5c7f6e5aac..7dca0c6cdc84 100644 --- a/arch/csky/include/asm/Kbuild +++ b/arch/csky/include/asm/Kbuild @@ -9,6 +9,7 @@ generic-y += qrwlock.h generic-y += qrwlock_types.h generic-y += qspinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += user.h generic-y += vmlinux.lds.h generic-y += text-patching.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 1efa1e993d4b..0f887d4238ed 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -5,4 +5,5 @@ generic-y += extable.h generic-y += iomap.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/loongarch/include/asm/Kbuild b/arch/loongarch/include/asm/Kbuild index 9034b583a88a..7e92957baf6a 100644 --- a/arch/loongarch/include/asm/Kbuild +++ b/arch/loongarch/include/asm/Kbuild @@ -10,5 +10,6 @@ generic-y += qrwlock.h generic-y += user.h generic-y += ioctl.h generic-y += mmzone.h +generic-y += ring_buffer.h generic-y += statfs.h generic-y += text-patching.h diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index b282e0dd8dc1..62543bf305ff 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -3,5 +3,6 @@ generated-y += syscall_table.h generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += spinlock.h generic-y += text-patching.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 7178f990e8b3..0030309b47ad 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -5,6 +5,7 @@ generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += syscalls.h generic-y += tlb.h generic-y += user.h diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild index 684569b2ecd6..9771c3d85074 100644 --- a/arch/mips/include/asm/Kbuild +++ b/arch/mips/include/asm/Kbuild @@ -12,5 +12,6 @@ generic-y += mcs_spinlock.h generic-y += parport.h generic-y += qrwlock.h generic-y += qspinlock.h +generic-y += ring_buffer.h generic-y += user.h generic-y += text-patching.h diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild index 28004301c236..0a2530964413 100644 --- a/arch/nios2/include/asm/Kbuild +++ b/arch/nios2/include/asm/Kbuild @@ -5,6 +5,7 @@ generic-y += cmpxchg.h generic-y += extable.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += spinlock.h generic-y += user.h generic-y += text-patching.h diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index cef49d60d74c..8aa34621702d 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -8,4 +8,5 @@ generic-y += spinlock_types.h generic-y += spinlock.h generic-y += qrwlock_types.h generic-y += qrwlock.h +generic-y += ring_buffer.h generic-y += user.h diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild index 4fb596d94c89..d48d158f7241 100644 --- a/arch/parisc/include/asm/Kbuild +++ b/arch/parisc/include/asm/Kbuild @@ -4,4 +4,5 @@ generated-y += syscall_table_64.h generic-y += agp.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += user.h diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index ccabc6e17168..eda1fec7ffd9 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -393,6 +393,7 @@ CONFIG_NETCONSOLE=m CONFIG_TUN=m CONFIG_VETH=m CONFIG_VIRTIO_NET=m +CONFIG_EL3=m CONFIG_VORTEX=m CONFIG_TYPHOON=m CONFIG_ADAPTEC_STARFIRE=m diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 2e23533b67e3..805b5aeebb6f 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -5,4 +5,5 @@ generated-y += syscall_table_spu.h generic-y += agp.h generic-y += mcs_spinlock.h generic-y += qrwlock.h +generic-y += ring_buffer.h generic-y += early_ioremap.h diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi index 2d14e92f068d..9078e5b1e49c 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -101,16 +101,6 @@ &ccc_nw { status = "okay"; }; -&i2c0 { - pinctrl-names = "default"; - pinctrl-0 = <&i2c0_fabric>; -}; - -&i2c1 { - pinctrl-names = "default"; - pinctrl-0 = <&i2c1_mssio>; -}; - &mmuart1 { pinctrl-names = "default"; pinctrl-0 = <&uart1_fabric>; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts index 8afedece89d1..636493f6584d 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts @@ -14,6 +14,16 @@ / { "microchip,mpfs"; }; +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_fabric>; +}; + +&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_mssio>; +}; + &syscontroller { microchip,bitstream-flash = <&sys_ctrl_flash>; }; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts index 556aa9638282..6fadce815c9a 100644 --- a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -11,3 +11,22 @@ / { "microchip,mpfs-icicle-kit", "microchip,mpfs"; }; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_fabric>; +}; + +/* + * Due to silicon errata, routing via MSS IOs doesn't work on ES devices. + * Instead, i2c1, appearing on B1/C1, which are normally MSS IOs, is routed + * via the fabric and back to B1/C1 via "fabric-test" functionality. + * This is done silently by Libero, so the iomux0 setting for i2c1 has to + * be fabric IO, despite tooling etc saying that MSS IOs are used. + * + * See Section 3.3 of https://ww1.microchip.com/downloads/aemDocuments/documents/FPGA/ProductDocuments/Errata/polarfiresoc/microsemi_polarfire_soc_fpga_egineering_samples_errata_er0219_v1.pdf + */ +&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_fabric>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi index 8cfe8033305d..a7a1c09a2c90 100644 --- a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi @@ -135,29 +135,6 @@ &tdm_ext { clock-frequency = <49152000>; }; -&camss { - assigned-clocks = <&ispcrg JH7110_ISPCLK_DOM4_APB_FUNC>, - <&ispcrg JH7110_ISPCLK_MIPI_RX0_PXL>; - assigned-clock-rates = <49500000>, <198000000>; - - ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - }; - - port@1 { - reg = <1>; - - camss_from_csi2rx: endpoint { - remote-endpoint = <&csi2rx_to_camss>; - }; - }; - }; -}; - &csi2rx { assigned-clocks = <&ispcrg JH7110_ISPCLK_VIN_SYS>; assigned-clock-rates = <297000000>; @@ -175,9 +152,7 @@ port@0 { port@1 { reg = <1>; - csi2rx_to_camss: endpoint { - remote-endpoint = <&camss_from_csi2rx>; - }; + /* remote CAMSS endpoint */ }; }; }; diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi index 6e56e9d20bb0..9c3e4598747e 100644 --- a/arch/riscv/boot/dts/starfive/jh7110.dtsi +++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi @@ -1199,34 +1199,6 @@ csi_phy: phy@19820000 { #phy-cells = <0>; }; - camss: isp@19840000 { - compatible = "starfive,jh7110-camss"; - reg = <0x0 0x19840000 0x0 0x10000>, - <0x0 0x19870000 0x0 0x30000>; - reg-names = "syscon", "isp"; - clocks = <&ispcrg JH7110_ISPCLK_DOM4_APB_FUNC>, - <&ispcrg JH7110_ISPCLK_ISPV2_TOP_WRAPPER_C>, - <&ispcrg JH7110_ISPCLK_DVP_INV>, - <&ispcrg JH7110_ISPCLK_VIN_P_AXI_WR>, - <&ispcrg JH7110_ISPCLK_MIPI_RX0_PXL>, - <&syscrg JH7110_SYSCLK_ISP_TOP_CORE>, - <&syscrg JH7110_SYSCLK_ISP_TOP_AXI>; - clock-names = "apb_func", "wrapper_clk_c", "dvp_inv", - "axiwr", "mipi_rx0_pxl", "ispcore_2x", - "isp_axi"; - resets = <&ispcrg JH7110_ISPRST_ISPV2_TOP_WRAPPER_P>, - <&ispcrg JH7110_ISPRST_ISPV2_TOP_WRAPPER_C>, - <&ispcrg JH7110_ISPRST_VIN_P_AXI_RD>, - <&ispcrg JH7110_ISPRST_VIN_P_AXI_WR>, - <&syscrg JH7110_SYSRST_ISP_TOP>, - <&syscrg JH7110_SYSRST_ISP_TOP_AXI>; - reset-names = "wrapper_p", "wrapper_c", "axird", - "axiwr", "isp_top_n", "isp_top_axi"; - power-domains = <&pwrc JH7110_PD_ISP>; - interrupts = <92>, <87>, <90>, <88>; - status = "disabled"; - }; - voutcrg: clock-controller@295c0000 { compatible = "starfive,jh7110-voutcrg"; reg = <0x0 0x295c0000 0x0 0x10000>; diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index bd5fc9403295..7721b63642f4 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -14,5 +14,6 @@ generic-y += ticket_spinlock.h generic-y += qrwlock.h generic-y += qrwlock_types.h generic-y += qspinlock.h +generic-y += ring_buffer.h generic-y += user.h generic-y += vmlinux.lds.h diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 80bad7de7a04..0c1fc47c3ba0 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -7,3 +7,4 @@ generated-y += unistd_nr.h generic-y += asm-offsets.h generic-y += mcs_spinlock.h generic-y += mmzone.h +generic-y += ring_buffer.h diff --git a/arch/s390/kvm/dat.c b/arch/s390/kvm/dat.c index 7b8d70fe406d..4a41c0247ffa 100644 --- a/arch/s390/kvm/dat.c +++ b/arch/s390/kvm/dat.c @@ -267,6 +267,7 @@ static int dat_split_ste(struct kvm_s390_mmu_cache *mc, union pmd *pmdp, gfn_t g /* No need to take locks as the page table is not installed yet. */ pgste_init.prefix_notif = old.s.fc1.prefix_notif; pgste_init.vsie_notif = old.s.fc1.vsie_notif; + pgste_init.vsie_gmem = old.s.fc1.vsie_notif; pgste_init.pcl = uses_skeys && init.h.i; dat_init_pgstes(pt, pgste_init.val); } else { diff --git a/arch/s390/kvm/dat.h b/arch/s390/kvm/dat.h index 8f8278c44879..873e13ac5a27 100644 --- a/arch/s390/kvm/dat.h +++ b/arch/s390/kvm/dat.h @@ -145,7 +145,8 @@ union pgste { unsigned long cmma_d : 1; /* Dirty flag for CMMA bits */ unsigned long prefix_notif : 1; /* Guest prefix invalidation notification */ unsigned long vsie_notif : 1; /* Referenced in a shadow table */ - unsigned long : 5; + unsigned long vsie_gmem : 1; /* Contains nested guest memory */ + unsigned long : 4; unsigned long : 8; }; struct { diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index b07accd19618..4f8d5592c9a9 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1445,6 +1445,7 @@ static int _do_shadow_pte(struct gmap *sg, gpa_t raddr, union pte *ptep_h, union } else { pgste = _gmap_ptep_xchg(sg->parent, ptep_h, newpte, pgste, f->gfn, false); pgste.vsie_notif = 1; + pgste.vsie_gmem = 1; } pgste_set_unlock(ptep_h, pgste); if (rc) diff --git a/arch/s390/kvm/gmap.c b/arch/s390/kvm/gmap.c index 3c26e35af0ef..957126ab991c 100644 --- a/arch/s390/kvm/gmap.c +++ b/arch/s390/kvm/gmap.c @@ -125,7 +125,7 @@ struct gmap *gmap_new_child(struct gmap *parent, gfn_t limit) int gmap_set_limit(struct gmap *gmap, gfn_t limit) { - struct kvm_s390_mmu_cache *mc; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; int rc, type; type = gmap_limit_to_type(limit); @@ -142,7 +142,6 @@ int gmap_set_limit(struct gmap *gmap, gfn_t limit) rc = dat_set_asce_limit(mc, &gmap->asce, type); } while (rc == -ENOMEM); - kvm_s390_free_mmu_cache(mc); return 0; } @@ -822,8 +821,8 @@ int gmap_ucas_translate(struct kvm_s390_mmu_cache *mc, struct gmap *gmap, gpa_t int gmap_ucas_map(struct gmap *gmap, gfn_t p_gfn, gfn_t c_gfn, unsigned long count) { - struct kvm_s390_mmu_cache *mc; - int rc; + struct kvm_s390_mmu_cache *mc __free(kvm_s390_mmu_cache) = NULL; + int rc = 0; mc = kvm_s390_new_mmu_cache(); if (!mc) @@ -1026,13 +1025,15 @@ int gmap_insert_rmap(struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, int level) int gmap_protect_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gfn, gfn_t r_gfn, kvm_pfn_t pfn, int level, bool wr) { + unsigned long bitmask; union crste *crstep; union pgste pgste; union pte *ptep; union pte pte; int flags, rc; - KVM_BUG_ON(!is_shadow(sg), sg->kvm); + if (KVM_BUG_ON(!is_shadow(sg) || level <= TABLE_TYPE_PAGE_TABLE, sg->kvm)) + return -EINVAL; lockdep_assert_held(&sg->parent->children_lock); flags = DAT_WALK_SPLIT_ALLOC | (uses_skeys(sg->parent) ? DAT_WALK_USES_SKEYS : 0); @@ -1041,8 +1042,9 @@ int gmap_protect_rmap(struct kvm_s390_mmu_cache *mc, struct gmap *sg, gfn_t p_gf if (rc) return rc; if (level <= TABLE_TYPE_REGION1) { + bitmask = -1UL << (8 + 11 * level); scoped_guard(spinlock, &sg->host_to_rmap_lock) - rc = gmap_insert_rmap(sg, p_gfn, r_gfn, level); + rc = gmap_insert_rmap(sg, p_gfn, r_gfn & bitmask, level); } if (rc) return rc; @@ -1143,8 +1145,10 @@ void _gmap_handle_vsie_unshadow_event(struct gmap *parent, gfn_t gfn) } scoped_guard(spinlock, &sg->host_to_rmap_lock) head = radix_tree_delete(&sg->host_to_rmap, gfn); - gmap_for_each_rmap_safe(rmap, rnext, head) + gmap_for_each_rmap_safe(rmap, rnext, head) { gmap_unshadow_level(sg, rmap->r_gfn, rmap->level); + kfree(rmap); + } } } diff --git a/arch/s390/kvm/gmap.h b/arch/s390/kvm/gmap.h index 96ee1395a592..742e42a31744 100644 --- a/arch/s390/kvm/gmap.h +++ b/arch/s390/kvm/gmap.h @@ -167,6 +167,36 @@ static inline bool gmap_unmap_prefix(struct gmap *gmap, gfn_t gfn, gfn_t end) return _gmap_unmap_prefix(gmap, gfn, end, false); } +/** + * pte_needs_unshadow() -- Check if the pte operations triggers unshadowing. + * @oldpte: the previous value for the guest pte. + * @newpte: the new pte being set. + * @pgste: the pgste for the pte entry. + * + * If the pgste.vsie_notif bit is not set, return false: the page is not + * involved in vsie and thus should not trigger an unshadow operation. + * + * If the pgste.vsie_gmem bit is set, this pte represents shadowed guest + * memory. The access rights on g3's memory should be synchronized with g1's + * and g2's. Therefore unshadowing is triggered if the new and old pte + * differ in protection, or if the new pte is invalid. + * + * If the pgste.vsie_gmem bit is not set, this pte maps the g2 dat tables + * for g3. If the entry becomes writable or absent, it becomes impossible to + * guarantee that the shadow mapping will match g2's mapping. In that case, + * trigger an unshadow event. + * + * Return: true if an unshadow event should be triggered, otherwise false. + */ +static inline bool pte_needs_unshadow(union pte oldpte, union pte newpte, union pgste pgste) +{ + if (!pgste.vsie_notif) + return false; + if (pgste.vsie_gmem) + return (oldpte.h.p != newpte.h.p) || newpte.h.i; + return !newpte.h.p || !newpte.s.pr; +} + static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, union pte newpte, union pgste pgste, gfn_t gfn, bool needs_lock) { @@ -180,8 +210,9 @@ static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, un pgste.prefix_notif = 0; gmap_unmap_prefix(gmap, gfn, gfn + 1); } - if (pgste.vsie_notif && (ptep->h.p != newpte.h.p || newpte.h.i)) { + if (pte_needs_unshadow(*ptep, newpte, pgste)) { pgste.vsie_notif = 0; + pgste.vsie_gmem = 0; if (needs_lock) gmap_handle_vsie_unshadow_event(gmap, gfn); else @@ -189,6 +220,7 @@ static inline union pgste _gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, un } if (!ptep->s.d && newpte.s.d && !newpte.s.s) SetPageDirty(pfn_to_page(newpte.h.pfra)); + pgste.zero = 0; return __dat_ptep_xchg(ptep, pgste, newpte, gfn, gmap->asce, uses_skeys(gmap)); } @@ -198,6 +230,30 @@ static inline union pgste gmap_ptep_xchg(struct gmap *gmap, union pte *ptep, uni return _gmap_ptep_xchg(gmap, ptep, newpte, pgste, gfn, true); } +/** + * crste_needs_unshadow() -- Check if the crste operations triggers unshadowing. + * @oldcrste: the previous value for the crste. + * @newcrste: the new value for the crste. + * + * If the old crste did not have the vsie_notif bit set, return false: the + * page is not involved in vsie and thus should not trigger an unshadow + * operation. Conversely, if the bit is set, it can only be g3 memory, since + * dat tables are never mapped using large pages. + * + * Similar to the pgste.vsie_gmem case of pte_needs_unshadow(), if the + * protection bit is changing or the new page is invalid, trigger an + * unshadow event. Also trigger an unshadow event if the new crste does not + * have the vsie_notif bit set. + * + * Return: true if an unshadow event should be triggered, otherwise false. + */ +static inline bool crste_needs_unshadow(union crste oldcrste, union crste newcrste) +{ + if (!oldcrste.s.fc1.vsie_notif) + return false; + return (newcrste.h.p != oldcrste.h.p) || newcrste.h.i || !newcrste.s.fc1.vsie_notif; +} + static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, union crste *crstep, union crste oldcrste, union crste newcrste, gfn_t gfn, bool needs_lock) @@ -216,8 +272,7 @@ static inline bool __must_check _gmap_crstep_xchg_atomic(struct gmap *gmap, unio newcrste.s.fc1.prefix_notif = 0; gmap_unmap_prefix(gmap, gfn, gfn + align); } - if (crste_leaf(oldcrste) && oldcrste.s.fc1.vsie_notif && - (newcrste.h.p || newcrste.h.i || !newcrste.s.fc1.vsie_notif)) { + if (crste_leaf(oldcrste) && crste_needs_unshadow(oldcrste, newcrste)) { newcrste.s.fc1.vsie_notif = 0; if (needs_lock) gmap_handle_vsie_unshadow_event(gmap, gfn); diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 4d3f10ed8275..f0403d3ee8ab 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -3,4 +3,5 @@ generated-y += syscall_table.h generic-y += kvm_para.h generic-y += mcs_spinlock.h generic-y += parport.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index 17ee8a273aa6..49c6bb326b75 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -4,4 +4,5 @@ generated-y += syscall_table_64.h generic-y += agp.h generic-y += kvm_para.h generic-y += mcs_spinlock.h +generic-y += ring_buffer.h generic-y += text-patching.h diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild index 1b9b82bbe322..2a1629ba8140 100644 --- a/arch/um/include/asm/Kbuild +++ b/arch/um/include/asm/Kbuild @@ -17,6 +17,7 @@ generic-y += module.lds.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h +generic-y += ring_buffer.h generic-y += runtime-const.h generic-y += softirq_stack.h generic-y += switch_to.h diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 4566000e15c4..078fd2c0d69d 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -14,3 +14,4 @@ generic-y += early_ioremap.h generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h +generic-y += ring_buffer.h diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 13fe45dea296..e57af619263a 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -6,5 +6,6 @@ generic-y += mcs_spinlock.h generic-y += parport.h generic-y += qrwlock.h generic-y += qspinlock.h +generic-y += ring_buffer.h generic-y += user.h generic-y += text-patching.h diff --git a/crypto/krb5/krb5_api.c b/crypto/krb5/krb5_api.c index 23026d4206c8..c7ea40f900a7 100644 --- a/crypto/krb5/krb5_api.c +++ b/crypto/krb5/krb5_api.c @@ -134,27 +134,69 @@ EXPORT_SYMBOL(crypto_krb5_how_much_data); * Find the offset and size of the data in a secure message so that this * information can be used in the metadata buffer which will get added to the * digest by crypto_krb5_verify_mic(). + * + * Return: 0 if successful, -EBADMSG if the message is too short or -EINVAL if + * the mode is unsupported. */ -void crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, - enum krb5_crypto_mode mode, - size_t *_offset, size_t *_len) +int crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t *_offset, size_t *_len) { switch (mode) { case KRB5_CHECKSUM_MODE: + if (*_len < krb5->cksum_len) + return -EBADMSG; *_offset += krb5->cksum_len; *_len -= krb5->cksum_len; - return; + return 0; case KRB5_ENCRYPT_MODE: + if (*_len < krb5->conf_len + krb5->cksum_len) + return -EBADMSG; *_offset += krb5->conf_len; *_len -= krb5->conf_len + krb5->cksum_len; - return; + return 0; default: WARN_ON_ONCE(1); - return; + return -EINVAL; } } EXPORT_SYMBOL(crypto_krb5_where_is_the_data); +/** + * crypto_krb5_check_data_len - Check a message is big enough + * @krb5: The encoding to use. + * @mode: Mode of operation. + * @len: The length of the secure blob. + * @min_content: Minimum length of the content inside the blob. + * + * Check that a message is large enough to hold whatever bits the encryption + * type wants to glue on (nonce, checksum) plus a minimum amount of content. + * + * Return: 0 if successful, -EBADMSG if the message is too short or -EINVAL if + * the mode is unsupported. + */ +int crypto_krb5_check_data_len(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t len, size_t min_content) +{ + switch (mode) { + case KRB5_CHECKSUM_MODE: + if (len < krb5->cksum_len || + len - krb5->cksum_len < min_content) + return -EBADMSG; + return 0; + case KRB5_ENCRYPT_MODE: + if (len < krb5->conf_len + krb5->cksum_len || + len - (krb5->conf_len + krb5->cksum_len) < min_content) + return -EBADMSG; + return 0; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } +} +EXPORT_SYMBOL(crypto_krb5_check_data_len); + /* * Prepare the encryption with derived key data. */ diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index e76d15411e2a..3d0027ec33c2 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5584,6 +5584,7 @@ void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp) link->pmp = pmp; link->active_tag = ATA_TAG_POISON; link->hw_sata_spd_limit = UINT_MAX; + INIT_WORK(&link->deferred_qc_work, ata_scsi_deferred_qc_work); /* can't use iterator, ap isn't initialized yet */ for (i = 0; i < ATA_MAX_DEVICES; i++) { @@ -5666,7 +5667,6 @@ struct ata_port *ata_port_alloc(struct ata_host *host) mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_DELAYED_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); - INIT_WORK(&ap->deferred_qc_work, ata_scsi_deferred_qc_work); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); @@ -6291,12 +6291,15 @@ static void ata_port_detach(struct ata_port *ap) /* It better be dead now and not have any remaining deferred qc. */ WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); - WARN_ON(ap->deferred_qc); - cancel_work_sync(&ap->deferred_qc_work); cancel_delayed_work_sync(&ap->hotplug_task); cancel_delayed_work_sync(&ap->scsi_rescan_task); + ata_for_each_link(link, ap, PMP_FIRST) { + WARN_ON(link->deferred_qc); + cancel_work_sync(&link->deferred_qc_work); + } + /* Delete port multiplier link transport devices */ if (ap->pmp_link) { int i; diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index 9a4b67b90b17..d623eb32ed8b 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -651,11 +651,11 @@ int ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, if (qc->scsicmd != scmd) continue; if ((qc->flags & ATA_QCFLAG_ACTIVE) || - qc == ap->deferred_qc) + qc == qc->dev->link->deferred_qc) break; } - if (i < ATA_MAX_QUEUE && qc == ap->deferred_qc) { + if (i < ATA_MAX_QUEUE && qc == qc->dev->link->deferred_qc) { /* * This is a deferred command that timed out while * waiting for the command queue to drain. Since the qc @@ -666,8 +666,8 @@ int ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, * deferred qc work from issuing this qc. */ WARN_ON_ONCE(qc->flags & ATA_QCFLAG_ACTIVE); - ap->deferred_qc = NULL; - cancel_work(&ap->deferred_qc_work); + qc->dev->link->deferred_qc = NULL; + cancel_work(&qc->dev->link->deferred_qc_work); set_host_byte(scmd, DID_TIME_OUT); scsi_eh_finish_cmd(scmd, &ap->eh_done_q); } else if (i < ATA_MAX_QUEUE) { diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c index e3adc008fed1..e8540931b4a1 100644 --- a/drivers/ata/libata-pmp.c +++ b/drivers/ata/libata-pmp.c @@ -110,13 +110,24 @@ int sata_pmp_qc_defer_cmd_switch(struct ata_queued_cmd *qc) { struct ata_link *link = qc->dev->link; struct ata_port *ap = link->ap; + int ret; if (ap->excl_link == NULL || ap->excl_link == link) { if (ap->nr_active_links == 0 || ata_link_active(link)) { qc->flags |= ATA_QCFLAG_CLEAR_EXCL; - return ata_std_qc_defer(qc); + ret = ata_std_qc_defer(qc); + if (ret == ATA_DEFER_LINK) + return ATA_DEFER_LINK_EXCL; + return ret; } + /* + * Note: ap->excl_link contains the link that is next in line, + * i.e. implicit round robin. If there is only one link + * dispatching, ap->excl_link will be left unclaimed, allowing + * other links to set ap->excl_link, ensuring that the currently + * active link cannot queue any more. + */ ap->excl_link = link; } @@ -571,8 +582,11 @@ static void sata_pmp_detach(struct ata_device *dev) if (ap->ops->pmp_detach) ap->ops->pmp_detach(ap); - ata_for_each_link(tlink, ap, EDGE) + ata_for_each_link(tlink, ap, EDGE) { + WARN_ON(tlink->deferred_qc); + cancel_work_sync(&tlink->deferred_qc_work); ata_eh_detach_dev(tlink->device); + } spin_lock_irqsave(ap->lock, flags); ap->nr_pmp_links = 0; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index f44612e269a4..d43207c6e467 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1664,8 +1664,9 @@ static void ata_scsi_qc_done(struct ata_queued_cmd *qc, bool set_result, void ata_scsi_deferred_qc_work(struct work_struct *work) { - struct ata_port *ap = - container_of(work, struct ata_port, deferred_qc_work); + struct ata_link *link = + container_of(work, struct ata_link, deferred_qc_work); + struct ata_port *ap = link->ap; struct ata_queued_cmd *qc; unsigned long flags; @@ -1676,10 +1677,10 @@ void ata_scsi_deferred_qc_work(struct work_struct *work) * such case, we should not need any more deferring the qc, so warn if * qc_defer() says otherwise. */ - qc = ap->deferred_qc; + qc = link->deferred_qc; if (qc && !ata_port_eh_scheduled(ap)) { WARN_ON_ONCE(ap->ops->qc_defer(qc)); - ap->deferred_qc = NULL; + link->deferred_qc = NULL; ata_qc_issue(qc); } @@ -1688,7 +1689,7 @@ void ata_scsi_deferred_qc_work(struct work_struct *work) void ata_scsi_requeue_deferred_qc(struct ata_port *ap) { - struct ata_queued_cmd *qc = ap->deferred_qc; + struct ata_link *link; lockdep_assert_held(ap->lock); @@ -1697,16 +1698,21 @@ void ata_scsi_requeue_deferred_qc(struct ata_port *ap) * do not try to be smart about what to do with this deferred command * and simply requeue it by completing it with DID_REQUEUE. */ - if (qc) { - ap->deferred_qc = NULL; - cancel_work(&ap->deferred_qc_work); - ata_scsi_qc_done(qc, true, DID_REQUEUE << 16); + ata_for_each_link(link, ap, PMP_FIRST) { + struct ata_queued_cmd *qc = link->deferred_qc; + + if (qc) { + link->deferred_qc = NULL; + cancel_work(&link->deferred_qc_work); + ata_scsi_qc_done(qc, true, DID_REQUEUE << 16); + } } } -static void ata_scsi_schedule_deferred_qc(struct ata_port *ap) +static void ata_scsi_schedule_deferred_qc(struct ata_link *link) { - struct ata_queued_cmd *qc = ap->deferred_qc; + struct ata_queued_cmd *qc = link->deferred_qc; + struct ata_port *ap = link->ap; lockdep_assert_held(ap->lock); @@ -1723,12 +1729,12 @@ static void ata_scsi_schedule_deferred_qc(struct ata_port *ap) return; } if (!ap->ops->qc_defer(qc)) - queue_work(system_highpri_wq, &ap->deferred_qc_work); + queue_work(system_highpri_wq, &link->deferred_qc_work); } static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) { - struct ata_port *ap = qc->ap; + struct ata_link *link = qc->dev->link; struct scsi_cmnd *cmd = qc->scsicmd; u8 *cdb = cmd->cmnd; bool have_sense = qc->flags & ATA_QCFLAG_SENSE_VALID; @@ -1759,22 +1765,23 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc) ata_scsi_qc_done(qc, false, 0); - ata_scsi_schedule_deferred_qc(ap); + ata_scsi_schedule_deferred_qc(link); } static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) { + struct ata_link *link = qc->dev->link; int ret; if (!ap->ops->qc_defer) - goto issue; + goto issue_qc; /* * If we already have a deferred qc, then rely on the SCSI layer to * requeue and defer all incoming commands until the deferred qc is * processed, once all on-going commands complete. */ - if (ap->deferred_qc) { + if (link->deferred_qc) { ata_qc_free(qc); return SCSI_MLQUEUE_DEVICE_BUSY; } @@ -1786,38 +1793,46 @@ static int ata_scsi_qc_issue(struct ata_port *ap, struct ata_queued_cmd *qc) break; case ATA_DEFER_LINK: ret = SCSI_MLQUEUE_DEVICE_BUSY; - break; + goto defer_qc; + case ATA_DEFER_LINK_EXCL: + /* + * Drivers making use of ap->excl_link cannot store the QC in + * link->deferred_qc, because the ap->excl_link handling is + * incompatible with the link->deferred_qc workqueue handling. + */ + ret = SCSI_MLQUEUE_DEVICE_BUSY; + goto free_qc; case ATA_DEFER_PORT: ret = SCSI_MLQUEUE_HOST_BUSY; - break; + goto free_qc; default: WARN_ON_ONCE(1); ret = SCSI_MLQUEUE_HOST_BUSY; - break; + goto free_qc; } - if (ret) { - /* - * We must defer this qc: if this is not an NCQ command, keep - * this qc as a deferred one and report to the SCSI layer that - * we issued it so that it is not requeued. The deferred qc will - * be issued with the port deferred_qc_work once all on-going - * commands complete. - */ - if (!ata_is_ncq(qc->tf.protocol)) { - ap->deferred_qc = qc; - return 0; - } - - /* Force a requeue of the command to defer its execution. */ - ata_qc_free(qc); - return ret; - } - -issue: +issue_qc: ata_qc_issue(qc); - return 0; + +defer_qc: + /* + * We must defer this qc: if this is not an NCQ command, keep + * this qc as a deferred one and report to the SCSI layer that + * we issued it so that it is not requeued. The deferred qc will + * be issued with the port deferred_qc_work once all on-going + * commands complete. + */ + if (!ata_is_ncq(qc->tf.protocol)) { + link->deferred_qc = qc; + return 0; + } + +free_qc: + /* Force a requeue of the command to defer its execution. */ + ata_qc_free(qc); + + return ret; } /** diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c index d642ece9f07a..57f1081b86db 100644 --- a/drivers/ata/sata_sil24.c +++ b/drivers/ata/sata_sil24.c @@ -789,6 +789,7 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) struct ata_link *link = qc->dev->link; struct ata_port *ap = link->ap; u8 prot = qc->tf.protocol; + int ret; /* * There is a bug in the chip: @@ -826,7 +827,10 @@ static int sil24_qc_defer(struct ata_queued_cmd *qc) qc->flags |= ATA_QCFLAG_CLEAR_EXCL; } - return ata_std_qc_defer(qc); + ret = ata_std_qc_defer(qc); + if (ret == ATA_DEFER_LINK) + return ATA_DEFER_LINK_EXCL; + return ret; } static enum ata_completion_errors sil24_qc_prep(struct ata_queued_cmd *qc) diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f806a683b767..6981b55d582a 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -1230,8 +1230,10 @@ void memblk_nr_poison_inc(unsigned long pfn) const unsigned long block_id = pfn_to_block_id(pfn); struct memory_block *mem = find_memory_block_by_id(block_id); - if (mem) + if (mem) { atomic_long_inc(&mem->nr_hwpoison); + put_device(&mem->dev); + } } void memblk_nr_poison_sub(unsigned long pfn, long i) @@ -1239,8 +1241,10 @@ void memblk_nr_poison_sub(unsigned long pfn, long i) const unsigned long block_id = pfn_to_block_id(pfn); struct memory_block *mem = find_memory_block_by_id(block_id); - if (mem) + if (mem) { atomic_long_sub(i, &mem->nr_hwpoison); + put_device(&mem->dev); + } } static unsigned long memblk_nr_poison(struct memory_block *mem) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 4065336ebd1f..6c1e7347e6a7 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4565,24 +4565,12 @@ static int rbd_register_watch(struct rbd_device *rbd_dev) return ret; } -static void cancel_tasks_sync(struct rbd_device *rbd_dev) -{ - dout("%s rbd_dev %p\n", __func__, rbd_dev); - - cancel_work_sync(&rbd_dev->acquired_lock_work); - cancel_work_sync(&rbd_dev->released_lock_work); - cancel_delayed_work_sync(&rbd_dev->lock_dwork); - cancel_work_sync(&rbd_dev->unlock_work); -} - /* * header_rwsem must not be held to avoid a deadlock with * rbd_dev_refresh() when flushing notifies. */ static void rbd_unregister_watch(struct rbd_device *rbd_dev) { - cancel_tasks_sync(rbd_dev); - mutex_lock(&rbd_dev->watch_mutex); if (rbd_dev->watch_state == RBD_WATCH_STATE_REGISTERED) __rbd_unregister_watch(rbd_dev); @@ -6548,10 +6536,18 @@ static int rbd_add_parse_args(const char *buf, static void rbd_dev_image_unlock(struct rbd_device *rbd_dev) { + dout("%s rbd_dev %p\n", __func__, rbd_dev); + + disable_delayed_work_sync(&rbd_dev->lock_dwork); + disable_work_sync(&rbd_dev->unlock_work); + down_write(&rbd_dev->lock_rwsem); if (__rbd_is_lock_owner(rbd_dev)) __rbd_release_lock(rbd_dev); up_write(&rbd_dev->lock_rwsem); + + flush_work(&rbd_dev->acquired_lock_work); + flush_work(&rbd_dev->released_lock_work); } /* diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c index a3643e67b33f..37e050763633 100644 --- a/drivers/bluetooth/btintel_pcie.c +++ b/drivers/bluetooth/btintel_pcie.c @@ -582,12 +582,10 @@ static int btintel_pcie_get_mac_access(struct btintel_pcie_data *data) reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG); - reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS; - reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ; - if ((reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_STS) == 0) + if (!(reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ)) { reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ; - - btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + } do { reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG); @@ -607,16 +605,10 @@ static void btintel_pcie_release_mac_access(struct btintel_pcie_data *data) reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG); - if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ) + if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ) { reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ; - - if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS) - reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS; - - if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ) - reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ; - - btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg); + } } static void *btintel_pcie_copy_tlv(void *dest, enum btintel_pcie_tlv_type type, diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h index f922abd1e7d8..13efef499e4e 100644 --- a/drivers/bluetooth/btintel_pcie.h +++ b/drivers/bluetooth/btintel_pcie.h @@ -34,9 +34,6 @@ #define BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_STS (BIT(20)) #define BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ (BIT(21)) -/* Stop MAC Access disconnection request */ -#define BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS (BIT(22)) -#define BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ (BIT(23)) #define BTINTEL_PCIE_CSR_FUNC_CTRL_BUS_MASTER_STS (BIT(28)) #define BTINTEL_PCIE_CSR_FUNC_CTRL_BUS_MASTER_DISCON (BIT(29)) diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index f70c1b0f8990..8ff66b276af0 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -537,6 +537,7 @@ static void btmtk_usb_wmt_recv(struct urb *urb) return; } else if (urb->status == -ENOENT) { /* Avoid suspend failed when usb_kill_urb */ + kfree(urb->setup_packet); return; } @@ -610,6 +611,7 @@ static int btmtk_usb_submit_wmt_recv_urb(struct hci_dev *hdev) if (err != -EPERM && err != -ENODEV) bt_dev_err(hdev, "urb %p submission failed (%d)", urb, -err); + kfree(dr); usb_unanchor_urb(urb); } @@ -719,8 +721,8 @@ static int btmtk_usb_hci_wmt_sync(struct hci_dev *hdev, case BTMTK_WMT_FUNC_CTRL: if (!skb_pull_data(data->evt_skb, sizeof(wmt_evt_funcc->status))) { - err = -EINVAL; - goto err_free_skb; + status = BTMTK_WMT_ON_UNDONE; + break; } wmt_evt_funcc = (struct btmtk_hci_wmt_evt_funcc *)wmt_evt; diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 275ea865bc29..47f4902b40b4 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -194,7 +194,15 @@ void hci_uart_init_work(struct work_struct *work) err = hci_register_dev(hu->hdev); if (err < 0) { BT_ERR("Can't register HCI device"); + + percpu_down_write(&hu->proto_lock); clear_bit(HCI_UART_PROTO_READY, &hu->flags); + percpu_up_write(&hu->proto_lock); + + /* Safely cancel work after clearing flags */ + cancel_work_sync(&hu->write_work); + + /* Close protocol before freeing hdev */ hu->proto->close(hu); hdev = hu->hdev; hu->hdev = NULL; @@ -263,8 +271,12 @@ static int hci_uart_open(struct hci_dev *hdev) /* Close device */ static int hci_uart_close(struct hci_dev *hdev) { + struct hci_uart *hu = hci_get_drvdata(hdev); + BT_DBG("hdev %p", hdev); + cancel_work_sync(&hu->write_work); + hci_uart_flush(hdev); hdev->flush = NULL; return 0; @@ -531,6 +543,7 @@ static void hci_uart_tty_close(struct tty_struct *tty) { struct hci_uart *hu = tty->disc_data; struct hci_dev *hdev; + bool proto_ready; BT_DBG("tty %p", tty); @@ -540,24 +553,38 @@ static void hci_uart_tty_close(struct tty_struct *tty) if (!hu) return; - hdev = hu->hdev; - if (hdev) - hci_uart_close(hdev); + /* Wait for init_ready to finish to prevent registration races */ + cancel_work_sync(&hu->init_ready); - if (test_bit(HCI_UART_PROTO_READY, &hu->flags)) { + proto_ready = test_bit(HCI_UART_PROTO_READY, &hu->flags); + if (proto_ready) { percpu_down_write(&hu->proto_lock); clear_bit(HCI_UART_PROTO_READY, &hu->flags); percpu_up_write(&hu->proto_lock); + } - cancel_work_sync(&hu->init_ready); - cancel_work_sync(&hu->write_work); + /* + * Unconditionally cancel write_work AFTER clearing PROTO_READY. + * This ensures that concurrent protocol timers cannot requeue + * write_work via hci_uart_tx_wakeup(), permanently preventing + * double-free races and UAFs. + */ + cancel_work_sync(&hu->write_work); + hdev = hu->hdev; + if (hdev) + hci_uart_close(hdev); /* proto->flush is safely skipped */ + + if (proto_ready) { if (hdev) { if (test_bit(HCI_UART_REGISTERED, &hu->flags)) hci_unregister_dev(hdev); - hci_free_dev(hdev); } + /* Close protocol before freeing hdev (intrinsically purges queues) */ hu->proto->close(hu); + + if (hdev) + hci_free_dev(hdev); } clear_bit(HCI_UART_PROTO_SET, &hu->flags); @@ -625,11 +652,12 @@ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, * tty caller */ hu->proto->recv(hu, data, count); - percpu_up_read(&hu->proto_lock); if (hu->hdev) hu->hdev->stat.byte_rx += count; + percpu_up_read(&hu->proto_lock); + tty_unthrottle(tty); } @@ -695,6 +723,10 @@ static int hci_uart_register_dev(struct hci_uart *hu) percpu_down_write(&hu->proto_lock); clear_bit(HCI_UART_PROTO_INIT, &hu->flags); percpu_up_write(&hu->proto_lock); + /* Cancel work after clearing flags */ + cancel_work_sync(&hu->write_work); + + /* Close protocol before freeing hdev */ hu->proto->close(hu); hu->hdev = NULL; hci_free_dev(hdev); diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index cd1834246b47..ed280399bf47 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -48,13 +48,12 @@ #define HCI_MAX_IBS_SIZE 10 #define IBS_WAKE_RETRANS_TIMEOUT_MS 100 -#define IBS_BTSOC_TX_IDLE_TIMEOUT_MS 200 +#define IBS_BTSOC_TX_IDLE_TIMEOUT msecs_to_jiffies(200) #define IBS_HOST_TX_IDLE_TIMEOUT_MS 2000 -#define CMD_TRANS_TIMEOUT_MS 100 -#define MEMDUMP_TIMEOUT_MS 8000 -#define IBS_DISABLE_SSR_TIMEOUT_MS \ - (MEMDUMP_TIMEOUT_MS + FW_DOWNLOAD_TIMEOUT_MS) -#define FW_DOWNLOAD_TIMEOUT_MS 3000 +#define CMD_TRANS_TIMEOUT msecs_to_jiffies(100) +#define MEMDUMP_TIMEOUT msecs_to_jiffies(8000) +#define FW_DOWNLOAD_TIMEOUT msecs_to_jiffies(3000) +#define IBS_DISABLE_SSR_TIMEOUT (MEMDUMP_TIMEOUT + FW_DOWNLOAD_TIMEOUT) /* susclk rate */ #define SUSCLK_RATE_32KHZ 32768 @@ -1096,7 +1095,7 @@ static void qca_controller_memdump(struct work_struct *work) queue_delayed_work(qca->workqueue, &qca->ctrl_memdump_timeout, - msecs_to_jiffies(MEMDUMP_TIMEOUT_MS)); + MEMDUMP_TIMEOUT); skb_pull(skb, sizeof(qca_memdump->ram_dump_size)); qca_memdump->current_seq_no = 0; qca_memdump->received_dump = 0; @@ -1369,7 +1368,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate) if (hu->serdev) serdev_device_wait_until_sent(hu->serdev, - msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS)); + CMD_TRANS_TIMEOUT); /* Give the controller time to process the request */ switch (qca_soc_type(hu)) { @@ -1401,8 +1400,8 @@ static inline void host_set_baudrate(struct hci_uart *hu, unsigned int speed) static int qca_send_power_pulse(struct hci_uart *hu, bool on) { + int timeout = CMD_TRANS_TIMEOUT; int ret; - int timeout = msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS); u8 cmd = on ? QCA_WCN3990_POWERON_PULSE : QCA_WCN3990_POWEROFF_PULSE; /* These power pulses are single byte command which are sent @@ -1607,7 +1606,7 @@ static void qca_wait_for_dump_collection(struct hci_dev *hdev) struct qca_data *qca = hu->priv; wait_on_bit_timeout(&qca->flags, QCA_MEMDUMP_COLLECTION, - TASK_UNINTERRUPTIBLE, MEMDUMP_TIMEOUT_MS); + TASK_UNINTERRUPTIBLE, MEMDUMP_TIMEOUT); clear_bit(QCA_MEMDUMP_COLLECTION, &qca->flags); } @@ -2591,7 +2590,7 @@ static void qca_serdev_remove(struct serdev_device *serdev) static void qca_serdev_shutdown(struct serdev_device *serdev) { int ret; - int timeout = msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS); + int timeout = CMD_TRANS_TIMEOUT; struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); struct hci_uart *hu = &qcadev->serdev_hu; struct hci_dev *hdev = hu->hdev; @@ -2648,7 +2647,7 @@ static int __maybe_unused qca_suspend(struct device *dev) bool tx_pending = false; int ret = 0; u8 cmd; - u32 wait_timeout = 0; + unsigned long wait_timeout = 0; set_bit(QCA_SUSPENDING, &qca->flags); @@ -2669,15 +2668,15 @@ static int __maybe_unused qca_suspend(struct device *dev) if (test_bit(QCA_IBS_DISABLED, &qca->flags) || test_bit(QCA_SSR_TRIGGERED, &qca->flags)) { wait_timeout = test_bit(QCA_SSR_TRIGGERED, &qca->flags) ? - IBS_DISABLE_SSR_TIMEOUT_MS : - FW_DOWNLOAD_TIMEOUT_MS; + IBS_DISABLE_SSR_TIMEOUT : + FW_DOWNLOAD_TIMEOUT; /* QCA_IBS_DISABLED flag is set to true, During FW download * and during memory dump collection. It is reset to false, * After FW download complete. */ wait_on_bit_timeout(&qca->flags, QCA_IBS_DISABLED, - TASK_UNINTERRUPTIBLE, msecs_to_jiffies(wait_timeout)); + TASK_UNINTERRUPTIBLE, wait_timeout); if (test_bit(QCA_IBS_DISABLED, &qca->flags)) { bt_dev_err(hu->hdev, "SSR or FW download time out"); @@ -2729,7 +2728,7 @@ static int __maybe_unused qca_suspend(struct device *dev) if (tx_pending) { serdev_device_wait_until_sent(hu->serdev, - msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS)); + CMD_TRANS_TIMEOUT); serial_clock_vote(HCI_IBS_TX_VOTE_CLOCK_OFF, hu); } @@ -2738,7 +2737,7 @@ static int __maybe_unused qca_suspend(struct device *dev) */ ret = wait_event_interruptible_timeout(qca->suspend_wait_q, qca->rx_ibs_state == HCI_IBS_RX_ASLEEP, - msecs_to_jiffies(IBS_BTSOC_TX_IDLE_TIMEOUT_MS)); + IBS_BTSOC_TX_IDLE_TIMEOUT); if (ret == 0) { ret = -ETIMEDOUT; goto error; diff --git a/drivers/dpll/zl3073x/dpll.c b/drivers/dpll/zl3073x/dpll.c index c95e93ef3ab0..64b4e9e3e8fe 100644 --- a/drivers/dpll/zl3073x/dpll.c +++ b/drivers/dpll/zl3073x/dpll.c @@ -1394,8 +1394,8 @@ zl3073x_dpll_pin_register(struct zl3073x_dpll_pin *pin, u32 index) err_register: dpll_pin_put(pin->dpll_pin, &pin->tracker); - pin->dpll_pin = NULL; err_pin_get: + pin->dpll_pin = NULL; fwnode_handle_put(pin->fwnode); pin->fwnode = NULL; zl3073x_pin_props_put(props); @@ -1563,8 +1563,10 @@ zl3073x_dpll_pins_register(struct zl3073x_dpll *zldpll) } rc = zl3073x_dpll_pin_register(pin, index); - if (rc) + if (rc) { + zl3073x_dpll_pin_free(pin); goto error; + } list_add(&pin->list, &zldpll->pins); } diff --git a/drivers/firmware/arm_ffa/bus.c b/drivers/firmware/arm_ffa/bus.c index 9576862d89c4..601c3418e0d9 100644 --- a/drivers/firmware/arm_ffa/bus.c +++ b/drivers/firmware/arm_ffa/bus.c @@ -26,6 +26,8 @@ static int ffa_device_match(struct device *dev, const struct device_driver *drv) id_table = to_ffa_driver(drv)->id_table; ffa_dev = to_ffa_dev(dev); + if (!id_table) + return 0; while (!uuid_is_null(&id_table->uuid)) { /* @@ -123,7 +125,7 @@ int ffa_driver_register(struct ffa_driver *driver, struct module *owner, { int ret; - if (!driver->probe) + if (!driver->probe || !driver->id_table) return -EINVAL; driver->driver.bus = &ffa_bus_type; diff --git a/drivers/firmware/arm_ffa/driver.c b/drivers/firmware/arm_ffa/driver.c index eb2782848283..b9f17fda7243 100644 --- a/drivers/firmware/arm_ffa/driver.c +++ b/drivers/firmware/arm_ffa/driver.c @@ -87,6 +87,7 @@ static inline int ffa_to_linux_errno(int errno) struct ffa_pcpu_irq { struct ffa_drv_info *info; + struct work_struct notif_pcpu_work; }; struct ffa_drv_info { @@ -100,13 +101,13 @@ struct ffa_drv_info { bool mem_ops_native; bool msg_direct_req2_supp; bool bitmap_created; + bool bus_notifier_registered; bool notif_enabled; unsigned int sched_recv_irq; unsigned int notif_pend_irq; unsigned int cpuhp_state; struct ffa_pcpu_irq __percpu *irq_pcpu; struct workqueue_struct *notif_pcpu_wq; - struct work_struct notif_pcpu_work; struct work_struct sched_recv_irq_work; struct xarray partition_info; DECLARE_HASHTABLE(notifier_hash, ilog2(FFA_MAX_NOTIFICATIONS)); @@ -322,6 +323,12 @@ __ffa_partition_info_get(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, #define PART_INFO_ID_MASK GENMASK(15, 0) #define PART_INFO_EXEC_CXT_MASK GENMASK(31, 16) #define PART_INFO_PROPS_MASK GENMASK(63, 32) +#define FFA_PART_INFO_GET_REGS_FIRST_REG 3 +#define FFA_PART_INFO_GET_REGS_REGS_PER_DESC 3 +#define FFA_PART_INFO_GET_REGS_MAX_DESC \ + (((sizeof(ffa_value_t) / sizeof_field(ffa_value_t, a0)) - \ + FFA_PART_INFO_GET_REGS_FIRST_REG) / \ + FFA_PART_INFO_GET_REGS_REGS_PER_DESC) #define PART_INFO_ID(x) ((u16)(FIELD_GET(PART_INFO_ID_MASK, (x)))) #define PART_INFO_EXEC_CXT(x) ((u16)(FIELD_GET(PART_INFO_EXEC_CXT_MASK, (x)))) #define PART_INFO_PROPERTIES(x) ((u32)(FIELD_GET(PART_INFO_PROPS_MASK, (x)))) @@ -329,15 +336,13 @@ static int __ffa_partition_info_get_regs(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, struct ffa_partition_info *buffer, int num_parts) { - u16 buf_sz, start_idx, cur_idx, count = 0, prev_idx = 0, tag = 0; + u16 buf_sz, start_idx = 0, cur_idx, count = 0, tag = 0; struct ffa_partition_info *buf = buffer; ffa_value_t partition_info; do { __le64 *regs; - int idx; - - start_idx = prev_idx ? prev_idx + 1 : 0; + int idx, nr_desc, buf_idx; invoke_ffa_fn((ffa_value_t){ .a0 = FFA_PARTITION_INFO_GET_REGS, @@ -353,15 +358,28 @@ __ffa_partition_info_get_regs(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, count = PARTITION_COUNT(partition_info.a2); if (!buffer || !num_parts) /* count only */ return count; + if (count > num_parts) + return -EINVAL; cur_idx = CURRENT_INDEX(partition_info.a2); + if (cur_idx < start_idx || cur_idx >= count) + return -EINVAL; + + nr_desc = cur_idx - start_idx + 1; + if (nr_desc > FFA_PART_INFO_GET_REGS_MAX_DESC) + return -EINVAL; + + buf_idx = buf - buffer; + if (buf_idx + nr_desc > num_parts) + return -EINVAL; + tag = UUID_INFO_TAG(partition_info.a2); buf_sz = PARTITION_INFO_SZ(partition_info.a2); if (buf_sz > sizeof(*buffer)) buf_sz = sizeof(*buffer); regs = (void *)&partition_info.a3; - for (idx = 0; idx < cur_idx - start_idx + 1; idx++, buf++) { + for (idx = 0; idx < nr_desc; idx++, buf++) { union { uuid_t uuid; u64 regs[2]; @@ -379,7 +397,7 @@ __ffa_partition_info_get_regs(u32 uuid0, u32 uuid1, u32 uuid2, u32 uuid3, uuid_copy(&buf->uuid, &uuid_regs.uuid); regs += 3; } - prev_idx = cur_idx; + start_idx = cur_idx + 1; } while (cur_idx < (count - 1)); @@ -1189,7 +1207,7 @@ static int ffa_sched_recv_cb_update(struct ffa_device *dev, ffa_sched_recv_cb callback, void *cb_data, bool is_registration) { - struct ffa_dev_part_info *partition = NULL, *tmp; + struct ffa_dev_part_info *partition = NULL; struct list_head *phead; bool cb_valid; @@ -1202,11 +1220,11 @@ ffa_sched_recv_cb_update(struct ffa_device *dev, ffa_sched_recv_cb callback, return -EINVAL; } - list_for_each_entry_safe(partition, tmp, phead, node) + list_for_each_entry(partition, phead, node) if (partition->dev == dev) break; - if (!partition) { + if (&partition->node == phead) { pr_err("%s: No such partition ID 0x%x\n", __func__, dev->vm_id); return -EINVAL; } @@ -1445,20 +1463,25 @@ static int ffa_notify_send(struct ffa_device *dev, int notify_id, static void handle_notif_callbacks(u64 bitmap, enum notify_type type) { + ffa_notifier_cb cb; + void *cb_data; int notify_id; - struct notifier_cb_info *cb_info = NULL; for (notify_id = 0; notify_id <= FFA_MAX_NOTIFICATIONS && bitmap; notify_id++, bitmap >>= 1) { if (!(bitmap & 1)) continue; - read_lock(&drv_info->notify_lock); - cb_info = notifier_hnode_get_by_type(notify_id, type); - read_unlock(&drv_info->notify_lock); + scoped_guard(read_lock, &drv_info->notify_lock) { + struct notifier_cb_info *cb_info; - if (cb_info && cb_info->cb) - cb_info->cb(notify_id, cb_info->cb_data); + cb_info = notifier_hnode_get_by_type(notify_id, type); + cb = cb_info ? cb_info->cb : NULL; + cb_data = cb_info ? cb_info->cb_data : NULL; + } + + if (cb) + cb(notify_id, cb_data); } } @@ -1466,39 +1489,56 @@ static void handle_fwk_notif_callbacks(u32 bitmap) { void *buf; uuid_t uuid; + void *fwk_cb_data; int notify_id = 0, target; + ffa_fwk_notifier_cb fwk_cb; struct ffa_indirect_msg_hdr *msg; - struct notifier_cb_info *cb_info = NULL; + size_t min_offset = offsetof(struct ffa_indirect_msg_hdr, uuid); /* Only one framework notification defined and supported for now */ if (!(bitmap & FRAMEWORK_NOTIFY_RX_BUFFER_FULL)) return; - mutex_lock(&drv_info->rx_lock); + scoped_guard(mutex, &drv_info->rx_lock) { + u32 offset, size; - msg = drv_info->rx_buffer; - buf = kmemdup((void *)msg + msg->offset, msg->size, GFP_KERNEL); - if (!buf) { - mutex_unlock(&drv_info->rx_lock); - return; + msg = drv_info->rx_buffer; + offset = msg->offset; + size = msg->size; + + if (!size || (offset != min_offset && offset < sizeof(*msg)) || + offset > drv_info->rxtx_bufsz || + size > drv_info->rxtx_bufsz - offset) { + pr_err("invalid framework notification message\n"); + ffa_rx_release(); + return; + } + + buf = kmemdup((void *)msg + offset, size, GFP_KERNEL); + if (!buf) { + ffa_rx_release(); + return; + } + + target = SENDER_ID(msg->send_recv_id); + if (offset >= sizeof(*msg)) + uuid_copy(&uuid, &msg->uuid); + else + uuid_copy(&uuid, &uuid_null); + ffa_rx_release(); } - target = SENDER_ID(msg->send_recv_id); - if (msg->offset >= sizeof(*msg)) - uuid_copy(&uuid, &msg->uuid); - else - uuid_copy(&uuid, &uuid_null); + scoped_guard(read_lock, &drv_info->notify_lock) { + struct notifier_cb_info *cb_info; - mutex_unlock(&drv_info->rx_lock); + cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, target, + &uuid); + fwk_cb = cb_info ? cb_info->fwk_cb : NULL; + fwk_cb_data = cb_info ? cb_info->cb_data : NULL; + } - ffa_rx_release(); - - read_lock(&drv_info->notify_lock); - cb_info = notifier_hnode_get_by_vmid_uuid(notify_id, target, &uuid); - read_unlock(&drv_info->notify_lock); - - if (cb_info && cb_info->fwk_cb) - cb_info->fwk_cb(notify_id, cb_info->cb_data, buf); + if (fwk_cb) + fwk_cb(notify_id, fwk_cb_data, buf); kfree(buf); } @@ -1539,10 +1579,11 @@ ffa_self_notif_handle(u16 vcpu, bool is_per_vcpu, void *cb_data) static void notif_pcpu_irq_work_fn(struct work_struct *work) { - struct ffa_drv_info *info = container_of(work, struct ffa_drv_info, + struct ffa_pcpu_irq *pcpu = container_of(work, struct ffa_pcpu_irq, notif_pcpu_work); + struct ffa_drv_info *info = pcpu->info; - ffa_self_notif_handle(smp_processor_id(), true, info); + notif_get_and_handle(info); } static const struct ffa_info_ops ffa_drv_info_ops = { @@ -1629,6 +1670,15 @@ static struct notifier_block ffa_bus_nb = { .notifier_call = ffa_bus_notifier, }; +static void ffa_bus_notifier_unregister(void) +{ + if (!drv_info->bus_notifier_registered) + return; + + bus_unregister_notifier(&ffa_bus_type, &ffa_bus_nb); + drv_info->bus_notifier_registered = false; +} + static int ffa_xa_add_partition_info(struct ffa_device *dev) { struct ffa_dev_part_info *info; @@ -1712,6 +1762,8 @@ static void ffa_partitions_cleanup(void) struct list_head *phead; unsigned long idx; + ffa_bus_notifier_unregister(); + /* Clean up/free all registered devices */ ffa_devices_unregister(); @@ -1739,11 +1791,14 @@ static int ffa_setup_partitions(void) ret = bus_register_notifier(&ffa_bus_type, &ffa_bus_nb); if (ret) pr_err("Failed to register FF-A bus notifiers\n"); + else + drv_info->bus_notifier_registered = true; } count = ffa_partition_probe(&uuid_null, &pbuf); if (count <= 0) { pr_info("%s: No partitions found, error %d\n", __func__, count); + ffa_bus_notifier_unregister(); return -EINVAL; } @@ -1811,7 +1866,7 @@ static irqreturn_t notif_pend_irq_handler(int irq, void *irq_data) struct ffa_drv_info *info = pcpu->info; queue_work_on(smp_processor_id(), info->notif_pcpu_wq, - &info->notif_pcpu_work); + &pcpu->notif_pcpu_work); return IRQ_HANDLED; } @@ -1928,8 +1983,11 @@ static int ffa_init_pcpu_irq(void) if (!irq_pcpu) return -ENOMEM; - for_each_present_cpu(cpu) + for_each_present_cpu(cpu) { per_cpu_ptr(irq_pcpu, cpu)->info = drv_info; + INIT_WORK(&per_cpu_ptr(irq_pcpu, cpu)->notif_pcpu_work, + notif_pcpu_irq_work_fn); + } drv_info->irq_pcpu = irq_pcpu; @@ -1958,7 +2016,6 @@ static int ffa_init_pcpu_irq(void) } INIT_WORK(&drv_info->sched_recv_irq_work, ffa_sched_recv_irq_work_fn); - INIT_WORK(&drv_info->notif_pcpu_work, notif_pcpu_irq_work_fn); drv_info->notif_pcpu_wq = create_workqueue("ffa_pcpu_irq_notification"); if (!drv_info->notif_pcpu_wq) return -EINVAL; @@ -2063,11 +2120,12 @@ static int __init ffa_init(void) rxtx_bufsz = SZ_4K; } + rxtx_bufsz = PAGE_ALIGN(rxtx_bufsz); drv_info->rxtx_bufsz = rxtx_bufsz; drv_info->rx_buffer = alloc_pages_exact(rxtx_bufsz, GFP_KERNEL); if (!drv_info->rx_buffer) { ret = -ENOMEM; - goto free_pages; + goto free_drv_info; } drv_info->tx_buffer = alloc_pages_exact(rxtx_bufsz, GFP_KERNEL); @@ -2078,7 +2136,7 @@ static int __init ffa_init(void) ret = ffa_rxtx_map(virt_to_phys(drv_info->tx_buffer), virt_to_phys(drv_info->rx_buffer), - PAGE_ALIGN(rxtx_bufsz) / FFA_PAGE_SIZE); + rxtx_bufsz / FFA_PAGE_SIZE); if (ret) { pr_err("failed to register FFA RxTx buffers\n"); goto free_pages; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index d04be38f1750..318d1cc9a066 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -402,21 +402,11 @@ static void __init efi_debugfs_init(void) static inline void efi_debugfs_init(void) {} #endif -/* - * We register the efi subsystem with the firmware subsystem and the - * efivars subsystem with the efi subsystem, if the system was booted with - * EFI. - */ -static int __init efisubsys_init(void) +static int __init efipostcore_init(void) { - int error; - if (!efi_enabled(EFI_RUNTIME_SERVICES)) efi.runtime_supported_mask = 0; - if (!efi_enabled(EFI_BOOT)) - return 0; - if (efi.runtime_supported_mask) { /* * Since we process only one efi_runtime_service() at a time, an @@ -428,9 +418,23 @@ static int __init efisubsys_init(void) pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n"); clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); efi.runtime_supported_mask = 0; - return 0; } } + return 0; +} +postcore_initcall(efipostcore_init); + +/* + * We register the efi subsystem with the firmware subsystem and the + * efivars subsystem with the efi subsystem, if the system was booted with + * EFI. + */ +static int __init efisubsys_init(void) +{ + int error; + + if (!efi_enabled(EFI_BOOT)) + return 0; if (efi_rt_services_supported(EFI_RT_SUPPORTED_TIME_SERVICES)) platform_device_register_simple("rtc-efi", 0, NULL, 0); diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c index 4c3986ddcd54..685283bb7327 100644 --- a/drivers/firmware/efi/sysfb_efi.c +++ b/drivers/firmware/efi/sysfb_efi.c @@ -311,11 +311,14 @@ static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { .callback = efifb_swap_width_height, }, { - /* Lenovo IdeaPad Duet 3 10IGL5 with 1200x1920 portrait screen */ + /* + * Lenovo IdeaPad Duet 3 10IGL5 and 10IGL5-LTE with + * 1200x1920 portrait screen + */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), - DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, - "IdeaPad Duet 3 10IGL5"), + /* Non exact match to also match the LTE version */ + DMI_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"), }, .callback = efifb_swap_width_height, }, diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index 38ca190d4a22..e73bae6cb23a 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -539,12 +539,22 @@ static int psci_system_suspend(unsigned long unused) static int psci_system_suspend_enter(suspend_state_t state) { + pm_set_resume_via_firmware(); + return cpu_suspend(0, psci_system_suspend); } +static int psci_system_suspend_begin(suspend_state_t state) +{ + pm_set_suspend_via_firmware(); + + return 0; +} + static const struct platform_suspend_ops psci_suspend_ops = { .valid = suspend_valid_only_mem, .enter = psci_system_suspend_enter, + .begin = psci_system_suspend_begin, }; static void __init psci_init_system_reset2(void) diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index b3596851c719..41a79e43c82b 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2050,7 +2050,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * return 0; if (unlikely(bsize < csize)) { - hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %ld)\n", + hid_warn_ratelimited(hid, "Event data for report %d is incorrect (%d vs %zu)\n", report->id, csize, bsize); return -EINVAL; } @@ -2072,7 +2072,7 @@ int hid_report_raw_event(struct hid_device *hid, enum hid_report_type type, u8 * rsize = max_buffer_size; if (bsize < rsize) { - hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %ld)\n", + hid_warn_ratelimited(hid, "Event data for report %d was too short (%d vs %zu)\n", report->id, rsize, bsize); return -EINVAL; } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 402671567736..3e1e1e861739 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1297,7 +1297,9 @@ static int ipoib_hard_header(struct sk_buff *skb, return IPOIB_HARD_LEN; } -static void ipoib_set_mcast_list(struct net_device *dev) +static void ipoib_set_rx_mode_async(struct net_device *dev, + struct netdev_hw_addr_list *uc, + struct netdev_hw_addr_list *mc) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -2160,7 +2162,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, - .ndo_set_rx_mode = ipoib_set_mcast_list, + .ndo_set_rx_mode_async = ipoib_set_rx_mode_async, .ndo_get_iflink = ipoib_get_iflink, .ndo_set_vf_link_state = ipoib_set_vf_link_state, .ndo_get_vf_config = ipoib_get_vf_config, @@ -2183,7 +2185,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_fix_features = ipoib_fix_features, .ndo_start_xmit = ipoib_start_xmit, .ndo_tx_timeout = ipoib_timeout, - .ndo_set_rx_mode = ipoib_set_mcast_list, + .ndo_set_rx_mode_async = ipoib_set_rx_mode_async, .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, diff --git a/drivers/media/rc/ttusbir.c b/drivers/media/rc/ttusbir.c index 3848ad3a6b85..db2f6698a6c0 100644 --- a/drivers/media/rc/ttusbir.c +++ b/drivers/media/rc/ttusbir.c @@ -191,7 +191,7 @@ static int ttusbir_probe(struct usb_interface *intf, tt = kzalloc_obj(*tt); buffer = kzalloc(5, GFP_KERNEL); rc = rc_allocate_device(RC_DRIVER_IR_RAW); - if (!tt || !rc || buffer) { + if (!tt || !rc || !buffer) { ret = -ENOMEM; goto out; } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 44d670904ad8..3c2a3029b10c 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1023,12 +1023,16 @@ mt7530_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) unsigned int age_count; unsigned int age_unit; - /* Applied timer is (AGE_CNT + 1) * (AGE_UNIT + 1) seconds */ - if (secs < 1 || secs > (AGE_CNT_MAX + 1) * (AGE_UNIT_MAX + 1)) - return -ERANGE; - - /* iterate through all possible age_count to find the closest pair */ - for (tmp_age_count = 0; tmp_age_count <= AGE_CNT_MAX; ++tmp_age_count) { + /* Applied timer is (AGE_CNT + 1) * (AGE_UNIT + 1) seconds. + * The DSA core has already validated the range using + * ds->ageing_time_min and ds->ageing_time_max. + * + * Iterate through all possible age_count values to find the closest + * pair. Start from 1 because the per-entry aging counter is + * initialized to AGE_CNT and a value of 0 means the entry will + * never be aged out. + */ + for (tmp_age_count = 1; tmp_age_count <= AGE_CNT_MAX; ++tmp_age_count) { unsigned int tmp_age_unit = secs / (tmp_age_count + 1) - 1; if (tmp_age_unit <= AGE_UNIT_MAX) { @@ -1296,37 +1300,40 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface) static void mt753x_trap_frames(struct mt7530_priv *priv) { - /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them - * VLAN-untagged. + /* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress + * them with the EG_TAG attribute set to disabled (system default) + * so that any VLAN tags in the frame are not modified by the + * switch egress VLAN tag processing. This preserves VLAN tags + * for reception on VLAN sub-interfaces. */ mt7530_rmw(priv, MT753X_BPC, PAE_BPDU_FR | PAE_EG_TAG_MASK | PAE_PORT_FW_MASK | BPDU_EG_TAG_MASK | BPDU_PORT_FW_MASK, - PAE_BPDU_FR | PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + PAE_BPDU_FR | PAE_EG_TAG(MT7530_VLAN_EG_DISABLED) | PAE_PORT_FW(TO_CPU_FW_CPU_ONLY) | - BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + BPDU_EG_TAG(MT7530_VLAN_EG_DISABLED) | TO_CPU_FW_CPU_ONLY); - /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress - * them VLAN-untagged. + /* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and + * egress them with EG_TAG disabled. */ mt7530_rmw(priv, MT753X_RGAC1, R02_BPDU_FR | R02_EG_TAG_MASK | R02_PORT_FW_MASK | R01_BPDU_FR | R01_EG_TAG_MASK | R01_PORT_FW_MASK, - R02_BPDU_FR | R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R02_BPDU_FR | R02_EG_TAG(MT7530_VLAN_EG_DISABLED) | R02_PORT_FW(TO_CPU_FW_CPU_ONLY) | R01_BPDU_FR | - R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R01_EG_TAG(MT7530_VLAN_EG_DISABLED) | TO_CPU_FW_CPU_ONLY); - /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress - * them VLAN-untagged. + /* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and + * egress them with EG_TAG disabled. */ mt7530_rmw(priv, MT753X_RGAC2, R0E_BPDU_FR | R0E_EG_TAG_MASK | R0E_PORT_FW_MASK | R03_BPDU_FR | R03_EG_TAG_MASK | R03_PORT_FW_MASK, - R0E_BPDU_FR | R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R0E_BPDU_FR | R0E_EG_TAG(MT7530_VLAN_EG_DISABLED) | R0E_PORT_FW(TO_CPU_FW_CPU_ONLY) | R03_BPDU_FR | - R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) | + R03_EG_TAG(MT7530_VLAN_EG_DISABLED) | TO_CPU_FW_CPU_ONLY); } @@ -1616,6 +1623,49 @@ mt7530_port_bridge_join(struct dsa_switch *ds, int port, return 0; } +static int +mt7530_vlan_cmd(struct mt7530_priv *priv, enum mt7530_vlan_cmd cmd, u16 vid) +{ + struct mt7530_dummy_poll p; + u32 val; + int ret; + + val = VTCR_BUSY | VTCR_FUNC(cmd) | vid; + mt7530_write(priv, MT7530_VTCR, val); + + INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_VTCR); + ret = readx_poll_timeout(_mt7530_read, &p, val, + !(val & VTCR_BUSY), 20, 20000); + if (ret < 0) { + dev_err(priv->dev, "poll timeout\n"); + return ret; + } + + val = mt7530_read(priv, MT7530_VTCR); + if (val & VTCR_INVALID) { + dev_err(priv->dev, "read VTCR invalid\n"); + return -EINVAL; + } + + return 0; +} + +static int +mt7530_setup_vlan0(struct mt7530_priv *priv) +{ + u32 val; + + /* Validate the entry with independent learning, keep the original + * ingress tag attribute. + */ + val = IVL_MAC | EG_CON | PORT_MEM(MT7530_ALL_MEMBERS) | FID(FID_BRIDGED) | + VLAN_VALID; + mt7530_write(priv, MT7530_VAWD1, val); + mt7530_write(priv, MT7530_VAWD2, 0); + + return mt7530_vlan_cmd(priv, MT7530_VTCR_WR_VID, 0); +} + static void mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port) { @@ -1641,6 +1691,8 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port) G0_PORT_VID_DEF); for (i = 0; i < priv->ds->num_ports; i++) { + if (i == port) + continue; if (dsa_is_user_port(ds, i) && dsa_port_is_vlan_filtering(dsa_to_port(ds, i))) { all_user_ports_removed = false; @@ -1652,13 +1704,9 @@ mt7530_port_set_vlan_unaware(struct dsa_switch *ds, int port) * the CPU port get out of VLAN filtering mode. */ if (all_user_ports_removed) { - struct dsa_port *dp = dsa_to_port(ds, port); - struct dsa_port *cpu_dp = dp->cpu_dp; - - mt7530_write(priv, MT7530_PCR_P(cpu_dp->index), - PCR_MATRIX(dsa_user_ports(priv->ds))); - mt7530_write(priv, MT7530_PVC_P(cpu_dp->index), PORT_SPEC_TAG - | PVC_EG_TAG(MT7530_VLAN_EG_CONSISTENT)); + mutex_lock(&priv->reg_mutex); + mt7530_setup_vlan0(priv); + mutex_unlock(&priv->reg_mutex); } } @@ -1846,33 +1894,6 @@ mt7530_port_mdb_del(struct dsa_switch *ds, int port, return ret; } -static int -mt7530_vlan_cmd(struct mt7530_priv *priv, enum mt7530_vlan_cmd cmd, u16 vid) -{ - struct mt7530_dummy_poll p; - u32 val; - int ret; - - val = VTCR_BUSY | VTCR_FUNC(cmd) | vid; - mt7530_write(priv, MT7530_VTCR, val); - - INIT_MT7530_DUMMY_POLL(&p, priv, MT7530_VTCR); - ret = readx_poll_timeout(_mt7530_read, &p, val, - !(val & VTCR_BUSY), 20, 20000); - if (ret < 0) { - dev_err(priv->dev, "poll timeout\n"); - return ret; - } - - val = mt7530_read(priv, MT7530_VTCR); - if (val & VTCR_INVALID) { - dev_err(priv->dev, "read VTCR invalid\n"); - return -EINVAL; - } - - return 0; -} - static int mt7530_port_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering, struct netlink_ext_ack *extack) @@ -1977,21 +1998,6 @@ mt7530_hw_vlan_update(struct mt7530_priv *priv, u16 vid, mt7530_vlan_cmd(priv, MT7530_VTCR_WR_VID, vid); } -static int -mt7530_setup_vlan0(struct mt7530_priv *priv) -{ - u32 val; - - /* Validate the entry with independent learning, keep the original - * ingress tag attribute. - */ - val = IVL_MAC | EG_CON | PORT_MEM(MT7530_ALL_MEMBERS) | FID(FID_BRIDGED) | - VLAN_VALID; - mt7530_write(priv, MT7530_VAWD1, val); - - return mt7530_vlan_cmd(priv, MT7530_VTCR_WR_VID, 0); -} - static int mt7530_port_vlan_add(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, @@ -2004,9 +2010,18 @@ mt7530_port_vlan_add(struct dsa_switch *ds, int port, mutex_lock(&priv->reg_mutex); + /* VID 0 is managed exclusively by mt7530_setup_vlan0() for + * VLAN-unaware bridge operation. Don't let the bridge overwrite + * its EG_CON flag with VTAG_EN and corrupt PORT_MEM. + */ + if (vlan->vid == 0) + goto skip_vlan_table; + mt7530_hw_vlan_entry_init(&new_entry, port, untagged); mt7530_hw_vlan_update(priv, vlan->vid, &new_entry, mt7530_hw_vlan_add); +skip_vlan_table: + if (pvid) { priv->ports[port].pvid = vlan->vid; @@ -2046,10 +2061,15 @@ mt7530_port_vlan_del(struct dsa_switch *ds, int port, mutex_lock(&priv->reg_mutex); + /* VID 0 is managed exclusively by mt7530_setup_vlan0(). */ + if (vlan->vid == 0) + goto skip_vlan_table; + mt7530_hw_vlan_entry_init(&target_entry, port, 0); mt7530_hw_vlan_update(priv, vlan->vid, &target_entry, mt7530_hw_vlan_del); +skip_vlan_table: /* PVID is being restored to the default whenever the PVID port * is being removed from the VLAN. */ @@ -2427,7 +2447,10 @@ mt7530_setup(struct dsa_switch *ds) } ds->assisted_learning_on_cpu_port = true; + ds->untag_vlan_aware_bridge_pvid = true; ds->mtu_enforcement_ingress = true; + ds->ageing_time_min = 2 * 1000; + ds->ageing_time_max = (AGE_CNT_MAX + 1) * (AGE_UNIT_MAX + 1) * 1000; if (priv->id == ID_MT7530) { regulator_set_voltage(priv->core_pwr, 1000000, 1000000); @@ -2616,7 +2639,10 @@ mt7531_setup_common(struct dsa_switch *ds) int ret, i; ds->assisted_learning_on_cpu_port = true; + ds->untag_vlan_aware_bridge_pvid = true; ds->mtu_enforcement_ingress = true; + ds->ageing_time_min = 2 * 1000; + ds->ageing_time_max = (AGE_CNT_MAX + 1) * (AGE_UNIT_MAX + 1) * 1000; mt753x_trap_frames(priv); diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c new file mode 100644 index 000000000000..f23be7425daf --- /dev/null +++ b/drivers/net/ethernet/3com/3c509.c @@ -0,0 +1,1543 @@ +// SPDX-License-Identifier: GPL-2.0 +/* 3c509.c: A 3c509 EtherLink3 ethernet driver for linux. */ +/* + * Written 1993-2000 by Donald Becker. + * + * Copyright 1994-2000 by Donald Becker. + * Copyright 1993 United States Government as represented by the + * Director, National Security Agency. This software may be used and + * distributed according to the terms of the GNU General Public License, + * incorporated herein by reference. + * + * This driver is for the 3Com EtherLinkIII series. + * + * The author may be reached as becker@scyld.com, or C/O + * Scyld Computing Corporation + * 410 Severn Ave., Suite 210 + * Annapolis MD 21403 + * + * Known limitations: + * Because of the way 3c509 ISA detection works it's difficult to predict + * a priori which of several ISA-mode cards will be detected first. + * + * This driver does not use predictive interrupt mode, resulting in higher + * packet latency but lower overhead. If interrupts are disabled for an + * unusually long time it could also result in missed packets, but in + * practice this rarely happens. + * + * + * FIXES: + * Alan Cox: Removed the 'Unexpected interrupt' bug. + * Michael Meskes: Upgraded to Donald Becker's version 1.07. + * Alan Cox: Increased the eeprom delay. Regardless of + * what the docs say some people definitely + * get problems with lower (but in card spec) + * delays. + * v1.10 4/21/97 Fixed module code so that multiple cards may be + * detected, other cleanups. -djb + * Andrea Arcangeli: Upgraded to Donald Becker's version 1.12. + * Rick Payne: Fixed SMP race condition. + * v1.13 9/8/97 Made 'max_interrupt_work' an insmod-settable + * variable. -djb + * v1.14 10/15/97 Avoided waiting..discard message for fast + * machines. -djb + * v1.15 1/31/98 Faster recovery for Tx errors. -djb + * v1.16 2/3/98 Different ID port handling to avoid sound + * cards. -djb + * v1.18 12Mar2001 Andrew Morton + * - Avoid bogus detect of 3c590's (Andrzej Krzysztofowicz) + * - Reviewed against 1.18 from scyld.com + * v1.18a 17Nov2001 Jeff Garzik + * - ethtool support. + * v1.18b 1Mar2002 Zwane Mwaikambo + * - Power Management support. + * v1.18c 1Mar2002 David Ruggiero + * - Full duplex support. + * v1.19 16Oct2002 Zwane Mwaikambo + * - Additional ethtool features. + * v1.19a 28Oct2002 David Ruggiero + * - Increase *read_eeprom udelay to workaround oops with + * 2 cards. + * v1.19b 08Nov2002 Marc Zyngier + * - Introduce driver model for EISA cards. + * v1.20 04Feb2008 Ondrej Zary + * - convert to isa_driver and pnp_driver and some + * cleanups. + */ + +#define DRV_NAME "3c509" + +/* A few values that may be tweaked. */ + +/* Time in jiffies before concluding the transmitter is hung. */ +#define TX_TIMEOUT (400 * HZ / 1000) + +#include +#include /* for udelay() */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#ifdef EL3_DEBUG +static int el3_debug = EL3_DEBUG; +#else +static int el3_debug = 2; +#endif + +/* Used to do a global count of all the cards in the system. Must be + * a global variable so that the eisa probe routines can increment it. + */ +static int el3_cards; +#define EL3_MAX_CARDS 8 + +/* To minimize the size of the driver source I only define operating + * constants if they are used several times. You'll need the manual + * anyway if you want to understand driver details. + */ +/* Offsets from base I/O address. */ +#define EL3_DATA 0x00 +#define EL3_CMD 0x0e +#define EL3_STATUS 0x0e +#define EEPROM_READ 0x80 + +#define EL3_IO_EXTENT 16 + +#define EL3WINDOW(win_num) outw(SELECT_WINDOW + (win_num), ioaddr + EL3_CMD) + +/* The top five bits written to EL3_CMD are a command, the lower + * 11 bits are the parameter, if applicable. + */ +enum c509cmd { + TOTAL_RESET = 0 << 11, + SELECT_WINDOW = 1 << 11, + START_COAX = 2 << 11, + RX_DISABLE = 3 << 11, + RX_ENABLE = 4 << 11, + RX_RESET = 5 << 11, + RX_DISCARD = 8 << 11, + TX_ENABLE = 9 << 11, + TX_DISABLE = 10 << 11, + TX_RESET = 11 << 11, + FAKE_INTR = 12 << 11, + ACK_INTR = 13 << 11, + SET_INTR_ENB = 14 << 11, + SET_STATUS_ENB = 15 << 11, + SET_RX_FILTER = 16 << 11, + SET_RX_THRESHOLD = 17 << 11, + SET_TX_THRESHOLD = 18 << 11, + SET_TX_START = 19 << 11, + STATS_ENABLE = 21 << 11, + STATS_DISABLE = 22 << 11, + STOP_COAX = 23 << 11, + POWER_UP = 27 << 11, + POWER_DOWN = 28 << 11, + POWER_AUTO = 29 << 11, +}; + +enum c509status { + INT_LATCH = 0x0001, + ADAPTER_FAILURE = 0x0002, + TX_COMPLETE = 0x0004, + TX_AVAILABLE = 0x0008, + RX_COMPLETE = 0x0010, + RX_EARLY = 0x0020, + INT_REQ = 0x0040, + STATS_FULL = 0x0080, + CMD_BUSY = 0x1000, +}; + +/* The SET_RX_FILTER command accepts the following classes: */ +enum rx_filter { + RX_STATION = 1, + RX_MULTICAST = 2, + RX_BROADCAST = 4, + RX_PROM = 8, +}; + +/* Register window 1 offsets, the window used in normal operation. */ +#define TX_FIFO 0x00 +#define RX_FIFO 0x00 +#define RX_STATUS 0x08 +#define TX_STATUS 0x0B +#define TX_FREE 0x0C /* Remaining free bytes in Tx buffer. */ + +#define WN0_CONF_CTRL 0x04 /* Window 0: Configuration control register. */ +#define WN0_ADDR_CONF 0x06 /* Window 0: Address configuration register. */ +#define WN0_IRQ 0x08 /* Window 0: Set IRQ line in bits 12-15. */ +#define WN4_MEDIA 0x0A /* Window 4: Various transcvr/media bits. */ +#define MEDIA_TP 0x00C0 /* Enable link beat and jabber for 10baseT. */ +#define WN4_NETDIAG 0x06 /* Window 4: Net diagnostic. */ +#define FD_ENABLE 0x8000 /* Enable full-duplex ("external loopback"). */ + +/* + * Must be a power of two (we use a binary and in the + * circular queue). + */ +#define SKB_QUEUE_SIZE 64 + +enum el3_cardtype { EL3_ISA, EL3_PNP, EL3_EISA }; + +struct el3_private { + /* for device access */ + spinlock_t lock; + /* skb send-queue */ + int head, size; + struct sk_buff *queue[SKB_QUEUE_SIZE]; + enum el3_cardtype type; +}; + +static int id_port; +static int current_tag; +static struct net_device *el3_devs[EL3_MAX_CARDS]; + +/* Parameters that may be passed into the module. */ +static int debug = -1; +static int irq[] = {-1, -1, -1, -1, -1, -1, -1, -1}; +/* Maximum events (Rx packets, etc.) to handle at each interrupt. */ +static int max_interrupt_work = 10; +#ifdef CONFIG_PNP +static int nopnp; +#endif + +static int el3_common_init(struct net_device *dev); +static void el3_common_remove(struct net_device *dev); +static ushort id_read_eeprom(int index); +static ushort read_eeprom(int ioaddr, int index); +static int el3_open(struct net_device *dev); +static netdev_tx_t el3_start_xmit(struct sk_buff *skb, struct net_device *dev); +static irqreturn_t el3_interrupt(int irq, void *dev_id); +static void update_stats(struct net_device *dev); +static struct net_device_stats *el3_get_stats(struct net_device *dev); +static int el3_rx(struct net_device *dev); +static int el3_close(struct net_device *dev); +static void set_multicast_list(struct net_device *dev); +static void el3_tx_timeout(struct net_device *dev, unsigned int txqueue); +static void el3_down(struct net_device *dev); +static void el3_up(struct net_device *dev); +static const struct ethtool_ops ethtool_ops; +#ifdef CONFIG_PM +static int el3_suspend(struct device *, pm_message_t); +static int el3_resume(struct device *); +#else +#define el3_suspend NULL +#define el3_resume NULL +#endif + +/* Generic device remove for all device types. */ +static int el3_device_remove(struct device *device); +#ifdef CONFIG_NET_POLL_CONTROLLER +static void el3_poll_controller(struct net_device *dev); +#endif + +/* Return 0 on success, 1 on error, 2 when found already detected PnP card. */ +static int el3_isa_id_sequence(__be16 *phys_addr) +{ + short lrs_state = 0xff; + int i; + + /* ISA boards are detected by sending the ID sequence to the + * ID_PORT. We find cards past the first by setting the 'current_tag' + * on cards as they are found. Cards with their tag set will not + * respond to subsequent ID sequences. + */ + outb(0x00, id_port); + outb(0x00, id_port); + for (i = 0; i < 255; i++) { + outb(lrs_state, id_port); + lrs_state <<= 1; + lrs_state = lrs_state & 0x100 ? lrs_state ^ 0xcf : lrs_state; + } + /* For the first probe, clear all board's tag registers. */ + if (current_tag == 0) + outb(0xd0, id_port); + else /* Otherwise kill off already-found boards. */ + outb(0xd8, id_port); + if (id_read_eeprom(7) != 0x6d50) + return 1; + /* Read in EEPROM data, which does contention-select. + * Only the lowest address board will stay "on-line". + * 3Com got the byte order backwards. + */ + for (i = 0; i < 3; i++) + phys_addr[i] = htons(id_read_eeprom(i)); +#ifdef CONFIG_PNP + if (!nopnp) { + /* The ISA PnP 3c509 cards respond to the ID sequence too. + * This check is needed in order not to register them twice. + */ + for (i = 0; i < el3_cards; i++) { + struct el3_private *lp = netdev_priv(el3_devs[i]); + + if (lp->type == EL3_PNP && + ether_addr_equal((u8 *)phys_addr, + el3_devs[i]->dev_addr)) { + if (el3_debug > 3) + pr_debug("3c509 with address %02x %02x %02x %02x %02x %02x was found by ISAPnP\n", + phys_addr[0] & 0xff, + phys_addr[0] >> 8, + phys_addr[1] & 0xff, + phys_addr[1] >> 8, + phys_addr[2] & 0xff, + phys_addr[2] >> 8); + /* Set the adaptor tag so that the next card + * can be found. + */ + outb(0xd0 + ++current_tag, id_port); + return 2; + } + } + } +#endif /* CONFIG_PNP */ + return 0; +} + +static void el3_dev_fill(struct net_device *dev, __be16 *phys_addr, int ioaddr, + int irq, int if_port, enum el3_cardtype type) +{ + struct el3_private *lp = netdev_priv(dev); + + eth_hw_addr_set(dev, (u8 *)phys_addr); + dev->base_addr = ioaddr; + dev->irq = irq; + dev->if_port = if_port; + lp->type = type; +} + +static int el3_isa_match(struct device *pdev, unsigned int ndev) +{ + int ioaddr, isa_irq, if_port, err; + struct net_device *dev; + unsigned int iobase; + __be16 phys_addr[3]; + + while ((err = el3_isa_id_sequence(phys_addr)) == 2) + ; /* Skip to next card when PnP card found */ + if (err == 1) + return 0; + + iobase = id_read_eeprom(8); + if_port = iobase >> 14; + ioaddr = 0x200 + ((iobase & 0x1f) << 4); + if (irq[el3_cards] > 1 && irq[el3_cards] < 16) + isa_irq = irq[el3_cards]; + else + isa_irq = id_read_eeprom(9) >> 12; + + dev = alloc_etherdev(sizeof(struct el3_private)); + if (!dev) + return -ENOMEM; + + SET_NETDEV_DEV(dev, pdev); + + if (!request_region(ioaddr, EL3_IO_EXTENT, "3c509-isa")) { + free_netdev(dev); + return 0; + } + + /* Set the adaptor tag so that the next card can be found. */ + outb(0xd0 + ++current_tag, id_port); + + /* Activate the adaptor at the EEPROM location. */ + outb((ioaddr >> 4) | 0xe0, id_port); + + EL3WINDOW(0); + if (inw(ioaddr) != 0x6d50) { + free_netdev(dev); + return 0; + } + + /* Free the interrupt so that some other card can use it. */ + outw(0x0f00, ioaddr + WN0_IRQ); + + el3_dev_fill(dev, phys_addr, ioaddr, isa_irq, if_port, EL3_ISA); + dev_set_drvdata(pdev, dev); + if (el3_common_init(dev)) { + free_netdev(dev); + return 0; + } + + el3_devs[el3_cards++] = dev; + return 1; +} + +static void el3_isa_remove(struct device *pdev, unsigned int ndev) +{ + el3_device_remove(pdev); + dev_set_drvdata(pdev, NULL); +} + +#ifdef CONFIG_PM +static int el3_isa_suspend(struct device *dev, unsigned int n, + pm_message_t state) +{ + current_tag = 0; + return el3_suspend(dev, state); +} + +static int el3_isa_resume(struct device *dev, unsigned int n) +{ + struct net_device *ndev = dev_get_drvdata(dev); + int ioaddr = ndev->base_addr, err; + __be16 phys_addr[3]; + + while ((err = el3_isa_id_sequence(phys_addr)) == 2) + ; /* Skip to next card when PnP card found */ + if (err == 1) + return 0; + /* Set the adaptor tag so that the next card can be found. */ + outb(0xd0 + ++current_tag, id_port); + /* Enable the card */ + outb((ioaddr >> 4) | 0xe0, id_port); + EL3WINDOW(0); + if (inw(ioaddr) != 0x6d50) + return 1; + /* Free the interrupt so that some other card can use it. */ + outw(0x0f00, ioaddr + WN0_IRQ); + return el3_resume(dev); +} +#endif + +static struct isa_driver el3_isa_driver = { + .match = el3_isa_match, + .remove = el3_isa_remove, +#ifdef CONFIG_PM + .suspend = el3_isa_suspend, + .resume = el3_isa_resume, +#endif + .driver = { + .name = "3c509" + }, +}; + +static int isa_registered; + +#ifdef CONFIG_PNP +static const struct pnp_device_id el3_pnp_ids[] = { + { .id = "TCM5090" }, /* 3Com Etherlink III (TP) */ + { .id = "TCM5091" }, /* 3Com Etherlink III */ + { .id = "TCM5094" }, /* 3Com Etherlink III (combo) */ + { .id = "TCM5095" }, /* 3Com Etherlink III (TPO) */ + { .id = "TCM5098" }, /* 3Com Etherlink III (TPC) */ + { .id = "PNP80f7" }, /* 3Com Etherlink III compatible */ + { .id = "PNP80f8" }, /* 3Com Etherlink III compatible */ + { .id = "" } +}; +MODULE_DEVICE_TABLE(pnp, el3_pnp_ids); + +static int el3_pnp_probe(struct pnp_dev *pdev, const struct pnp_device_id *id) +{ + struct net_device *dev = NULL; + int ioaddr, irq, if_port; + __be16 phys_addr[3]; + short i; + int err; + + ioaddr = pnp_port_start(pdev, 0); + if (!request_region(ioaddr, EL3_IO_EXTENT, "3c509-pnp")) + return -EBUSY; + irq = pnp_irq(pdev, 0); + EL3WINDOW(0); + for (i = 0; i < 3; i++) + phys_addr[i] = htons(read_eeprom(ioaddr, i)); + if_port = read_eeprom(ioaddr, 8) >> 14; + dev = alloc_etherdev(sizeof(struct el3_private)); + if (!dev) { + release_region(ioaddr, EL3_IO_EXTENT); + return -ENOMEM; + } + SET_NETDEV_DEV(dev, &pdev->dev); + + el3_dev_fill(dev, phys_addr, ioaddr, irq, if_port, EL3_PNP); + pnp_set_drvdata(pdev, dev); + err = el3_common_init(dev); + + if (err) { + pnp_set_drvdata(pdev, NULL); + free_netdev(dev); + return err; + } + + el3_devs[el3_cards++] = dev; + return 0; +} + +static void el3_pnp_remove(struct pnp_dev *pdev) +{ + el3_common_remove(pnp_get_drvdata(pdev)); + pnp_set_drvdata(pdev, NULL); +} + +#ifdef CONFIG_PM +static int el3_pnp_suspend(struct pnp_dev *pdev, pm_message_t state) +{ + return el3_suspend(&pdev->dev, state); +} + +static int el3_pnp_resume(struct pnp_dev *pdev) +{ + return el3_resume(&pdev->dev); +} +#endif + +static struct pnp_driver el3_pnp_driver = { + .name = "3c509", + .id_table = el3_pnp_ids, + .probe = el3_pnp_probe, + .remove = el3_pnp_remove, +#ifdef CONFIG_PM + .suspend = el3_pnp_suspend, + .resume = el3_pnp_resume, +#endif +}; + +static int pnp_registered; +#endif /* CONFIG_PNP */ + +#ifdef CONFIG_EISA +static const struct eisa_device_id el3_eisa_ids[] = { + { "TCM5090" }, + { "TCM5091" }, + { "TCM5092" }, + { "TCM5093" }, + { "TCM5094" }, + { "TCM5095" }, + { "TCM5098" }, + { "" } +}; +MODULE_DEVICE_TABLE(eisa, el3_eisa_ids); + +static int el3_eisa_probe(struct device *device); + +static struct eisa_driver el3_eisa_driver = { + .id_table = el3_eisa_ids, + .driver = { + .name = "3c579", + .probe = el3_eisa_probe, + .remove = el3_device_remove, + .suspend = el3_suspend, + .resume = el3_resume, + } +}; + +static int eisa_registered; +#endif + +static const struct net_device_ops netdev_ops = { + .ndo_open = el3_open, + .ndo_stop = el3_close, + .ndo_start_xmit = el3_start_xmit, + .ndo_get_stats = el3_get_stats, + .ndo_set_rx_mode = set_multicast_list, + .ndo_tx_timeout = el3_tx_timeout, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = el3_poll_controller, +#endif +}; + +static int el3_common_init(struct net_device *dev) +{ + static const char *const if_names[] = { + "10baseT", "AUI", "undefined", "BNC" + }; + struct el3_private *lp = netdev_priv(dev); + int err; + + spin_lock_init(&lp->lock); + + if (dev->mem_start & 0x05) { /* xcvr codes 1/3/4/12 */ + dev->if_port = (dev->mem_start & 0x0f); + } else { /* xcvr codes 0/8 */ + /* use eeprom value, but save user's full-duplex selection */ + dev->if_port |= (dev->mem_start & 0x08); + } + + /* The EL3-specific entries in the device structure. */ + dev->netdev_ops = &netdev_ops; + dev->watchdog_timeo = TX_TIMEOUT; + dev->ethtool_ops = ðtool_ops; + + err = register_netdev(dev); + if (err) { + pr_err("Failed to register 3c5x9 at %#3.3lx, IRQ %d.\n", + dev->base_addr, dev->irq); + release_region(dev->base_addr, EL3_IO_EXTENT); + return err; + } + + pr_info("%s: 3c5x9 found at %#3.3lx, %s port, address %pM, IRQ %d.\n", + dev->name, dev->base_addr, if_names[(dev->if_port & 0x03)], + dev->dev_addr, dev->irq); + + return 0; +} + +static void el3_common_remove(struct net_device *dev) +{ + unregister_netdev(dev); + release_region(dev->base_addr, EL3_IO_EXTENT); + free_netdev(dev); +} + +#ifdef CONFIG_EISA +static int el3_eisa_probe(struct device *device) +{ + struct net_device *dev = NULL; + struct eisa_device *edev; + int ioaddr, irq, if_port; + __be16 phys_addr[3]; + short i; + int err; + + /* Yeepee, The driver framework is calling us ! */ + edev = to_eisa_device(device); + ioaddr = edev->base_addr; + + if (!request_region(ioaddr, EL3_IO_EXTENT, "3c579-eisa")) + return -EBUSY; + + /* Change the register set to the configuration window 0. */ + outw(SELECT_WINDOW | 0, ioaddr + 0xC80 + EL3_CMD); + + irq = inw(ioaddr + WN0_IRQ) >> 12; + if_port = inw(ioaddr + 6) >> 14; + for (i = 0; i < 3; i++) + phys_addr[i] = htons(read_eeprom(ioaddr, i)); + + /* Restore the "Product ID" to the EEPROM read register. */ + read_eeprom(ioaddr, 3); + + dev = alloc_etherdev(sizeof(struct el3_private)); + if (!dev) { + release_region(ioaddr, EL3_IO_EXTENT); + return -ENOMEM; + } + + SET_NETDEV_DEV(dev, device); + + el3_dev_fill(dev, phys_addr, ioaddr, irq, if_port, EL3_EISA); + eisa_set_drvdata(edev, dev); + err = el3_common_init(dev); + + if (err) { + eisa_set_drvdata(edev, NULL); + free_netdev(dev); + return err; + } + + el3_devs[el3_cards++] = dev; + return 0; +} +#endif + +/* This remove works for all device types. + * + * The net dev must be stored in the driver data field. + */ +static int el3_device_remove(struct device *device) +{ + struct net_device *dev; + + dev = dev_get_drvdata(device); + + el3_common_remove(dev); + return 0; +} + +/* Read a word from the EEPROM using the regular EEPROM access register. + * Assume that we are in register window zero. + */ +static ushort read_eeprom(int ioaddr, int index) +{ + outw(EEPROM_READ + index, ioaddr + 10); + /* Pause for at least 162 us for the read to take place. + * Some chips seem to require much longer. + */ + mdelay(2); + return inw(ioaddr + 12); +} + +/* Read a word from the EEPROM when in the ISA ID probe state. */ +static ushort id_read_eeprom(int index) +{ + int bit, word = 0; + + /* Issue read command, and pause for at least 162 us for it to + * complete. Assume extra-fast 16MHz bus. + */ + outb(EEPROM_READ + index, id_port); + + /* Pause for at least 162 us for the read to take place. + * Some chips seem to require much longer. + */ + mdelay(4); + + for (bit = 15; bit >= 0; bit--) + word = (word << 1) + (inb(id_port) & 0x01); + + if (el3_debug > 3) + pr_debug(" 3c509 EEPROM word %d %#4.4x.\n", index, word); + + return word; +} + +static int el3_open(struct net_device *dev) +{ + int ioaddr = dev->base_addr; + int i; + + outw(TX_RESET, ioaddr + EL3_CMD); + outw(RX_RESET, ioaddr + EL3_CMD); + outw(SET_STATUS_ENB | 0x00, ioaddr + EL3_CMD); + + i = request_irq(dev->irq, el3_interrupt, 0, dev->name, dev); + if (i) + return i; + + EL3WINDOW(0); + if (el3_debug > 3) + pr_debug("%s: Opening, IRQ %d status@%x %4.4x.\n", + dev->name, dev->irq, + ioaddr + EL3_STATUS, inw(ioaddr + EL3_STATUS)); + + el3_up(dev); + + if (el3_debug > 3) + pr_debug("%s: Opened 3c509 IRQ %d status %4.4x.\n", + dev->name, dev->irq, inw(ioaddr + EL3_STATUS)); + + return 0; +} + +static void el3_tx_timeout(struct net_device *dev, unsigned int txqueue) +{ + int ioaddr = dev->base_addr; + + /* Transmitter timeout, serious problems. */ + pr_warn("%s: transmit timed out, Tx_status %2.2x status %4.4x Tx FIFO room %d\n", + dev->name, inb(ioaddr + TX_STATUS), inw(ioaddr + EL3_STATUS), + inw(ioaddr + TX_FREE)); + dev->stats.tx_errors++; + netif_trans_update(dev); /* prevent tx timeout */ + /* Issue TX_RESET and TX_START commands. */ + outw(TX_RESET, ioaddr + EL3_CMD); + outw(TX_ENABLE, ioaddr + EL3_CMD); + netif_wake_queue(dev); +} + +static netdev_tx_t el3_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct el3_private *lp = netdev_priv(dev); + int ioaddr = dev->base_addr; + unsigned long flags; + + netif_stop_queue(dev); + + dev->stats.tx_bytes += skb->len; + + if (el3_debug > 4) { + pr_debug("%s: el3_start_xmit(length = %u) called, status %4.4x.\n", + dev->name, skb->len, inw(ioaddr + EL3_STATUS)); + } + /* + * We lock the driver against other processors. Note + * we don't need to lock versus the IRQ as we suspended + * that. This means that we lose the ability to take + * an RX during a TX upload. That sucks a bit with SMP + * on an original 3c509 (2K buffer). + * + * Using disable_irq stops us crapping on other + * time sensitive devices. + */ + + spin_lock_irqsave(&lp->lock, flags); + + /* Put out the doubleword header... */ + outw(skb->len, ioaddr + TX_FIFO); + outw(0x00, ioaddr + TX_FIFO); + /* ... and the packet rounded to a doubleword. */ + outsl(ioaddr + TX_FIFO, skb->data, (skb->len + 3) >> 2); + + if (inw(ioaddr + TX_FREE) > 1536) { + netif_start_queue(dev); + } else { + /* Interrupt us when the FIFO has room for max-sized packet. */ + outw(SET_TX_THRESHOLD + 1536, ioaddr + EL3_CMD); + } + + spin_unlock_irqrestore(&lp->lock, flags); + + dev_consume_skb_any(skb); + + /* Clear the Tx status stack. */ + { + short tx_status; + int i = 4; + + while (--i > 0 && (tx_status = inb(ioaddr + TX_STATUS)) > 0) { + if (tx_status & 0x38) + dev->stats.tx_aborted_errors++; + if (tx_status & 0x30) + outw(TX_RESET, ioaddr + EL3_CMD); + if (tx_status & 0x3C) + outw(TX_ENABLE, ioaddr + EL3_CMD); + /* Pop the status stack. */ + outb(0x00, ioaddr + TX_STATUS); + } + } + return NETDEV_TX_OK; +} + +/* The EL3 interrupt handler. */ +static irqreturn_t el3_interrupt(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + int i = max_interrupt_work; + struct el3_private *lp; + int ioaddr, status; + + lp = netdev_priv(dev); + spin_lock(&lp->lock); + + ioaddr = dev->base_addr; + + if (el3_debug > 4) { + status = inw(ioaddr + EL3_STATUS); + pr_debug("%s: interrupt, status %4.4x.\n", dev->name, status); + } + + while ((status = inw(ioaddr + EL3_STATUS)) & + (INT_LATCH | RX_COMPLETE | STATS_FULL)) { + + if (status & RX_COMPLETE) + el3_rx(dev); + + if (status & TX_AVAILABLE) { + if (el3_debug > 5) + pr_debug(" TX room bit was handled.\n"); + /* There's room in the FIFO for a full-sized packet. */ + outw(ACK_INTR | TX_AVAILABLE, ioaddr + EL3_CMD); + netif_wake_queue(dev); + } + if (status & + (ADAPTER_FAILURE | RX_EARLY | STATS_FULL | TX_COMPLETE)) { + /* Handle all uncommon interrupts. */ + if (status & STATS_FULL) { + /* Empty statistics. */ + update_stats(dev); + } + if (status & RX_EARLY) { + /* Rx early is unused. */ + el3_rx(dev); + outw(ACK_INTR | RX_EARLY, ioaddr + EL3_CMD); + } + if (status & TX_COMPLETE) { + /* Really Tx error. */ + short tx_status; + int i = 4; + + while (--i > 0 && + ((tx_status = inb(ioaddr + TX_STATUS)) + > 0)) { + if (tx_status & 0x38) + dev->stats.tx_aborted_errors++; + if (tx_status & 0x30) + outw(TX_RESET, + ioaddr + EL3_CMD); + if (tx_status & 0x3C) + outw(TX_ENABLE, + ioaddr + EL3_CMD); + /* Pop the status stack. */ + outb(0x00, ioaddr + TX_STATUS); + } + } + if (status & ADAPTER_FAILURE) { + /* Adapter failure requires Rx reset + * and reinit. + */ + outw(RX_RESET, ioaddr + EL3_CMD); + /* Set the Rx filter to the current state. */ + outw((SET_RX_FILTER | RX_STATION | + RX_BROADCAST | + (dev->flags & IFF_ALLMULTI ? + RX_MULTICAST : 0) | + (dev->flags & IFF_PROMISC ? + RX_PROM : 0)), + ioaddr + EL3_CMD); + /* Re-enable the receiver. */ + outw(RX_ENABLE, ioaddr + EL3_CMD); + outw(ACK_INTR | ADAPTER_FAILURE, + ioaddr + EL3_CMD); + } + } + + if (--i < 0) { + pr_err("%s: Infinite loop in interrupt, status %4.4x.\n", + dev->name, status); + /* Clear all interrupts. */ + outw(ACK_INTR | 0xFF, ioaddr + EL3_CMD); + break; + } + /* Acknowledge the IRQ. */ + outw(ACK_INTR | INT_REQ | INT_LATCH, ioaddr + EL3_CMD); + } + + if (el3_debug > 4) { + pr_debug("%s: exiting interrupt, status %4.4x.\n", dev->name, + inw(ioaddr + EL3_STATUS)); + } + spin_unlock(&lp->lock); + return IRQ_HANDLED; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +/* + * Polling receive - used by netconsole and other diagnostic tools + * to allow network i/o with interrupts disabled. + */ +static void el3_poll_controller(struct net_device *dev) +{ + disable_irq(dev->irq); + el3_interrupt(dev->irq, dev); + enable_irq(dev->irq); +} +#endif + +static struct net_device_stats *el3_get_stats(struct net_device *dev) +{ + struct el3_private *lp = netdev_priv(dev); + unsigned long flags; + + /* This is fast enough not to bother with disable IRQ stuff. */ + spin_lock_irqsave(&lp->lock, flags); + update_stats(dev); + spin_unlock_irqrestore(&lp->lock, flags); + return &dev->stats; +} + +/* Update statistics. We change to register window 6, so this should be run + * single-threaded if the device is active. This is expected to be a rare + * operation, and it's simpler for the rest of the driver to assume that + * window 1 is always valid rather than use a special window-state variable. + */ +static void update_stats(struct net_device *dev) +{ + int ioaddr = dev->base_addr; + + if (el3_debug > 5) + pr_debug(" Updating the statistics.\n"); + /* Turn off statistics updates while reading. */ + outw(STATS_DISABLE, ioaddr + EL3_CMD); + /* Switch to the stats window, and read everything. */ + EL3WINDOW(6); + dev->stats.tx_carrier_errors += inb(ioaddr + 0); + dev->stats.tx_heartbeat_errors += inb(ioaddr + 1); + /* Multiple collisions. */ inb(ioaddr + 2); + dev->stats.collisions += inb(ioaddr + 3); + dev->stats.tx_window_errors += inb(ioaddr + 4); + dev->stats.rx_fifo_errors += inb(ioaddr + 5); + dev->stats.tx_packets += inb(ioaddr + 6); + /* Rx packets */ inb(ioaddr + 7); + /* Tx deferrals */ inb(ioaddr + 8); + inw(ioaddr + 10); /* Total Rx and Tx octets. */ + inw(ioaddr + 12); + + /* Back to window 1, and turn statistics back on. */ + EL3WINDOW(1); + outw(STATS_ENABLE, ioaddr + EL3_CMD); +} + +static int el3_rx(struct net_device *dev) +{ + int ioaddr = dev->base_addr; + short rx_status; + + if (el3_debug > 5) + pr_debug(" In rx_packet(), status %4.4x, rx_status %4.4x.\n", + inw(ioaddr + EL3_STATUS), inw(ioaddr + RX_STATUS)); + while ((rx_status = inw(ioaddr + RX_STATUS)) > 0) { + if (rx_status & 0x4000) { + /* Error, update stats. */ + short error = rx_status & 0x3800; + + outw(RX_DISCARD, ioaddr + EL3_CMD); + dev->stats.rx_errors++; + switch (error) { + case 0x0000: + dev->stats.rx_over_errors++; + break; + case 0x0800: + dev->stats.rx_length_errors++; + break; + case 0x1000: + dev->stats.rx_frame_errors++; + break; + case 0x1800: + dev->stats.rx_length_errors++; + break; + case 0x2000: + dev->stats.rx_frame_errors++; + break; + case 0x2800: + dev->stats.rx_crc_errors++; break; + } + } else { + short pkt_len = rx_status & 0x7ff; + struct sk_buff *skb; + + skb = netdev_alloc_skb(dev, pkt_len + 5); + if (el3_debug > 4) + pr_debug("Receiving packet size %d status %4.4x.\n", + pkt_len, rx_status); + if (skb) { + /* Align IP on 16 byte. */ + skb_reserve(skb, 2); + + /* 'skb->data' points to the start of sk_buff + * data area. + */ + insl(ioaddr + RX_FIFO, skb_put(skb, pkt_len), + (pkt_len + 3) >> 2); + + /* Pop top Rx packet. */ + outw(RX_DISCARD, ioaddr + EL3_CMD); + skb->protocol = eth_type_trans(skb, dev); + netif_rx(skb); + dev->stats.rx_bytes += pkt_len; + dev->stats.rx_packets++; + continue; + } + outw(RX_DISCARD, ioaddr + EL3_CMD); + dev->stats.rx_dropped++; + if (el3_debug) + pr_debug("%s: Couldn't allocate a sk_buff of size %d.\n", + dev->name, pkt_len); + } + inw(ioaddr + EL3_STATUS); /* Delay. */ + while (inw(ioaddr + EL3_STATUS) & 0x1000) + pr_debug(" Waiting for 3c509 to discard packet, status %x.\n", + inw(ioaddr + EL3_STATUS)); + } + + return 0; +} + +/* Set or clear the multicast filter for this adaptor. */ +static void set_multicast_list(struct net_device *dev) +{ + struct el3_private *lp = netdev_priv(dev); + int ioaddr = dev->base_addr; + int mc_count = netdev_mc_count(dev); + unsigned long flags; + + if (el3_debug > 1) { + static int old; + + if (old != mc_count) { + old = mc_count; + pr_debug("%s: Setting Rx mode to %d addresses.\n", + dev->name, mc_count); + } + } + spin_lock_irqsave(&lp->lock, flags); + if (dev->flags & IFF_PROMISC) { + outw((SET_RX_FILTER | RX_STATION | RX_MULTICAST | + RX_BROADCAST | RX_PROM), + ioaddr + EL3_CMD); + } else if (mc_count || (dev->flags & IFF_ALLMULTI)) { + outw(SET_RX_FILTER | RX_STATION | RX_MULTICAST | RX_BROADCAST, + ioaddr + EL3_CMD); + } else { + outw(SET_RX_FILTER | RX_STATION | RX_BROADCAST, + ioaddr + EL3_CMD); + } + spin_unlock_irqrestore(&lp->lock, flags); +} + +static int el3_close(struct net_device *dev) +{ + struct el3_private *lp = netdev_priv(dev); + int ioaddr = dev->base_addr; + + if (el3_debug > 2) + pr_debug("%s: Shutting down ethercard.\n", dev->name); + + el3_down(dev); + + free_irq(dev->irq, dev); + /* Switching back to window 0 disables the IRQ. */ + EL3WINDOW(0); + if (lp->type != EL3_EISA) { + /* But we explicitly zero the IRQ line select anyway. Don't do + * it on EISA cards, it prevents the module from getting an + * IRQ after unload+reload... + */ + outw(0x0f00, ioaddr + WN0_IRQ); + } + + return 0; +} + +static int el3_link_ok(struct net_device *dev) +{ + int ioaddr = dev->base_addr; + u16 tmp; + + EL3WINDOW(4); + tmp = inw(ioaddr + WN4_MEDIA); + EL3WINDOW(1); + return tmp & (1 << 11); +} + +static void el3_netdev_get_ecmd(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + int ioaddr = dev->base_addr; + u32 supported; + u16 tmp; + + EL3WINDOW(0); + /* Obtain current transceiver via WN4_MEDIA? */ + tmp = inw(ioaddr + WN0_ADDR_CONF); + switch (tmp >> 14) { + case 0: + cmd->base.port = PORT_TP; + break; + case 1: + cmd->base.port = PORT_AUI; + break; + case 3: + cmd->base.port = PORT_BNC; + break; + default: + break; + } + + cmd->base.duplex = DUPLEX_HALF; + supported = 0; + tmp = inw(ioaddr + WN0_CONF_CTRL); + if (tmp & (1 << 13)) + supported |= SUPPORTED_AUI; + if (tmp & (1 << 12)) + supported |= SUPPORTED_BNC; + if (tmp & (1 << 9)) { + supported |= SUPPORTED_TP | SUPPORTED_10baseT_Half | + SUPPORTED_10baseT_Full; /* hmm... */ + EL3WINDOW(4); + tmp = inw(ioaddr + WN4_NETDIAG); + if (tmp & FD_ENABLE) + cmd->base.duplex = DUPLEX_FULL; + } + + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + supported); + cmd->base.speed = SPEED_10; + EL3WINDOW(1); +} + +static int el3_netdev_set_ecmd(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) +{ + int ioaddr = dev->base_addr; + u16 tmp; + + if (cmd->base.speed != SPEED_10) + return -EINVAL; + if (cmd->base.duplex != DUPLEX_HALF && cmd->base.duplex != DUPLEX_FULL) + return -EINVAL; + + /* change XCVR type */ + EL3WINDOW(0); + tmp = inw(ioaddr + WN0_ADDR_CONF); + switch (cmd->base.port) { + case PORT_TP: + tmp &= ~(3 << 14); + dev->if_port = 0; + break; + case PORT_AUI: + tmp &= ~(3 << 14); + tmp |= 1 << 14; + dev->if_port = 1; + break; + case PORT_BNC: + tmp |= 3 << 14; + dev->if_port = 3; + break; + default: + return -EINVAL; + } + + outw(tmp, ioaddr + WN0_ADDR_CONF); + if (dev->if_port == 3) { + /* Fire up the DC-DC converter if BNC gets enabled. */ + tmp = inw(ioaddr + WN0_ADDR_CONF); + if (tmp & (3 << 14)) { + outw(START_COAX, ioaddr + EL3_CMD); + udelay(800); + } else { + return -EIO; + } + } + + EL3WINDOW(4); + tmp = inw(ioaddr + WN4_NETDIAG); + if (cmd->base.duplex == DUPLEX_FULL) + tmp |= FD_ENABLE; + else + tmp &= ~FD_ENABLE; + outw(tmp, ioaddr + WN4_NETDIAG); + EL3WINDOW(1); + + return 0; +} + +static void el3_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strscpy(info->driver, DRV_NAME, sizeof(info->driver)); +} + +static int el3_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct el3_private *lp = netdev_priv(dev); + + spin_lock_irq(&lp->lock); + el3_netdev_get_ecmd(dev, cmd); + spin_unlock_irq(&lp->lock); + return 0; +} + +static int el3_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) +{ + struct el3_private *lp = netdev_priv(dev); + int ret; + + spin_lock_irq(&lp->lock); + ret = el3_netdev_set_ecmd(dev, cmd); + spin_unlock_irq(&lp->lock); + return ret; +} + +static u32 el3_get_link(struct net_device *dev) +{ + struct el3_private *lp = netdev_priv(dev); + u32 ret; + + spin_lock_irq(&lp->lock); + ret = el3_link_ok(dev); + spin_unlock_irq(&lp->lock); + return ret; +} + +static u32 el3_get_msglevel(struct net_device *dev) +{ + return el3_debug; +} + +static void el3_set_msglevel(struct net_device *dev, u32 v) +{ + el3_debug = v; +} + +static const struct ethtool_ops ethtool_ops = { + .get_drvinfo = el3_get_drvinfo, + .get_link = el3_get_link, + .get_msglevel = el3_get_msglevel, + .set_msglevel = el3_set_msglevel, + .get_link_ksettings = el3_get_link_ksettings, + .set_link_ksettings = el3_set_link_ksettings, +}; + +static void el3_down(struct net_device *dev) +{ + int ioaddr = dev->base_addr; + + netif_stop_queue(dev); + + /* Turn off statistics ASAP. We update lp->stats below. */ + outw(STATS_DISABLE, ioaddr + EL3_CMD); + + /* Disable the receiver and transmitter. */ + outw(RX_DISABLE, ioaddr + EL3_CMD); + outw(TX_DISABLE, ioaddr + EL3_CMD); + + if (dev->if_port == 3) { + /* Turn off thinnet power. Green! */ + outw(STOP_COAX, ioaddr + EL3_CMD); + } else if (dev->if_port == 0) { + /* Disable link beat and jabber, if_port may change here next + * open(). + */ + EL3WINDOW(4); + outw(inw(ioaddr + WN4_MEDIA) & ~MEDIA_TP, ioaddr + WN4_MEDIA); + } + + outw(SET_INTR_ENB | 0x0000, ioaddr + EL3_CMD); + + update_stats(dev); +} + +static void el3_up(struct net_device *dev) +{ + int ioaddr = dev->base_addr; + int i, sw_info, net_diag; + + /* Activating the board required and does no harm otherwise. */ + outw(0x0001, ioaddr + 4); + + /* Set the IRQ line. */ + outw((dev->irq << 12) | 0x0f00, ioaddr + WN0_IRQ); + + /* Set the station address in window 2 each time opened. */ + EL3WINDOW(2); + + for (i = 0; i < 6; i++) + outb(dev->dev_addr[i], ioaddr + i); + + if ((dev->if_port & 0x03) == 3) { + /* BNC interface */ + + /* Start the thinnet transceiver. We should really wait + * 50ms... + */ + outw(START_COAX, ioaddr + EL3_CMD); + } else if ((dev->if_port & 0x03) == 0) { + /* 10baseT interface */ + + /* Combine secondary sw_info word (the adapter level) and + * primary sw_info word (duplex setting plus other useless + * bits). + */ + EL3WINDOW(0); + sw_info = (read_eeprom(ioaddr, 0x14) & 0x400f) | + (read_eeprom(ioaddr, 0x0d) & 0xBff0); + + EL3WINDOW(4); + net_diag = inw(ioaddr + WN4_NETDIAG); + /* Temporarily assume full-duplex will be set. */ + net_diag = (net_diag | FD_ENABLE); + pr_info("%s: ", dev->name); + switch (dev->if_port & 0x0c) { + case 12: + /* Force full-duplex mode if 3c5x9b. */ + if (sw_info & 0x000f) { + pr_cont("Forcing 3c5x9b full-duplex mode"); + break; + } + fallthrough; + case 8: + /* Set full-duplex mode based on eeprom config + * setting. + */ + if ((sw_info & 0x000f) && (sw_info & 0x8000)) { + pr_cont("Setting 3c5x9b full-duplex mode (from EEPROM configuration bit)"); + break; + } + fallthrough; + default: + /* xcvr = (0 || 4) OR user has an old 3c5x9 non "B" + * model. + */ + pr_cont("Setting 3c5x9/3c5x9B half-duplex mode"); + /* Disable full duplex. */ + net_diag = (net_diag & ~FD_ENABLE); + } + + outw(net_diag, ioaddr + WN4_NETDIAG); + pr_cont(" if_port: %d, sw_info: %4.4x\n", + dev->if_port, sw_info); + if (el3_debug > 3) + pr_debug("%s: 3c5x9 net diag word is now: %4.4x.\n", + dev->name, net_diag); + /* Enable link beat and jabber check. */ + outw(inw(ioaddr + WN4_MEDIA) | MEDIA_TP, ioaddr + WN4_MEDIA); + } + + /* Switch to the stats window, and clear all stats by reading. */ + outw(STATS_DISABLE, ioaddr + EL3_CMD); + EL3WINDOW(6); + for (i = 0; i < 9; i++) + inb(ioaddr + i); + inw(ioaddr + 10); + inw(ioaddr + 12); + + /* Switch to register set 1 for normal use. */ + EL3WINDOW(1); + + /* Accept b-case and phys addr only. */ + outw(SET_RX_FILTER | RX_STATION | RX_BROADCAST, ioaddr + EL3_CMD); + /* Turn on statistics. */ + outw(STATS_ENABLE, ioaddr + EL3_CMD); + + /* Enable the receiver. */ + outw(RX_ENABLE, ioaddr + EL3_CMD); + /* Enable transmitter. */ + outw(TX_ENABLE, ioaddr + EL3_CMD); + /* Allow status bits to be seen. */ + outw(SET_STATUS_ENB | 0xff, ioaddr + EL3_CMD); + /* Ack all pending events, and set active indicator mask. */ + outw(ACK_INTR | INT_LATCH | TX_AVAILABLE | RX_EARLY | INT_REQ, + ioaddr + EL3_CMD); + outw((SET_INTR_ENB | INT_LATCH | TX_AVAILABLE | TX_COMPLETE | + RX_COMPLETE | STATS_FULL), + ioaddr + EL3_CMD); + + netif_start_queue(dev); +} + +/* Power Management support functions */ +#ifdef CONFIG_PM + +static int el3_suspend(struct device *pdev, pm_message_t state) +{ + struct net_device *dev; + struct el3_private *lp; + unsigned long flags; + int ioaddr; + + dev = dev_get_drvdata(pdev); + lp = netdev_priv(dev); + ioaddr = dev->base_addr; + + spin_lock_irqsave(&lp->lock, flags); + + if (netif_running(dev)) + netif_device_detach(dev); + + el3_down(dev); + outw(POWER_DOWN, ioaddr + EL3_CMD); + + spin_unlock_irqrestore(&lp->lock, flags); + return 0; +} + +static int el3_resume(struct device *pdev) +{ + struct net_device *dev; + struct el3_private *lp; + unsigned long flags; + int ioaddr; + + dev = dev_get_drvdata(pdev); + lp = netdev_priv(dev); + ioaddr = dev->base_addr; + + spin_lock_irqsave(&lp->lock, flags); + + outw(POWER_UP, ioaddr + EL3_CMD); + EL3WINDOW(0); + el3_up(dev); + + if (netif_running(dev)) + netif_device_attach(dev); + + spin_unlock_irqrestore(&lp->lock, flags); + return 0; +} + +#endif /* CONFIG_PM */ + +module_param(debug, int, 0); +module_param_hw_array(irq, int, irq, NULL, 0); +module_param(max_interrupt_work, int, 0); +MODULE_PARM_DESC(debug, "debug level (0-6)"); +MODULE_PARM_DESC(irq, "IRQ number(s) (assigned)"); +MODULE_PARM_DESC(max_interrupt_work, "maximum events handled per interrupt"); +#ifdef CONFIG_PNP +module_param(nopnp, int, 0); +MODULE_PARM_DESC(nopnp, "disable ISA PnP support (0-1)"); +#endif /* CONFIG_PNP */ +MODULE_DESCRIPTION("3Com Etherlink III (3c509, 3c509B, 3c529, 3c579) ethernet driver"); +MODULE_LICENSE("GPL"); + +static int __init el3_init_module(void) +{ + int ret = 0; + + if (debug >= 0) + el3_debug = debug; + +#ifdef CONFIG_PNP + if (!nopnp) { + ret = pnp_register_driver(&el3_pnp_driver); + if (!ret) + pnp_registered = 1; + } +#endif + /* Select an open I/O location at 0x1*0 to do ISA contention select. */ + /* Start with 0x110 to avoid some sound cards.*/ + for (id_port = 0x110; id_port < 0x200; id_port += 0x10) { + if (!request_region(id_port, 1, "3c509-control")) + continue; + outb(0x00, id_port); + outb(0xff, id_port); + if (inb(id_port) & 0x01) + break; + release_region(id_port, 1); + } + if (id_port >= 0x200) { + id_port = 0; + pr_err("No I/O port available for 3c509 activation.\n"); + } else { + ret = isa_register_driver(&el3_isa_driver, EL3_MAX_CARDS); + if (!ret) + isa_registered = 1; + } +#ifdef CONFIG_EISA + ret = eisa_driver_register(&el3_eisa_driver); + if (!ret) + eisa_registered = 1; +#endif + +#ifdef CONFIG_PNP + if (pnp_registered) + ret = 0; +#endif + if (isa_registered) + ret = 0; +#ifdef CONFIG_EISA + if (eisa_registered) + ret = 0; +#endif + return ret; +} + +static void __exit el3_cleanup_module(void) +{ +#ifdef CONFIG_PNP + if (pnp_registered) + pnp_unregister_driver(&el3_pnp_driver); +#endif + if (isa_registered) + isa_unregister_driver(&el3_isa_driver); + if (id_port) + release_region(id_port, 1); +#ifdef CONFIG_EISA + if (eisa_registered) + eisa_driver_unregister(&el3_eisa_driver); +#endif +} + +module_init(el3_init_module); +module_exit(el3_cleanup_module); diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig index 399cb6c56198..81db16744f94 100644 --- a/drivers/net/ethernet/3com/Kconfig +++ b/drivers/net/ethernet/3com/Kconfig @@ -17,6 +17,20 @@ config NET_VENDOR_3COM if NET_VENDOR_3COM +config EL3 + tristate "3c509/3c579 \"EtherLink III\" support" + depends on (ISA || EISA) + help + If you have a network (Ethernet) card belonging to the 3Com + EtherLinkIII series, say Y here. + + If your card is not working you may need to use the DOS + setup disk to disable Plug & Play mode, and to select the default + media type. + + To compile this driver as a module, choose M here. The module + will be called 3c509. + config VORTEX tristate "3c590/3c900 series (592/595/597) \"Vortex/Boomerang\" support" depends on (PCI || EISA) && HAS_IOPORT_MAP diff --git a/drivers/net/ethernet/3com/Makefile b/drivers/net/ethernet/3com/Makefile index 5c4d07f1d456..2c65e472196f 100644 --- a/drivers/net/ethernet/3com/Makefile +++ b/drivers/net/ethernet/3com/Makefile @@ -3,5 +3,6 @@ # Makefile for the 3Com Ethernet device drivers # +obj-$(CONFIG_EL3) += 3c509.o obj-$(CONFIG_VORTEX) += 3c59x.o obj-$(CONFIG_TYPHOON) += typhoon.o diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index d0c0c0ec8a80..cecd66251dba 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -1793,11 +1793,8 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_port *port) u32 val, pse_port, chan; int i, src_port; - /* Forward the traffic to the proper GDM port */ - pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 - : FE_PSE_PORT_GDM4; airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), - pse_port); + FE_PSE_PORT_DROP); airoha_fe_clear(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), GDM_STRIP_CRC_MASK); @@ -1815,6 +1812,11 @@ static int airoha_set_gdm2_loopback(struct airoha_gdm_port *port) GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK, FIELD_PREP(GDM_SHORT_LEN_MASK, 60) | FIELD_PREP(GDM_LONG_LEN_MASK, AIROHA_MAX_MTU)); + /* Forward the traffic to the proper GDM port */ + pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 + : FE_PSE_PORT_GDM4; + airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(AIROHA_GDM2_IDX), + pse_port); /* Disable VIP and IFC for GDM2 */ airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(AIROHA_GDM2_IDX)); diff --git a/drivers/net/ethernet/amd/pds_core/debugfs.c b/drivers/net/ethernet/amd/pds_core/debugfs.c index 04c5e3abd8d7..810a0cd9bcac 100644 --- a/drivers/net/ethernet/amd/pds_core/debugfs.c +++ b/drivers/net/ethernet/amd/pds_core/debugfs.c @@ -64,9 +64,14 @@ DEFINE_SHOW_ATTRIBUTE(identity); void pdsc_debugfs_add_ident(struct pdsc *pdsc) { + struct dentry *dentry; + /* This file will already exist in the reset flow */ - if (debugfs_lookup("identity", pdsc->dentry)) + dentry = debugfs_lookup("identity", pdsc->dentry); + if (!IS_ERR_OR_NULL(dentry)) { + dput(dentry); return; + } debugfs_create_file("identity", 0400, pdsc->dentry, pdsc, &identity_fops); diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c index 2e1d0d01d03a..bded6b33289c 100644 --- a/drivers/net/ethernet/amd/pds_core/dev.c +++ b/drivers/net/ethernet/amd/pds_core/dev.c @@ -162,12 +162,19 @@ static int pdsc_devcmd_wait(struct pdsc *pdsc, u8 opcode, int max_seconds) dev_dbg(dev, "DEVCMD %d %s after %ld secs\n", opcode, pdsc_devcmd_str(opcode), duration / HZ); - if ((!done || timeout) && running) { + if (!running) { + dev_err(dev, "DEVCMD %d %s fw not running\n", + opcode, pdsc_devcmd_str(opcode)); + pdsc_devcmd_clean(pdsc); + return -ENXIO; + } + + if (!done || timeout) { dev_err(dev, "DEVCMD %d %s timeout, done %d timeout %d max_seconds=%d\n", opcode, pdsc_devcmd_str(opcode), done, timeout, max_seconds); - err = -ETIMEDOUT; pdsc_devcmd_clean(pdsc); + return -ETIMEDOUT; } status = pdsc_devcmd_status(pdsc); diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index b576be626a29..3f0e56b951bf 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -122,12 +122,14 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names)); for (i = 0; i < listlen; i++) { + char *fw_ver = fw_list.fw_names[i].fw_version; + if (i < ARRAY_SIZE(fw_slotnames)) strscpy(buf, fw_slotnames[i], sizeof(buf)); else snprintf(buf, sizeof(buf), "fw.slot_%d", i); - err = devlink_info_version_stored_put(req, buf, - fw_list.fw_names[i].fw_version); + fw_ver[sizeof(fw_list.fw_names[i].fw_version) - 1] = '\0'; + err = devlink_info_version_stored_put(req, buf, fw_ver); if (err) return err; } diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index a5ab99474179..4e4794c4dfdc 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1856,6 +1856,9 @@ static int ag71xx_probe(struct platform_device *pdev) ag71xx_int_disable(ag, AG71XX_INT_POLL); ndev->irq = platform_get_irq(pdev, 0); + if (ndev->irq < 0) + return ndev->irq; + err = devm_request_irq(&pdev->dev, ndev->irq, ag71xx_interrupt, 0x0, dev_name(&pdev->dev), ndev); if (err) { diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 54f71b1e85fc..7c11cf916762 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1368,13 +1368,12 @@ void bcmgenet_eee_enable_set(struct net_device *dev, bool enable) reg &= ~(TBUF_EEE_EN | TBUF_PM_EN); bcmgenet_writel(reg, priv->base + off); - /* Do the same for thing for RBUF */ + /* RBUF EEE/PM can break the RX path on GENET. Keep it disabled. */ reg = bcmgenet_rbuf_readl(priv, RBUF_ENERGY_CTRL); - if (enable) - reg |= RBUF_EEE_EN | RBUF_PM_EN; - else + if (reg & (RBUF_EEE_EN | RBUF_PM_EN)) { reg &= ~(RBUF_EEE_EN | RBUF_PM_EN); - bcmgenet_rbuf_writel(priv, reg, RBUF_ENERGY_CTRL); + bcmgenet_rbuf_writel(priv, reg, RBUF_ENERGY_CTRL); + } if (!enable && priv->clk_eee_enabled) { clk_disable_unprepare(priv->clk_eee); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 662e4fbafb74..e58cc81d199d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -56,11 +56,21 @@ static inline u32 enetc_vsi_set_msize(u32 size) } #define ENETC_PSIMSGRR 0x204 -#define ENETC_PSIMSGRR_MR_MASK GENMASK(2, 1) -#define ENETC_PSIMSGRR_MR(n) BIT((n) + 1) /* n = VSI index */ #define ENETC_PSIVMSGRCVAR0(n) (0x210 + (n) * 0x8) /* n = VSI index */ #define ENETC_PSIVMSGRCVAR1(n) (0x214 + (n) * 0x8) +/* Message received mask, n is the active number of VSIs. + * It is available for ENETC_PSIMSGRR, ENETC_PSIIER, and + * ENETC_PSIIDR registers. + */ +#define ENETC_PSIMR_MASK(n) \ + ({ typeof(n) _n = (n); (_n) ? GENMASK((_n), 1) : 0; }) + +/* Message received bit, n is VSI index. It is available for + * ENETC_PSIMSGRR, ENETC_PSIIER, and ENETC_PSIIDR registers. + */ +#define ENETC_PSIMR_BIT(n) BIT((n) + 1) + #define ENETC_VSIMSGSR 0x204 /* RO */ #define ENETC_VSIMSGSR_MB BIT(0) #define ENETC_VSIMSGSR_MS BIT(1) @@ -94,7 +104,6 @@ static inline u32 enetc_vsi_set_msize(u32 size) #define ENETC_SICAPR1 0x904 #define ENETC_PSIIER 0xa00 -#define ENETC_PSIIER_MR_MASK GENMASK(2, 1) #define ENETC_PSIIDR 0xa08 #define ENETC_SITXIDR 0xa18 #define ENETC_SIRXIDR 0xa28 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_msg.c b/drivers/net/ethernet/freescale/enetc/enetc_msg.c index 40d22ebe9224..c09635e7eb3d 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_msg.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_msg.c @@ -3,18 +3,25 @@ #include "enetc_pf.h" -static void enetc_msg_disable_mr_int(struct enetc_hw *hw) +static void enetc_msg_disable_mr_int(struct enetc_pf *pf) { - u32 psiier = enetc_rd(hw, ENETC_PSIIER); + struct enetc_hw *hw = &pf->si->hw; + u32 psiier; + + psiier = enetc_rd(hw, ENETC_PSIIER) & ~ENETC_PSIMR_MASK(pf->num_vfs); + /* disable MR int source(s) */ - enetc_wr(hw, ENETC_PSIIER, psiier & ~ENETC_PSIIER_MR_MASK); + enetc_wr(hw, ENETC_PSIIER, psiier); } -static void enetc_msg_enable_mr_int(struct enetc_hw *hw) +static void enetc_msg_enable_mr_int(struct enetc_pf *pf) { - u32 psiier = enetc_rd(hw, ENETC_PSIIER); + struct enetc_hw *hw = &pf->si->hw; + u32 psiier; - enetc_wr(hw, ENETC_PSIIER, psiier | ENETC_PSIIER_MR_MASK); + psiier = enetc_rd(hw, ENETC_PSIIER) | ENETC_PSIMR_MASK(pf->num_vfs); + + enetc_wr(hw, ENETC_PSIIER, psiier); } static irqreturn_t enetc_msg_psi_msix(int irq, void *data) @@ -22,7 +29,7 @@ static irqreturn_t enetc_msg_psi_msix(int irq, void *data) struct enetc_si *si = (struct enetc_si *)data; struct enetc_pf *pf = enetc_si_priv(si); - enetc_msg_disable_mr_int(&si->hw); + enetc_msg_disable_mr_int(pf); schedule_work(&pf->msg_task); return IRQ_HANDLED; @@ -31,33 +38,35 @@ static irqreturn_t enetc_msg_psi_msix(int irq, void *data) static void enetc_msg_task(struct work_struct *work) { struct enetc_pf *pf = container_of(work, struct enetc_pf, msg_task); + u32 mr_mask = ENETC_PSIMR_MASK(pf->num_vfs); struct enetc_hw *hw = &pf->si->hw; - unsigned long mr_mask; + u32 mr_status; int i; - for (;;) { - mr_mask = enetc_rd(hw, ENETC_PSIMSGRR) & ENETC_PSIMSGRR_MR_MASK; - if (!mr_mask) { - /* re-arm MR interrupts, w1c the IDR reg */ - enetc_wr(hw, ENETC_PSIIDR, ENETC_PSIIER_MR_MASK); - enetc_msg_enable_mr_int(hw); - return; - } + mr_status = (enetc_rd(hw, ENETC_PSIMSGRR) & mr_mask) | + (enetc_rd(hw, ENETC_PSIIDR) & mr_mask); + if (!mr_status) + goto out; - for (i = 0; i < pf->num_vfs; i++) { - u32 psimsgrr; - u16 msg_code; + for (i = 0; i < pf->num_vfs; i++) { + u32 psimsgrr; + u16 msg_code; - if (!(ENETC_PSIMSGRR_MR(i) & mr_mask)) - continue; + if (!(ENETC_PSIMR_BIT(i) & mr_status)) + continue; - enetc_msg_handle_rxmsg(pf, i, &msg_code); + enetc_msg_handle_rxmsg(pf, i, &msg_code); - psimsgrr = ENETC_SIMSGSR_SET_MC(msg_code); - psimsgrr |= ENETC_PSIMSGRR_MR(i); /* w1c */ - enetc_wr(hw, ENETC_PSIMSGRR, psimsgrr); - } + /* w1c to clear the corresponding VF MR bit */ + enetc_wr(hw, ENETC_PSIIDR, ENETC_PSIMR_BIT(i)); + + psimsgrr = ENETC_SIMSGSR_SET_MC(msg_code); + psimsgrr |= ENETC_PSIMR_BIT(i); /* w1c */ + enetc_wr(hw, ENETC_PSIMSGRR, psimsgrr); } + +out: + enetc_msg_enable_mr_int(pf); } /* Init */ @@ -96,12 +105,12 @@ static void enetc_msg_free_mbx(struct enetc_si *si, int idx) struct enetc_hw *hw = &si->hw; struct enetc_msg_swbd *msg; + enetc_wr(hw, ENETC_PSIVMSGRCVAR0(idx), 0); + enetc_wr(hw, ENETC_PSIVMSGRCVAR1(idx), 0); + msg = &pf->rxmsg[idx]; dma_free_coherent(&si->pdev->dev, msg->size, msg->vaddr, msg->dma); memset(msg, 0, sizeof(*msg)); - - enetc_wr(hw, ENETC_PSIVMSGRCVAR0(idx), 0); - enetc_wr(hw, ENETC_PSIVMSGRCVAR1(idx), 0); } int enetc_msg_psi_init(struct enetc_pf *pf) @@ -109,6 +118,15 @@ int enetc_msg_psi_init(struct enetc_pf *pf) struct enetc_si *si = pf->si; int vector, i, err; + for (i = 0; i < pf->num_vfs; i++) { + err = enetc_msg_alloc_mbx(si, i); + if (err) + goto free_mbx; + } + + /* initialize PSI mailbox */ + INIT_WORK(&pf->msg_task, enetc_msg_task); + /* register message passing interrupt handler */ snprintf(pf->msg_int_name, sizeof(pf->msg_int_name), "%s-vfmsg", si->ndev->name); @@ -117,32 +135,21 @@ int enetc_msg_psi_init(struct enetc_pf *pf) if (err) { dev_err(&si->pdev->dev, "PSI messaging: request_irq() failed!\n"); - return err; + goto free_mbx; } /* set one IRQ entry for PSI message receive notification (SI int) */ enetc_wr(&si->hw, ENETC_SIMSIVR, ENETC_SI_INT_IDX); - /* initialize PSI mailbox */ - INIT_WORK(&pf->msg_task, enetc_msg_task); - - for (i = 0; i < pf->num_vfs; i++) { - err = enetc_msg_alloc_mbx(si, i); - if (err) - goto err_init_mbx; - } - /* enable MR interrupts */ - enetc_msg_enable_mr_int(&si->hw); + enetc_msg_enable_mr_int(pf); return 0; -err_init_mbx: +free_mbx: for (i--; i >= 0; i--) enetc_msg_free_mbx(si, i); - free_irq(vector, si); - return err; } @@ -151,14 +158,17 @@ void enetc_msg_psi_free(struct enetc_pf *pf) struct enetc_si *si = pf->si; int i; - cancel_work_sync(&pf->msg_task); - /* disable MR interrupts */ - enetc_msg_disable_mr_int(&si->hw); - - for (i = 0; i < pf->num_vfs; i++) - enetc_msg_free_mbx(si, i); + enetc_msg_disable_mr_int(pf); /* de-register message passing interrupt handler */ free_irq(pci_irq_vector(si->pdev, ENETC_SI_INT_IDX), si); + + cancel_work_sync(&pf->msg_task); + + /* MR interrupts may be re-enabled by workqueue */ + enetc_msg_disable_mr_int(pf); + + for (i = 0; i < pf->num_vfs; i++) + enetc_msg_free_mbx(si, i); } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index a12fd54a475f..3206b3daa1a0 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -252,8 +252,12 @@ static int enetc_pf_set_vf_mac(struct net_device *ndev, int vf, u8 *mac) return -EADDRNOTAVAIL; vf_state = &pf->vf_state[vf]; + + mutex_lock(&vf_state->lock); vf_state->flags |= ENETC_VF_FLAG_PF_SET_MAC; enetc_pf_set_primary_mac_addr(&priv->si->hw, vf + 1, mac); + mutex_unlock(&vf_state->lock); + return 0; } @@ -478,49 +482,77 @@ static void enetc_configure_port(struct enetc_pf *pf) /* Messaging */ static u16 enetc_msg_pf_set_vf_primary_mac_addr(struct enetc_pf *pf, - int vf_id) + int vf_id, void *msg) { struct enetc_vf_state *vf_state = &pf->vf_state[vf_id]; - struct enetc_msg_swbd *msg = &pf->rxmsg[vf_id]; - struct enetc_msg_cmd_set_primary_mac *cmd; + struct enetc_msg_cmd_set_primary_mac *cmd = msg; struct device *dev = &pf->si->pdev->dev; - u16 cmd_id; + u16 cmd_id = cmd->header.id; char *addr; - cmd = (struct enetc_msg_cmd_set_primary_mac *)msg->vaddr; - cmd_id = cmd->header.id; if (cmd_id != ENETC_MSG_CMD_MNG_ADD) return ENETC_MSG_CMD_STATUS_FAIL; addr = cmd->mac.sa_data; - if (vf_state->flags & ENETC_VF_FLAG_PF_SET_MAC) - dev_warn(dev, "Attempt to override PF set mac addr for VF%d\n", - vf_id); - else - enetc_pf_set_primary_mac_addr(&pf->si->hw, vf_id + 1, addr); + if (!is_valid_ether_addr(addr)) { + dev_err_ratelimited(dev, "VF%d attempted to set invalid MAC\n", + vf_id); + return ENETC_MSG_CMD_STATUS_FAIL; + } + + mutex_lock(&vf_state->lock); + if (vf_state->flags & ENETC_VF_FLAG_PF_SET_MAC) { + mutex_unlock(&vf_state->lock); + dev_err_ratelimited(dev, + "VF%d attempted to override PF set MAC\n", + vf_id); + return ENETC_MSG_CMD_STATUS_FAIL; + } + + enetc_pf_set_primary_mac_addr(&pf->si->hw, vf_id + 1, addr); + mutex_unlock(&vf_state->lock); return ENETC_MSG_CMD_STATUS_OK; } void enetc_msg_handle_rxmsg(struct enetc_pf *pf, int vf_id, u16 *status) { - struct enetc_msg_swbd *msg = &pf->rxmsg[vf_id]; + struct enetc_msg_swbd *msg_swbd = &pf->rxmsg[vf_id]; struct device *dev = &pf->si->pdev->dev; struct enetc_msg_cmd_header *cmd_hdr; u16 cmd_type; + u8 *msg; - *status = ENETC_MSG_CMD_STATUS_OK; - cmd_hdr = (struct enetc_msg_cmd_header *)msg->vaddr; + msg = kzalloc_objs(*msg, msg_swbd->size); + if (!msg) { + dev_err_ratelimited(dev, + "Failed to allocate message buffer\n"); + *status = ENETC_MSG_CMD_STATUS_FAIL; + return; + } + + /* Currently, only ENETC_MSG_CMD_MNG_MAC command is supported, so + * only sizeof(struct enetc_msg_cmd_set_primary_mac) bytes need to + * be copied. This data already includes the cmd_type field, so it + * can correctly return an error code. + */ + memcpy(msg, msg_swbd->vaddr, + sizeof(struct enetc_msg_cmd_set_primary_mac)); + cmd_hdr = (struct enetc_msg_cmd_header *)msg; cmd_type = cmd_hdr->type; switch (cmd_type) { case ENETC_MSG_CMD_MNG_MAC: - *status = enetc_msg_pf_set_vf_primary_mac_addr(pf, vf_id); + *status = enetc_msg_pf_set_vf_primary_mac_addr(pf, vf_id, msg); break; default: - dev_err(dev, "command not supported (cmd_type: 0x%x)\n", - cmd_type); + *status = ENETC_MSG_CMD_STATUS_FAIL; + dev_err_ratelimited(dev, + "command not supported (cmd_type: 0x%x)\n", + cmd_type); } + + kfree(msg); } #ifdef CONFIG_PCI_IOV @@ -531,9 +563,9 @@ static int enetc_sriov_configure(struct pci_dev *pdev, int num_vfs) int err; if (!num_vfs) { + pci_disable_sriov(pdev); enetc_msg_psi_free(pf); pf->num_vfs = 0; - pci_disable_sriov(pdev); } else { pf->num_vfs = num_vfs; @@ -960,8 +992,13 @@ static int enetc_pf_probe(struct pci_dev *pdev, if (pf->total_vfs) { pf->vf_state = kzalloc_objs(struct enetc_vf_state, pf->total_vfs); - if (!pf->vf_state) + if (!pf->vf_state) { + err = -ENOMEM; goto err_alloc_vf_state; + } + + for (int i = 0; i < pf->total_vfs; i++) + mutex_init(&pf->vf_state[i].lock); } err = enetc_setup_mac_addresses(node, pf); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h index ae407e9e9ee7..35d484858c7b 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h @@ -14,6 +14,7 @@ enum enetc_vf_flags { }; struct enetc_vf_state { + struct mutex lock; /* Prevent concurrent access */ enum enetc_vf_flags flags; }; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index c52c465280f7..e2fbe111f849 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3682,7 +3682,7 @@ int ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) ret = ice_fltr_set_vsi_promisc(&vsi->back->hw, vsi->idx, ICE_MCAST_VLAN_PROMISC_BITS, vid); - if (ret) + if (ret && ret != -EEXIST) goto finish; } @@ -4104,6 +4104,12 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) } ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); + /* Rx rings are reallocated during VSI rebuild and lose their ptp_rx + * flag. Restore timestamp mode so newly allocated rings are set up + * for hardware Rx timestamping. + */ + if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) + ice_ptp_restore_timestamp_mode(pf); goto done; rebuild_err: diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index 24fb7a3e14d6..2c18e16fe053 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -2141,16 +2141,23 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) } incval = (u64)hi << 32 | lo; + if (!ice_ptp_lock(hw)) { + dev_err(ice_hw_to_dev(hw), "Failed to acquire PTP semaphore\n"); + return -EBUSY; + } + err = ice_write_40b_ptp_reg_eth56g(hw, port, PHY_REG_TIMETUS_L, incval); if (err) - return err; + goto err_ptp_unlock; err = ice_ptp_one_port_cmd(hw, port, ICE_PTP_INIT_INCVAL); if (err) - return err; + goto err_ptp_unlock; ice_ptp_exec_tmr_cmd(hw); + ice_ptp_unlock(hw); + err = ice_sync_phy_timer_eth56g(hw, port); if (err) return err; @@ -2166,6 +2173,10 @@ int ice_start_phy_timer_eth56g(struct ice_hw *hw, u8 port) ice_debug(hw, ICE_DBG_PTP, "Enabled clock on PHY port %u\n", port); return 0; + +err_ptp_unlock: + ice_ptp_unlock(hw); + return err; } /** @@ -4503,18 +4514,17 @@ static int ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) { struct ice_e810_params *params = &hw->ptp.phy.e810; - unsigned long flags; u32 val; int err; - spin_lock_irqsave(¶ms->atqbal_wq.lock, flags); + spin_lock_irq(¶ms->atqbal_wq.lock); /* Wait for any pending in-progress low latency interrupt */ err = wait_event_interruptible_locked_irq(params->atqbal_wq, !(params->atqbal_flags & ATQBAL_FLAGS_INTR_IN_PROGRESS)); if (err) { - spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + spin_unlock_irq(¶ms->atqbal_wq.lock); return err; } @@ -4529,7 +4539,7 @@ ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) REG_LL_PROXY_H); if (err) { ice_debug(hw, ICE_DBG_PTP, "Failed to read PTP timestamp using low latency read\n"); - spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + spin_unlock_irq(¶ms->atqbal_wq.lock); return err; } @@ -4539,7 +4549,7 @@ ice_read_phy_tstamp_ll_e810(struct ice_hw *hw, u8 idx, u8 *hi, u32 *lo) /* Read the low 32 bit value and set the TS valid bit */ *lo = rd32(hw, REG_LL_PROXY_L) | TS_VALID; - spin_unlock_irqrestore(¶ms->atqbal_wq.lock, flags); + spin_unlock_irq(¶ms->atqbal_wq.lock); return 0; } @@ -5254,9 +5264,13 @@ static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp) */ bool ice_ptp_lock(struct ice_hw *hw) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); u32 hw_lock; int i; + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + #define MAX_TRIES 15 for (i = 0; i < MAX_TRIES; i++) { @@ -5283,6 +5297,11 @@ bool ice_ptp_lock(struct ice_hw *hw) */ void ice_ptp_unlock(struct ice_hw *hw) { + struct ice_pf *pf = container_of(hw, struct ice_pf, hw); + + if (!ice_is_primary(hw)) + hw = ice_get_primary_hw(pf); + wr32(hw, PFTSYN_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), 0); } diff --git a/drivers/net/ethernet/intel/ice/virt/queues.c b/drivers/net/ethernet/intel/ice/virt/queues.c index f73d5a3e83d4..31be2f76181c 100644 --- a/drivers/net/ethernet/intel/ice/virt/queues.c +++ b/drivers/net/ethernet/intel/ice/virt/queues.c @@ -840,7 +840,7 @@ int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) if (qpi->rxq.databuffer_size != 0 && (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || - qpi->rxq.databuffer_size < 1024)) + qpi->rxq.databuffer_size < 128)) goto error_param; ring->rx_buf_len = qpi->rxq.databuffer_size; diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 8a110145bfee..52de2bcbadbe 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -34,6 +34,7 @@ static int igc_fpe_init_smd_frame(struct igc_ring *ring, return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_SKB; buffer->skb = skb; buffer->protocol = 0; buffer->bytecount = skb->len; @@ -109,10 +110,16 @@ static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter, __netif_tx_lock(nq, cpu); err = igc_fpe_init_tx_descriptor(ring, skb, type); + if (err) + goto err_free_skb_any; + igc_flush_tx_descriptors(ring); - __netif_tx_unlock(nq); + return 0; +err_free_skb_any: + __netif_tx_unlock(nq); + dev_kfree_skb_any(skb); return err; } diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 42f89a179a3f..4ba3be961ab6 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1221,6 +1221,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, ether_addr_equal(rx_ring->netdev->dev_addr, eth_hdr(skb)->h_source)) { dev_kfree_skb_irq(skb); + skb = NULL; continue; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 4f33a816bc7a..2e94d5105016 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1294,13 +1294,18 @@ static inline void link_status_user_format(u64 lstat, struct cgx_link_user_info *linfo, struct cgx *cgx, u8 lmac_id) { + unsigned int speed; + linfo->link_up = FIELD_GET(RESP_LINKSTAT_UP, lstat); linfo->full_duplex = FIELD_GET(RESP_LINKSTAT_FDUPLEX, lstat); - linfo->speed = cgx_speed_mbps[FIELD_GET(RESP_LINKSTAT_SPEED, lstat)]; linfo->an = FIELD_GET(RESP_LINKSTAT_AN, lstat); linfo->fec = FIELD_GET(RESP_LINKSTAT_FEC, lstat); linfo->lmac_type_id = FIELD_GET(RESP_LINKSTAT_LMAC_TYPE, lstat); + speed = FIELD_GET(RESP_LINKSTAT_SPEED, lstat); + linfo->speed = speed < ARRAY_SIZE(cgx_speed_mbps) ? + cgx_speed_mbps[speed] : 0; + if (linfo->lmac_type_id >= LMAC_MODE_MAX) { dev_err(&cgx->pdev->dev, "Unknown lmac_type_id %d reported by firmware on cgx port%d:%d", linfo->lmac_type_id, cgx->cgx_id, lmac_id); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 3c814d157ab9..607d0cf1a778 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -990,7 +990,7 @@ void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u16 vf_func; /* Only CGX PF/VF can add allmulticast entry */ - if (is_lbk_vf(rvu, pcifunc) && is_sdp_vf(rvu, pcifunc)) + if (is_lbk_vf(rvu, pcifunc) || is_sdp_vf(rvu, pcifunc)) return; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c index a5a8f4558717..dbf173196608 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c @@ -619,11 +619,13 @@ static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id, err = otx2_sync_mbox_msg(&pfvf->mbox); if (err) { qmem_free(pfvf->dev, pool->stack); + pool->stack = NULL; return err; } aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox); if (!aq) { qmem_free(pfvf->dev, pool->stack); + pool->stack = NULL; return -ENOMEM; } } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 971fcab1c248..3d253132a17f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1482,11 +1482,13 @@ int otx2_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id, err = otx2_sync_mbox_msg(&pfvf->mbox); if (err) { qmem_free(pfvf->dev, pool->stack); + pool->stack = NULL; return err; } aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox); if (!aq) { qmem_free(pfvf->dev, pool->stack); + pool->stack = NULL; return -ENOMEM; } } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c index 94f155ffb17f..0f5d5642d3f7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c @@ -609,7 +609,7 @@ static int rvu_rep_rsrc_init(struct otx2_nic *priv) err = otx2_init_hw_resources(priv); if (err) - goto err_free_rsrc; + goto err_free_mem; /* Set maximum frame size allowed in HW */ err = otx2_hw_set_mtu(priv, priv->hw.max_mtu); @@ -621,6 +621,7 @@ static int rvu_rep_rsrc_init(struct otx2_nic *priv) err_free_rsrc: otx2_free_hw_resources(priv); +err_free_mem: otx2_free_queue_mem(qset); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index afdeb1b3d425..8409ae73768f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -160,13 +160,13 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) * channels are being closed for other reason and this work is not * relevant anymore. */ - while (!netdev_trylock(sq->netdev)) { + while (!netdev_trylock(priv->netdev)) { if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) return 0; msleep(20); } - err = mlx5e_health_channel_eq_recover(sq->netdev, eq, sq->cq.ch_stats); + err = mlx5e_health_channel_eq_recover(priv->netdev, eq, sq->cq.ch_stats); if (!err) { to_ctx->status = 0; /* this sq recovered */ goto out; @@ -186,7 +186,7 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx) "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n", err); out: - netdev_unlock(sq->netdev); + netdev_unlock(priv->netdev); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c index a52e12c3c95a..db260e3d1412 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c @@ -792,8 +792,10 @@ static int mlx5e_xfrm_add_state(struct net_device *dev, sa_entry->dev = dev; sa_entry->ipsec = ipsec; /* Check if this SA is originated from acquire flow temporary SA */ - if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) - goto out; + if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ) { + x->xso.offload_handle = (unsigned long)sa_entry; + return 0; + } err = mlx5e_xfrm_validate_state(priv->mdev, x, extack); if (err) @@ -870,7 +872,6 @@ static int mlx5e_xfrm_add_state(struct net_device *dev, xa_unlock_bh(&ipsec->sadb); } -out: x->xso.offload_handle = (unsigned long)sa_entry; if (allow_tunnel_mode) mlx5_eswitch_unblock_encap(priv->mdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index bb61e2179078..99a0034b9b20 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1574,8 +1574,11 @@ static int mlx5e_create_rxfh_context(struct net_device *dev, rxfh->indir, rxfh->key, hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc, rxfh->input_xfrm == RXH_XFRM_NO_CHANGE ? NULL : &symmetric); - if (err) + if (err) { + WARN_ON(mlx5e_rx_res_rss_destroy(priv->rx_res, + rxfh->rss_context)); goto unlock; + } mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rxfh->rss_context, ethtool_rxfh_context_indir(ctx), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index b31f689fe271..e90c6c6df835 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -252,7 +252,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_cq_arm(&c->xdpsq->cq); if (unlikely(aff_change && busy_xsk)) { - mlx5e_trigger_irq(&c->icosq); + mlx5e_trigger_napi_async_icosq(c); ch_stats->force_irq++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c index 3cfe743610d3..ab50d2c734ed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c @@ -142,7 +142,8 @@ static int mlx5_esw_ipsec_modify_flow_dests(struct mlx5_eswitch *esw, attr = flow->attr; esw_attr = attr->esw_attr; - if (esw_attr->out_count - esw_attr->split_count > 1) + if (!esw_attr->out_count || + esw_attr->out_count - esw_attr->split_count > 1) return 0; err = mlx5_eswitch_restore_ipsec_rule(esw, flow->rule[0], esw_attr, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 123c96716a54..7c8311f41232 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -908,6 +908,24 @@ static void esw_vport_cleanup(struct mlx5_eswitch *esw, struct mlx5_vport *vport esw_vport_cleanup_acl(esw, vport); } +static void mlx5_esw_vport_set_max_tx_speed(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) +{ + int ret; + + if (!MLX5_CAP_ESW(esw->dev, esw_vport_state_max_tx_speed)) + return; + + ret = mlx5_modify_vport_max_tx_speed(esw->dev, + MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, + vport->vport, true, + vport->agg_max_tx_speed); + if (ret) + mlx5_core_dbg(esw->dev, + "Failed to set vport %d speed %d, err=%d\n", + vport->vport, vport->agg_max_tx_speed, ret); +} + int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, enum mlx5_eswitch_vport_event enabled_events) { @@ -948,6 +966,9 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw->enabled_vports++; esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num); + + if (vport->agg_max_tx_speed) + mlx5_esw_vport_set_max_tx_speed(esw, vport); done: mutex_unlock(&esw->state_lock); return ret; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 5128f5020dae..e9cf7c592ce9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -247,6 +247,7 @@ struct mlx5_vport { enum mlx5_eswitch_vport_event enabled_events; int index; struct mlx5_devlink_port *dl_port; + u32 agg_max_tx_speed; }; struct mlx5_esw_indir_table; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 449e4bd86c06..f8e70ac5a85b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1274,6 +1274,11 @@ static void mlx5_lag_modify_device_vports_speed(struct mlx5_core_dev *mdev, if (vport->vport == MLX5_VPORT_UPLINK) continue; + vport->agg_max_tx_speed = speed; + + if (!vport->enabled) + continue; + ret = mlx5_modify_vport_max_tx_speed(mdev, op_mod, vport->vport, true, speed); if (ret) diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index dbbde0fa57e7..e3c24d50dad0 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -77,21 +77,19 @@ static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq, } static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len, - struct hwc_work_request *rx_req) + struct hwc_work_request *rx_req, u16 msg_id) { const struct gdma_resp_hdr *resp_msg = rx_req->buf_va; struct hwc_caller_ctx *ctx; int err; - if (!test_bit(resp_msg->response.hwc_msg_id, - hwc->inflight_msg_res.map)) { - dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n", - resp_msg->response.hwc_msg_id); + if (!test_bit(msg_id, hwc->inflight_msg_res.map)) { + dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n", msg_id); mana_hwc_post_rx_wqe(hwc->rxq, rx_req); return; } - ctx = hwc->caller_ctx + resp_msg->response.hwc_msg_id; + ctx = hwc->caller_ctx + msg_id; err = mana_hwc_verify_resp_msg(ctx, resp_msg, resp_len); if (err) goto out; @@ -251,6 +249,7 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id, struct gdma_sge *sge; u64 rq_base_addr; u64 rx_req_idx; + u16 msg_id; u8 *wqe; if (WARN_ON_ONCE(hwc_rxq->gdma_wq->id != gdma_rxq_id)) @@ -266,16 +265,26 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id, rq_base_addr = hwc_rxq->msg_buf->mem_info.dma_handle; rx_req_idx = (sge->address - rq_base_addr) / hwc->max_req_msg_size; - rx_req = &hwc_rxq->msg_buf->reqs[rx_req_idx]; - resp = (struct gdma_resp_hdr *)rx_req->buf_va; - - if (resp->response.hwc_msg_id >= hwc->num_inflight_msg) { - dev_err(hwc->dev, "HWC RX: wrong msg_id=%u\n", - resp->response.hwc_msg_id); + if (rx_req_idx >= hwc_rxq->msg_buf->num_reqs) { + dev_err(hwc->dev, "HWC RX: wrong rx_req_idx=%llu, num_reqs=%u\n", + rx_req_idx, hwc_rxq->msg_buf->num_reqs); return; } - mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req); + rx_req = &hwc_rxq->msg_buf->reqs[rx_req_idx]; + resp = (struct gdma_resp_hdr *)rx_req->buf_va; + + /* Read msg_id once from DMA buffer to prevent TOCTOU: + * DMA memory is shared/unencrypted in CVMs - host can + * modify it between reads. + */ + msg_id = READ_ONCE(resp->response.hwc_msg_id); + if (msg_id >= hwc->num_inflight_msg) { + dev_err(hwc->dev, "HWC RX: wrong msg_id=%u\n", msg_id); + return; + } + + mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req, msg_id); /* Can no longer use 'resp', because the buffer is posted to the HW * in mana_hwc_handle_resp() above. diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 9861daa82d9e..b70262e70baf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -1036,11 +1036,13 @@ static void qed_cid_map_free(struct qed_hwfn *p_hwfn) for (type = 0; type < MAX_CONN_TYPES; type++) { bitmap_free(p_mngr->acquired[type].cid_map); + p_mngr->acquired[type].cid_map = NULL; p_mngr->acquired[type].max_count = 0; p_mngr->acquired[type].start_cid = 0; for (vf = 0; vf < MAX_NUM_VFS; vf++) { bitmap_free(p_mngr->acquired_vf[type][vf].cid_map); + p_mngr->acquired_vf[type][vf].cid_map = NULL; p_mngr->acquired_vf[type][vf].max_count = 0; p_mngr->acquired_vf[type][vf].start_cid = 0; } diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c index 269c0449760c..78d4df55740a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c @@ -213,8 +213,8 @@ static void rmnet_dellink(struct net_device *dev, struct list_head *head) ep = rmnet_get_endpoint(real_port, mux_id); if (ep) { hlist_del_init_rcu(&ep->hlnode); - rmnet_vnd_dellink(mux_id, real_port, ep); - kfree(ep); + real_port->nr_rmnet_devs--; + kfree_rcu(ep, rcu); } netdev_upper_dev_unlink(real_dev, dev); @@ -238,9 +238,9 @@ static void rmnet_force_unassociate_device(struct net_device *real_dev) hash_for_each_safe(port->muxed_ep, bkt_ep, tmp_ep, ep, hlnode) { unregister_netdevice_queue(ep->egress_dev, &list); netdev_upper_dev_unlink(real_dev, ep->egress_dev); - rmnet_vnd_dellink(ep->mux_id, port, ep); hlist_del_init_rcu(&ep->hlnode); - kfree(ep); + port->nr_rmnet_devs--; + kfree_rcu(ep, rcu); } rmnet_unregister_real_device(real_dev); unregister_netdevice_many(&list); diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h index ed112d51ac5a..f50fae1c6bdd 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.h @@ -18,6 +18,7 @@ struct rmnet_endpoint { u8 mux_id; struct net_device *egress_dev; struct hlist_node hlnode; + struct rcu_head rcu; }; struct rmnet_egress_agg_params { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c index bcb8e000e720..4ac979d874d6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c @@ -28,13 +28,16 @@ /* * TX/RX Clock Delay Bit Masks: - * - TX Delay: bits [14:8] — TX_CLK delay (unit: 0.1ns per bit) - * - RX Delay: bits [30:24] — RX_CLK delay (unit: 0.1ns per bit) + * - TX Delay: bits [14:8] — TX_CLK delay (unit: 0.02ns per bit) + * - RX Delay: bits [30:24] — RX_CLK delay (unit: 0.02ns per bit) */ #define EIC7700_ETH_TX_ADJ_DELAY GENMASK(14, 8) #define EIC7700_ETH_RX_ADJ_DELAY GENMASK(30, 24) -#define EIC7700_MAX_DELAY_UNIT 0x7F +#define EIC7700_MAX_DELAY_STEPS 0x7F +#define EIC7700_DELAY_STEP_PS 20 +#define EIC7700_MAX_DELAY_PS \ + (EIC7700_MAX_DELAY_STEPS * EIC7700_DELAY_STEP_PS) static const char * const eic7700_clk_names[] = { "tx", "axi", "cfg", @@ -42,6 +45,15 @@ static const char * const eic7700_clk_names[] = { struct eic7700_qos_priv { struct plat_stmmacenet_data *plat_dat; + struct regmap *eic7700_hsp_regmap; + u32 eth_axi_lp_ctrl_offset; + u32 eth_phy_ctrl_offset; + u32 eth_clk_offset; + u32 eth_txd_offset; + u32 eth_rxd_offset; + u32 eth_clk_dly_param; + bool has_txd_offset; + bool has_rxd_offset; }; static int eic7700_clks_config(void *priv, bool enabled) @@ -61,8 +73,34 @@ static int eic7700_clks_config(void *priv, bool enabled) static int eic7700_dwmac_init(struct device *dev, void *priv) { struct eic7700_qos_priv *dwc = priv; + int ret; - return eic7700_clks_config(dwc, true); + ret = eic7700_clks_config(dwc, true); + if (ret) + return ret; + + ret = regmap_set_bits(dwc->eic7700_hsp_regmap, + dwc->eth_phy_ctrl_offset, + EIC7700_ETH_TX_CLK_SEL | + EIC7700_ETH_PHY_INTF_SELI); + if (ret) { + eic7700_clks_config(dwc, false); + return ret; + } + + regmap_write(dwc->eic7700_hsp_regmap, dwc->eth_axi_lp_ctrl_offset, + EIC7700_ETH_CSYSREQ_VAL); + + if (dwc->has_txd_offset) + regmap_write(dwc->eic7700_hsp_regmap, dwc->eth_txd_offset, 0); + + if (dwc->has_rxd_offset) + regmap_write(dwc->eic7700_hsp_regmap, dwc->eth_rxd_offset, 0); + + regmap_write(dwc->eic7700_hsp_regmap, dwc->eth_clk_offset, + dwc->eth_clk_dly_param); + + return 0; } static void eic7700_dwmac_exit(struct device *dev, void *priv) @@ -93,13 +131,7 @@ static int eic7700_dwmac_probe(struct platform_device *pdev) struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; struct eic7700_qos_priv *dwc_priv; - struct regmap *eic7700_hsp_regmap; - u32 eth_axi_lp_ctrl_offset; - u32 eth_phy_ctrl_offset; - u32 eth_phy_ctrl_regset; - u32 eth_rxd_dly_offset; - u32 eth_dly_param = 0; - u32 delay_ps; + u32 delay_ps, val; int i, ret; ret = stmmac_get_platform_resources(pdev, &stmmac_res); @@ -119,10 +151,20 @@ static int eic7700_dwmac_probe(struct platform_device *pdev) /* Read rx-internal-delay-ps and update rx_clk delay */ if (!of_property_read_u32(pdev->dev.of_node, "rx-internal-delay-ps", &delay_ps)) { - u32 val = min(delay_ps / 100, EIC7700_MAX_DELAY_UNIT); + if (delay_ps % EIC7700_DELAY_STEP_PS) + return dev_err_probe(&pdev->dev, -EINVAL, + "rx delay must be multiple of %dps\n", + EIC7700_DELAY_STEP_PS); - eth_dly_param &= ~EIC7700_ETH_RX_ADJ_DELAY; - eth_dly_param |= FIELD_PREP(EIC7700_ETH_RX_ADJ_DELAY, val); + if (delay_ps > EIC7700_MAX_DELAY_PS) + return dev_err_probe(&pdev->dev, -EINVAL, + "rx delay out of range\n"); + + val = delay_ps / EIC7700_DELAY_STEP_PS; + + dwc_priv->eth_clk_dly_param &= ~EIC7700_ETH_RX_ADJ_DELAY; + dwc_priv->eth_clk_dly_param |= + FIELD_PREP(EIC7700_ETH_RX_ADJ_DELAY, val); } else { return dev_err_probe(&pdev->dev, -EINVAL, "missing required property rx-internal-delay-ps\n"); @@ -131,55 +173,65 @@ static int eic7700_dwmac_probe(struct platform_device *pdev) /* Read tx-internal-delay-ps and update tx_clk delay */ if (!of_property_read_u32(pdev->dev.of_node, "tx-internal-delay-ps", &delay_ps)) { - u32 val = min(delay_ps / 100, EIC7700_MAX_DELAY_UNIT); + if (delay_ps % EIC7700_DELAY_STEP_PS) + return dev_err_probe(&pdev->dev, -EINVAL, + "tx delay must be multiple of %dps\n", + EIC7700_DELAY_STEP_PS); - eth_dly_param &= ~EIC7700_ETH_TX_ADJ_DELAY; - eth_dly_param |= FIELD_PREP(EIC7700_ETH_TX_ADJ_DELAY, val); + if (delay_ps > EIC7700_MAX_DELAY_PS) + return dev_err_probe(&pdev->dev, -EINVAL, + "tx delay out of range\n"); + + val = delay_ps / EIC7700_DELAY_STEP_PS; + + dwc_priv->eth_clk_dly_param &= ~EIC7700_ETH_TX_ADJ_DELAY; + dwc_priv->eth_clk_dly_param |= + FIELD_PREP(EIC7700_ETH_TX_ADJ_DELAY, val); } else { return dev_err_probe(&pdev->dev, -EINVAL, "missing required property tx-internal-delay-ps\n"); } - eic7700_hsp_regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, - "eswin,hsp-sp-csr"); - if (IS_ERR(eic7700_hsp_regmap)) + dwc_priv->eic7700_hsp_regmap = + syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "eswin,hsp-sp-csr"); + if (IS_ERR(dwc_priv->eic7700_hsp_regmap)) return dev_err_probe(&pdev->dev, - PTR_ERR(eic7700_hsp_regmap), + PTR_ERR(dwc_priv->eic7700_hsp_regmap), "Failed to get hsp-sp-csr regmap\n"); ret = of_property_read_u32_index(pdev->dev.of_node, "eswin,hsp-sp-csr", - 1, ð_phy_ctrl_offset); + 1, &dwc_priv->eth_phy_ctrl_offset); if (ret) return dev_err_probe(&pdev->dev, ret, "can't get eth_phy_ctrl_offset\n"); - regmap_read(eic7700_hsp_regmap, eth_phy_ctrl_offset, - ð_phy_ctrl_regset); - eth_phy_ctrl_regset |= - (EIC7700_ETH_TX_CLK_SEL | EIC7700_ETH_PHY_INTF_SELI); - regmap_write(eic7700_hsp_regmap, eth_phy_ctrl_offset, - eth_phy_ctrl_regset); - ret = of_property_read_u32_index(pdev->dev.of_node, "eswin,hsp-sp-csr", - 2, ð_axi_lp_ctrl_offset); + 2, &dwc_priv->eth_axi_lp_ctrl_offset); if (ret) return dev_err_probe(&pdev->dev, ret, "can't get eth_axi_lp_ctrl_offset\n"); - regmap_write(eic7700_hsp_regmap, eth_axi_lp_ctrl_offset, - EIC7700_ETH_CSYSREQ_VAL); + ret = of_property_read_u32_index(pdev->dev.of_node, + "eswin,hsp-sp-csr", + 3, &dwc_priv->eth_clk_offset); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "can't get eth_clk_offset\n"); ret = of_property_read_u32_index(pdev->dev.of_node, "eswin,hsp-sp-csr", - 3, ð_rxd_dly_offset); - if (ret) - return dev_err_probe(&pdev->dev, ret, - "can't get eth_rxd_dly_offset\n"); + 4, &dwc_priv->eth_txd_offset); + if (!ret) + dwc_priv->has_txd_offset = true; - regmap_write(eic7700_hsp_regmap, eth_rxd_dly_offset, - eth_dly_param); + ret = of_property_read_u32_index(pdev->dev.of_node, + "eswin,hsp-sp-csr", + 5, &dwc_priv->eth_rxd_offset); + if (!ret) + dwc_priv->has_rxd_offset = true; plat_dat->num_clks = ARRAY_SIZE(eic7700_clk_names); plat_dat->clks = devm_kcalloc(&pdev->dev, diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 5407d2ed71b3..43aa1bfd41cf 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -211,12 +211,12 @@ static void ifb_get_strings(struct net_device *dev, u32 stringset, u8 *buf) switch (stringset) { case ETH_SS_STATS: - for (i = 0; i < dev->real_num_rx_queues; i++) + for (i = 0; i < dev->num_tx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "rx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); - for (i = 0; i < dev->real_num_tx_queues; i++) + for (i = 0; i < dev->num_tx_queues; i++) for (j = 0; j < IFB_Q_STATS_LEN; j++) ethtool_sprintf(&p, "tx_queue_%u_%.18s", i, ifb_q_stats_desc[j].desc); @@ -229,8 +229,7 @@ static int ifb_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: - return IFB_Q_STATS_LEN * (dev->real_num_rx_queues + - dev->real_num_tx_queues); + return IFB_Q_STATS_LEN * dev->num_tx_queues * 2; default: return -EOPNOTSUPP; } @@ -262,12 +261,12 @@ static void ifb_get_ethtool_stats(struct net_device *dev, struct ifb_q_private *txp; int i; - for (i = 0; i < dev->real_num_rx_queues; i++) { + for (i = 0; i < dev->num_tx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->rx_stats); } - for (i = 0; i < dev->real_num_tx_queues; i++) { + for (i = 0; i < dev->num_tx_queues; i++) { txp = dp->tx_private + i; ifb_fill_stats_data(&data, &txp->tx_stats); } diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index 22c555dd962e..a6b777a9c2d9 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -201,7 +201,7 @@ void ovpn_decrypt_post(void *data, int ret) skb = NULL; drop: if (unlikely(skb)) - dev_dstats_rx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); kfree_skb(skb); drop_nocount: if (likely(peer)) @@ -225,7 +225,7 @@ void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb) net_info_ratelimited("%s: no available key for peer %u, key-id: %u\n", netdev_name(peer->ovpn->dev), peer->id, key_id); - dev_dstats_rx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); kfree_skb(skb); ovpn_peer_put(peer); return; @@ -301,7 +301,7 @@ void ovpn_encrypt_post(void *data, int ret) rcu_read_unlock(); err: if (unlikely(skb)) - dev_dstats_tx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_tx_dropped(peer->ovpn->dev); if (likely(peer)) ovpn_peer_put(peer); if (likely(ks)) @@ -343,7 +343,7 @@ static void ovpn_send(struct ovpn_priv *ovpn, struct sk_buff *skb, */ skb_list_walk_safe(skb, curr, next) { if (unlikely(!ovpn_encrypt_one(peer, curr))) { - dev_dstats_tx_dropped(ovpn->dev); + ovpn_dev_dstats_tx_dropped(ovpn->dev); kfree_skb(curr); } } @@ -414,7 +414,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(!curr)) { net_err_ratelimited("%s: skb_share_check failed for payload packet\n", netdev_name(dev)); - dev_dstats_tx_dropped(ovpn->dev); + ovpn_dev_dstats_tx_dropped(ovpn->dev); continue; } @@ -440,7 +440,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) drop: ovpn_peer_put(peer); drop_no_peer: - dev_dstats_tx_dropped(ovpn->dev); + ovpn_dev_dstats_tx_dropped(ovpn->dev); skb_tx_error(skb); kfree_skb_list(skb); return NETDEV_TX_OK; diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c index 2e0420febda0..9993c1dfe471 100644 --- a/drivers/net/ovpn/main.c +++ b/drivers/net/ovpn/main.c @@ -92,6 +92,8 @@ static void ovpn_net_uninit(struct net_device *dev) { struct ovpn_priv *ovpn = netdev_priv(dev); + disable_delayed_work_sync(&ovpn->keepalive_work); + ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN); gro_cells_destroy(&ovpn->gro_cells); } @@ -208,15 +210,6 @@ static int ovpn_newlink(struct net_device *dev, return register_netdevice(dev); } -static void ovpn_dellink(struct net_device *dev, struct list_head *head) -{ - struct ovpn_priv *ovpn = netdev_priv(dev); - - cancel_delayed_work_sync(&ovpn->keepalive_work); - ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN); - unregister_netdevice_queue(dev, head); -} - static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ovpn_priv *ovpn = netdev_priv(dev); @@ -235,7 +228,6 @@ static struct rtnl_link_ops ovpn_link_ops = { .policy = ovpn_policy, .maxtype = IFLA_OVPN_MAX, .newlink = ovpn_newlink, - .dellink = ovpn_dellink, .fill_info = ovpn_fill_info, }; diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c index 291e2e5bb450..4c66c1ec497e 100644 --- a/drivers/net/ovpn/netlink.c +++ b/drivers/net/ovpn/netlink.c @@ -462,10 +462,12 @@ int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info) sock_release: ovpn_socket_release(peer); peer_release: - /* release right away because peer was not yet hashed, thus it is not - * used in any context + /* For UDP, the peer is unreachable until added to the hashtables, so + * dropping the initial reference is enough. For TCP, the peer may be + * concurrently reachable via sk_user_data->peer until + * ovpn_socket_release() detaches; rely on the refcount. */ - ovpn_peer_release(peer); + ovpn_peer_put(peer); return ret; } diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c index c02dfab51a6e..a09d61296425 100644 --- a/drivers/net/ovpn/peer.c +++ b/drivers/net/ovpn/peer.c @@ -354,7 +354,7 @@ static void ovpn_peer_release_rcu(struct rcu_head *head) * ovpn_peer_release - release peer private members * @peer: the peer to release */ -void ovpn_peer_release(struct ovpn_peer *peer) +static void ovpn_peer_release(struct ovpn_peer *peer) { ovpn_crypto_state_release(&peer->crypto); spin_lock_bh(&peer->lock); @@ -1034,14 +1034,29 @@ static int ovpn_peer_add_p2p(struct ovpn_priv *ovpn, struct ovpn_peer *peer) */ int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer) { + int ret = -ENODEV; + + /* Prevent adding new peers while destroying the ovpn interface. + * Failing to do so would end up holding the device reference + * endlessly hostage of the new peer object with no chance of + * release.. + */ + netdev_lock(ovpn->dev); + if (ovpn->dev->reg_state != NETREG_REGISTERED) + goto out; + switch (ovpn->mode) { case OVPN_MODE_MP: - return ovpn_peer_add_mp(ovpn, peer); + ret = ovpn_peer_add_mp(ovpn, peer); + break; case OVPN_MODE_P2P: - return ovpn_peer_add_p2p(ovpn, peer); + ret = ovpn_peer_add_p2p(ovpn, peer); + break; } +out: + netdev_unlock(ovpn->dev); - return -EOPNOTSUPP; + return ret; } /** diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h index 328401570cba..86c8cffada6d 100644 --- a/drivers/net/ovpn/peer.h +++ b/drivers/net/ovpn/peer.h @@ -127,7 +127,6 @@ static inline bool ovpn_peer_hold(struct ovpn_peer *peer) return kref_get_unless_zero(&peer->refcount); } -void ovpn_peer_release(struct ovpn_peer *peer); void ovpn_peer_release_kref(struct kref *kref); /** diff --git a/drivers/net/ovpn/stats.h b/drivers/net/ovpn/stats.h index 53433d8b6c33..3a45b97c0056 100644 --- a/drivers/net/ovpn/stats.h +++ b/drivers/net/ovpn/stats.h @@ -11,6 +11,8 @@ #ifndef _NET_OVPN_OVPNSTATS_H_ #define _NET_OVPN_OVPNSTATS_H_ +#include + /* one stat */ struct ovpn_peer_stat { atomic64_t bytes; @@ -44,4 +46,18 @@ static inline void ovpn_peer_stats_increment_tx(struct ovpn_peer_stats *stats, ovpn_peer_stats_increment(&stats->tx, n); } +static inline void ovpn_dev_dstats_tx_dropped(struct net_device *dev) +{ + local_bh_disable(); + dev_dstats_tx_dropped(dev); + local_bh_enable(); +} + +static inline void ovpn_dev_dstats_rx_dropped(struct net_device *dev) +{ + local_bh_disable(); + dev_dstats_rx_dropped(dev); + local_bh_enable(); +} + #endif /* _NET_OVPN_OVPNSTATS_H_ */ diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 65054cc84be5..433bd07a4f1b 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -152,7 +152,7 @@ static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb) if (WARN_ON(!ovpn_peer_hold(peer))) goto err_nopeer; schedule_work(&peer->tcp.defer_del_work); - dev_dstats_rx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_rx_dropped(peer->ovpn->dev); err_nopeer: kfree_skb(skb); } @@ -298,9 +298,9 @@ static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk) } while (peer->tcp.out_msg.len > 0); if (!peer->tcp.out_msg.len) { - preempt_disable(); + local_bh_disable(); dev_dstats_tx_add(peer->ovpn->dev, skb->len); - preempt_enable(); + local_bh_enable(); } kfree_skb(peer->tcp.out_msg.skb); @@ -331,7 +331,7 @@ static void ovpn_tcp_send_sock_skb(struct ovpn_peer *peer, struct sock *sk, ovpn_tcp_send_sock(peer, sk); if (peer->tcp.out_msg.skb) { - dev_dstats_tx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_tx_dropped(peer->ovpn->dev); kfree_skb(skb); return; } @@ -353,7 +353,7 @@ void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct sock *sk, if (sock_owned_by_user(sk)) { if (skb_queue_len(&peer->tcp.out_queue) >= READ_ONCE(net_hotdata.max_backlog)) { - dev_dstats_tx_dropped(peer->ovpn->dev); + ovpn_dev_dstats_tx_dropped(peer->ovpn->dev); kfree_skb(skb); goto unlock; } @@ -581,14 +581,19 @@ static void ovpn_tcp_close(struct sock *sk, long timeout) rcu_read_lock(); sock = rcu_dereference_sk_user_data(sk); - if (!sock || !sock->peer || !ovpn_peer_hold(sock->peer)) { + if (!sock) { rcu_read_unlock(); return; } + peer = sock->peer; + if (!peer || !ovpn_peer_hold(peer)) { + rcu_read_unlock(); + return; + } rcu_read_unlock(); - ovpn_peer_del(sock->peer, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT); + ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT); peer->tcp.sk_cb.prot->close(sk, timeout); ovpn_peer_put(peer); } diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c index 059e896b4a2f..8811aa9eedeb 100644 --- a/drivers/net/ovpn/udp.c +++ b/drivers/net/ovpn/udp.c @@ -125,7 +125,7 @@ static int ovpn_udp_encap_recv(struct sock *sk, struct sk_buff *skb) return 0; drop: - dev_dstats_rx_dropped(ovpn->dev); + ovpn_dev_dstats_rx_dropped(ovpn->dev); drop_noovpn: kfree_skb(skb); return 0; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index d48aa7231b37..126951741428 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -940,6 +940,14 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_eee_abilities); */ int genphy_c45_an_config_eee_aneg(struct phy_device *phydev) { + /* Writing MMD AN advertisements while autoneg is disabled has no + * effect on link-partner negotiation, but on some PHYs (e.g. the + * Broadcom BCM54213PE) the write itself disturbs the receive + * datapath. Skip it. + */ + if (phydev->autoneg == AUTONEG_DISABLE) + return 0; + if (!phydev->eee_cfg.eee_enabled) { __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index c2cdf1ae3542..3370eb822017 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2877,7 +2877,8 @@ EXPORT_SYMBOL(phy_advertise_supported); */ void phy_advertise_eee_all(struct phy_device *phydev) { - linkmode_copy(phydev->advertising_eee, phydev->supported_eee); + linkmode_andnot(phydev->advertising_eee, phydev->supported_eee, + phydev->eee_disabled_modes); } EXPORT_SYMBOL_GPL(phy_advertise_eee_all); @@ -2903,7 +2904,8 @@ EXPORT_SYMBOL_GPL(phy_advertise_eee_all); */ void phy_support_eee(struct phy_device *phydev) { - linkmode_copy(phydev->advertising_eee, phydev->supported_eee); + linkmode_andnot(phydev->advertising_eee, phydev->supported_eee, + phydev->eee_disabled_modes); phydev->eee_cfg.tx_lpi_enabled = true; phydev->eee_cfg.eee_enabled = true; diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c index 87aa4f4e9724..69dbdbde9d71 100644 --- a/drivers/net/pse-pd/pse_core.c +++ b/drivers/net/pse-pd/pse_core.c @@ -210,7 +210,7 @@ static int of_load_pse_pis(struct pse_controller_dev *pcdev) ret = of_load_pse_pi_pairsets(node, &pi, ret); if (ret) goto out; - } else if (ret != ENOENT) { + } else if (ret != -ENOENT) { dev_err(pcdev->dev, "error: wrong number of pairsets. Should be 1 or 2, got %d (%pOF)\n", ret, node); diff --git a/drivers/net/tap.c b/drivers/net/tap.c index b8240737dc51..a590e07ce0a9 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -919,11 +919,11 @@ static long tap_ioctl(struct file *file, unsigned int cmd, struct tap_queue *q = file->private_data; struct tap_dev *tap; void __user *argp = (void __user *)arg; + struct sockaddr_storage ss = {}; struct ifreq __user *ifr = argp; unsigned int __user *up = argp; unsigned short u; int __user *sp = argp; - struct sockaddr_storage ss; int s; int ret; diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 0bdb38edd915..e57588c19c80 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -1947,15 +1946,15 @@ int ath10k_wmi_cmd_send(struct ath10k *ar, struct sk_buff *skb, u32 cmd_id) ret = -ESHUTDOWN; ath10k_dbg(ar, ATH10K_DBG_WMI, "drop wmi command %d, hardware is wedged\n", cmd_id); + } else { + /* try to send pending beacons first. they take priority */ + ath10k_wmi_tx_beacons_nowait(ar); + + ret = ath10k_wmi_cmd_send_nowait(ar, skb, cmd_id); + + if (ret && test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags)) + ret = -ESHUTDOWN; } - /* try to send pending beacons first. they take priority */ - ath10k_wmi_tx_beacons_nowait(ar); - - ret = ath10k_wmi_cmd_send_nowait(ar, skb, cmd_id); - - if (ret && test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags)) - ret = -ESHUTDOWN; - (ret != -EAGAIN); }), 3 * HZ); diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c index fe79109adc70..2a413e3a07a7 100644 --- a/drivers/net/wireless/ath/ath11k/dp_rx.c +++ b/drivers/net/wireless/ath/ath11k/dp_rx.c @@ -1761,6 +1761,7 @@ static int ath11k_dp_rx_msdu_coalesce(struct ath11k *ar, int buf_first_hdr_len, buf_first_len; struct hal_rx_desc *ldesc; int space_extra, rem_len, buf_len; + bool is_continuation; u32 hal_rx_desc_sz = ar->ab->hw_params.hal_desc_sz; /* As the msdu is spread across multiple rx buffers, @@ -1810,7 +1811,8 @@ static int ath11k_dp_rx_msdu_coalesce(struct ath11k *ar, rem_len = msdu_len - buf_first_len; while ((skb = __skb_dequeue(msdu_list)) != NULL && rem_len > 0) { rxcb = ATH11K_SKB_RXCB(skb); - if (rxcb->is_continuation) + is_continuation = rxcb->is_continuation; + if (is_continuation) buf_len = DP_RX_BUFFER_SIZE - hal_rx_desc_sz; else buf_len = rem_len; @@ -1828,7 +1830,7 @@ static int ath11k_dp_rx_msdu_coalesce(struct ath11k *ar, dev_kfree_skb_any(skb); rem_len -= buf_len; - if (!rxcb->is_continuation) + if (!is_continuation) break; } @@ -2214,8 +2216,7 @@ ath11k_dp_rx_h_find_peer(struct ath11k_base *ab, struct sk_buff *msdu) lockdep_assert_held(&ab->base_lock); - if (rxcb->peer_id) - peer = ath11k_peer_find_by_id(ab, rxcb->peer_id); + peer = ath11k_peer_find_by_id(ab, rxcb->peer_id); if (peer) return peer; diff --git a/drivers/net/wireless/ath/ath11k/hal.c b/drivers/net/wireless/ath/ath11k/hal.c index e821e5a62c1c..98bd9e3f0aae 100644 --- a/drivers/net/wireless/ath/ath11k/hal.c +++ b/drivers/net/wireless/ath/ath11k/hal.c @@ -1387,14 +1387,22 @@ EXPORT_SYMBOL(ath11k_hal_srng_deinit); void ath11k_hal_srng_clear(struct ath11k_base *ab) { - /* No need to memset rdp and wrp memory since each individual - * segment would get cleared in ath11k_hal_srng_src_hw_init() - * and ath11k_hal_srng_dst_hw_init(). + /* + * Preserve the shared pointer buffers, but clear the previous + * firmware instance's hp/tp state before handing them back to FW. + * LMAC rings reuse this shared memory without going through the + * normal SRNG hw-init path that zeros non-LMAC ring pointers. */ memset(ab->hal.srng_list, 0, sizeof(ab->hal.srng_list)); memset(ab->hal.shadow_reg_addr, 0, sizeof(ab->hal.shadow_reg_addr)); + if (ab->hal.rdp.vaddr) + memset(ab->hal.rdp.vaddr, 0, + sizeof(*ab->hal.rdp.vaddr) * HAL_SRNG_RING_ID_MAX); + if (ab->hal.wrp.vaddr) + memset(ab->hal.wrp.vaddr, 0, + sizeof(*ab->hal.wrp.vaddr) * HAL_SRNG_NUM_LMAC_RINGS); ab->hal.avail_blk_resource = 0; ab->hal.current_blk_index = 0; ab->hal.num_shadow_reg_configured = 0; diff --git a/drivers/net/wireless/ath/ath11k/hal_rx.c b/drivers/net/wireless/ath/ath11k/hal_rx.c index 753bd93f0212..51e0840bc0d1 100644 --- a/drivers/net/wireless/ath/ath11k/hal_rx.c +++ b/drivers/net/wireless/ath/ath11k/hal_rx.c @@ -1467,11 +1467,8 @@ ath11k_hal_rx_parse_mon_status_tlv(struct ath11k_base *ab, case HAL_RX_MPDU_START: { struct hal_rx_mpdu_info *mpdu_info = (struct hal_rx_mpdu_info *)tlv_data; - u16 peer_id; - peer_id = ath11k_hal_rx_mpduinfo_get_peerid(ab, mpdu_info); - if (peer_id) - ppdu_info->peer_id = peer_id; + ppdu_info->peer_id = ath11k_hal_rx_mpduinfo_get_peerid(ab, mpdu_info); break; } case HAL_RXPCU_PPDU_END_INFO: { diff --git a/drivers/net/wireless/ath/ath11k/testmode.c b/drivers/net/wireless/ath/ath11k/testmode.c index a9751ea2a0b7..c72eed358f6d 100644 --- a/drivers/net/wireless/ath/ath11k/testmode.c +++ b/drivers/net/wireless/ath/ath11k/testmode.c @@ -457,6 +457,7 @@ static int ath11k_tm_cmd_wmi_ftm(struct ath11k *ar, struct nlattr *tb[]) ret = ath11k_wmi_cmd_send(wmi, skb, cmd_id); if (ret) { ath11k_warn(ar->ab, "failed to send wmi ftm command: %d\n", ret); + dev_kfree_skb(skb); goto out; } diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index 40747fba3b0c..dca6e011cc40 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -9299,7 +9299,7 @@ int ath11k_wmi_hw_data_filter_cmd(struct ath11k *ar, u32 vdev_id, { struct wmi_hw_data_filter_cmd *cmd; struct sk_buff *skb; - int len; + int ret, len; len = sizeof(*cmd); skb = ath11k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -9324,7 +9324,13 @@ int ath11k_wmi_hw_data_filter_cmd(struct ath11k *ar, u32 vdev_id, "hw data filter enable %d filter_bitmap 0x%x\n", enable, filter_bitmap); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_HW_DATA_FILTER_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_HW_DATA_FILTER_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_HW_DATA_FILTER_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_wow_host_wakeup_ind(struct ath11k *ar) @@ -9332,6 +9338,7 @@ int ath11k_wmi_wow_host_wakeup_ind(struct ath11k *ar) struct wmi_wow_host_wakeup_ind *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd); skb = ath11k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -9345,14 +9352,20 @@ int ath11k_wmi_wow_host_wakeup_ind(struct ath11k *ar) ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "tlv wow host wakeup ind\n"); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_WOW_HOSTWAKEUP_FROM_SLEEP_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_wow_enable(struct ath11k *ar) { struct wmi_wow_enable_cmd *cmd; struct sk_buff *skb; - int len; + int ret, len; len = sizeof(*cmd); skb = ath11k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -9367,7 +9380,13 @@ int ath11k_wmi_wow_enable(struct ath11k *ar) cmd->pause_iface_config = WOW_IFACE_PAUSE_ENABLED; ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "tlv wow enable\n"); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_WOW_ENABLE_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_scan_prob_req_oui(struct ath11k *ar, @@ -9376,7 +9395,7 @@ int ath11k_wmi_scan_prob_req_oui(struct ath11k *ar, struct sk_buff *skb; struct wmi_scan_prob_req_oui_cmd *cmd; u32 prob_req_oui; - int len; + int ret, len; prob_req_oui = (((u32)mac_addr[0]) << 16) | (((u32)mac_addr[1]) << 8) | mac_addr[2]; @@ -9395,7 +9414,13 @@ int ath11k_wmi_scan_prob_req_oui(struct ath11k *ar, ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "scan prob req oui %d\n", prob_req_oui); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_SCAN_PROB_REQ_OUI_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_SCAN_PROB_REQ_OUI_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_SCAN_PROB_REQ_OUI_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_wow_add_wakeup_event(struct ath11k *ar, u32 vdev_id, @@ -9405,6 +9430,7 @@ int ath11k_wmi_wow_add_wakeup_event(struct ath11k *ar, u32 vdev_id, struct wmi_wow_add_del_event_cmd *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd); skb = ath11k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -9422,7 +9448,13 @@ int ath11k_wmi_wow_add_wakeup_event(struct ath11k *ar, u32 vdev_id, ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "tlv wow add wakeup event %s enable %d vdev_id %d\n", wow_wakeup_event(event), enable, vdev_id); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_WOW_ENABLE_DISABLE_WAKE_EVENT_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_wow_add_pattern(struct ath11k *ar, u32 vdev_id, u32 pattern_id, @@ -9435,6 +9467,7 @@ int ath11k_wmi_wow_add_pattern(struct ath11k *ar, u32 vdev_id, u32 pattern_id, struct sk_buff *skb; u8 *ptr; size_t len; + int ret; len = sizeof(*cmd) + sizeof(*tlv) + /* array struct */ @@ -9527,7 +9560,13 @@ int ath11k_wmi_wow_add_pattern(struct ath11k *ar, u32 vdev_id, u32 pattern_id, ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "tlv wow add pattern vdev_id %d pattern_id %d pattern_offset %d\n", vdev_id, pattern_id, pattern_offset); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ADD_WAKE_PATTERN_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_ADD_WAKE_PATTERN_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_WOW_ADD_WAKE_PATTERN_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_wow_del_pattern(struct ath11k *ar, u32 vdev_id, u32 pattern_id) @@ -9535,6 +9574,7 @@ int ath11k_wmi_wow_del_pattern(struct ath11k *ar, u32 vdev_id, u32 pattern_id) struct wmi_wow_del_pattern_cmd *cmd; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd); skb = ath11k_wmi_alloc_skb(ar->wmi->wmi_ab, len); @@ -9553,7 +9593,13 @@ int ath11k_wmi_wow_del_pattern(struct ath11k *ar, u32 vdev_id, u32 pattern_id) ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "tlv wow del pattern vdev_id %d pattern_id %d\n", vdev_id, pattern_id); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_DEL_WAKE_PATTERN_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_WOW_DEL_WAKE_PATTERN_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_WOW_DEL_WAKE_PATTERN_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } static struct sk_buff * @@ -9697,6 +9743,7 @@ int ath11k_wmi_wow_config_pno(struct ath11k *ar, u32 vdev_id, struct wmi_pno_scan_req *pno_scan) { struct sk_buff *skb; + int ret; if (pno_scan->enable) skb = ath11k_wmi_op_gen_config_pno_start(ar, vdev_id, pno_scan); @@ -9706,7 +9753,13 @@ int ath11k_wmi_wow_config_pno(struct ath11k *ar, u32 vdev_id, if (IS_ERR_OR_NULL(skb)) return -ENOMEM; - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_NETWORK_LIST_OFFLOAD_CONFIG_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_NETWORK_LIST_OFFLOAD_CONFIG_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_NETWORK_LIST_OFFLOAD_CONFIG_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } static void ath11k_wmi_fill_ns_offload(struct ath11k *ar, @@ -9824,6 +9877,7 @@ int ath11k_wmi_arp_ns_offload(struct ath11k *ar, u8 *buf_ptr; size_t len; u8 ns_cnt, ns_ext_tuples = 0; + int ret; offload = &arvif->arp_ns_offload; ns_cnt = offload->ipv6_count; @@ -9862,7 +9916,13 @@ int ath11k_wmi_arp_ns_offload(struct ath11k *ar, if (ns_ext_tuples) ath11k_wmi_fill_ns_offload(ar, offload, &buf_ptr, enable, 1); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_SET_ARP_NS_OFFLOAD_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_SET_ARP_NS_OFFLOAD_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_SET_ARP_NS_OFFLOAD_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_gtk_rekey_offload(struct ath11k *ar, @@ -9870,7 +9930,7 @@ int ath11k_wmi_gtk_rekey_offload(struct ath11k *ar, { struct wmi_gtk_rekey_offload_cmd *cmd; struct ath11k_rekey_data *rekey_data = &arvif->rekey_data; - int len; + int ret, len; struct sk_buff *skb; __le64 replay_ctr; @@ -9904,14 +9964,20 @@ int ath11k_wmi_gtk_rekey_offload(struct ath11k *ar, ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "offload gtk rekey vdev: %d %d\n", arvif->vdev_id, enable); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_GTK_OFFLOAD_CMDID offload\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_gtk_rekey_getinfo(struct ath11k *ar, struct ath11k_vif *arvif) { struct wmi_gtk_rekey_offload_cmd *cmd; - int len; + int ret, len; struct sk_buff *skb; len = sizeof(*cmd); @@ -9928,7 +9994,13 @@ int ath11k_wmi_gtk_rekey_getinfo(struct ath11k *ar, ath11k_dbg(ar->ab, ATH11K_DBG_WMI, "get gtk rekey vdev_id: %d\n", arvif->vdev_id); - return ath11k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + ret = ath11k_wmi_cmd_send(ar->wmi, skb, WMI_GTK_OFFLOAD_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_GTK_OFFLOAD_CMDID getinfo\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_pdev_set_bios_sar_table_param(struct ath11k *ar, const u8 *sar_val) @@ -9938,6 +10010,7 @@ int ath11k_wmi_pdev_set_bios_sar_table_param(struct ath11k *ar, const u8 *sar_va struct sk_buff *skb; u8 *buf_ptr; u32 len, sar_len_aligned, rsvd_len_aligned; + int ret; sar_len_aligned = roundup(BIOS_SAR_TABLE_LEN, sizeof(u32)); rsvd_len_aligned = roundup(BIOS_SAR_RSVD1_LEN, sizeof(u32)); @@ -9968,7 +10041,13 @@ int ath11k_wmi_pdev_set_bios_sar_table_param(struct ath11k *ar, const u8 *sar_va tlv->header = FIELD_PREP(WMI_TLV_TAG, WMI_TAG_ARRAY_BYTE) | FIELD_PREP(WMI_TLV_LEN, rsvd_len_aligned); - return ath11k_wmi_cmd_send(wmi, skb, WMI_PDEV_SET_BIOS_SAR_TABLE_CMDID); + ret = ath11k_wmi_cmd_send(wmi, skb, WMI_PDEV_SET_BIOS_SAR_TABLE_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_PDEV_SET_BIOS_SAR_TABLE_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_pdev_set_bios_geo_table_param(struct ath11k *ar) @@ -9979,6 +10058,7 @@ int ath11k_wmi_pdev_set_bios_geo_table_param(struct ath11k *ar) struct sk_buff *skb; u8 *buf_ptr; u32 len, rsvd_len_aligned; + int ret; rsvd_len_aligned = roundup(BIOS_SAR_RSVD2_LEN, sizeof(u32)); len = sizeof(*cmd) + TLV_HDR_SIZE + rsvd_len_aligned; @@ -9998,7 +10078,13 @@ int ath11k_wmi_pdev_set_bios_geo_table_param(struct ath11k *ar) tlv->header = FIELD_PREP(WMI_TLV_TAG, WMI_TAG_ARRAY_BYTE) | FIELD_PREP(WMI_TLV_LEN, rsvd_len_aligned); - return ath11k_wmi_cmd_send(wmi, skb, WMI_PDEV_SET_BIOS_GEO_TABLE_CMDID); + ret = ath11k_wmi_cmd_send(wmi, skb, WMI_PDEV_SET_BIOS_GEO_TABLE_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_PDEV_SET_BIOS_GEO_TABLE_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } int ath11k_wmi_sta_keepalive(struct ath11k *ar, @@ -10009,6 +10095,7 @@ int ath11k_wmi_sta_keepalive(struct ath11k *ar, struct wmi_sta_keepalive_arp_resp *arp; struct sk_buff *skb; size_t len; + int ret; len = sizeof(*cmd) + sizeof(*arp); skb = ath11k_wmi_alloc_skb(wmi->wmi_ab, len); @@ -10040,7 +10127,13 @@ int ath11k_wmi_sta_keepalive(struct ath11k *ar, "sta keepalive vdev %d enabled %d method %d interval %d\n", arg->vdev_id, arg->enabled, arg->method, arg->interval); - return ath11k_wmi_cmd_send(wmi, skb, WMI_STA_KEEPALIVE_CMDID); + ret = ath11k_wmi_cmd_send(wmi, skb, WMI_STA_KEEPALIVE_CMDID); + if (ret) { + ath11k_warn(ar->ab, "failed to send WMI_STA_KEEPALIVE_CMDID\n"); + dev_kfree_skb(skb); + } + + return ret; } bool ath11k_wmi_supports_6ghz_cc_ext(struct ath11k *ar) diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index df2334f3bad6..2cff9485c95a 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -3446,7 +3446,9 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, arg->peer_eht_mcs_count++; fallthrough; default: - if (!(link_sta->he_cap.he_cap_elem.phy_cap_info[0] & + if ((vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_MESH_POINT) && + !(link_sta->he_cap.he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) { bw_20 = &eht_cap->eht_mcs_nss_supp.only_20mhz; @@ -3475,7 +3477,9 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, arg->punct_bitmap = ~arvif->punct_bitmap; arg->eht_disable_mcs15 = link_conf->eht_disable_mcs15; - if (!(link_sta->he_cap.he_cap_elem.phy_cap_info[0] & + if ((vif->type == NL80211_IFTYPE_AP || + vif->type == NL80211_IFTYPE_MESH_POINT) && + !(link_sta->he_cap.he_cap_elem.phy_cap_info[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) { if (bw_20->rx_tx_mcs13_max_nss) max_nss = max(max_nss, u8_get_bits(bw_20->rx_tx_mcs13_max_nss, diff --git a/drivers/net/wireless/intel/iwlwifi/mld/constants.h b/drivers/net/wireless/intel/iwlwifi/mld/constants.h index e2a5eecc18c3..890abcab3837 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/constants.h +++ b/drivers/net/wireless/intel/iwlwifi/mld/constants.h @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2024-2025 Intel Corporation + * Copyright (C) 2024-2026 Intel Corporation */ #ifndef __iwl_mld_constants_h__ #define __iwl_mld_constants_h__ -#define IWL_MLD_MISSED_BEACONS_SINCE_RX_THOLD 4 +#define IWL_MLD_MISSED_BEACONS_SINCE_RX_THOLD 6 #define IWL_MLD_MISSED_BEACONS_THRESHOLD 8 #define IWL_MLD_MISSED_BEACONS_THRESHOLD_LONG 19 #define IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH_2_LINKS 5 diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.c b/drivers/net/wireless/intel/iwlwifi/mld/d3.c index ef98efc8fb1b..3a595a1c2e00 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.c @@ -1930,12 +1930,12 @@ int iwl_mld_wowlan_suspend(struct iwl_mld *mld, struct cfg80211_wowlan *wowlan) if (WARN_ON(!wowlan)) return 1; - IWL_DEBUG_WOWLAN(mld, "Starting the wowlan suspend flow\n"); - bss_vif = iwl_mld_get_bss_vif(mld); - if (WARN_ON(!bss_vif)) + if (!bss_vif) return 1; + IWL_DEBUG_WOWLAN(mld, "Starting the wowlan suspend flow\n"); + if (!bss_vif->cfg.assoc) { int ret; /* If we're not associated, this must be netdetect */ diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c index b66e84d2365f..be2cdf43c72e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2024-2025 Intel Corporation + * Copyright (C) 2024-2026 Intel Corporation */ #include "constants.h" @@ -504,7 +504,6 @@ void iwl_mld_remove_link(struct iwl_mld *mld, struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(bss_conf->vif); struct iwl_mld_link *link = iwl_mld_link_from_mac80211(bss_conf); bool is_deflink = link == &mld_vif->deflink; - u8 fw_id = link->fw_id; if (WARN_ON(!link || link->active)) return; @@ -512,15 +511,15 @@ void iwl_mld_remove_link(struct iwl_mld *mld, iwl_mld_rm_link_from_fw(mld, bss_conf); /* Continue cleanup on failure */ - if (!is_deflink) - kfree_rcu(link, rcu_head); - RCU_INIT_POINTER(mld_vif->link[bss_conf->link_id], NULL); - if (WARN_ON(fw_id >= mld->fw->ucode_capa.num_links)) + if (WARN_ON(link->fw_id >= mld->fw->ucode_capa.num_links)) return; - RCU_INIT_POINTER(mld->fw_id_to_bss_conf[fw_id], NULL); + RCU_INIT_POINTER(mld->fw_id_to_bss_conf[link->fw_id], NULL); + + if (!is_deflink) + kfree_rcu(link, rcu_head); } void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld, diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tx.c b/drivers/net/wireless/intel/iwlwifi/mld/tx.c index 546d09a38dab..0bcb1ae69468 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/tx.c @@ -834,7 +834,7 @@ static int iwl_mld_tx_tso_segment(struct iwl_mld *mld, struct sk_buff *skb, return -EINVAL; max_tid_amsdu_len = sta->cur->max_tid_amsdu_len[tid]; - if (!max_tid_amsdu_len) + if (!max_tid_amsdu_len || max_tid_amsdu_len == 1) return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skbs); /* Sub frame header + SNAP + IP header + TCP header + MSS */ @@ -846,6 +846,9 @@ static int iwl_mld_tx_tso_segment(struct iwl_mld *mld, struct sk_buff *skb, */ num_subframes = (max_tid_amsdu_len + pad) / (subf_len + pad); + if (WARN_ON_ONCE(!num_subframes)) + return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skbs); + if (sta->max_amsdu_subframes && num_subframes > sta->max_amsdu_subframes) num_subframes = sta->max_amsdu_subframes; @@ -970,6 +973,16 @@ void iwl_mld_tx_from_txq(struct iwl_mld *mld, struct ieee80211_txq *txq) struct sk_buff *skb = NULL; u8 zero_addr[ETH_ALEN] = {}; + /* + * Don't transmit during firmware restart. The firmware is dead, + * so iwl_trans_tx() would return -EIO for each frame. Avoid the + * overhead of dequeuing from mac80211 only to immediately free + * the skbs, and the potential memory pressure from rapid skb + * allocation churn during high-throughput restart scenarios. + */ + if (unlikely(mld->fw_status.in_hw_restart)) + return; + /* * No need for threads to be pending here, they can leave the first * taker all the work. diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index c523c5e82d4a..8ffa72aca3cf 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -927,13 +927,18 @@ u8 iwl_mvm_mac_ctxt_get_lowest_rate(struct iwl_mvm *mvm, u16 iwl_mvm_mac_ctxt_get_beacon_flags(const struct iwl_fw *fw, u8 rate_idx) { - u16 flags = iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); bool is_new_rate = iwl_fw_lookup_cmd_ver(fw, BEACON_TEMPLATE_CMD, 0) > 10; + u16 flags = 0; if (rate_idx <= IWL_LAST_CCK_RATE) flags |= is_new_rate ? IWL_MAC_BEACON_CCK : IWL_MAC_BEACON_CCK_V1; + if (iwl_fw_lookup_cmd_ver(fw, TX_CMD, 0) > 8) + flags |= iwl_mvm_mac80211_idx_to_hwrate(fw, rate_idx); + else + flags |= iwl_fw_rate_idx_to_plcp(rate_idx); + return flags; } @@ -962,6 +967,7 @@ static void iwl_mvm_mac_ctxt_set_tx(struct iwl_mvm *mvm, { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct ieee80211_tx_info *info; + u32 rate_n_flags = 0; u8 rate; u32 tx_flags; @@ -981,18 +987,21 @@ static void iwl_mvm_mac_ctxt_set_tx(struct iwl_mvm *mvm, IWL_UCODE_TLV_CAPA_BEACON_ANT_SELECTION)) { iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx); - tx_params->rate_n_flags = - cpu_to_le32(BIT(mvm->mgmt_last_antenna_idx) << - RATE_MCS_ANT_POS); + rate_n_flags |= BIT(mvm->mgmt_last_antenna_idx) << + RATE_MCS_ANT_POS; } rate = iwl_mvm_mac_ctxt_get_beacon_rate(mvm, info, vif); - tx_params->rate_n_flags |= - cpu_to_le32(iwl_mvm_mac80211_idx_to_hwrate(mvm->fw, rate)); - if (rate == IWL_FIRST_CCK_RATE) - tx_params->rate_n_flags |= cpu_to_le32(RATE_MCS_CCK_MSK_V1); + if (rate < IWL_FIRST_OFDM_RATE) + rate_n_flags |= RATE_MCS_MOD_TYPE_CCK; + else + rate_n_flags |= RATE_MCS_MOD_TYPE_LEGACY_OFDM; + rate_n_flags |= iwl_mvm_mac80211_idx_to_hwrate(mvm->fw, rate); + + tx_params->rate_n_flags = iwl_mvm_v3_rate_to_fw(rate_n_flags, + mvm->fw_rates_ver); } int iwl_mvm_mac_ctxt_send_beacon_cmd(struct iwl_mvm *mvm, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index 4a33a032c2a7..f052537e9567 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2025 Intel Corporation + * Copyright (C) 2012-2014, 2018-2026 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH */ @@ -159,15 +159,9 @@ int iwl_mvm_legacy_rate_to_mac80211_idx(u32 rate_n_flags, u8 iwl_mvm_mac80211_idx_to_hwrate(const struct iwl_fw *fw, int rate_idx) { - if (iwl_fw_lookup_cmd_ver(fw, TX_CMD, 0) > 8) - /* In the new rate legacy rates are indexed: - * 0 - 3 for CCK and 0 - 7 for OFDM. - */ - return (rate_idx >= IWL_FIRST_OFDM_RATE ? - rate_idx - IWL_FIRST_OFDM_RATE : - rate_idx); - - return iwl_fw_rate_idx_to_plcp(rate_idx); + return rate_idx >= IWL_FIRST_OFDM_RATE ? + rate_idx - IWL_FIRST_OFDM_RATE : + rate_idx; } u8 iwl_mvm_mac80211_ac_to_ucode_ac(enum ieee80211_ac_numbers ac) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans-gen2.c index a50e845cea42..64262bcca55d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans-gen2.c @@ -398,9 +398,9 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans) mutex_unlock(&trans_pcie->mutex); if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) - trans->step_urm = !!(iwl_read_umac_prph(trans, - CNVI_PMU_STEP_FLOW) & - CNVI_PMU_STEP_FLOW_FORCE_URM); + trans->step_urm = !!(iwl_read_prph(trans, + CNVI_PMU_STEP_FLOW) & + CNVI_PMU_STEP_FLOW_FORCE_URM); } static bool iwl_pcie_set_ltr(struct iwl_trans *trans) diff --git a/drivers/net/wireless/microchip/wilc1000/wlan.c b/drivers/net/wireless/microchip/wilc1000/wlan.c index 3fa8592eb250..4b116fe6f9ea 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan.c +++ b/drivers/net/wireless/microchip/wilc1000/wlan.c @@ -1265,7 +1265,7 @@ int wilc_wlan_firmware_download(struct wilc *wilc, const u8 *buffer, ret = acquire_bus(wilc, WILC_BUS_ACQUIRE_AND_WAKEUP); if (ret) - return ret; + goto fail; wilc->hif_func->hif_read_reg(wilc, WILC_GLB_RESET_0, ®); reg &= ~BIT(10); diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index 1b7bc7d63a2e..4405c8531888 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -1425,6 +1425,8 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, protocol_init_fail: cancel_work_sync(&ipc_imem->run_state_worker); ipc_task_deinit(ipc_imem->ipc_task); + if (ipc_imem->ipc_protocol) + ipc_protocol_deinit(ipc_imem->ipc_protocol); ipc_task_init_fail: kfree(ipc_imem->ipc_task); ipc_task_fail: diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index 714bcab97b60..08a0e7091ced 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -2072,8 +2072,10 @@ static int brcm_pcie_probe(struct platform_device *pdev) return PTR_ERR(pcie->clk); ret = of_pci_get_max_link_speed(np); - if (pcie_get_link_speed(ret) == PCI_SPEED_UNKNOWN) + if (ret < 0 || ret > 3) pcie->gen = 0; + else + pcie->gen = ret; pcie->ssc = of_property_read_bool(np, "brcm,enable-ssc"); diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h index d3aefbec4de6..34c115d7c250 100644 --- a/fs/9p/v9fs_vfs.h +++ b/fs/9p/v9fs_vfs.h @@ -75,17 +75,4 @@ static inline void v9fs_invalidate_inode_attr(struct inode *inode) int v9fs_open_to_dotl_flags(int flags); -static inline void v9fs_i_size_write(struct inode *inode, loff_t i_size) -{ - /* - * 32-bit need the lock, concurrent updates could break the - * sequences and make i_size_read() loop forever. - * 64-bit updates are atomic and can skip the locking. - */ - if (sizeof(i_size) > sizeof(long)) - spin_lock(&inode->i_lock); - i_size_write(inode, i_size); - if (sizeof(i_size) > sizeof(long)) - spin_unlock(&inode->i_lock); -} #endif diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index d1508b1fe109..f468acb8ee7d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1141,11 +1141,13 @@ v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - v9inode->netfs.remote_i_size = stat->length; + spin_lock(&inode->i_lock); + netfs_write_remote_i_size(inode, stat->length); if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) - v9fs_i_size_write(inode, stat->length); + i_size_write(inode, stat->length); /* not real number of blocks, but 512 byte ones ... */ inode->i_blocks = (stat->length + 512 - 1) >> 9; + spin_unlock(&inode->i_lock); v9inode->cache_validity &= ~V9FS_INO_INVALID_ATTR; } diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 71796a89bcf4..141fb54db65d 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -634,10 +634,12 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; - v9inode->netfs.remote_i_size = stat->st_size; + spin_lock(&inode->i_lock); + netfs_write_remote_i_size(inode, stat->st_size); if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE)) - v9fs_i_size_write(inode, stat->st_size); + i_size_write(inode, stat->st_size); inode->i_blocks = stat->st_blocks; + spin_unlock(&inode->i_lock); } else { if (stat->st_result_mask & P9_STATS_ATIME) { inode_set_atime(inode, stat->st_atime_sec, @@ -662,13 +664,15 @@ v9fs_stat2inode_dotl(struct p9_stat_dotl *stat, struct inode *inode, mode |= inode->i_mode & ~S_IALLUGO; inode->i_mode = mode; } + spin_lock(&inode->i_lock); if (!(flags & V9FS_STAT2INODE_KEEP_ISIZE) && stat->st_result_mask & P9_STATS_SIZE) { - v9inode->netfs.remote_i_size = stat->st_size; - v9fs_i_size_write(inode, stat->st_size); + netfs_write_remote_i_size(inode, stat->st_size); + i_size_write(inode, stat->st_size); } if (stat->st_result_mask & P9_STATS_BLOCKS) inode->i_blocks = stat->st_blocks; + spin_unlock(&inode->i_lock); } if (stat->st_result_mask & P9_STATS_GEN) inode->i_generation = stat->st_gen; diff --git a/fs/afs/Makefile b/fs/afs/Makefile index b49b8fe682f3..0d8f1982d596 100644 --- a/fs/afs/Makefile +++ b/fs/afs/Makefile @@ -30,6 +30,7 @@ kafs-y := \ server.o \ server_list.o \ super.o \ + symlink.o \ validation.o \ vlclient.o \ vl_alias.o \ diff --git a/fs/afs/dir.c b/fs/afs/dir.c index aaaa55878ffd..498b99ccdf0e 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -44,6 +44,8 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags); +static int afs_dir_writepages(struct address_space *mapping, + struct writeback_control *wbc); const struct file_operations afs_dir_file_operations = { .open = afs_dir_open, @@ -68,7 +70,7 @@ const struct inode_operations afs_dir_inode_operations = { }; const struct address_space_operations afs_dir_aops = { - .writepages = afs_single_writepages, + .writepages = afs_dir_writepages, }; const struct dentry_operations afs_fs_dentry_operations = { @@ -233,22 +235,13 @@ static ssize_t afs_do_read_single(struct afs_vnode *dvnode, struct file *file) struct iov_iter iter; ssize_t ret; loff_t i_size; - bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) && - !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags)); i_size = i_size_read(&dvnode->netfs.inode); - if (is_dir) { - if (i_size < AFS_DIR_BLOCK_SIZE) - return afs_bad(dvnode, afs_file_error_dir_small); - if (i_size > AFS_DIR_BLOCK_SIZE * 1024) { - trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); - return -EFBIG; - } - } else { - if (i_size > AFSPATHMAX) { - trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); - return -EFBIG; - } + if (i_size < AFS_DIR_BLOCK_SIZE) + return afs_bad(dvnode, afs_file_error_dir_small); + if (i_size > AFS_DIR_BLOCK_SIZE * 1024) { + trace_afs_file_error(dvnode, -EFBIG, afs_file_error_dir_big); + return -EFBIG; } /* Expand the storage. TODO: Shrink the storage too. */ @@ -277,24 +270,18 @@ static ssize_t afs_do_read_single(struct afs_vnode *dvnode, struct file *file) * buffer. */ ret = -ESTALE; - } else if (is_dir) { + } else { int ret2 = afs_dir_check(dvnode); if (ret2 < 0) ret = ret2; - } else if (i_size < folioq_folio_size(dvnode->directory, 0)) { - /* NUL-terminate a symlink. */ - char *symlink = kmap_local_folio(folioq_folio(dvnode->directory, 0), 0); - - symlink[i_size] = 0; - kunmap_local(symlink); } } return ret; } -ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file) +static ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file) { ssize_t ret; @@ -1763,13 +1750,20 @@ static int afs_link(struct dentry *from, struct inode *dir, return ret; } +static void afs_symlink_put(struct afs_operation *op) +{ + kfree(op->create.symlink); + op->create.symlink = NULL; + afs_create_put(op); +} + static const struct afs_operation_ops afs_symlink_operation = { .issue_afs_rpc = afs_fs_symlink, .issue_yfs_rpc = yfs_fs_symlink, .success = afs_create_success, .aborted = afs_check_for_remote_deletion, .edit_dir = afs_create_edit_dir, - .put = afs_create_put, + .put = afs_symlink_put, }; /* @@ -1779,7 +1773,9 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *content) { struct afs_operation *op; + struct afs_symlink *symlink; struct afs_vnode *dvnode = AFS_FS_I(dir); + size_t clen = strlen(content); int ret; _enter("{%llx:%llu},{%pd},%s", @@ -1791,12 +1787,20 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, goto error; ret = -EINVAL; - if (strlen(content) >= AFSPATHMAX) + if (clen >= AFSPATHMAX) goto error; + ret = -ENOMEM; + symlink = kmalloc_flex(struct afs_symlink, content, clen + 1, GFP_KERNEL); + if (!symlink) + goto error; + refcount_set(&symlink->ref, 1); + memcpy(symlink->content, content, clen + 1); + op = afs_alloc_operation(NULL, dvnode->volume); if (IS_ERR(op)) { ret = PTR_ERR(op); + kfree(symlink); goto error; } @@ -1808,7 +1812,7 @@ static int afs_symlink(struct mnt_idmap *idmap, struct inode *dir, op->dentry = dentry; op->ops = &afs_symlink_operation; op->create.reason = afs_edit_dir_for_symlink; - op->create.symlink = content; + op->create.symlink = symlink; op->mtime = current_time(dir); ret = afs_do_sync_operation(op); afs_dir_unuse_cookie(dvnode, ret); @@ -2192,28 +2196,33 @@ static int afs_rename(struct mnt_idmap *idmap, struct inode *old_dir, } /* - * Write the file contents to the cache as a single blob. + * Write the directory contents to the cache as a single blob. */ -int afs_single_writepages(struct address_space *mapping, - struct writeback_control *wbc) +static int afs_dir_writepages(struct address_space *mapping, + struct writeback_control *wbc) { struct afs_vnode *dvnode = AFS_FS_I(mapping->host); struct iov_iter iter; - bool is_dir = (S_ISDIR(dvnode->netfs.inode.i_mode) && - !test_bit(AFS_VNODE_MOUNTPOINT, &dvnode->flags)); int ret = 0; /* Need to lock to prevent the folio queue and folios from being thrown * away. */ - down_read(&dvnode->validate_lock); + if (!down_read_trylock(&dvnode->validate_lock)) { + if (wbc->sync_mode == WB_SYNC_NONE) { + /* The VFS will have undirtied the inode. */ + netfs_single_mark_inode_dirty(&dvnode->netfs.inode); + return 0; + } + down_read(&dvnode->validate_lock); + } - if (is_dir ? - test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags) : - atomic64_read(&dvnode->cb_expires_at) != AFS_NO_CB_PROMISE) { + if (test_bit(AFS_VNODE_DIR_VALID, &dvnode->flags)) { iov_iter_folio_queue(&iter, ITER_SOURCE, dvnode->directory, 0, 0, i_size_read(&dvnode->netfs.inode)); ret = netfs_writeback_single(mapping, wbc, &iter); + if (ret == 1) + ret = 0; /* Skipped write due to lock conflict. */ } up_read(&dvnode->validate_lock); diff --git a/fs/afs/file.c b/fs/afs/file.c index 85696ac984cc..0467742bfeee 100644 --- a/fs/afs/file.c +++ b/fs/afs/file.c @@ -427,21 +427,35 @@ static void afs_free_request(struct netfs_io_request *rreq) afs_put_wb_key(rreq->netfs_priv2); } -static void afs_update_i_size(struct inode *inode, loff_t new_i_size) +/* + * Set the file size and block count, taking ->cb_lock and ->i_lock to maintain + * coherency and prevent 64-bit tearing on 32-bit arches. + * + * Also, estimate the number of 512 bytes blocks used, rounded up to nearest 1K + * for consistency with other AFS clients. + */ +void afs_set_i_size(struct afs_vnode *vnode, loff_t new_i_size) { - struct afs_vnode *vnode = AFS_FS_I(inode); + struct inode *inode = &vnode->netfs.inode; loff_t i_size; write_seqlock(&vnode->cb_lock); - i_size = i_size_read(&vnode->netfs.inode); + spin_lock(&inode->i_lock); + i_size = i_size_read(inode); if (new_i_size > i_size) { - i_size_write(&vnode->netfs.inode, new_i_size); - inode_set_bytes(&vnode->netfs.inode, new_i_size); + i_size_write(inode, new_i_size); + inode_set_bytes(inode, round_up(new_i_size, 1024)); } + spin_unlock(&inode->i_lock); write_sequnlock(&vnode->cb_lock); fscache_update_cookie(afs_vnode_cache(vnode), NULL, &new_i_size); } +static void afs_update_i_size(struct inode *inode, loff_t new_i_size) +{ + afs_set_i_size(AFS_FS_I(inode), new_i_size); +} + static void afs_netfs_invalidate_cache(struct netfs_io_request *wreq) { struct afs_vnode *vnode = AFS_FS_I(wreq->inode); diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index 95494d5f2b8a..a2ffd60889f8 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -886,7 +886,7 @@ void afs_fs_symlink(struct afs_operation *op) namesz = name->len; padsz = (4 - (namesz & 3)) & 3; - c_namesz = strlen(op->create.symlink); + c_namesz = strlen(op->create.symlink->content); c_padsz = (4 - (c_namesz & 3)) & 3; reqsz = (6 * 4) + namesz + padsz + c_namesz + c_padsz + (6 * 4); @@ -910,7 +910,7 @@ void afs_fs_symlink(struct afs_operation *op) bp = (void *) bp + padsz; } *bp++ = htonl(c_namesz); - memcpy(bp, op->create.symlink, c_namesz); + memcpy(bp, op->create.symlink->content, c_namesz); bp = (void *) bp + c_namesz; if (c_padsz > 0) { memset(bp, 0, c_padsz); diff --git a/fs/afs/inode.c b/fs/afs/inode.c index a5173434f786..3f48458694ba 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -25,96 +25,6 @@ #include "internal.h" #include "afs_fs.h" -void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op) -{ - size_t size = strlen(op->create.symlink) + 1; - size_t dsize = 0; - char *p; - - if (netfs_alloc_folioq_buffer(NULL, &vnode->directory, &dsize, size, - mapping_gfp_mask(vnode->netfs.inode.i_mapping)) < 0) - return; - - vnode->directory_size = dsize; - p = kmap_local_folio(folioq_folio(vnode->directory, 0), 0); - memcpy(p, op->create.symlink, size); - kunmap_local(p); - set_bit(AFS_VNODE_DIR_READ, &vnode->flags); - netfs_single_mark_inode_dirty(&vnode->netfs.inode); -} - -static void afs_put_link(void *arg) -{ - struct folio *folio = virt_to_folio(arg); - - kunmap_local(arg); - folio_put(folio); -} - -const char *afs_get_link(struct dentry *dentry, struct inode *inode, - struct delayed_call *callback) -{ - struct afs_vnode *vnode = AFS_FS_I(inode); - struct folio *folio; - char *content; - ssize_t ret; - - if (!dentry) { - /* RCU pathwalk. */ - if (!test_bit(AFS_VNODE_DIR_READ, &vnode->flags) || !afs_check_validity(vnode)) - return ERR_PTR(-ECHILD); - goto good; - } - - if (test_bit(AFS_VNODE_DIR_READ, &vnode->flags)) - goto fetch; - - ret = afs_validate(vnode, NULL); - if (ret < 0) - return ERR_PTR(ret); - - if (!test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags) && - test_bit(AFS_VNODE_DIR_READ, &vnode->flags)) - goto good; - -fetch: - ret = afs_read_single(vnode, NULL); - if (ret < 0) - return ERR_PTR(ret); - set_bit(AFS_VNODE_DIR_READ, &vnode->flags); - -good: - folio = folioq_folio(vnode->directory, 0); - folio_get(folio); - content = kmap_local_folio(folio, 0); - set_delayed_call(callback, afs_put_link, content); - return content; -} - -int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen) -{ - DEFINE_DELAYED_CALL(done); - const char *content; - int len; - - content = afs_get_link(dentry, d_inode(dentry), &done); - if (IS_ERR(content)) { - do_delayed_call(&done); - return PTR_ERR(content); - } - - len = umin(strlen(content), buflen); - if (copy_to_user(buffer, content, len)) - len = -EFAULT; - do_delayed_call(&done); - return len; -} - -static const struct inode_operations afs_symlink_inode_operations = { - .get_link = afs_get_link, - .readlink = afs_readlink, -}; - static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode) { static unsigned long once_only; @@ -214,7 +124,7 @@ static int afs_inode_init_from_status(struct afs_operation *op, inode->i_mode = S_IFLNK | status->mode; inode->i_op = &afs_symlink_inode_operations; } - inode->i_mapping->a_ops = &afs_dir_aops; + inode->i_mapping->a_ops = &afs_symlink_aops; inode_nohighmem(inode); mapping_set_release_always(inode->i_mapping); break; @@ -224,7 +134,8 @@ static int afs_inode_init_from_status(struct afs_operation *op, return afs_protocol_error(NULL, afs_eproto_file_type); } - afs_set_i_size(vnode, status->size); + i_size_write(inode, status->size); + inode_set_bytes(inode, status->size); afs_set_netfs_context(vnode); vnode->invalid_before = status->data_version; @@ -253,7 +164,8 @@ static void afs_apply_status(struct afs_operation *op, { struct afs_file_status *status = &vp->scb.status; struct afs_vnode *vnode = vp->vnode; - struct inode *inode = &vnode->netfs.inode; + struct netfs_inode *ictx = &vnode->netfs; + struct inode *inode = &ictx->inode; struct timespec64 t; umode_t mode; bool unexpected_jump = false; @@ -336,6 +248,8 @@ static void afs_apply_status(struct afs_operation *op, } if (data_changed) { + unsigned long long zero_point, size = status->size; + inode_set_iversion_raw(inode, status->data_version); /* Only update the size if the data version jumped. If the @@ -343,16 +257,25 @@ static void afs_apply_status(struct afs_operation *op, * idea of what the size should be that's not the same as * what's on the server. */ - vnode->netfs.remote_i_size = status->size; - if (change_size || status->size > i_size_read(inode)) { - afs_set_i_size(vnode, status->size); + spin_lock(&inode->i_lock); + + if (change_size || size > i_size_read(inode)) { + /* We can read the sizes directly as we hold i_lock. */ + zero_point = ictx->_zero_point; + if (unexpected_jump) - vnode->netfs.zero_point = status->size; + zero_point = size; + netfs_write_sizes(inode, size, size, zero_point); + inode_set_bytes(inode, size); inode_set_ctime_to_ts(inode, t); inode_set_atime_to_ts(inode, t); + } else { + netfs_write_remote_i_size(inode, size); } + spin_unlock(&inode->i_lock); + if (op->ops == &afs_fetch_data_operation) - op->fetch.subreq->rreq->i_size = status->size; + op->fetch.subreq->rreq->i_size = size; } } @@ -709,7 +632,7 @@ int afs_getattr(struct mnt_idmap *idmap, const struct path *path, * it, but we need to give userspace the server's size. */ if (S_ISDIR(inode->i_mode)) - stat->size = vnode->netfs.remote_i_size; + stat->size = netfs_read_remote_i_size(inode); } while (read_seqretry(&vnode->cb_lock, seq)); return 0; @@ -756,12 +679,14 @@ void afs_evict_inode(struct inode *inode) .range_end = LLONG_MAX, }; - afs_single_writepages(inode->i_mapping, &wbc); + inode->i_mapping->a_ops->writepages(inode->i_mapping, &wbc); } netfs_wait_for_outstanding_io(inode); truncate_inode_pages_final(&inode->i_data); netfs_free_folioq_buffer(vnode->directory); + if (vnode->symlink) + afs_evict_symlink(vnode); afs_set_cache_aux(vnode, &aux); netfs_clear_inode_writeback(inode, &aux); @@ -889,7 +814,7 @@ int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, */ if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) && attr->ia_size < i_size && - attr->ia_size > vnode->netfs.remote_i_size) { + attr->ia_size > netfs_read_remote_i_size(inode)) { truncate_setsize(inode, attr->ia_size); netfs_resize_file(&vnode->netfs, size, false); fscache_resize_cookie(afs_vnode_cache(vnode), diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 599353c33337..0b72a8566299 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -710,6 +710,7 @@ struct afs_vnode { #define AFS_VNODE_DIR_READ 11 /* Set if we've read a dir's contents */ struct folio_queue *directory; /* Directory contents */ + struct afs_symlink __rcu *symlink; /* Symlink content */ struct list_head wb_keys; /* List of keys available for writeback */ struct list_head pending_locks; /* locks waiting to be granted */ struct list_head granted_locks; /* locks granted on this file */ @@ -776,6 +777,15 @@ struct afs_permits { struct afs_permit permits[] __counted_by(nr_permits); /* List of permits sorted by key pointer */ }; +/* + * Copy of symlink content for normal use. + */ +struct afs_symlink { + struct rcu_head rcu; + refcount_t ref; + char content[]; +}; + /* * Error prioritisation and accumulation. */ @@ -887,7 +897,7 @@ struct afs_operation { struct { int reason; /* enum afs_edit_dir_reason */ mode_t mode; - const char *symlink; + struct afs_symlink *symlink; } create; struct { bool need_rehash; @@ -1098,13 +1108,10 @@ extern const struct inode_operations afs_dir_inode_operations; extern const struct address_space_operations afs_dir_aops; extern const struct dentry_operations afs_fs_dentry_operations; -ssize_t afs_read_single(struct afs_vnode *dvnode, struct file *file); ssize_t afs_read_dir(struct afs_vnode *dvnode, struct file *file) __acquires(&dvnode->validate_lock); extern void afs_d_release(struct dentry *); extern void afs_check_for_remote_deletion(struct afs_operation *); -int afs_single_writepages(struct address_space *mapping, - struct writeback_control *wbc); /* * dir_edit.c @@ -1157,6 +1164,7 @@ extern int afs_open(struct inode *, struct file *); extern int afs_release(struct inode *, struct file *); void afs_fetch_data_async_rx(struct work_struct *work); void afs_fetch_data_immediate_cancel(struct afs_call *call); +void afs_set_i_size(struct afs_vnode *vnode, loff_t new_i_size); /* * flock.c @@ -1246,10 +1254,6 @@ extern void afs_fs_probe_cleanup(struct afs_net *); */ extern const struct afs_operation_ops afs_fetch_status_operation; -void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op); -const char *afs_get_link(struct dentry *dentry, struct inode *inode, - struct delayed_call *callback); -int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen); extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *); extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *); extern int afs_ilookup5_test_by_fid(struct inode *, void *); @@ -1599,6 +1603,21 @@ void afs_detach_volume_from_servers(struct afs_volume *volume, struct afs_server extern int __init afs_fs_init(void); extern void afs_fs_exit(void); +/* + * symlink.c + */ +extern const struct inode_operations afs_symlink_inode_operations; +extern const struct address_space_operations afs_symlink_aops; + +void afs_invalidate_symlink(struct afs_vnode *vnode); +void afs_evict_symlink(struct afs_vnode *vnode); +void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op); +const char *afs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback); +int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen); +int afs_symlink_writepages(struct address_space *mapping, + struct writeback_control *wbc); + /* * validation.c */ @@ -1758,16 +1777,6 @@ static inline void afs_update_dentry_version(struct afs_operation *op, (void *)(unsigned long)dir_vp->scb.status.data_version; } -/* - * Set the file size and block count. Estimate the number of 512 bytes blocks - * used, rounded up to nearest 1K for consistency with other AFS clients. - */ -static inline void afs_set_i_size(struct afs_vnode *vnode, u64 size) -{ - i_size_write(&vnode->netfs.inode, size); - vnode->netfs.inode.i_blocks = ((size + 1023) >> 10) << 1; -} - /* * Check for a conflicting operation on a directory that we just unlinked from. * If someone managed to sneak a link or an unlink in on the file we just diff --git a/fs/afs/symlink.c b/fs/afs/symlink.c new file mode 100644 index 000000000000..ed5868369f37 --- /dev/null +++ b/fs/afs/symlink.c @@ -0,0 +1,278 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* AFS filesystem symbolic link handling + * + * Copyright (C) 2026 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include +#include +#include +#include +#include +#include "internal.h" + +static void afs_put_symlink(struct afs_symlink *symlink) +{ + if (refcount_dec_and_test(&symlink->ref)) + kfree_rcu(symlink, rcu); +} + +static void afs_replace_symlink(struct afs_vnode *vnode, struct afs_symlink *symlink) +{ + struct afs_symlink *old; + + old = rcu_replace_pointer(vnode->symlink, symlink, + lockdep_is_held(&vnode->validate_lock)); + if (old) + afs_put_symlink(old); +} + +/* + * In the event that a third-party update of a symlink occurs, dispose of the + * copy of the old contents. Called under ->validate_lock. + */ +void afs_invalidate_symlink(struct afs_vnode *vnode) +{ + afs_replace_symlink(vnode, NULL); +} + +/* + * Dispose of a symlink copy during inode deletion. + */ +void afs_evict_symlink(struct afs_vnode *vnode) +{ + struct afs_symlink *old; + + old = rcu_replace_pointer(vnode->symlink, NULL, true); + if (old) + afs_put_symlink(old); + +} + +/* + * Set up a locally created symlink inode for immediate write to the cache. + */ +void afs_init_new_symlink(struct afs_vnode *vnode, struct afs_operation *op) +{ + struct afs_symlink *symlink = op->create.symlink; + size_t dsize = 0; + size_t size = strlen(symlink->content) + 1; + char *p; + + rcu_assign_pointer(vnode->symlink, symlink); + op->create.symlink = NULL; + + if (!fscache_cookie_enabled(netfs_i_cookie(&vnode->netfs))) + return; + + if (netfs_alloc_folioq_buffer(NULL, &vnode->directory, &dsize, size, + mapping_gfp_mask(vnode->netfs.inode.i_mapping)) < 0) + return; + + vnode->directory_size = dsize; + p = kmap_local_folio(folioq_folio(vnode->directory, 0), 0); + memcpy(p, symlink->content, size); + kunmap_local(p); + netfs_single_mark_inode_dirty(&vnode->netfs.inode); +} + +/* + * Read a symlink in a single download. + */ +static ssize_t afs_do_read_symlink(struct afs_vnode *vnode) +{ + struct afs_symlink *symlink; + struct iov_iter iter; + ssize_t ret; + loff_t i_size; + + i_size = i_size_read(&vnode->netfs.inode); + if (i_size > PAGE_SIZE - 1) { + trace_afs_file_error(vnode, -EFBIG, afs_file_error_dir_big); + return -EFBIG; + } + + if (!vnode->directory) { + size_t cur_size = 0; + + ret = netfs_alloc_folioq_buffer(NULL, + &vnode->directory, &cur_size, PAGE_SIZE, + mapping_gfp_mask(vnode->netfs.inode.i_mapping)); + vnode->directory_size = PAGE_SIZE - 1; + if (ret < 0) + return ret; + } + + iov_iter_folio_queue(&iter, ITER_DEST, vnode->directory, 0, 0, PAGE_SIZE); + + /* AFS requires us to perform the read of a symlink as a single unit to + * avoid issues with the content being changed between reads. + */ + ret = netfs_read_single(&vnode->netfs.inode, NULL, &iter); + if (ret >= 0) { + i_size = ret; + if (i_size > PAGE_SIZE - 1) { + trace_afs_file_error(vnode, -EFBIG, afs_file_error_dir_big); + return -EFBIG; + } + vnode->directory_size = i_size; + + /* Copy the symlink. */ + symlink = kmalloc_flex(struct afs_symlink, content, i_size + 1, + GFP_KERNEL); + if (!symlink) + return -ENOMEM; + + refcount_set(&symlink->ref, 1); + symlink->content[i_size] = 0; + + const char *s = kmap_local_folio(folioq_folio(vnode->directory, 0), 0); + + memcpy(symlink->content, s, i_size); + kunmap_local(s); + + afs_replace_symlink(vnode, symlink); + } + + if (!fscache_cookie_enabled(netfs_i_cookie(&vnode->netfs))) { + netfs_free_folioq_buffer(vnode->directory); + vnode->directory = NULL; + vnode->directory_size = 0; + } + + return ret; +} + +static ssize_t afs_read_symlink(struct afs_vnode *vnode) +{ + ssize_t ret; + + fscache_use_cookie(afs_vnode_cache(vnode), false); + ret = afs_do_read_symlink(vnode); + fscache_unuse_cookie(afs_vnode_cache(vnode), NULL, NULL); + return ret; +} + +static void afs_put_link(void *arg) +{ + afs_put_symlink(arg); +} + +const char *afs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *callback) +{ + struct afs_symlink *symlink; + struct afs_vnode *vnode = AFS_FS_I(inode); + ssize_t ret; + + if (!dentry) { + /* RCU pathwalk. */ + symlink = rcu_dereference(vnode->symlink); + if (!symlink || !afs_check_validity(vnode)) + return ERR_PTR(-ECHILD); + set_delayed_call(callback, NULL, NULL); + return symlink->content; + } + + if (vnode->symlink) { + ret = afs_validate(vnode, NULL); + if (ret < 0) + return ERR_PTR(ret); + + down_read(&vnode->validate_lock); + if (vnode->symlink) + goto good; + up_read(&vnode->validate_lock); + } + + if (down_write_killable(&vnode->validate_lock) < 0) + return ERR_PTR(-ERESTARTSYS); + if (!vnode->symlink) { + ret = afs_read_symlink(vnode); + if (ret < 0) { + up_write(&vnode->validate_lock); + return ERR_PTR(ret); + } + } + + downgrade_write(&vnode->validate_lock); + +good: + symlink = rcu_dereference_protected(vnode->symlink, + lockdep_is_held(&vnode->validate_lock)); + refcount_inc(&symlink->ref); + up_read(&vnode->validate_lock); + + set_delayed_call(callback, afs_put_link, symlink); + return symlink->content; +} + +int afs_readlink(struct dentry *dentry, char __user *buffer, int buflen) +{ + DEFINE_DELAYED_CALL(done); + const char *content; + int len; + + content = afs_get_link(dentry, d_inode(dentry), &done); + if (IS_ERR(content)) { + do_delayed_call(&done); + return PTR_ERR(content); + } + + len = umin(strlen(content), buflen); + if (copy_to_user(buffer, content, len)) + len = -EFAULT; + do_delayed_call(&done); + return len; +} + +/* + * Write the symlink contents to the cache as a single blob. We then throw + * away the page we used to receive it. + */ +int afs_symlink_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct afs_vnode *vnode = AFS_FS_I(mapping->host); + struct iov_iter iter; + int ret = 0; + + if (!down_read_trylock(&vnode->validate_lock)) { + if (wbc->sync_mode == WB_SYNC_NONE) { + /* The VFS will have undirtied the inode. */ + netfs_single_mark_inode_dirty(&vnode->netfs.inode); + return 0; + } + down_read(&vnode->validate_lock); + } + + if (vnode->directory && + atomic64_read(&vnode->cb_expires_at) != AFS_NO_CB_PROMISE) { + iov_iter_folio_queue(&iter, ITER_SOURCE, vnode->directory, 0, 0, + i_size_read(&vnode->netfs.inode)); + ret = netfs_writeback_single(mapping, wbc, &iter); + } + + if (ret == 0) { + mutex_lock(&vnode->netfs.wb_lock); + netfs_free_folioq_buffer(vnode->directory); + vnode->directory = NULL; + vnode->directory_size = 0; + mutex_unlock(&vnode->netfs.wb_lock); + } else if (ret == 1) { + ret = 0; /* Skipped write due to lock conflict. */ + } + + up_read(&vnode->validate_lock); + return ret; +} + +const struct inode_operations afs_symlink_inode_operations = { + .get_link = afs_get_link, + .readlink = afs_readlink, +}; + +const struct address_space_operations afs_symlink_aops = { + .writepages = afs_symlink_writepages, +}; diff --git a/fs/afs/validation.c b/fs/afs/validation.c index 0ba8336c9025..e997563af658 100644 --- a/fs/afs/validation.c +++ b/fs/afs/validation.c @@ -465,11 +465,17 @@ int afs_validate(struct afs_vnode *vnode, struct key *key) vnode->cb_ro_snapshot = cb_ro_snapshot; vnode->cb_scrub = cb_scrub; - /* if the vnode's data version number changed then its contents are - * different */ + /* If the vnode's data version number changed then its contents are + * different. Note that afs_apply_status() doesn't set ZAP_DATA on + * directories. + */ zap |= test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags); - if (zap) - afs_zap_data(vnode); + if (zap) { + if (S_ISREG(vnode->netfs.inode.i_mode)) + afs_zap_data(vnode); + else if (S_ISLNK(vnode->netfs.inode.i_mode)) + afs_invalidate_symlink(vnode); + } up_write(&vnode->validate_lock); _leave(" = 0"); return 0; diff --git a/fs/afs/write.c b/fs/afs/write.c index fcfed9d24e0a..7f34b939706a 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -142,7 +142,7 @@ static void afs_issue_write_worker(struct work_struct *work) afs_begin_vnode_operation(op); op->store.write_iter = &subreq->io_iter; - op->store.i_size = umax(pos + len, vnode->netfs.remote_i_size); + op->store.i_size = umax(pos + len, netfs_read_remote_i_size(&vnode->netfs.inode)); op->mtime = inode_get_mtime(&vnode->netfs.inode); afs_wait_for_operation(op); diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c index 24fb562ebd33..d941179730a9 100644 --- a/fs/afs/yfsclient.c +++ b/fs/afs/yfsclient.c @@ -960,7 +960,7 @@ void yfs_fs_symlink(struct afs_operation *op) _enter(""); - contents_sz = strlen(op->create.symlink); + contents_sz = strlen(op->create.symlink->content); call = afs_alloc_flat_call(op->net, &yfs_RXYFSSymlink, sizeof(__be32) + sizeof(struct yfs_xdr_RPCFlags) + @@ -981,7 +981,7 @@ void yfs_fs_symlink(struct afs_operation *op) bp = xdr_encode_u32(bp, 0); /* RPC flags */ bp = xdr_encode_YFSFid(bp, &dvp->fid); bp = xdr_encode_name(bp, name); - bp = xdr_encode_string(bp, op->create.symlink, contents_sz); + bp = xdr_encode_string(bp, op->create.symlink->content, contents_sz); bp = xdr_encode_YFSStoreStatus(bp, &mode, &op->mtime); yfs_check_req(call, bp); diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index 1b83ed0e0a63..2937db690b40 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -130,6 +130,8 @@ struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache, ret = cachefiles_inject_write_error(); if (ret == 0) { subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700, NULL); + if (IS_ERR(subdir)) + ret = PTR_ERR(subdir); } else { end_creating(subdir); subdir = ERR_PTR(ret); diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 41e311019a25..df7ea019526d 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -89,13 +89,11 @@ static int erofs_init_inode_xattrs(struct inode *inode) vi->xattr_isize - sizeof(struct erofs_xattr_ibody_header)) { erofs_err(sb, "invalid h_shared_count %u @ nid %llu", vi->xattr_shared_count, vi->nid); - erofs_put_metabuf(&buf); ret = -EFSCORRUPTED; goto out_unlock; } vi->xattr_shared_xattrs = kmalloc_objs(uint, vi->xattr_shared_count); if (!vi->xattr_shared_xattrs) { - erofs_put_metabuf(&buf); ret = -ENOMEM; goto out_unlock; } @@ -112,12 +110,12 @@ static int erofs_init_inode_xattrs(struct inode *inode) } vi->xattr_shared_xattrs[i] = le32_to_cpu(*xattr_id); } - erofs_put_metabuf(&buf); /* paired with smp_mb() at the beginning of the function. */ smp_mb(); set_bit(EROFS_I_EA_INITED_BIT, &vi->flags); out_unlock: + erofs_put_metabuf(&buf); clear_and_wake_up_bit(EROFS_I_BL_XATTR_BIT, &vi->flags); return ret; } diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 43bb5a6a9924..27ab7bd844ec 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1509,8 +1509,15 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec, DBG_BUGON(z_erofs_is_shortlived_page(bvec->bv_page)); folio = page_folio(zbv.page); - /* For preallocated managed folios, add them to page cache here */ + /* + * Preallocated folios are added to the managed cache here rather than + * in z_erofs_bind_cache() in order to keep these folios locked in + * increasing (physical) address order. + * Clear folio->private before these folios become visible to others in + * the managed cache to avoid duplicate additions for unaligned extents. + */ if (folio->private == Z_EROFS_PREALLOCATED_FOLIO) { + folio->private = NULL; tocache = true; goto out_tocache; } @@ -1546,14 +1553,8 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec, } return; } - /* - * Already linked with another pcluster, which only appears in - * crafted images by fuzzers for now. But handle this anyway. - */ - tocache = false; /* use temporary short-lived pages */ } else { DBG_BUGON(1); /* referenced managed folios can't be truncated */ - tocache = true; } folio_unlock(folio); folio_put(folio); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index c59452d60b8d..f94f3dc082c6 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2176,7 +2176,10 @@ static bool fuse_folios_need_send(struct fuse_conn *fc, loff_t pos, WARN_ON(!ap->num_folios); - /* Reached max pages */ + /* Reached max pages or max folio slots */ + if (ap->num_folios >= fc->max_pages) + return true; + if (DIV_ROUND_UP(bytes, PAGE_SIZE) > fc->max_pages) return true; diff --git a/fs/inode.c b/fs/inode.c index 6a3cbc7dcd28..62c579a0cf7d 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -2124,7 +2124,13 @@ static int inode_update_cmtime(struct inode *inode, unsigned int flags) inode_iversion_need_inc(inode)) return -EAGAIN; } else { - if (inode_maybe_inc_iversion(inode, !!dirty)) + /* + * Don't force iversion increment for pure lazytime + * updates (I_DIRTY_TIME only), let I_VERSION_QUERIED + * dictate whether the increment is needed. + */ + if (inode_maybe_inc_iversion(inode, + dirty != I_DIRTY_TIME)) dirty |= I_DIRTY_SYNC; } } diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c index 60c4a0e0fca5..442d62679262 100644 --- a/fs/jfs/namei.c +++ b/fs/jfs/namei.c @@ -309,7 +309,7 @@ static struct dentry *jfs_mkdir(struct mnt_idmap *idmap, struct inode *dip, out1: jfs_info("jfs_mkdir: rc:%d", rc); - return ERR_PTR(rc); + return rc ? ERR_PTR(rc) : NULL; } /* diff --git a/fs/mnt_idmapping.c b/fs/mnt_idmapping.c index 6472c4ea3d1e..cb61fbdb52e9 100644 --- a/fs/mnt_idmapping.c +++ b/fs/mnt_idmapping.c @@ -375,6 +375,8 @@ int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_ continue; seq_printf(seq, "%u %u %u", extent->first, lower, extent->count); + if (seq_has_overflowed(seq)) + return -EAGAIN; seq->count++; /* mappings are separated by \0 */ if (seq_has_overflowed(seq)) diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c index a8c0d86118c5..76d0f6a29aba 100644 --- a/fs/netfs/buffered_read.c +++ b/fs/netfs/buffered_read.c @@ -156,9 +156,8 @@ static void netfs_read_cache_to_pagecache(struct netfs_io_request *rreq, netfs_cache_read_terminated, subreq); } -static void netfs_queue_read(struct netfs_io_request *rreq, - struct netfs_io_subrequest *subreq, - bool last_subreq) +void netfs_queue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq) { struct netfs_io_stream *stream = &rreq->io_streams[0]; @@ -169,7 +168,8 @@ static void netfs_queue_read(struct netfs_io_request *rreq, * remove entries off of the front. */ spin_lock(&rreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); + /* Write IN_PROGRESS before pointer to new subreq */ + list_add_tail_release(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { if (!stream->active) { stream->collected_to = subreq->start; @@ -178,11 +178,6 @@ static void netfs_queue_read(struct netfs_io_request *rreq, } } - if (last_subreq) { - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); - } - spin_unlock(&rreq->lock); } @@ -214,7 +209,6 @@ static void netfs_issue_read(struct netfs_io_request *rreq, static void netfs_read_to_pagecache(struct netfs_io_request *rreq, struct readahead_control *ractl) { - struct netfs_inode *ictx = netfs_inode(rreq->inode); unsigned long long start = rreq->start; ssize_t size = rreq->len; int ret = 0; @@ -233,10 +227,13 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, subreq->start = start; subreq->len = size; + netfs_queue_read(rreq, subreq); + source = netfs_cache_prepare_read(rreq, subreq, rreq->i_size); subreq->source = source; if (source == NETFS_DOWNLOAD_FROM_SERVER) { - unsigned long long zp = umin(ictx->zero_point, rreq->i_size); + unsigned long long zero_point = netfs_read_zero_point(rreq->inode); + unsigned long long zp = umin(zero_point, rreq->i_size); size_t len = subreq->len; if (unlikely(rreq->origin == NETFS_READ_SINGLE)) @@ -252,7 +249,8 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, pr_err("ZERO-LEN READ: R=%08x[%x] l=%zx/%zx s=%llx z=%llx i=%llx", rreq->debug_id, subreq->debug_index, subreq->len, size, - subreq->start, ictx->zero_point, rreq->i_size); + subreq->start, zero_point, rreq->i_size); + netfs_cancel_read(subreq, ret); break; } subreq->len = len; @@ -261,12 +259,7 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - subreq->error = ret; - /* Not queued - release both refs. */ - netfs_put_subrequest(subreq, - netfs_sreq_trace_put_cancel); - netfs_put_subrequest(subreq, - netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); break; } trace_netfs_sreq(subreq, netfs_sreq_trace_prepare); @@ -289,24 +282,29 @@ static void netfs_read_to_pagecache(struct netfs_io_request *rreq, pr_err("Unexpected read source %u\n", source); WARN_ON_ONCE(1); + netfs_cancel_read(subreq, ret); break; issue: slice = netfs_prepare_read_iterator(subreq, ractl); if (slice < 0) { ret = slice; - subreq->error = ret; - trace_netfs_sreq(subreq, netfs_sreq_trace_cancel); - /* Not queued - release both refs. */ - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); break; } - size -= slice; start += slice; + size -= slice; + if (size <= 0) { + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + } - netfs_queue_read(rreq, subreq, size <= 0); netfs_issue_read(rreq, subreq); + + if (test_bit(NETFS_RREQ_PAUSE, &rreq->flags)) + netfs_wait_for_paused_read(rreq); + if (test_bit(NETFS_RREQ_FAILED, &rreq->flags)) + break; cond_resched(); } while (size > 0); @@ -397,6 +395,7 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) { struct netfs_io_request *rreq; struct address_space *mapping = folio->mapping; + struct netfs_group *group = netfs_folio_group(folio); struct netfs_folio *finfo = netfs_folio_info(folio); struct netfs_inode *ctx = netfs_inode(mapping->host); struct folio *sink = NULL; @@ -458,14 +457,20 @@ static int netfs_read_gaps(struct file *file, struct folio *folio) netfs_read_to_pagecache(rreq, NULL); - if (sink) - folio_put(sink); - ret = netfs_wait_for_read(rreq); if (ret >= 0) { + if (group) + folio_change_private(folio, group); + else + folio_detach_private(folio); + kfree(finfo); + trace_netfs_folio(folio, netfs_folio_trace_filled_gaps); flush_dcache_folio(folio); folio_mark_uptodate(folio); } + + if (sink) + folio_put(sink); folio_unlock(folio); netfs_put_request(rreq, netfs_rreq_trace_put_return); return ret < 0 ? ret : 0; @@ -498,10 +503,10 @@ int netfs_read_folio(struct file *file, struct folio *folio) struct netfs_inode *ctx = netfs_inode(mapping->host); int ret; - if (folio_test_dirty(folio)) { - trace_netfs_folio(folio, netfs_folio_trace_read_gaps); + folio_wait_writeback(folio); + + if (folio_test_dirty(folio)) return netfs_read_gaps(file, folio); - } _enter("%lx", folio->index); @@ -667,7 +672,7 @@ int netfs_write_begin(struct netfs_inode *ctx, ret = PTR_ERR(rreq); goto error; } - rreq->no_unlock_folio = folio->index; + rreq->no_unlock_folio = folio; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); @@ -684,9 +689,9 @@ int netfs_write_begin(struct netfs_inode *ctx, netfs_read_to_pagecache(rreq, NULL); ret = netfs_wait_for_read(rreq); + netfs_put_request(rreq, netfs_rreq_trace_put_return); if (ret < 0) goto error; - netfs_put_request(rreq, netfs_rreq_trace_put_return); have_folio: ret = folio_wait_private_2_killable(folio); @@ -733,7 +738,7 @@ int netfs_prefetch_for_write(struct file *file, struct folio *folio, goto error; } - rreq->no_unlock_folio = folio->index; + rreq->no_unlock_folio = folio; __set_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags); ret = netfs_begin_cache_read(rreq, ctx); if (ret == -ENOMEM || ret == -EINTR || ret == -ERESTARTSYS) diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index 05ea5b0cc0e8..6bde3320bcec 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -12,24 +12,6 @@ #include #include "internal.h" -static void __netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) -{ - if (netfs_group) - folio_attach_private(folio, netfs_get_group(netfs_group)); -} - -static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group) -{ - void *priv = folio_get_private(folio); - - if (unlikely(priv != netfs_group)) { - if (netfs_group && (!priv || priv == NETFS_FOLIO_COPY_TO_CACHE)) - folio_attach_private(folio, netfs_get_group(netfs_group)); - else if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) - folio_detach_private(folio); - } -} - /* * Grab a folio for writing and lock it. Attempt to allocate as large a folio * as possible to hold as much of the remaining length as possible in one go. @@ -149,6 +131,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, } do { + enum netfs_folio_trace trace; struct netfs_folio *finfo; struct netfs_group *group; unsigned long long fpos; @@ -156,6 +139,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, size_t offset; /* Offset into pagecache folio */ size_t part; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ + void *priv; offset = pos & (max_chunk - 1); part = min(max_chunk - offset, iov_iter_count(iter)); @@ -201,73 +185,99 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto error_folio_unlock; } - /* Decide how we should modify a folio. We might be attempting - * to do write-streaming, in which case we don't want to a - * local RMW cycle if we can avoid it. If we're doing local - * caching or content crypto, we award that priority over - * avoiding RMW. If the file is open readably, then we also - * assume that we may want to read what we wrote. - */ finfo = netfs_folio_info(folio); group = netfs_folio_group(folio); + /* If the requested group differs from the group set on the + * page, then we need to flush out the folio if it has a group + * set (ie. is non-NULL). Note that COPY_TO_CACHE is a special + * case, being a netfs annotation rather than an actual group. + * + * The filesystem isn't permitted to mix writes with groups and + * writes without groups as the NULL group is used to indicate + * that no group is set. + */ if (unlikely(group != netfs_group) && - group != NETFS_FOLIO_COPY_TO_CACHE) + group != NETFS_FOLIO_COPY_TO_CACHE && + group) { + WARN_ON_ONCE(!netfs_group); goto flush_content; + } + /* Decide how we should modify a folio. We might be attempting + * to do write-streaming, as we don't want to a local RMW cycle + * if we can avoid it. If we're doing local caching or content + * crypto, we award that priority over avoiding RMW. If the + * file is open readably, then we let ->read_folio() fill in + * the gaps. + */ if (folio_test_uptodate(folio)) { if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, part, iter); if (unlikely(copied == 0)) goto copy_failed; - netfs_set_group(folio, netfs_group); - trace_netfs_folio(folio, netfs_folio_is_uptodate); - goto copied; + trace = netfs_folio_is_uptodate; + goto copied_uptodate; } /* If the page is above the zero-point then we assume that the * server would just return a block of zeros or a short read if * we try to read it. */ - if (fpos >= ctx->zero_point) { + if (fpos >= netfs_read_zero_point(inode)) { folio_zero_segment(folio, 0, offset); copied = copy_folio_from_iter_atomic(folio, offset, part, iter); if (unlikely(copied == 0)) goto copy_failed; folio_zero_segment(folio, offset + copied, flen); - __netfs_set_group(folio, netfs_group); - folio_mark_uptodate(folio); - trace_netfs_folio(folio, netfs_modify_and_clear); - goto copied; + if (finfo) + trace = netfs_modify_and_clear_rm_finfo; + else + trace = netfs_modify_and_clear; + goto mark_uptodate; } /* See if we can write a whole folio in one go. */ if (!maybe_trouble && offset == 0 && part >= flen) { copied = copy_folio_from_iter_atomic(folio, offset, part, iter); - if (unlikely(copied == 0)) + if (likely(copied == part)) { + if (finfo) + trace = netfs_whole_folio_modify_filled; + else + trace = netfs_whole_folio_modify; + goto mark_uptodate; + } + if (copied == 0) goto copy_failed; - if (unlikely(copied < part)) { + if (!finfo || copied <= finfo->dirty_offset) { maybe_trouble = true; iov_iter_revert(iter, copied); copied = 0; folio_unlock(folio); goto retry; } - __netfs_set_group(folio, netfs_group); - folio_mark_uptodate(folio); - trace_netfs_folio(folio, netfs_whole_folio_modify); + + /* We overwrote some existing dirty data, so we have to + * accept the partial write. + */ + finfo->dirty_len += finfo->dirty_offset; + if (finfo->dirty_len == flen) { + trace = netfs_whole_folio_modify_filled_efault; + goto mark_uptodate; + } + if (copied > finfo->dirty_len) + finfo->dirty_len = copied; + finfo->dirty_offset = 0; + trace = netfs_whole_folio_modify_efault; goto copied; } /* We don't want to do a streaming write on a file that loses * caching service temporarily because the backing store got - * culled and we don't really want to get a streaming write on - * a file that's open for reading as ->read_folio() then has to - * be able to flush it. + * culled. */ - if ((file->f_mode & FMODE_READ) || - netfs_is_cache_enabled(ctx)) { + if (netfs_is_cache_enabled(ctx)) { if (finfo) { netfs_stat(&netfs_n_wh_wstream_conflict); goto flush_content; @@ -282,11 +292,11 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, copied = copy_folio_from_iter_atomic(folio, offset, part, iter); if (unlikely(copied == 0)) goto copy_failed; - netfs_set_group(folio, netfs_group); - trace_netfs_folio(folio, netfs_just_prefetch); - goto copied; + trace = netfs_just_prefetch; + goto copied_uptodate; } + /* Do a streaming write on a folio that has nothing in it yet. */ if (!finfo) { ret = -EIO; if (WARN_ON(folio_get_private(folio))) @@ -295,10 +305,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, if (unlikely(copied == 0)) goto copy_failed; if (offset == 0 && copied == flen) { - __netfs_set_group(folio, netfs_group); - folio_mark_uptodate(folio); - trace_netfs_folio(folio, netfs_streaming_filled_page); - goto copied; + trace = netfs_streaming_filled_page; + goto mark_uptodate; } finfo = kzalloc_obj(*finfo); @@ -312,7 +320,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, finfo->dirty_len = copied; folio_attach_private(folio, (void *)((unsigned long)finfo | NETFS_FOLIO_INFO)); - trace_netfs_folio(folio, netfs_streaming_write); + trace = netfs_streaming_write; goto copied; } @@ -326,16 +334,10 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto copy_failed; finfo->dirty_len += copied; if (finfo->dirty_offset == 0 && finfo->dirty_len == flen) { - if (finfo->netfs_group) - folio_change_private(folio, finfo->netfs_group); - else - folio_detach_private(folio); - folio_mark_uptodate(folio); - kfree(finfo); - trace_netfs_folio(folio, netfs_streaming_cont_filled_page); - } else { - trace_netfs_folio(folio, netfs_streaming_write_cont); + trace = netfs_streaming_cont_filled_page; + goto mark_uptodate; } + trace = netfs_streaming_write_cont; goto copied; } @@ -349,7 +351,38 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter, goto out; continue; + /* Mark a folio as being up to data when we've filled it + * completely. If the folio has a group attached, then it must + * be the same group, otherwise we should have flushed it out + * above. We have to get rid of the netfs_folio struct if + * there was one. + */ + mark_uptodate: + folio_mark_uptodate(folio); + + copied_uptodate: + priv = folio_get_private(folio); + if (likely(priv == netfs_group)) { + /* Already set correctly; no change required. */ + } else if (priv == NETFS_FOLIO_COPY_TO_CACHE) { + if (!netfs_group) + folio_detach_private(folio); + else + folio_change_private(folio, netfs_get_group(netfs_group)); + } else if (!priv) { + folio_attach_private(folio, netfs_get_group(netfs_group)); + } else { + WARN_ON_ONCE(!finfo); + if (netfs_group) + /* finfo->netfs_group has a ref */ + folio_change_private(folio, netfs_group); + else + folio_detach_private(folio); + kfree(finfo); + } + copied: + trace_netfs_folio(folio, trace); flush_dcache_folio(folio); /* Update the inode size if we moved the EOF marker */ @@ -510,6 +543,7 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr struct inode *inode = file_inode(file); struct netfs_inode *ictx = netfs_inode(inode); vm_fault_t ret = VM_FAULT_NOPAGE; + void *priv; int err; _enter("%lx", folio->index); @@ -530,7 +564,9 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr } group = netfs_folio_group(folio); - if (group != netfs_group && group != NETFS_FOLIO_COPY_TO_CACHE) { + if (group && + group != netfs_group && + group != NETFS_FOLIO_COPY_TO_CACHE) { folio_unlock(folio); err = filemap_fdatawrite_range(mapping, folio_pos(folio), @@ -552,7 +588,19 @@ vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_gr trace_netfs_folio(folio, netfs_folio_trace_mkwrite_plus); else trace_netfs_folio(folio, netfs_folio_trace_mkwrite); - netfs_set_group(folio, netfs_group); + + priv = folio_get_private(folio); + if (priv != netfs_group) { + if (!netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) + folio_detach_private(folio); + else if (netfs_group && priv == NETFS_FOLIO_COPY_TO_CACHE) + folio_change_private(folio, netfs_get_group(netfs_group)); + else if (netfs_group && !priv) + folio_attach_private(folio, netfs_get_group(netfs_group)); + else + WARN_ON_ONCE(1); + } + file_update_time(file); set_bit(NETFS_ICTX_MODIFIED_ATTR, &ictx->flags); if (ictx->ops->post_modify) diff --git a/fs/netfs/direct_read.c b/fs/netfs/direct_read.c index f72e6da88cca..6a8fb0d55e04 100644 --- a/fs/netfs/direct_read.c +++ b/fs/netfs/direct_read.c @@ -45,12 +45,11 @@ static void netfs_prepare_dio_read_iterator(struct netfs_io_subrequest *subreq) * Perform a read to a buffer from the server, slicing up the region to be read * according to the network rsize. */ -static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) +static void netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) { - struct netfs_io_stream *stream = &rreq->io_streams[0]; unsigned long long start = rreq->start; ssize_t size = rreq->len; - int ret = 0; + int ret; do { struct netfs_io_subrequest *subreq; @@ -58,7 +57,10 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) subreq = netfs_alloc_subrequest(rreq); if (!subreq) { - ret = -ENOMEM; + /* Stash the error in the request if there's not + * already an error set. + */ + cmpxchg(&rreq->error, 0, -ENOMEM); break; } @@ -66,25 +68,13 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) subreq->start = start; subreq->len = size; - __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - - spin_lock(&rreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); - if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { - if (!stream->active) { - stream->collected_to = subreq->start; - /* Store list pointers before active flag */ - smp_store_release(&stream->active, true); - } - } - trace_netfs_sreq(subreq, netfs_sreq_trace_added); - spin_unlock(&rreq->lock); + netfs_queue_read(rreq, subreq); netfs_stat(&netfs_n_rh_download); if (rreq->netfs_ops->prepare_read) { ret = rreq->netfs_ops->prepare_read(subreq); if (ret < 0) { - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); break; } } @@ -113,8 +103,6 @@ static int netfs_dispatch_unbuffered_reads(struct netfs_io_request *rreq) set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); netfs_wake_collector(rreq); } - - return ret; } /* @@ -137,21 +125,17 @@ static ssize_t netfs_unbuffered_read(struct netfs_io_request *rreq, bool sync) // TODO: Use bounce buffer if requested inode_dio_begin(rreq->inode); + netfs_dispatch_unbuffered_reads(rreq); - ret = netfs_dispatch_unbuffered_reads(rreq); - - if (!rreq->submitted) { - netfs_put_request(rreq, netfs_rreq_trace_put_no_submit); - inode_dio_end(rreq->inode); - ret = 0; - goto out; - } + /* The collector will get run, even if we don't manage to submit any + * subreqs, so we shouldn't call inode_dio_end() here. + */ if (sync) ret = netfs_wait_for_read(rreq); else ret = -EIOCBQUEUED; -out: + _leave(" = %zd", ret); return ret; } diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index f9ab69de3e29..25f8ceb15fad 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -376,8 +376,10 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ret < 0) goto out; end = iocb->ki_pos + iov_iter_count(from); - if (end > ictx->zero_point) - ictx->zero_point = end; + spin_lock(&inode->i_lock); + if (end > ictx->_zero_point) + netfs_write_zero_point(inode, end); + spin_unlock(&inode->i_lock); fscache_invalidate(netfs_i_cookie(ictx), NULL, i_size_read(inode), FSCACHE_INVAL_DIO_WRITE); diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h index d436e20d3418..645996ecfc80 100644 --- a/fs/netfs/internal.h +++ b/fs/netfs/internal.h @@ -23,6 +23,8 @@ /* * buffered_read.c */ +void netfs_queue_read(struct netfs_io_request *rreq, + struct netfs_io_subrequest *subreq); void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error); int netfs_prefetch_for_write(struct file *file, struct folio *folio, size_t offset, size_t len); @@ -108,6 +110,7 @@ static inline void netfs_see_subrequest(struct netfs_io_subrequest *subreq, */ bool netfs_read_collection(struct netfs_io_request *rreq); void netfs_read_collection_worker(struct work_struct *work); +void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error); void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error); /* diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index 154a14bb2d7f..b375567e0520 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -22,7 +22,7 @@ * * Extract the page fragments from the given amount of the source iterator and * build up a second iterator that refers to all of those bits. This allows - * the original iterator to disposed of. + * the original iterator to be disposed of. * * @extraction_flags can have ITER_ALLOW_P2PDMA set to request peer-to-peer DMA be * allowed on the pages extracted. @@ -43,7 +43,7 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, unsigned int max_pages; unsigned int npages = 0; unsigned int i; - ssize_t ret; + ssize_t ret = 0; size_t count = orig_len, offset, len; size_t bv_size, pg_size; @@ -67,25 +67,28 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, ret = iov_iter_extract_pages(orig, &pages, count, max_pages - npages, extraction_flags, &offset); - if (ret < 0) { - pr_err("Couldn't get user pages (rc=%zd)\n", ret); + if (unlikely(ret <= 0)) { + ret = ret ?: -EIO; break; } - if (ret > count) { - pr_err("get_pages rc=%zd more than %zu\n", ret, count); + if (WARN(ret > count, + "%s: extract_pages overrun %zd > %zu bytes\n", + __func__, ret, count)) { + ret = -EIO; + break; + } + + cur_npages = DIV_ROUND_UP(offset + ret, PAGE_SIZE); + if (WARN(cur_npages > max_pages - npages, + "%s: extract_pages overrun %u > %u pages\n", + __func__, npages + cur_npages, max_pages)) { + ret = -EIO; break; } count -= ret; ret += offset; - cur_npages = DIV_ROUND_UP(ret, PAGE_SIZE); - - if (npages + cur_npages > max_pages) { - pr_err("Out of bvec array capacity (%u vs %u)\n", - npages + cur_npages, max_pages); - break; - } for (i = 0; i < cur_npages; i++) { len = ret > PAGE_SIZE ? PAGE_SIZE : ret; @@ -97,6 +100,18 @@ ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len, npages += cur_npages; } + /* Note: Don't try to clean up after EIO. Either we got no pages, so + * nothing to clean up, or we got a buffer overrun, memory corruption + * and can't trust the stuff in the buffer (a WARN was emitted). + */ + + if (ret < 0 && (ret == -ENOMEM || npages == 0)) { + for (i = 0; i < npages; i++) + unpin_user_page(bv[i].bv_page); + kvfree(bv); + return ret; + } + iov_iter_bvec(new, orig->data_source, bv, npages, orig_len - count); return npages; } diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c index 6df89c92b10b..5d554512ed23 100644 --- a/fs/netfs/misc.c +++ b/fs/netfs/misc.c @@ -211,18 +211,25 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback); void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct netfs_folio *finfo; - struct netfs_inode *ctx = netfs_inode(folio_inode(folio)); + struct inode *inode = folio_inode(folio); + struct netfs_inode *ctx = netfs_inode(inode); size_t flen = folio_size(folio); _enter("{%lx},%zx,%zx", folio->index, offset, length); if (offset == 0 && length == flen) { - unsigned long long i_size = i_size_read(&ctx->inode); + unsigned long long i_size, remote_i_size, zero_point; unsigned long long fpos = folio_pos(folio), end; + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); end = umin(fpos + flen, i_size); - if (fpos < i_size && end > ctx->zero_point) - ctx->zero_point = end; + if (fpos < i_size && end > zero_point) { + spin_lock(&inode->i_lock); + end = umin(fpos + flen, inode->i_size); + if (fpos < i_size && end > ctx->_zero_point) + netfs_write_zero_point(inode, end); + spin_unlock(&inode->i_lock); + } } folio_wait_private_2(folio); /* [DEPRECATED] */ @@ -255,7 +262,8 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) goto erase_completely; /* Move the start of the data. */ finfo->dirty_len = fend - iend; - finfo->dirty_offset = offset; + finfo->dirty_offset = iend; + trace_netfs_folio(folio, netfs_folio_trace_invalidate_front); return; } @@ -264,12 +272,14 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) */ if (iend >= fend) { finfo->dirty_len = offset - fstart; + trace_netfs_folio(folio, netfs_folio_trace_invalidate_tail); return; } /* A partial write was split. The caller has already zeroed * it, so just absorb the hole. */ + trace_netfs_folio(folio, netfs_folio_trace_invalidate_middle); } return; @@ -277,8 +287,9 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length) netfs_put_group(netfs_folio_group(folio)); folio_detach_private(folio); folio_clear_uptodate(folio); + folio_cancel_dirty(folio); kfree(finfo); - return; + trace_netfs_folio(folio, netfs_folio_trace_invalidate_all); } EXPORT_SYMBOL(netfs_invalidate_folio); @@ -292,15 +303,22 @@ EXPORT_SYMBOL(netfs_invalidate_folio); */ bool netfs_release_folio(struct folio *folio, gfp_t gfp) { - struct netfs_inode *ctx = netfs_inode(folio_inode(folio)); - unsigned long long end; + struct inode *inode = folio_inode(folio); + struct netfs_inode *ctx = netfs_inode(inode); + unsigned long long i_size, remote_i_size, zero_point, end; if (folio_test_dirty(folio)) return false; - end = umin(folio_next_pos(folio), i_size_read(&ctx->inode)); - if (end > ctx->zero_point) - ctx->zero_point = end; + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); + end = folio_next_pos(folio); + if (end > zero_point) { + spin_lock(&inode->i_lock); + end = umin(end, ctx->_remote_i_size); + if (end > ctx->_zero_point) + netfs_write_zero_point(inode, end); + spin_unlock(&inode->i_lock); + } if (folio_test_private(folio)) return false; @@ -356,6 +374,7 @@ void netfs_wait_for_in_progress_stream(struct netfs_io_request *rreq, DEFINE_WAIT(myself); list_for_each_entry(subreq, &stream->subrequests, rreq_link) { + smp_rmb(); /* Read ->next before IN_PROGRESS. */ if (!netfs_check_subreq_in_progress(subreq)) continue; diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index e5f6665b3341..23660a590124 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -83,7 +83,7 @@ static void netfs_unlock_read_folio(struct netfs_io_request *rreq, } just_unlock: - if (folio->index == rreq->no_unlock_folio && + if (folio == rreq->no_unlock_folio && test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, &rreq->flags)) { _debug("no unlock"); } else { @@ -205,8 +205,10 @@ static void netfs_collect_read_results(struct netfs_io_request *rreq) * in progress. The issuer thread may be adding stuff to the tail * whilst we're doing this. */ - front = list_first_entry_or_null(&stream->subrequests, - struct netfs_io_subrequest, rreq_link); + front = list_first_entry_or_null_acquire(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + /* Read first subreq pointer before IN_PROGRESS flag. */ + while (front) { size_t transferred; @@ -575,6 +577,17 @@ void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq) } EXPORT_SYMBOL(netfs_read_subreq_terminated); +/* + * Cancel a read subrequest due to preparation failure. + */ +void netfs_cancel_read(struct netfs_io_subrequest *subreq, int error) +{ + trace_netfs_sreq(subreq, netfs_sreq_trace_cancel); + subreq->error = error; + __set_bit(NETFS_SREQ_FAILED, &subreq->flags); + netfs_read_subreq_terminated(subreq); +} + /* * Handle termination of a read from the cache. */ diff --git a/fs/netfs/read_retry.c b/fs/netfs/read_retry.c index cca9ac43c077..f59a70f3a086 100644 --- a/fs/netfs/read_retry.c +++ b/fs/netfs/read_retry.c @@ -175,7 +175,9 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) list_for_each_entry_safe_from(subreq, tmp, &stream->subrequests, rreq_link) { trace_netfs_sreq(subreq, netfs_sreq_trace_superfluous); + spin_lock(&rreq->lock); list_del(&subreq->rreq_link); + spin_unlock(&rreq->lock); netfs_put_subrequest(subreq, netfs_sreq_trace_put_done); if (subreq == to) break; @@ -203,8 +205,10 @@ static void netfs_retry_read_subrequests(struct netfs_io_request *rreq) refcount_read(&subreq->ref), netfs_sreq_trace_new); + spin_lock(&rreq->lock); list_add(&subreq->rreq_link, &to->rreq_link); - to = list_next_entry(to, rreq_link); + spin_unlock(&rreq->lock); + to = subreq; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); stream->sreq_max_len = umin(len, rreq->rsize); @@ -288,8 +292,15 @@ void netfs_unlock_abandoned_read_pages(struct netfs_io_request *rreq) struct folio *folio = folioq_folio(p, slot); if (folio && !folioq_is_marked2(p, slot)) { - trace_netfs_folio(folio, netfs_folio_trace_abandon); - folio_unlock(folio); + if (folio == rreq->no_unlock_folio && + test_bit(NETFS_RREQ_NO_UNLOCK_FOLIO, + &rreq->flags)) { + _debug("no unlock"); + } else { + trace_netfs_folio(folio, + netfs_folio_trace_abandon); + folio_unlock(folio); + } } } } diff --git a/fs/netfs/read_single.c b/fs/netfs/read_single.c index d0e23bc42445..8833550d2eb6 100644 --- a/fs/netfs/read_single.c +++ b/fs/netfs/read_single.c @@ -89,7 +89,6 @@ static void netfs_single_read_cache(struct netfs_io_request *rreq, */ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) { - struct netfs_io_stream *stream = &rreq->io_streams[0]; struct netfs_io_subrequest *subreq; int ret = 0; @@ -102,14 +101,7 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) subreq->len = rreq->len; subreq->io_iter = rreq->buffer.iter; - __set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags); - - spin_lock(&rreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); - trace_netfs_sreq(subreq, netfs_sreq_trace_added); - /* Store list pointers before active flag */ - smp_store_release(&stream->active, true); - spin_unlock(&rreq->lock); + netfs_queue_read(rreq, subreq); netfs_single_cache_prepare_read(rreq, subreq); switch (subreq->source) { @@ -121,10 +113,14 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) goto cancel; } + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); rreq->netfs_ops->issue_read(subreq); rreq->submitted += subreq->len; break; case NETFS_READ_FROM_CACHE: + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); trace_netfs_sreq(subreq, netfs_sreq_trace_submit); netfs_single_read_cache(rreq, subreq); rreq->submitted += subreq->len; @@ -134,14 +130,15 @@ static int netfs_single_dispatch_read(struct netfs_io_request *rreq) pr_warn("Unexpected single-read source %u\n", subreq->source); WARN_ON_ONCE(true); ret = -EIO; - break; + goto cancel; } - smp_wmb(); /* Write lists before ALL_QUEUED. */ - set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); return ret; cancel: - netfs_put_subrequest(subreq, netfs_sreq_trace_put_cancel); + netfs_cancel_read(subreq, ret); + smp_wmb(); /* Write lists before ALL_QUEUED. */ + set_bit(NETFS_RREQ_ALL_QUEUED, &rreq->flags); + netfs_wake_collector(rreq); return ret; } diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c index b194447f4b11..24fc2bb2f8a4 100644 --- a/fs/netfs/write_collect.c +++ b/fs/netfs/write_collect.c @@ -57,7 +57,8 @@ static void netfs_dump_request(const struct netfs_io_request *rreq) int netfs_folio_written_back(struct folio *folio) { enum netfs_folio_trace why = netfs_folio_trace_clear; - struct netfs_inode *ictx = netfs_inode(folio->mapping->host); + struct inode *inode = folio_inode(folio); + struct netfs_inode *ictx = netfs_inode(inode); struct netfs_folio *finfo; struct netfs_group *group = NULL; int gcount = 0; @@ -69,8 +70,10 @@ int netfs_folio_written_back(struct folio *folio) unsigned long long fend; fend = folio_pos(folio) + finfo->dirty_offset + finfo->dirty_len; - if (fend > ictx->zero_point) - ictx->zero_point = fend; + spin_lock(&ictx->inode.i_lock); + if (fend > ictx->_zero_point) + netfs_write_zero_point(inode, fend); + spin_unlock(&ictx->inode.i_lock); folio_detach_private(folio); group = finfo->netfs_group; @@ -228,8 +231,10 @@ static void netfs_collect_write_results(struct netfs_io_request *wreq) if (!smp_load_acquire(&stream->active)) continue; - front = list_first_entry_or_null(&stream->subrequests, - struct netfs_io_subrequest, rreq_link); + front = list_first_entry_or_null_acquire(&stream->subrequests, + struct netfs_io_subrequest, rreq_link); + /* Read first subreq pointer before IN_PROGRESS flag. */ + while (front) { trace_netfs_collect_sreq(wreq, front); //_debug("sreq [%x] %llx %zx/%zx", diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c index 2db688f94125..c03c7cc45e47 100644 --- a/fs/netfs/write_issue.c +++ b/fs/netfs/write_issue.c @@ -204,7 +204,8 @@ void netfs_prepare_write(struct netfs_io_request *wreq, * remove entries off of the front. */ spin_lock(&wreq->lock); - list_add_tail(&subreq->rreq_link, &stream->subrequests); + /* Write IN_PROGRESS before pointer to new subreq */ + list_add_tail_release(&subreq->rreq_link, &stream->subrequests); if (list_is_first(&subreq->rreq_link, &stream->subrequests)) { if (!stream->active) { stream->collected_to = subreq->start; @@ -413,12 +414,7 @@ static int netfs_write_folio(struct netfs_io_request *wreq, if (streamw) netfs_issue_write(wreq, cache); - /* Flip the page to the writeback state and unlock. If we're called - * from write-through, then the page has already been put into the wb - * state. - */ - if (wreq->origin == NETFS_WRITEBACK) - folio_start_writeback(folio); + folio_start_writeback(folio); folio_unlock(folio); if (fgroup == NETFS_FOLIO_COPY_TO_CACHE) { @@ -646,29 +642,41 @@ int netfs_advance_writethrough(struct netfs_io_request *wreq, struct writeback_c struct folio *folio, size_t copied, bool to_page_end, struct folio **writethrough_cache) { + int ret; + _enter("R=%x ic=%zu ws=%u cp=%zu tp=%u", wreq->debug_id, wreq->buffer.iter.count, wreq->wsize, copied, to_page_end); - if (!*writethrough_cache) { - if (folio_test_dirty(folio)) - /* Sigh. mmap. */ - folio_clear_dirty_for_io(folio); + /* The folio is locked. */ + if (*writethrough_cache != folio) { + if (*writethrough_cache) { + /* Did the folio get moved? */ + folio_put(*writethrough_cache); + *writethrough_cache = NULL; + } /* We can make multiple writes to the folio... */ - folio_start_writeback(folio); if (wreq->len == 0) trace_netfs_folio(folio, netfs_folio_trace_wthru); else trace_netfs_folio(folio, netfs_folio_trace_wthru_plus); *writethrough_cache = folio; + folio_get(folio); } wreq->len += copied; - if (!to_page_end) - return 0; + if (!to_page_end) { + folio_mark_dirty(folio); + folio_unlock(folio); + return 0; + } + + ret = netfs_write_folio(wreq, wbc, folio); + folio_put(*writethrough_cache); *writethrough_cache = NULL; - return netfs_write_folio(wreq, wbc, folio); + wreq->submitted = wreq->len; + return ret; } /* @@ -682,8 +690,12 @@ ssize_t netfs_end_writethrough(struct netfs_io_request *wreq, struct writeback_c _enter("R=%x", wreq->debug_id); - if (writethrough_cache) + if (writethrough_cache) { + folio_lock(writethrough_cache); netfs_write_folio(wreq, wbc, writethrough_cache); + folio_put(writethrough_cache); + wreq->submitted = wreq->len; + } netfs_end_issue_write(wreq); @@ -818,6 +830,9 @@ static int netfs_write_folio_single(struct netfs_io_request *wreq, * * Write a monolithic, non-pagecache object back to the server and/or * the cache. + * + * Return: 0 if successful; 1 if skipped due to lock conflict and WB_SYNC_NONE; + * or a negative error code. */ int netfs_writeback_single(struct address_space *mapping, struct writeback_control *wbc, @@ -834,8 +849,10 @@ int netfs_writeback_single(struct address_space *mapping, if (!mutex_trylock(&ictx->wb_lock)) { if (wbc->sync_mode == WB_SYNC_NONE) { + /* The VFS will have undirtied the inode. */ + netfs_single_mark_inode_dirty(&ictx->inode); netfs_stat(&netfs_n_wb_lock_skip); - return 0; + return 1; } netfs_stat(&netfs_n_wb_lock_wait); mutex_lock(&ictx->wb_lock); diff --git a/fs/netfs/write_retry.c b/fs/netfs/write_retry.c index 29489a23a220..32735abfa03f 100644 --- a/fs/netfs/write_retry.c +++ b/fs/netfs/write_retry.c @@ -130,7 +130,9 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, list_for_each_entry_safe_from(subreq, tmp, &stream->subrequests, rreq_link) { trace_netfs_sreq(subreq, netfs_sreq_trace_discard); + spin_lock(&wreq->lock); list_del(&subreq->rreq_link); + spin_unlock(&wreq->lock); netfs_put_subrequest(subreq, netfs_sreq_trace_put_done); if (subreq == to) break; @@ -153,8 +155,10 @@ static void netfs_retry_write_stream(struct netfs_io_request *wreq, netfs_sreq_trace_new); trace_netfs_sreq(subreq, netfs_sreq_trace_split); + spin_lock(&wreq->lock); list_add(&subreq->rreq_link, &to->rreq_link); - to = list_next_entry(to, rreq_link); + spin_unlock(&wreq->lock); + to = subreq; trace_netfs_sreq(subreq, netfs_sreq_trace_retry); stream->sreq_max_len = len; diff --git a/fs/nsfs.c b/fs/nsfs.c index 51e8c9430477..160018c4fb36 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -266,7 +266,7 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl, else tsk = find_task_by_pid_ns(arg, pid_ns); if (!tsk) - break; + return ret; switch (ioctl) { case NS_GET_PID_FROM_PIDNS: diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 97b660eaa00c..421c6cdcbb53 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -583,24 +583,13 @@ static u32 ntfs_resident_attr_min_value_length(const __le32 type) case AT_STANDARD_INFORMATION: return offsetof(struct standard_information, ver) + sizeof(((struct standard_information *)0)->ver.v1.reserved12); - case AT_ATTRIBUTE_LIST: - return offsetof(struct attr_list_entry, name); case AT_FILE_NAME: - return offsetof(struct file_name_attr, file_name); - case AT_OBJECT_ID: - return sizeof(struct guid); - case AT_SECURITY_DESCRIPTOR: - return sizeof(struct security_descriptor_relative); + return offsetof(struct file_name_attr, file_name) + + sizeof(__le16) * 1; case AT_VOLUME_INFORMATION: return sizeof(struct volume_information); - case AT_INDEX_ROOT: - return sizeof(struct index_root); - case AT_REPARSE_POINT: - return offsetof(struct reparse_point, reparse_data); case AT_EA_INFORMATION: return sizeof(struct ea_information); - case AT_EA: - return offsetof(struct ea_attr, ea_name) + 1; default: return 0; } @@ -672,6 +661,9 @@ static int ntfs_attr_find(const __le32 type, const __le16 *name, __le16 *upcase = vol->upcase; u32 upcase_len = vol->upcase_len; unsigned int space; + u16 name_offset; + u32 attr_len; + u32 name_size; /* * Iterate over attributes in mft record starting at @ctx->attr, or the @@ -699,6 +691,20 @@ static int ntfs_attr_find(const __le32 type, const __le16 *name, return -ENOENT; if (unlikely(!a->length)) break; + if (a->name_length) { + name_offset = le16_to_cpu(a->name_offset); + attr_len = le32_to_cpu(a->length); + name_size = a->name_length * sizeof(__le16); + + if (name_offset > attr_len || + attr_len - name_offset < name_size) { + ntfs_error(vol->sb, + "Corrupt attribute name in MFT record %llu\n", + ctx->ntfs_ino->mft_no); + break; + } + } + if (type == AT_UNUSED) return 0; if (a->type != type) @@ -712,14 +718,6 @@ static int ntfs_attr_find(const __le32 type, const __le16 *name, if (a->name_length) return -ENOENT; } else { - if (a->name_length && ((le16_to_cpu(a->name_offset) + - a->name_length * sizeof(__le16)) > - le32_to_cpu(a->length))) { - ntfs_error(vol->sb, "Corrupt attribute name in MFT record %llu\n", - ctx->ntfs_ino->mft_no); - break; - } - if (!ntfs_are_names_equal(name, name_len, (__le16 *)((u8 *)a + le16_to_cpu(a->name_offset)), a->name_length, ic, upcase, upcase_len)) { @@ -2924,12 +2922,12 @@ int ntfs_attr_open(struct ntfs_inode *ni, const __le32 type, struct ntfs_inode *base_ni; int err; - ntfs_debug("Entering for inode %lld, attr 0x%x.\n", - (unsigned long long)ni->mft_no, type); - if (!ni || !ni->vol) return -EINVAL; + ntfs_debug("Entering for inode %lld, attr 0x%x.\n", + ni->mft_no, type); + if (NInoAttr(ni)) base_ni = ni->ext.base_ntfs_ino; else diff --git a/fs/ntfs/attrlist.c b/fs/ntfs/attrlist.c index bd501e8a628c..c2594d4c83b0 100644 --- a/fs/ntfs/attrlist.c +++ b/fs/ntfs/attrlist.c @@ -119,15 +119,14 @@ int ntfs_attrlist_entry_add(struct ntfs_inode *ni, struct attr_record *attr) struct mft_record *ni_mrec; u8 *old_al; - ntfs_debug("Entering for inode 0x%llx, attr 0x%x.\n", - (long long) ni->mft_no, - (unsigned int) le32_to_cpu(attr->type)); - if (!ni || !attr) { ntfs_debug("Invalid arguments.\n"); return -EINVAL; } + ntfs_debug("Entering for inode 0x%llx, attr 0x%x.\n", + ni->mft_no, (unsigned int) le32_to_cpu(attr->type)); + ni_mrec = map_mft_record(ni); if (IS_ERR(ni_mrec)) { ntfs_debug("Invalid arguments.\n"); diff --git a/fs/ntfs/bdev-io.c b/fs/ntfs/bdev-io.c index 67e65c88d681..27d7c2767a33 100644 --- a/fs/ntfs/bdev-io.c +++ b/fs/ntfs/bdev-io.c @@ -97,6 +97,8 @@ int ntfs_bdev_write(struct super_block *sb, void *buf, loff_t start, size_t size idx_end++; for (; idx < idx_end; idx++, from = 0) { + u32 len; + folio = read_mapping_folio(sb->s_bdev->bd_mapping, idx, NULL); if (IS_ERR(folio)) { ntfs_error(sb, "Unable to read %ld page", idx); @@ -105,9 +107,10 @@ int ntfs_bdev_write(struct super_block *sb, void *buf, loff_t start, size_t size offset = (loff_t)idx << PAGE_SHIFT; to = min_t(u32, end - offset, PAGE_SIZE); + len = to - from; - memcpy_to_folio(folio, from, buf + buf_off, to); - buf_off += to; + memcpy_to_folio(folio, from, buf + buf_off, len); + buf_off += len; folio_mark_uptodate(folio); folio_mark_dirty(folio); folio_put(folio); diff --git a/fs/ntfs/index.c b/fs/ntfs/index.c index a547bdcfa456..146e011c1a41 100644 --- a/fs/ntfs/index.c +++ b/fs/ntfs/index.c @@ -677,11 +677,11 @@ static int ntfs_ib_read(struct ntfs_index_context *icx, s64 vcn, struct index_bl static int ntfs_icx_parent_inc(struct ntfs_index_context *icx) { - icx->pindex++; - if (icx->pindex >= MAX_PARENT_VCN) { + if (icx->pindex >= MAX_PARENT_VCN - 1) { ntfs_error(icx->idx_ni->vol->sb, "Index is over %d level deep", MAX_PARENT_VCN); return -EOPNOTSUPP; } + icx->pindex++; return 0; } @@ -1970,6 +1970,7 @@ struct index_entry *ntfs_index_walk_down(struct index_entry *ie, struct ntfs_ind { struct index_entry *entry; struct index_block *ib; + int err; s64 vcn; entry = ie; @@ -1979,14 +1980,20 @@ struct index_entry *ntfs_index_walk_down(struct index_entry *ie, struct ntfs_ind ib = kvzalloc(ictx->block_size, GFP_NOFS); if (!ib) return ERR_PTR(-ENOMEM); - /* down from level zero */ + /* + * Descending from root index (level 0) to the first + * child level. is_in_root == true implies pindex == 0, + * so advance to level 1. + */ + ictx->pindex = 1; ictx->ir = NULL; ictx->ib = ib; - ictx->pindex = 1; ictx->is_in_root = false; } else { /* down from non-zero level */ - ictx->pindex++; + err = ntfs_icx_parent_inc(ictx); + if (err) + return ERR_PTR(err); } ictx->parent_pos[ictx->pindex] = 0; diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 16890d411194..360bebd1ee3f 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -2582,8 +2582,8 @@ int ntfs_inode_sync_filename(struct ntfs_inode *ni) mutex_lock_nested(&index_ni->mrec_lock, NTFS_INODE_MUTEX_PARENT); if (NInoBeingDeleted(ni)) { - iput(index_vi); mutex_unlock(&index_ni->mrec_lock); + iput(index_vi); continue; } @@ -2591,8 +2591,8 @@ int ntfs_inode_sync_filename(struct ntfs_inode *ni) if (!ictx) { ntfs_error(sb, "Failed to get index ctx, inode %llu", index_ni->mft_no); - iput(index_vi); mutex_unlock(&index_ni->mrec_lock); + iput(index_vi); continue; } @@ -2601,8 +2601,8 @@ int ntfs_inode_sync_filename(struct ntfs_inode *ni) ntfs_debug("Index lookup failed, inode %llu", index_ni->mft_no); ntfs_index_ctx_put(ictx); - iput(index_vi); mutex_unlock(&index_ni->mrec_lock); + iput(index_vi); continue; } /* Update flags and file size. */ diff --git a/fs/ntfs/logfile.c b/fs/ntfs/logfile.c index 3f8d1640f1d5..d3f25d8e29f9 100644 --- a/fs/ntfs/logfile.c +++ b/fs/ntfs/logfile.c @@ -710,6 +710,9 @@ bool ntfs_empty_logfile(struct inode *log_vi) if (unlikely(lcn == LCN_RL_NOT_MAPPED)) { vcn = rl->vcn; kvfree(empty_buf); + empty_buf = NULL; + kfree(ra); + ra = NULL; goto map_vcn; } /* If this run is not valid abort with an error. */ @@ -753,7 +756,7 @@ bool ntfs_empty_logfile(struct inode *log_vi) } while (start < end); } while ((++rl)->vcn < end_vcn); up_write(&log_ni->runlist.lock); - kfree(empty_buf); + kvfree(empty_buf); kfree(ra); truncate_inode_pages(log_vi->i_mapping, 0); /* Set the flag so we do not have to do it again on remount. */ diff --git a/fs/ntfs/mft.c b/fs/ntfs/mft.c index 7d989267a82b..a7d10ee41b34 100644 --- a/fs/ntfs/mft.c +++ b/fs/ntfs/mft.c @@ -30,6 +30,8 @@ int ntfs_mft_record_check(const struct ntfs_volume *vol, struct mft_record *m, { struct attr_record *a; struct super_block *sb = vol->sb; + u16 attrs_offset; + u32 bytes_in_use; if (!ntfs_is_file_record(m->magic)) { ntfs_error(sb, "Record %llu has no FILE magic (0x%x)\n", @@ -65,7 +67,16 @@ int ntfs_mft_record_check(const struct ntfs_volume *vol, struct mft_record *m, goto err_out; } - a = (struct attr_record *)((char *)m + le16_to_cpu(m->attrs_offset)); + attrs_offset = le16_to_cpu(m->attrs_offset); + bytes_in_use = le32_to_cpu(m->bytes_in_use); + + if (attrs_offset > bytes_in_use || + bytes_in_use - attrs_offset < sizeof_field(struct attr_record, type)) { + ntfs_error(sb, "Record %llu has corrupt attribute offset\n", mft_no); + goto err_out; + } + + a = (struct attr_record *)((char *)m + attrs_offset); if ((char *)a < (char *)m || (char *)a > (char *)m + vol->mft_record_size) { ntfs_error(sb, "Record %llu is corrupt\n", mft_no); goto err_out; @@ -449,7 +460,7 @@ static void ntfs_bio_end_io(struct bio *bio) int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, struct mft_record *m) { - u8 *kmirr = NULL; + u8 *kmirr; struct folio *folio; unsigned int folio_ofs, lcn_folio_off = 0; int err = 0; @@ -479,6 +490,7 @@ int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, kmirr = kmap_local_folio(folio, 0) + folio_ofs; /* Copy the mst protected mft record to the mirror. */ memcpy(kmirr, m, vol->mft_record_size); + kunmap_local(kmirr); if (vol->cluster_size_bits > PAGE_SHIFT) { lcn_folio_off = folio->index << PAGE_SHIFT; @@ -490,20 +502,22 @@ int ntfs_sync_mft_mirror(struct ntfs_volume *vol, const u64 mft_no, NTFS_B_TO_SECTOR(vol, NTFS_CLU_TO_B(vol, vol->mftmirr_lcn) + lcn_folio_off + folio_ofs); - if (!bio_add_folio(bio, folio, vol->mft_record_size, folio_ofs)) { + if (bio_add_folio(bio, folio, vol->mft_record_size, folio_ofs)) + err = submit_bio_wait(bio); + else err = -EIO; - bio_put(bio); - goto unlock_folio; - } + bio_put(bio); - bio->bi_end_io = ntfs_bio_end_io; - submit_bio(bio); - /* Current state: all buffers are clean, unlocked, and uptodate. */ + /* + * The in-memory mirror is now valid because we just memcpy()'d the + * mst-protected mft record into it. Mark the folio uptodate even on + * write error so a subsequent read_mapping_folio() does not refetch + * the stale on-disk mirror and overwrite this copy. The error is + * propagated to the caller via @err. + */ folio_mark_uptodate(folio); -unlock_folio: folio_unlock(folio); - kunmap_local(kmirr); folio_put(folio); if (likely(!err)) { ntfs_debug("Done."); @@ -588,20 +602,36 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn } /* Synchronize the mft mirror now if not @sync. */ - if (!sync && ni->mft_no < vol->mftmirr_size) - ntfs_sync_mft_mirror(vol, ni->mft_no, fixup_m); + if (!sync && ni->mft_no < vol->mftmirr_size) { + int sub_err = ntfs_sync_mft_mirror(vol, ni->mft_no, + fixup_m); + if (unlikely(sub_err) && !err) + err = sub_err; + } - folio_get(folio); - bio->bi_private = folio; - bio->bi_end_io = ntfs_bio_end_io; - submit_bio(bio); + if (sync) { + int sub_err = submit_bio_wait(bio); + + bio_put(bio); + if (unlikely(sub_err) && !err) + err = sub_err; + } else { + folio_get(folio); + bio->bi_private = folio; + bio->bi_end_io = ntfs_bio_end_io; + submit_bio(bio); + } offset += vol->cluster_size; i++; } /* If @sync, now synchronize the mft mirror. */ - if (sync && ni->mft_no < vol->mftmirr_size) - ntfs_sync_mft_mirror(vol, ni->mft_no, fixup_m); + if (sync && ni->mft_no < vol->mftmirr_size) { + int sub_err = ntfs_sync_mft_mirror(vol, ni->mft_no, fixup_m); + + if (unlikely(sub_err) && !err) + err = sub_err; + } kunmap_local(kaddr); if (unlikely(err)) { /* I/O error during writing. This is really bad! */ @@ -617,10 +647,10 @@ int write_mft_record_nolock(struct ntfs_inode *ni, struct mft_record *m, int syn bio_put(bio); err_out: /* - * Current state: all buffers are clean, unlocked, and uptodate. - * The caller should mark the base inode as bad so that no more i/o - * happens. ->drop_inode() will still be invoked so all extent inodes - * and other allocated memory will be freed. + * The caller should mark the base inode as bad so no more I/O + * happens. ->drop_inode() will still be invoked so all extent inodes + * and other allocated memory will be freed. ENOMEM is retried by + * redirtying the mft record below. */ if (err == -ENOMEM) { ntfs_error(vol->sb, @@ -833,7 +863,7 @@ static bool ntfs_may_write_mft_record(struct ntfs_volume *vol, const u64 mft_no, vi = igrab(mft_vi); WARN_ON(vi != mft_vi); } else { - vi = find_inode_nowait(sb, mft_no, ntfs_test_inode_wb, &na); + vi = find_inode_nowait(sb, na.mft_no, ntfs_test_inode_wb, &na); if (na.state == NI_BeingDeleted || na.state == NI_BeingCreated) return false; } @@ -1034,7 +1064,7 @@ static s64 ntfs_mft_bitmap_find_and_alloc_free_rec_nolock(struct ntfs_volume *vo b = ffz((unsigned long)*byte); if (b < 8 && b >= (bit & 7)) { ll = data_pos + (bit & ~7ull) + b; - if (unlikely(ll > (1ll << 32))) { + if (unlikely(ll >= (1ll << 32))) { folio_unlock(folio); kunmap_local(buf); folio_put(folio); @@ -2721,8 +2751,11 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w ntfs_debug("Entering for inode 0x%llx, attribute type 0x%x, folio index 0x%lx.", ni->mft_no, ni->type, folio->index); - if (!locked_nis || !ref_inos) + if (!locked_nis || !ref_inos) { + folio_redirty_for_writepage(wbc, folio); + folio_unlock(folio); return -ENOMEM; + } /* We have to zero every time due to mmap-at-end-of-file. */ if (folio->index >= (i_size >> folio_shift(folio))) @@ -2840,9 +2873,13 @@ static int ntfs_write_mft_block(struct folio *folio, struct writeback_control *w } prev_mft_ofs = mft_ofs; - if (mft_no < vol->mftmirr_size) - ntfs_sync_mft_mirror(vol, mft_no, + if (mft_no < vol->mftmirr_size) { + int sub_err = ntfs_sync_mft_mirror(vol, mft_no, (struct mft_record *)(kaddr + mft_ofs)); + + if (unlikely(sub_err) && !err) + err = sub_err; + } } else if (ref_inos[nr_ref_inos]) nr_ref_inos++; } diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c index 96c450e62efc..c4f82846c58c 100644 --- a/fs/ntfs/namei.c +++ b/fs/ntfs/namei.c @@ -344,9 +344,9 @@ static int ntfs_sd_add_everyone(struct ntfs_inode *ni) sd_len = sizeof(struct security_descriptor_relative) + 2 * (sizeof(struct ntfs_sid) + 8) + sizeof(struct ntfs_acl) + sizeof(struct ntfs_ace) + 4; - sd = kmalloc(sd_len, GFP_NOFS); + sd = kzalloc(sd_len, GFP_NOFS); if (!sd) - return -1; + return -ENOMEM; sd->revision = 1; sd->control = SE_DACL_PRESENT | SE_SELF_RELATIVE; diff --git a/fs/ntfs/runlist.c b/fs/ntfs/runlist.c index da21dbeaaf66..e7de3d01257e 100644 --- a/fs/ntfs/runlist.c +++ b/fs/ntfs/runlist.c @@ -2056,10 +2056,11 @@ struct runlist_element *ntfs_rl_collapse_range(struct runlist_element *dst_rl, i * consists of holes. */ merge_cnt = 0; - i = new_1st_cnt == 0 ? 1 : new_1st_cnt; - if (ntfs_rle_lcn_contiguous(&new_rl[i - 1], &new_rl[i])) { - /* Merge right and left */ - s_rl = &new_rl[new_1st_cnt - 1]; + if (new_1st_cnt > 0 && + ntfs_rle_lcn_contiguous(&new_rl[new_1st_cnt - 1], + &new_rl[new_1st_cnt])) { + /* Merge right and left. */ + s_rl = &new_rl[new_1st_cnt - 1]; s_rl->length += s_rl[1].length; merge_cnt = 1; } diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 22dc7865eca7..9e321cc2febe 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -413,6 +413,7 @@ int ntfs_write_volume_label(struct ntfs_volume *vol, char *label) { struct ntfs_inode *vol_ni = NTFS_I(vol->vol_ino); struct ntfs_attr_search_ctx *ctx; + char *new_label; __le16 *uname; int uname_len, ret; @@ -425,7 +426,7 @@ int ntfs_write_volume_label(struct ntfs_volume *vol, char *label) return uname_len; } - if (uname_len > NTFS_MAX_LABEL_LEN) { + if (uname_len > NTFS_MAX_LABEL_LEN) { ntfs_error(vol->sb, "Volume label is too long (max %d characters).", NTFS_MAX_LABEL_LEN); @@ -433,11 +434,22 @@ int ntfs_write_volume_label(struct ntfs_volume *vol, char *label) return -EINVAL; } + /* + * Allocate the in-memory label copy up front. If kstrdup() fails we + * bail out before touching on-disk metadata, so the in-memory label + * and the on-disk label stay in sync. + */ + new_label = kstrdup(label, GFP_KERNEL); + if (!new_label) { + kvfree(uname); + return -ENOMEM; + } + mutex_lock(&vol_ni->mrec_lock); ctx = ntfs_attr_get_search_ctx(vol_ni, NULL); if (!ctx) { ret = -ENOMEM; - goto out; + goto out; } if (!ntfs_attr_lookup(AT_VOLUME_NAME, NULL, 0, 0, 0, NULL, 0, @@ -450,12 +462,14 @@ int ntfs_write_volume_label(struct ntfs_volume *vol, char *label) out: mutex_unlock(&vol_ni->mrec_lock); kvfree(uname); - mark_inode_dirty_sync(vol->vol_ino); if (ret >= 0) { kfree(vol->volume_label); - vol->volume_label = kstrdup(label, GFP_KERNEL); + vol->volume_label = new_label; + mark_inode_dirty_sync(vol->vol_ino); ret = 0; + } else { + kfree(new_label); } return ret; } @@ -979,6 +993,13 @@ static bool check_mft_mirror(struct ntfs_volume *vol) ntfs_is_baad_recordp((__le32 *)kmirr)) bytes = vol->mft_record_size; } + /* Compare the two records. */ + if (memcmp(kmft, kmirr, bytes)) { + ntfs_error(sb, + "$MFT and $MFTMirr record %i do not match. Run chkdsk.", + i); + goto mm_unmap_out; + } kmft += vol->mft_record_size; kmirr += vol->mft_record_size; } while (++i < vol->mftmirr_size); @@ -1671,7 +1692,7 @@ static bool load_system_files(struct ntfs_volume *vol) iput_upcase_err_out: vol->upcase_len = 0; mutex_lock(&ntfs_lock); - if (vol->upcase == default_upcase) { + if (vol->upcase && vol->upcase == default_upcase) { ntfs_nr_upcase_users--; vol->upcase = NULL; } @@ -1701,7 +1722,7 @@ static void ntfs_volume_free(struct ntfs_volume *vol) * the number of upcase users if we are a user. */ mutex_lock(&ntfs_lock); - if (vol->upcase == default_upcase) { + if (vol->upcase && vol->upcase == default_upcase) { ntfs_nr_upcase_users--; vol->upcase = NULL; } @@ -2494,7 +2515,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) } vol->upcase_len = 0; mutex_lock(&ntfs_lock); - if (vol->upcase == default_upcase) { + if (vol->upcase && vol->upcase == default_upcase) { ntfs_nr_upcase_users--; vol->upcase = NULL; } diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c index bec5475de094..75e65e72c2d6 100644 --- a/fs/orangefs/namei.c +++ b/fs/orangefs/namei.c @@ -362,7 +362,7 @@ static struct dentry *orangefs_mkdir(struct mnt_idmap *idmap, struct inode *dir, __orangefs_setattr(dir, &iattr); out: op_release(new_op); - return ERR_PTR(ret); + return ret ? ERR_PTR(ret) : NULL; } static int orangefs_rename(struct mnt_idmap *idmap, diff --git a/fs/select.c b/fs/select.c index 75978b18f48f..bf71c9838dfe 100644 --- a/fs/select.c +++ b/fs/select.c @@ -708,6 +708,17 @@ static int kern_select(int n, fd_set __user *inp, fd_set __user *outp, if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; + /* + * Reject negative components before normalisation. The seconds + * sum below is performed in signed long and a crafted negative + * timeval can wrap to a positive value that passes + * timespec64_valid() and turns into an effectively-infinite + * deadline via timespec64_add_safe()'s saturation, instead of + * the -EINVAL POSIX requires for negative timeouts. + */ + if (tv.tv_sec < 0 || tv.tv_usec < 0) + return -EINVAL; + to = &end_time; if (poll_select_set_timeout(to, tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 9f76b0347fa9..f557eb7875c7 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -434,7 +434,8 @@ cifs_alloc_inode(struct super_block *sb) spin_lock_init(&cifs_inode->writers_lock); cifs_inode->writers = 0; cifs_inode->netfs.inode.i_blkbits = 14; /* 2**14 = CIFS_MAX_MSGSIZE */ - cifs_inode->netfs.remote_i_size = 0; + cifs_inode->netfs._remote_i_size = 0; + cifs_inode->netfs._zero_point = 0; cifs_inode->uniqueid = 0; cifs_inode->createtime = 0; cifs_inode->epoch = 0; @@ -1303,7 +1304,8 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, struct cifsFileInfo *smb_file_src = src_file->private_data; struct cifsFileInfo *smb_file_target = dst_file->private_data; struct cifs_tcon *target_tcon, *src_tcon; - unsigned long long destend, fstart, fend, old_size, new_size; + unsigned long long i_size, new_size; + unsigned long long destend, fstart, fend; unsigned int xid; int rc; @@ -1347,7 +1349,7 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, * Advance the EOF marker after the flush above to the end of the range * if it's short of that. */ - if (src_cifsi->netfs.remote_i_size < off + len) { + if (netfs_read_remote_i_size(src_inode) < off + len) { rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); if (rc < 0) goto unlock; @@ -1368,22 +1370,24 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false); if (rc) goto unlock; - if (fend > target_cifsi->netfs.zero_point) - target_cifsi->netfs.zero_point = fend + 1; - old_size = target_cifsi->netfs.remote_i_size; + + spin_lock(&target_inode->i_lock); + if (fend > target_cifsi->netfs._zero_point) + netfs_write_zero_point(target_inode, fend + 1); + i_size = target_inode->i_size; + spin_unlock(&target_inode->i_lock); /* Discard all the folios that overlap the destination region. */ cifs_dbg(FYI, "about to discard pages %llx-%llx\n", fstart, fend); truncate_inode_pages_range(&target_inode->i_data, fstart, fend); - fscache_invalidate(cifs_inode_cookie(target_inode), NULL, - i_size_read(target_inode), 0); + fscache_invalidate(cifs_inode_cookie(target_inode), NULL, i_size, 0); rc = -EOPNOTSUPP; if (target_tcon->ses->server->ops->duplicate_extents) { rc = target_tcon->ses->server->ops->duplicate_extents(xid, smb_file_src, smb_file_target, off, len, destoff); - if (rc == 0 && new_size > old_size) { + if (rc == 0 && new_size > i_size) { truncate_setsize(target_inode, new_size); fscache_resize_cookie(cifs_inode_cookie(target_inode), new_size); @@ -1402,8 +1406,12 @@ static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, rc = -EINVAL; } } - if (rc == 0 && new_size > target_cifsi->netfs.zero_point) - target_cifsi->netfs.zero_point = new_size; + if (rc == 0) { + spin_lock(&target_inode->i_lock); + if (new_size > target_cifsi->netfs._zero_point) + netfs_write_zero_point(target_inode, new_size); + spin_unlock(&target_inode->i_lock); + } } /* force revalidate of size and timestamps of target file now @@ -1474,7 +1482,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, * Advance the EOF marker after the flush above to the end of the range * if it's short of that. */ - if (src_cifsi->netfs.remote_i_size < off + len) { + if (netfs_read_remote_i_size(src_inode) < off + len) { rc = cifs_precopy_set_eof(src_inode, src_cifsi, src_tcon, xid, off + len); if (rc < 0) goto unlock; @@ -1502,8 +1510,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, fscache_resize_cookie(cifs_inode_cookie(target_inode), i_size_read(target_inode)); } - if (rc > 0 && destoff + rc > target_cifsi->netfs.zero_point) - target_cifsi->netfs.zero_point = destoff + rc; + if (rc > 0) { + spin_lock(&target_inode->i_lock); + if (destoff + rc > target_cifsi->netfs._zero_point) + netfs_write_zero_point(target_inode, destoff + rc); + spin_unlock(&target_inode->i_lock); + } } file_accessed(src_file); diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 3990a9012264..9e27bfa7376b 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1465,6 +1465,7 @@ cifs_readv_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid) struct cifs_io_subrequest *rdata = mid->callback_data; struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); + struct inode *inode = &ictx->inode; struct smb_rqst rqst = { .rq_iov = rdata->iov, .rq_nvec = 1, .rq_iter = rdata->subreq.io_iter }; @@ -1538,7 +1539,7 @@ cifs_readv_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid) } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && - rdata->subreq.start + trans >= ictx->remote_i_size) { + rdata->subreq.start + trans >= netfs_read_remote_i_size(inode)) { rdata->result = 0; __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); } else if (rdata->got_bytes > 0) { diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 664a2c223089..b60344125f27 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -2517,18 +2517,23 @@ int cifs_lock(struct file *file, int cmd, struct file_lock *flock) void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t result) { struct netfs_io_request *wreq = wdata->rreq; - struct netfs_inode *ictx = netfs_inode(wreq->inode); + struct inode *inode = wreq->inode; + struct netfs_inode *ictx = netfs_inode(inode); loff_t wrend; if (result > 0) { + spin_lock(&inode->i_lock); + wrend = wdata->subreq.start + wdata->subreq.transferred + result; - if (wrend > ictx->zero_point && + if (wrend > ictx->_zero_point && (wdata->rreq->origin == NETFS_UNBUFFERED_WRITE || wdata->rreq->origin == NETFS_DIO_WRITE)) - ictx->zero_point = wrend; - if (wrend > ictx->remote_i_size) + netfs_write_zero_point(inode, wrend); + if (wrend > ictx->_remote_i_size) netfs_resize_file(ictx, wrend, true); + + spin_unlock(&inode->i_lock); } netfs_write_subrequest_terminated(&wdata->subreq, result); diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 16a5310155d5..9472c0a6c187 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -119,7 +119,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); mtime = inode_get_mtime(inode); if (timespec64_equal(&mtime, &fattr->cf_mtime) && - cifs_i->netfs.remote_i_size == fattr->cf_eof) { + netfs_read_remote_i_size(inode) == fattr->cf_eof) { cifs_dbg(FYI, "%s: inode %llu is unchanged\n", __func__, cifs_i->uniqueid); return; @@ -173,12 +173,12 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, CIFS_I(inode)->time = 0; /* force reval */ return -ESTALE; } - if (inode_state_read_once(inode) & I_NEW) - CIFS_I(inode)->netfs.zero_point = fattr->cf_eof; - cifs_revalidate_cache(inode, fattr); spin_lock(&inode->i_lock); + if (inode_state_read_once(inode) & I_NEW) + netfs_write_zero_point(inode, fattr->cf_eof); + fattr->cf_mtime = timestamp_truncate(fattr->cf_mtime, inode); fattr->cf_atime = timestamp_truncate(fattr->cf_atime, inode); fattr->cf_ctime = timestamp_truncate(fattr->cf_ctime, inode); @@ -212,7 +212,7 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr, else clear_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags); - cifs_i->netfs.remote_i_size = fattr->cf_eof; + netfs_write_remote_i_size(inode, fattr->cf_eof); /* * Can't safely change the file size here if the client is writing to * it due to potential races. @@ -2772,7 +2772,9 @@ cifs_revalidate_mapping(struct inode *inode) if (cifs_sb_flags(cifs_sb) & CIFS_MOUNT_RW_CACHE) goto skip_invalidate; - cifs_inode->netfs.zero_point = cifs_inode->netfs.remote_i_size; + spin_lock(&inode->i_lock); + netfs_write_zero_point(inode, netfs_inode(inode)->_remote_i_size); + spin_unlock(&inode->i_lock); rc = filemap_invalidate_inode(inode, true, 0, LLONG_MAX); if (rc) { cifs_dbg(VFS, "%s: invalidate inode %p failed with rc %d\n", diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c index be22bbc4a65a..e860fa08b5e3 100644 --- a/fs/smb/client/readdir.c +++ b/fs/smb/client/readdir.c @@ -143,7 +143,8 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name, fattr->cf_rdev = inode->i_rdev; fattr->cf_uid = inode->i_uid; fattr->cf_gid = inode->i_gid; - fattr->cf_eof = CIFS_I(inode)->netfs.remote_i_size; + fattr->cf_eof = + netfs_read_remote_i_size(inode); fattr->cf_symlink_target = NULL; } else { CIFS_I(inode)->time = 0; diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 3738204984f5..189bb863a9af 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -3402,8 +3402,7 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct netfs_inode *ictx = netfs_inode(inode); - unsigned long long i_size, new_size, remote_size; + unsigned long long i_size, new_size, remote_i_size, zero_point; long rc; unsigned int xid; @@ -3414,9 +3413,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, filemap_invalidate_lock(inode->i_mapping); - i_size = i_size_read(inode); - remote_size = ictx->remote_i_size; - if (offset + len >= remote_size && offset < i_size) { + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); + if (offset + len >= remote_i_size && offset < i_size) { unsigned long long top = umin(offset + len, i_size); rc = filemap_write_and_wait_range(inode->i_mapping, offset, top - 1); @@ -3449,9 +3447,11 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon, cfile->fid.volatile_fid, cfile->pid, new_size); if (rc >= 0) { truncate_setsize(inode, new_size); + spin_lock(&inode->i_lock); netfs_resize_file(&cifsi->netfs, new_size, true); - if (offset < cifsi->netfs.zero_point) - cifsi->netfs.zero_point = offset; + if (offset < cifsi->netfs._zero_point) + netfs_write_zero_point(inode, offset); + spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), new_size); } } @@ -3474,7 +3474,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, struct inode *inode = file_inode(file); struct cifsFileInfo *cfile = file->private_data; struct file_zero_data_information fsctl_buf; - unsigned long long end = offset + len, i_size, remote_i_size; + unsigned long long end = offset + len, i_size, remote_i_size, zero_point; long rc; unsigned int xid; __u8 set_sparse = 1; @@ -3516,14 +3516,17 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon, * that we locally hole-punch the tail of the dirty data, the proposed * EOF update will end up in the wrong place. */ - i_size = i_size_read(inode); - remote_i_size = netfs_inode(inode)->remote_i_size; + netfs_read_sizes(inode, &i_size, &remote_i_size, &zero_point); + if (end > remote_i_size && i_size > remote_i_size) { unsigned long long extend_to = umin(end, i_size); rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid, cfile->fid.volatile_fid, cfile->pid, extend_to); - if (rc >= 0) - netfs_inode(inode)->remote_i_size = extend_to; + if (rc >= 0) { + spin_lock(&inode->i_lock); + netfs_write_remote_i_size(inode, extend_to); + spin_unlock(&inode->i_lock); + } } unlock: @@ -3787,7 +3790,6 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, struct inode *inode = file_inode(file); struct cifsInodeInfo *cifsi = CIFS_I(inode); struct cifsFileInfo *cfile = file->private_data; - struct netfs_inode *ictx = &cifsi->netfs; loff_t old_eof, new_eof; xid = get_xid(); @@ -3805,7 +3807,9 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, goto out_2; truncate_pagecache_range(inode, off, old_eof); - ictx->zero_point = old_eof; + spin_lock(&inode->i_lock); + netfs_write_zero_point(inode, old_eof); + spin_unlock(&inode->i_lock); netfs_wait_for_outstanding_io(inode); rc = smb2_copychunk_range(xid, cfile, cfile, off + len, @@ -3822,8 +3826,10 @@ static long smb3_collapse_range(struct file *file, struct cifs_tcon *tcon, rc = 0; truncate_setsize(inode, new_eof); + spin_lock(&inode->i_lock); netfs_resize_file(&cifsi->netfs, new_eof, true); - ictx->zero_point = new_eof; + netfs_write_zero_point(inode, new_eof); + spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), new_eof); out_2: filemap_invalidate_unlock(inode->i_mapping); @@ -3866,13 +3872,17 @@ static long smb3_insert_range(struct file *file, struct cifs_tcon *tcon, goto out_2; truncate_setsize(inode, new_eof); + spin_lock(&inode->i_lock); netfs_resize_file(&cifsi->netfs, i_size_read(inode), true); + spin_unlock(&inode->i_lock); fscache_resize_cookie(cifs_inode_cookie(inode), i_size_read(inode)); rc = smb2_copychunk_range(xid, cfile, cfile, off, count, off + len); if (rc < 0) goto out_2; - cifsi->netfs.zero_point = new_eof; + spin_lock(&inode->i_lock); + netfs_write_zero_point(inode, new_eof); + spin_unlock(&inode->i_lock); rc = smb3_zero_data(file, tcon, off, len, xid); if (rc < 0) diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 995fcdd30681..3bd300347f16 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -4608,6 +4608,7 @@ smb2_readv_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid) struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode); struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink); struct smb2_hdr *shdr = (struct smb2_hdr *)rdata->iov[0].iov_base; + struct inode *inode = &ictx->inode; struct cifs_credits credits = { .value = 0, .instance = 0, @@ -4721,7 +4722,7 @@ smb2_readv_callback(struct TCP_Server_Info *server, struct mid_q_entry *mid) } else { size_t trans = rdata->subreq.transferred + rdata->got_bytes; if (trans < rdata->subreq.len && - rdata->subreq.start + trans >= ictx->remote_i_size) { + rdata->subreq.start + trans >= netfs_read_remote_i_size(inode)) { __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags); rdata->result = 0; } diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 8feca02ddbf2..0f5c18520eff 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -481,8 +481,12 @@ static inline int compare_guid_key(struct oplock_info *opinfo, const char *guid1, const char *key1) { const char *guid2, *key2; + struct ksmbd_conn *conn; - guid2 = opinfo->conn->ClientGUID; + conn = READ_ONCE(opinfo->conn); + if (!conn) + return 0; + guid2 = conn->ClientGUID; key2 = opinfo->o_lease->lease_key; if (!memcmp(guid1, guid2, SMB2_CLIENT_GUID_SIZE) && !memcmp(key1, key2, SMB2_LEASE_KEY_SIZE)) diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index c1d1f34581d6..9161e9d7ed24 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -643,8 +643,10 @@ static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, ntace = (struct smb_ace *)((char *)pndace + *size); ace_sz = fill_ace_for_sid(ntace, sid, ACCESS_ALLOWED, flags, pace->e_perm, 0777); - if (check_add_overflow(*size, ace_sz, size)) + if (check_add_overflow(*size, ace_sz, size)) { + kfree(sid); break; + } (*num_aces)++; if (pace->e_tag == ACL_USER) ntace->access_req |= @@ -655,8 +657,10 @@ static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, ntace = (struct smb_ace *)((char *)pndace + *size); ace_sz = fill_ace_for_sid(ntace, sid, ACCESS_ALLOWED, 0x03, pace->e_perm, 0777); - if (check_add_overflow(*size, ace_sz, size)) + if (check_add_overflow(*size, ace_sz, size)) { + kfree(sid); break; + } (*num_aces)++; if (pace->e_tag == ACL_USER) ntace->access_req |= @@ -698,8 +702,10 @@ static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap, ntace = (struct smb_ace *)((char *)pndace + *size); ace_sz = fill_ace_for_sid(ntace, sid, ACCESS_ALLOWED, 0x0b, pace->e_perm, 0777); - if (check_add_overflow(*size, ace_sz, size)) + if (check_add_overflow(*size, ace_sz, size)) { + kfree(sid); break; + } (*num_aces)++; if (pace->e_tag == ACL_USER) ntace->access_req |= diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index 354c4d8a1cfb..913164c958b1 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -81,7 +81,7 @@ static int proc_show_files(struct seq_file *m, void *v) read_lock(&global_ft.lock); idr_for_each_entry(global_ft.idr, fp, id) { seq_printf(m, "%#-10x %#-10llx %#-10llx %#-10x", - fp->tcon->id, + fp->tcon ? fp->tcon->id : 0, fp->persistent_id, fp->volatile_id, atomic_read(&fp->refcount)); diff --git a/include/asm-generic/ring_buffer.h b/include/asm-generic/ring_buffer.h new file mode 100644 index 000000000000..201d2aee1005 --- /dev/null +++ b/include/asm-generic/ring_buffer.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Generic arch dependent ring_buffer macros. + */ +#ifndef __ASM_GENERIC_RING_BUFFER_H__ +#define __ASM_GENERIC_RING_BUFFER_H__ + +#include + +/* Flush cache on ring buffer range if needed. Do nothing by default. */ +#define arch_ring_buffer_flush_range(start, end) do { } while (0) + +#endif /* __ASM_GENERIC_RING_BUFFER_H__ */ diff --git a/include/crypto/krb5.h b/include/crypto/krb5.h index 71dd38f59be1..aac3ecf88467 100644 --- a/include/crypto/krb5.h +++ b/include/crypto/krb5.h @@ -121,9 +121,12 @@ size_t crypto_krb5_how_much_buffer(const struct krb5_enctype *krb5, size_t crypto_krb5_how_much_data(const struct krb5_enctype *krb5, enum krb5_crypto_mode mode, size_t *_buffer_size, size_t *_offset); -void crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, - enum krb5_crypto_mode mode, - size_t *_offset, size_t *_len); +int crypto_krb5_where_is_the_data(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t *_offset, size_t *_len); +int crypto_krb5_check_data_len(const struct krb5_enctype *krb5, + enum krb5_crypto_mode mode, + size_t len, size_t min_content); struct crypto_aead *crypto_krb5_prepare_encryption(const struct krb5_enctype *krb5, const struct krb5_buffer *TK, u32 usage, gfp_t gfp); diff --git a/include/linux/efi.h b/include/linux/efi.h index 72e76ec54641..ccbc35479684 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -61,7 +61,7 @@ typedef void *efi_handle_t; /* * The UEFI spec and EDK2 reference implementation both define EFI_GUID as - * struct { u32 a; u16; b; u16 c; u8 d[8]; }; and so the implied alignment + * struct { u32 a; u16 b; u16 c; u8 d[8]; }; and so the implied alignment * is 32 bits not 8 bits like our guid_t. In some cases (i.e., on 32-bit ARM), * this means that firmware services invoked by the kernel may assume that * efi_guid_t* arguments are 32-bit aligned, and use memory accessors that diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h index 6c75df30a281..cd4972a7c97c 100644 --- a/include/linux/gfp_types.h +++ b/include/linux/gfp_types.h @@ -273,11 +273,11 @@ enum { * * %__GFP_ZERO returns a zeroed page on success. * - * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself - * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that - * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting - * memory tags at the same time as zeroing memory has minimal additional - * performance impact. + * %__GFP_ZEROTAGS zeroes memory tags at allocation time. Setting memory tags at + * the same time as zeroing memory (e.g., with __GFP_ZERO) has minimal + * additional performance impact. However, __GFP_ZEROTAGS also zeroes the tags + * even if memory is not getting zeroed at allocation time (e.g., + * with init_on_free). * * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation. * Used for userspace and vmalloc pages; the latter are unpoisoned by diff --git a/include/linux/highmem.h b/include/linux/highmem.h index af03db851a1d..d7aac9de1c8a 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -347,10 +347,11 @@ static inline void clear_highpage_kasan_tagged(struct page *page) #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES -/* Return false to let people know we did not initialize the pages */ -static inline bool tag_clear_highpages(struct page *page, int numpages) +/* Returns true if the caller has to initialize the pages */ +static inline bool tag_clear_highpages(struct page *page, int numpages, + bool clear_pages) { - return false; + return clear_pages; } #endif diff --git a/include/linux/libata.h b/include/linux/libata.h index 5c085ef4eda7..127229fbd1a6 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -371,6 +371,7 @@ enum { /* return values for ->qc_defer */ ATA_DEFER_LINK = 1, ATA_DEFER_PORT = 2, + ATA_DEFER_LINK_EXCL = 3, /* desc_len for ata_eh_info and context */ ATA_EH_DESC_LEN = 80, @@ -854,6 +855,9 @@ struct ata_link { unsigned int sata_spd; /* current SATA PHY speed */ enum ata_lpm_policy lpm_policy; + struct work_struct deferred_qc_work; + struct ata_queued_cmd *deferred_qc; + /* record runtime error info, protected by host_set lock */ struct ata_eh_info eh_info; /* EH context */ @@ -899,9 +903,6 @@ struct ata_port { u64 qc_active; int nr_active_links; /* #links with active qcs */ - struct work_struct deferred_qc_work; - struct ata_queued_cmd *deferred_qc; - struct ata_link link; /* host default link */ struct ata_link *slave_link; /* see ata_slave_link_init() */ diff --git a/include/linux/list.h b/include/linux/list.h index 00ea8e5fb88b..09d979976b3b 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -191,6 +191,29 @@ static inline void list_add_tail(struct list_head *new, struct list_head *head) __list_add(new, head->prev, head); } +/** + * list_add_tail_release - add a new entry with release barrier + * @new: new entry to be added + * @head: list head to add it before + * + * Insert a new entry before the specified head, using a release barrier to set + * the ->next pointer that points to it. This is useful for implementing + * queues, in particular one that the elements will be walked through forwards + * locklessly. + */ +static inline void list_add_tail_release(struct list_head *new, + struct list_head *head) +{ + struct list_head *prev = head->prev; + + if (__list_add_valid(new, prev, head)) { + new->next = head; + new->prev = prev; + head->prev = new; + smp_store_release(&prev->next, new); + } +} + /* * Delete a list entry by making the prev/next entries * point to each other. @@ -644,6 +667,20 @@ static inline void list_splice_tail_init(struct list_head *list, pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ }) +/** + * list_first_entry_or_null_acquire - get the first element from a list with barrier + * @ptr: the list head to take the element from. + * @type: the type of the struct this is embedded in. + * @member: the name of the list_head within the struct. + * + * Note that if the list is empty, it returns NULL. + */ +#define list_first_entry_or_null_acquire(ptr, type, member) ({ \ + struct list_head *head__ = (ptr); \ + struct list_head *pos__ = smp_load_acquire(&head__->next); \ + pos__ != head__ ? list_entry(pos__, type, member) : NULL; \ +}) + /** * list_last_entry_or_null - get the last element from a list * @ptr: the list head to take the element from. diff --git a/include/linux/netfs.h b/include/linux/netfs.h index ba17ac5bf356..243c0f737938 100644 --- a/include/linux/netfs.h +++ b/include/linux/netfs.h @@ -62,8 +62,8 @@ struct netfs_inode { struct fscache_cookie *cache; #endif struct mutex wb_lock; /* Writeback serialisation */ - loff_t remote_i_size; /* Size of the remote file */ - loff_t zero_point; /* Size after which we assume there's no data + loff_t _remote_i_size; /* Size of the remote file */ + loff_t _zero_point; /* Size after which we assume there's no data * on the server */ atomic_t io_count; /* Number of outstanding reqs */ unsigned long flags; @@ -252,7 +252,7 @@ struct netfs_io_request { unsigned long long collected_to; /* Point we've collected to */ unsigned long long cleaned_to; /* Position we've cleaned folios to */ unsigned long long abandon_to; /* Position to abandon folios to */ - pgoff_t no_unlock_folio; /* Don't unlock this folio after read */ + const struct folio *no_unlock_folio; /* Don't unlock this folio after read */ unsigned int direct_bv_count; /* Number of elements in direct_bv[] */ unsigned int debug_id; unsigned int rsize; /* Maximum read size (0 for none) */ @@ -474,6 +474,254 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode) return container_of(inode, struct netfs_inode, inode); } +/** + * netfs_read_remote_i_size - Read remote_i_size safely + * @inode: The inode to access + * + * Read remote_i_size safely without the potential for tearing on 32-bit + * arches. + * + * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the + * i_size_read/write must be atomic with respect to the local cpu (unlike with + * preempt disabled), but they don't need to be atomic with respect to other + * cpus like in true SMP (so they need either to either locally disable irq + * around the read or for example on x86 they can be still implemented as a + * cmpxchg8b without the need of the lock prefix). For SMP compiles and 64bit + * archs it makes no difference if preempt is enabled or not. + */ +static inline unsigned long long netfs_read_remote_i_size(const struct inode *inode) +{ + const struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode); + unsigned long long remote_i_size; + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + unsigned int seq; + + do { + seq = read_seqcount_begin(&inode->i_size_seqcount); + remote_i_size = ictx->_remote_i_size; + } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + remote_i_size = ictx->_remote_i_size; + preempt_enable(); +#else + /* Pairs with smp_store_release() in netfs_write_remote_i_size() */ + remote_i_size = smp_load_acquire(&ictx->_remote_i_size); +#endif + return remote_i_size; +} + +/* + * netfs_write_remote_i_size - Set remote_i_size safely + * @inode: The inode to access + * @remote_i_size: The new value for the size of the file on the server + * + * Set remote_i_size safely without the potential for tearing on 32-bit arches. + * + * Context: The caller must hold inode->i_lock. + * + * NOTE: unlike netfs_read_remote_i_size(), netfs_write_remote_i_size() does + * need locking around it (normally i_rwsem), otherwise on 32bit/SMP an update + * of i_size_seqcount can be lost, resulting in subsequent i_size_read() calls + * spinning forever. + */ +static inline void netfs_write_remote_i_size(struct inode *inode, + unsigned long long remote_i_size) +{ + struct netfs_inode *ictx = netfs_inode(inode); + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_begin(&inode->i_size_seqcount); + ictx->_remote_i_size = remote_i_size; + write_seqcount_end(&inode->i_size_seqcount); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + ictx->_remote_i_size = remote_i_size; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in netfs_read_remote_i_size() to + * ensure changes related to inode size (such as page contents) are + * visible before we see the changed inode size. + */ + smp_store_release(&ictx->_remote_i_size, remote_i_size); +#endif +} + +/** + * netfs_read_zero_point - Read zero_point safely + * @inode: The inode to access + * + * Read zero_point safely without the potential for tearing on 32-bit + * arches. + * + * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the + * i_size_read/write must be atomic with respect to the local cpu (unlike with + * preempt disabled), but they don't need to be atomic with respect to other + * cpus like in true SMP (so they need either to either locally disable irq + * around the read or for example on x86 they can be still implemented as a + * cmpxchg8b without the need of the lock prefix). For SMP compiles and 64bit + * archs it makes no difference if preempt is enabled or not. + */ +static inline unsigned long long netfs_read_zero_point(const struct inode *inode) +{ + struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode); + unsigned long long zero_point; + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + unsigned int seq; + + do { + seq = read_seqcount_begin(&inode->i_size_seqcount); + zero_point = ictx->_zero_point; + } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + zero_point = ictx->_zero_point; + preempt_enable(); +#else + /* Pairs with smp_store_release() in netfs_write_zero_point() */ + zero_point = smp_load_acquire(&ictx->_zero_point); +#endif + return zero_point; +} + +/* + * netfs_write_zero_point - Set zero_point safely + * @inode: The inode to access + * @zero_point: The new value for the point beyond which the server has no data + * + * Set zero_point safely without the potential for tearing on 32-bit arches. + * + * Context: The caller must hold inode->i_lock. + * + * NOTE: unlike netfs_read_zero_point(), netfs_write_zero_point() does need + * locking around it (normally i_rwsem), otherwise on 32bit/SMP an update of + * i_size_seqcount can be lost, resulting in subsequent read calls spinning + * forever. + */ +static inline void netfs_write_zero_point(struct inode *inode, + unsigned long long zero_point) +{ + struct netfs_inode *ictx = netfs_inode(inode); + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_begin(&inode->i_size_seqcount); + ictx->_zero_point = zero_point; + write_seqcount_end(&inode->i_size_seqcount); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + ictx->_zero_point = zero_point; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in netfs_read_zero_point() to + * ensure changes related to inode size (such as page contents) are + * visible before we see the changed inode size. + */ + smp_store_release(&ictx->_zero_point, zero_point); +#endif +} + +/** + * netfs_read_sizes - Read remote_i_size and zero_point safely + * @inode: The inode to access + * @i_size: Where to return the local file size. + * @remote_i_size: Where to return the size of the file on the server + * @zero_point: Where to return the the point beyond which the server has no data + * + * Read remote_i_size and zero_point safely without the potential for tearing + * on 32-bit arches. + * + * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the + * i_size_read/write must be atomic with respect to the local cpu (unlike with + * preempt disabled), but they don't need to be atomic with respect to other + * cpus like in true SMP (so they need either to either locally disable irq + * around the read or for example on x86 they can be still implemented as a + * cmpxchg8b without the need of the lock prefix). For SMP compiles and 64bit + * archs it makes no difference if preempt is enabled or not. + */ +static inline void netfs_read_sizes(const struct inode *inode, + unsigned long long *i_size, + unsigned long long *remote_i_size, + unsigned long long *zero_point) +{ + const struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode); +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + unsigned int seq; + + do { + seq = read_seqcount_begin(&inode->i_size_seqcount); + *i_size = inode->i_size; + *remote_i_size = ictx->_remote_i_size; + *zero_point = ictx->_zero_point; + } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + *i_size = inode->i_size; + *remote_i_size = ictx->_remote_i_size; + *zero_point = ictx->_zero_point; + preempt_enable(); +#else + /* Pairs with smp_store_release() in i_size_write() */ + *i_size = smp_load_acquire(&inode->i_size); + /* Pairs with smp_store_release() in netfs_write_remote_i_size() */ + *remote_i_size = smp_load_acquire(&ictx->_remote_i_size); + /* Pairs with smp_store_release() in netfs_write_zero_point() */ + *zero_point = smp_load_acquire(&ictx->_zero_point); +#endif +} + +/* + * netfs_write_sizes - Set i_size, remote_i_size and zero_point safely + * @inode: The inode to access + * @i_size: The new value for the local size of the file + * @remote_i_size: The new value for the size of the file on the server + * @zero_point: The new value for the point beyond which the server has no data + * + * Set both remote_i_size and zero_point safely without the potential for + * tearing on 32-bit arches. + * + * Context: The caller must hold inode->i_lock. + * + * NOTE: unlike netfs_read_zero_point(), netfs_write_zero_point() does need + * locking around it (normally i_rwsem), otherwise on 32bit/SMP an update of + * i_size_seqcount can be lost, resulting in subsequent read calls spinning + * forever. + */ +static inline void netfs_write_sizes(struct inode *inode, + unsigned long long i_size, + unsigned long long remote_i_size, + unsigned long long zero_point) +{ + struct netfs_inode *ictx = netfs_inode(inode); + +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + write_seqcount_begin(&inode->i_size_seqcount); + inode->i_size = i_size; + ictx->_remote_i_size = remote_i_size; + ictx->_zero_point = zero_point; + write_seqcount_end(&inode->i_size_seqcount); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + inode->i_size = i_size; + ictx->_remote_i_size = remote_i_size; + ictx->_zero_point = zero_point; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in i_size_read(), + * netfs_read_remote_i_size() and netfs_read_zero_point() to ensure + * changes related to inode size (such as page contents) are visible + * before we see the changed inode size. + */ + smp_store_release(&inode->i_size, i_size); + smp_store_release(&ictx->_remote_i_size, remote_i_size); + smp_store_release(&ictx->_zero_point, zero_point); +#endif +} + /** * netfs_inode_init - Initialise a netfslib inode context * @ctx: The netfs inode to initialise @@ -488,8 +736,8 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, bool use_zero_point) { ctx->ops = ops; - ctx->remote_i_size = i_size_read(&ctx->inode); - ctx->zero_point = LLONG_MAX; + ctx->_remote_i_size = i_size_read(&ctx->inode); + ctx->_zero_point = LLONG_MAX; ctx->flags = 0; atomic_set(&ctx->io_count, 0); #if IS_ENABLED(CONFIG_FSCACHE) @@ -498,7 +746,7 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, mutex_init(&ctx->wb_lock); /* ->releasepage() drives zero_point */ if (use_zero_point) { - ctx->zero_point = ctx->remote_i_size; + ctx->_zero_point = ctx->_remote_i_size; mapping_set_release_always(ctx->inode.i_mapping); } } @@ -511,13 +759,40 @@ static inline void netfs_inode_init(struct netfs_inode *ctx, * * Inform the netfs lib that a file got resized so that it can adjust its state. */ -static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size, +static inline void netfs_resize_file(struct netfs_inode *ictx, + unsigned long long new_i_size, bool changed_on_server) { +#if BITS_PER_LONG==32 && defined(CONFIG_SMP) + struct inode *inode = &ictx->inode; + + preempt_disable(); + write_seqcount_begin(&inode->i_size_seqcount); if (changed_on_server) - ctx->remote_i_size = new_i_size; - if (new_i_size < ctx->zero_point) - ctx->zero_point = new_i_size; + ictx->_remote_i_size = new_i_size; + if (new_i_size < ictx->_zero_point) + ictx->_zero_point = new_i_size; + write_seqcount_end(&inode->i_size_seqcount); + preempt_enable(); +#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) + preempt_disable(); + if (changed_on_server) + ictx->_remote_i_size = new_i_size; + if (new_i_size < ictx->_zero_point) + ictx->_zero_point = new_i_size; + preempt_enable(); +#else + /* + * Pairs with smp_load_acquire() in netfs_read_remote_i_size and + * netfs_read_zero_point() to ensure changes related to inode size + * (such as page contents) are visible before we see the changed inode + * size. + */ + if (changed_on_server) + smp_store_release(&ictx->_remote_i_size, new_i_size); + if (new_i_size < ictx->_zero_point) + smp_store_release(&ictx->_zero_point, new_i_size); +#endif } /** diff --git a/include/linux/soc/airoha/airoha_offload.h b/include/linux/soc/airoha/airoha_offload.h index d01ef4a6b3d7..7589fccfeef6 100644 --- a/include/linux/soc/airoha/airoha_offload.h +++ b/include/linux/soc/airoha/airoha_offload.h @@ -71,9 +71,9 @@ static inline void airoha_ppe_dev_check_skb(struct airoha_ppe_dev *dev, #define NPU_RX1_DESC_NUM 512 /* CTRL */ -#define NPU_RX_DMA_DESC_LAST_MASK BIT(27) -#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(26, 14) -#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(13, 1) +#define NPU_RX_DMA_DESC_LAST_MASK BIT(29) +#define NPU_RX_DMA_DESC_LEN_MASK GENMASK(28, 15) +#define NPU_RX_DMA_DESC_CUR_LEN_MASK GENMASK(14, 1) #define NPU_RX_DMA_DESC_DONE_MASK BIT(0) /* INFO */ #define NPU_RX_DMA_PKT_COUNT_MASK GENMASK(31, 29) diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 69eed69f7f26..3faea66b1979 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -398,6 +398,7 @@ void baswap(bdaddr_t *dst, const bdaddr_t *src); struct bt_sock { struct sock sk; struct list_head accept_q; + spinlock_t accept_q_lock; /* protects accept_q */ struct sock *parent; unsigned long flags; void (*skb_msg_name)(struct sk_buff *, void *, int *); diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 02762ce73a0c..a02e569813d2 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1186,8 +1186,9 @@ struct netns_ipvs { struct timer_list dest_trash_timer; /* expiration timer */ struct mutex service_mutex; /* service reconfig */ struct rw_semaphore svc_resize_sem; /* svc_table resizing */ + struct rw_semaphore svc_replace_sem; /* svc_table replace */ struct delayed_work svc_resize_work; /* resize svc_table */ - atomic_t svc_table_changes;/* ++ on new table */ + atomic_t svc_table_changes;/* ++ on table changes */ /* Service counters */ atomic_t num_services[IP_VS_AF_MAX]; /* Services */ atomic_t fwm_services[IP_VS_AF_MAX]; /* Services */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 2dfee6d4258a..8860cc2175fc 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -489,11 +489,15 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { - unsigned int seq, hh_alen; + unsigned int seq, hh_alen = HH_DATA_ALIGN(ETH_HLEN); + int err; + + err = skb_cow_head(skb, hh_alen); + if (err) + return err; do { seq = read_seqbegin(&hh->hh_lock); - hh_alen = HH_DATA_ALIGN(ETH_HLEN); memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); } while (read_seqretry(&hh->hh_lock, seq)); return 0; diff --git a/include/net/net_shaper.h b/include/net/net_shaper.h index 5c3f49b52fe9..3939b816b001 100644 --- a/include/net/net_shaper.h +++ b/include/net/net_shaper.h @@ -53,6 +53,7 @@ struct net_shaper { /* private: */ u32 leaves; /* accounted only for NODE scope */ + bool valid; struct rcu_head rcu; }; diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index d17035d14d96..3978c3174cdb 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -14,6 +14,7 @@ struct nf_queue_entry { struct list_head list; struct rhash_head hash_node; struct sk_buff *skb; + struct net_device *skb_dev; unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) diff --git a/include/net/tcp.h b/include/net/tcp.h index ecbadcb3a744..98848db62894 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -65,8 +65,6 @@ static inline void tcp_orphan_count_dec(void) this_cpu_dec(tcp_orphan_count); } -DECLARE_PER_CPU(u32, tcp_tw_isn); - void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER L1_CACHE_ALIGN(128 + MAX_HEADER) @@ -1102,10 +1100,13 @@ struct tcp_skb_cb { __u32 seq; /* Starting sequence number */ __u32 end_seq; /* SEQ + FIN + SYN + datalen */ union { - /* Note : + /* Notes : + * tcp_tw_isn is used in input path only + * (isn chosen by tcp_timewait_state_process()) * tcp_gso_segs/size are used in write queue only, * cf tcp_skb_pcount()/tcp_skb_mss() */ + u32 tcp_tw_isn; struct { u16 tcp_gso_segs; u16 tcp_gso_size; diff --git a/include/trace/events/damon.h b/include/trace/events/damon.h index 24fc402ab3c8..7e25f4469b81 100644 --- a/include/trace/events/damon.h +++ b/include/trace/events/damon.h @@ -41,7 +41,7 @@ TRACE_EVENT(damos_stat_after_apply_interval, ), TP_printk("ctx_idx=%u scheme_idx=%u nr_tried=%lu sz_tried=%lu " - "nr_applied=%lu sz_tried=%lu sz_ops_filter_passed=%lu " + "nr_applied=%lu sz_applied=%lu sz_ops_filter_passed=%lu " "qt_exceeds=%lu nr_snapshots=%lu", __entry->context_idx, __entry->scheme_idx, __entry->nr_tried, __entry->sz_tried, diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h index 8c936fc575d5..082cb03c6131 100644 --- a/include/trace/events/netfs.h +++ b/include/trace/events/netfs.h @@ -177,7 +177,11 @@ EM(netfs_folio_is_uptodate, "mod-uptodate") \ EM(netfs_just_prefetch, "mod-prefetch") \ EM(netfs_whole_folio_modify, "mod-whole-f") \ + EM(netfs_whole_folio_modify_efault, "mod-whole-f!") \ + EM(netfs_whole_folio_modify_filled, "mod-whole-f+") \ + EM(netfs_whole_folio_modify_filled_efault, "mod-whole-f+!") \ EM(netfs_modify_and_clear, "mod-n-clear") \ + EM(netfs_modify_and_clear_rm_finfo, "mod-n-clear+") \ EM(netfs_streaming_write, "mod-streamw") \ EM(netfs_streaming_write_cont, "mod-streamw+") \ EM(netfs_flush_content, "flush") \ @@ -194,6 +198,10 @@ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \ EM(netfs_folio_trace_end_copy, "end-copy") \ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \ + EM(netfs_folio_trace_invalidate_all, "inval-all") \ + EM(netfs_folio_trace_invalidate_front, "inval-front") \ + EM(netfs_folio_trace_invalidate_middle, "inval-mid") \ + EM(netfs_folio_trace_invalidate_tail, "inval-tail") \ EM(netfs_folio_trace_kill, "kill") \ EM(netfs_folio_trace_kill_cc, "kill-cc") \ EM(netfs_folio_trace_kill_g, "kill-g") \ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 573f2df3a2c9..704a10de6670 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -71,6 +71,7 @@ EM(rxkad_abort_resp_unknown_tkt, "rxkad-resp-unknown-tkt") \ EM(rxkad_abort_resp_version, "rxkad-resp-version") \ /* RxGK security errors */ \ + EM(rxgk_abort_1_short_header, "rxgk1-short-hdr") \ EM(rxgk_abort_1_verify_mic_eproto, "rxgk1-vfy-mic-eproto") \ EM(rxgk_abort_2_decrypt_eproto, "rxgk2-dec-eproto") \ EM(rxgk_abort_2_short_data, "rxgk2-short-data") \ diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 0d01cd8c4b4a..7c2f7cc131f7 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -897,11 +897,9 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp { int cpu; - for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { - if (!(mask & (1UL << (cpu - snp->grplo)))) - continue; - srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay); - } + for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) + if ((mask & (1UL << (cpu - snp->grplo))) && rcu_cpu_beenfullyonline(cpu)) + srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay); } /* @@ -1322,7 +1320,9 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, */ idx = __srcu_read_lock_nmisafe(ssp); ss_state = smp_load_acquire(&ssp->srcu_sup->srcu_size_state); - if (ss_state < SRCU_SIZE_WAIT_CALL) + // If !rcu_cpu_beenfullyonline(), interrupts are still disabled, + // so no migration is possible in either direction from this CPU. + if (ss_state < SRCU_SIZE_WAIT_CALL || !rcu_cpu_beenfullyonline(raw_smp_processor_id())) sdp = per_cpu_ptr(ssp->sda, get_boot_cpu_id()); else sdp = raw_cpu_ptr(ssp->sda); diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 9b0834134cae..8d3d96e847d8 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -154,7 +154,8 @@ quiet_cmd_check_undefined = NM $< echo "Unexpected symbols in $<:" >&2; \ echo "$$undefsyms" >&2; \ false; \ - fi + fi; \ + touch $@ $(obj)/%.o.checked: $(obj)/%.o $(obj)/undefsyms_base.o FORCE $(call if_changed,check_undefined) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 5326924615a4..7b07d2004cc6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -7,6 +7,7 @@ #include #include #include +#include #include #include #include @@ -31,6 +32,7 @@ #include #include +#include #include #include #include @@ -559,6 +561,7 @@ struct trace_buffer { unsigned long range_addr_start; unsigned long range_addr_end; + struct notifier_block flush_nb; struct ring_buffer_meta *meta; @@ -2521,6 +2524,16 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer) kfree(cpu_buffer); } +/* Stop recording on a persistent buffer and flush cache if needed. */ +static int rb_flush_buffer_cb(struct notifier_block *nb, unsigned long event, void *data) +{ + struct trace_buffer *buffer = container_of(nb, struct trace_buffer, flush_nb); + + ring_buffer_record_off(buffer); + arch_ring_buffer_flush_range(buffer->range_addr_start, buffer->range_addr_end); + return NOTIFY_DONE; +} + static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, int order, unsigned long start, unsigned long end, @@ -2651,6 +2664,12 @@ static struct trace_buffer *alloc_buffer(unsigned long size, unsigned flags, mutex_init(&buffer->mutex); + /* Persistent ring buffer needs to flush cache before reboot. */ + if (start && end) { + buffer->flush_nb.notifier_call = rb_flush_buffer_cb; + atomic_notifier_chain_register(&panic_notifier_list, &buffer->flush_nb); + } + return_ptr(buffer); fail_free_buffers: @@ -2749,6 +2768,9 @@ ring_buffer_free(struct trace_buffer *buffer) { int cpu; + if (buffer->range_addr_start && buffer->range_addr_end) + atomic_notifier_chain_unregister(&panic_notifier_list, &buffer->flush_nb); + cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node); irq_work_sync(&buffer->irq_work.work); @@ -5407,6 +5429,7 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) iter->head_page = cpu_buffer->reader_page; iter->head = cpu_buffer->reader_page->read; iter->next_event = iter->head; + iter->missed_events = 0; iter->cache_reader_page = iter->head_page; iter->cache_read = cpu_buffer->read; @@ -6086,10 +6109,7 @@ ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts, */ bool ring_buffer_iter_dropped(struct ring_buffer_iter *iter) { - bool ret = iter->missed_events != 0; - - iter->missed_events = 0; - return ret; + return iter->missed_events != 0; } EXPORT_SYMBOL_GPL(ring_buffer_iter_dropped); @@ -6251,7 +6271,7 @@ void ring_buffer_iter_advance(struct ring_buffer_iter *iter) unsigned long flags; raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - + iter->missed_events = 0; rb_advance_iter(iter); raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); diff --git a/kernel/trace/simple_ring_buffer.c b/kernel/trace/simple_ring_buffer.c index 02af2297ae5a..f4642f5adda3 100644 --- a/kernel/trace/simple_ring_buffer.c +++ b/kernel/trace/simple_ring_buffer.c @@ -395,7 +395,6 @@ int simple_ring_buffer_init_mm(struct simple_rb_per_cpu *cpu_buffer, memset(cpu_buffer->meta, 0, sizeof(*cpu_buffer->meta)); cpu_buffer->meta->meta_page_size = PAGE_SIZE; - cpu_buffer->meta->nr_subbufs = cpu_buffer->nr_pages; /* The reader page is not part of the ring initially */ page = load_page(desc->page_va[0]); @@ -431,12 +430,13 @@ int simple_ring_buffer_init_mm(struct simple_rb_per_cpu *cpu_buffer, if (ret) { for (i--; i >= 0; i--) - unload_page((void *)desc->page_va[i]); + unload_page(bpages[i].page); unload_page(cpu_buffer->meta); return ret; } + cpu_buffer->meta->nr_subbufs = cpu_buffer->nr_pages; /* Close the ring */ bpage->link.next = &cpu_buffer->tail_page->link; cpu_buffer->tail_page->link.prev = &bpage->link; diff --git a/lib/tests/kunit_iov_iter.c b/lib/tests/kunit_iov_iter.c index 37bd6eb25896..f02f7b7aa796 100644 --- a/lib/tests/kunit_iov_iter.c +++ b/lib/tests/kunit_iov_iter.c @@ -1128,7 +1128,7 @@ static void __init iov_kunit_iter_to_sg_kvec(struct kunit *test) struct kvec kvec; size_t bufsize; - bufsize = 0x100000; + bufsize = 0x200000; iov_kunit_iter_to_sg_init(test, bufsize, false, &data); kvec.iov_base = data.buffer; @@ -1146,7 +1146,7 @@ static void __init iov_kunit_iter_to_sg_bvec(struct kunit *test) struct bio_vec *bvec; struct iov_iter iter; - bufsize = 0x100000; + bufsize = 0x200000; iov_kunit_iter_to_sg_init(test, bufsize, false, &data); bvec = kunit_kmalloc_array(test, data.npages, sizeof(*bvec), @@ -1173,7 +1173,7 @@ static void __init iov_kunit_iter_to_sg_folioq(struct kunit *test) struct iov_iter iter; size_t bufsize; - bufsize = 0x100000; + bufsize = 0x200000; iov_kunit_iter_to_sg_init(test, bufsize, false, &data); folioq = iov_kunit_create_folioq(test); @@ -1190,7 +1190,7 @@ static void __init iov_kunit_iter_to_sg_xarray(struct kunit *test) struct iov_iter iter; size_t bufsize; - bufsize = 0x100000; + bufsize = 0x200000; iov_kunit_iter_to_sg_init(test, bufsize, false, &data); xarray = iov_kunit_create_xarray(test); @@ -1206,7 +1206,7 @@ static void __init iov_kunit_iter_to_sg_ubuf(struct kunit *test) struct iov_iter iter; size_t bufsize; - bufsize = 0x100000; + bufsize = 0x200000; iov_kunit_iter_to_sg_init(test, bufsize, true, &data); iov_iter_ubuf(&iter, READ, data.ubuf, bufsize); diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 245d63808411..04746cbb3327 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -2594,6 +2594,7 @@ static int damon_sysfs_memcg_path_to_id(char *memcg_path, u64 *id) if (damon_sysfs_memcg_path_eq(memcg, path, memcg_path)) { *id = mem_cgroup_id(memcg); found = true; + mem_cgroup_iter_break(NULL, memcg); break; } } diff --git a/mm/memory.c b/mm/memory.c index ea6568571131..86a973119bd4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -612,6 +612,21 @@ static void print_bad_page_map(struct vm_area_struct *vma, dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); } + +static inline bool pgtable_level_has_pxx_special(enum pgtable_level level) +{ + switch (level) { + case PGTABLE_LEVEL_PTE: + return IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL); + case PGTABLE_LEVEL_PMD: + return IS_ENABLED(CONFIG_ARCH_SUPPORTS_PMD_PFNMAP); + case PGTABLE_LEVEL_PUD: + return IS_ENABLED(CONFIG_ARCH_SUPPORTS_PUD_PFNMAP); + default: + return false; + } +} + #define print_bad_pte(vma, addr, pte, page) \ print_bad_page_map(vma, addr, pte_val(pte), page, PGTABLE_LEVEL_PTE) @@ -684,7 +699,7 @@ static inline struct page *__vm_normal_page(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, bool special, unsigned long long entry, enum pgtable_level level) { - if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL)) { + if (pgtable_level_has_pxx_special(level)) { if (unlikely(special)) { #ifdef CONFIG_FIND_NORMAL_PAGE if (vma->vm_ops && vma->vm_ops->find_normal_page) @@ -699,8 +714,9 @@ static inline struct page *__vm_normal_page(struct vm_area_struct *vma, return NULL; } /* - * With CONFIG_ARCH_HAS_PTE_SPECIAL, any special page table - * mappings (incl. shared zero folios) are marked accordingly. + * With working pte_special()/pmd_special()..., any special page + * table mappings (incl. shared zero folios) are marked + * accordingly. */ } else { if (unlikely(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))) { @@ -1739,7 +1755,7 @@ static inline int zap_nonpresent_ptes(struct mmu_gather *tlb, * consider uffd-wp bit when zap. For more information, * see zap_install_uffd_wp_if_needed(). */ - WARN_ON_ONCE(!vma_is_anonymous(vma)); + WARN_ON_ONCE(!folio_test_anon(folio)); rss[mm_counter(folio)]--; folio_remove_rmap_pte(folio, page, vma); folio_put(folio); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 2a943ec57c85..40c7915dabe0 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1422,6 +1422,8 @@ static void remove_memory_blocks_and_altmaps(u64 start, u64 size) altmap = mem->altmap; mem->altmap = NULL; + /* drop the ref. we got via find_memory_block() */ + put_device(&mem->dev); remove_memory_block_devices(cur_start, memblock_size); diff --git a/mm/migrate_device.c b/mm/migrate_device.c index fbfe5715f635..ab49d4dcdb60 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -850,7 +850,7 @@ static int migrate_vma_insert_huge_pmd_page(struct migrate_vma *migrate, ptl = pmd_lock(vma->vm_mm, pmdp); csa_ret = check_stable_address_space(vma->vm_mm); if (csa_ret) - goto abort; + goto unlock_abort; /* * Check for userfaultfd but do not deliver the fault. Instead, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 227d58dc3de6..23c7298d3be2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1808,9 +1808,9 @@ static inline bool should_skip_init(gfp_t flags) inline void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags) { + const bool zero_tags = gfp_flags & __GFP_ZEROTAGS; bool init = !want_init_on_free() && want_init_on_alloc(gfp_flags) && !should_skip_init(gfp_flags); - bool zero_tags = init && (gfp_flags & __GFP_ZEROTAGS); int i; set_page_private(page, 0); @@ -1832,11 +1832,11 @@ inline void post_alloc_hook(struct page *page, unsigned int order, */ /* - * If memory tags should be zeroed - * (which happens only when memory should be initialized as well). + * Clearing tags can efficiently clear the memory for us as well, if + * required. */ if (zero_tags) - init = !tag_clear_highpages(page, 1 << order); + init = tag_clear_highpages(page, 1 << order, /* clear_pages= */init); if (!should_skip_kasan_unpoison(gfp_flags) && kasan_unpoison_pages(page, order, init)) { diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index e7315c01a299..30493ea3c010 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -542,6 +542,11 @@ int aarp_send_ddp(struct net_device *dev, struct sk_buff *skb, struct ddpehdr *ddp = (struct ddpehdr *)skb->data; int ft = 2; + if (!at) { + kfree_skb(skb); + return NET_XMIT_DROP; + } + /* * Compressible ? * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 74ef7dc2b2f9..b8b1b997960a 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -224,6 +224,8 @@ static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) hard_iface->bat_iv.ogm_buff = NULL; mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); + + cancel_delayed_work_sync(&hard_iface->bat_iv.reschedule_work); } static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) @@ -536,8 +538,10 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet, * @if_incoming: interface where the packet was received * @if_outgoing: interface for which the retransmission should be considered * @own_packet: true if it is a self-generated ogm + * + * Return: whether forward packet was scheduled */ -static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, +static bool batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, int packet_len, unsigned long send_time, bool direct_link, struct batadv_hard_iface *if_incoming, @@ -561,13 +565,13 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, skb = netdev_alloc_skb_ip_align(NULL, skb_size); if (!skb) - return; + return false; forw_packet_aggr = batadv_forw_packet_alloc(if_incoming, if_outgoing, queue_left, bat_priv, skb); if (!forw_packet_aggr) { kfree_skb(skb); - return; + return false; } forw_packet_aggr->skb->priority = TC_PRIO_CONTROL; @@ -590,6 +594,8 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff, batadv_iv_send_outstanding_bat_ogm_packet); batadv_forw_packet_ogmv1_queue(bat_priv, forw_packet_aggr, send_time); + + return true; } /* aggregate a new packet into the existing ogm packet */ @@ -617,8 +623,10 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr, * @if_outgoing: interface for which the retransmission should be considered * @own_packet: true if it is a self-generated ogm * @send_time: timestamp (jiffies) when the packet is to be sent + * + * Return: whether forward packet was scheduled */ -static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, +static bool batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, unsigned char *packet_buff, int packet_len, struct batadv_hard_iface *if_incoming, @@ -670,14 +678,16 @@ static void batadv_iv_ogm_queue_add(struct batadv_priv *bat_priv, if (!own_packet && atomic_read(&bat_priv->aggregated_ogms)) send_time += max_aggregation_jiffies; - batadv_iv_ogm_aggregate_new(packet_buff, packet_len, - send_time, direct_link, - if_incoming, if_outgoing, - own_packet); + return batadv_iv_ogm_aggregate_new(packet_buff, packet_len, + send_time, direct_link, + if_incoming, if_outgoing, + own_packet); } else { batadv_iv_ogm_aggregate(forw_packet_aggr, packet_buff, packet_len, direct_link); spin_unlock_bh(&bat_priv->forw_bat_list_lock); + + return true; } } @@ -790,6 +800,9 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) u32 seqno; u16 tvlv_len = 0; unsigned long send_time; + bool reschedule = false; + bool scheduled; + int ret; lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); @@ -813,9 +826,15 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) * appended as it may alter the tt tvlv container */ batadv_tt_local_commit_changes(bat_priv); - tvlv_len = batadv_tvlv_container_ogm_append(bat_priv, ogm_buff, - ogm_buff_len, - BATADV_OGM_HLEN); + ret = batadv_tvlv_container_ogm_append(bat_priv, ogm_buff, + ogm_buff_len, + BATADV_OGM_HLEN); + if (ret < 0) { + reschedule = true; + goto out; + } + + tvlv_len = ret; } batadv_ogm_packet = (struct batadv_ogm_packet *)(*ogm_buff); @@ -834,8 +853,11 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) /* OGMs from secondary interfaces are only scheduled on their * respective interfaces. */ - batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len, - hard_iface, hard_iface, 1, send_time); + scheduled = batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, *ogm_buff_len, + hard_iface, hard_iface, 1, send_time); + if (!scheduled) + reschedule = true; + goto out; } @@ -847,15 +869,28 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) if (!kref_get_unless_zero(&tmp_hard_iface->refcount)) continue; - batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, - *ogm_buff_len, hard_iface, - tmp_hard_iface, 1, send_time); - + scheduled = batadv_iv_ogm_queue_add(bat_priv, *ogm_buff, + *ogm_buff_len, hard_iface, + tmp_hard_iface, 1, send_time); batadv_hardif_put(tmp_hard_iface); + + if (!scheduled && tmp_hard_iface == hard_iface) + reschedule = true; } rcu_read_unlock(); out: + if (reschedule) { + /* there was a failure scheduling the own forward packet. + * as result, the batadv_iv_send_outstanding_bat_ogm_packet() + * work item is no longer scheduled. it is therefore necessary + * to reschedule it manually + */ + queue_delayed_work(batadv_event_workqueue, + &hard_iface->bat_iv.reschedule_work, + msecs_to_jiffies(atomic_read(&bat_priv->orig_interval))); + } + batadv_hardif_put(primary_if); } @@ -870,6 +905,17 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } +static void batadv_iv_ogm_reschedule(struct work_struct *work) +{ + struct delayed_work *delayed_work = to_delayed_work(work); + struct batadv_hard_iface *hard_iface; + + hard_iface = container_of(delayed_work, + struct batadv_hard_iface, + bat_iv.reschedule_work); + batadv_iv_ogm_schedule(hard_iface); +} + /** * batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over interface * @orig_node: originator which reproadcasted the OGMs directly @@ -2262,6 +2308,8 @@ batadv_iv_ogm_neigh_is_sob(struct batadv_neigh_node *neigh1, static void batadv_iv_iface_enabled(struct batadv_hard_iface *hard_iface) { + INIT_DELAYED_WORK(&hard_iface->bat_iv.reschedule_work, batadv_iv_ogm_reschedule); + /* begin scheduling originator messages on that interface */ batadv_iv_ogm_schedule(hard_iface); } diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index e3870492dab7..d66ca77b1aaa 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -113,14 +113,14 @@ static void batadv_v_ogm_start_timer(struct batadv_priv *bat_priv) /** * batadv_v_ogm_send_to_if() - send a batman ogm using a given interface + * @bat_priv: the bat priv with all the mesh interface information * @skb: the OGM to send * @hard_iface: the interface to use to send the OGM */ -static void batadv_v_ogm_send_to_if(struct sk_buff *skb, +static void batadv_v_ogm_send_to_if(struct batadv_priv *bat_priv, + struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { - struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); - if (hard_iface->if_status != BATADV_IF_ACTIVE) { kfree_skb(skb); return; @@ -187,6 +187,7 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) /** * batadv_v_ogm_aggr_send() - flush & send aggregation queue + * @bat_priv: the bat priv with all the mesh interface information * @hard_iface: the interface with the aggregation queue to flush * * Aggregates all OGMv2 packets currently in the aggregation queue into a @@ -196,7 +197,8 @@ static void batadv_v_ogm_aggr_list_free(struct batadv_hard_iface *hard_iface) * * Caller needs to hold the hard_iface->bat_v.aggr_list.lock. */ -static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) +static void batadv_v_ogm_aggr_send(struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface) { unsigned int aggr_len = hard_iface->bat_v.aggr_len; struct sk_buff *skb_aggr; @@ -226,27 +228,32 @@ static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface) consume_skb(skb); } - batadv_v_ogm_send_to_if(skb_aggr, hard_iface); + batadv_v_ogm_send_to_if(bat_priv, skb_aggr, hard_iface); } /** * batadv_v_ogm_queue_on_if() - queue a batman ogm on a given interface + * @bat_priv: the bat priv with all the mesh interface information * @skb: the OGM to queue * @hard_iface: the interface to queue the OGM on */ -static void batadv_v_ogm_queue_on_if(struct sk_buff *skb, +static void batadv_v_ogm_queue_on_if(struct batadv_priv *bat_priv, + struct sk_buff *skb, struct batadv_hard_iface *hard_iface) { - struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface); + if (hard_iface->mesh_iface != bat_priv->mesh_iface) { + kfree_skb(skb); + return; + } if (!atomic_read(&bat_priv->aggregated_ogms)) { - batadv_v_ogm_send_to_if(skb, hard_iface); + batadv_v_ogm_send_to_if(bat_priv, skb, hard_iface); return; } spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); if (!batadv_v_ogm_queue_left(skb, hard_iface)) - batadv_v_ogm_aggr_send(hard_iface); + batadv_v_ogm_aggr_send(bat_priv, hard_iface); hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb); __skb_queue_tail(&hard_iface->bat_v.aggr_list, skb); @@ -262,10 +269,10 @@ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) struct batadv_hard_iface *hard_iface; struct batadv_ogm2_packet *ogm_packet; struct sk_buff *skb, *skb_tmp; - unsigned char *ogm_buff; + unsigned char **ogm_buff; struct list_head *iter; - int ogm_buff_len; - u16 tvlv_len = 0; + int *ogm_buff_len; + u16 tvlv_len; int ret; lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex); @@ -273,25 +280,27 @@ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) goto out; - ogm_buff = bat_priv->bat_v.ogm_buff; - ogm_buff_len = bat_priv->bat_v.ogm_buff_len; + ogm_buff = &bat_priv->bat_v.ogm_buff; + ogm_buff_len = &bat_priv->bat_v.ogm_buff_len; + /* tt changes have to be committed before the tvlv data is * appended as it may alter the tt tvlv container */ batadv_tt_local_commit_changes(bat_priv); - tvlv_len = batadv_tvlv_container_ogm_append(bat_priv, &ogm_buff, - &ogm_buff_len, - BATADV_OGM2_HLEN); + ret = batadv_tvlv_container_ogm_append(bat_priv, ogm_buff, + ogm_buff_len, + BATADV_OGM2_HLEN); + if (ret < 0) + goto reschedule; - bat_priv->bat_v.ogm_buff = ogm_buff; - bat_priv->bat_v.ogm_buff_len = ogm_buff_len; + tvlv_len = ret; - skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + ogm_buff_len); + skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + *ogm_buff_len); if (!skb) goto reschedule; skb_reserve(skb, ETH_HLEN); - skb_put_data(skb, ogm_buff, ogm_buff_len); + skb_put_data(skb, *ogm_buff, *ogm_buff_len); ogm_packet = (struct batadv_ogm2_packet *)skb->data; ogm_packet->seqno = htonl(atomic_read(&bat_priv->bat_v.ogm_seqno)); @@ -343,7 +352,7 @@ static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv) break; } - batadv_v_ogm_queue_on_if(skb_tmp, hard_iface); + batadv_v_ogm_queue_on_if(bat_priv, skb_tmp, hard_iface); batadv_hardif_put(hard_iface); } rcu_read_unlock(); @@ -383,12 +392,14 @@ void batadv_v_ogm_aggr_work(struct work_struct *work) { struct batadv_hard_iface_bat_v *batv; struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv; batv = container_of(work, struct batadv_hard_iface_bat_v, aggr_wq.work); hard_iface = container_of(batv, struct batadv_hard_iface, bat_v); + bat_priv = netdev_priv(hard_iface->mesh_iface); spin_lock_bh(&hard_iface->bat_v.aggr_list.lock); - batadv_v_ogm_aggr_send(hard_iface); + batadv_v_ogm_aggr_send(bat_priv, hard_iface); spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock); batadv_v_ogm_start_queue_timer(hard_iface); @@ -578,7 +589,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv, if_outgoing->net_dev->name, ntohl(ogm_forward->throughput), ogm_forward->ttl, if_incoming->net_dev->name); - batadv_v_ogm_queue_on_if(skb, if_outgoing); + batadv_v_ogm_queue_on_if(bat_priv, skb, if_outgoing); out: batadv_orig_ifinfo_put(orig_ifinfo); diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index cec11f1251d6..ffe854018bd3 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -356,12 +356,14 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac, sizeof(local_claim_dest)); local_claim_dest.type = claimtype; - mesh_iface = primary_if->mesh_iface; + mesh_iface = READ_ONCE(primary_if->mesh_iface); + if (!mesh_iface) + goto out; skb = arp_create(ARPOP_REPLY, ETH_P_ARP, /* IP DST: 0.0.0.0 */ zeroip, - primary_if->mesh_iface, + mesh_iface, /* IP SRC: 0.0.0.0 */ zeroip, /* Ethernet DST: Broadcast */ @@ -514,8 +516,8 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, entry->crc = BATADV_BLA_CRC_INIT; entry->bat_priv = bat_priv; spin_lock_init(&entry->crc_lock); - atomic_set(&entry->request_sent, 0); - atomic_set(&entry->wait_periods, 0); + entry->state = BATADV_BLA_BACKBONE_GW_SYNCED; + entry->wait_periods = 0; ether_addr_copy(entry->orig, orig); INIT_WORK(&entry->report_work, batadv_bla_loopdetect_report); kref_init(&entry->refcount); @@ -544,9 +546,13 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig, batadv_bla_send_announce(bat_priv, entry); /* this will be decreased in the worker thread */ - atomic_inc(&entry->request_sent); - atomic_set(&entry->wait_periods, BATADV_BLA_WAIT_PERIODS); - atomic_inc(&bat_priv->bla.num_requests); + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (entry->state == BATADV_BLA_BACKBONE_GW_SYNCED) { + entry->state = BATADV_BLA_BACKBONE_GW_UNSYNCED; + entry->wait_periods = BATADV_BLA_WAIT_PERIODS; + atomic_inc(&bat_priv->bla.num_requests); + } + spin_unlock_bh(&bat_priv->bla.num_requests_lock); } return entry; @@ -649,10 +655,12 @@ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw) backbone_gw->vid, BATADV_CLAIM_TYPE_REQUEST); /* no local broadcasts should be sent or received, for now. */ - if (!atomic_read(&backbone_gw->request_sent)) { + spin_lock_bh(&backbone_gw->bat_priv->bla.num_requests_lock); + if (backbone_gw->state == BATADV_BLA_BACKBONE_GW_SYNCED) { + backbone_gw->state = BATADV_BLA_BACKBONE_GW_UNSYNCED; atomic_inc(&backbone_gw->bat_priv->bla.num_requests); - atomic_set(&backbone_gw->request_sent, 1); } + spin_unlock_bh(&backbone_gw->bat_priv->bla.num_requests_lock); } /** @@ -873,10 +881,12 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, /* if we have sent a request and the crc was OK, * we can allow traffic again. */ - if (atomic_read(&backbone_gw->request_sent)) { + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (backbone_gw->state == BATADV_BLA_BACKBONE_GW_UNSYNCED) { + backbone_gw->state = BATADV_BLA_BACKBONE_GW_SYNCED; atomic_dec(&backbone_gw->bat_priv->bla.num_requests); - atomic_set(&backbone_gw->request_sent, 0); } + spin_unlock_bh(&bat_priv->bla.num_requests_lock); } batadv_backbone_gw_put(backbone_gw); @@ -1224,6 +1234,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) struct hlist_head *head; struct batadv_hashtable *hash; spinlock_t *list_lock; /* protects write access to the hash lists */ + bool purged; int i; hash = bat_priv->bla.backbone_hash; @@ -1234,30 +1245,49 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now) head = &hash->table[i]; list_lock = &hash->list_locks[i]; - spin_lock_bh(list_lock); - hlist_for_each_entry_safe(backbone_gw, node_tmp, - head, hash_entry) { - if (now) - goto purge_now; - if (!batadv_has_timed_out(backbone_gw->lasttime, - BATADV_BLA_BACKBONE_TIMEOUT)) - continue; + do { + purged = false; - batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, - "%s(): backbone gw %pM timed out\n", - __func__, backbone_gw->orig); + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(backbone_gw, node_tmp, + head, hash_entry) { + if (now) + goto purge_now; + if (!batadv_has_timed_out(backbone_gw->lasttime, + BATADV_BLA_BACKBONE_TIMEOUT)) + continue; + + batadv_dbg(BATADV_DBG_BLA, backbone_gw->bat_priv, + "%s(): backbone gw %pM timed out\n", + __func__, backbone_gw->orig); purge_now: - /* don't wait for the pending request anymore */ - if (atomic_read(&backbone_gw->request_sent)) - atomic_dec(&bat_priv->bla.num_requests); + purged = true; - batadv_bla_del_backbone_claims(backbone_gw); + /* don't wait for the pending request anymore */ + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (backbone_gw->state == BATADV_BLA_BACKBONE_GW_UNSYNCED) + atomic_dec(&bat_priv->bla.num_requests); - hlist_del_rcu(&backbone_gw->hash_entry); - batadv_backbone_gw_put(backbone_gw); - } - spin_unlock_bh(list_lock); + backbone_gw->state = BATADV_BLA_BACKBONE_GW_STOPPED; + spin_unlock_bh(&bat_priv->bla.num_requests_lock); + + batadv_bla_del_backbone_claims(backbone_gw); + + hlist_del_rcu(&backbone_gw->hash_entry); + break; + } + spin_unlock_bh(list_lock); + + if (purged) { + /* reference for pending report_work */ + if (cancel_work_sync(&backbone_gw->report_work)) + batadv_backbone_gw_put(backbone_gw); + + /* reference for hash_entry */ + batadv_backbone_gw_put(backbone_gw); + } + } while (purged); } } @@ -1492,7 +1522,7 @@ static void batadv_bla_periodic_work(struct work_struct *work) batadv_bla_send_loopdetect(bat_priv, backbone_gw); - /* request_sent is only set after creation to avoid + /* state is only set to unsynced after creation to avoid * problems when we are not yet known as backbone gw * in the backbone. * @@ -1501,14 +1531,21 @@ static void batadv_bla_periodic_work(struct work_struct *work) * some grace time. */ - if (atomic_read(&backbone_gw->request_sent) == 0) - continue; + spin_lock_bh(&bat_priv->bla.num_requests_lock); + if (backbone_gw->state != BATADV_BLA_BACKBONE_GW_UNSYNCED) + goto unlock_next; - if (!atomic_dec_and_test(&backbone_gw->wait_periods)) - continue; + if (backbone_gw->wait_periods > 0) + backbone_gw->wait_periods--; + if (backbone_gw->wait_periods > 0) + goto unlock_next; + + backbone_gw->state = BATADV_BLA_BACKBONE_GW_SYNCED; atomic_dec(&backbone_gw->bat_priv->bla.num_requests); - atomic_set(&backbone_gw->request_sent, 0); + +unlock_next: + spin_unlock_bh(&bat_priv->bla.num_requests_lock); } rcu_read_unlock(); } diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index 3efc4cf50b46..0a8bd95e2f99 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -696,6 +696,9 @@ static bool batadv_dat_forward_data(struct batadv_priv *bat_priv, goto free_orig; tmp_skb = pskb_copy_for_clone(skb, GFP_ATOMIC); + if (!tmp_skb) + goto free_neigh; + if (!batadv_send_skb_prepare_unicast_4addr(bat_priv, tmp_skb, cand[i].orig_node, packet_subtype)) { diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index f4e45cc25816..e9553db42349 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -80,9 +81,9 @@ void batadv_frag_purge_orig(struct batadv_orig_node *orig_node, * * Return: the maximum size of payload that can be fragmented. */ -static int batadv_frag_size_limit(void) +static size_t batadv_frag_size_limit(void) { - int limit = BATADV_FRAG_MAX_FRAG_SIZE; + size_t limit = BATADV_FRAG_MAX_FRAG_SIZE; limit -= sizeof(struct batadv_frag_packet); limit *= BATADV_FRAG_MAX_FRAGMENTS; @@ -143,7 +144,9 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, struct batadv_frag_packet *frag_packet; u8 bucket; u16 seqno, hdr_size = sizeof(struct batadv_frag_packet); + bool overflow = false; bool ret = false; + size_t data_len; /* Linearize packet to avoid linearizing 16 packets in a row when doing * the later merge. Non-linear merge should be added to remove this @@ -153,6 +156,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, goto err; frag_packet = (struct batadv_frag_packet *)skb->data; + data_len = skb->len - hdr_size; seqno = ntohs(frag_packet->seqno); bucket = seqno % BATADV_FRAG_BUFFER_COUNT; @@ -171,7 +175,7 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, spin_lock_bh(&chain->lock); if (batadv_frag_init_chain(chain, seqno)) { hlist_add_head(&frag_entry_new->list, &chain->fragment_list); - chain->size = skb->len - hdr_size; + chain->size = data_len; chain->timestamp = jiffies; chain->total_size = ntohs(frag_packet->total_size); ret = true; @@ -188,7 +192,11 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, if (frag_entry_curr->no < frag_entry_new->no) { hlist_add_before(&frag_entry_new->list, &frag_entry_curr->list); - chain->size += skb->len - hdr_size; + + if (check_add_overflow(chain->size, data_len, + &chain->size)) + overflow = true; + chain->timestamp = jiffies; ret = true; goto out; @@ -201,13 +209,16 @@ static bool batadv_frag_insert_packet(struct batadv_orig_node *orig_node, /* Reached the end of the list, so insert after 'frag_entry_last'. */ if (likely(frag_entry_last)) { hlist_add_behind(&frag_entry_new->list, &frag_entry_last->list); - chain->size += skb->len - hdr_size; + + if (check_add_overflow(chain->size, data_len, &chain->size)) + overflow = true; + chain->timestamp = jiffies; ret = true; } out: - if (chain->size > batadv_frag_size_limit() || + if (overflow || chain->size > batadv_frag_size_limit() || chain->total_size != ntohs(frag_packet->total_size) || chain->total_size > batadv_frag_size_limit()) { /* Clear chain if total size of either the list or the packet @@ -293,6 +304,31 @@ batadv_frag_merge_packets(struct hlist_head *chain) return skb_out; } +/** + * batadv_skb_is_frag() - check if newly merged skb contains unicast fragment + * @skb: newly merged skb + * + * Return: if newly merged skb is of type BATADV_UNICAST_FRAG + */ +static bool batadv_skb_is_frag(struct sk_buff *skb) +{ + struct batadv_ogm_packet *batadv_ogm_packet; + + /* packet should hold at least type and version */ + if (unlikely(!pskb_may_pull(skb, 2))) + return false; + + batadv_ogm_packet = (struct batadv_ogm_packet *)skb->data; + + if (batadv_ogm_packet->version != BATADV_COMPAT_VERSION) + return false; + + if (batadv_ogm_packet->packet_type != BATADV_UNICAST_FRAG) + return false; + + return true; +} + /** * batadv_frag_skb_buffer() - buffer fragment for later merge * @skb: skb to buffer @@ -326,6 +362,16 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb, if (!skb_out) goto out_err; + /* fragment in fragment is not allowed. otherwise it is possible + * to exhaust the stack when receiving a matryoshka-style + * "fragments in a fragment packet" + */ + if (batadv_skb_is_frag(skb_out)) { + kfree_skb(skb_out); + skb_out = NULL; + goto out_err; + } + out: ret = true; out_err: diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 51e9c081a2a4..a9d0346e8332 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -478,10 +478,14 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv, */ void batadv_gw_node_free(struct batadv_priv *bat_priv) { + struct batadv_gw_node *curr_gw; struct batadv_gw_node *gw_node; struct hlist_node *node_tmp; spin_lock_bh(&bat_priv->gw.list_lock); + curr_gw = rcu_replace_pointer(bat_priv->gw.curr_gw, NULL, true); + batadv_gw_node_put(curr_gw); + hlist_for_each_entry_safe(gw_node, node_tmp, &bat_priv->gw.gateway_list, list) { hlist_del_init_rcu(&gw_node->list); diff --git a/net/batman-adv/mesh-interface.c b/net/batman-adv/mesh-interface.c index 56ca1c1b83f2..e7aa45bc6b7a 100644 --- a/net/batman-adv/mesh-interface.c +++ b/net/batman-adv/mesh-interface.c @@ -787,6 +787,7 @@ static int batadv_meshif_init_late(struct net_device *dev) atomic_set(&bat_priv->tt.ogm_append_cnt, 0); #ifdef CONFIG_BATMAN_ADV_BLA atomic_set(&bat_priv->bla.num_requests, 0); + spin_lock_init(&bat_priv->bla.num_requests_lock); #endif atomic_set(&bat_priv->tp_num, 0); diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index b3468ccab535..ad4921b659d9 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -835,8 +835,6 @@ static void batadv_orig_node_free_rcu(struct rcu_head *rcu) orig_node = container_of(rcu, struct batadv_orig_node, rcu); - batadv_mcast_purge_orig(orig_node); - batadv_frag_purge_orig(orig_node, NULL); kfree(orig_node->tt_buff); @@ -887,6 +885,8 @@ void batadv_orig_node_release(struct kref *ref) } spin_unlock_bh(&orig_node->vlan_list_lock); + batadv_mcast_purge_orig(orig_node); + call_rcu(&orig_node->rcu, batadv_orig_node_free_rcu); } diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 066c76113fc4..0fc4ca78e84e 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -8,6 +8,7 @@ #include "main.h" #include +#include #include #include #include @@ -254,6 +255,7 @@ static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason, * batadv_tp_list_find() - find a tp_vars object in the global list * @bat_priv: the bat priv with all the mesh interface information * @dst: the other endpoint MAC address to look for + * @role: role of the session * * Look for a tp_vars object matching dst as end_point and return it after * having increment the refcounter. Return NULL is not found @@ -261,7 +263,8 @@ static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason, * Return: matching tp_vars or NULL when no tp_vars with @dst was found */ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, - const u8 *dst) + const u8 *dst, + enum batadv_tp_meter_role role) { struct batadv_tp_vars *pos, *tp_vars = NULL; @@ -270,6 +273,9 @@ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, if (!batadv_compare_eth(pos->other_end, dst)) continue; + if (pos->role != role) + continue; + /* most of the time this function is invoked during the normal * process..it makes sens to pay more when the session is * finished and to speed the process up during the measurement @@ -285,12 +291,33 @@ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, return tp_vars; } +/** + * batadv_tp_list_active() - check if session from/to destination is ongoing + * @bat_priv: the bat priv with all the mesh interface information + * @dst: the other endpoint MAC address to look for + * + * Return: if matching session with @dst was found + */ +static bool batadv_tp_list_active(struct batadv_priv *bat_priv, const u8 *dst) + __must_hold(&bat_priv->tp_list_lock) +{ + struct batadv_tp_vars *tp_vars; + + hlist_for_each_entry_rcu(tp_vars, &bat_priv->tp_list, list) { + if (batadv_compare_eth(tp_vars->other_end, dst)) + return true; + } + + return false; +} + /** * batadv_tp_list_find_session() - find tp_vars session object in the global * list * @bat_priv: the bat priv with all the mesh interface information * @dst: the other endpoint MAC address to look for * @session: session identifier + * @role: role of the session * * Look for a tp_vars object matching dst as end_point, session as tp meter * session and return it after having increment the refcounter. Return NULL @@ -300,7 +327,7 @@ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv, */ static struct batadv_tp_vars * batadv_tp_list_find_session(struct batadv_priv *bat_priv, const u8 *dst, - const u8 *session) + const u8 *session, enum batadv_tp_meter_role role) { struct batadv_tp_vars *pos, *tp_vars = NULL; @@ -312,6 +339,9 @@ batadv_tp_list_find_session(struct batadv_priv *bat_priv, const u8 *dst, if (memcmp(pos->session, session, sizeof(pos->session)) != 0) continue; + if (pos->role != role) + continue; + /* most of the time this function is invoked during the normal * process..it makes sense to pay more when the session is * finished and to speed the process up during the measurement @@ -400,13 +430,7 @@ static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars) batadv_tp_list_detach(tp_vars); /* kill the timer and remove its reference */ - timer_delete_sync(&tp_vars->timer); - /* the worker might have rearmed itself therefore we kill it again. Note - * that if the worker should run again before invoking the following - * timer_delete(), it would not re-arm itself once again because the status - * is OFF now - */ - timer_delete(&tp_vars->timer); + timer_shutdown_sync(&tp_vars->timer); batadv_tp_vars_put(tp_vars); } @@ -418,11 +442,14 @@ static void batadv_tp_sender_cleanup(struct batadv_tp_vars *tp_vars) static void batadv_tp_sender_end(struct batadv_priv *bat_priv, struct batadv_tp_vars *tp_vars) { + enum batadv_tp_meter_reason reason; u32 session_cookie; + reason = atomic_read(&tp_vars->send_result); + batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Test towards %pM finished..shutting down (reason=%d)\n", - tp_vars->other_end, tp_vars->reason); + tp_vars->other_end, reason); batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Last timing stats: SRTT=%ums RTTVAR=%ums RTO=%ums\n", @@ -435,7 +462,7 @@ static void batadv_tp_sender_end(struct batadv_priv *bat_priv, session_cookie = batadv_tp_session_cookie(tp_vars->session, tp_vars->icmp_uid); - batadv_tp_batctl_notify(tp_vars->reason, + batadv_tp_batctl_notify(reason, tp_vars->other_end, bat_priv, tp_vars->start_time, @@ -451,10 +478,18 @@ static void batadv_tp_sender_end(struct batadv_priv *bat_priv, static void batadv_tp_sender_shutdown(struct batadv_tp_vars *tp_vars, enum batadv_tp_meter_reason reason) { - if (!atomic_dec_and_test(&tp_vars->sending)) - return; + atomic_cmpxchg(&tp_vars->send_result, 0, reason); +} - tp_vars->reason = reason; +/** + * batadv_tp_sender_stopped() - check if tp session was stopped with reason + * @tp_vars: the private data of the current TP meter session + * + * Return: whether stop reason was found + */ +static bool batadv_tp_sender_stopped(struct batadv_tp_vars *tp_vars) +{ + return atomic_read(&tp_vars->send_result) != 0; } /** @@ -484,7 +519,7 @@ static void batadv_tp_reset_sender_timer(struct batadv_tp_vars *tp_vars) /* most of the time this function is invoked while normal packet * reception... */ - if (unlikely(atomic_read(&tp_vars->sending) == 0)) + if (unlikely(batadv_tp_sender_stopped(tp_vars))) /* timer ref will be dropped in batadv_tp_sender_cleanup */ return; @@ -504,7 +539,7 @@ static void batadv_tp_sender_timeout(struct timer_list *t) struct batadv_tp_vars *tp_vars = timer_container_of(tp_vars, t, timer); struct batadv_priv *bat_priv = tp_vars->bat_priv; - if (atomic_read(&tp_vars->sending) == 0) + if (batadv_tp_sender_stopped(tp_vars)) return; /* if the user waited long enough...shutdown the test */ @@ -659,11 +694,11 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv, /* find the tp_vars */ tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, - icmp->session); + icmp->session, BATADV_TP_SENDER); if (unlikely(!tp_vars)) return; - if (unlikely(atomic_read(&tp_vars->sending) == 0)) + if (unlikely(batadv_tp_sender_stopped(tp_vars))) goto out; /* old ACK? silently drop it.. */ @@ -829,21 +864,21 @@ static int batadv_tp_send(void *arg) if (unlikely(tp_vars->role != BATADV_TP_SENDER)) { err = BATADV_TP_REASON_DST_UNREACHABLE; - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); goto out; } orig_node = batadv_orig_hash_find(bat_priv, tp_vars->other_end); if (unlikely(!orig_node)) { err = BATADV_TP_REASON_DST_UNREACHABLE; - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); goto out; } primary_if = batadv_primary_if_get_selected(bat_priv); if (unlikely(!primary_if)) { err = BATADV_TP_REASON_DST_UNREACHABLE; - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); goto out; } @@ -862,7 +897,7 @@ static int batadv_tp_send(void *arg) queue_delayed_work(batadv_event_workqueue, &tp_vars->finish_work, msecs_to_jiffies(tp_vars->test_length)); - while (atomic_read(&tp_vars->sending) != 0) { + while (!batadv_tp_sender_stopped(tp_vars)) { if (unlikely(!batadv_tp_avail(tp_vars, payload_len))) { batadv_tp_wait_available(tp_vars, payload_len); continue; @@ -885,8 +920,7 @@ static int batadv_tp_send(void *arg) "Meter: %s() cannot send packets (%d)\n", __func__, err); /* ensure nobody else tries to stop the thread now */ - if (atomic_dec_and_test(&tp_vars->sending)) - tp_vars->reason = err; + batadv_tp_sender_shutdown(tp_vars, err); break; } @@ -972,10 +1006,8 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, return; } - tp_vars = batadv_tp_list_find(bat_priv, dst); - if (tp_vars) { + if (batadv_tp_list_active(bat_priv, dst)) { spin_unlock_bh(&bat_priv->tp_list_lock); - batadv_tp_vars_put(tp_vars); batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: test to or from the same node already ongoing, aborting\n"); batadv_tp_batctl_error_notify(BATADV_TP_REASON_ALREADY_ONGOING, @@ -1008,7 +1040,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst, ether_addr_copy(tp_vars->other_end, dst); kref_init(&tp_vars->refcount); tp_vars->role = BATADV_TP_SENDER; - atomic_set(&tp_vars->sending, 1); + atomic_set(&tp_vars->send_result, 0); memcpy(tp_vars->session, session_id, sizeof(session_id)); tp_vars->icmp_uid = icmp_uid; @@ -1096,16 +1128,16 @@ void batadv_tp_stop(struct batadv_priv *bat_priv, const u8 *dst, if (!orig_node) return; - tp_vars = batadv_tp_list_find(bat_priv, orig_node->orig); + tp_vars = batadv_tp_list_find(bat_priv, orig_node->orig, BATADV_TP_SENDER); if (!tp_vars) { batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Meter: trying to interrupt an already over connection\n"); - goto out; + goto out_put_orig_node; } batadv_tp_sender_shutdown(tp_vars, return_value); batadv_tp_vars_put(tp_vars); -out: +out_put_orig_node: batadv_orig_node_put(orig_node); } @@ -1156,6 +1188,9 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t) spin_unlock_bh(&tp_vars->unacked_lock); /* drop reference of timer */ + if (WARN_ON(atomic_xchg(&tp_vars->receiving, 0) != 1)) + return; + batadv_tp_vars_put(tp_vars); } @@ -1356,7 +1391,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, goto out_unlock; tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, - icmp->session); + icmp->session, BATADV_TP_RECEIVER); if (tp_vars) goto out_unlock; @@ -1374,6 +1409,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv, ether_addr_copy(tp_vars->other_end, icmp->orig); tp_vars->role = BATADV_TP_RECEIVER; + atomic_set(&tp_vars->receiving, 1); memcpy(tp_vars->session, icmp->session, sizeof(tp_vars->session)); tp_vars->last_recv = BATADV_TP_FIRST_SEQ; tp_vars->bat_priv = bat_priv; @@ -1426,7 +1462,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, } } else { tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig, - icmp->session); + icmp->session, BATADV_TP_RECEIVER); if (!tp_vars) { batadv_dbg(BATADV_DBG_TP_METER, bat_priv, "Unexpected packet from %pM!\n", @@ -1435,13 +1471,6 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv, } } - if (unlikely(tp_vars->role != BATADV_TP_RECEIVER)) { - batadv_dbg(BATADV_DBG_TP_METER, bat_priv, - "Meter: dropping packet: not expected (role=%u)\n", - tp_vars->role); - goto out; - } - tp_vars->last_recv_time = jiffies; /* if the packet is a duplicate, it may be the case that an ACK has been @@ -1546,8 +1575,12 @@ void batadv_tp_stop_all(struct batadv_priv *bat_priv) break; case BATADV_TP_RECEIVER: batadv_tp_list_detach(tp_var); - if (timer_shutdown_sync(&tp_var->timer)) - batadv_tp_vars_put(tp_var); + timer_shutdown_sync(&tp_var->timer); + + if (atomic_xchg(&tp_var->receiving, 0) != 1) + break; + + batadv_tp_vars_put(tp_var); break; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 05cddcf994f6..9f6e67771ffa 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -797,24 +797,33 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, s32 *tt_len) { u16 num_vlan = 0; - u16 num_entries = 0; u16 tvlv_len = 0; unsigned int change_offset; struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_orig_node_vlan *vlan; + u16 total_entries = 0; u8 *tt_change_ptr; + int vlan_entries; + u16 sum_entries; spin_lock_bh(&orig_node->vlan_list_lock); hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + + if (check_add_overflow(vlan_entries, total_entries, &sum_entries)) { + *tt_len = 0; + goto out; + } + + total_entries = sum_entries; num_vlan++; - num_entries += atomic_read(&vlan->tt.num_entries); } change_offset = struct_size(*tt_data, vlan_data, num_vlan); /* if tt_len is negative, allocate the space needed by the full table */ if (*tt_len < 0) - *tt_len = batadv_tt_len(num_entries); + *tt_len = batadv_tt_len(total_entries); if (change_offset > U16_MAX || *tt_len > U16_MAX - change_offset) { *tt_len = 0; @@ -835,14 +844,26 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (*tt_data)->vlan_data; + num_vlan = 0; hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { + vlan_entries = atomic_read(&vlan->tt.num_entries); + if (vlan_entries < 1) + continue; + tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); tt_vlan->reserved = 0; tt_vlan++; + num_vlan++; } + /* recalculate in case number of VLANs reduced */ + change_offset = struct_size(*tt_data, vlan_data, num_vlan); + tvlv_len = *tt_len + change_offset; + + (*tt_data)->num_vlan = htons(num_vlan); + tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; @@ -877,21 +898,25 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, { struct batadv_tvlv_tt_vlan_data *tt_vlan; struct batadv_meshif_vlan *vlan; + size_t change_offset; u16 num_vlan = 0; - u16 vlan_entries = 0; u16 total_entries = 0; u16 tvlv_len; u8 *tt_change_ptr; - int change_offset; + int vlan_entries; + u16 sum_entries; spin_lock_bh(&bat_priv->meshif_vlan_list_lock); hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); - if (vlan_entries < 1) - continue; + if (check_add_overflow(vlan_entries, total_entries, &sum_entries)) { + tvlv_len = 0; + goto out; + } + + total_entries = sum_entries; num_vlan++; - total_entries += vlan_entries; } change_offset = struct_size(*tt_data, vlan_data, num_vlan); @@ -900,8 +925,10 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, if (*tt_len < 0) *tt_len = batadv_tt_len(total_entries); - tvlv_len = *tt_len; - tvlv_len += change_offset; + if (check_add_overflow(*tt_len, change_offset, &tvlv_len)) { + tvlv_len = 0; + goto out; + } *tt_data = kmalloc(tvlv_len, GFP_ATOMIC); if (!*tt_data) { @@ -914,6 +941,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, (*tt_data)->num_vlan = htons(num_vlan); tt_vlan = (*tt_data)->vlan_data; + num_vlan = 0; hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) { vlan_entries = atomic_read(&vlan->tt.num_entries); if (vlan_entries < 1) @@ -924,8 +952,15 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, tt_vlan->reserved = 0; tt_vlan++; + num_vlan++; } + /* recalculate in case number of VLANs reduced */ + change_offset = struct_size(*tt_data, vlan_data, num_vlan); + tvlv_len = *tt_len + change_offset; + + (*tt_data)->num_vlan = htons(num_vlan); + tt_change_ptr = (u8 *)*tt_data + change_offset; *tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr; diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 8129a3f9c44d..cc6ac580c620 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -8,10 +8,12 @@ #include #include +#include #include #include #include #include +#include #include #include #include @@ -159,10 +161,10 @@ batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version) * * Return: size of all currently registered tvlv containers in bytes. */ -static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) +static size_t batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) { struct batadv_tvlv_container *tvlv; - u16 tvlv_len = 0; + size_t tvlv_len = 0; lockdep_assert_held(&bat_priv->tvlv.container_list_lock); @@ -306,26 +308,35 @@ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff, * The ogm packet might be enlarged or shrunk depending on the current size * and the size of the to-be-appended tvlv containers. * - * Return: size of all appended tvlv containers in bytes. + * Return: size of all appended tvlv containers in bytes (max U16_MAX), negative + * if operation failed */ -u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, +int batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, unsigned char **packet_buff, int *packet_buff_len, int packet_min_len) { struct batadv_tvlv_container *tvlv; struct batadv_tvlv_hdr *tvlv_hdr; - u16 tvlv_value_len; + size_t tvlv_value_len; void *tvlv_value; + int tvlv_len_ret; bool ret; spin_lock_bh(&bat_priv->tvlv.container_list_lock); tvlv_value_len = batadv_tvlv_container_list_size(bat_priv); + if (tvlv_value_len > U16_MAX) { + tvlv_len_ret = -E2BIG; + goto end; + } ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len, packet_min_len, tvlv_value_len); - - if (!ret) + if (!ret) { + tvlv_len_ret = -ENOMEM; goto end; + } + + tvlv_len_ret = tvlv_value_len; if (!tvlv_value_len) goto end; @@ -344,7 +355,8 @@ u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, end: spin_unlock_bh(&bat_priv->tvlv.container_list_lock); - return tvlv_value_len; + + return tvlv_len_ret; } /** diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index e5697230d991..f96f6b3f44a0 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -16,7 +16,7 @@ void batadv_tvlv_container_register(struct batadv_priv *bat_priv, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len); -u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, +int batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, unsigned char **packet_buff, int *packet_buff_len, int packet_min_len); void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index daa06f421154..a01ee46d97f3 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -83,6 +83,9 @@ struct batadv_hard_iface_bat_iv { /** @ogm_seqno: OGM sequence number - used to identify each OGM */ atomic_t ogm_seqno; + /** @reschedule_work: recover OGM schedule after schedule error */ + struct delayed_work reschedule_work; + /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ struct mutex ogm_buff_mutex; }; @@ -301,7 +304,7 @@ struct batadv_frag_table_entry { u16 seqno; /** @size: accumulated size of packets in list */ - u16 size; + size_t size; /** @total_size: expected size of the assembled packet */ u16 total_size; @@ -452,7 +455,7 @@ struct batadv_orig_node { * @tt_buff_len: length of the last tt changeset this node received * from the orig node */ - s16 tt_buff_len; + u16 tt_buff_len; /** @tt_buff_lock: lock that protects tt_buff and tt_buff_len */ spinlock_t tt_buff_lock; @@ -993,7 +996,7 @@ struct batadv_priv_tt { * @last_changeset_len: length of last tt changeset this host has * generated */ - s16 last_changeset_len; + u16 last_changeset_len; /** * @last_changeset_lock: lock protecting last_changeset & @@ -1023,6 +1026,12 @@ struct batadv_priv_bla { /** @num_requests: number of bla requests in flight */ atomic_t num_requests; + /** + * @num_requests_lock: locks update num_requests + + * batadv_backbone_gw::state + batadv_backbone_gw::wait_periods update + */ + spinlock_t num_requests_lock; + /** * @claim_hash: hash table containing mesh nodes this host has claimed */ @@ -1320,11 +1329,14 @@ struct batadv_tp_vars { /** @role: receiver/sender modi */ enum batadv_tp_meter_role role; - /** @sending: sending binary semaphore: 1 if sending, 0 is not */ - atomic_t sending; + /** + * @send_result: 0 when sending is ongoing and otherwise + * enum batadv_tp_meter_reason + */ + atomic_t send_result; - /** @reason: reason for a stopped session */ - enum batadv_tp_meter_reason reason; + /** @receiving: receiving binary semaphore: 1 if receiving, 0 is not */ + atomic_t receiving; /** @finish_work: work item for the finishing procedure */ struct delayed_work finish_work; @@ -1666,6 +1678,27 @@ struct batadv_priv { #ifdef CONFIG_BATMAN_ADV_BLA +enum batadv_bla_backbone_gw_state { + /** + * @BATADV_BLA_BACKBONE_GW_STOPPED: backbone gw is being removed + * and it must not longer work on requests + */ + BATADV_BLA_BACKBONE_GW_STOPPED, + + /** + * @BATADV_BLA_BACKBONE_GW_UNSYNCED: backbone was detected out + * of sync and a request was send. No traffic is forwarded until the + * situation is resolved + */ + BATADV_BLA_BACKBONE_GW_UNSYNCED, + + /** + * @BATADV_BLA_BACKBONE_GW_SYNCED: backbone is consider to be in + * sync. traffic can be forwarded + */ + BATADV_BLA_BACKBONE_GW_SYNCED, +}; + /** * struct batadv_bla_backbone_gw - batman-adv gateway bridged into the LAN */ @@ -1691,16 +1724,12 @@ struct batadv_bla_backbone_gw { /** * @wait_periods: grace time for bridge forward delays and bla group * forming at bootup phase - no bcast traffic is formwared until it has - * elapsed + * elapsed. Must only be access with num_requests_lock. */ - atomic_t wait_periods; + u8 wait_periods; - /** - * @request_sent: if this bool is set to true we are out of sync with - * this backbone gateway - no bcast traffic is formwared until the - * situation was resolved - */ - atomic_t request_sent; + /** @state: sync state. Must only be access with num_requests_lock. */ + enum batadv_bla_backbone_gw_state state; /** @crc: crc16 checksum over all claims */ u16 crc; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 33d053d63407..1a6aa3f8d4d6 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -154,6 +154,7 @@ struct sock *bt_sock_alloc(struct net *net, struct socket *sock, sock_init_data(sock, sk); INIT_LIST_HEAD(&bt_sk(sk)->accept_q); + spin_lock_init(&bt_sk(sk)->accept_q_lock); sock_reset_flag(sk, SOCK_ZAPPED); @@ -214,6 +215,7 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { const struct cred *old_cred; struct pid *old_pid; + struct bt_sock *par = bt_sk(parent); BT_DBG("parent %p, sk %p", parent, sk); @@ -224,9 +226,13 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) else lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; + spin_lock_bh(&par->accept_q_lock); + list_add_tail(&bt_sk(sk)->accept_q, &par->accept_q); + sk_acceptq_added(parent); + spin_unlock_bh(&par->accept_q_lock); + /* Copy credentials from parent since for incoming connections the * socket is allocated by the kernel. */ @@ -244,8 +250,6 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) bh_unlock_sock(sk); else release_sock(sk); - - sk_acceptq_added(parent); } EXPORT_SYMBOL(bt_accept_enqueue); @@ -254,45 +258,72 @@ EXPORT_SYMBOL(bt_accept_enqueue); */ void bt_accept_unlink(struct sock *sk) { + struct sock *parent = bt_sk(sk)->parent; + BT_DBG("sk %p state %d", sk, sk->sk_state); + spin_lock_bh(&bt_sk(parent)->accept_q_lock); list_del_init(&bt_sk(sk)->accept_q); - sk_acceptq_removed(bt_sk(sk)->parent); + sk_acceptq_removed(parent); + spin_unlock_bh(&bt_sk(parent)->accept_q_lock); bt_sk(sk)->parent = NULL; sock_put(sk); } EXPORT_SYMBOL(bt_accept_unlink); +static struct sock *bt_accept_get(struct sock *parent, struct sock *sk) +{ + struct bt_sock *bt = bt_sk(parent); + struct sock *next = NULL; + + /* accept_q is modified from child teardown paths too, so take a + * temporary reference before dropping the queue lock. + */ + spin_lock_bh(&bt->accept_q_lock); + + if (sk) { + if (bt_sk(sk)->parent != parent) + goto out; + + if (!list_is_last(&bt_sk(sk)->accept_q, &bt->accept_q)) { + next = &list_next_entry(bt_sk(sk), accept_q)->sk; + sock_hold(next); + } + } else if (!list_empty(&bt->accept_q)) { + next = &list_first_entry(&bt->accept_q, + struct bt_sock, accept_q)->sk; + sock_hold(next); + } + +out: + spin_unlock_bh(&bt->accept_q_lock); + return next; +} + struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) { - struct bt_sock *s, *n; - struct sock *sk; + struct sock *sk, *next; BT_DBG("parent %p", parent); restart: - list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { - sk = (struct sock *)s; - + for (sk = bt_accept_get(parent, NULL); sk; sk = next) { /* Prevent early freeing of sk due to unlink and sock_kill */ - sock_hold(sk); lock_sock(sk); /* Check sk has not already been unlinked via * bt_accept_unlink() due to serialisation caused by sk locking */ - if (!bt_sk(sk)->parent) { + if (bt_sk(sk)->parent != parent) { BT_DBG("sk %p, already unlinked", sk); release_sock(sk); sock_put(sk); - /* Restart the loop as sk is no longer in the list - * and also avoid a potential infinite loop because - * list_for_each_entry_safe() is not thread safe. - */ goto restart; } + next = bt_accept_get(parent, sk); + /* sk is safely in the parent list so reduce reference count */ sock_put(sk); @@ -309,7 +340,19 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) if (newsock) sock_graft(sk, newsock); + /* Hand the caller a reference taken while sk is + * still locked. bt_accept_unlink() just dropped + * the accept-queue reference; without this hold a + * concurrent teardown (e.g. l2cap_conn_del() -> + * l2cap_sock_kill()) could free sk between + * release_sock() and the caller using it. Every + * caller drops this with sock_put() when done. + */ + sock_hold(sk); + release_sock(sk); + if (next) + sock_put(next); return sk; } @@ -518,18 +561,28 @@ EXPORT_SYMBOL(bt_sock_stream_recvmsg); static inline __poll_t bt_accept_poll(struct sock *parent) { - struct bt_sock *s, *n; + struct bt_sock *bt = bt_sk(parent); + struct bt_sock *s; struct sock *sk; + __poll_t mask = 0; + + spin_lock_bh(&bt->accept_q_lock); + list_for_each_entry(s, &bt->accept_q, accept_q) { + int state; - list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; - if (sk->sk_state == BT_CONNECTED || - (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) && - sk->sk_state == BT_CONNECT2)) - return EPOLLIN | EPOLLRDNORM; - } + state = READ_ONCE(sk->sk_state); - return 0; + if (state == BT_CONNECTED || + (test_bit(BT_SK_DEFER_SETUP, &bt->flags) && + state == BT_CONNECT2)) { + mask = EPOLLIN | EPOLLRDNORM; + break; + } + } + spin_unlock_bh(&bt->accept_q_lock); + + return mask; } __poll_t bt_sock_poll(struct file *file, struct socket *sock, diff --git a/net/bluetooth/bnep/core.c b/net/bluetooth/bnep/core.c index 853c8d7644b5..0de5df690bd0 100644 --- a/net/bluetooth/bnep/core.c +++ b/net/bluetooth/bnep/core.c @@ -645,8 +645,8 @@ int bnep_add_connection(struct bnep_connadd_req *req, struct socket *sock) goto failed; } - up_write(&bnep_session_sem); strcpy(req->device, dev->name); + up_write(&bnep_session_sem); return 0; failed: diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index fd3aacdea512..aff8562a8690 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4438,6 +4438,9 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) events[4] |= 0x02; /* LE BIG Info Advertising Report */ } + if (ll_ext_feature_capable(hdev)) + events[5] |= BIT(2); + if (le_cs_capable(hdev)) { /* Channel Sounding events */ events[5] |= 0x08; /* LE CS Read Remote Supported Cap Complete event */ @@ -7413,9 +7416,6 @@ static int hci_le_read_all_remote_features_sync(struct hci_dev *hdev, sizeof(cp), &cp, HCI_EVT_LE_ALL_REMOTE_FEATURES_COMPLETE, HCI_CMD_TIMEOUT, NULL); - - return __hci_cmd_sync_status(hdev, HCI_OP_LE_READ_ALL_REMOTE_FEATURES, - sizeof(cp), &cp, HCI_CMD_TIMEOUT); } static int hci_le_read_remote_features_sync(struct hci_dev *hdev, void *data) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 7cb2864fe872..d7af617cda45 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -751,6 +751,8 @@ static void iso_sock_cleanup_listen(struct sock *parent) while ((sk = bt_accept_dequeue(parent, NULL))) { iso_sock_close(sk); iso_sock_kill(sk); + /* Drop the reference handed back by bt_accept_dequeue(). */ + sock_put(sk); } /* If listening socket has a hcon, properly disconnect it */ @@ -1356,8 +1358,13 @@ static int iso_sock_accept(struct socket *sock, struct socket *newsock, } ch = bt_accept_dequeue(sk, newsock); - if (ch) + if (ch) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps ch alive from here. + */ + sock_put(ch); break; + } if (!timeo) { err = -EAGAIN; @@ -2593,6 +2600,11 @@ int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, u16 flags) break; case ISO_END: + if (!conn->rx_len) { + BT_ERR("Unexpected end frame (len %d)", skb->len); + goto drop; + } + skb_copy_from_linear_data(skb, skb_put(conn->rx_skb, skb->len), skb->len); conn->rx_len -= skb->len; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 7701528f1167..fdccd62ccca8 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7274,7 +7274,7 @@ static void l2cap_ecred_reconfigure(struct l2cap_chan *chan) chan->ident = l2cap_get_ident(conn); l2cap_send_cmd(conn, chan->ident, L2CAP_ECRED_RECONF_REQ, - sizeof(pdu), &pdu); + struct_size(pdu, scid, 1), pdu); } int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index cf590a67d364..b34e7da8d906 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -349,8 +349,13 @@ static int l2cap_sock_accept(struct socket *sock, struct socket *newsock, } nsk = bt_accept_dequeue(sk, newsock); - if (nsk) + if (nsk) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps nsk alive from here. + */ + sock_put(nsk); break; + } if (!timeo) { err = -EAGAIN; @@ -1475,22 +1480,54 @@ static void l2cap_sock_cleanup_listen(struct sock *parent) BT_DBG("parent %p state %s", parent, state_to_string(parent->sk_state)); - /* Close not yet accepted channels */ + /* Close not yet accepted channels. + * + * bt_accept_dequeue() now returns sk with an extra reference held + * (taken while sk was still locked) so a concurrent l2cap_conn_del() + * -> l2cap_sock_kill() cannot free sk under us. + * + * cleanup_listen() runs under the parent sk lock, so unlike + * l2cap_sock_shutdown() we must NOT take conn->lock here: that would + * establish sk_lock -> conn->lock and invert the established + * conn->lock -> chan->lock -> sk_lock order (lockdep deadlock). + * + * Instead, briefly take the child sk lock to fetch and pin its chan. + * l2cap_conn_del() reaches the chan free only via + * l2cap_chan_del() -> l2cap_sock_teardown_cb(), which itself takes + * the child sk lock; holding it across l2cap_chan_hold_unless_zero() + * therefore guarantees the chan cannot be freed while we read and + * pin it (hold_unless_zero() additionally skips a chan already past + * its last reference). We then drop the sk lock before taking + * chan->lock, so sk and chan locks are never held together. + */ while ((sk = bt_accept_dequeue(parent, NULL))) { - struct l2cap_chan *chan = l2cap_pi(sk)->chan; + struct l2cap_chan *chan; + + lock_sock_nested(sk, L2CAP_NESTING_NORMAL); + chan = l2cap_chan_hold_unless_zero(l2cap_pi(sk)->chan); + release_sock(sk); + if (!chan) { + /* l2cap_conn_del() already tearing this child down */ + sock_put(sk); + continue; + } BT_DBG("child chan %p state %s", chan, state_to_string(chan->state)); - l2cap_chan_hold(chan); l2cap_chan_lock(chan); - __clear_chan_timer(chan); l2cap_chan_close(chan, ECONNRESET); - l2cap_sock_kill(sk); - + /* l2cap_conn_del() may already have killed this socket + * (it sets SOCK_DEAD); skip the duplicate to avoid a + * double sock_put()/l2cap_chan_put(). + */ + if (!sock_flag(sk, SOCK_DEAD)) + l2cap_sock_kill(sk); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); + sock_put(sk); } } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index b05bb380e5f8..de5bd6b637b2 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -9110,9 +9110,15 @@ static int add_ext_adv_data(struct sock *sk, struct hci_dev *hdev, void *data, struct adv_info *adv_instance; int err = 0; struct mgmt_pending_cmd *cmd; + u16 expected_len; BT_DBG("%s", hdev->name); + expected_len = struct_size(cp, data, cp->adv_data_len + cp->scan_rsp_len); + if (expected_len != data_len) + return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA, + MGMT_STATUS_INVALID_PARAMS); + hci_dev_lock(hdev); adv_instance = hci_find_adv_instance(hdev, cp->instance); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index be6639cd6f59..bd7d959c6e9e 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -180,6 +180,8 @@ static void rfcomm_sock_cleanup_listen(struct sock *parent) while ((sk = bt_accept_dequeue(parent, NULL))) { rfcomm_sock_close(sk); rfcomm_sock_kill(sk); + /* Drop the reference handed back by bt_accept_dequeue(). */ + sock_put(sk); } parent->sk_state = BT_CLOSED; @@ -497,8 +499,13 @@ static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, } nsk = bt_accept_dequeue(sk, newsock); - if (nsk) + if (nsk) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps nsk alive from here. + */ + sock_put(nsk); break; + } if (!timeo) { err = -EAGAIN; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index eba44525d41d..f1799c6a6f87 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -502,6 +502,8 @@ static void sco_sock_cleanup_listen(struct sock *parent) while ((sk = bt_accept_dequeue(parent, NULL))) { sco_sock_close(sk); sco_sock_kill(sk); + /* Drop the reference handed back by bt_accept_dequeue(). */ + sock_put(sk); } parent->sk_state = BT_CLOSED; @@ -765,8 +767,13 @@ static int sco_sock_accept(struct socket *sock, struct socket *newsock, } ch = bt_accept_dequeue(sk, newsock); - if (ch) + if (ch) { + /* Drop the bridging ref from bt_accept_dequeue(); + * the grafted socket keeps ch alive from here. + */ + sock_put(ch); break; + } if (!timeo) { err = -EAGAIN; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 881d866d687a..2eef4f3345cd 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4640,10 +4640,24 @@ static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, rcu_read_unlock(); } -static void br_multicast_del_grps(struct net_bridge *br) +static void br_multicast_enable_all_ports(struct net_bridge *br) { struct net_bridge_port *port; + if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return; + + list_for_each_entry(port, &br->port_list, list) + __br_multicast_enable_port_ctx(&port->multicast_ctx); +} + +static void br_multicast_disable_all_ports(struct net_bridge *br) +{ + struct net_bridge_port *port; + + if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) + return; + list_for_each_entry(port, &br->port_list, list) __br_multicast_disable_port_ctx(&port->multicast_ctx); } @@ -4651,7 +4665,6 @@ static void br_multicast_del_grps(struct net_bridge *br) int br_multicast_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { - struct net_bridge_port *port; bool change_snoopers = false; int err = 0; @@ -4668,7 +4681,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val, br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { change_snoopers = true; - br_multicast_del_grps(br); + br_multicast_disable_all_ports(br); goto unlock; } @@ -4676,8 +4689,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val, goto unlock; br_multicast_open(br); - list_for_each_entry(port, &br->port_list, list) - __br_multicast_enable_port_ctx(&port->multicast_ctx); + br_multicast_enable_all_ports(br); change_snoopers = true; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 0ab1c94db4b9..0a394e5f4391 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -297,7 +297,11 @@ int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_ goto free_skb; } - neigh_hh_bridge(&neigh->hh, skb); + if (neigh_hh_bridge(&neigh->hh, skb)) { + neigh_release(neigh); + goto free_skb; + } + skb->dev = br_indev; ret = br_handle_frame_finish(net, sk, skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6fd5386a1d64..c04a4d0889ae 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1824,6 +1824,7 @@ static int br_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { + unsigned int limit = U16_MAX - nla_total_size(0); struct nlattr *nla __maybe_unused; struct net_bridge_port *p = NULL; struct net_bridge_vlan_group *vg; @@ -1841,6 +1842,7 @@ static int br_fill_linkxstats(struct sk_buff *skb, p = br_port_get_rtnl(dev); if (!p) return 0; + limit -= nla_total_size_64bit(sizeof(p->stp_xstats)); br = p->br; vg = nbp_vlan_group(p); break; @@ -1855,6 +1857,9 @@ static int br_fill_linkxstats(struct sk_buff *skb, if (vg) { u16 pvid; +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + limit -= nla_total_size_64bit(sizeof(struct br_mcast_stats)); +#endif pvid = br_get_pvid(vg); list_for_each_entry(v, &vg->vlan_list, vlist) { struct bridge_vlan_xstats vxi; @@ -1862,6 +1867,11 @@ static int br_fill_linkxstats(struct sk_buff *skb, if (++vl_idx < *prividx) continue; + + if (skb_tail_pointer(skb) - (unsigned char *)nest + + nla_total_size(sizeof(vxi)) >= limit) + goto nla_put_failure; + memset(&vxi, 0, sizeof(vxi)); vxi.vid = v->vid; vxi.flags = v->flags; diff --git a/net/core/devmem.c b/net/core/devmem.c index 468344739db2..4f71de44c0fb 100644 --- a/net/core/devmem.c +++ b/net/core/devmem.c @@ -241,6 +241,11 @@ net_devmem_bind_dmabuf(struct net_device *dev, } if (direction == DMA_TO_DEVICE) { + if (!IS_ALIGNED(dmabuf->size, PAGE_SIZE)) { + err = -EINVAL; + NL_SET_ERR_MSG(extack, "TX dma-buf size must be a multiple of PAGE_SIZE"); + goto err_unmap; + } binding->tx_vec = kvmalloc_objs(struct net_iov *, dmabuf->size / PAGE_SIZE); if (!binding->tx_vec) { @@ -267,6 +272,12 @@ net_devmem_bind_dmabuf(struct net_device *dev, size_t len = sg_dma_len(sg); struct net_iov *niov; + if (!IS_ALIGNED(len, PAGE_SIZE)) { + err = -EINVAL; + NL_SET_ERR_MSG(extack, "dma-buf SG length must be PAGE_SIZE aligned"); + goto err_free_chunks; + } + owner = kzalloc_node(sizeof(*owner), GFP_KERNEL, dev_to_node(&dev->dev)); if (!owner) { diff --git a/net/core/gro.c b/net/core/gro.c index 31d21de5b15a..a84753983467 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -109,6 +109,9 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) if (p->pp_recycle != skb->pp_recycle) return -ETOOMANYREFS; + if (skb_zcopy(p) || skb_zcopy(skb)) + return -ETOOMANYREFS; + if (unlikely(p->len + len >= netif_get_gro_max_size(p->dev, p) || NAPI_GRO_CB(skb)->flush)) return -E2BIG; @@ -213,10 +216,12 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) p->data_len += len; p->truesize += delta_truesize; p->len += len; + skb_shinfo(p)->flags |= skbinfo->flags & SKBFL_SHARED_FRAG; if (lp != p) { lp->data_len += len; lp->truesize += delta_truesize; lp->len += len; + skb_shinfo(lp)->flags |= skbinfo->flags & SKBFL_SHARED_FRAG; } NAPI_GRO_CB(skb)->same_flow = 1; return 0; @@ -244,6 +249,8 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb) p->truesize += skb->truesize; p->len += skb->len; + skb_shinfo(p)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + NAPI_GRO_CB(skb)->same_flow = 1; return 0; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 84faace50ac2..3f4a17fa5713 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -319,6 +319,8 @@ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) lockdep_assert_irqs_disabled(); dev = np->dev; + /* npinfo->txq belongs to np->dev, so retries must stay bound to it. */ + skb->dev = dev; rcu_read_lock(); npinfo = rcu_dereference_bh(dev->npinfo); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index df042da422ef..511c25bf6f2a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -6328,8 +6328,9 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, &filters, &idxattr, &prividx, extack); if (err < 0) { - /* -EMSGSIZE implies BUG in if_nlmsg_stats_size */ - WARN_ON(err == -EMSGSIZE); + /* -EMSGSIZE implies BUG in if_nlmsg_stats_size + * or a too big nested attribute. + */ kfree_skb(nskb); } else { err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7dad68e3b518..44ac121cfccb 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2248,6 +2248,7 @@ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, skb_frag_ref(skb, i); } skb_shinfo(n)->nr_frags = i; + skb_shinfo(n)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; } if (skb_has_frag_list(skb)) { @@ -4349,6 +4350,8 @@ int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) tgt->ip_summed = CHECKSUM_PARTIAL; skb->ip_summed = CHECKSUM_PARTIAL; + skb_shinfo(tgt)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; + skb_len_add(skb, -shiftlen); skb_len_add(tgt, shiftlen); @@ -4959,7 +4962,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, skb_copy_from_linear_data_offset(head_skb, offset, skb_put(nskb, hsize), hsize); - skb_shinfo(nskb)->flags |= skb_shinfo(head_skb)->flags & + skb_shinfo(nskb)->flags |= (skb_shinfo(head_skb)->flags | + skb_shinfo(frag_skb)->flags) & SKBFL_SHARED_FRAG; if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC)) @@ -4976,6 +4980,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, nfrags = skb_shinfo(list_skb)->nr_frags; frag = skb_shinfo(list_skb)->frags; frag_skb = list_skb; + + skb_shinfo(nskb)->flags |= skb_shinfo(frag_skb)->flags & SKBFL_SHARED_FRAG; + if (!skb_headlen(list_skb)) { BUG_ON(!nfrags); } else { @@ -6200,6 +6207,8 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, from_shinfo->frags, from_shinfo->nr_frags * sizeof(skb_frag_t)); to_shinfo->nr_frags += from_shinfo->nr_frags; + if (from_shinfo->nr_frags) + to_shinfo->flags |= from_shinfo->flags & SKBFL_SHARED_FRAG; if (!skb_cloned(from)) from_shinfo->nr_frags = 0; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 6187a83bd741..e1850caf1a71 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1268,12 +1268,19 @@ static int sk_psock_verdict_recv(struct sock *sk, struct sk_buff *skb) static void sk_psock_verdict_data_ready(struct sock *sk) { const struct proto_ops *ops = NULL; + struct sk_psock *psock; struct socket *sock; int copied; trace_sk_data_ready(sk); rcu_read_lock(); + psock = sk_psock(sk); + if (psock && tls_sw_has_ctx_rx(sk)) { + psock->saved_data_ready(sk); + rcu_read_unlock(); + return; + } sock = READ_ONCE(sk->sk_socket); if (likely(sock)) ops = READ_ONCE(sock->ops); @@ -1283,8 +1290,6 @@ static void sk_psock_verdict_data_ready(struct sock *sk) copied = ops->read_skb(sk, sk_psock_verdict_recv); if (copied >= 0) { - struct sk_psock *psock; - rcu_read_lock(); psock = sk_psock(sk); if (psock) diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 124619920d38..b514e43766ef 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -163,8 +163,8 @@ void hsr_del_nodes(struct list_head *node_db) struct hsr_node *tmp; list_for_each_entry_safe(node, tmp, node_db, mac_list) { - list_del(&node->mac_list); - hsr_free_node(node); + list_del_rcu(&node->mac_list); + call_rcu(&node->rcu_head, hsr_free_node_rcu); } } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 7eeff658b467..23e921d313b3 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -961,6 +961,9 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (IS_ERR(rt)) goto out_unlock; + if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + goto ende; + /* peer icmp_ratelimit */ if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit)) goto ende; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 5aaf9c62c8e1..68e88cb3e55c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -391,7 +391,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, * in, reject the frame as invalid */ err = -EINVAL; - if (iphlen > length) + if (iphlen > length || iphlen < sizeof(*iph)) goto error_free; if (iphlen >= sizeof(*iph)) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bc1296f0ea69..3d62d45d84bd 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1272,7 +1272,7 @@ static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); - WARN_ON(1); + WARN_ON_ONCE(1); return 0; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 432fa28e47d4..389a7cc17110 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -299,9 +299,6 @@ enum { DEFINE_PER_CPU(unsigned int, tcp_orphan_count); EXPORT_PER_CPU_SYMBOL_GPL(tcp_orphan_count); -DEFINE_PER_CPU(u32, tcp_tw_isn); -EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn); - long sysctl_tcp_mem[3] __read_mostly; DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d5c9e65d9760..de9f68a9c0cf 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7589,6 +7589,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct sock *sk, struct sk_buff *skb) { struct tcp_fastopen_cookie foc = { .len = -1 }; + u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; const struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); @@ -7599,20 +7600,16 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, struct dst_entry *dst; struct flowi fl; u8 syncookies; - u32 isn; #ifdef CONFIG_TCP_AO const struct tcp_ao_hdr *aoh; #endif - isn = __this_cpu_read(tcp_tw_isn); - if (isn) { - /* TW buckets are converted to open requests without - * limitations, they conserve resources and peer is - * evidently real one. - */ - __this_cpu_write(tcp_tw_isn, 0); - } else { + /* If isn is non-zero, this SYN originally matched a TIME_WAIT socket. + * TW sockets are converted to open requests without limitations, + * we skip the queue limits and syncookie checks in the block below. + */ + if (!isn) { syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); if (syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c0526cc03980..fdc81150ff6c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2198,6 +2198,7 @@ int tcp_v4_rcv(struct sk_buff *skb) } } + isn = 0; process: if (static_branch_unlikely(&ip4_min_ttl)) { /* min_ttl can be changed concurrently from do_ip_setsockopt() */ @@ -2227,6 +2228,7 @@ int tcp_v4_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); + TCP_SKB_CB(skb)->tcp_tw_isn = isn; skb->dev = NULL; @@ -2313,7 +2315,6 @@ int tcp_v4_rcv(struct sk_buff *skb) sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; - __this_cpu_write(tcp_tw_isn, isn); goto process; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f9d8755705f7..6e4bb411dc04 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2626,6 +2626,7 @@ static int tcp_clone_payload(struct sock *sk, struct sk_buff *to, todo = min_t(int, skb_frag_size(fragfrom), probe_size - len); len += todo; + skb_shinfo(to)->flags |= skb_shinfo(skb)->flags & SKBFL_SHARED_FRAG; if (lastfrag && skb_frag_page(fragfrom) == skb_frag_page(lastfrag) && skb_frag_off(fragfrom) == skb_frag_off(lastfrag) + diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index a0813d425b71..29651b1a0bc7 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -482,11 +482,11 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, struct sock *sk = gso_skb->sk; unsigned int sum_truesize = 0; struct sk_buff *segs, *seg; - __be16 newlen, msslen; struct udphdr *uh; unsigned int mss; bool copy_dtor; __sum16 check; + __be16 newlen; int ret = 0; mss = skb_shinfo(gso_skb)->gso_size; @@ -555,15 +555,6 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, return segs; } - msslen = htons(sizeof(*uh) + mss); - - /* GSO partial and frag_list segmentation only requires splitting - * the frame into an MSS multiple and possibly a remainder, both - * cases return a GSO skb. So update the mss now. - */ - if (skb_is_gso(segs)) - mss *= skb_shinfo(segs)->gso_segs; - seg = segs; uh = udp_hdr(seg); @@ -586,7 +577,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, if (!seg->next) break; - uh->len = msslen; + uh->len = newlen; uh->check = check; if (seg->ip_summed == CHECKSUM_PARTIAL) @@ -599,9 +590,12 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, uh = udp_hdr(seg); } - /* last packet can be partial gso_size, account for that in checksum */ - newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + - seg->data_len); + /* Unless skb fits perfectly as GSO_PARTIAL, the trailing + * segment may not be full MSS, account for that in the checksum + */ + if (!skb_is_gso(seg)) + newlen = htons(skb_tail_pointer(seg) - + skb_transport_header(seg) + seg->data_len); check = csum16_add(csum16_sub(uh->check, uh->len), newlen); uh->len = newlen; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 03cbce842c1a..cf90f933ca1a 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -910,16 +910,27 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) { + enum skb_drop_reason drop_reason; struct ioam6_trace_hdr *trace; struct ioam6_namespace *ns; + struct inet6_dev *idev; struct ioam6_hdr *hdr; + drop_reason = SKB_DROP_REASON_IP_INHDR; + /* Bad alignment (must be 4n-aligned) */ if (optoff & 3) goto drop; + /* Does the device still have IPv6 configuration? */ + idev = __in6_dev_get(skb->dev); + if (!idev) { + drop_reason = SKB_DROP_REASON_IPV6DISABLED; + goto drop; + } + /* Ignore if IOAM is not enabled on ingress */ - if (!READ_ONCE(__in6_dev_get(skb->dev)->cnf.ioam6_enabled)) + if (!READ_ONCE(idev->cnf.ioam6_enabled)) goto ignore; /* Truncated Option header */ @@ -955,9 +966,9 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) goto drop; - /* Trace pointer may have changed */ - trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) - + optoff + sizeof(*hdr)); + /* Trace and hdr pointers may have changed */ + hdr = (struct ioam6_hdr *)(skb_network_header(skb) + optoff); + trace = (struct ioam6_trace_hdr *)((u8 *)hdr + sizeof(*hdr)); ioam6_fill_trace_data(skb, ns, trace, true); @@ -972,7 +983,7 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) return true; drop: - kfree_skb_reason(skb, SKB_DROP_REASON_IP_INHDR); + kfree_skb_reason(skb, drop_reason); return false; } diff --git a/net/ipv6/netfilter/ip6t_hbh.c b/net/ipv6/netfilter/ip6t_hbh.c index e7a3fb9355ee..450dd53846a2 100644 --- a/net/ipv6/netfilter/ip6t_hbh.c +++ b/net/ipv6/netfilter/ip6t_hbh.c @@ -168,6 +168,10 @@ static int hbh_mt6_check(const struct xt_mtchk_param *par) pr_debug("unknown flags %X\n", optsinfo->invflags); return -EINVAL; } + if (optsinfo->optsnr > IP6T_OPTS_OPTSNR) { + pr_debug("too many supported opts specified\n"); + return -EINVAL; + } if (optsinfo->flags & IP6T_OPTS_NSTRICT) { pr_debug("Not strict - not implemented"); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e3d355d1fbd6..b106e5fef9cb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6933,7 +6933,7 @@ int __init ip6_route_init(void) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) ret = bpf_iter_register(); if (ret) - goto out_register_late_subsys; + goto out_register_notifier; #endif for_each_possible_cpu(cpu) { @@ -6946,6 +6946,10 @@ int __init ip6_route_init(void) out: return ret; +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +out_register_notifier: + unregister_netdevice_notifier(&ip6_route_dev_notifier); +#endif out_register_late_subsys: rtnl_unregister_all(PF_INET6); unregister_pernet_subsys(&ip6_route_net_late_ops); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d13d49bfef19..36d75fb50a70 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1839,6 +1839,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) } } + isn = 0; process: if (static_branch_unlikely(&ip6_min_hopcount)) { /* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */ @@ -1868,6 +1869,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); + TCP_SKB_CB(skb)->tcp_tw_isn = isn; skb->dev = NULL; @@ -1956,7 +1958,6 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) sk = sk2; tcp_v6_restore_cb(skb); refcounted = false; - __this_cpu_write(tcp_tw_isn, isn); goto process; } diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 157fc23ce4e1..1455f67e01dd 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1360,7 +1360,7 @@ static void l2tp_session_unhash(struct l2tp_session *session) spin_lock_bh(&pn->l2tp_session_idr_lock); /* Remove from the per-tunnel list */ - list_del_init(&session->list); + list_del_rcu(&session->list); /* Remove from per-net IDR */ if (tunnel->version == L2TP_HDR_VER_3) { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 7b77d57c9f96..f9ee9947a94d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2344,8 +2344,9 @@ static int sta_apply_parameters(struct ieee80211_local *local, sta->sta.max_sp = params->max_sp; } - ieee80211_sta_set_max_amsdu_subframes(sta, params->ext_capab, - params->ext_capab_len); + if (params->ext_capab) + ieee80211_sta_set_max_amsdu_subframes(sta, params->ext_capab, + params->ext_capab_len); /* * cfg80211 validates this (1-2007) and allows setting the AID diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 0a0f27836d57..b98ddfa3003e 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8164,6 +8164,7 @@ ieee80211_parse_neg_ttlm(struct ieee80211_sub_if_data *sdata, "No active links for TID %d", tid); return -EINVAL; } + pos += map_size; } else { map = 0; } @@ -8182,7 +8183,6 @@ ieee80211_parse_neg_ttlm(struct ieee80211_sub_if_data *sdata, default: return -EINVAL; } - pos += map_size; } return 0; } @@ -11232,6 +11232,9 @@ static void ieee80211_ml_epcs(struct ieee80211_sub_if_data *sdata, control = get_unaligned_le16(pos); link_id = control & IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID; + if (link_id >= IEEE80211_MLD_MAX_NUM_LINKS) + continue; + link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c index 2b3632c6008a..77894d997113 100644 --- a/net/mac80211/parse.c +++ b/net/mac80211/parse.c @@ -34,6 +34,22 @@ #include "led.h" #include "wep.h" +static const u8 empty_non_inheritance[] = { + WLAN_EID_EXTENSION, 1, WLAN_EID_EXT_NON_INHERITANCE, + /* + * cfg80211_is_element_inherited() hardcodes elements that + * cannot be inherited, so we just need an empty one to be + * calling it at all. + */ +}; + +struct ieee80211_elem_defrag { + const struct element *elem; + /* container start/len */ + const u8 *start; + size_t len; +}; + struct ieee80211_elems_parse { /* must be first for kfree to work */ struct ieee802_11_elems elems; @@ -41,11 +57,7 @@ struct ieee80211_elems_parse { /* The basic Multi-Link element in the original elements */ const struct element *ml_basic_elem; - /* The reconfiguration Multi-Link element in the original elements */ - const struct element *ml_reconf_elem; - - /* The EPCS Multi-Link element in the original elements */ - const struct element *ml_epcs_elem; + struct ieee80211_elem_defrag ml_reconf, ml_epcs; bool multi_link_inner; bool skip_vendor; @@ -162,10 +174,14 @@ ieee80211_parse_extension_element(u32 *crc, } break; case IEEE80211_ML_CONTROL_TYPE_RECONF: - elems_parse->ml_reconf_elem = elem; + elems_parse->ml_reconf.elem = elem; + elems_parse->ml_reconf.start = params->start; + elems_parse->ml_reconf.len = params->len; break; case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - elems_parse->ml_epcs_elem = elem; + elems_parse->ml_epcs.elem = elem; + elems_parse->ml_epcs.start = params->start; + elems_parse->ml_epcs.len = params->len; break; default: break; @@ -916,7 +932,7 @@ ieee80211_prep_mle_link_parse(struct ieee80211_elems_parse *elems_parse, { struct ieee802_11_elems *elems = &elems_parse->elems; struct ieee80211_mle_per_sta_profile *prof; - const struct element *tmp; + const struct element *tmp, *ret; ssize_t ml_len; const u8 *end; @@ -986,50 +1002,40 @@ ieee80211_prep_mle_link_parse(struct ieee80211_elems_parse *elems_parse, sub->from_ap = params->from_ap; sub->link_id = -1; - return cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, - sub->start, sub->len); + ret = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, + sub->start, sub->len); + if (ret) + return ret; + + /* + * Since we know we want and found a profile, apply an empty + * non-inheritance if the profile didn't have one, so that any + * element that shouldn't be inherited by spec isn't. + */ + return (const void *)empty_non_inheritance; } -static void -ieee80211_mle_defrag_reconf(struct ieee80211_elems_parse *elems_parse) +static const void * +ieee80211_mle_defrag(struct ieee80211_elems_parse *elems_parse, + struct ieee80211_elem_defrag *defrag, + size_t *out_len) { - struct ieee802_11_elems *elems = &elems_parse->elems; + const void *ret; ssize_t ml_len; - ml_len = cfg80211_defragment_element(elems_parse->ml_reconf_elem, - elems->ie_start, - elems->total_len, + ml_len = cfg80211_defragment_element(defrag->elem, + defrag->start, defrag->len, elems_parse->scratch_pos, elems_parse->scratch + elems_parse->scratch_len - elems_parse->scratch_pos, WLAN_EID_FRAGMENT); if (ml_len < 0) - return; - elems->ml_reconf = (void *)elems_parse->scratch_pos; - elems->ml_reconf_len = ml_len; - elems_parse->scratch_pos += ml_len; -} - -static void -ieee80211_mle_defrag_epcs(struct ieee80211_elems_parse *elems_parse) -{ - struct ieee802_11_elems *elems = &elems_parse->elems; - ssize_t ml_len; - - ml_len = cfg80211_defragment_element(elems_parse->ml_epcs_elem, - elems->ie_start, - elems->total_len, - elems_parse->scratch_pos, - elems_parse->scratch + - elems_parse->scratch_len - - elems_parse->scratch_pos, - WLAN_EID_FRAGMENT); - if (ml_len < 0) - return; - elems->ml_epcs = (void *)elems_parse->scratch_pos; - elems->ml_epcs_len = ml_len; + return NULL; + ret = elems_parse->scratch_pos; + *out_len = ml_len; elems_parse->scratch_pos += ml_len; + return ret; } struct ieee802_11_elems * @@ -1042,6 +1048,7 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) size_t scratch_len = 3 * params->len; bool multi_link_inner = false; + BUILD_BUG_ON(sizeof(empty_non_inheritance) != empty_non_inheritance[1] + 2); BUILD_BUG_ON(offsetof(typeof(*elems_parse), elems) != 0); /* cannot parse for both a specific link and non-transmitted BSS */ @@ -1089,6 +1096,17 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE, sub.start, nontx_len); + /* + * If it's a non-transmitted BSS, we shouldn't pick + * any elements in the outer parsing that shouldn't + * be inherited. If the profile has a non-inheritance + * element this automatically happens, but if not then + * provide an empty one so that the hard-coded elements + * in cfg80211_is_element_inherited() are ignored, but + * it must be called. + */ + if (params->bss->transmitted_bss && !non_inherit) + non_inherit = (const void *)empty_non_inheritance; } else { /* must always parse to get elems_parse->ml_basic_elem */ non_inherit = ieee80211_prep_mle_link_parse(elems_parse, params, @@ -1109,9 +1127,12 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) _ieee802_11_parse_elems_full(&sub, elems_parse, NULL); } - ieee80211_mle_defrag_reconf(elems_parse); - - ieee80211_mle_defrag_epcs(elems_parse); + elems->ml_reconf = ieee80211_mle_defrag(elems_parse, + &elems_parse->ml_reconf, + &elems->ml_reconf_len); + elems->ml_epcs = ieee80211_mle_defrag(elems_parse, + &elems_parse->ml_epcs, + &elems->ml_epcs_len); if (elems->tim && !elems->parse_error) { const struct ieee80211_tim_ie *tim_ie = elems->tim; diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index d18e962126ce..3fb40449c6c5 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4984,6 +4984,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, u8 sa[ETH_ALEN]; } addrs __aligned(2); struct ieee80211_sta_rx_stats *stats; + u32 encoded_rate; /* for parallel-rx, we need to have DUP_VALIDATED, otherwise we write * to a common data structure; drivers can implement that per queue @@ -5091,11 +5092,14 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, /* push the addresses in front */ memcpy(skb_push(skb, sizeof(addrs)), &addrs, sizeof(addrs)); + /* capture before mesh forward may memset or free skb->cb */ + encoded_rate = sta_stats_encode_rate(status); + res = ieee80211_rx_mesh_data(rx->sdata, rx->sta, rx->skb); switch (res) { case RX_QUEUED: stats->last_rx = jiffies; - stats->last_rate = sta_stats_encode_rate(status); + stats->last_rate = encoded_rate; return true; case RX_CONTINUE: break; diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 3c152bf66cd5..3e770c7407e1 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -364,7 +364,13 @@ static void mptcp_pm_add_timer(struct timer_list *timer) spin_lock_bh(&msk->pm.lock); - if (!mptcp_pm_should_add_signal_addr(msk)) { + /* The cancel path (mptcp_pm_del_add_timer()) can race with this + * callback. Once cancel updates retrans_times to MAX, suppress further + * retransmissions here. If this callback acquires pm.lock first, one + * final transmit attempt is still possible. + */ + if (entry->retrans_times < ADD_ADDR_RETRANS_MAX && + !mptcp_pm_should_add_signal_addr(msk)) { pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id); mptcp_pm_announce_addr(msk, &entry->addr, false); mptcp_pm_add_addr_send_ack(msk); @@ -414,8 +420,12 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, /* Note: entry might have been removed by another thread. * We hold rcu_read_lock() to ensure it is not freed under us. */ - if (stop_timer) - sk_stop_timer_sync(sk, &entry->add_timer); + if (stop_timer) { + if (check_id) + sk_stop_timer(sk, &entry->add_timer); + else + sk_stop_timer_sync(sk, &entry->add_timer); + } rcu_read_unlock(); return entry; @@ -882,6 +892,7 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, struct mptcp_addr_info *addr, bool *echo, bool *drop_other_suboptions) { + bool skip_add_addr = false; int ret = false; u8 add_addr; u8 family; @@ -903,24 +914,49 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, } *echo = mptcp_pm_should_add_signal_echo(msk); - port = !!(*echo ? msk->pm.remote.port : msk->pm.local.port); - - family = *echo ? msk->pm.remote.family : msk->pm.local.family; - if (remaining < mptcp_add_addr_len(family, *echo, port)) - goto out_unlock; - if (*echo) { *addr = msk->pm.remote; add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_ECHO); + port = !!msk->pm.remote.port; + family = msk->pm.remote.family; } else { *addr = msk->pm.local; add_addr = msk->pm.addr_signal & ~BIT(MPTCP_ADD_ADDR_SIGNAL); + port = !!msk->pm.local.port; + family = msk->pm.local.family; } - WRITE_ONCE(msk->pm.addr_signal, add_addr); + + if (remaining < mptcp_add_addr_len(family, *echo, port)) { + struct net *net = sock_net((struct sock *)msk); + + if (!*drop_other_suboptions) + goto out_unlock; + + if (*echo) { + MPTCP_INC_STATS(net, MPTCP_MIB_ECHOADDTXDROP); + } else { + skip_add_addr = true; + MPTCP_INC_STATS(net, MPTCP_MIB_ADDADDRTXDROP); + } + goto drop_signal_mark; + } + ret = true; +drop_signal_mark: + WRITE_ONCE(msk->pm.addr_signal, add_addr); + out_unlock: spin_unlock_bh(&msk->pm.lock); + + /* On pure-ACK option-space exhaustion, stop retrying this ADD_ADDR: + * clear the signal bit, cancel the matching retransmission timer, and + * let the PM state machine progress. + */ + if (skip_add_addr) { + mptcp_pm_del_add_timer(msk, addr, true); + mptcp_pm_subflow_established(msk); + } return ret; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 4546a8b09884..a72a6ad6ee8b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -397,12 +397,26 @@ static bool __mptcp_move_skb(struct sock *sk, struct sk_buff *skb) return false; } - /* old data, keep it simple and drop the whole pkt, sender - * will retransmit as needed, if needed. + /* Completely old data? */ + if (!after64(MPTCP_SKB_CB(skb)->end_seq, msk->ack_seq)) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); + mptcp_drop(sk, skb); + return false; + } + + /* Partial packet: map_seq < ack_seq < end_seq. + * Skip the already-acked bytes and enqueue the new data. */ - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA); - mptcp_drop(sk, skb); - return false; + copy_len = MPTCP_SKB_CB(skb)->end_seq - msk->ack_seq; + MPTCP_SKB_CB(skb)->offset += msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; + MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq - + MPTCP_SKB_CB(skb)->map_seq; + msk->bytes_received += copy_len; + WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); + + skb_set_owner_r(skb, sk); + __skb_queue_tail(&sk->sk_receive_queue, skb); + return true; } static void mptcp_stop_rtx_timer(struct sock *sk) @@ -3473,6 +3487,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) /* for fallback's sake */ WRITE_ONCE(msk->ack_seq, 0); + atomic64_set(&msk->rcv_wnd_sent, 0); WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 1cf608e7357b..87b5796d0135 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -67,6 +67,12 @@ static int mptcp_get_int_option(struct mptcp_sock *msk, sockptr_t optval, return 0; } +static void __mptcp_subflow_set_rcvbuf(struct sock *ssk, int val) +{ + WRITE_ONCE(ssk->sk_rcvbuf, val); + tcp_set_rcvbuf(ssk, val); +} + static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, int val) { struct mptcp_subflow_context *subflow; @@ -100,7 +106,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in case SO_RCVBUF: case SO_RCVBUFFORCE: ssk->sk_userlocks |= SOCK_RCVBUF_LOCK; - WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); + __mptcp_subflow_set_rcvbuf(ssk, sk->sk_rcvbuf); break; case SO_MARK: if (READ_ONCE(ssk->sk_mark) != sk->sk_mark) { @@ -1560,7 +1566,7 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; } if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) - WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); + __mptcp_subflow_set_rcvbuf(ssk, sk->sk_rcvbuf); } if (sock_flag(sk, SOCK_LINGER)) { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index c5a26236a0bb..3706b4a85a0f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1613,6 +1613,7 @@ ip_set_dump_do(struct sk_buff *skb, struct netlink_callback *cb) ((dump_type == DUMP_ALL) == !!(set->type->features & IPSET_DUMP_LAST))) { write_unlock_bh(&ip_set_ref_lock); + set = NULL; continue; } pr_debug("List set: %s\n", set->name); @@ -1648,13 +1649,13 @@ ip_set_dump_do(struct sk_buff *skb, struct netlink_callback *cb) if (cb->args[IPSET_CB_PROTO] > IPSET_PROTOCOL_MIN && nla_put_net16(skb, IPSET_ATTR_INDEX, htons(index))) goto nla_put_failure; + if (set->variant->uref) + set->variant->uref(set, cb, true); ret = set->variant->head(set, skb); if (ret < 0) goto release_refcount; if (dump_flags & IPSET_FLAG_LIST_HEADER) goto next_set; - if (set->variant->uref) - set->variant->uref(set, cb, true); fallthrough; default: ret = set->variant->list(set, skb, cb); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index b79e5dd2af03..04e4627ddfc1 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -386,8 +386,9 @@ static void mtype_ext_cleanup(struct ip_set *set, struct hbucket *n) { int i; + u8 pos = smp_load_acquire(&n->pos); - for (i = 0; i < n->pos; i++) + for (i = 0; i < pos; i++) if (test_bit(i, n->used)) ip_set_ext_destroy(set, ahash_data(n, i, set->dsize)); } @@ -490,7 +491,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif - u8 htable_bits = t->htable_bits; + u8 pos, htable_bits = t->htable_bits; spin_lock_bh(&t->hregion[r].lock); for (i = ahash_bucket_start(r, htable_bits); @@ -498,7 +499,8 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) n = __ipset_dereference(hbucket(t, i)); if (!n) continue; - for (j = 0, d = 0; j < n->pos; j++) { + pos = smp_load_acquire(&n->pos); + for (j = 0, d = 0; j < pos; j++) { if (!test_bit(j, n->used)) { d++; continue; @@ -534,7 +536,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; - for (j = 0, d = 0; j < n->pos; j++) { + for (j = 0, d = 0; j < pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); @@ -623,7 +625,7 @@ mtype_resize(struct ip_set *set, bool retried) { struct htype *h = set->data; struct htable *t, *orig; - u8 htable_bits; + u8 pos, htable_bits; size_t hsize, dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; @@ -685,7 +687,8 @@ mtype_resize(struct ip_set *set, bool retried) n = __ipset_dereference(hbucket(orig, i)); if (!n) continue; - for (j = 0; j < n->pos; j++) { + pos = smp_load_acquire(&n->pos); + for (j = 0; j < pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); @@ -809,9 +812,10 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) { struct htype *h = set->data; const struct htable *t; - u32 i, j, r; struct hbucket *n; struct mtype_elem *data; + u32 i, j, r; + u8 pos; t = rcu_dereference_bh(h->table); for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { @@ -820,7 +824,8 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) n = rcu_dereference_bh(hbucket(t, i)); if (!n) continue; - for (j = 0; j < n->pos; j++) { + pos = smp_load_acquire(&n->pos); + for (j = 0; j < pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, set->dsize); @@ -848,6 +853,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; u32 r, key, multi = 0, elements, maxelem; + u8 npos = 0; rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); @@ -889,7 +895,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } - for (i = 0; i < n->pos; i++) { + npos = smp_load_acquire(&n->pos); + for (i = 0; i < npos; i++) { if (!test_bit(i, n->used)) { /* Reuse first deleted entry */ if (j == -1) { @@ -933,7 +940,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (elements >= maxelem) goto set_full; /* Create a new slot */ - if (n->pos >= n->size) { + if (npos >= n->size) { #ifdef IP_SET_HASH_WITH_MULTI if (h->bucketsize >= AHASH_MAX_TUNED) goto set_full; @@ -962,7 +969,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } copy_elem: - j = n->pos++; + j = npos++; data = ahash_data(n, j, set->dsize); copy_data: t->hregion[r].elements++; @@ -985,6 +992,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (SET_WITH_TIMEOUT(set)) ip_set_timeout_set(ext_timeout(data, set), ext->timeout); smp_mb__before_atomic(); + /* Ensure all data writes are visible before updating position */ + smp_store_release(&n->pos, npos); set_bit(j, n->used); if (old != ERR_PTR(-ENOENT)) { rcu_assign_pointer(hbucket(t, key), n); @@ -1043,6 +1052,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; + u8 pos; /* Userspace add and resize is excluded by the mutex. * Kernespace add does not trigger resize. @@ -1058,7 +1068,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; - for (i = 0, k = 0; i < n->pos; i++) { + pos = smp_load_acquire(&n->pos); + for (i = 0, k = 0; i < pos; i++) { if (!test_bit(i, n->used)) { k++; continue; @@ -1072,8 +1083,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, ret = 0; clear_bit(i, n->used); smp_mb__after_atomic(); - if (i + 1 == n->pos) - n->pos--; + if (i + 1 == pos) + smp_store_release(&n->pos, --pos); t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) @@ -1094,11 +1105,11 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, x->flags = flags; } } - for (; i < n->pos; i++) { + for (; i < pos; i++) { if (!test_bit(i, n->used)) k++; } - if (k == n->pos) { + if (k == pos) { t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); @@ -1109,7 +1120,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (!tmp) goto out; tmp->size = n->size - AHASH_INIT_SIZE; - for (j = 0, k = 0; j < n->pos; j++) { + for (j = 0, k = 0; j < pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); @@ -1170,6 +1181,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, int ret, i, j = 0; #endif u32 key, multi = 0; + u8 pos; pr_debug("test by nets\n"); for (; j < NLEN && h->nets[j].cidr[0] && !multi; j++) { @@ -1187,7 +1199,8 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, n = rcu_dereference_bh(hbucket(t, key)); if (!n) continue; - for (i = 0; i < n->pos; i++) { + pos = smp_load_acquire(&n->pos); + for (i = 0; i < pos; i++) { if (!test_bit(i, n->used)) continue; data = ahash_data(n, i, set->dsize); @@ -1221,6 +1234,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct mtype_elem *data; int i, ret = 0; u32 key, multi = 0; + u8 pos; rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); @@ -1243,7 +1257,8 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, ret = 0; goto out; } - for (i = 0; i < n->pos; i++) { + pos = smp_load_acquire(&n->pos); + for (i = 0; i < pos; i++) { if (!test_bit(i, n->used)) continue; data = ahash_data(n, i, set->dsize); @@ -1360,6 +1375,7 @@ mtype_list(const struct ip_set *set, /* We assume that one hash bucket fills into one page */ void *incomplete; int i, ret = 0; + u8 pos; atd = nla_nest_start(skb, IPSET_ATTR_ADT); if (!atd) @@ -1378,7 +1394,8 @@ mtype_list(const struct ip_set *set, cb->args[IPSET_CB_ARG0], t, n); if (!n) continue; - for (i = 0; i < n->pos; i++) { + pos = smp_load_acquire(&n->pos); + for (i = 0; i < pos; i++) { if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index a22ec1a6f6ec..e26ca2a370e3 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -150,7 +150,7 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++, i++) { + for (; ip <= ip_to; i++) { e.ip = htonl(ip); if (i > IPSET_MAX_RANGE) { hash_ipmark4_data_next(&h->next, &e); @@ -162,6 +162,10 @@ hash_ipmark4_uadt(struct ip_set *set, struct nlattr *tb[], return ret; ret = 0; + + if (ip == ip_to) + break; + ip++; } return ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index e977b5a9c48d..41ca24a22a02 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -186,7 +186,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to;) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++, i++) { @@ -203,6 +203,9 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], ret = 0; } + if (ip == ip_to) + break; + ip++; } return ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 39a01934b153..b9ac2efaa15c 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -182,7 +182,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (retried) ip = ntohl(h->next.ip); - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to;) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++, i++) { @@ -199,6 +199,9 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], ret = 0; } + if (ip == ip_to) + break; + ip++; } return ret; } diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 5c6de605a9fb..2d6652d43199 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -274,7 +274,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], p = port; ip2 = ip2_from; } - for (; ip <= ip_to; ip++) { + for (; ip <= ip_to;) { e.ip = htonl(ip); for (; p <= port_to; p++) { e.port = htons(p); @@ -298,6 +298,9 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], ip2 = ip2_from; } p = port; + if (ip == ip_to) + break; + ip++; } return ret; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c7c7f6a7a9f6..bd9cae44d214 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -327,18 +327,22 @@ ip_vs_use_count_dec(void) /* Service hashing: * Operation Locking order * --------------------------------------------------------------------------- - * add table service_mutex, svc_resize_sem(W) - * del table service_mutex - * move between tables svc_resize_sem(W), seqcount_t(W), bit lock - * add/del service service_mutex, bit lock + * add first table service_mutex + * attach new table service_mutex + * add/del service service_mutex, RCU, bit lock + * move between tables (rehash) svc_resize_sem(W), seqcount_t(W), bit lock + * replace old with attached svc_resize_sem(W), svc_replace_sem(W) * find service RCU, seqcount_t(R) * walk services(blocking) service_mutex, svc_resize_sem(R) * walk services(non-blocking) RCU, seqcount_t(R) + * walk services(non-blocking) svc_resize_sem(R), RCU, seqcount_t(R) + * walk services(non-blocking) svc_replace_sem(R), RCU, seqcount_t(R) + * del table service_mutex after stopped work * - * - new tables are linked/unlinked under service_mutex and svc_resize_sem - * - new table is linked on resizing and all operations can run in parallel - * in 2 tables until the new table is registered as current one - * - two contexts can modify buckets: config and table resize, both in + * - new table is attached on resizing under service_mutex and all operations + * can run in parallel in 2 tables until the new table is registered as current + * one + * - two contexts can modify buckets: config and table resize (work), both in * process context * - only table resizer can move entries, so we do not protect t->seqc[] * items with t->lock[] @@ -346,9 +350,13 @@ ip_vs_use_count_dec(void) * services are moved to new table * - move operations may disturb readers: find operation will not miss entries * but walkers may see same entry twice if they are forced to retry chains - * - walkers using cond_resched_rcu() on !PREEMPT_RCU may need to hold - * service_mutex to disallow new tables to be installed or to check + * or to walk the newly attached second table + * - walkers using cond_resched_rcu() on !PREEMPT_RCU may need to check * svc_table_changes and repeat the RCU read section if new table is installed + * - walkers may serialize with the whole resizing process (svc_resize_sem) + * to prevent seeing same service twice or just with the svc_table + * replace (svc_replace_sem) when we can see entries twice but we + * prefer to run concurrently with the rehashing. */ /* @@ -387,9 +395,16 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) /* increase its refcnt because it is referenced by the svc table */ atomic_inc(&svc->refcnt); + /* We know if new table is attached under service_mutex but rely on + * RCU to hold the old table to be freed in resizer + */ + rcu_read_lock(); + + /* This can be the old or the new table */ + t = rcu_dereference(ipvs->svc_table); + /* New entries go into recent table */ - t = rcu_dereference_protected(ipvs->svc_table, 1); - t = rcu_dereference_protected(t->new_tbl, 1); + t = rcu_dereference(t->new_tbl); if (svc->fwmark == 0) { /* @@ -410,6 +425,8 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) hlist_bl_add_head_rcu(&svc->s_list, head); hlist_bl_unlock(head); + rcu_read_unlock(); + return 1; } @@ -432,7 +449,13 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) return 0; } - t = rcu_dereference_protected(ipvs->svc_table, 1); + /* We know if new table is attached under service_mutex but rely on + * RCU to hold the old table to be freed in resizer + */ + rcu_read_lock(); + + /* This can be the old or the new table */ + t = rcu_dereference(ipvs->svc_table); hash_key = READ_ONCE(svc->hash_key); /* We need to lock the bucket in the right table */ if (ip_vs_rht_same_table(t, hash_key)) { @@ -443,13 +466,13 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) /* Moved to new table ? */ if (hash_key != hash_key2) { hlist_bl_unlock(head); - t = rcu_dereference_protected(t->new_tbl, 1); + t = rcu_dereference(t->new_tbl); head = t->buckets + (hash_key2 & t->mask); hlist_bl_lock(head); } } else { /* It is already moved to new table */ - t = rcu_dereference_protected(t->new_tbl, 1); + t = rcu_dereference(t->new_tbl); head = t->buckets + (hash_key & t->mask); hlist_bl_lock(head); } @@ -459,6 +482,8 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) svc->flags &= ~IP_VS_SVC_F_HASHED; atomic_dec(&svc->refcnt); hlist_bl_unlock(head); + + rcu_read_unlock(); return 1; } @@ -666,15 +691,14 @@ static void svc_resize_work_handler(struct work_struct *work) goto unlock_sem; more_work = false; clear_bit(IP_VS_WORK_SVC_RESIZE, &ipvs->work_flags); - if (!READ_ONCE(ipvs->enable) || - test_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags)) + if (!READ_ONCE(ipvs->enable)) goto unlock_m; t = rcu_dereference_protected(ipvs->svc_table, 1); /* Do nothing if table is removed */ if (!t) goto unlock_m; - /* New table needs to be registered? BUG! */ - if (t != rcu_dereference_protected(t->new_tbl, 1)) + /* New table already attached? BUG! */ + if (t != rcu_access_pointer(t->new_tbl)) goto unlock_m; lfactor = sysctl_svc_lfactor(ipvs); @@ -691,6 +715,7 @@ static void svc_resize_work_handler(struct work_struct *work) /* Flip the table_id */ t_new->table_id = t->table_id ^ IP_VS_RHT_TABLE_ID_MASK; + /* Attach new table */ rcu_assign_pointer(t->new_tbl, t_new); /* Allow add/del to new_tbl while moving from old table */ mutex_unlock(&ipvs->service_mutex); @@ -698,8 +723,8 @@ static void svc_resize_work_handler(struct work_struct *work) ip_vs_rht_for_each_bucket(t, bucket, head) { same_bucket: if (++limit >= 16) { - if (!READ_ONCE(ipvs->enable) || - test_bit(IP_VS_WORK_SVC_NORESIZE, + /* Check if work is stopped */ + if (test_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags)) goto unlock_sem; if (resched_score >= 100) { @@ -764,16 +789,12 @@ static void svc_resize_work_handler(struct work_struct *work) goto same_bucket; } - /* Tables can be switched only under service_mutex */ - while (!mutex_trylock(&ipvs->service_mutex)) { - cond_resched(); - if (!READ_ONCE(ipvs->enable) || - test_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags)) - goto unlock_sem; - } - if (!READ_ONCE(ipvs->enable) || - test_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags)) - goto unlock_m; + /* Serialize with readers that don't like svc_table changes */ + down_write(&ipvs->svc_replace_sem); + + /* Check if work is stopped to avoid synchronize_rcu() */ + if (test_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags)) + goto unlock_repl; rcu_assign_pointer(ipvs->svc_table, t_new); /* Inform readers that new table is installed */ @@ -781,8 +802,8 @@ static void svc_resize_work_handler(struct work_struct *work) atomic_inc(&ipvs->svc_table_changes); t_free = t; -unlock_m: - mutex_unlock(&ipvs->service_mutex); +unlock_repl: + up_write(&ipvs->svc_replace_sem); unlock_sem: up_write(&ipvs->svc_resize_sem); @@ -801,6 +822,11 @@ static void svc_resize_work_handler(struct work_struct *work) test_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags)) return; queue_delayed_work(system_unbound_wq, &ipvs->svc_resize_work, 1); + return; + +unlock_m: + mutex_unlock(&ipvs->service_mutex); + goto unlock_sem; } static inline void @@ -1691,6 +1717,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_pe *pe = NULL; int ret_hooks = -1; int ret = 0; + bool grow; /* increase the module use count */ if (!ip_vs_use_count_inc()) @@ -1732,16 +1759,25 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, } #endif - t = rcu_dereference_protected(ipvs->svc_table, 1); + /* The old table can be freed, protect it with RCU */ + rcu_read_lock(); + t = rcu_dereference(ipvs->svc_table); if (!t) { int lfactor = sysctl_svc_lfactor(ipvs); int new_size = ip_vs_svc_desired_size(ipvs, NULL, lfactor); + rcu_read_unlock(); t_new = ip_vs_svc_table_alloc(ipvs, new_size, lfactor); if (!t_new) { ret = -ENOMEM; goto out_err; } + grow = false; + } else { + /* Even the currently attached new table may need to grow */ + t = rcu_dereference(t->new_tbl); + grow = ip_vs_get_num_services(ipvs) + 1 > t->u_thresh; + rcu_read_unlock(); } if (!rcu_dereference_protected(ipvs->conn_tab, 1)) { @@ -1800,6 +1836,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, goto out_err; if (t_new) { + /* Add table for first time */ clear_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags); rcu_assign_pointer(ipvs->svc_table, t_new); t_new = NULL; @@ -1831,8 +1868,7 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ip_vs_svc_hash(svc); /* Schedule resize work */ - if (t && ip_vs_get_num_services(ipvs) > t->u_thresh && - !test_and_set_bit(IP_VS_WORK_SVC_RESIZE, &ipvs->work_flags)) + if (grow && !test_and_set_bit(IP_VS_WORK_SVC_RESIZE, &ipvs->work_flags)) queue_delayed_work(system_unbound_wq, &ipvs->svc_resize_work, 1); @@ -2054,7 +2090,6 @@ static int ip_vs_del_service(struct ip_vs_service *svc) return -EEXIST; ipvs = svc->ipvs; ip_vs_unlink_service(svc, false); - t = rcu_dereference_protected(ipvs->svc_table, 1); /* Drop the table if no more services */ ns = ip_vs_get_num_services(ipvs); @@ -2062,6 +2097,7 @@ static int ip_vs_del_service(struct ip_vs_service *svc) /* Stop the resizer and drop the tables */ set_bit(IP_VS_WORK_SVC_NORESIZE, &ipvs->work_flags); cancel_delayed_work_sync(&ipvs->svc_resize_work); + t = rcu_dereference_protected(ipvs->svc_table, 1); if (t) { rcu_assign_pointer(ipvs->svc_table, NULL); /* Inform readers that table is removed */ @@ -2075,11 +2111,19 @@ static int ip_vs_del_service(struct ip_vs_service *svc) t = p; } } - } else if (ns <= t->l_thresh && - !test_and_set_bit(IP_VS_WORK_SVC_RESIZE, - &ipvs->work_flags)) { - queue_delayed_work(system_unbound_wq, &ipvs->svc_resize_work, - 1); + } else { + bool shrink; + + rcu_read_lock(); + t = rcu_dereference(ipvs->svc_table); + /* Even the currently attached new table may need to shrink */ + t = rcu_dereference(t->new_tbl); + shrink = ns <= t->l_thresh; + rcu_read_unlock(); + if (shrink && !test_and_set_bit(IP_VS_WORK_SVC_RESIZE, + &ipvs->work_flags)) + queue_delayed_work(system_unbound_wq, + &ipvs->svc_resize_work, 1); } return 0; } @@ -2184,17 +2228,21 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, struct ip_vs_service *svc; struct hlist_bl_node *e; struct ip_vs_dest *dest; - int old_gen, new_gen; + int old_gen; if (event != NETDEV_DOWN || !ipvs) return NOTIFY_DONE; IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); + /* Allow concurrent rehashing on resize but to avoid loop + * serialize with installing the new table. + */ + down_read(&ipvs->svc_replace_sem); + old_gen = atomic_read(&ipvs->svc_table_changes); rcu_read_lock(); -repeat: smp_rmb(); /* ipvs->svc_table and svc_table_changes */ ip_vs_rht_walk_buckets_rcu(ipvs->svc_table, head) { hlist_bl_for_each_entry_rcu(svc, e, head, s_list) { @@ -2207,17 +2255,17 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, } resched_score++; if (resched_score >= 100) { - resched_score = 0; cond_resched_rcu(); - new_gen = atomic_read(&ipvs->svc_table_changes); - /* New table installed ? */ - if (old_gen != new_gen) { - old_gen = new_gen; - goto repeat; - } + /* Flushed? So no more dev refs */ + if (atomic_read(&ipvs->svc_table_changes) != old_gen) + goto done; + resched_score = 0; } } + +done: rcu_read_unlock(); + up_read(&ipvs->svc_replace_sem); return NOTIFY_DONE; } @@ -2244,6 +2292,10 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs) struct ip_vs_service *svc; struct hlist_bl_node *e; + /* svc_table can not be replaced (svc_replace_sem) or + * removed (service_mutex) + */ + down_read(&ipvs->svc_replace_sem); rcu_read_lock(); ip_vs_rht_walk_buckets_rcu(ipvs->svc_table, head) { @@ -2259,6 +2311,7 @@ static int ip_vs_zero_all(struct netns_ipvs *ipvs) } rcu_read_unlock(); + up_read(&ipvs->svc_replace_sem); ip_vs_zero_stats(&ipvs->tot_stats->s); return 0; @@ -3062,6 +3115,7 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) u32 sum; int i; + /* Info for conns */ rcu_read_lock(); t = rcu_dereference(ipvs->conn_tab); @@ -3123,6 +3177,12 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) } after_conns: + rcu_read_unlock(); + + /* Info for services */ + down_read(&ipvs->svc_replace_sem); + rcu_read_lock(); + t = rcu_dereference(ipvs->svc_table); count = ip_vs_get_num_services(ipvs); @@ -3133,9 +3193,7 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) if (!count) goto after_svc; old_gen = atomic_read(&ipvs->svc_table_changes); - loops = 0; -repeat_svc: smp_rmb(); /* ipvs->svc_table and svc_table_changes */ memset(counts, 0, sizeof(counts)); ip_vs_rht_for_each_table_rcu(ipvs->svc_table, t, pt) { @@ -3157,15 +3215,10 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) if (resched_score >= 100) { resched_score = 0; cond_resched_rcu(); - new_gen = atomic_read(&ipvs->svc_table_changes); - /* New table installed ? */ - if (old_gen != new_gen) { - /* Too many changes? */ - if (++loops >= 5) - goto after_svc; - old_gen = new_gen; - goto repeat_svc; - } + /* Flushed? */ + if (atomic_read(&ipvs->svc_table_changes) != + old_gen) + goto after_svc; } counts[count]++; } @@ -3184,6 +3237,9 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) } after_svc: + rcu_read_unlock(); + up_read(&ipvs->svc_replace_sem); + seq_printf(seq, "Stats thread slots:\t%d (max %lu)\n", ipvs->est_kt_count, ipvs->est_max_threads); seq_printf(seq, "Stats chain max len:\t%d\n", ipvs->est_chain_max); @@ -3191,7 +3247,6 @@ static int ip_vs_status_show(struct seq_file *seq, void *v) ipvs->est_chain_max * IPVS_EST_CHAIN_FACTOR * IPVS_EST_NTICKS); - rcu_read_unlock(); return 0; } @@ -3503,7 +3558,7 @@ __ip_vs_get_service_entries(struct netns_ipvs *ipvs, int ret = 0; lockdep_assert_held(&ipvs->svc_resize_sem); - /* All service modifications are disabled, go ahead */ + /* All svc_table modifications are disabled, go ahead */ ip_vs_rht_walk_buckets(ipvs->svc_table, head) { hlist_bl_for_each_entry(svc, e, head, s_list) { /* Only expose IPv4 entries to old interface */ @@ -3687,7 +3742,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) pr_err("length: %u != %zu\n", *len, size); return -EINVAL; } - /* Protect against table resizer moving the entries. + /* Prevent modifications to the list with services. * Try reverse locking, so that we do not hold the mutex * while waiting for semaphore. */ @@ -4029,6 +4084,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, int start = cb->args[0]; int idx = 0; + /* Make sure we do not see same service twice during resize */ down_read(&ipvs->svc_resize_sem); rcu_read_lock(); ip_vs_rht_walk_buckets_safe_rcu(ipvs->svc_table, head) { @@ -5072,6 +5128,7 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) /* Initialize service_mutex, svc_table per netns */ __mutex_init(&ipvs->service_mutex, "ipvs->service_mutex", &__ipvs_service_key); init_rwsem(&ipvs->svc_resize_sem); + init_rwsem(&ipvs->svc_replace_sem); INIT_DELAYED_WORK(&ipvs->svc_resize_work, svc_resize_work_handler); atomic_set(&ipvs->svc_table_changes, 0); RCU_INIT_POINTER(ipvs->svc_table, NULL); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index b594cd244fe1..17e971bd4c74 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -321,8 +321,8 @@ __printf(3, 4) void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, const char *fmt, ...) { + const char *helper_name = "(null)"; const struct nf_conn_help *help; - const struct nf_conntrack_helper *helper; struct va_format vaf; va_list args; @@ -331,14 +331,17 @@ void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, vaf.fmt = fmt; vaf.va = &args; - /* Called from the helper function, this call never fails */ help = nfct_help(ct); + if (help) { + const struct nf_conntrack_helper *helper; - /* rcu_read_lock()ed by nf_hook_thresh */ - helper = rcu_dereference(help->helper); + helper = rcu_dereference(help->helper); + if (helper) + helper_name = helper->name; + } nf_log_packet(nf_ct_net(ct), nf_ct_l3num(ct), 0, skb, NULL, NULL, NULL, - "nf_ct_%s: dropping packet: %pV ", helper->name, &vaf); + "helper %s dropping packet: %pV ", helper_name, &vaf); va_end(args); } diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index a6c81c04b3a5..57b450024a99 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -61,6 +61,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) struct nf_hook_state *state = &entry->state; /* Release those devices we held, or Alexey will kill me. */ + dev_put(entry->skb_dev); dev_put(state->in); dev_put(state->out); if (state->sk) @@ -102,6 +103,7 @@ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt)) return false; + dev_hold(entry->skb_dev); dev_hold(state->in); dev_hold(state->out); @@ -202,11 +204,11 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, *entry = (struct nf_queue_entry) { .skb = skb, + .skb_dev = skb->dev, .state = *state, .hook_index = index, .size = sizeof(*entry) + route_key_size, }; - __nf_queue_entry_init_physdevs(entry); if (!nf_queue_entry_get_refs(entry)) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 58304fd1f70f..984a0eb9e149 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1212,6 +1212,8 @@ dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex) if (physinif == ifindex || physoutif == ifindex) return 1; #endif + if (entry->skb_dev && entry->skb_dev->ifindex == ifindex) + return 1; if (entry->state.in) if (entry->state.in->ifindex == ifindex) return 1; diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 03ffb1159fc1..d14ca157910b 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -163,7 +163,6 @@ static int nft_inner_parse_l2l3(const struct nft_inner *priv, return -1; if (fragoff == 0) { - thoff = nhoff + sizeof(_ip6h); ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; ctx->inner_thoff = thoff; ctx->l4proto = l4proto; @@ -247,8 +246,8 @@ static bool nft_inner_restore_tun_ctx(const struct nft_pktinfo *pkt, local_lock_nested_bh(&nft_pcpu_tun_ctx.bh_lock); this_cpu_tun_ctx = this_cpu_ptr(&nft_pcpu_tun_ctx.ctx); if (this_cpu_tun_ctx->cookie != (unsigned long)pkt->skb) { - local_bh_enable(); local_unlock_nested_bh(&nft_pcpu_tun_ctx.bh_lock); + local_bh_enable(); return false; } *tun_ctx = *this_cpu_tun_ctx; diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c index c42642075685..e7e8490a53d8 100644 --- a/net/openvswitch/vport-netdev.c +++ b/net/openvswitch/vport-netdev.c @@ -83,6 +83,14 @@ struct vport *ovs_netdev_link(struct vport *vport, bool tunnel) } rtnl_lock(); + /* Do not link devices that are not registered to avoid a potential + * race with the NETDEV_UNREGISTER notification in dp_device_event(). + */ + if (vport->dev->reg_state != NETREG_REGISTERED) { + err = -ENODEV; + goto error_put_unlock; + } + err = netdev_master_upper_dev_link(vport->dev, get_dpdev(vport->dp), NULL, NULL, NULL); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 4dbf0914df7d..706927139393 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -671,8 +671,23 @@ static int pep_do_rcv(struct sock *sk, struct sk_buff *skb) /* Look for an existing pipe handle */ sknode = pep_find_pipe(&pn->hlist, &dst, pipe_handle); - if (sknode) - return sk_receive_skb(sknode, skb, 1); + if (sknode) { + int rc; + + /* pep_do_rcv() runs from two contexts: from softirq via + * phonet_rcv() -> __sk_receive_skb() with BH disabled, + * and from process context via + * release_sock() -> __release_sock(), which drops + * the listener slock with spin_unlock_bh() before draining + * the backlog. The child pipe slock is taken below via + * bh_lock_sock_nested(), which does not itself disable BH, so + * disable BH here to keep both acquire contexts consistent. + */ + local_bh_disable(); + rc = sk_receive_skb(sknode, skb, 1); + local_bh_enable(); + return rc; + } switch (hdr->message_id) { case PNS_PEP_CONNECT_REQ: diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 654e23d13e3d..5830b31a1f37 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -198,8 +198,13 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp) rdsdebug("setting sock %p callbacks to tc %p\n", sock, tc); write_lock_bh(&sock->sk->sk_callback_lock); - /* done under the callback_lock to serialize with write_space */ + /* done under the callback_lock to serialize with write_space. + * Set t_sock inside rds_tcp_tc_list_lock so readers walking + * rds_tcp_tc_list under the same lock cannot observe an + * entry whose t_sock is NULL. + */ spin_lock(&rds_tcp_tc_list_lock); + tc->t_sock = sock; list_add_tail(&tc->t_list_item, &rds_tcp_tc_list); #if IS_ENABLED(CONFIG_IPV6) rds6_tcp_tc_count++; @@ -211,8 +216,6 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp) /* accepted sockets need our listen data ready undone */ if (sock->sk->sk_data_ready == rds_tcp_listen_data_ready) sock->sk->sk_data_ready = sock->sk->sk_user_data; - - tc->t_sock = sock; if (!tc->t_rtn) tc->t_rtn = net_generic(sock_net(sock->sk), rds_tcp_netid); tc->t_cpath = cp; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 27c2aa2dd023..98f2165159d7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -213,8 +213,6 @@ struct rxrpc_skb_priv { struct { u16 offset; /* Offset of data */ u16 len; /* Length of data */ - u8 flags; -#define RXRPC_RX_VERIFIED 0x01 }; struct { rxrpc_seq_t first_ack; /* First packet in acks table */ @@ -309,15 +307,16 @@ struct rxrpc_security { struct sk_buff *challenge); /* verify a response */ - int (*verify_response)(struct rxrpc_connection *, - struct sk_buff *); + int (*verify_response)(struct rxrpc_connection *conn, + struct sk_buff *response_skb, + void *response, unsigned int len); /* clear connection security */ void (*clear)(struct rxrpc_connection *); /* Default ticket -> key decoder */ int (*default_decode_ticket)(struct rxrpc_connection *conn, struct sk_buff *skb, - unsigned int ticket_offset, unsigned int ticket_len, + void *ticket, unsigned int ticket_len, struct key **_key); }; @@ -774,6 +773,11 @@ struct rxrpc_call { struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ struct sk_buff_head rx_queue; /* Queue of packets for this call to receive */ struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ + void *rx_dec_buffer; /* Decryption buffer */ + unsigned short rx_dec_bsize; /* rx_dec_buffer size */ + unsigned short rx_dec_offset; /* Decrypted packet data offset */ + unsigned short rx_dec_len; /* Decrypted packet data len */ + rxrpc_seq_t rx_dec_seq; /* Packet in decryption buffer */ rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ rxrpc_seq_t rx_consumed; /* Highest packet consumed */ diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 2b19b252225e..fec59d9338b9 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -332,27 +332,7 @@ bool rxrpc_input_call_event(struct rxrpc_call *call) saw_ack |= sp->hdr.type == RXRPC_PACKET_TYPE_ACK; - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && - sp->hdr.securityIndex != 0 && - (skb_cloned(skb) || - skb_has_frag_list(skb) || - skb_has_shared_frag(skb))) { - /* Unshare the packet so that it can be - * modified by in-place decryption. - */ - struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); - - if (nskb) { - rxrpc_new_skb(nskb, rxrpc_skb_new_unshared); - rxrpc_input_call_packet(call, nskb); - rxrpc_free_skb(nskb, rxrpc_skb_put_call_rx); - } else { - /* OOM - Drop the packet. */ - rxrpc_see_skb(skb, rxrpc_skb_see_unshare_nomem); - } - } else { - rxrpc_input_call_packet(call, skb); - } + rxrpc_input_call_packet(call, skb); rxrpc_free_skb(skb, rxrpc_skb_put_call_rx); did_receive = true; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f035f486c139..fcb9d38bb521 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -152,6 +152,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, spin_lock_init(&call->notify_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; + call->rx_pkt_offset = USHRT_MAX; call->tx_total_len = -1; call->tx_jumbo_max = 1; call->next_rx_timo = 20 * HZ; @@ -553,6 +554,7 @@ static void rxrpc_cleanup_rx_buffers(struct rxrpc_call *call) rxrpc_purge_queue(&call->recvmsg_queue); rxrpc_purge_queue(&call->rx_queue); rxrpc_purge_queue(&call->rx_oos_queue); + kfree(call->rx_dec_buffer); } /* diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 442414d90ba1..c96ca615b787 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -243,28 +243,22 @@ static void rxrpc_call_is_secure(struct rxrpc_call *call) static int rxrpc_verify_response(struct rxrpc_connection *conn, struct sk_buff *skb) { + unsigned int len = skb->len - sizeof(struct rxrpc_wire_header); + void *buffer; int ret; - if (skb_cloned(skb) || skb_has_frag_list(skb) || - skb_has_shared_frag(skb)) { - /* Copy the packet if shared so that we can do in-place - * decryption. - */ - struct sk_buff *nskb = skb_copy(skb, GFP_NOFS); + buffer = kmalloc(len, GFP_NOFS); + if (!buffer) + return -ENOMEM; - if (nskb) { - rxrpc_new_skb(nskb, rxrpc_skb_new_unshared); - ret = conn->security->verify_response(conn, nskb); - rxrpc_free_skb(nskb, rxrpc_skb_put_response_copy); - } else { - /* OOM - Drop the packet. */ - rxrpc_see_skb(skb, rxrpc_skb_see_unshare_nomem); - ret = -ENOMEM; - } - } else { - ret = conn->security->verify_response(conn, skb); - } + ret = skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), buffer, len); + if (ret < 0) + goto out; + ret = conn->security->verify_response(conn, skb, buffer, len); + +out: + kfree(buffer); return ret; } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 0a260df45d25..0b39046bdc61 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -32,9 +32,6 @@ static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - sp->flags |= RXRPC_RX_VERIFIED; return 0; } @@ -57,9 +54,10 @@ static int none_sendmsg_respond_to_challenge(struct sk_buff *challenge, } static int none_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb) + struct sk_buff *response_skb, + void *response, unsigned int len) { - return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + return rxrpc_abort_conn(conn, response_skb, RX_PROTOCOL_ERROR, -EPROTO, rxrpc_eproto_rxnull_response); } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index e1f7513a46db..c940600117a4 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -147,15 +147,52 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) } /* - * Decrypt and verify a DATA packet. + * Decrypt and verify a DATA packet. The content of the packet is pulled out + * into a flat buffer rather than decrypting in place in the skbuff. This also + * has the advantage of aligning the buffer correctly for the crypto routines. + * + * We keep track of the sequence number of the packet currently decrypted into + * the buffer in ->rx_dec_seq. If MSG_PEEK is used and steps onto a new + * packet, subsequent recvmsg() calls will have to go back and re-decrypt the + * current packet. */ static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + int ret; - if (sp->flags & RXRPC_RX_VERIFIED) - return 0; - return call->security->verify_packet(call, skb); + if (sp->len > call->rx_dec_bsize) { + /* Make sure we can hold a 1412-byte jumbo subpacket and make + * sure that the buffer size is aligned to a crypto blocksize. + */ + size_t size = clamp(round_up(sp->len, 32), 2048, 65535); + void *buffer = krealloc(call->rx_dec_buffer, size, GFP_NOFS); + + if (!buffer) + return -ENOMEM; + call->rx_dec_buffer = buffer; + call->rx_dec_bsize = size; + } + + ret = -EFAULT; + if (skb_copy_bits(skb, sp->offset, call->rx_dec_buffer, sp->len) < 0) + goto err; + + call->rx_dec_offset = 0; + call->rx_dec_len = sp->len; + call->rx_dec_seq = sp->hdr.seq; + ret = call->security->verify_packet(call, skb); + if (ret < 0) + goto err; + return 0; + +err: + kfree(call->rx_dec_buffer); + call->rx_dec_buffer = NULL; + call->rx_dec_bsize = 0; + call->rx_dec_offset = 0; + call->rx_dec_len = 0; + return ret; } /* @@ -283,16 +320,21 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (msg) sock_recv_timestamp(msg, sock->sk, skb); - if (rx_pkt_offset == 0) { + if (call->rx_dec_seq != sp->hdr.seq || + !call->rx_dec_buffer) { ret2 = rxrpc_verify_data(call, skb); trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, - sp->offset, sp->len, ret2); + call->rx_dec_offset, + call->rx_dec_len, ret2); if (ret2 < 0) { ret = ret2; goto out; } - rx_pkt_offset = sp->offset; - rx_pkt_len = sp->len; + } + + if (rx_pkt_offset == USHRT_MAX) { + rx_pkt_offset = call->rx_dec_offset; + rx_pkt_len = call->rx_dec_len; } else { trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, rx_pkt_offset, rx_pkt_len, 0); @@ -304,10 +346,10 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (copy > remain) copy = remain; if (copy > 0) { - ret2 = skb_copy_datagram_iter(skb, rx_pkt_offset, iter, - copy); - if (ret2 < 0) { - ret = ret2; + ret2 = copy_to_iter(call->rx_dec_buffer + rx_pkt_offset, + copy, iter); + if (ret2 != copy) { + ret = -EFAULT; goto out; } @@ -328,7 +370,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, /* The whole packet has been transferred. */ if (sp->hdr.flags & RXRPC_LAST_PACKET) ret = 1; - rx_pkt_offset = 0; + rx_pkt_offset = USHRT_MAX; rx_pkt_len = 0; skb = skb_peek_next(skb, &call->recvmsg_queue); diff --git a/net/rxrpc/rxgk.c b/net/rxrpc/rxgk.c index 0d5e654da918..a1ee102abae1 100644 --- a/net/rxrpc/rxgk.c +++ b/net/rxrpc/rxgk.c @@ -473,15 +473,20 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxgk_header *hdr; struct krb5_buffer metadata; - unsigned int offset = sp->offset, len = sp->len; + unsigned int len = call->rx_dec_len; size_t data_offset = 0, data_len = len; + void *data = call->rx_dec_buffer, *p = data; u32 ac = 0; int ret = -ENOMEM; _enter(""); - crypto_krb5_where_is_the_data(gk->krb5, KRB5_CHECKSUM_MODE, - &data_offset, &data_len); + if (crypto_krb5_where_is_the_data(gk->krb5, KRB5_CHECKSUM_MODE, + &data_offset, &data_len) < 0) { + ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, + rxgk_abort_1_short_header); + goto put_gk; + } hdr = kzalloc_obj(*hdr, GFP_NOFS); if (!hdr) @@ -496,16 +501,15 @@ static int rxgk_verify_packet_integrity(struct rxrpc_call *call, metadata.len = sizeof(*hdr); metadata.data = hdr; - ret = rxgk_verify_mic_skb(gk->krb5, gk->rx_Kc, &metadata, - skb, &offset, &len, &ac); + ret = rxgk_verify_mic(gk->krb5, gk->rx_Kc, &metadata, &p, &len, &ac); kfree(hdr); if (ret < 0) { if (ret != -ENOMEM) rxrpc_abort_eproto(call, skb, ac, rxgk_abort_1_verify_mic_eproto); } else { - sp->offset = offset; - sp->len = len; + call->rx_dec_offset = p - data; + call->rx_dec_len = len; } put_gk: @@ -522,49 +526,53 @@ static int rxgk_verify_packet_encrypted(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxgk_header hdr; - unsigned int offset = sp->offset, len = sp->len; + struct rxgk_header *hdr; + unsigned int offset = 0, len = call->rx_dec_len; + void *data = call->rx_dec_buffer, *p = data; int ret; u32 ac = 0; _enter(""); - ret = rxgk_decrypt_skb(gk->krb5, gk->rx_enc, skb, &offset, &len, &ac); + if (crypto_krb5_check_data_len(gk->krb5, KRB5_ENCRYPT_MODE, + len, sizeof(*hdr)) < 0) { + ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, + rxgk_abort_2_short_header); + goto error; + } + + ret = rxgk_decrypt(gk->krb5, gk->rx_enc, &p, &len, &ac); if (ret < 0) { if (ret != -ENOMEM) rxrpc_abort_eproto(call, skb, ac, rxgk_abort_2_decrypt_eproto); goto error; } + offset = p - data; - if (len < sizeof(hdr)) { + if (len < sizeof(*hdr)) { ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, rxgk_abort_2_short_header); goto error; } /* Extract the header from the skb */ - ret = skb_copy_bits(skb, offset, &hdr, sizeof(hdr)); - if (ret < 0) { - ret = rxrpc_abort_eproto(call, skb, RXGK_PACKETSHORT, - rxgk_abort_2_short_encdata); - goto error; - } - offset += sizeof(hdr); - len -= sizeof(hdr); + hdr = data + offset; + offset += sizeof(*hdr); + len -= sizeof(*hdr); - if (ntohl(hdr.epoch) != call->conn->proto.epoch || - ntohl(hdr.cid) != call->cid || - ntohl(hdr.call_number) != call->call_id || - ntohl(hdr.seq) != sp->hdr.seq || - ntohl(hdr.sec_index) != call->security_ix || - ntohl(hdr.data_len) > len) { + if (ntohl(hdr->epoch) != call->conn->proto.epoch || + ntohl(hdr->cid) != call->cid || + ntohl(hdr->call_number) != call->call_id || + ntohl(hdr->seq) != sp->hdr.seq || + ntohl(hdr->sec_index) != call->security_ix || + ntohl(hdr->data_len) > len) { ret = rxrpc_abort_eproto(call, skb, RXGK_SEALEDINCON, rxgk_abort_2_short_data); goto error; } - sp->offset = offset; - sp->len = ntohl(hdr.data_len); + call->rx_dec_offset = offset; + call->rx_dec_len = ntohl(hdr->data_len); ret = 0; error: rxgk_put(gk); @@ -1076,11 +1084,12 @@ static int rxgk_sendmsg_respond_to_challenge(struct sk_buff *challenge, * unsigned int call_numbers<>; * }; */ -static int rxgk_do_verify_authenticator(struct rxrpc_connection *conn, - const struct krb5_enctype *krb5, - struct sk_buff *skb, - __be32 *p, __be32 *end) +static int rxgk_verify_authenticator(struct rxrpc_connection *conn, + const struct krb5_enctype *krb5, + struct sk_buff *skb, + void *auth, unsigned int auth_len) { + __be32 *p = auth, *end = auth + auth_len; u32 app_len, call_count, level, epoch, cid, i; _enter(""); @@ -1143,37 +1152,6 @@ static int rxgk_do_verify_authenticator(struct rxrpc_connection *conn, return 0; } -/* - * Extract the authenticator and verify it. - */ -static int rxgk_verify_authenticator(struct rxrpc_connection *conn, - const struct krb5_enctype *krb5, - struct sk_buff *skb, - unsigned int auth_offset, unsigned int auth_len) -{ - void *auth; - __be32 *p; - int ret; - - auth = kmalloc(auth_len, GFP_NOFS); - if (!auth) - return -ENOMEM; - - ret = skb_copy_bits(skb, auth_offset, auth, auth_len); - if (ret < 0) { - ret = rxrpc_abort_conn(conn, skb, RXGK_NOTAUTH, -EPROTO, - rxgk_abort_resp_short_auth); - goto error; - } - - p = auth; - ret = rxgk_do_verify_authenticator(conn, krb5, skb, p, - p + auth_len / sizeof(*p)); -error: - kfree(auth); - return ret; -} - /* * Verify a response. * @@ -1184,49 +1162,45 @@ static int rxgk_verify_authenticator(struct rxrpc_connection *conn, * }; */ static int rxgk_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb) + struct sk_buff *skb, + void *buffer, unsigned int len) { const struct krb5_enctype *krb5; struct rxrpc_key_token *token; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxgk_response rhdr; + struct rxgk_response *rhdr; struct rxgk_context *gk; struct key *key = NULL; - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len = skb->len - sizeof(struct rxrpc_wire_header); - unsigned int token_offset, token_len; - unsigned int auth_offset, auth_len; + unsigned int resp_token_len, auth_len; + void *resp_token, *auth; __be32 xauth_len; int ret, ec; _enter("{%d}", conn->debug_id); /* Parse the RXGK_Response object */ - if (sizeof(rhdr) + sizeof(__be32) > len) + if (len < sizeof(*rhdr) + sizeof(__be32)) + goto short_packet; + rhdr = buffer; + buffer += sizeof(*rhdr); + len -= sizeof(*rhdr); + + resp_token = buffer; + resp_token_len = ntohl(rhdr->token_len); + if (resp_token_len > len || + xdr_round_up(resp_token_len) + sizeof(__be32) > len) goto short_packet; - if (skb_copy_bits(skb, offset, &rhdr, sizeof(rhdr)) < 0) - goto short_packet; - offset += sizeof(rhdr); - len -= sizeof(rhdr); + trace_rxrpc_rx_response(conn, sp->hdr.serial, 0, sp->hdr.cksum, resp_token_len); - token_offset = offset; - token_len = ntohl(rhdr.token_len); - if (token_len > len || - xdr_round_up(token_len) + sizeof(__be32) > len) - goto short_packet; + buffer += xdr_round_up(resp_token_len); + len -= xdr_round_up(resp_token_len); - trace_rxrpc_rx_response(conn, sp->hdr.serial, 0, sp->hdr.cksum, token_len); - - offset += xdr_round_up(token_len); - len -= xdr_round_up(token_len); - - if (skb_copy_bits(skb, offset, &xauth_len, sizeof(xauth_len)) < 0) - goto short_packet; - offset += sizeof(xauth_len); + xauth_len = *(__be32 *)buffer; + buffer += sizeof(xauth_len); len -= sizeof(xauth_len); - auth_offset = offset; + auth = buffer; auth_len = ntohl(xauth_len); if (auth_len > len) goto short_packet; @@ -1241,7 +1215,7 @@ static int rxgk_verify_response(struct rxrpc_connection *conn, * to the app to deal with - which might mean a round trip to * userspace. */ - ret = rxgk_extract_token(conn, skb, token_offset, token_len, &key); + ret = rxgk_extract_token(conn, skb, resp_token, resp_token_len, &key); if (ret < 0) goto out; @@ -1255,7 +1229,7 @@ static int rxgk_verify_response(struct rxrpc_connection *conn, */ token = key->payload.data[0]; conn->security_level = token->rxgk->level; - conn->rxgk.start_time = __be64_to_cpu(rhdr.start_time); + conn->rxgk.start_time = __be64_to_cpu(rhdr->start_time); gk = rxgk_generate_transport_key(conn, token->rxgk, sp->hdr.cksum, GFP_NOFS); if (IS_ERR(gk)) { @@ -1265,18 +1239,18 @@ static int rxgk_verify_response(struct rxrpc_connection *conn, krb5 = gk->krb5; - trace_rxrpc_rx_response(conn, sp->hdr.serial, krb5->etype, sp->hdr.cksum, token_len); + trace_rxrpc_rx_response(conn, sp->hdr.serial, krb5->etype, sp->hdr.cksum, + resp_token_len); /* Decrypt, parse and verify the authenticator. */ - ret = rxgk_decrypt_skb(krb5, gk->resp_enc, skb, - &auth_offset, &auth_len, &ec); + ret = rxgk_decrypt(krb5, gk->resp_enc, &auth, &auth_len, &ec); if (ret < 0) { rxrpc_abort_conn(conn, skb, RXGK_SEALEDINCON, ret, rxgk_abort_resp_auth_dec); goto out_gk; } - ret = rxgk_verify_authenticator(conn, krb5, skb, auth_offset, auth_len); + ret = rxgk_verify_authenticator(conn, krb5, skb, auth, auth_len); if (ret < 0) goto out_gk; diff --git a/net/rxrpc/rxgk_app.c b/net/rxrpc/rxgk_app.c index 0ef2a29eb695..200a30064fae 100644 --- a/net/rxrpc/rxgk_app.c +++ b/net/rxrpc/rxgk_app.c @@ -40,7 +40,7 @@ * }; */ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, - unsigned int ticket_offset, unsigned int ticket_len, + void *buffer, unsigned int ticket_len, struct key **_key) { struct rxrpc_key_token *token; @@ -49,7 +49,7 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, size_t pre_ticket_len, payload_len; unsigned int klen, enctype; void *payload, *ticket; - __be32 *t, *p, *q, tmp[2]; + __be32 *t, *p, *q, *tmp; int ret; _enter(""); @@ -59,10 +59,7 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, rxgk_abort_resp_short_yfs_tkt); /* Get the session key length */ - ret = skb_copy_bits(skb, ticket_offset, tmp, sizeof(tmp)); - if (ret < 0) - return rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO, - rxgk_abort_resp_short_yfs_klen); + tmp = buffer; enctype = ntohl(tmp[0]); klen = ntohl(tmp[1]); @@ -84,12 +81,7 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, * it. */ ticket = payload + pre_ticket_len; - ret = skb_copy_bits(skb, ticket_offset, ticket, ticket_len); - if (ret < 0) { - ret = rxrpc_abort_conn(conn, skb, RXGK_INCONSISTENCY, -EPROTO, - rxgk_abort_resp_short_yfs_tkt); - goto error; - } + memcpy(ticket, buffer, ticket_len); /* Fill out the form header. */ p = payload; @@ -131,7 +123,7 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, goto error; } - /* Ticket read in with skb_copy_bits above */ + /* Ticket appended above. */ q += xdr_round_up(ticket_len) / 4; if (WARN_ON((unsigned long)q - (unsigned long)payload != payload_len)) { ret = -EIO; @@ -182,14 +174,15 @@ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, * [tools.ietf.org/html/draft-wilkinson-afs3-rxgk-afs-08 sec 6.1] */ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, - unsigned int token_offset, unsigned int token_len, + void *token, unsigned int token_len, struct key **_key) { const struct krb5_enctype *krb5; const struct krb5_buffer *server_secret; struct crypto_aead *token_enc = NULL; struct key *server_key; - unsigned int ticket_offset, ticket_len; + unsigned int ticket_len; + void *ticket; u32 kvno, enctype; int ret, ec = 0; @@ -197,24 +190,23 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, __be32 kvno; __be32 enctype; __be32 token_len; - } container; + } *container; - if (token_len < sizeof(container)) + if (token_len < sizeof(*container)) goto short_packet; /* Decode the RXGK_TokenContainer object. This tells us which server * key we should be using. We can then fetch the key, get the secret * and set up the crypto to extract the token. */ - if (skb_copy_bits(skb, token_offset, &container, sizeof(container)) < 0) - goto short_packet; + container = token; + token += sizeof(*container); - kvno = ntohl(container.kvno); - enctype = ntohl(container.enctype); - ticket_len = ntohl(container.token_len); - ticket_offset = token_offset + sizeof(container); + kvno = ntohl(container->kvno); + enctype = ntohl(container->enctype); + ticket_len = ntohl(container->token_len); - if (ticket_len > xdr_round_down(token_len - sizeof(container))) + if (ticket_len > xdr_round_down(token_len - sizeof(*container))) goto short_packet; _debug("KVNO %u", kvno); @@ -237,8 +229,8 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, * gain access to K0, from which we can derive the transport key and * thence decode the authenticator. */ - ret = rxgk_decrypt_skb(krb5, token_enc, skb, - &ticket_offset, &ticket_len, &ec); + ticket = token; + ret = rxgk_decrypt(krb5, token_enc, &ticket, &ticket_len, &ec); crypto_free_aead(token_enc); token_enc = NULL; if (ret < 0) { @@ -248,7 +240,7 @@ int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, return ret; } - ret = conn->security->default_decode_ticket(conn, skb, ticket_offset, + ret = conn->security->default_decode_ticket(conn, skb, ticket, ticket_len, _key); if (ret < 0) goto cant_get_token; diff --git a/net/rxrpc/rxgk_common.h b/net/rxrpc/rxgk_common.h index 1e257d7ab8ec..3deed5863f5a 100644 --- a/net/rxrpc/rxgk_common.h +++ b/net/rxrpc/rxgk_common.h @@ -41,10 +41,10 @@ struct rxgk_context { * rxgk_app.c */ int rxgk_yfs_decode_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, - unsigned int ticket_offset, unsigned int ticket_len, + void *ticket, unsigned int ticket_len, struct key **_key); int rxgk_extract_token(struct rxrpc_connection *conn, struct sk_buff *skb, - unsigned int token_offset, unsigned int token_len, + void *token, unsigned int token_len, struct key **_key); /* @@ -62,31 +62,30 @@ int rxgk_set_up_token_cipher(const struct krb5_buffer *server_key, gfp_t gfp); /* - * Apply decryption and checksumming functions to part of an skbuff. The - * offset and length are updated to reflect the actual content of the encrypted + * Apply decryption and checksumming functions a flat data buffer. The data + * point and length are updated to reflect the actual content of the encrypted * region. */ -static inline -int rxgk_decrypt_skb(const struct krb5_enctype *krb5, - struct crypto_aead *aead, - struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len, - int *_error_code) +static inline int rxgk_decrypt(const struct krb5_enctype *krb5, + struct crypto_aead *aead, + void **_data, unsigned int *_len, + int *_error_code) { - struct scatterlist sg[16]; + struct scatterlist sg[1]; size_t offset = 0, len = *_len; - int nr_sg, ret; + int ret; - sg_init_table(sg, ARRAY_SIZE(sg)); - nr_sg = skb_to_sgvec(skb, sg, *_offset, len); - if (unlikely(nr_sg < 0)) - return nr_sg; + sg_init_one(sg, *_data, len); - ret = crypto_krb5_decrypt(krb5, aead, sg, nr_sg, - &offset, &len); + ret = crypto_krb5_decrypt(krb5, aead, sg, 1, &offset, &len); switch (ret) { case 0: - *_offset += offset; + if (offset & 3) { + *_error_code = RXGK_INCONSISTENCY; + ret = -EPROTO; + break; + } + *_data += offset; *_len = len; break; case -EBADMSG: /* Checksum mismatch. */ @@ -106,31 +105,26 @@ int rxgk_decrypt_skb(const struct krb5_enctype *krb5, } /* - * Check the MIC on a region of an skbuff. The offset and length are updated - * to reflect the actual content of the secure region. + * Check the MIC on a flat buffer. The data pointer and length are updated to + * reflect the actual content of the secure region. */ static inline -int rxgk_verify_mic_skb(const struct krb5_enctype *krb5, - struct crypto_shash *shash, - const struct krb5_buffer *metadata, - struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len, - u32 *_error_code) +int rxgk_verify_mic(const struct krb5_enctype *krb5, + struct crypto_shash *shash, + const struct krb5_buffer *metadata, + void **_data, unsigned int *_len, + u32 *_error_code) { - struct scatterlist sg[16]; + struct scatterlist sg[1]; size_t offset = 0, len = *_len; - int nr_sg, ret; + int ret; - sg_init_table(sg, ARRAY_SIZE(sg)); - nr_sg = skb_to_sgvec(skb, sg, *_offset, len); - if (unlikely(nr_sg < 0)) - return nr_sg; + sg_init_one(sg, *_data, len); - ret = crypto_krb5_verify_mic(krb5, shash, metadata, sg, nr_sg, - &offset, &len); + ret = crypto_krb5_verify_mic(krb5, shash, metadata, sg, 1, &offset, &len); switch (ret) { case 0: - *_offset += offset; + *_data += offset; *_len = len; break; case -EBADMSG: /* Checksum mismatch */ diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index cba7935977f0..6fbd883401ac 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -430,27 +430,25 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, rxrpc_seq_t seq, struct skcipher_request *req) { - struct rxkad_level1_hdr sechdr; + struct rxkad_level1_hdr *sechdr; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; - struct scatterlist sg[16]; - u32 data_size, buf; + struct scatterlist sg[1]; + void *data = call->rx_dec_buffer; + u32 len = sp->len, data_size, buf; u16 check; int ret; _enter(""); - if (sp->len < 8) + if (len < 8) return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, rxkad_abort_1_short_header); /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. */ - sg_init_table(sg, ARRAY_SIZE(sg)); - ret = skb_to_sgvec(skb, sg, sp->offset, 8); - if (unlikely(ret < 0)) - return ret; + sg_init_one(sg, data, len); /* start the decryption afresh */ memset(&iv, 0, sizeof(iv)); @@ -464,13 +462,11 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, return ret; /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) - return rxrpc_abort_eproto(call, skb, RXKADDATALEN, - rxkad_abort_1_short_encdata); - sp->offset += sizeof(sechdr); - sp->len -= sizeof(sechdr); + sechdr = data; + call->rx_dec_offset = sizeof(*sechdr); + len -= sizeof(*sechdr); - buf = ntohl(sechdr.data_size); + buf = ntohl(sechdr->data_size); data_size = buf & 0xffff; check = buf >> 16; @@ -479,10 +475,10 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, if (check != 0) return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, rxkad_abort_1_short_check); - if (data_size > sp->len) + if (data_size > len) return rxrpc_abort_eproto(call, skb, RXKADDATALEN, rxkad_abort_1_short_data); - sp->len = data_size; + call->rx_dec_len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -496,43 +492,28 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr sechdr; + struct rxkad_level2_hdr *sechdr; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; - struct scatterlist _sg[4], *sg; - u32 data_size, buf; + struct scatterlist sg[1]; + void *data = call->rx_dec_buffer; + u32 len = sp->len, data_size, buf; u16 check; - int nsg, ret; + int ret; - _enter(",{%d}", sp->len); + _enter(",{%d}", len); - if (sp->len < 8) + if (len < 8) return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, rxkad_abort_2_short_header); /* Don't let the crypto algo see a misaligned length. */ - sp->len = round_down(sp->len, 8); + len = round_down(len, 8); - /* Decrypt the skbuff in-place. TODO: We really want to decrypt - * directly into the target buffer. + /* Decrypt in place in the call's decryption buffer. TODO: We really + * want to decrypt directly into the target buffer. */ - sg = _sg; - nsg = skb_shinfo(skb)->nr_frags + 1; - if (nsg <= 4) { - nsg = 4; - } else { - sg = kmalloc_objs(*sg, nsg, GFP_NOIO); - if (!sg) - return -ENOMEM; - } - - sg_init_table(sg, nsg); - ret = skb_to_sgvec(skb, sg, sp->offset, sp->len); - if (unlikely(ret < 0)) { - if (sg != _sg) - kfree(sg); - return ret; - } + sg_init_one(sg, data, len); /* decrypt from the session key */ token = call->conn->key->payload.data[0]; @@ -540,11 +521,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, sg, sg, sp->len, iv.x); + skcipher_request_set_crypt(req, sg, sg, len, iv.x); ret = crypto_skcipher_decrypt(req); skcipher_request_zero(req); - if (sg != _sg) - kfree(sg); if (ret < 0) { if (ret == -ENOMEM) return ret; @@ -553,13 +532,11 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) - return rxrpc_abort_eproto(call, skb, RXKADDATALEN, - rxkad_abort_2_short_len); - sp->offset += sizeof(sechdr); - sp->len -= sizeof(sechdr); + sechdr = data; + call->rx_dec_offset = sizeof(*sechdr); + len -= sizeof(*sechdr); - buf = ntohl(sechdr.data_size); + buf = ntohl(sechdr->data_size); data_size = buf & 0xffff; check = buf >> 16; @@ -569,17 +546,18 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, rxkad_abort_2_short_check); - if (data_size > sp->len) + if (data_size > len) return rxrpc_abort_eproto(call, skb, RXKADDATALEN, rxkad_abort_2_short_data); - sp->len = data_size; + call->rx_dec_len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; } /* - * Verify the security on a received packet and the subpackets therein. + * Verify the security on a received (sub)packet. If the packet needs + * modifying (e.g. decrypting), it must be copied. */ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { @@ -985,7 +963,6 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, *_expiry = 0; ASSERT(server_key->payload.data[0] != NULL); - ASSERTCMP((unsigned long) ticket & 7UL, ==, 0); memcpy(&iv, &server_key->payload.data[2], sizeof(iv)); @@ -1134,14 +1111,15 @@ static int rxkad_decrypt_response(struct rxrpc_connection *conn, * verify a response */ static int rxkad_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb) + struct sk_buff *skb, + void *buffer, unsigned int len) { struct rxkad_response *response; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt session_key; struct key *server_key; time64_t expiry; - void *ticket = NULL; + void *ticket; u32 version, kvno, ticket_len, level; __be32 csum; int ret, i; @@ -1164,13 +1142,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, } } - ret = -ENOMEM; - response = kzalloc_obj(struct rxkad_response, GFP_NOFS); - if (!response) - goto error; - - if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - response, sizeof(*response)) < 0) { + response = buffer; + if (len < sizeof(*response)) { ret = rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, rxkad_abort_resp_short); goto error; @@ -1182,6 +1155,9 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len); + buffer += sizeof(*response); + len -= sizeof(*response); + if (version != RXKAD_VERSION) { ret = rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO, rxkad_abort_resp_version); @@ -1201,13 +1177,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, } /* extract the kerberos ticket and decrypt and decode it */ - ret = -ENOMEM; - ticket = kmalloc(ticket_len, GFP_NOFS); - if (!ticket) - goto error; - - if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), - ticket, ticket_len) < 0) { + ticket = buffer; + if (ticket_len > len) { ret = rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, rxkad_abort_resp_short_tkt); goto error; @@ -1287,8 +1258,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, ret = rxrpc_get_server_data_key(conn, &session_key, expiry, kvno); error: - kfree(ticket); - kfree(response); key_put(server_key); _leave(" = %d", ret); return ret; diff --git a/net/shaper/shaper.c b/net/shaper/shaper.c index b1c65110f04d..dea9270f3e57 100644 --- a/net/shaper/shaper.c +++ b/net/shaper/shaper.c @@ -138,35 +138,58 @@ static int net_shaper_fill_handle(struct sk_buff *msg, return -EMSGSIZE; } +static void net_shaper_copy(struct net_shaper *dst, + const struct net_shaper *src) +{ + WRITE_ONCE(dst->parent.scope, READ_ONCE(src->parent.scope)); + WRITE_ONCE(dst->parent.id, READ_ONCE(src->parent.id)); + WRITE_ONCE(dst->handle.scope, READ_ONCE(src->handle.scope)); + WRITE_ONCE(dst->handle.id, READ_ONCE(src->handle.id)); + + WRITE_ONCE(dst->metric, READ_ONCE(src->metric)); + WRITE_ONCE(dst->bw_min, READ_ONCE(src->bw_min)); + WRITE_ONCE(dst->bw_max, READ_ONCE(src->bw_max)); + WRITE_ONCE(dst->burst, READ_ONCE(src->burst)); + WRITE_ONCE(dst->priority, READ_ONCE(src->priority)); + WRITE_ONCE(dst->weight, READ_ONCE(src->weight)); + + /* private fields are only used on the write path under the lock */ + data_race(dst->leaves = src->leaves); +} + static int net_shaper_fill_one(struct sk_buff *msg, const struct net_shaper_binding *binding, const struct net_shaper *shaper, const struct genl_info *info) { + struct net_shaper cur; void *hdr; hdr = genlmsg_iput(msg, info); if (!hdr) return -EMSGSIZE; + /* Make a copy to avoid data races */ + net_shaper_copy(&cur, shaper); + if (net_shaper_fill_binding(msg, binding, NET_SHAPER_A_IFINDEX) || - net_shaper_fill_handle(msg, &shaper->parent, + net_shaper_fill_handle(msg, &cur.parent, NET_SHAPER_A_PARENT) || - net_shaper_fill_handle(msg, &shaper->handle, + net_shaper_fill_handle(msg, &cur.handle, NET_SHAPER_A_HANDLE) || - ((shaper->bw_min || shaper->bw_max || shaper->burst) && - nla_put_u32(msg, NET_SHAPER_A_METRIC, shaper->metric)) || - (shaper->bw_min && - nla_put_uint(msg, NET_SHAPER_A_BW_MIN, shaper->bw_min)) || - (shaper->bw_max && - nla_put_uint(msg, NET_SHAPER_A_BW_MAX, shaper->bw_max)) || - (shaper->burst && - nla_put_uint(msg, NET_SHAPER_A_BURST, shaper->burst)) || - (shaper->priority && - nla_put_u32(msg, NET_SHAPER_A_PRIORITY, shaper->priority)) || - (shaper->weight && - nla_put_u32(msg, NET_SHAPER_A_WEIGHT, shaper->weight))) + ((cur.bw_min || cur.bw_max || cur.burst) && + nla_put_u32(msg, NET_SHAPER_A_METRIC, cur.metric)) || + (cur.bw_min && + nla_put_uint(msg, NET_SHAPER_A_BW_MIN, cur.bw_min)) || + (cur.bw_max && + nla_put_uint(msg, NET_SHAPER_A_BW_MAX, cur.bw_max)) || + (cur.burst && + nla_put_uint(msg, NET_SHAPER_A_BURST, cur.burst)) || + (cur.priority && + nla_put_u32(msg, NET_SHAPER_A_PRIORITY, cur.priority)) || + (cur.weight && + nla_put_u32(msg, NET_SHAPER_A_WEIGHT, cur.weight))) goto nla_put_failure; genlmsg_end(msg, hdr); @@ -283,31 +306,24 @@ static void net_shaper_default_parent(const struct net_shaper_handle *handle, parent->id = 0; } -/* MARK_0 is already in use due to XA_FLAGS_ALLOC. The VALID mark is set on - * an entry only after the device-side configuration has completed - * successfully (see net_shaper_commit()). Lookups and dumps must filter on - * this mark to avoid exposing tentative entries inserted by - * net_shaper_pre_insert() while the driver call is still in flight. - */ -#define NET_SHAPER_VALID XA_MARK_1 - static struct net_shaper * net_shaper_lookup(struct net_shaper_binding *binding, const struct net_shaper_handle *handle) { u32 index = net_shaper_handle_to_index(handle); struct net_shaper_hierarchy *hierarchy; + struct net_shaper *cur; hierarchy = net_shaper_hierarchy_rcu(binding); - if (!hierarchy || !xa_get_mark(&hierarchy->shapers, index, - NET_SHAPER_VALID)) + if (!hierarchy) return NULL; - /* Pairs with smp_wmb() in net_shaper_commit(): if the entry is - * valid, its contents must be visible too. - */ - smp_rmb(); - return xa_load(&hierarchy->shapers, index); + cur = xa_load(&hierarchy->shapers, index); + /* Check valid before reading fields */ + if (!cur || !smp_load_acquire(&cur->valid)) + return NULL; + + return cur; } /* Allocate on demand the per device shaper's hierarchy container. @@ -421,12 +437,10 @@ static void net_shaper_commit(struct net_shaper_binding *binding, if (WARN_ON_ONCE(!cur)) continue; - /* Successful update: drop the tentative mark - * and update the hierarchy container. - */ - *cur = shapers[i]; - smp_wmb(); - __xa_set_mark(&hierarchy->shapers, index, NET_SHAPER_VALID); + /* Successful update: update the hierarchy container... */ + net_shaper_copy(cur, &shapers[i]); + /* ... publish to lockless readers. */ + smp_store_release(&cur->valid, true); } xa_unlock(&hierarchy->shapers); } @@ -443,10 +457,10 @@ static void net_shaper_rollback(struct net_shaper_binding *binding) xa_lock(&hierarchy->shapers); xa_for_each(&hierarchy->shapers, index, cur) { - if (xa_get_mark(&hierarchy->shapers, index, NET_SHAPER_VALID)) + if (cur->valid) continue; __xa_erase(&hierarchy->shapers, index); - kfree(cur); + kfree_rcu(cur, rcu); } xa_unlock(&hierarchy->shapers); } @@ -859,12 +873,12 @@ int net_shaper_nl_get_dumpit(struct sk_buff *skb, goto out_unlock; for (; (shaper = xa_find(&hierarchy->shapers, &ctx->start_index, - U32_MAX, NET_SHAPER_VALID)); + U32_MAX, XA_PRESENT)); ctx->start_index++) { - /* Pairs with smp_wmb() in net_shaper_commit(): the entry - * is marked VALID, so its contents must be visible too. - */ - smp_rmb(); + /* Check valid before reading fields */ + if (!smp_load_acquire(&shaper->valid)) + continue; + ret = net_shaper_fill_one(skb, binding, shaper, info); if (ret) break; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 3bfdaf5e64f5..964ebc268ee4 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1366,9 +1366,14 @@ void tls_sw_splice_eof(struct socket *sock) mutex_unlock(&tls_ctx->tx_lock); } +/* When has_copied is true the caller has already moved bytes to + * userspace. Report sk_err but leave it set so the next read + * surfaces it instead of a spurious EOF, otherwise sk_err is + * consumed via sock_error(). + */ static int tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, - bool released) + bool released, bool has_copied) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1386,8 +1391,11 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, if (!sk_psock_queue_empty(psock)) return 0; - if (sk->sk_err) + if (sk->sk_err) { + if (has_copied) + return -READ_ONCE(sk->sk_err); return sock_error(sk); + } if (ret < 0) return ret; @@ -1423,7 +1431,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, } if (unlikely(!tls_strp_msg_load(&ctx->strp, released))) - return tls_rx_rec_wait(sk, psock, nonblock, false); + return tls_rx_rec_wait(sk, psock, nonblock, false, has_copied); return 1; } @@ -2110,7 +2118,7 @@ int tls_sw_recvmsg(struct sock *sk, int to_decrypt, chunk; err = tls_rx_rec_wait(sk, psock, flags & MSG_DONTWAIT, - released); + released, !!(decrypted + copied)); if (err <= 0) { if (psock) { chunk = sk_msg_recvmsg(sk, psock, msg, len, @@ -2297,7 +2305,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct tls_decrypt_arg darg; err = tls_rx_rec_wait(sk, NULL, flags & SPLICE_F_NONBLOCK, - true); + true, false); if (err <= 0) goto splice_read_end; @@ -2383,7 +2391,7 @@ int tls_sw_read_sock(struct sock *sk, read_descriptor_t *desc, } else { struct tls_decrypt_arg darg; - err = tls_rx_rec_wait(sk, NULL, true, released); + err = tls_rx_rec_wait(sk, NULL, true, released, !!copied); if (err <= 0) goto read_sock_end; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 1cbf36ea043b..dc71ed79be4a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2711,8 +2711,7 @@ static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor) * Sleep until more data has arrived. But check for races.. */ static long unix_stream_data_wait(struct sock *sk, long timeo, - struct sk_buff *last, unsigned int last_len, - bool freezable) + struct sk_buff *last, bool freezable) { unsigned int state = TASK_INTERRUPTIBLE | freezable * TASK_FREEZABLE; struct sk_buff *tail; @@ -2725,7 +2724,6 @@ static long unix_stream_data_wait(struct sock *sk, long timeo, tail = skb_peek_tail(&sk->sk_receive_queue); if (tail != last || - (tail && tail->len != last_len) || sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN) || signal_pending(current) || @@ -2921,7 +2919,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, int flags = state->flags; bool check_creds = false; struct scm_cookie scm; - unsigned int last_len; struct unix_sock *u; int copied = 0; int err = 0; @@ -2967,7 +2964,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, goto unlock; } last = skb = skb_peek(&sk->sk_receive_queue); - last_len = last ? last->len : 0; again: #if IS_ENABLED(CONFIG_AF_UNIX_OOB) @@ -3001,8 +2997,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, mutex_unlock(&u->iolock); - timeo = unix_stream_data_wait(sk, timeo, last, - last_len, freezable); + timeo = unix_stream_data_wait(sk, timeo, last, freezable); if (signal_pending(current)) { err = sock_intr_errno(timeo); @@ -3019,7 +3014,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, while (skip >= unix_skb_len(skb)) { skip -= unix_skb_len(skb); last = skb; - last_len = skb->len; skb = skb_peek_next(skb, &sk->sk_receive_queue); if (!skb) goto again; @@ -3094,7 +3088,6 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, skip = 0; last = skb; - last_len = skb->len; unix_state_lock(sk); skb = skb_peek_next(skb, &sk->sk_receive_queue); if (skb) diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 989cc252d3d3..df3b418e0392 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -70,34 +70,6 @@ static bool virtio_transport_can_zcopy(const struct virtio_transport *t_ops, return true; } -static int virtio_transport_init_zcopy_skb(struct vsock_sock *vsk, - struct sk_buff *skb, - struct msghdr *msg, - size_t pkt_len, - bool zerocopy) -{ - struct ubuf_info *uarg; - - if (msg->msg_ubuf) { - uarg = msg->msg_ubuf; - net_zcopy_get(uarg); - } else { - struct ubuf_info_msgzc *uarg_zc; - - uarg = msg_zerocopy_realloc(sk_vsock(vsk), - pkt_len, NULL, false); - if (!uarg) - return -1; - - uarg_zc = uarg_to_msgzc(uarg); - uarg_zc->zerocopy = zerocopy ? 1 : 0; - } - - skb_zcopy_init(skb, uarg); - - return 0; -} - static int virtio_transport_fill_skb(struct sk_buff *skb, struct virtio_vsock_pkt_info *info, size_t len, @@ -317,8 +289,10 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, u32 src_cid, src_port, dst_cid, dst_port; const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; + struct ubuf_info *uarg = NULL; u32 pkt_len = info->pkt_len; bool can_zcopy = false; + bool have_uref = false; u32 rest_len; int ret; @@ -360,6 +334,25 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, if (can_zcopy) max_skb_len = min_t(u32, VIRTIO_VSOCK_MAX_PKT_BUF_SIZE, (MAX_SKB_FRAGS * PAGE_SIZE)); + + if (info->msg->msg_flags & MSG_ZEROCOPY && + info->op == VIRTIO_VSOCK_OP_RW) { + uarg = info->msg->msg_ubuf; + + if (!uarg) { + uarg = msg_zerocopy_realloc(sk_vsock(vsk), + pkt_len, NULL, false); + if (!uarg) { + virtio_transport_put_credit(vvs, pkt_len); + return -ENOMEM; + } + + if (!can_zcopy) + uarg_to_msgzc(uarg)->zerocopy = 0; + + have_uref = true; + } + } } rest_len = pkt_len; @@ -378,27 +371,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, break; } - /* We process buffer part by part, allocating skb on - * each iteration. If this is last skb for this buffer - * and MSG_ZEROCOPY mode is in use - we must allocate - * completion for the current syscall. - * - * Pass pkt_len because msg iter is already consumed - * by virtio_transport_fill_skb(), so iter->count - * can not be used for RLIMIT_MEMLOCK pinned-pages - * accounting done by msg_zerocopy_realloc(). - */ - if (info->msg && info->msg->msg_flags & MSG_ZEROCOPY && - skb_len == rest_len && info->op == VIRTIO_VSOCK_OP_RW) { - if (virtio_transport_init_zcopy_skb(vsk, skb, - info->msg, - pkt_len, - can_zcopy)) { - kfree_skb(skb); - ret = -ENOMEM; - break; - } - } + skb_zcopy_set(skb, uarg, NULL); virtio_transport_inc_tx_pkt(vvs, skb); @@ -422,6 +395,18 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, virtio_transport_put_credit(vvs, rest_len); + /* msg_zerocopy_realloc() initializes the ubuf_info refcnt to 1. + * skb_zcopy_set() increases it for each skb, so we can drop that + * initial reference to keep it balanced. + */ + if (have_uref) { + if (rest_len == pkt_len) + /* No data sent, abort the notification. */ + net_zcopy_put_abort(uarg, true); + else + net_zcopy_put(uarg); + } + /* Return number of bytes, if any data has been sent. */ if (rest_len != pkt_len) ret = pkt_len - rest_len; @@ -434,7 +419,14 @@ static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, { u64 skb_overhead = (skb_queue_len(&vvs->rx_queue) + 1) * SKB_TRUESIZE(0); - if (skb_overhead + vvs->buf_used + len > vvs->buf_alloc) + /* Allow at most buf_alloc * 2 total budget (payload + overhead), + * similar to how SO_RCVBUF is doubled to reserve space for sk_buff + * metadata. Check payload against buf_alloc to be sure the other + * peer is respecting the credit, and sk_buff overhead to bound + * queue growth. + */ + if ((u64)vvs->buf_used + len > vvs->buf_alloc || + skb_overhead > vvs->buf_alloc) return false; vvs->rx_bytes += len; @@ -1350,7 +1342,7 @@ virtio_transport_recv_connecting(struct sock *sk, return err; } -static void +static bool virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct sk_buff *skb) { @@ -1365,10 +1357,8 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, spin_lock_bh(&vvs->rx_lock); can_enqueue = virtio_transport_inc_rx_pkt(vvs, len); - if (!can_enqueue) { - free_pkt = true; + if (!can_enqueue) goto out; - } if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) vvs->msg_count++; @@ -1408,6 +1398,8 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, spin_unlock_bh(&vvs->rx_lock); if (free_pkt) kfree_skb(skb); + + return can_enqueue; } static int @@ -1420,7 +1412,17 @@ virtio_transport_recv_connected(struct sock *sk, switch (le16_to_cpu(hdr->op)) { case VIRTIO_VSOCK_OP_RW: - virtio_transport_recv_enqueue(vsk, skb); + if (!virtio_transport_recv_enqueue(vsk, skb)) { + /* There is no more space to queue the packet, so let's + * close the connection; otherwise, we'll lose data. + */ + (void)virtio_transport_reset(vsk, skb); + virtio_transport_do_close(vsk, true); + sk->sk_err = ENOBUFS; + sk_error_report(sk); + vsock_remove_sock(vsk); + break; + } vsock_data_ready(sk); return err; case VIRTIO_VSOCK_OP_CREDIT_REQUEST: diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index 4296ca1183f1..d2579380f51e 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1164,7 +1164,7 @@ vmci_transport_recv_connecting_server(struct sock *listener, /* Close and cleanup the connection. */ vmci_transport_send_reset(pending, pkt); skerr = EPROTO; - err = pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST ? 0 : -EINVAL; + err = -EINVAL; goto destroy; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 328af43ef832..358cbc9e43d8 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2462,6 +2462,9 @@ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen, memcpy(merged_ie + copied_len, next_sub->data, next_sub->datalen); copied_len += next_sub->datalen; + + mbssid_elem = next_mbssid; + sub_elem = next_sub; } return copied_len; diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 22d9d9bae8f5..63d145b524c9 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -789,6 +789,8 @@ static int cfg80211_wext_siwfreq(struct net_device *dev, chandef.chan = ieee80211_get_channel(&rdev->wiphy, freq); if (!chandef.chan) return -EINVAL; + if (!cfg80211_chandef_valid(&chandef)) + return -EINVAL; return cfg80211_set_monitor_channel(rdev, dev, &chandef); case NL80211_IFTYPE_MESH_POINT: freq = cfg80211_wext_freq(wextfreq); diff --git a/scripts/gdb/linux/mm.py b/scripts/gdb/linux/mm.py index d78908f6664d..dffadccbb01d 100644 --- a/scripts/gdb/linux/mm.py +++ b/scripts/gdb/linux/mm.py @@ -40,11 +40,11 @@ class x86_page_ops(): self.PAGE_OFFSET = int(gdb.parse_and_eval("page_offset_base")) self.VMEMMAP_START = int(gdb.parse_and_eval("vmemmap_base")) - self.PHYS_BASE = int(gdb.parse_and_eval("phys_base")) + self.PHYS_BASE = int(gdb.parse_and_eval("(unsigned long) phys_base")) self.START_KERNEL_map = 0xffffffff80000000 - self.KERNEL_START = gdb.parse_and_eval("_text") - self.KERNEL_END = gdb.parse_and_eval("_end") + self.KERNEL_START = gdb.parse_and_eval("(unsigned long) &_text") + self.KERNEL_END = gdb.parse_and_eval("(unsigned long) &_end") self.VMALLOC_START = int(gdb.parse_and_eval("vmalloc_base")) if self.VMALLOC_START == 0xffffc90000000000: diff --git a/scripts/gdb/linux/slab.py b/scripts/gdb/linux/slab.py index 0e2d93867fe2..ddde25aeca8d 100644 --- a/scripts/gdb/linux/slab.py +++ b/scripts/gdb/linux/slab.py @@ -196,7 +196,7 @@ def slabtrace(alloc, cache_name): if target_cache['flags'] & SLAB_STORE_USER: for i in range(0, nr_node_ids): - cache_node = target_cache['node'][i] + cache_node = target_cache['per_node']['node'][i] if cache_node['nr_slabs']['counter'] == 0: continue process_slab(loc_track, cache_node['partial'], alloc, target_cache) @@ -300,7 +300,7 @@ def slabinfo(): nr_free = 0 nr_slabs = 0 for i in range(0, nr_node_ids): - cache_node = cache['node'][i] + cache_node = cache['per_node']['node'][i] try: nr_slabs += cache_node['nr_slabs']['counter'] nr_objs = int(cache_node['total_objects']['counter']) diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c index 4e99393a35f1..2ad87a74bb03 100644 --- a/scripts/mod/file2alias.c +++ b/scripts/mod/file2alias.c @@ -651,7 +651,26 @@ static void do_vio_entry(struct module *mod, void *symval) module_alias_printf(mod, true, "%s", alias); } -static void do_input(char *alias, +static void __attribute__((format(printf, 3, 4))) +alias_append(char *alias, size_t size, const char *fmt, ...) +{ + size_t len = strlen(alias); + va_list args; + int n; + + if (len >= size) + fatal("alias buffer (%zu) overflow before append\n", size); + + va_start(args, fmt); + n = vsnprintf(alias + len, size - len, fmt, args); + va_end(args); + + if (n < 0 || (size_t)n >= size - len) + fatal("alias buffer (%zu) overflow on append (need %d, have %zu)\n", + size, n, size - len); +} + +static void do_input(char *alias, size_t size, kernel_ulong_t *arr, unsigned int min, unsigned int max) { unsigned int i; @@ -659,13 +678,14 @@ static void do_input(char *alias, for (i = min; i <= max; i++) if (get_unaligned_native(arr + i / BITS_PER_LONG) & (1ULL << (i % BITS_PER_LONG))) - sprintf(alias + strlen(alias), "%X,*", i); + alias_append(alias, size, "%X,*", i); } /* input:b0v0p0e0-eXkXrXaXmXlXsXfXwX where X is comma-separated %02X. */ static void do_input_entry(struct module *mod, void *symval) { char alias[256] = {}; + const size_t sizeof_alias = sizeof(alias); DEF_FIELD(symval, input_device_id, flags); DEF_FIELD(symval, input_device_id, bustype); @@ -687,35 +707,35 @@ static void do_input_entry(struct module *mod, void *symval) ADD(alias, "p", flags & INPUT_DEVICE_ID_MATCH_PRODUCT, product); ADD(alias, "e", flags & INPUT_DEVICE_ID_MATCH_VERSION, version); - sprintf(alias + strlen(alias), "-e*"); + alias_append(alias, sizeof_alias, "-e*"); if (flags & INPUT_DEVICE_ID_MATCH_EVBIT) - do_input(alias, *evbit, 0, INPUT_DEVICE_ID_EV_MAX); - sprintf(alias + strlen(alias), "k*"); + do_input(alias, sizeof_alias, *evbit, 0, INPUT_DEVICE_ID_EV_MAX); + alias_append(alias, sizeof_alias, "k*"); if (flags & INPUT_DEVICE_ID_MATCH_KEYBIT) - do_input(alias, *keybit, + do_input(alias, sizeof_alias, *keybit, INPUT_DEVICE_ID_KEY_MIN_INTERESTING, INPUT_DEVICE_ID_KEY_MAX); - sprintf(alias + strlen(alias), "r*"); + alias_append(alias, sizeof_alias, "r*"); if (flags & INPUT_DEVICE_ID_MATCH_RELBIT) - do_input(alias, *relbit, 0, INPUT_DEVICE_ID_REL_MAX); - sprintf(alias + strlen(alias), "a*"); + do_input(alias, sizeof_alias, *relbit, 0, INPUT_DEVICE_ID_REL_MAX); + alias_append(alias, sizeof_alias, "a*"); if (flags & INPUT_DEVICE_ID_MATCH_ABSBIT) - do_input(alias, *absbit, 0, INPUT_DEVICE_ID_ABS_MAX); - sprintf(alias + strlen(alias), "m*"); + do_input(alias, sizeof_alias, *absbit, 0, INPUT_DEVICE_ID_ABS_MAX); + alias_append(alias, sizeof_alias, "m*"); if (flags & INPUT_DEVICE_ID_MATCH_MSCIT) - do_input(alias, *mscbit, 0, INPUT_DEVICE_ID_MSC_MAX); - sprintf(alias + strlen(alias), "l*"); + do_input(alias, sizeof_alias, *mscbit, 0, INPUT_DEVICE_ID_MSC_MAX); + alias_append(alias, sizeof_alias, "l*"); if (flags & INPUT_DEVICE_ID_MATCH_LEDBIT) - do_input(alias, *ledbit, 0, INPUT_DEVICE_ID_LED_MAX); - sprintf(alias + strlen(alias), "s*"); + do_input(alias, sizeof_alias, *ledbit, 0, INPUT_DEVICE_ID_LED_MAX); + alias_append(alias, sizeof_alias, "s*"); if (flags & INPUT_DEVICE_ID_MATCH_SNDBIT) - do_input(alias, *sndbit, 0, INPUT_DEVICE_ID_SND_MAX); - sprintf(alias + strlen(alias), "f*"); + do_input(alias, sizeof_alias, *sndbit, 0, INPUT_DEVICE_ID_SND_MAX); + alias_append(alias, sizeof_alias, "f*"); if (flags & INPUT_DEVICE_ID_MATCH_FFBIT) - do_input(alias, *ffbit, 0, INPUT_DEVICE_ID_FF_MAX); - sprintf(alias + strlen(alias), "w*"); + do_input(alias, sizeof_alias, *ffbit, 0, INPUT_DEVICE_ID_FF_MAX); + alias_append(alias, sizeof_alias, "w*"); if (flags & INPUT_DEVICE_ID_MATCH_SWBIT) - do_input(alias, *swbit, 0, INPUT_DEVICE_ID_SW_MAX); + do_input(alias, sizeof_alias, *swbit, 0, INPUT_DEVICE_ID_SW_MAX); module_alias_printf(mod, false, "input:%s", alias); } @@ -895,12 +915,16 @@ static const struct dmifield { { NULL, DMI_NONE } }; -static void dmi_ascii_filter(char *d, const char *s) +static void dmi_ascii_filter(char *d, size_t avail, const char *s) { /* Filter out characters we don't want to see in the modalias string */ for (; *s; s++) - if (*s > ' ' && *s < 127 && *s != ':') + if (*s > ' ' && *s < 127 && *s != ':') { + if (avail <= 1) + fatal("%s: alias buffer overflow\n", __func__); *(d++) = *s; + avail--; + } *d = 0; } @@ -909,6 +933,8 @@ static void dmi_ascii_filter(char *d, const char *s) static void do_dmi_entry(struct module *mod, void *symval) { char alias[256] = {}; + const size_t sizeof_alias = sizeof(alias); + size_t len; int i, j; DEF_FIELD_ADDR(symval, dmi_system_id, matches); @@ -916,11 +942,12 @@ static void do_dmi_entry(struct module *mod, void *symval) for (j = 0; j < 4; j++) { if ((*matches)[j].slot && (*matches)[j].slot == dmi_fields[i].field) { - sprintf(alias + strlen(alias), ":%s*", - dmi_fields[i].prefix); - dmi_ascii_filter(alias + strlen(alias), + alias_append(alias, sizeof_alias, ":%s*", + dmi_fields[i].prefix); + len = strlen(alias); + dmi_ascii_filter(alias + len, sizeof_alias - len, (*matches)[j].substr); - strcat(alias, "*"); + alias_append(alias, sizeof_alias, "*"); } } } diff --git a/scripts/package/PKGBUILD b/scripts/package/PKGBUILD index 452374d63c24..1213c8e04671 100644 --- a/scripts/package/PKGBUILD +++ b/scripts/package/PKGBUILD @@ -10,7 +10,7 @@ for pkg in $_extrapackages; do pkgname+=("${pkgbase}-${pkg}") done -pkgver="${KERNELRELEASE//-/_}" +pkgver="$(echo "${KERNELRELEASE}" | sed 's/-\(rc[0-9]\+\)/\1/;s/-/_/g')" # The PKGBUILD is evaluated multiple times. # Running scripts/build-version from here would introduce inconsistencies. pkgrel="${KBUILD_REVISION}" diff --git a/security/lsm_syscalls.c b/security/lsm_syscalls.c index 5648b1f0ce9c..08a017669c02 100644 --- a/security/lsm_syscalls.c +++ b/security/lsm_syscalls.c @@ -57,7 +57,14 @@ u64 lsm_name_to_attr(const char *name) SYSCALL_DEFINE4(lsm_set_self_attr, unsigned int, attr, struct lsm_ctx __user *, ctx, u32, size, u32, flags) { - return security_setselfattr(attr, ctx, size, flags); + int rc; + + rc = mutex_lock_interruptible(¤t->signal->cred_guard_mutex); + if (rc < 0) + return rc; + rc = security_setselfattr(attr, ctx, size, flags); + mutex_unlock(¤t->signal->cred_guard_mutex); + return rc; } /** diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index f63c6f828735..010aac0c6c67 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -42,6 +42,7 @@ class Netlink: SOL_NETLINK = 270 NETLINK_ADD_MEMBERSHIP = 1 + NETLINK_LISTEN_ALL_NSID = 8 NETLINK_CAP_ACK = 10 NETLINK_EXT_ACK = 11 NETLINK_GET_STRICT_CHK = 12 @@ -680,6 +681,7 @@ class YnlFamily(SpecFamily): Notification API: ynl.ntf_subscribe(mcast_name) -- join a multicast group + ynl.ntf_listen_all_nsid() -- listen on all netns ynl.check_ntf() -- drain pending notifications ynl.poll_ntf(duration=None) -- yield notifications @@ -748,6 +750,23 @@ class YnlFamily(SpecFamily): self.sock.setsockopt(Netlink.SOL_NETLINK, Netlink.NETLINK_ADD_MEMBERSHIP, mcast_id) + def ntf_listen_all_nsid(self): + """Enable NETLINK_LISTEN_ALL_NSID to receive notifications from all + namespaces that have an nsid mapped in the current one.""" + self.sock.setsockopt(Netlink.SOL_NETLINK, + Netlink.NETLINK_LISTEN_ALL_NSID, 1) + + @staticmethod + def _decode_nsid(ancdata): + for cmsg_level, cmsg_type, cmsg_data in ancdata: + if (cmsg_level == Netlink.SOL_NETLINK and + cmsg_type == Netlink.NETLINK_LISTEN_ALL_NSID): + nsid = struct.unpack('i', cmsg_data)[0] + if nsid >= 0: + return nsid + return None + return None + def set_recv_dbg(self, enabled): self._recv_dbg = enabled @@ -1235,7 +1254,7 @@ class YnlFamily(SpecFamily): f" when parsing '{attr_spec['name']}'") return raw - def handle_ntf(self, decoded): + def handle_ntf(self, decoded, nsid=None): msg = {} if self.include_raw: msg['raw'] = decoded @@ -1246,15 +1265,22 @@ class YnlFamily(SpecFamily): msg['name'] = op['name'] msg['msg'] = attrs + if nsid is not None: + msg['nsid'] = nsid self.async_msg_queue.put(msg) + def _recvmsg(self, flags=0): + reply, ancdata, _, _ = self.sock.recvmsg(self._recv_size, 4096, flags) + return reply, ancdata + def check_ntf(self): while True: try: - reply = self.sock.recv(self._recv_size, socket.MSG_DONTWAIT) + reply, ancdata = self._recvmsg(socket.MSG_DONTWAIT) except BlockingIOError: return + nsid = self._decode_nsid(ancdata) nms = NlMsgs(reply) self._recv_dbg_print(reply, nms) for nl_msg in nms: @@ -1271,7 +1297,7 @@ class YnlFamily(SpecFamily): print("Unexpected msg id while checking for ntf", decoded) continue - self.handle_ntf(decoded) + self.handle_ntf(decoded, nsid) def poll_ntf(self, duration=None): start_time = time.time() @@ -1335,7 +1361,8 @@ class YnlFamily(SpecFamily): rsp = [] op_rsp = [] while not done: - reply = self.sock.recv(self._recv_size) + reply, ancdata = self._recvmsg() + nsid = self._decode_nsid(ancdata) nms = NlMsgs(reply) self._recv_dbg_print(reply, nms) for nl_msg in nms: @@ -1374,7 +1401,7 @@ class YnlFamily(SpecFamily): # Check if this is a reply to our request if nl_msg.nl_seq not in reqs_by_seq or decoded.cmd() != op.rsp_value: if decoded.cmd() in self.async_msg_ids: - self.handle_ntf(decoded) + self.handle_ntf(decoded, nsid) continue print('Unexpected message: ' + repr(decoded)) continue diff --git a/tools/perf/Makefile b/tools/perf/Makefile index 816d5d84816b..5b713837eede 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -111,6 +111,9 @@ build-test: build-test-tarball: @$(MAKE) -f tests/make REUSE_FEATURES_DUMP=1 MK=Makefile SET_PARALLEL=1 --no-print-directory out +check-headers: + @./check-headers.sh + # # All other targets get passed through: # @@ -118,4 +121,4 @@ build-test-tarball: $(print_msg) $(make) -.PHONY: tags TAGS FORCE Makefile +.PHONY: tags TAGS FORCE Makefile build-test build-test-tarball check-headers diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index cee19c923c06..76b35ac19acb 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -285,7 +285,6 @@ goals := $(filter-out all sub-make, $(MAKECMDGOALS)) $(goals) all: sub-make sub-make: fixdep - @./check-headers.sh $(Q)$(MAKE) FIXDEP_BUILT=1 -f Makefile.perf $(goals) else # force_fixdep @@ -565,6 +564,12 @@ fsmount_tbls := $(srctree)/tools/perf/trace/beauty/fsmount.sh $(fsmount_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsmount_tbls) $(Q)$(SHELL) '$(fsmount_tbls)' $(beauty_uapi_linux_dir) > $@ +fsmount_attr_arrays := $(beauty_outdir)/fsmount_attr_arrays.c +fsmount_attr_tbls := $(srctree)/tools/perf/trace/beauty/fsmount_attr.sh + +$(fsmount_attr_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsmount_attr_tbls) + $(Q)$(SHELL) '$(fsmount_attr_tbls)' $(beauty_uapi_linux_dir) > $@ + fspick_arrays := $(beauty_outdir)/fspick_arrays.c fspick_tbls := $(srctree)/tools/perf/trace/beauty/fspick.sh @@ -855,6 +860,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE archheaders \ $(fadvise_advice_array) \ $(fsconfig_arrays) \ $(fsmount_arrays) \ + $(fsmount_attr_arrays) \ $(fspick_arrays) \ $(pkey_alloc_access_rights_array) \ $(sndrv_pcm_ioctl_array) \ @@ -1302,6 +1308,7 @@ clean:: $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean $(LIBSYMBOL)-clean $( $(OUTPUT)$(fadvise_advice_array) \ $(OUTPUT)$(fsconfig_arrays) \ $(OUTPUT)$(fsmount_arrays) \ + $(OUTPUT)$(fsmount_attr_arrays) \ $(OUTPUT)$(fspick_arrays) \ $(OUTPUT)$(madvise_behavior_array) \ $(OUTPUT)$(mmap_flags_array) \ diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e58c49d047a2..48615ddccd93 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -771,11 +771,6 @@ static const char *bpf_cmd[] = { }; static DEFINE_STRARRAY(bpf_cmd, "BPF_"); -static const char *fsmount_flags[] = { - [1] = "CLOEXEC", -}; -static DEFINE_STRARRAY(fsmount_flags, "FSMOUNT_"); - #include "trace/beauty/generated/fsconfig_arrays.c" static DEFINE_STRARRAY(fsconfig_cmds, "FSCONFIG_"); @@ -1202,7 +1197,9 @@ static const struct syscall_fmt syscall_fmts[] = { { .name = "fsconfig", .arg = { [1] = STRARRAY(cmd, fsconfig_cmds), }, }, { .name = "fsmount", - .arg = { [1] = STRARRAY_FLAGS(flags, fsmount_flags), + .arg = { [1] = { .scnprintf = SCA_FSMOUNT_FLAGS, /* fsmount_flags */ + .strtoul = STUL_STRARRAYS, + .show_zero = true, }, [2] = { .scnprintf = SCA_FSMOUNT_ATTR_FLAGS, /* attr_flags */ }, }, }, { .name = "fspick", .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h index 0a07ad158f87..a90c35fa5c12 100644 --- a/tools/perf/trace/beauty/beauty.h +++ b/tools/perf/trace/beauty/beauty.h @@ -179,6 +179,9 @@ size_t syscall_arg__scnprintf_fcntl_arg(char *bf, size_t size, struct syscall_ar size_t syscall_arg__scnprintf_flock(char *bf, size_t size, struct syscall_arg *arg); #define SCA_FLOCK syscall_arg__scnprintf_flock +size_t syscall_arg__scnprintf_fsmount_flags(char *bf, size_t size, struct syscall_arg *arg); +#define SCA_FSMOUNT_FLAGS syscall_arg__scnprintf_fsmount_flags + size_t syscall_arg__scnprintf_fsmount_attr_flags(char *bf, size_t size, struct syscall_arg *arg); #define SCA_FSMOUNT_ATTR_FLAGS syscall_arg__scnprintf_fsmount_attr_flags diff --git a/tools/perf/trace/beauty/clone.sh b/tools/perf/trace/beauty/clone.sh index 18b6c0d75693..98cb1f8d4a6f 100755 --- a/tools/perf/trace/beauty/clone.sh +++ b/tools/perf/trace/beauty/clone.sh @@ -14,4 +14,8 @@ regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+CLONE_([^_]+[[:alnum:]_]+)[[: grep -E $regex ${linux_sched} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+CLONE_([^_]+[[:alnum:]_]+)[[:space:]]+\(1ULL[[:space:]]*<<[[:space:]]*([[:digit:]]+)\)[[:space:]]*.*' +grep -E $regex ${linux_sched} | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[%s + 1] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/trace/beauty/fsmount.c b/tools/perf/trace/beauty/fsmount.c index 28c2c16fc1a8..179e649fc72a 100644 --- a/tools/perf/trace/beauty/fsmount.c +++ b/tools/perf/trace/beauty/fsmount.c @@ -16,9 +16,25 @@ #define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */ #endif -static size_t fsmount__scnprintf_attr_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) + +static size_t fsmount__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) { #include "trace/beauty/generated/fsmount_arrays.c" + static DEFINE_STRARRAY(fsmount_flags, "FSMOUNT_"); + + return strarray__scnprintf_flags(&strarray__fsmount_flags, bf, size, show_prefix, flags); +} + +size_t syscall_arg__scnprintf_fsmount_flags(char *bf, size_t size, struct syscall_arg *arg) +{ + unsigned long flags = arg->val; + + return fsmount__scnprintf_flags(flags, bf, size, arg->show_string_prefix); +} + +static size_t fsmount__scnprintf_attr_flags(unsigned long flags, char *bf, size_t size, bool show_prefix) +{ +#include "trace/beauty/generated/fsmount_attr_arrays.c" static DEFINE_STRARRAY(fsmount_attr_flags, "MOUNT_ATTR_"); size_t printed = 0; diff --git a/tools/perf/trace/beauty/fsmount.sh b/tools/perf/trace/beauty/fsmount.sh index 6b67a54cdeee..6d1e80bc15e4 100755 --- a/tools/perf/trace/beauty/fsmount.sh +++ b/tools/perf/trace/beauty/fsmount.sh @@ -9,14 +9,9 @@ fi linux_mount=${beauty_uapi_linux_dir}/mount.h -# Remove MOUNT_ATTR_RELATIME as it is zeros, handle it a special way in the beautifier -# Only handle MOUNT_ATTR_ followed by a capital letter/num as __ is special case -# for things like MOUNT_ATTR__ATIME that is a mask for the possible ATIME handling -# bits. Special case it as well in the beautifier - -printf "static const char *fsmount_attr_flags[] = {\n" -regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOUNT_ATTR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' -grep -E $regex ${linux_mount} | grep -v MOUNT_ATTR_RELATIME | \ +printf "static const char *fsmount_flags[] = {\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+FSMOUNT_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' +grep -E $regex ${linux_mount} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" printf "};\n" diff --git a/tools/perf/trace/beauty/fsmount_attr.sh b/tools/perf/trace/beauty/fsmount_attr.sh new file mode 100644 index 000000000000..6b67a54cdeee --- /dev/null +++ b/tools/perf/trace/beauty/fsmount_attr.sh @@ -0,0 +1,22 @@ +#!/bin/sh +# SPDX-License-Identifier: LGPL-2.1 + +if [ $# -ne 1 ] ; then + beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/ +else + beauty_uapi_linux_dir=$1 +fi + +linux_mount=${beauty_uapi_linux_dir}/mount.h + +# Remove MOUNT_ATTR_RELATIME as it is zeros, handle it a special way in the beautifier +# Only handle MOUNT_ATTR_ followed by a capital letter/num as __ is special case +# for things like MOUNT_ATTR__ATIME that is a mask for the possible ATIME handling +# bits. Special case it as well in the beautifier + +printf "static const char *fsmount_attr_flags[] = {\n" +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOUNT_ATTR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' +grep -E $regex ${linux_mount} | grep -v MOUNT_ATTR_RELATIME | \ + sed -r "s/$regex/\2 \1/g" | \ + xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" +printf "};\n" diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index ec715ad4bf25..ec4a0a025793 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -415,7 +415,7 @@ struct __kernel_timespec; struct old_timespec32; struct scm_timestamping_internal { - struct timespec64 ts[3]; + ktime_t ts[3]; }; extern void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss); diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h index 70b2b661f42c..13f71202845e 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/fs.h +++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h @@ -657,4 +657,16 @@ struct procmap_query { __u64 build_id_addr; /* in */ }; +/* + * Shutdown the filesystem. + */ +#define FS_IOC_SHUTDOWN _IOR('X', 125, __u32) + +/* + * Flags for FS_IOC_SHUTDOWN + */ +#define FS_SHUTDOWN_FLAGS_DEFAULT 0x0 +#define FS_SHUTDOWN_FLAGS_LOGFLUSH 0x1 /* flush log but not data*/ +#define FS_SHUTDOWN_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */ + #endif /* _UAPI_LINUX_FS_H */ diff --git a/tools/perf/trace/beauty/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h index d9d86598d100..2204708dbf7a 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/mount.h +++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h @@ -110,6 +110,7 @@ enum fsconfig_command { * fsmount() flags. */ #define FSMOUNT_CLOEXEC 0x00000001 +#define FSMOUNT_NAMESPACE 0x00000002 /* Create the mount in a new mount namespace */ /* * Mount attributes. diff --git a/tools/perf/trace/beauty/include/uapi/linux/sched.h b/tools/perf/trace/beauty/include/uapi/linux/sched.h index 359a14cc76a4..33a4624285cd 100644 --- a/tools/perf/trace/beauty/include/uapi/linux/sched.h +++ b/tools/perf/trace/beauty/include/uapi/linux/sched.h @@ -34,8 +34,12 @@ #define CLONE_IO 0x80000000 /* Clone io context */ /* Flags for the clone3() syscall. */ -#define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */ -#define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */ +#define CLONE_CLEAR_SIGHAND (1ULL << 32) /* Clear any signal handler and reset to SIG_DFL. */ +#define CLONE_INTO_CGROUP (1ULL << 33) /* Clone into a specific cgroup given the right permissions. */ +#define CLONE_AUTOREAP (1ULL << 34) /* Auto-reap child on exit. */ +#define CLONE_NNP (1ULL << 35) /* Set no_new_privs on child. */ +#define CLONE_PIDFD_AUTOKILL (1ULL << 36) /* Kill child when clone pidfd closes. */ +#define CLONE_EMPTY_MNTNS (1ULL << 37) /* Create an empty mount namespace. */ /* * cloning flags intersect with CSIGNAL so can be used with unshare and clone3 @@ -43,6 +47,12 @@ */ #define CLONE_NEWTIME 0x00000080 /* New time namespace */ +/* + * unshare flags share the bit space with clone flags but only apply to the + * unshare syscall: + */ +#define UNSHARE_EMPTY_MNTNS 0x00100000 /* Unshare an empty mount namespace. */ + #ifndef __ASSEMBLY__ /** * struct clone_args - arguments for the clone3 syscall @@ -146,4 +156,7 @@ struct clone_args { SCHED_FLAG_KEEP_ALL | \ SCHED_FLAG_UTIL_CLAMP) +/* Only for sched_getattr() own flag param, if task is SCHED_DEADLINE */ +#define SCHED_GETATTR_FLAG_DL_DYNAMIC 0x01 + #endif /* _UAPI_LINUX_SCHED_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c index b87e7f39e15a..6ed8e149e3d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_ktls.c @@ -417,6 +417,107 @@ static void run_tests(int family, enum bpf_map_type map_type) close(map); } +/* + * Regression test for the KTLS + sockmap (verdict) reverse-order UAF. + * + * Vulnerable sequence: + * 1. Insert receiver socket into sockmap with BPF_SK_SKB_VERDICT program. + * sk->sk_data_ready becomes sk_psock_verdict_data_ready. + * 2. Configure TLS RX: tls_sw_strparser_arm() saves + * sk_psock_verdict_data_ready as rx_ctx->saved_data_ready. + * + * When data arrives, tls_rx_msg_ready() calls saved_data_ready() = + * sk_psock_verdict_data_ready(), which calls tcp_read_skb() and drains + * sk_receive_queue via __skb_unlink() without advancing copied_seq. + * tls_strp_msg_load() then finds the queue empty while tcp_inq() is still + * non-zero, hits WARN_ON_ONCE(!first), and leaves a dangling frag_list + * pointer that tls_decrypt_sg() walks — a use-after-free. + * + * The fix adds a tls_sw_has_ctx_rx() check to sk_psock_verdict_data_ready(), + * mirroring what sk_psock_strp_data_ready() already does: when a TLS RX + * context is present, defer to psock->saved_data_ready (sock_def_readable) + * instead of calling tcp_read_skb(), so TLS retains sole ownership of the + * receive queue. Data is then decrypted and returned correctly by + * tls_sw_recvmsg(). + */ +static void test_sockmap_ktls_verdict_with_tls_rx(int family, int sotype) +{ + struct tls12_crypto_info_aes_gcm_128 crypto_info = {}; + char send_buf[] = "hello ktls sockmap reverse order"; + char recv_buf[sizeof(send_buf)] = {}; + struct test_sockmap_ktls *skel; + int c = -1, p = -1, zero = 0; + int prog_fd, map_fd; + ssize_t n; + int err; + + skel = test_sockmap_ktls__open_and_load(); + if (!ASSERT_TRUE(skel, "open_and_load")) + return; + + err = create_pair(family, sotype, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto out; + + prog_fd = bpf_program__fd(skel->progs.prog_skb_verdict_pass); + map_fd = bpf_map__fd(skel->maps.sock_map_verdict); + + err = bpf_prog_attach(prog_fd, map_fd, BPF_SK_SKB_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach sk_skb verdict")) + goto out; + + /* Step 1: configure TLS TX on sender (no sockmap involvement) */ + err = setsockopt(c, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); + if (!ASSERT_OK(err, "setsockopt(TCP_ULP) client")) + goto out; + + crypto_info.info.version = TLS_1_2_VERSION; + crypto_info.info.cipher_type = TLS_CIPHER_AES_GCM_128; + memset(crypto_info.key, 0x01, sizeof(crypto_info.key)); + memset(crypto_info.salt, 0x02, sizeof(crypto_info.salt)); + + err = setsockopt(c, SOL_TLS, TLS_TX, &crypto_info, sizeof(crypto_info)); + if (!ASSERT_OK(err, "setsockopt(TLS_TX)")) + goto out; + + /* Step 2: insert receiver into sockmap BEFORE TLS RX */ + err = bpf_map_update_elem(map_fd, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem")) + goto out; + + /* Step 3: configure TLS RX AFTER sockmap insertion */ + err = setsockopt(p, IPPROTO_TCP, TCP_ULP, "tls", strlen("tls")); + if (!ASSERT_OK(err, "setsockopt(TCP_ULP) server")) + goto out; + + err = setsockopt(p, SOL_TLS, TLS_RX, &crypto_info, sizeof(crypto_info)); + if (!ASSERT_OK(err, "setsockopt(TLS_RX)")) + goto out; + + /* + * A buggy kernel hits WARN_ON_ONCE in tls_strp_load_anchor_with_queue + * and may UAF in tls_decrypt_sg here. With the fix, + * sk_psock_verdict_data_ready defers to sock_def_readable and TLS + * decrypts the record normally. + */ + n = send(c, send_buf, sizeof(send_buf), 0); + if (!ASSERT_EQ(n, (ssize_t)sizeof(send_buf), "send")) + goto out; + + n = recv_timeout(p, recv_buf, sizeof(recv_buf), 0, 5); + if (!ASSERT_EQ(n, (ssize_t)sizeof(send_buf), "recv")) + goto out; + + ASSERT_OK(memcmp(send_buf, recv_buf, sizeof(send_buf)), "data integrity"); + +out: + if (c != -1) + close(c); + if (p != -1) + close(p); + test_sockmap_ktls__destroy(skel); +} + static void run_ktls_test(int family, int sotype) { if (test__start_subtest("tls simple offload")) @@ -429,6 +530,8 @@ static void run_ktls_test(int family, int sotype) test_sockmap_ktls_tx_no_buf(family, sotype, true); if (test__start_subtest("tls tx with pop")) test_sockmap_ktls_tx_pop(family, sotype); + if (test__start_subtest("tls verdict with tls rx")) + test_sockmap_ktls_verdict_with_tls_rx(family, sotype); } void test_sockmap_ktls(void) diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c index 83df4919c224..facafeaf4620 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_ktls.c @@ -17,6 +17,13 @@ struct { __type(value, int); } sock_map SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 2); + __type(key, int); + __type(value, int); +} sock_map_verdict SEC(".maps"); + SEC("sk_msg") int prog_sk_policy(struct sk_msg_md *msg) { @@ -38,3 +45,17 @@ int prog_sk_policy_redir(struct sk_msg_md *msg) bpf_msg_apply_bytes(msg, apply_bytes); return bpf_msg_redirect_map(msg, &sock_map, two, 0); } + +/* + * Verdict program for the reverse-order TLS/sockmap regression test. + * Returns SK_PASS so tcp_read_skb() drains the receive queue via + * sk_psock_verdict_recv() without calling tcp_eat_skb(), which is + * the precondition for the KTLS strparser frag_list UAF. + */ +SEC("sk_skb/verdict") +int prog_skb_verdict_pass(struct __sk_buff *skb) +{ + return SK_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/mm/hmm-tests.c b/tools/testing/selftests/mm/hmm-tests.c index 788689497e92..77fb4c5d871b 100644 --- a/tools/testing/selftests/mm/hmm-tests.c +++ b/tools/testing/selftests/mm/hmm-tests.c @@ -985,6 +985,56 @@ TEST_F(hmm, migrate) hmm_buffer_free(buffer); } +/* + * Migrate private file memory to device private memory. + */ +TEST_F(hmm, migrate_file_private) +{ + struct hmm_buffer *buffer; + unsigned long npages; + unsigned long size; + unsigned long i; + int *ptr; + int ret; + int fd; + + npages = ALIGN(HMM_BUFFER_SIZE, self->page_size) >> self->page_shift; + ASSERT_NE(npages, 0); + size = npages << self->page_shift; + + fd = hmm_create_file(size); + ASSERT_GE(fd, 0); + + buffer = malloc(sizeof(*buffer)); + ASSERT_NE(buffer, NULL); + + buffer->fd = fd; + buffer->size = size; + buffer->mirror = malloc(size); + ASSERT_NE(buffer->mirror, NULL); + + buffer->ptr = mmap(NULL, size, + PROT_READ | PROT_WRITE, + MAP_PRIVATE, + buffer->fd, 0); + ASSERT_NE(buffer->ptr, MAP_FAILED); + + /* Initialize buffer in system memory. */ + for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i) + ptr[i] = i; + + /* Migrate memory to device. */ + ret = hmm_migrate_sys_to_dev(self->fd, buffer, npages); + ASSERT_EQ(ret, 0); + ASSERT_EQ(buffer->cpages, npages); + + /* Check what the device read. */ + for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i) + ASSERT_EQ(ptr[i], i); + + hmm_buffer_free(buffer); +} + /* * Migrate anonymous memory to device private memory and fault some of it back * to system memory, then try migrating the resulting mix of system and device diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index d8468451b3a3..c17b133a81d2 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -103,7 +103,7 @@ RUN_ALL=false RUN_DESTRUCTIVE=false TAP_PREFIX="# " -while getopts "aht:n" OPT; do +while getopts "aht:nd" OPT; do case ${OPT} in "a") RUN_ALL=true ;; "h") usage ;; diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh index e8031f68200a..ebdb4c790a5d 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_mcast.sh @@ -4,7 +4,7 @@ ALL_TESTS="vlmc_control_test vlmc_querier_test vlmc_igmp_mld_version_test \ vlmc_last_member_test vlmc_startup_query_test vlmc_membership_test \ vlmc_querier_intvl_test vlmc_query_intvl_test vlmc_query_response_intvl_test \ - vlmc_router_port_test vlmc_filtering_test" + vlmc_router_port_test vlmc_filtering_test vlmc_mcast_toggle_test" NUM_NETIFS=4 CHECK_TC="yes" TEST_GROUP="239.10.10.10" @@ -537,6 +537,34 @@ vlmc_filtering_test() log_test "Disable multicast vlan snooping when vlan filtering is disabled" } +vlmc_mcast_toggle_test() +{ + RET=0 + + ip link add name br1-mcast up type bridge mcast_snooping 1 mcast_querier 1 vlan_filtering 1 + ip link add name dummy1-mcast up master br1-mcast type dummy + + # Enabling per-VLAN multicast snooping should disable the per-port + # multicast context on "dummy1-mcast". + ip link set dev br1-mcast type bridge mcast_vlan_snooping 1 + + # Toggling multicast snooping on the bridge should not affect the + # per-port multicast context on "dummy1-mcast" given that per-VLAN + # multicast snooping is enabled. + ip link set dev br1-mcast type bridge mcast_snooping 0 + ip link set dev br1-mcast type bridge mcast_snooping 1 + + # If both the per-port and per-{port, VLAN} multicast contexts are + # enabled on "dummy1-mcast", removing it from the bridge will result + # in a splat. + ip link set dev dummy1-mcast nomaster + + log_test "Toggling mcast snooping with per-VLAN mcast snooping enabled" + + ip link del dev dummy1-mcast + ip link del dev br1-mcast +} + trap cleanup EXIT setup_prepare diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c index 64f05229ab24..ded3f896e622 100644 --- a/tools/testing/selftests/net/lib/xdp_native.bpf.c +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -268,6 +268,17 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port) return XDP_PASS; } +static __always_inline __u16 csum_fold_helper(__u32 csum) +{ + csum = (csum & 0xffff) + (csum >> 16); + return ~((csum & 0xffff) + (csum >> 16)); +} + +static __always_inline __u16 csum_fold_udp_helper(__u32 csum) +{ + return csum_fold_helper(csum) ? : 0xffff; +} + static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) { void *data_end = (void *)(long)ctx->data_end; @@ -281,21 +292,22 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) if (eth->h_proto == bpf_htons(ETH_P_IP)) { struct iphdr *iph = data + sizeof(*eth); - __u16 total_len; if (iph + 1 > (struct iphdr *)data_end) return NULL; - iph->tot_len = bpf_htons(bpf_ntohs(iph->tot_len) + offset); - udph = (void *)eth + sizeof(*iph) + sizeof(*eth); if (!udph || udph + 1 > (struct udphdr *)data_end) return NULL; - len_new = bpf_htons(bpf_ntohs(udph->len) + offset); + len = iph->tot_len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + iph->tot_len = len_new; + iph->check = csum_fold_helper( + bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), ~((__u32)iph->check))); } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) { struct ipv6hdr *ipv6h = data + sizeof(*eth); - __u16 payload_len; if (ipv6h + 1 > (struct ipv6hdr *)data_end) return NULL; @@ -304,33 +316,27 @@ static void *update_pkt(struct xdp_md *ctx, __s16 offset, __u32 *udp_csum) if (!udph || udph + 1 > (struct udphdr *)data_end) return NULL; - *udp_csum = ~((__u32)udph->check); - len = ipv6h->payload_len; len_new = bpf_htons(bpf_ntohs(len) + offset); ipv6h->payload_len = len_new; - - *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, - sizeof(len_new), *udp_csum); - - len = udph->len; - len_new = bpf_htons(bpf_ntohs(udph->len) + offset); - *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, - sizeof(len_new), *udp_csum); } else { return NULL; } + len = udph->len; + len_new = bpf_htons(bpf_ntohs(len) + offset); + + *udp_csum = ~((__u32)udph->check); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + *udp_csum = bpf_csum_diff(&len, sizeof(len), &len_new, + sizeof(len_new), *udp_csum); + udph->len = len_new; return udph; } -static __u16 csum_fold_helper(__u32 csum) -{ - return ~((csum & 0xffff) + (csum >> 16)) ? : 0xffff; -} - static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, unsigned long hdr_len) { @@ -359,7 +365,7 @@ static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, return -1; udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (bpf_xdp_adjust_tail(ctx, 0 - offset) < 0) return -1; @@ -403,7 +409,7 @@ static int xdp_adjst_tail_grow_data(struct xdp_md *ctx, __u16 offset) return -1; udp_csum = bpf_csum_diff(0, 0, (__be32 *)tmp_buff, offset, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); buff_len = bpf_xdp_get_buff_len(ctx); @@ -484,8 +490,7 @@ static int xdp_adjst_head_shrnk_data(struct xdp_md *ctx, __u64 hdr_len, return -1; udp_csum = bpf_csum_diff((__be32 *)tmp_buff, offset, 0, 0, udp_csum); - - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (bpf_xdp_load_bytes(ctx, 0, tmp_buff, MAX_ADJST_OFFSET) < 0) return -1; @@ -542,7 +547,7 @@ static int xdp_adjst_head_grow_data(struct xdp_md *ctx, __u64 hdr_len, return -1; udp_csum = bpf_csum_diff(0, 0, (__be32 *)data_buff, offset, udp_csum); - udph->check = (__u16)csum_fold_helper(udp_csum); + udph->check = (__u16)csum_fold_udp_helper(udp_csum); if (hdr_len > MAX_ADJST_OFFSET || hdr_len == 0) return -1; diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index a6447f7a31fe..d158678fa6ab 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -401,7 +401,7 @@ do_transfer() mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" local start - start=$(date +%s%3N) + start=$(date +%s%N) ip netns exec ${connector_ns} \ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_args $connect_addr < "$cin" > "$cout" & @@ -423,7 +423,7 @@ do_transfer() fi local stop - stop=$(date +%s%3N) + stop=$(date +%s%N) if $capture; then sleep 1 @@ -439,7 +439,7 @@ do_transfer() fi local duration - duration=$((stop-start)) + duration=$(((stop-start) / 1000000)) printf "(duration %05sms) " "${duration}" if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index beec41f6662a..5acd12021e6e 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1828,6 +1828,22 @@ chk_add_tx_nr() fi } +chk_add_drop_tx_nr() +{ + local drop_tx_nr=$1 + local count + + print_check "add addr tx drop" + count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTxDrop") + if [ -z "$count" ]; then + print_skip + elif [ "$count" != "$drop_tx_nr" ]; then + fail_test "got $count ADD_ADDR drop[s] TX, expected $drop_tx_nr" + else + print_ok + fi +} + chk_rm_nr() { local rm_addr_nr=$1 @@ -3278,6 +3294,21 @@ add_addr_ports_tests() chk_mpc_endp_attempt ${retl} 1 fi + + # first signal address drops, second one still progresses + if reset "signal addr list progresses after tx drop"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 0 + ip netns exec $ns1 sysctl -q net.ipv4.tcp_timestamps=1 + ip netns exec $ns2 sysctl -q net.ipv4.tcp_timestamps=1 + + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal port 10100 + pm_nl_add_endpoint $ns1 dead:beef:3::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 + chk_add_drop_tx_nr 1 + chk_add_tx_nr 1 1 + chk_add_nr 1 1 0 + fi } bind_tests() diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index 989a5975dcea..5ef6033775c8 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -28,7 +28,7 @@ declare -rx MPTCP_LIB_AF_INET6=10 MPTCP_LIB_SUBTESTS=() MPTCP_LIB_SUBTESTS_DUPLICATED=0 MPTCP_LIB_SUBTEST_FLAKY=0 -MPTCP_LIB_SUBTESTS_LAST_TS_MS= +MPTCP_LIB_SUBTESTS_LAST_TS_NS= MPTCP_LIB_TEST_COUNTER=0 MPTCP_LIB_TEST_FORMAT="%02u %-50s" MPTCP_LIB_IP_MPTCP=0 @@ -236,7 +236,7 @@ mptcp_lib_kversion_ge() { } mptcp_lib_subtests_last_ts_reset() { - MPTCP_LIB_SUBTESTS_LAST_TS_MS="$(date +%s%3N)" + MPTCP_LIB_SUBTESTS_LAST_TS_NS="$(date +%s%N)" } mptcp_lib_subtests_last_ts_reset @@ -255,7 +255,7 @@ __mptcp_lib_result_check_duplicated() { __mptcp_lib_result_add() { local result="${1}" local time="time=" - local ts_prev_ms + local ts_prev_ns shift local id=$((${#MPTCP_LIB_SUBTESTS[@]} + 1)) @@ -265,9 +265,9 @@ __mptcp_lib_result_add() { # not to add two '#' [[ "${*}" != *"#"* ]] && time="# ${time}" - ts_prev_ms="${MPTCP_LIB_SUBTESTS_LAST_TS_MS}" + ts_prev_ns="${MPTCP_LIB_SUBTESTS_LAST_TS_NS}" mptcp_lib_subtests_last_ts_reset - time+="$((MPTCP_LIB_SUBTESTS_LAST_TS_MS - ts_prev_ms))ms" + time+="$(((MPTCP_LIB_SUBTESTS_LAST_TS_NS - ts_prev_ns) / 1000000))ms" MPTCP_LIB_SUBTESTS+=("${result} ${id} - ${KSFT_TEST}: ${*} ${time}") } diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh index af1532b4d2da..ec9a51bbf3c9 100755 --- a/tools/testing/selftests/net/ovpn/test-close-socket.sh +++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh @@ -53,7 +53,7 @@ ovpn_run_ping_traffic() { for p in $(seq 1 ${OVPN_NUM_PEERS}); do ovpn_cmd_ok "send ping traffic to peer ${p}" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \ + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \ 5.5.5.$((p + 1)) done } diff --git a/tools/testing/selftests/net/ovpn/test-mark.sh b/tools/testing/selftests/net/ovpn/test-mark.sh index 5a8f47554286..7c1d56e9c525 100755 --- a/tools/testing/selftests/net/ovpn/test-mark.sh +++ b/tools/testing/selftests/net/ovpn/test-mark.sh @@ -66,7 +66,7 @@ ovpn_mark_run_baseline_traffic() { for p in $(seq 1 3); do ovpn_cmd_ok "send baseline traffic to peer ${p}" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \ + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \ 5.5.5.$((p + 1)) done } @@ -101,7 +101,7 @@ ovpn_mark_verify_drop_traffic() { local total_count for p in $(seq 1 3); do - if ping_output=$(ip netns exec ovpn_peer0 ping -qfc 500 -w 1 \ + if ping_output=$(ip netns exec ovpn_peer0 ping -qfc 100 -w 1 \ 5.5.5.$((p + 1)) 2>&1); then printf '%s\n' "expected ping to peer ${p} to fail \ after nft drop rule" @@ -144,7 +144,7 @@ ovpn_mark_verify_traffic_recovery() { sleep 1 for p in $(seq 1 3); do ovpn_cmd_ok "send recovery traffic to peer ${p}" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 \ + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 \ 5.5.5.$((p + 1)) done } diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh index c06e3135fbef..9b5610837032 100755 --- a/tools/testing/selftests/net/ovpn/test.sh +++ b/tools/testing/selftests/net/ovpn/test.sh @@ -110,7 +110,7 @@ ovpn_run_basic_traffic() { ovpn_run_lan_traffic() { ovpn_cmd_ok "ping LAN behind peer1" \ - ip netns exec ovpn_peer0 ping -qfc 500 -w 3 "${OVPN_LAN_IP}" + ip netns exec ovpn_peer0 ping -qfc 100 -w 3 "${OVPN_LAN_IP}" } ovpn_run_float_mode() { @@ -127,7 +127,7 @@ ovpn_run_float_mode() { for p in $(seq 1 ${OVPN_NUM_PEERS}); do peer_ns="ovpn_peer${p}" ovpn_cmd_ok "ping tunnel after float peer ${p}" \ - ip netns exec "${peer_ns}" ping -qfc 500 -w 3 5.5.5.1 + ip netns exec "${peer_ns}" ping -qfc 100 -w 3 5.5.5.1 done } diff --git a/tools/testing/selftests/net/rds/config b/tools/testing/selftests/net/rds/config index 97db7ecb892a..3d62d0c750a8 100644 --- a/tools/testing/selftests/net/rds/config +++ b/tools/testing/selftests/net/rds/config @@ -1,3 +1,4 @@ +CONFIG_MODULES=n CONFIG_NET_NS=y CONFIG_NET_SCH_NETEM=y CONFIG_RDS=y