diff options
141 files changed, 2076 insertions, 495 deletions
diff --git a/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml b/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml index fc2f63860cc8..be32f087c529 100644 --- a/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml +++ b/Documentation/devicetree/bindings/bus/allwinner,sun8i-a23-rsb.yaml @@ -42,6 +42,7 @@ properties: patternProperties: "^.*@[0-9a-fA-F]+$": + type: object properties: reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml index cf494a08b837..9692b7f719f5 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7124.yaml @@ -114,42 +114,47 @@ patternProperties: examples: - | - adc@0 { - compatible = "adi,ad7124-4"; - reg = <0>; - spi-max-frequency = <5000000>; - interrupts = <25 2>; - interrupt-parent = <&gpio>; - refin1-supply = <&adc_vref>; - clocks = <&ad7124_mclk>; - clock-names = "mclk"; - + spi { #address-cells = <1>; #size-cells = <0>; - channel@0 { + adc@0 { + compatible = "adi,ad7124-4"; reg = <0>; - diff-channels = <0 1>; - adi,reference-select = <0>; - adi,buffered-positive; - }; - - channel@1 { - reg = <1>; - bipolar; - diff-channels = <2 3>; - adi,reference-select = <0>; - adi,buffered-positive; - adi,buffered-negative; - }; - - channel@2 { - reg = <2>; - diff-channels = <4 5>; - }; - - channel@3 { - reg = <3>; - diff-channels = <6 7>; + spi-max-frequency = <5000000>; + interrupts = <25 2>; + interrupt-parent = <&gpio>; + refin1-supply = <&adc_vref>; + clocks = <&ad7124_mclk>; + clock-names = "mclk"; + + #address-cells = <1>; + #size-cells = <0>; + + channel@0 { + reg = <0>; + diff-channels = <0 1>; + adi,reference-select = <0>; + adi,buffered-positive; + }; + + channel@1 { + reg = <1>; + bipolar; + diff-channels = <2 3>; + adi,reference-select = <0>; + adi,buffered-positive; + adi,buffered-negative; + }; + + channel@2 { + reg = <2>; + diff-channels = <4 5>; + }; + + channel@3 { + reg = <3>; + diff-channels = <6 7>; + }; }; }; diff --git a/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml b/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml index 8a4100ceeaf2..d76ece97c76c 100644 --- a/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml +++ b/Documentation/devicetree/bindings/iio/adc/avia-hx711.yaml @@ -61,6 +61,6 @@ examples: compatible = "avia,hx711"; sck-gpios = <&gpio3 10 GPIO_ACTIVE_HIGH>; dout-gpios = <&gpio0 7 GPIO_ACTIVE_HIGH>; - avdd-suppy = <&avdd>; + avdd-supply = <&avdd>; clock-frequency = <100000>; }; diff --git a/Documentation/devicetree/bindings/mtd/allwinner,sun4i-a10-nand.yaml b/Documentation/devicetree/bindings/mtd/allwinner,sun4i-a10-nand.yaml index e5a411518be1..b5b3cf5b1ac2 100644 --- a/Documentation/devicetree/bindings/mtd/allwinner,sun4i-a10-nand.yaml +++ b/Documentation/devicetree/bindings/mtd/allwinner,sun4i-a10-nand.yaml @@ -55,6 +55,7 @@ patternProperties: "^pinctrl-[0-9]+$": true "^nand@[a-f0-9]+$": + type: object properties: reg: minimum: 0 diff --git a/Documentation/devicetree/bindings/mtd/nand-controller.yaml b/Documentation/devicetree/bindings/mtd/nand-controller.yaml index 199ba5ac2a06..d261b7096c69 100644 --- a/Documentation/devicetree/bindings/mtd/nand-controller.yaml +++ b/Documentation/devicetree/bindings/mtd/nand-controller.yaml @@ -40,6 +40,7 @@ properties: patternProperties: "^nand@[a-f0-9]$": + type: object properties: reg: description: diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml index 61a110a7db8a..125599a2dc5e 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2400-pinctrl.yaml @@ -22,7 +22,9 @@ description: |+ properties: compatible: - enum: [ aspeed,ast2400-pinctrl, aspeed,g4-pinctrl ] + enum: + - aspeed,ast2400-pinctrl + - aspeed,g4-pinctrl patternProperties: '^.*$': diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml index cf561bd55128..3e6d85318577 100644 --- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2500-pinctrl.yaml @@ -22,7 +22,9 @@ description: |+ properties: compatible: - enum: [ aspeed,ast2500-pinctrl, aspeed,g5-pinctrl ] + enum: + - aspeed,ast2500-pinctrl + - aspeed,g5-pinctrl aspeed,external-nodes: minItems: 2 maxItems: 2 @@ -74,9 +76,6 @@ required: examples: - | - compatible = "simple-bus"; - ranges; - apb { compatible = "simple-bus"; #address-cells = <1>; @@ -89,7 +88,7 @@ examples: pinctrl: pinctrl { compatible = "aspeed,g5-pinctrl"; - aspeed,external-nodes = <&gfx &lhc>; + aspeed,external-nodes = <&gfx>, <&lhc>; pinctrl_i2c3_default: i2c3_default { function = "I2C3"; diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml index 06c4b66c3ee6..91d3e78b3395 100644 --- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml +++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.yaml @@ -55,6 +55,7 @@ properties: patternProperties: '^gpio@[0-9a-f]*$': + type: object properties: gpio-controller: true '#gpio-cells': @@ -113,8 +114,10 @@ patternProperties: - st,bank-name '-[0-9]*$': + type: object patternProperties: '^pins': + type: object description: | A pinctrl node should contain at least one subnode representing the pinctrl group available on the machine. Each subnode will list the @@ -194,6 +197,7 @@ required: examples: - | #include <dt-bindings/pinctrl/stm32-pinfunc.h> + #include <dt-bindings/mfd/stm32f4-rcc.h> //Example 1 pinctrl@40020000 { #address-cells = <1>; @@ -207,6 +211,7 @@ examples: #gpio-cells = <2>; reg = <0x0 0x400>; resets = <&reset_ahb1 0>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOA)>; st,bank-name = "GPIOA"; }; }; @@ -224,6 +229,7 @@ examples: #gpio-cells = <2>; reg = <0x1000 0x400>; resets = <&reset_ahb1 0>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOB)>; st,bank-name = "GPIOB"; gpio-ranges = <&pinctrl 0 0 16>; }; @@ -233,6 +239,7 @@ examples: #gpio-cells = <2>; reg = <0x2000 0x400>; resets = <&reset_ahb1 0>; + clocks = <&rcc 0 STM32F4_AHB1_CLOCK(GPIOC)>; st,bank-name = "GPIOC"; ngpios = <5>; gpio-ranges = <&pinctrl 0 16 3>, diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index f97a4ecd7b91..c899111aa5e3 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -10,97 +10,76 @@ maintainers: - Paul Walmsley <paul.walmsley@sifive.com> - Palmer Dabbelt <palmer@sifive.com> -allOf: - - $ref: /schemas/cpus.yaml# - properties: - $nodename: - const: cpus - description: Container of cpu nodes - - '#address-cells': - const: 1 - description: | - A single unsigned 32-bit integer uniquely identifies each RISC-V - hart in a system. (See the "reg" node under the "cpu" node, - below). - - '#size-cells': - const: 0 + compatible: + items: + - enum: + - sifive,rocket0 + - sifive,e5 + - sifive,e51 + - sifive,u54-mc + - sifive,u54 + - sifive,u5 + - const: riscv + description: + Identifies that the hart uses the RISC-V instruction set + and identifies the type of the hart. + + mmu-type: + allOf: + - $ref: "/schemas/types.yaml#/definitions/string" + - enum: + - riscv,sv32 + - riscv,sv39 + - riscv,sv48 + description: + Identifies the MMU address translation mode used on this + hart. These values originate from the RISC-V Privileged + Specification document, available from + https://riscv.org/specifications/ + + riscv,isa: + allOf: + - $ref: "/schemas/types.yaml#/definitions/string" + - enum: + - rv64imac + - rv64imafdc + description: + Identifies the specific RISC-V instruction set architecture + supported by the hart. These are documented in the RISC-V + User-Level ISA document, available from + https://riscv.org/specifications/ + + timebase-frequency: + type: integer + minimum: 1 + description: + Specifies the clock frequency of the system timer in Hz. + This value is common to all harts on a single system image. + + interrupt-controller: + type: object + description: Describes the CPU's local interrupt controller -patternProperties: - '^cpu@[0-9a-f]+$': properties: - compatible: - type: array - items: - - enum: - - sifive,rocket0 - - sifive,e5 - - sifive,e51 - - sifive,u54-mc - - sifive,u54 - - sifive,u5 - - const: riscv - description: - Identifies that the hart uses the RISC-V instruction set - and identifies the type of the hart. - - mmu-type: - allOf: - - $ref: "/schemas/types.yaml#/definitions/string" - - enum: - - riscv,sv32 - - riscv,sv39 - - riscv,sv48 - description: - Identifies the MMU address translation mode used on this - hart. These values originate from the RISC-V Privileged - Specification document, available from - https://riscv.org/specifications/ - - riscv,isa: - allOf: - - $ref: "/schemas/types.yaml#/definitions/string" - - enum: - - rv64imac - - rv64imafdc - description: - Identifies the specific RISC-V instruction set architecture - supported by the hart. These are documented in the RISC-V - User-Level ISA document, available from - https://riscv.org/specifications/ + '#interrupt-cells': + const: 1 - timebase-frequency: - type: integer - minimum: 1 - description: - Specifies the clock frequency of the system timer in Hz. - This value is common to all harts on a single system image. - - interrupt-controller: - type: object - description: Describes the CPU's local interrupt controller - - properties: - '#interrupt-cells': - const: 1 - - compatible: - const: riscv,cpu-intc - - interrupt-controller: true + compatible: + const: riscv,cpu-intc - required: - - '#interrupt-cells' - - compatible - - interrupt-controller + interrupt-controller: true required: - - riscv,isa - - timebase-frequency + - '#interrupt-cells' + - compatible - interrupt-controller +required: + - riscv,isa + - timebase-frequency + - interrupt-controller + examples: - | // Example 1: SiFive Freedom U540G Development Kit diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml index c374fd4923a6..6d1329c28170 100644 --- a/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml +++ b/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml @@ -50,6 +50,7 @@ properties: patternProperties: "^.*@[0-9a-f]+": + type: object properties: reg: items: diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml index bda7a5befd8b..f36c46d236d7 100644 --- a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml +++ b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml @@ -55,6 +55,7 @@ properties: patternProperties: "^.*@[0-9a-f]+": + type: object properties: reg: items: diff --git a/Documentation/driver-api/ntb.rst b/Documentation/driver-api/ntb.rst index 074a423c853c..87d1372da879 100644 --- a/Documentation/driver-api/ntb.rst +++ b/Documentation/driver-api/ntb.rst @@ -200,6 +200,33 @@ Debugfs Files: This file is used to read and write peer scratchpads. See *spad* for details. +NTB MSI Test Client (ntb\_msi\_test) +------------------------------------ + +The MSI test client serves to test and debug the MSI library which +allows for passing MSI interrupts across NTB memory windows. The +test client is interacted with through the debugfs filesystem: + +* *debugfs*/ntb\_tool/*hw*/ + A directory in debugfs will be created for each + NTB device probed by the tool. This directory is shortened to *hw* + below. +* *hw*/port + This file describes the local port number +* *hw*/irq*_occurrences + One occurrences file exists for each interrupt and, when read, + returns the number of times the interrupt has been triggered. +* *hw*/peer*/port + This file describes the port number for each peer +* *hw*/peer*/count + This file describes the number of interrupts that can be + triggered on each peer +* *hw*/peer*/trigger + Writing an interrupt number (any number less than the value + specified in count) will trigger the interrupt on the + specified peer. That peer's interrupt's occurrence file + should be incremented. + NTB Hardware Drivers ==================== diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting index 209672010fb4..6b7a41cfcaed 100644 --- a/Documentation/filesystems/porting +++ b/Documentation/filesystems/porting @@ -436,7 +436,7 @@ for the inode. If d_make_root(inode) is passed a NULL inode it returns NULL and also requires no further error handling. Typical usage is: inode = foofs_new_inode(....); - s->s_root = d_make_inode(inode); + s->s_root = d_make_root(inode); if (!s->s_root) /* Nothing needed for the inode cleanup */ return -ENOMEM; @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 -PATCHLEVEL = 2 +PATCHLEVEL = 3 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Bobtail Squid # *DOCUMENTATION* diff --git a/arch/hexagon/include/asm/pgalloc.h b/arch/hexagon/include/asm/pgalloc.h index 3c9e1bd9a3e9..d6544dc71258 100644 --- a/arch/hexagon/include/asm/pgalloc.h +++ b/arch/hexagon/include/asm/pgalloc.h @@ -11,6 +11,8 @@ #include <asm/mem-layout.h> #include <asm/atomic.h> +#include <asm-generic/pgalloc.h> /* for pte_{alloc,free}_one */ + #define check_pgt_cache() do {} while (0) extern unsigned long long kmap_generation; @@ -46,38 +48,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) free_page((unsigned long) pgd); } -static inline struct page *pte_alloc_one(struct mm_struct *mm) -{ - struct page *pte; - - pte = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!pte) - return NULL; - if (!pgtable_page_ctor(pte)) { - __free_page(pte); - return NULL; - } - return pte; -} - -/* _kernel variant gets to use a different allocator */ -static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm) -{ - gfp_t flags = GFP_KERNEL | __GFP_ZERO; - return (pte_t *) __get_free_page(flags); -} - -static inline void pte_free(struct mm_struct *mm, struct page *pte) -{ - pgtable_page_dtor(pte); - __free_page(pte); -} - -static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) -{ - free_page((unsigned long)pte); -} - static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, pgtable_t pte) { diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 23553ed6b548..2d22d6bf52f2 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -248,16 +248,12 @@ static int __maybe_unused cn_proc_show(struct seq_file *m, void *v) return 0; } -static struct cn_dev cdev = { - .input = cn_rx_skb, -}; - static int cn_init(void) { struct cn_dev *dev = &cdev; struct netlink_kernel_cfg cfg = { .groups = CN_NETLINK_USERS + 0xf, - .input = dev->input, + .input = cn_rx_skb, }; dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg); diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 73740b969e62..b607a92791d3 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -2533,7 +2533,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist, npages = sg_num_pages(dev, sglist, nelems); address = dma_ops_alloc_iova(dev, dma_dom, npages, dma_mask); - if (address == DMA_MAPPING_ERROR) + if (!address) goto out_err; prot = dir2prot(direction); diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index 21fb90d66bfc..25c73c13cc7e 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -124,7 +124,7 @@ static inline int check_which(__u32 which) static inline int check_pad(struct v4l2_subdev *sd, __u32 pad) { #if defined(CONFIG_MEDIA_CONTROLLER) - if (sd->entity.graph_obj.mdev) { + if (sd->entity.num_pads) { if (pad >= sd->entity.num_pads) return -EINVAL; return 0; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 656ed80647f0..e2be5a685130 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -285,6 +285,9 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata) hw_cons = le16_to_cpu(*txdata->tx_cons_sb); sw_cons = txdata->tx_pkt_cons; + /* Ensure subsequent loads occur after hw_cons */ + smp_rmb(); + while (sw_cons != hw_cons) { u16 pkt_cons; diff --git a/drivers/net/ethernet/chelsio/cxgb/my3126.c b/drivers/net/ethernet/chelsio/cxgb/my3126.c index 20c09cc4b323..60aa45b375b6 100644 --- a/drivers/net/ethernet/chelsio/cxgb/my3126.c +++ b/drivers/net/ethernet/chelsio/cxgb/my3126.c @@ -94,7 +94,7 @@ static int my3126_interrupt_handler(struct cphy *cphy) return cphy_cause_link_change; } -static void my3216_poll(struct work_struct *work) +static void my3126_poll(struct work_struct *work) { struct cphy *cphy = container_of(work, struct cphy, phy_update.work); @@ -177,7 +177,7 @@ static struct cphy *my3126_phy_create(struct net_device *dev, return NULL; cphy_init(cphy, dev, phy_addr, &my3126_ops, mdio_ops); - INIT_DELAYED_WORK(&cphy->phy_update, my3216_poll); + INIT_DELAYED_WORK(&cphy->phy_update, my3126_poll); cphy->bmsr = 0; return cphy; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 67202b6f352e..4311ad9c84b2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -5561,7 +5561,6 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) char name[IFNAMSIZ]; u32 devcap2; u16 flags; - int pos; /* If we want to instantiate Virtual Functions, then our * parent bridge's PCI-E needs to support Alternative Routing @@ -5569,9 +5568,8 @@ static int cxgb4_iov_configure(struct pci_dev *pdev, int num_vfs) * and above. */ pbridge = pdev->bus->self; - pos = pci_find_capability(pbridge, PCI_CAP_ID_EXP); - pci_read_config_word(pbridge, pos + PCI_EXP_FLAGS, &flags); - pci_read_config_dword(pbridge, pos + PCI_EXP_DEVCAP2, &devcap2); + pcie_capability_read_word(pbridge, PCI_EXP_FLAGS, &flags); + pcie_capability_read_dword(pbridge, PCI_EXP_DEVCAP2, &devcap2); if ((flags & PCI_EXP_FLAGS_VERS) < 2 || !(devcap2 & PCI_EXP_DEVCAP2_ARI)) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 312599c6b35a..e447976bdd3e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -67,7 +67,8 @@ static struct ch_tc_pedit_fields pedits[] = { static struct ch_tc_flower_entry *allocate_flower_entry(void) { struct ch_tc_flower_entry *new = kzalloc(sizeof(*new), GFP_KERNEL); - spin_lock_init(&new->lock); + if (new) + spin_lock_init(&new->lock); return new; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 9dd5ed9a2965..f7fc553356f2 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -7309,7 +7309,6 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, } else { unsigned int pack_align; unsigned int ingpad, ingpack; - unsigned int pcie_cap; /* T5 introduced the separation of the Free List Padding and * Packing Boundaries. Thus, we can select a smaller Padding @@ -7334,8 +7333,7 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, * multiple of the Maximum Payload Size. */ pack_align = fl_align; - pcie_cap = pci_find_capability(adap->pdev, PCI_CAP_ID_EXP); - if (pcie_cap) { + if (pci_is_pcie(adap->pdev)) { unsigned int mps, mps_log; u16 devctl; @@ -7343,9 +7341,8 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size, * [bits 7:5] encodes sizes as powers of 2 starting at * 128 bytes. */ - pci_read_config_word(adap->pdev, - pcie_cap + PCI_EXP_DEVCTL, - &devctl); + pcie_capability_read_word(adap->pdev, PCI_EXP_DEVCTL, + &devctl); mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7; mps = 1 << mps_log; if (mps > pack_align) diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index b7a246b33599..2edb86ec9fe9 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4698,8 +4698,13 @@ int be_update_queues(struct be_adapter *adapter) int status; if (netif_running(netdev)) { + /* be_tx_timeout() must not run concurrently with this + * function, synchronize with an already-running dev_watchdog + */ + netif_tx_lock_bh(netdev); /* device cannot transmit now, avoid dev_watchdog timeouts */ netif_carrier_off(netdev); + netif_tx_unlock_bh(netdev); be_close(netdev); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 8ad5292eebbe..75329ab775a6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -43,7 +43,7 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_GET_QID_IN_PF, /* (VF -> PF) get queue id in pf */ HCLGE_MBX_LINK_STAT_MODE, /* (PF -> VF) link mode has changed */ HCLGE_MBX_GET_LINK_MODE, /* (VF -> PF) get the link mode of pf */ - HLCGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */ + HCLGE_MBX_PUSH_VLAN_INFO, /* (PF -> VF) push port base vlan */ HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */ HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index a38ac7cfe16b..690b9990215c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -304,7 +304,7 @@ int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, memcpy(&msg_data[6], &vlan_tag, sizeof(u16)); return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), - HLCGE_MBX_PUSH_VLAN_INFO, vfid); + HCLGE_MBX_PUSH_VLAN_INFO, vfid); } static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index f60b80bd605e..6a96987bd8f0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -204,7 +204,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) case HCLGE_MBX_LINK_STAT_CHANGE: case HCLGE_MBX_ASSERTING_RESET: case HCLGE_MBX_LINK_STAT_MODE: - case HLCGE_MBX_PUSH_VLAN_INFO: + case HCLGE_MBX_PUSH_VLAN_INFO: /* set this mbx event as pending. This is required as we * might loose interrupt event when mbx task is busy * handling. This shall be cleared when mbx task just @@ -307,7 +307,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) hclgevf_reset_task_schedule(hdev); break; - case HLCGE_MBX_PUSH_VLAN_INFO: + case HCLGE_MBX_PUSH_VLAN_INFO: state = le16_to_cpu(msg_q[1]); vlan_info = &msg_q[1]; hclgevf_update_port_base_vlan_info(hdev, state, diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 93f3b4e6185b..aa9323e55406 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3912,13 +3912,11 @@ void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) { struct igc_adapter *adapter = hw->back; - u16 cap_offset; - cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP); - if (!cap_offset) + if (!pci_is_pcie(adapter->pdev)) return -IGC_ERR_CONFIG; - pci_read_config_word(adapter->pdev, cap_offset + reg, value); + pcie_capability_read_word(adapter->pdev, reg, value); return IGC_SUCCESS; } @@ -3926,13 +3924,11 @@ s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) { struct igc_adapter *adapter = hw->back; - u16 cap_offset; - cap_offset = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP); - if (!cap_offset) + if (!pci_is_pcie(adapter->pdev)) return -IGC_ERR_CONFIG; - pci_write_config_word(adapter->pdev, cap_offset + reg, *value); + pcie_capability_write_word(adapter->pdev, reg, *value); return IGC_SUCCESS; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 7245d287633d..7f747cb1a4f4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -735,8 +735,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, list_add(&indr_priv->list, &rpriv->uplink_priv.tc_indr_block_priv_list); - block_cb = flow_block_cb_alloc(f->net, - mlx5e_rep_indr_setup_block_cb, + block_cb = flow_block_cb_alloc(mlx5e_rep_indr_setup_block_cb, indr_priv, indr_priv, mlx5e_rep_indr_tc_block_unbind); if (IS_ERR(block_cb)) { @@ -753,7 +752,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, if (!indr_priv) return -ENOENT; - block_cb = flow_block_cb_lookup(f, + block_cb = flow_block_cb_lookup(f->block, mlx5e_rep_indr_setup_block_cb, indr_priv); if (!block_cb) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 4d34d42b3b0e..650638152bbc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1604,14 +1604,14 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, bool register_block = false; int err; - block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower, + block_cb = flow_block_cb_lookup(f->block, + mlxsw_sp_setup_tc_block_cb_flower, mlxsw_sp); if (!block_cb) { acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, f->net); if (!acl_block) return -ENOMEM; - block_cb = flow_block_cb_alloc(f->net, - mlxsw_sp_setup_tc_block_cb_flower, + block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb_flower, mlxsw_sp, acl_block, mlxsw_sp_tc_block_flower_release); if (IS_ERR(block_cb)) { @@ -1657,7 +1657,8 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_cb *block_cb; int err; - block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower, + block_cb = flow_block_cb_lookup(f->block, + mlxsw_sp_setup_tc_block_cb_flower, mlxsw_sp); if (!block_cb) return; @@ -1680,7 +1681,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, struct flow_block_offload *f) { struct flow_block_cb *block_cb; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; bool ingress; int err; @@ -1702,7 +1703,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, &mlxsw_sp_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, mlxsw_sp_port, + block_cb = flow_block_cb_alloc(cb, mlxsw_sp_port, mlxsw_sp_port, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -1718,7 +1719,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port, case FLOW_BLOCK_UNBIND: mlxsw_sp_setup_tc_block_flower_unbind(mlxsw_sp_port, f, ingress); - block_cb = flow_block_cb_lookup(f, cb, mlxsw_sp_port); + block_cb = flow_block_cb_lookup(f->block, cb, mlxsw_sp_port); if (!block_cb) return -ENOENT; diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c index 7aaddc09c185..59487d446a09 100644 --- a/drivers/net/ethernet/mscc/ocelot_flower.c +++ b/drivers/net/ethernet/mscc/ocelot_flower.c @@ -316,15 +316,14 @@ int ocelot_setup_tc_block_flower_bind(struct ocelot_port *port, if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) return -EOPNOTSUPP; - block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower, - port); + block_cb = flow_block_cb_lookup(f->block, + ocelot_setup_tc_block_cb_flower, port); if (!block_cb) { port_block = ocelot_port_block_create(port); if (!port_block) return -ENOMEM; - block_cb = flow_block_cb_alloc(f->net, - ocelot_setup_tc_block_cb_flower, + block_cb = flow_block_cb_alloc(ocelot_setup_tc_block_cb_flower, port, port_block, ocelot_tc_block_unbind); if (IS_ERR(block_cb)) { @@ -351,8 +350,8 @@ void ocelot_setup_tc_block_flower_unbind(struct ocelot_port *port, { struct flow_block_cb *block_cb; - block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower, - port); + block_cb = flow_block_cb_lookup(f->block, + ocelot_setup_tc_block_cb_flower, port); if (!block_cb) return; diff --git a/drivers/net/ethernet/mscc/ocelot_tc.c b/drivers/net/ethernet/mscc/ocelot_tc.c index 9e6464ffae5d..16a6db71ca5e 100644 --- a/drivers/net/ethernet/mscc/ocelot_tc.c +++ b/drivers/net/ethernet/mscc/ocelot_tc.c @@ -134,7 +134,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port, struct flow_block_offload *f) { struct flow_block_cb *block_cb; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; int err; netdev_dbg(port->dev, "tc_block command %d, binder_type %d\n", @@ -156,7 +156,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port, if (flow_block_cb_is_busy(cb, port, &ocelot_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, port, port, NULL); + block_cb = flow_block_cb_alloc(cb, port, port, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -169,7 +169,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port, list_add_tail(&block_cb->driver_list, f->driver_block_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, port); + block_cb = flow_block_cb_lookup(f->block, cb, port); if (!block_cb) return -ENOENT; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index faa8ba012a37..e209f150c5f2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1318,8 +1318,7 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, &nfp_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, - nfp_flower_setup_tc_block_cb, + block_cb = flow_block_cb_alloc(nfp_flower_setup_tc_block_cb, repr, repr, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -1328,7 +1327,8 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev, list_add_tail(&block_cb->driver_list, &nfp_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, nfp_flower_setup_tc_block_cb, + block_cb = flow_block_cb_lookup(f->block, + nfp_flower_setup_tc_block_cb, repr); if (!block_cb) return -ENOENT; @@ -1424,8 +1424,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, cb_priv->app = app; list_add(&cb_priv->list, &priv->indr_block_cb_priv); - block_cb = flow_block_cb_alloc(f->net, - nfp_flower_setup_indr_block_cb, + block_cb = flow_block_cb_alloc(nfp_flower_setup_indr_block_cb, cb_priv, cb_priv, nfp_flower_setup_indr_tc_release); if (IS_ERR(block_cb)) { @@ -1442,7 +1441,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app, if (!cb_priv) return -ENOENT; - block_cb = flow_block_cb_lookup(f, + block_cb = flow_block_cb_lookup(f->block, nfp_flower_setup_indr_block_cb, cb_priv); if (!block_cb) diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index f900fde448db..17c64e43d6c3 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -530,9 +530,8 @@ static void qed_rdma_init_devinfo(struct qed_hwfn *p_hwfn, SET_FIELD(dev->dev_caps, QED_RDMA_DEV_CAP_LOCAL_INV_FENCE, 1); /* Check atomic operations support in PCI configuration space. */ - pci_read_config_dword(cdev->pdev, - cdev->pdev->pcie_cap + PCI_EXP_DEVCTL2, - &pci_status_control); + pcie_capability_read_dword(cdev->pdev, PCI_EXP_DEVCTL2, + &pci_status_control); if (pci_status_control & PCI_EXP_DEVCTL2_LTR_EN) SET_FIELD(dev->dev_caps, QED_RDMA_DEV_CAP_ATOMIC_OP, 1); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 0637c6752a78..6272115b2848 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -3251,9 +3251,9 @@ static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp) ret = phy_read_paged(tp->phydev, 0x0a46, 0x13); if (ret & BIT(8)) - phy_modify_paged(tp->phydev, 0x0c41, 0x12, 0, BIT(1)); + phy_modify_paged(tp->phydev, 0x0c41, 0x15, 0, BIT(1)); else - phy_modify_paged(tp->phydev, 0x0c41, 0x12, BIT(1), 0); + phy_modify_paged(tp->phydev, 0x0c41, 0x15, BIT(1), 0); /* Enable PHY auto speed down */ phy_modify_paged(tp->phydev, 0x0a44, 0x11, 0, BIT(3) | BIT(2)); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index afdcc5664ea6..3544e1991579 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -836,7 +836,6 @@ int netvsc_recv_callback(struct net_device *net, if (unlikely(!skb)) { ++net_device_ctx->eth_stats.rx_no_memory; - rcu_read_unlock(); return NVSP_STAT_FAIL; } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 2d816aadea79..e36c04c26866 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -517,7 +517,7 @@ static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value) static void sfp_hwmon_to_rx_power(long *value) { - *value = DIV_ROUND_CLOSEST(*value, 100); + *value = DIV_ROUND_CLOSEST(*value, 10); } static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset, diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 54edf8956a25..6e84328bdd40 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -165,23 +165,29 @@ static int vrf_ip6_local_out(struct net *net, struct sock *sk, static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, struct net_device *dev) { - const struct ipv6hdr *iph = ipv6_hdr(skb); + const struct ipv6hdr *iph; struct net *net = dev_net(skb->dev); - struct flowi6 fl6 = { - /* needed to match OIF rule */ - .flowi6_oif = dev->ifindex, - .flowi6_iif = LOOPBACK_IFINDEX, - .daddr = iph->daddr, - .saddr = iph->saddr, - .flowlabel = ip6_flowinfo(iph), - .flowi6_mark = skb->mark, - .flowi6_proto = iph->nexthdr, - .flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF, - }; + struct flowi6 fl6; int ret = NET_XMIT_DROP; struct dst_entry *dst; struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst; + if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) + goto err; + + iph = ipv6_hdr(skb); + + memset(&fl6, 0, sizeof(fl6)); + /* needed to match OIF rule */ + fl6.flowi6_oif = dev->ifindex; + fl6.flowi6_iif = LOOPBACK_IFINDEX; + fl6.daddr = iph->daddr; + fl6.saddr = iph->saddr; + fl6.flowlabel = ip6_flowinfo(iph); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = iph->nexthdr; + fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF; + dst = ip6_route_output(net, NULL, &fl6); if (dst == dst_null) goto err; @@ -237,21 +243,27 @@ static int vrf_ip_local_out(struct net *net, struct sock *sk, static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, struct net_device *vrf_dev) { - struct iphdr *ip4h = ip_hdr(skb); + struct iphdr *ip4h; int ret = NET_XMIT_DROP; - struct flowi4 fl4 = { - /* needed to match OIF rule */ - .flowi4_oif = vrf_dev->ifindex, - .flowi4_iif = LOOPBACK_IFINDEX, - .flowi4_tos = RT_TOS(ip4h->tos), - .flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF, - .flowi4_proto = ip4h->protocol, - .daddr = ip4h->daddr, - .saddr = ip4h->saddr, - }; + struct flowi4 fl4; struct net *net = dev_net(vrf_dev); struct rtable *rt; + if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) + goto err; + + ip4h = ip_hdr(skb); + + memset(&fl4, 0, sizeof(fl4)); + /* needed to match OIF rule */ + fl4.flowi4_oif = vrf_dev->ifindex; + fl4.flowi4_iif = LOOPBACK_IFINDEX; + fl4.flowi4_tos = RT_TOS(ip4h->tos); + fl4.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF; + fl4.flowi4_proto = ip4h->protocol; + fl4.daddr = ip4h->daddr; + fl4.saddr = ip4h->saddr; + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto err; diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c index d436cc51dfd1..2fb4258941a5 100644 --- a/drivers/net/wireless/ath/wil6210/cfg80211.c +++ b/drivers/net/wireless/ath/wil6210/cfg80211.c @@ -177,6 +177,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { .info.subcmd = QCA_NL80211_VENDOR_SUBCMD_DMG_RF_GET_SECTOR_CFG, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_get_cfg }, { @@ -184,6 +185,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { .info.subcmd = QCA_NL80211_VENDOR_SUBCMD_DMG_RF_SET_SECTOR_CFG, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_set_cfg }, { @@ -192,6 +194,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { QCA_NL80211_VENDOR_SUBCMD_DMG_RF_GET_SELECTED_SECTOR, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_get_selected }, { @@ -200,6 +203,7 @@ static const struct wiphy_vendor_command wil_nl80211_vendor_commands[] = { QCA_NL80211_VENDOR_SUBCMD_DMG_RF_SET_SELECTED_SECTOR, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, + .policy = wil_rf_sector_policy, .doit = wil_rf_sector_set_selected }, }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c index f6500899fc14..d07e7c7355d9 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/vendor.c @@ -112,6 +112,7 @@ const struct wiphy_vendor_command brcmf_vendor_cmds[] = { }, .flags = WIPHY_VENDOR_CMD_NEED_WDEV | WIPHY_VENDOR_CMD_NEED_NETDEV, + .policy = VENDOR_CMD_RAW_DATA, .doit = brcmf_cfg80211_vndr_cmds_dcmd_handler }, }; diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c index 5cf0b32c413b..e1bd344c4ebc 100644 --- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c +++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c @@ -163,6 +163,7 @@ static const struct wiphy_vendor_command wlcore_vendor_commands[] = { .flags = WIPHY_VENDOR_CMD_NEED_NETDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, .doit = wlcore_vendor_cmd_smart_config_start, + .policy = wlcore_vendor_attr_policy, }, { .info = { @@ -172,6 +173,7 @@ static const struct wiphy_vendor_command wlcore_vendor_commands[] = { .flags = WIPHY_VENDOR_CMD_NEED_NETDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, .doit = wlcore_vendor_cmd_smart_config_stop, + .policy = wlcore_vendor_attr_policy, }, { .info = { @@ -181,6 +183,7 @@ static const struct wiphy_vendor_command wlcore_vendor_commands[] = { .flags = WIPHY_VENDOR_CMD_NEED_NETDEV | WIPHY_VENDOR_CMD_NEED_RUNNING, .doit = wlcore_vendor_cmd_smart_config_set_group_key, + .policy = wlcore_vendor_attr_policy, }, }; diff --git a/drivers/ntb/Kconfig b/drivers/ntb/Kconfig index c99eed87382a..df16c755b4da 100644 --- a/drivers/ntb/Kconfig +++ b/drivers/ntb/Kconfig @@ -13,6 +13,17 @@ menuconfig NTB if NTB +config NTB_MSI + bool "MSI Interrupt Support" + depends on PCI_MSI + help + Support using MSI interrupt forwarding instead of (or in addition to) + hardware doorbells. MSI interrupts typically offer lower latency + than doorbells and more MSI interrupts can be made available to + clients. However this requires an extra memory window and support + in the hardware driver for creating the MSI interrupts. + + If unsure, say N. source "drivers/ntb/hw/Kconfig" source "drivers/ntb/test/Kconfig" diff --git a/drivers/ntb/Makefile b/drivers/ntb/Makefile index 5c64438d5b3f..3a6fa181ff99 100644 --- a/drivers/ntb/Makefile +++ b/drivers/ntb/Makefile @@ -1,3 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-$(CONFIG_NTB) += ntb.o hw/ test/ obj-$(CONFIG_NTB_TRANSPORT) += ntb_transport.o + +ntb-y := core.o +ntb-$(CONFIG_NTB_MSI) += msi.o diff --git a/drivers/ntb/ntb.c b/drivers/ntb/core.c index 2581ab724c34..2581ab724c34 100644 --- a/drivers/ntb/ntb.c +++ b/drivers/ntb/core.c diff --git a/drivers/ntb/hw/amd/ntb_hw_amd.c b/drivers/ntb/hw/amd/ntb_hw_amd.c index efb214fc545a..2859cc99b73e 100644 --- a/drivers/ntb/hw/amd/ntb_hw_amd.c +++ b/drivers/ntb/hw/amd/ntb_hw_amd.c @@ -160,8 +160,8 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, } /* set and verify setting the limit */ - write64(limit, mmio + limit_reg); - reg_val = read64(mmio + limit_reg); + write64(limit, peer_mmio + limit_reg); + reg_val = read64(peer_mmio + limit_reg); if (reg_val != limit) { write64(base_addr, mmio + limit_reg); write64(0, peer_mmio + xlat_reg); @@ -183,8 +183,8 @@ static int amd_ntb_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, } /* set and verify setting the limit */ - writel(limit, mmio + limit_reg); - reg_val = readl(mmio + limit_reg); + writel(limit, peer_mmio + limit_reg); + reg_val = readl(peer_mmio + limit_reg); if (reg_val != limit) { writel(base_addr, mmio + limit_reg); writel(0, peer_mmio + xlat_reg); @@ -333,7 +333,7 @@ static u64 amd_ntb_db_vector_mask(struct ntb_dev *ntb, int db_vector) if (db_vector < 0 || db_vector > ndev->db_count) return 0; - return ntb_ndev(ntb)->db_valid_mask & (1 << db_vector); + return ntb_ndev(ntb)->db_valid_mask & (1ULL << db_vector); } static u64 amd_ntb_db_read(struct ntb_dev *ntb) diff --git a/drivers/ntb/hw/intel/ntb_hw_gen3.c b/drivers/ntb/hw/intel/ntb_hw_gen3.c index f475b56a3f49..c3397160db7f 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen3.c +++ b/drivers/ntb/hw/intel/ntb_hw_gen3.c @@ -532,9 +532,9 @@ static int intel_ntb3_mw_set_trans(struct ntb_dev *ntb, int pidx, int idx, return 0; } -int intel_ntb3_peer_db_addr(struct ntb_dev *ntb, phys_addr_t *db_addr, - resource_size_t *db_size, - u64 *db_data, int db_bit) +static int intel_ntb3_peer_db_addr(struct ntb_dev *ntb, phys_addr_t *db_addr, + resource_size_t *db_size, + u64 *db_data, int db_bit) { phys_addr_t db_addr_base; struct intel_ntb_dev *ndev = ntb_ndev(ntb); diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c index db4967748e4d..f4959458d909 100644 --- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c +++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c @@ -86,7 +86,8 @@ struct switchtec_ntb { bool link_is_up; enum ntb_speed link_speed; enum ntb_width link_width; - struct work_struct link_reinit_work; + struct work_struct check_link_status_work; + bool link_force_down; }; static struct switchtec_ntb *ntb_sndev(struct ntb_dev *ntb) @@ -485,33 +486,11 @@ enum switchtec_msg { static int switchtec_ntb_reinit_peer(struct switchtec_ntb *sndev); -static void link_reinit_work(struct work_struct *work) -{ - struct switchtec_ntb *sndev; - - sndev = container_of(work, struct switchtec_ntb, link_reinit_work); - - switchtec_ntb_reinit_peer(sndev); -} - -static void switchtec_ntb_check_link(struct switchtec_ntb *sndev, - enum switchtec_msg msg) +static void switchtec_ntb_link_status_update(struct switchtec_ntb *sndev) { int link_sta; int old = sndev->link_is_up; - if (msg == MSG_LINK_FORCE_DOWN) { - schedule_work(&sndev->link_reinit_work); - - if (sndev->link_is_up) { - sndev->link_is_up = 0; - ntb_link_event(&sndev->ntb); - dev_info(&sndev->stdev->dev, "ntb link forced down\n"); - } - - return; - } - link_sta = sndev->self_shared->link_sta; if (link_sta) { u64 peer = ioread64(&sndev->peer_shared->magic); @@ -536,6 +515,38 @@ static void switchtec_ntb_check_link(struct switchtec_ntb *sndev, } } +static void check_link_status_work(struct work_struct *work) +{ + struct switchtec_ntb *sndev; + + sndev = container_of(work, struct switchtec_ntb, + check_link_status_work); + + if (sndev->link_force_down) { + sndev->link_force_down = false; + switchtec_ntb_reinit_peer(sndev); + + if (sndev->link_is_up) { + sndev->link_is_up = 0; + ntb_link_event(&sndev->ntb); + dev_info(&sndev->stdev->dev, "ntb link forced down\n"); + } + + return; + } + + switchtec_ntb_link_status_update(sndev); +} + +static void switchtec_ntb_check_link(struct switchtec_ntb *sndev, + enum switchtec_msg msg) +{ + if (msg == MSG_LINK_FORCE_DOWN) + sndev->link_force_down = true; + + schedule_work(&sndev->check_link_status_work); +} + static void switchtec_ntb_link_notification(struct switchtec_dev *stdev) { struct switchtec_ntb *sndev = stdev->sndev; @@ -568,7 +579,7 @@ static int switchtec_ntb_link_enable(struct ntb_dev *ntb, sndev->self_shared->link_sta = 1; switchtec_ntb_send_msg(sndev, LINK_MESSAGE, MSG_LINK_UP); - switchtec_ntb_check_link(sndev, MSG_CHECK_LINK); + switchtec_ntb_link_status_update(sndev); return 0; } @@ -582,7 +593,7 @@ static int switchtec_ntb_link_disable(struct ntb_dev *ntb) sndev->self_shared->link_sta = 0; switchtec_ntb_send_msg(sndev, LINK_MESSAGE, MSG_LINK_DOWN); - switchtec_ntb_check_link(sndev, MSG_CHECK_LINK); + switchtec_ntb_link_status_update(sndev); return 0; } @@ -835,7 +846,8 @@ static int switchtec_ntb_init_sndev(struct switchtec_ntb *sndev) sndev->ntb.topo = NTB_TOPO_SWITCH; sndev->ntb.ops = &switchtec_ntb_ops; - INIT_WORK(&sndev->link_reinit_work, link_reinit_work); + INIT_WORK(&sndev->check_link_status_work, check_link_status_work); + sndev->link_force_down = false; sndev->self_partition = sndev->stdev->partition; @@ -872,7 +884,7 @@ static int switchtec_ntb_init_sndev(struct switchtec_ntb *sndev) } sndev->peer_partition = ffs(tpart_vec) - 1; - if (!(part_map & (1 << sndev->peer_partition))) { + if (!(part_map & (1ULL << sndev->peer_partition))) { dev_err(&sndev->stdev->dev, "ntb target partition is not NT partition\n"); return -ENODEV; @@ -1448,10 +1460,16 @@ static void switchtec_ntb_deinit_db_msg_irq(struct switchtec_ntb *sndev) static int switchtec_ntb_reinit_peer(struct switchtec_ntb *sndev) { - dev_info(&sndev->stdev->dev, "peer reinitialized\n"); - switchtec_ntb_deinit_shared_mw(sndev); - switchtec_ntb_init_mw(sndev); - return switchtec_ntb_init_shared_mw(sndev); + int rc; + + if (crosslink_is_enabled(sndev)) + return 0; + + dev_info(&sndev->stdev->dev, "reinitialize shared memory window\n"); + rc = config_rsvd_lut_win(sndev, sndev->mmio_peer_ctrl, 0, + sndev->self_partition, + sndev->self_shared_dma); + return rc; } static int switchtec_ntb_add(struct device *dev, diff --git a/drivers/ntb/msi.c b/drivers/ntb/msi.c new file mode 100644 index 000000000000..9dddf133658f --- /dev/null +++ b/drivers/ntb/msi.c @@ -0,0 +1,415 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) + +#include <linux/irq.h> +#include <linux/module.h> +#include <linux/ntb.h> +#include <linux/msi.h> +#include <linux/pci.h> + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_VERSION("0.1"); +MODULE_AUTHOR("Logan Gunthorpe <logang@deltatee.com>"); +MODULE_DESCRIPTION("NTB MSI Interrupt Library"); + +struct ntb_msi { + u64 base_addr; + u64 end_addr; + + void (*desc_changed)(void *ctx); + + u32 __iomem *peer_mws[]; +}; + +/** + * ntb_msi_init() - Initialize the MSI context + * @ntb: NTB device context + * + * This function must be called before any other ntb_msi function. + * It initializes the context for MSI operations and maps + * the peer memory windows. + * + * This function reserves the last N outbound memory windows (where N + * is the number of peers). + * + * Return: Zero on success, otherwise a negative error number. + */ +int ntb_msi_init(struct ntb_dev *ntb, + void (*desc_changed)(void *ctx)) +{ + phys_addr_t mw_phys_addr; + resource_size_t mw_size; + size_t struct_size; + int peer_widx; + int peers; + int ret; + int i; + + peers = ntb_peer_port_count(ntb); + if (peers <= 0) + return -EINVAL; + + struct_size = sizeof(*ntb->msi) + sizeof(*ntb->msi->peer_mws) * peers; + + ntb->msi = devm_kzalloc(&ntb->dev, struct_size, GFP_KERNEL); + if (!ntb->msi) + return -ENOMEM; + + ntb->msi->desc_changed = desc_changed; + + for (i = 0; i < peers; i++) { + peer_widx = ntb_peer_mw_count(ntb) - 1 - i; + + ret = ntb_peer_mw_get_addr(ntb, peer_widx, &mw_phys_addr, + &mw_size); + if (ret) + goto unroll; + + ntb->msi->peer_mws[i] = devm_ioremap(&ntb->dev, mw_phys_addr, + mw_size); + if (!ntb->msi->peer_mws[i]) { + ret = -EFAULT; + goto unroll; + } + } + + return 0; + +unroll: + for (i = 0; i < peers; i++) + if (ntb->msi->peer_mws[i]) + devm_iounmap(&ntb->dev, ntb->msi->peer_mws[i]); + + devm_kfree(&ntb->dev, ntb->msi); + ntb->msi = NULL; + return ret; +} +EXPORT_SYMBOL(ntb_msi_init); + +/** + * ntb_msi_setup_mws() - Initialize the MSI inbound memory windows + * @ntb: NTB device context + * + * This function sets up the required inbound memory windows. It should be + * called from a work function after a link up event. + * + * Over the entire network, this function will reserves the last N + * inbound memory windows for each peer (where N is the number of peers). + * + * ntb_msi_init() must be called before this function. + * + * Return: Zero on success, otherwise a negative error number. + */ +int ntb_msi_setup_mws(struct ntb_dev *ntb) +{ + struct msi_desc *desc; + u64 addr; + int peer, peer_widx; + resource_size_t addr_align, size_align, size_max; + resource_size_t mw_size = SZ_32K; + resource_size_t mw_min_size = mw_size; + int i; + int ret; + + if (!ntb->msi) + return -EINVAL; + + desc = first_msi_entry(&ntb->pdev->dev); + addr = desc->msg.address_lo + ((uint64_t)desc->msg.address_hi << 32); + + for (peer = 0; peer < ntb_peer_port_count(ntb); peer++) { + peer_widx = ntb_peer_highest_mw_idx(ntb, peer); + if (peer_widx < 0) + return peer_widx; + + ret = ntb_mw_get_align(ntb, peer, peer_widx, &addr_align, + NULL, NULL); + if (ret) + return ret; + + addr &= ~(addr_align - 1); + } + + for (peer = 0; peer < ntb_peer_port_count(ntb); peer++) { + peer_widx = ntb_peer_highest_mw_idx(ntb, peer); + if (peer_widx < 0) { + ret = peer_widx; + goto error_out; + } + + ret = ntb_mw_get_align(ntb, peer, peer_widx, NULL, + &size_align, &size_max); + if (ret) + goto error_out; + + mw_size = round_up(mw_size, size_align); + mw_size = max(mw_size, size_max); + if (mw_size < mw_min_size) + mw_min_size = mw_size; + + ret = ntb_mw_set_trans(ntb, peer, peer_widx, + addr, mw_size); + if (ret) + goto error_out; + } + + ntb->msi->base_addr = addr; + ntb->msi->end_addr = addr + mw_min_size; + + return 0; + +error_out: + for (i = 0; i < peer; i++) { + peer_widx = ntb_peer_highest_mw_idx(ntb, peer); + if (peer_widx < 0) + continue; + + ntb_mw_clear_trans(ntb, i, peer_widx); + } + + return ret; +} +EXPORT_SYMBOL(ntb_msi_setup_mws); + +/** + * ntb_msi_clear_mws() - Clear all inbound memory windows + * @ntb: NTB device context + * + * This function tears down the resources used by ntb_msi_setup_mws(). + */ +void ntb_msi_clear_mws(struct ntb_dev *ntb) +{ + int peer; + int peer_widx; + + for (peer = 0; peer < ntb_peer_port_count(ntb); peer++) { + peer_widx = ntb_peer_highest_mw_idx(ntb, peer); + if (peer_widx < 0) + continue; + + ntb_mw_clear_trans(ntb, peer, peer_widx); + } +} +EXPORT_SYMBOL(ntb_msi_clear_mws); + +struct ntb_msi_devres { + struct ntb_dev *ntb; + struct msi_desc *entry; + struct ntb_msi_desc *msi_desc; +}; + +static int ntb_msi_set_desc(struct ntb_dev *ntb, struct msi_desc *entry, + struct ntb_msi_desc *msi_desc) +{ + u64 addr; + + addr = entry->msg.address_lo + + ((uint64_t)entry->msg.address_hi << 32); + + if (addr < ntb->msi->base_addr || addr >= ntb->msi->end_addr) { + dev_warn_once(&ntb->dev, + "IRQ %d: MSI Address not within the memory window (%llx, [%llx %llx])\n", + entry->irq, addr, ntb->msi->base_addr, + ntb->msi->end_addr); + return -EFAULT; + } + + msi_desc->addr_offset = addr - ntb->msi->base_addr; + msi_desc->data = entry->msg.data; + + return 0; +} + +static void ntb_msi_write_msg(struct msi_desc *entry, void *data) +{ + struct ntb_msi_devres *dr = data; + + WARN_ON(ntb_msi_set_desc(dr->ntb, entry, dr->msi_desc)); + + if (dr->ntb->msi->desc_changed) + dr->ntb->msi->desc_changed(dr->ntb->ctx); +} + +static void ntbm_msi_callback_release(struct device *dev, void *res) +{ + struct ntb_msi_devres *dr = res; + + dr->entry->write_msi_msg = NULL; + dr->entry->write_msi_msg_data = NULL; +} + +static int ntbm_msi_setup_callback(struct ntb_dev *ntb, struct msi_desc *entry, + struct ntb_msi_desc *msi_desc) +{ + struct ntb_msi_devres *dr; + + dr = devres_alloc(ntbm_msi_callback_release, + sizeof(struct ntb_msi_devres), GFP_KERNEL); + if (!dr) + return -ENOMEM; + + dr->ntb = ntb; + dr->entry = entry; + dr->msi_desc = msi_desc; + + devres_add(&ntb->dev, dr); + + dr->entry->write_msi_msg = ntb_msi_write_msg; + dr->entry->write_msi_msg_data = dr; + + return 0; +} + +/** + * ntbm_msi_request_threaded_irq() - allocate an MSI interrupt + * @ntb: NTB device context + * @handler: Function to be called when the IRQ occurs + * @thread_fn: Function to be called in a threaded interrupt context. NULL + * for clients which handle everything in @handler + * @devname: An ascii name for the claiming device, dev_name(dev) if NULL + * @dev_id: A cookie passed back to the handler function + * + * This function assigns an interrupt handler to an unused + * MSI interrupt and returns the descriptor used to trigger + * it. The descriptor can then be sent to a peer to trigger + * the interrupt. + * + * The interrupt resource is managed with devres so it will + * be automatically freed when the NTB device is torn down. + * + * If an IRQ allocated with this function needs to be freed + * separately, ntbm_free_irq() must be used. + * + * Return: IRQ number assigned on success, otherwise a negative error number. + */ +int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler, + irq_handler_t thread_fn, + const char *name, void *dev_id, + struct ntb_msi_desc *msi_desc) +{ + struct msi_desc *entry; + struct irq_desc *desc; + int ret; + + if (!ntb->msi) + return -EINVAL; + + for_each_pci_msi_entry(entry, ntb->pdev) { + desc = irq_to_desc(entry->irq); + if (desc->action) + continue; + + ret = devm_request_threaded_irq(&ntb->dev, entry->irq, handler, + thread_fn, 0, name, dev_id); + if (ret) + continue; + + if (ntb_msi_set_desc(ntb, entry, msi_desc)) { + devm_free_irq(&ntb->dev, entry->irq, dev_id); + continue; + } + + ret = ntbm_msi_setup_callback(ntb, entry, msi_desc); + if (ret) { + devm_free_irq(&ntb->dev, entry->irq, dev_id); + return ret; + } + + + return entry->irq; + } + + return -ENODEV; +} +EXPORT_SYMBOL(ntbm_msi_request_threaded_irq); + +static int ntbm_msi_callback_match(struct device *dev, void *res, void *data) +{ + struct ntb_dev *ntb = dev_ntb(dev); + struct ntb_msi_devres *dr = res; + + return dr->ntb == ntb && dr->entry == data; +} + +/** + * ntbm_msi_free_irq() - free an interrupt + * @ntb: NTB device context + * @irq: Interrupt line to free + * @dev_id: Device identity to free + * + * This function should be used to manually free IRQs allocated with + * ntbm_request_[threaded_]irq(). + */ +void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, void *dev_id) +{ + struct msi_desc *entry = irq_get_msi_desc(irq); + + entry->write_msi_msg = NULL; + entry->write_msi_msg_data = NULL; + + WARN_ON(devres_destroy(&ntb->dev, ntbm_msi_callback_release, + ntbm_msi_callback_match, entry)); + + devm_free_irq(&ntb->dev, irq, dev_id); +} +EXPORT_SYMBOL(ntbm_msi_free_irq); + +/** + * ntb_msi_peer_trigger() - Trigger an interrupt handler on a peer + * @ntb: NTB device context + * @peer: Peer index + * @desc: MSI descriptor data which triggers the interrupt + * + * This function triggers an interrupt on a peer. It requires + * the descriptor structure to have been passed from that peer + * by some other means. + * + * Return: Zero on success, otherwise a negative error number. + */ +int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc) +{ + int idx; + + if (!ntb->msi) + return -EINVAL; + + idx = desc->addr_offset / sizeof(*ntb->msi->peer_mws[peer]); + + iowrite32(desc->data, &ntb->msi->peer_mws[peer][idx]); + + return 0; +} +EXPORT_SYMBOL(ntb_msi_peer_trigger); + +/** + * ntb_msi_peer_addr() - Get the DMA address to trigger a peer's MSI interrupt + * @ntb: NTB device context + * @peer: Peer index + * @desc: MSI descriptor data which triggers the interrupt + * @msi_addr: Physical address to trigger the interrupt + * + * This function allows using DMA engines to trigger an interrupt + * (for example, trigger an interrupt to process the data after + * sending it). To trigger the interrupt, write @desc.data to the address + * returned in @msi_addr + * + * Return: Zero on success, otherwise a negative error number. + */ +int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc, + phys_addr_t *msi_addr) +{ + int peer_widx = ntb_peer_mw_count(ntb) - 1 - peer; + phys_addr_t mw_phys_addr; + int ret; + + ret = ntb_peer_mw_get_addr(ntb, peer_widx, &mw_phys_addr, NULL); + if (ret) + return ret; + + if (msi_addr) + *msi_addr = mw_phys_addr + desc->addr_offset; + + return 0; +} +EXPORT_SYMBOL(ntb_msi_peer_addr); diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index d4f39ba1d976..40c90ca10729 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -93,6 +93,12 @@ static bool use_dma; module_param(use_dma, bool, 0644); MODULE_PARM_DESC(use_dma, "Use DMA engine to perform large data copy"); +static bool use_msi; +#ifdef CONFIG_NTB_MSI +module_param(use_msi, bool, 0644); +MODULE_PARM_DESC(use_msi, "Use MSI interrupts instead of doorbells"); +#endif + static struct dentry *nt_debugfs_dir; /* Only two-ports NTB devices are supported */ @@ -188,6 +194,11 @@ struct ntb_transport_qp { u64 tx_err_no_buf; u64 tx_memcpy; u64 tx_async; + + bool use_msi; + int msi_irq; + struct ntb_msi_desc msi_desc; + struct ntb_msi_desc peer_msi_desc; }; struct ntb_transport_mw { @@ -221,6 +232,10 @@ struct ntb_transport_ctx { u64 qp_bitmap; u64 qp_bitmap_free; + bool use_msi; + unsigned int msi_spad_offset; + u64 msi_db_mask; + bool link_is_up; struct delayed_work link_work; struct work_struct link_cleanup; @@ -667,6 +682,114 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt, return 0; } +static irqreturn_t ntb_transport_isr(int irq, void *dev) +{ + struct ntb_transport_qp *qp = dev; + + tasklet_schedule(&qp->rxc_db_work); + + return IRQ_HANDLED; +} + +static void ntb_transport_setup_qp_peer_msi(struct ntb_transport_ctx *nt, + unsigned int qp_num) +{ + struct ntb_transport_qp *qp = &nt->qp_vec[qp_num]; + int spad = qp_num * 2 + nt->msi_spad_offset; + + if (!nt->use_msi) + return; + + if (spad >= ntb_spad_count(nt->ndev)) + return; + + qp->peer_msi_desc.addr_offset = + ntb_peer_spad_read(qp->ndev, PIDX, spad); + qp->peer_msi_desc.data = + ntb_peer_spad_read(qp->ndev, PIDX, spad + 1); + + dev_dbg(&qp->ndev->pdev->dev, "QP%d Peer MSI addr=%x data=%x\n", + qp_num, qp->peer_msi_desc.addr_offset, qp->peer_msi_desc.data); + + if (qp->peer_msi_desc.addr_offset) { + qp->use_msi = true; + dev_info(&qp->ndev->pdev->dev, + "Using MSI interrupts for QP%d\n", qp_num); + } +} + +static void ntb_transport_setup_qp_msi(struct ntb_transport_ctx *nt, + unsigned int qp_num) +{ + struct ntb_transport_qp *qp = &nt->qp_vec[qp_num]; + int spad = qp_num * 2 + nt->msi_spad_offset; + int rc; + + if (!nt->use_msi) + return; + + if (spad >= ntb_spad_count(nt->ndev)) { + dev_warn_once(&qp->ndev->pdev->dev, + "Not enough SPADS to use MSI interrupts\n"); + return; + } + + ntb_spad_write(qp->ndev, spad, 0); + ntb_spad_write(qp->ndev, spad + 1, 0); + + if (!qp->msi_irq) { + qp->msi_irq = ntbm_msi_request_irq(qp->ndev, ntb_transport_isr, + KBUILD_MODNAME, qp, + &qp->msi_desc); + if (qp->msi_irq < 0) { + dev_warn(&qp->ndev->pdev->dev, + "Unable to allocate MSI interrupt for qp%d\n", + qp_num); + return; + } + } + + rc = ntb_spad_write(qp->ndev, spad, qp->msi_desc.addr_offset); + if (rc) + goto err_free_interrupt; + + rc = ntb_spad_write(qp->ndev, spad + 1, qp->msi_desc.data); + if (rc) + goto err_free_interrupt; + + dev_dbg(&qp->ndev->pdev->dev, "QP%d MSI %d addr=%x data=%x\n", + qp_num, qp->msi_irq, qp->msi_desc.addr_offset, + qp->msi_desc.data); + + return; + +err_free_interrupt: + devm_free_irq(&nt->ndev->dev, qp->msi_irq, qp); +} + +static void ntb_transport_msi_peer_desc_changed(struct ntb_transport_ctx *nt) +{ + int i; + + dev_dbg(&nt->ndev->pdev->dev, "Peer MSI descriptors changed"); + + for (i = 0; i < nt->qp_count; i++) + ntb_transport_setup_qp_peer_msi(nt, i); +} + +static void ntb_transport_msi_desc_changed(void *data) +{ + struct ntb_transport_ctx *nt = data; + int i; + + dev_dbg(&nt->ndev->pdev->dev, "MSI descriptors changed"); + + for (i = 0; i < nt->qp_count; i++) + ntb_transport_setup_qp_msi(nt, i); + + ntb_peer_db_set(nt->ndev, nt->msi_db_mask); +} + static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw) { struct ntb_transport_mw *mw = &nt->mw_vec[num_mw]; @@ -905,6 +1028,20 @@ static void ntb_transport_link_work(struct work_struct *work) int rc = 0, i, spad; /* send the local info, in the opposite order of the way we read it */ + + if (nt->use_msi) { + rc = ntb_msi_setup_mws(ndev); + if (rc) { + dev_warn(&pdev->dev, + "Failed to register MSI memory window: %d\n", + rc); + nt->use_msi = false; + } + } + + for (i = 0; i < nt->qp_count; i++) + ntb_transport_setup_qp_msi(nt, i); + for (i = 0; i < nt->mw_count; i++) { size = nt->mw_vec[i].phys_size; @@ -962,6 +1099,7 @@ static void ntb_transport_link_work(struct work_struct *work) struct ntb_transport_qp *qp = &nt->qp_vec[i]; ntb_transport_setup_qp_mw(nt, i); + ntb_transport_setup_qp_peer_msi(nt, i); if (qp->client_ready) schedule_delayed_work(&qp->link_work, 0); @@ -1135,6 +1273,19 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) return -ENOMEM; nt->ndev = ndev; + + /* + * If we are using MSI, and have at least one extra memory window, + * we will reserve the last MW for the MSI window. + */ + if (use_msi && mw_count > 1) { + rc = ntb_msi_init(ndev, ntb_transport_msi_desc_changed); + if (!rc) { + mw_count -= 1; + nt->use_msi = true; + } + } + spad_count = ntb_spad_count(ndev); /* Limit the MW's based on the availability of scratchpads */ @@ -1148,6 +1299,8 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) max_mw_count_for_spads = (spad_count - MW0_SZ_HIGH) / 2; nt->mw_count = min(mw_count, max_mw_count_for_spads); + nt->msi_spad_offset = nt->mw_count * 2 + MW0_SZ_HIGH; + nt->mw_vec = kcalloc_node(mw_count, sizeof(*nt->mw_vec), GFP_KERNEL, node); if (!nt->mw_vec) { @@ -1178,6 +1331,12 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) qp_bitmap = ntb_db_valid_mask(ndev); qp_count = ilog2(qp_bitmap); + if (nt->use_msi) { + qp_count -= 1; + nt->msi_db_mask = 1 << qp_count; + ntb_db_clear_mask(ndev, nt->msi_db_mask); + } + if (max_num_clients && max_num_clients < qp_count) qp_count = max_num_clients; else if (nt->mw_count < qp_count) @@ -1601,7 +1760,10 @@ static void ntb_tx_copy_callback(void *data, iowrite32(entry->flags | DESC_DONE_FLAG, &hdr->flags); - ntb_peer_db_set(qp->ndev, BIT_ULL(qp->qp_num)); + if (qp->use_msi) + ntb_msi_peer_trigger(qp->ndev, PIDX, &qp->peer_msi_desc); + else + ntb_peer_db_set(qp->ndev, BIT_ULL(qp->qp_num)); /* The entry length can only be zero if the packet is intended to be a * "link down" or similar. Since no payload is being sent in these @@ -1869,6 +2031,7 @@ ntb_transport_create_queue(void *data, struct device *client_dev, qp->rx_dma_chan = NULL; } + qp->tx_mw_dma_addr = 0; if (qp->tx_dma_chan) { qp->tx_mw_dma_addr = dma_map_resource(qp->tx_dma_chan->device->dev, @@ -2268,6 +2431,11 @@ static void ntb_transport_doorbell_callback(void *data, int vector) u64 db_bits; unsigned int qp_num; + if (ntb_db_read(nt->ndev) & nt->msi_db_mask) { + ntb_transport_msi_peer_desc_changed(nt); + ntb_db_clear(nt->ndev, nt->msi_db_mask); + } + db_bits = (nt->qp_bitmap & ~nt->qp_bitmap_free & ntb_db_vector_mask(nt->ndev, vector)); diff --git a/drivers/ntb/test/Kconfig b/drivers/ntb/test/Kconfig index a8db00a7e087..516b991f33b9 100644 --- a/drivers/ntb/test/Kconfig +++ b/drivers/ntb/test/Kconfig @@ -26,3 +26,12 @@ config NTB_PERF to and from the window without additional software interaction. If unsure, say N. + +config NTB_MSI_TEST + tristate "NTB MSI Test Client" + depends on NTB_MSI + help + This tool demonstrates the use of the NTB MSI library to + send MSI interrupts between peers. + + If unsure, say N. diff --git a/drivers/ntb/test/Makefile b/drivers/ntb/test/Makefile index cbfd67622ef7..19ed91d8a3b1 100644 --- a/drivers/ntb/test/Makefile +++ b/drivers/ntb/test/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_NTB_PINGPONG) += ntb_pingpong.o obj-$(CONFIG_NTB_TOOL) += ntb_tool.o obj-$(CONFIG_NTB_PERF) += ntb_perf.o +obj-$(CONFIG_NTB_MSI_TEST) += ntb_msi_test.o diff --git a/drivers/ntb/test/ntb_msi_test.c b/drivers/ntb/test/ntb_msi_test.c new file mode 100644 index 000000000000..99d826ed9c34 --- /dev/null +++ b/drivers/ntb/test/ntb_msi_test.c @@ -0,0 +1,433 @@ +// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) + +#include <linux/module.h> +#include <linux/debugfs.h> +#include <linux/ntb.h> +#include <linux/pci.h> +#include <linux/radix-tree.h> +#include <linux/workqueue.h> + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_VERSION("0.1"); +MODULE_AUTHOR("Logan Gunthorpe <logang@deltatee.com>"); +MODULE_DESCRIPTION("Test for sending MSI interrupts over an NTB memory window"); + +static int num_irqs = 4; +module_param(num_irqs, int, 0644); +MODULE_PARM_DESC(num_irqs, "number of irqs to use"); + +struct ntb_msit_ctx { + struct ntb_dev *ntb; + struct dentry *dbgfs_dir; + struct work_struct setup_work; + + struct ntb_msit_isr_ctx { + int irq_idx; + int irq_num; + int occurrences; + struct ntb_msit_ctx *nm; + struct ntb_msi_desc desc; + } *isr_ctx; + + struct ntb_msit_peer { + struct ntb_msit_ctx *nm; + int pidx; + int num_irqs; + struct completion init_comp; + struct ntb_msi_desc *msi_desc; + } peers[]; +}; + +static struct dentry *ntb_msit_dbgfs_topdir; + +static irqreturn_t ntb_msit_isr(int irq, void *dev) +{ + struct ntb_msit_isr_ctx *isr_ctx = dev; + struct ntb_msit_ctx *nm = isr_ctx->nm; + + dev_dbg(&nm->ntb->dev, "Interrupt Occurred: %d", + isr_ctx->irq_idx); + + isr_ctx->occurrences++; + + return IRQ_HANDLED; +} + +static void ntb_msit_setup_work(struct work_struct *work) +{ + struct ntb_msit_ctx *nm = container_of(work, struct ntb_msit_ctx, + setup_work); + int irq_count = 0; + int irq; + int ret; + uintptr_t i; + + ret = ntb_msi_setup_mws(nm->ntb); + if (ret) { + dev_err(&nm->ntb->dev, "Unable to setup MSI windows: %d\n", + ret); + return; + } + + for (i = 0; i < num_irqs; i++) { + nm->isr_ctx[i].irq_idx = i; + nm->isr_ctx[i].nm = nm; + + if (!nm->isr_ctx[i].irq_num) { + irq = ntbm_msi_request_irq(nm->ntb, ntb_msit_isr, + KBUILD_MODNAME, + &nm->isr_ctx[i], + &nm->isr_ctx[i].desc); + if (irq < 0) + break; + + nm->isr_ctx[i].irq_num = irq; + } + + ret = ntb_spad_write(nm->ntb, 2 * i + 1, + nm->isr_ctx[i].desc.addr_offset); + if (ret) + break; + + ret = ntb_spad_write(nm->ntb, 2 * i + 2, + nm->isr_ctx[i].desc.data); + if (ret) + break; + + irq_count++; + } + + ntb_spad_write(nm->ntb, 0, irq_count); + ntb_peer_db_set(nm->ntb, BIT(ntb_port_number(nm->ntb))); +} + +static void ntb_msit_desc_changed(void *ctx) +{ + struct ntb_msit_ctx *nm = ctx; + int i; + + dev_dbg(&nm->ntb->dev, "MSI Descriptors Changed\n"); + + for (i = 0; i < num_irqs; i++) { + ntb_spad_write(nm->ntb, 2 * i + 1, + nm->isr_ctx[i].desc.addr_offset); + ntb_spad_write(nm->ntb, 2 * i + 2, + nm->isr_ctx[i].desc.data); + } + + ntb_peer_db_set(nm->ntb, BIT(ntb_port_number(nm->ntb))); +} + +static void ntb_msit_link_event(void *ctx) +{ + struct ntb_msit_ctx *nm = ctx; + + if (!ntb_link_is_up(nm->ntb, NULL, NULL)) + return; + + schedule_work(&nm->setup_work); +} + +static void ntb_msit_copy_peer_desc(struct ntb_msit_ctx *nm, int peer) +{ + int i; + struct ntb_msi_desc *desc = nm->peers[peer].msi_desc; + int irq_count = nm->peers[peer].num_irqs; + + for (i = 0; i < irq_count; i++) { + desc[i].addr_offset = ntb_peer_spad_read(nm->ntb, peer, + 2 * i + 1); + desc[i].data = ntb_peer_spad_read(nm->ntb, peer, 2 * i + 2); + } + + dev_info(&nm->ntb->dev, "Found %d interrupts on peer %d\n", + irq_count, peer); + + complete_all(&nm->peers[peer].init_comp); +} + +static void ntb_msit_db_event(void *ctx, int vec) +{ + struct ntb_msit_ctx *nm = ctx; + struct ntb_msi_desc *desc; + u64 peer_mask = ntb_db_read(nm->ntb); + u32 irq_count; + int peer; + + ntb_db_clear(nm->ntb, peer_mask); + + for (peer = 0; peer < sizeof(peer_mask) * 8; peer++) { + if (!(peer_mask & BIT(peer))) + continue; + + irq_count = ntb_peer_spad_read(nm->ntb, peer, 0); + if (irq_count == -1) + continue; + + desc = kcalloc(irq_count, sizeof(*desc), GFP_ATOMIC); + if (!desc) + continue; + + kfree(nm->peers[peer].msi_desc); + nm->peers[peer].msi_desc = desc; + nm->peers[peer].num_irqs = irq_count; + + ntb_msit_copy_peer_desc(nm, peer); + } +} + +static const struct ntb_ctx_ops ntb_msit_ops = { + .link_event = ntb_msit_link_event, + .db_event = ntb_msit_db_event, +}; + +static int ntb_msit_dbgfs_trigger(void *data, u64 idx) +{ + struct ntb_msit_peer *peer = data; + + if (idx >= peer->num_irqs) + return -EINVAL; + + dev_dbg(&peer->nm->ntb->dev, "trigger irq %llu on peer %u\n", + idx, peer->pidx); + + return ntb_msi_peer_trigger(peer->nm->ntb, peer->pidx, + &peer->msi_desc[idx]); +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_trigger_fops, NULL, + ntb_msit_dbgfs_trigger, "%llu\n"); + +static int ntb_msit_dbgfs_port_get(void *data, u64 *port) +{ + struct ntb_msit_peer *peer = data; + + *port = ntb_peer_port_number(peer->nm->ntb, peer->pidx); + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_port_fops, ntb_msit_dbgfs_port_get, + NULL, "%llu\n"); + +static int ntb_msit_dbgfs_count_get(void *data, u64 *count) +{ + struct ntb_msit_peer *peer = data; + + *count = peer->num_irqs; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_count_fops, ntb_msit_dbgfs_count_get, + NULL, "%llu\n"); + +static int ntb_msit_dbgfs_ready_get(void *data, u64 *ready) +{ + struct ntb_msit_peer *peer = data; + + *ready = try_wait_for_completion(&peer->init_comp); + + return 0; +} + +static int ntb_msit_dbgfs_ready_set(void *data, u64 ready) +{ + struct ntb_msit_peer *peer = data; + + return wait_for_completion_interruptible(&peer->init_comp); +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_ready_fops, ntb_msit_dbgfs_ready_get, + ntb_msit_dbgfs_ready_set, "%llu\n"); + +static int ntb_msit_dbgfs_occurrences_get(void *data, u64 *occurrences) +{ + struct ntb_msit_isr_ctx *isr_ctx = data; + + *occurrences = isr_ctx->occurrences; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_occurrences_fops, + ntb_msit_dbgfs_occurrences_get, + NULL, "%llu\n"); + +static int ntb_msit_dbgfs_local_port_get(void *data, u64 *port) +{ + struct ntb_msit_ctx *nm = data; + + *port = ntb_port_number(nm->ntb); + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(ntb_msit_local_port_fops, + ntb_msit_dbgfs_local_port_get, + NULL, "%llu\n"); + +static void ntb_msit_create_dbgfs(struct ntb_msit_ctx *nm) +{ + struct pci_dev *pdev = nm->ntb->pdev; + char buf[32]; + int i; + struct dentry *peer_dir; + + nm->dbgfs_dir = debugfs_create_dir(pci_name(pdev), + ntb_msit_dbgfs_topdir); + debugfs_create_file("port", 0400, nm->dbgfs_dir, nm, + &ntb_msit_local_port_fops); + + for (i = 0; i < ntb_peer_port_count(nm->ntb); i++) { + nm->peers[i].pidx = i; + nm->peers[i].nm = nm; + init_completion(&nm->peers[i].init_comp); + + snprintf(buf, sizeof(buf), "peer%d", i); + peer_dir = debugfs_create_dir(buf, nm->dbgfs_dir); + + debugfs_create_file_unsafe("trigger", 0200, peer_dir, + &nm->peers[i], + &ntb_msit_trigger_fops); + + debugfs_create_file_unsafe("port", 0400, peer_dir, + &nm->peers[i], &ntb_msit_port_fops); + + debugfs_create_file_unsafe("count", 0400, peer_dir, + &nm->peers[i], + &ntb_msit_count_fops); + + debugfs_create_file_unsafe("ready", 0600, peer_dir, + &nm->peers[i], + &ntb_msit_ready_fops); + } + + for (i = 0; i < num_irqs; i++) { + snprintf(buf, sizeof(buf), "irq%d_occurrences", i); + debugfs_create_file_unsafe(buf, 0400, nm->dbgfs_dir, + &nm->isr_ctx[i], + &ntb_msit_occurrences_fops); + } +} + +static void ntb_msit_remove_dbgfs(struct ntb_msit_ctx *nm) +{ + debugfs_remove_recursive(nm->dbgfs_dir); +} + +static int ntb_msit_probe(struct ntb_client *client, struct ntb_dev *ntb) +{ + struct ntb_msit_ctx *nm; + size_t struct_size; + int peers; + int ret; + + peers = ntb_peer_port_count(ntb); + if (peers <= 0) + return -EINVAL; + + if (ntb_spad_is_unsafe(ntb) || ntb_spad_count(ntb) < 2 * num_irqs + 1) { + dev_err(&ntb->dev, "NTB MSI test requires at least %d spads for %d irqs\n", + 2 * num_irqs + 1, num_irqs); + return -EFAULT; + } + + ret = ntb_spad_write(ntb, 0, -1); + if (ret) { + dev_err(&ntb->dev, "Unable to write spads: %d\n", ret); + return ret; + } + + ret = ntb_db_clear_mask(ntb, GENMASK(peers - 1, 0)); + if (ret) { + dev_err(&ntb->dev, "Unable to clear doorbell mask: %d\n", ret); + return ret; + } + + ret = ntb_msi_init(ntb, ntb_msit_desc_changed); + if (ret) { + dev_err(&ntb->dev, "Unable to initialize MSI library: %d\n", + ret); + return ret; + } + + struct_size = sizeof(*nm) + sizeof(*nm->peers) * peers; + + nm = devm_kzalloc(&ntb->dev, struct_size, GFP_KERNEL); + if (!nm) + return -ENOMEM; + + nm->isr_ctx = devm_kcalloc(&ntb->dev, num_irqs, sizeof(*nm->isr_ctx), + GFP_KERNEL); + if (!nm->isr_ctx) + return -ENOMEM; + + INIT_WORK(&nm->setup_work, ntb_msit_setup_work); + nm->ntb = ntb; + + ntb_msit_create_dbgfs(nm); + + ret = ntb_set_ctx(ntb, nm, &ntb_msit_ops); + if (ret) + goto remove_dbgfs; + + if (!nm->isr_ctx) + goto remove_dbgfs; + + ntb_link_enable(ntb, NTB_SPEED_AUTO, NTB_WIDTH_AUTO); + + return 0; + +remove_dbgfs: + ntb_msit_remove_dbgfs(nm); + devm_kfree(&ntb->dev, nm->isr_ctx); + devm_kfree(&ntb->dev, nm); + return ret; +} + +static void ntb_msit_remove(struct ntb_client *client, struct ntb_dev *ntb) +{ + struct ntb_msit_ctx *nm = ntb->ctx; + int i; + + ntb_link_disable(ntb); + ntb_db_set_mask(ntb, ntb_db_valid_mask(ntb)); + ntb_msi_clear_mws(ntb); + + for (i = 0; i < ntb_peer_port_count(ntb); i++) + kfree(nm->peers[i].msi_desc); + + ntb_clear_ctx(ntb); + ntb_msit_remove_dbgfs(nm); +} + +static struct ntb_client ntb_msit_client = { + .ops = { + .probe = ntb_msit_probe, + .remove = ntb_msit_remove + } +}; + +static int __init ntb_msit_init(void) +{ + int ret; + + if (debugfs_initialized()) + ntb_msit_dbgfs_topdir = debugfs_create_dir(KBUILD_MODNAME, + NULL); + + ret = ntb_register_client(&ntb_msit_client); + if (ret) + debugfs_remove_recursive(ntb_msit_dbgfs_topdir); + + return ret; +} +module_init(ntb_msit_init); + +static void __exit ntb_msit_exit(void) +{ + ntb_unregister_client(&ntb_msit_client); + debugfs_remove_recursive(ntb_msit_dbgfs_topdir); +} +module_exit(ntb_msit_exit); diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 11a6cd374004..d028331558ea 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -100,7 +100,7 @@ MODULE_DESCRIPTION("PCIe NTB Performance Measurement Tool"); #define DMA_TRIES 100 #define DMA_MDELAY 10 -#define MSG_TRIES 500 +#define MSG_TRIES 1000 #define MSG_UDELAY_LOW 1000 #define MSG_UDELAY_HIGH 2000 @@ -734,8 +734,6 @@ static void perf_disable_service(struct perf_ctx *perf) { int pidx; - ntb_link_disable(perf->ntb); - if (perf->cmd_send == perf_msg_cmd_send) { u64 inbits; @@ -752,6 +750,16 @@ static void perf_disable_service(struct perf_ctx *perf) for (pidx = 0; pidx < perf->pcnt; pidx++) flush_work(&perf->peers[pidx].service); + + for (pidx = 0; pidx < perf->pcnt; pidx++) { + struct perf_peer *peer = &perf->peers[pidx]; + + ntb_spad_write(perf->ntb, PERF_SPAD_CMD(peer->gidx), 0); + } + + ntb_db_clear(perf->ntb, PERF_SPAD_NOTIFY(perf->gidx)); + + ntb_link_disable(perf->ntb); } /*============================================================================== diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 59a6d232f77a..0884bedcfc7a 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -192,6 +192,9 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) { + if (desc->msi_attrib.is_virtual) + return NULL; + return desc->mask_base + desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE; } @@ -206,14 +209,19 @@ static void __iomem *pci_msix_desc_addr(struct msi_desc *desc) u32 __pci_msix_desc_mask_irq(struct msi_desc *desc, u32 flag) { u32 mask_bits = desc->masked; + void __iomem *desc_addr; if (pci_msi_ignore_mask) return 0; + desc_addr = pci_msix_desc_addr(desc); + if (!desc_addr) + return 0; mask_bits &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT; if (flag) mask_bits |= PCI_MSIX_ENTRY_CTRL_MASKBIT; - writel(mask_bits, pci_msix_desc_addr(desc) + PCI_MSIX_ENTRY_VECTOR_CTRL); + + writel(mask_bits, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL); return mask_bits; } @@ -273,6 +281,11 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) if (entry->msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); + if (!base) { + WARN_ON(1); + return; + } + msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR); msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR); msg->data = readl(base + PCI_MSIX_ENTRY_DATA); @@ -303,6 +316,9 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) } else if (entry->msi_attrib.is_msix) { void __iomem *base = pci_msix_desc_addr(entry); + if (!base) + goto skip; + writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR); writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR); writel(msg->data, base + PCI_MSIX_ENTRY_DATA); @@ -327,7 +343,13 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) msg->data); } } + +skip: entry->msg = *msg; + + if (entry->write_msi_msg) + entry->write_msi_msg(entry, entry->write_msi_msg_data); + } void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg) @@ -550,6 +572,7 @@ msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd) entry->msi_attrib.is_msix = 0; entry->msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); + entry->msi_attrib.is_virtual = 0; entry->msi_attrib.entry_nr = 0; entry->msi_attrib.maskbit = !!(control & PCI_MSI_FLAGS_MASKBIT); entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ @@ -674,6 +697,7 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, struct irq_affinity_desc *curmsk, *masks = NULL; struct msi_desc *entry; int ret, i; + int vec_count = pci_msix_vec_count(dev); if (affd) masks = irq_create_affinity_masks(nvec, affd); @@ -696,6 +720,10 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, entry->msi_attrib.entry_nr = entries[i].entry; else entry->msi_attrib.entry_nr = i; + + entry->msi_attrib.is_virtual = + entry->msi_attrib.entry_nr >= vec_count; + entry->msi_attrib.default_irq = dev->irq; entry->mask_base = base; @@ -714,12 +742,19 @@ static void msix_program_entries(struct pci_dev *dev, { struct msi_desc *entry; int i = 0; + void __iomem *desc_addr; for_each_pci_msi_entry(entry, dev) { if (entries) entries[i++].vector = entry->irq; - entry->masked = readl(pci_msix_desc_addr(entry) + - PCI_MSIX_ENTRY_VECTOR_CTRL); + + desc_addr = pci_msix_desc_addr(entry); + if (desc_addr) + entry->masked = readl(desc_addr + + PCI_MSIX_ENTRY_VECTOR_CTRL); + else + entry->masked = 0; + msix_mask_irq(entry, 1); } } @@ -932,7 +967,7 @@ int pci_msix_vec_count(struct pci_dev *dev) EXPORT_SYMBOL(pci_msix_vec_count); static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, - int nvec, struct irq_affinity *affd) + int nvec, struct irq_affinity *affd, int flags) { int nr_entries; int i, j; @@ -943,7 +978,7 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, nr_entries = pci_msix_vec_count(dev); if (nr_entries < 0) return nr_entries; - if (nvec > nr_entries) + if (nvec > nr_entries && !(flags & PCI_IRQ_VIRTUAL)) return nr_entries; if (entries) { @@ -1079,7 +1114,8 @@ EXPORT_SYMBOL(pci_enable_msi); static int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, - int maxvec, struct irq_affinity *affd) + int maxvec, struct irq_affinity *affd, + int flags) { int rc, nvec = maxvec; @@ -1096,7 +1132,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, return -ENOSPC; } - rc = __pci_enable_msix(dev, entries, nvec, affd); + rc = __pci_enable_msix(dev, entries, nvec, affd, flags); if (rc == 0) return nvec; @@ -1127,7 +1163,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { - return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL); + return __pci_enable_msix_range(dev, entries, minvec, maxvec, NULL, 0); } EXPORT_SYMBOL(pci_enable_msix_range); @@ -1167,7 +1203,7 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs, if (flags & PCI_IRQ_MSIX) { msix_vecs = __pci_enable_msix_range(dev, NULL, min_vecs, - max_vecs, affd); + max_vecs, affd, flags); if (msix_vecs > 0) return msix_vecs; } diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index bebbde4ebec0..8c94cd3fd1f2 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -30,6 +30,10 @@ module_param(use_dma_mrpc, bool, 0644); MODULE_PARM_DESC(use_dma_mrpc, "Enable the use of the DMA MRPC feature"); +static int nirqs = 32; +module_param(nirqs, int, 0644); +MODULE_PARM_DESC(nirqs, "number of interrupts to allocate (more may be useful for NTB applications)"); + static dev_t switchtec_devt; static DEFINE_IDA(switchtec_minor_ida); @@ -1263,8 +1267,12 @@ static int switchtec_init_isr(struct switchtec_dev *stdev) int dma_mrpc_irq; int rc; - nvecs = pci_alloc_irq_vectors(stdev->pdev, 1, 4, - PCI_IRQ_MSIX | PCI_IRQ_MSI); + if (nirqs < 4) + nirqs = 4; + + nvecs = pci_alloc_irq_vectors(stdev->pdev, 1, nirqs, + PCI_IRQ_MSIX | PCI_IRQ_MSI | + PCI_IRQ_VIRTUAL); if (nvecs < 0) return nvecs; diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 212b4a854f2c..38651fae7f21 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -4,6 +4,7 @@ config BTRFS_FS tristate "Btrfs filesystem support" select CRYPTO select CRYPTO_CRC32C + select LIBCRC32C select ZLIB_INFLATE select ZLIB_DEFLATE select LZO_COMPRESS diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 41a2bd2e0c56..5f7ee70b3d1a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4106,6 +4106,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); + btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1af069a9a0c7..ee582a36653d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -395,10 +395,31 @@ static noinline int add_async_extent(struct async_chunk *cow, return 0; } +/* + * Check if the inode has flags compatible with compression + */ +static inline bool inode_can_compress(struct inode *inode) +{ + if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW || + BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) + return false; + return true; +} + +/* + * Check if the inode needs to be submitted to compression, based on mount + * options, defragmentation, properties or heuristics. + */ static inline int inode_need_compress(struct inode *inode, u64 start, u64 end) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + if (!inode_can_compress(inode)) { + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: unexpected compression for ino %llu\n", + btrfs_ino(BTRFS_I(inode))); + return 0; + } /* force compress */ if (btrfs_test_opt(fs_info, FORCE_COMPRESS)) return 1; @@ -1631,7 +1652,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - } else if (!inode_need_compress(inode, start, end)) { + } else if (!inode_can_compress(inode) || + !inode_need_compress(inode, start, end)) { ret = cow_file_range(inode, locked_page, start, end, end, page_started, nr_written, 1, NULL); } else { diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a13ddba1ebc3..d74b74ca07af 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5941,6 +5941,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; + int ret = 0; ASSERT(op != BTRFS_MAP_DISCARD); @@ -5961,8 +5962,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, btrfs_crit(fs_info, "stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", stripe_offset, offset, em->start, logical, stripe_len); - free_extent_map(em); - return -EINVAL; + ret = -EINVAL; + goto out; } /* stripe_offset is the offset of this block in its stripe */ @@ -6009,7 +6010,10 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom->stripe_offset = stripe_offset; io_geom->raid56_stripe_offset = raid56_full_stripe_start; - return 0; +out: + /* once for us */ + free_extent_map(em); + return ret; } static int __btrfs_map_block(struct btrfs_fs_info *fs_info, diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 270d3c58fb3b..3289b566463f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1104,6 +1104,10 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, goto out; } + rc = -EOPNOTSUPP; + if (!target_tcon->ses->server->ops->copychunk_range) + goto out; + /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants @@ -1115,11 +1119,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, /* should we flush first and last page first */ truncate_inode_pages(&target_inode->i_data, 0); - if (target_tcon->ses->server->ops->copychunk_range) + rc = file_modified(dst_file); + if (!rc) rc = target_tcon->ses->server->ops->copychunk_range(xid, smb_file_src, smb_file_target, off, len, destoff); - else - rc = -EOPNOTSUPP; + + file_accessed(src_file); /* force revalidate of size and timestamps of target file now * that target is updated on the server diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index aea005703785..4b21a90015a9 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -152,5 +152,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.20" +#define CIFS_VERSION "2.21" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 1bffe029fb66..56ca4b8ccaba 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2406,6 +2406,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) struct inode *inode = d_inode(direntry); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cifsInode = CIFS_I(inode); + struct cifsFileInfo *wfile; + struct cifs_tcon *tcon; char *full_path = NULL; int rc = -EACCES; __u32 dosattr = 0; @@ -2452,6 +2454,20 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) mapping_set_error(inode->i_mapping, rc); rc = 0; + if (attrs->ia_valid & ATTR_MTIME) { + rc = cifs_get_writable_file(cifsInode, false, &wfile); + if (!rc) { + tcon = tlink_tcon(wfile->tlink); + rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid); + cifsFileInfo_put(wfile); + if (rc) + return rc; + } else if (rc != -EBADF) + return rc; + else + rc = 0; + } + if (attrs->ia_valid & ATTR_SIZE) { rc = cifs_set_file_size(inode, attrs, xid, full_path); if (rc != 0) diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 54bffb2a1786..e6a1fc72018f 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -88,14 +88,20 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, } if (buf) { - /* open response does not have IndexNumber field - get it */ - rc = SMB2_get_srv_num(xid, oparms->tcon, fid->persistent_fid, + /* if open response does not have IndexNumber field - get it */ + if (smb2_data->IndexNumber == 0) { + rc = SMB2_get_srv_num(xid, oparms->tcon, + fid->persistent_fid, fid->volatile_fid, &smb2_data->IndexNumber); - if (rc) { - /* let get_inode_info disable server inode numbers */ - smb2_data->IndexNumber = 0; - rc = 0; + if (rc) { + /* + * let get_inode_info disable server inode + * numbers + */ + smb2_data->IndexNumber = 0; + rc = 0; + } } move_smb2_info_to_cifs(buf, smb2_data); } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0cdc4e47ca87..a5bc1b671c12 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -694,8 +694,51 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) smb2_set_related(&rqst[1]); + /* + * We do not hold the lock for the open because in case + * SMB2_open needs to reconnect, it will end up calling + * cifs_mark_open_files_invalid() which takes the lock again + * thus causing a deadlock + */ + + mutex_unlock(&tcon->crfid.fid_mutex); rc = compound_send_recv(xid, ses, flags, 2, rqst, resp_buftype, rsp_iov); + mutex_lock(&tcon->crfid.fid_mutex); + + /* + * Now we need to check again as the cached root might have + * been successfully re-opened from a concurrent process + */ + + if (tcon->crfid.is_valid) { + /* work was already done */ + + /* stash fids for close() later */ + struct cifs_fid fid = { + .persistent_fid = pfid->persistent_fid, + .volatile_fid = pfid->volatile_fid, + }; + + /* + * caller expects this func to set pfid to a valid + * cached root, so we copy the existing one and get a + * reference. + */ + memcpy(pfid, tcon->crfid.fid, sizeof(*pfid)); + kref_get(&tcon->crfid.refcount); + + mutex_unlock(&tcon->crfid.fid_mutex); + + if (rc == 0) { + /* close extra handle outside of crit sec */ + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + } + goto oshr_free; + } + + /* Cached root is still invalid, continue normaly */ + if (rc) goto oshr_exit; @@ -711,11 +754,12 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) tcon->crfid.is_valid = true; kref_init(&tcon->crfid.refcount); + /* BB TBD check to see if oplock level check can be removed below */ if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { kref_get(&tcon->crfid.refcount); - oplock = smb2_parse_lease_state(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key); + smb2_parse_contexts(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key, &oplock, NULL); } else goto oshr_exit; @@ -729,8 +773,9 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) (char *)&tcon->crfid.file_all_info)) tcon->crfid.file_all_info_is_valid = 1; - oshr_exit: +oshr_exit: mutex_unlock(&tcon->crfid.fid_mutex); +oshr_free: SMB2_open_free(&rqst[0]); SMB2_query_info_free(&rqst[1]); free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index f58e4dc3987b..c8cd7b6cdda2 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1873,10 +1873,21 @@ create_reconnect_durable_buf(struct cifs_fid *fid) return buf; } -__u8 -smb2_parse_lease_state(struct TCP_Server_Info *server, +static void +parse_query_id_ctxt(struct create_context *cc, struct smb2_file_all_info *buf) +{ + struct create_on_disk_id *pdisk_id = (struct create_on_disk_id *)cc; + + cifs_dbg(FYI, "parse query id context 0x%llx 0x%llx\n", + pdisk_id->DiskFileId, pdisk_id->VolumeId); + buf->IndexNumber = pdisk_id->DiskFileId; +} + +void +smb2_parse_contexts(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key) + unsigned int *epoch, char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf) { char *data_offset; struct create_context *cc; @@ -1884,15 +1895,24 @@ smb2_parse_lease_state(struct TCP_Server_Info *server, unsigned int remaining; char *name; + *oplock = 0; data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; + + /* Initialize inode number to 0 in case no valid data in qfid context */ + if (buf) + buf->IndexNumber = 0; + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, "RqLs", 4) == 0) - return server->ops->parse_lease_buf(cc, epoch, - lease_key); + strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + else if (buf && (le16_to_cpu(cc->NameLength) == 4) && + strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) + parse_query_id_ctxt(cc, buf); next = le32_to_cpu(cc->Next); if (!next) @@ -1901,7 +1921,10 @@ smb2_parse_lease_state(struct TCP_Server_Info *server, cc = (struct create_context *)((char *)cc + next); } - return 0; + if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) + *oplock = rsp->OplockLevel; + + return; } static int @@ -2588,12 +2611,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, buf->DeletePending = 0; } - if (rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) - *oplock = smb2_parse_lease_state(server, rsp, - &oparms->fid->epoch, - oparms->fid->lease_key); - else - *oplock = rsp->OplockLevel; + + smb2_parse_contexts(server, rsp, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 7e2e782f8edd..747de9317659 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -818,7 +818,9 @@ struct durable_reconnect_context_v2 { } __packed; /* See MS-SMB2 2.2.14.2.9 */ -struct on_disk_id { +struct create_on_disk_id { + struct create_context ccontext; + __u8 Name[8]; __le64 DiskFileId; __le64 VolumeId; __u32 Reserved[4]; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 52df125e9189..07ca72486cfa 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -228,9 +228,10 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern __u8 smb2_parse_lease_state(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key); +extern void smb2_parse_contexts(struct TCP_Server_Info *server, + struct smb2_create_rsp *rsp, + unsigned int *epoch, char *lease_key, + __u8 *oplock, struct smb2_file_all_info *buf); extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/include/linux/connector.h b/include/linux/connector.h index 6b6c7396a584..cb732643471b 100644 --- a/include/linux/connector.h +++ b/include/linux/connector.h @@ -50,7 +50,6 @@ struct cn_dev { u32 seq, groups; struct sock *nls; - void (*input) (struct sk_buff *skb); struct cn_queue_dev *cbdev; }; diff --git a/include/linux/msi.h b/include/linux/msi.h index d48e919d55ae..8ad679e9d9c0 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -64,6 +64,10 @@ struct ti_sci_inta_msi_desc { * @msg: The last set MSI message cached for reuse * @affinity: Optional pointer to a cpu affinity mask for this descriptor * + * @write_msi_msg: Callback that may be called when the MSI message + * address or data changes + * @write_msi_msg_data: Data parameter for the callback. + * * @masked: [PCI MSI/X] Mask bits * @is_msix: [PCI MSI/X] True if MSI-X * @multiple: [PCI MSI/X] log2 num of messages allocated @@ -90,6 +94,9 @@ struct msi_desc { const void *iommu_cookie; #endif + void (*write_msi_msg)(struct msi_desc *entry, void *data); + void *write_msi_msg_data; + union { /* PCI MSI/X specific data */ struct { @@ -100,6 +107,7 @@ struct msi_desc { u8 multi_cap : 3; u8 maskbit : 1; u8 is_64 : 1; + u8 is_virtual : 1; u16 entry_nr; unsigned default_irq; } msi_attrib; diff --git a/include/linux/netfilter/nf_conntrack_h323_asn1.h b/include/linux/netfilter/nf_conntrack_h323_asn1.h index 91d6275292a5..19df78341fb3 100644 --- a/include/linux/netfilter/nf_conntrack_h323_asn1.h +++ b/include/linux/netfilter/nf_conntrack_h323_asn1.h @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /**************************************************************************** - * ip_conntrack_h323_asn1.h - BER and PER decoding library for H.323 - * conntrack/NAT module. + * BER and PER decoding library for H.323 conntrack/NAT module. * * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net> * diff --git a/include/linux/ntb.h b/include/linux/ntb.h index 56a92e3ae3ae..8c13538aeffe 100644 --- a/include/linux/ntb.h +++ b/include/linux/ntb.h @@ -58,9 +58,11 @@ #include <linux/completion.h> #include <linux/device.h> +#include <linux/interrupt.h> struct ntb_client; struct ntb_dev; +struct ntb_msi; struct pci_dev; /** @@ -205,7 +207,7 @@ static inline int ntb_ctx_ops_is_valid(const struct ntb_ctx_ops *ops) } /** - * struct ntb_ctx_ops - ntb device operations + * struct ntb_dev_ops - ntb device operations * @port_number: See ntb_port_number(). * @peer_port_count: See ntb_peer_port_count(). * @peer_port_number: See ntb_peer_port_number(). @@ -404,7 +406,7 @@ struct ntb_client { #define drv_ntb_client(__drv) container_of((__drv), struct ntb_client, drv) /** - * struct ntb_device - ntb device + * struct ntb_dev - ntb device * @dev: Linux device object. * @pdev: PCI device entry of the ntb. * @topo: Detected topology of the ntb. @@ -426,6 +428,10 @@ struct ntb_dev { spinlock_t ctx_lock; /* block unregister until device is fully released */ struct completion released; + +#ifdef CONFIG_NTB_MSI + struct ntb_msi *msi; +#endif }; #define dev_ntb(__dev) container_of((__dev), struct ntb_dev, dev) @@ -616,7 +622,6 @@ static inline int ntb_port_number(struct ntb_dev *ntb) return ntb->ops->port_number(ntb); } - /** * ntb_peer_port_count() - get the number of peer device ports * @ntb: NTB device context. @@ -654,6 +659,58 @@ static inline int ntb_peer_port_number(struct ntb_dev *ntb, int pidx) } /** + * ntb_logical_port_number() - get the logical port number of the local port + * @ntb: NTB device context. + * + * The Logical Port Number is defined to be a unique number for each + * port starting from zero through to the number of ports minus one. + * This is in contrast to the Port Number where each port can be assigned + * any unique physical number by the hardware. + * + * The logical port number is useful for calculating the resource indexes + * used by peers. + * + * Return: the logical port number or negative value indicating an error + */ +static inline int ntb_logical_port_number(struct ntb_dev *ntb) +{ + int lport = ntb_port_number(ntb); + int pidx; + + if (lport < 0) + return lport; + + for (pidx = 0; pidx < ntb_peer_port_count(ntb); pidx++) + if (lport <= ntb_peer_port_number(ntb, pidx)) + return pidx; + + return pidx; +} + +/** + * ntb_peer_logical_port_number() - get the logical peer port by given index + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * The Logical Port Number is defined to be a unique number for each + * port starting from zero through to the number of ports minus one. + * This is in contrast to the Port Number where each port can be assigned + * any unique physical number by the hardware. + * + * The logical port number is useful for calculating the resource indexes + * used by peers. + * + * Return: the peer's logical port number or negative value indicating an error + */ +static inline int ntb_peer_logical_port_number(struct ntb_dev *ntb, int pidx) +{ + if (ntb_peer_port_number(ntb, pidx) < ntb_port_number(ntb)) + return pidx; + else + return pidx + 1; +} + +/** * ntb_peer_port_idx() - get the peer device port index by given port number * @ntb: NTB device context. * @port: Peer port number. @@ -1506,4 +1563,141 @@ static inline int ntb_peer_msg_write(struct ntb_dev *ntb, int pidx, int midx, return ntb->ops->peer_msg_write(ntb, pidx, midx, msg); } +/** + * ntb_peer_resource_idx() - get a resource index for a given peer idx + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * When constructing a graph of peers, each remote peer must use a different + * resource index (mw, doorbell, etc) to communicate with each other + * peer. + * + * In a two peer system, this function should always return 0 such that + * resource 0 points to the remote peer on both ports. + * + * In a 5 peer system, this function will return the following matrix + * + * pidx \ port 0 1 2 3 4 + * 0 0 0 1 2 3 + * 1 0 1 1 2 3 + * 2 0 1 2 2 3 + * 3 0 1 2 3 3 + * + * For example, if this function is used to program peer's memory + * windows, port 0 will program MW 0 on all it's peers to point to itself. + * port 1 will program MW 0 in port 0 to point to itself and MW 1 on all + * other ports. etc. + * + * For the legacy two host case, ntb_port_number() and ntb_peer_port_number() + * both return zero and therefore this function will always return zero. + * So MW 0 on each host would be programmed to point to the other host. + * + * Return: the resource index to use for that peer. + */ +static inline int ntb_peer_resource_idx(struct ntb_dev *ntb, int pidx) +{ + int local_port, peer_port; + + if (pidx >= ntb_peer_port_count(ntb)) + return -EINVAL; + + local_port = ntb_logical_port_number(ntb); + peer_port = ntb_peer_logical_port_number(ntb, pidx); + + if (peer_port < local_port) + return local_port - 1; + else + return local_port; +} + +/** + * ntb_peer_highest_mw_idx() - get a memory window index for a given peer idx + * using the highest index memory windows first + * + * @ntb: NTB device context. + * @pidx: Peer port index. + * + * Like ntb_peer_resource_idx(), except it returns indexes starting with + * last memory window index. + * + * Return: the resource index to use for that peer. + */ +static inline int ntb_peer_highest_mw_idx(struct ntb_dev *ntb, int pidx) +{ + int ret; + + ret = ntb_peer_resource_idx(ntb, pidx); + if (ret < 0) + return ret; + + return ntb_mw_count(ntb, pidx) - ret - 1; +} + +struct ntb_msi_desc { + u32 addr_offset; + u32 data; +}; + +#ifdef CONFIG_NTB_MSI + +int ntb_msi_init(struct ntb_dev *ntb, void (*desc_changed)(void *ctx)); +int ntb_msi_setup_mws(struct ntb_dev *ntb); +void ntb_msi_clear_mws(struct ntb_dev *ntb); +int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, irq_handler_t handler, + irq_handler_t thread_fn, + const char *name, void *dev_id, + struct ntb_msi_desc *msi_desc); +void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, void *dev_id); +int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc); +int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc, + phys_addr_t *msi_addr); + +#else /* not CONFIG_NTB_MSI */ + +static inline int ntb_msi_init(struct ntb_dev *ntb, + void (*desc_changed)(void *ctx)) +{ + return -EOPNOTSUPP; +} +static inline int ntb_msi_setup_mws(struct ntb_dev *ntb) +{ + return -EOPNOTSUPP; +} +static inline void ntb_msi_clear_mws(struct ntb_dev *ntb) {} +static inline int ntbm_msi_request_threaded_irq(struct ntb_dev *ntb, + irq_handler_t handler, + irq_handler_t thread_fn, + const char *name, void *dev_id, + struct ntb_msi_desc *msi_desc) +{ + return -EOPNOTSUPP; +} +static inline void ntbm_msi_free_irq(struct ntb_dev *ntb, unsigned int irq, + void *dev_id) {} +static inline int ntb_msi_peer_trigger(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc) +{ + return -EOPNOTSUPP; +} +static inline int ntb_msi_peer_addr(struct ntb_dev *ntb, int peer, + struct ntb_msi_desc *desc, + phys_addr_t *msi_addr) +{ + return -EOPNOTSUPP; + +} + +#endif /* CONFIG_NTB_MSI */ + +static inline int ntbm_msi_request_irq(struct ntb_dev *ntb, + irq_handler_t handler, + const char *name, void *dev_id, + struct ntb_msi_desc *msi_desc) +{ + return ntbm_msi_request_threaded_irq(ntb, handler, NULL, name, + dev_id, msi_desc); +} + #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index 2972793e3028..9e700d9f9f28 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1412,6 +1412,15 @@ int pci_set_vga_state(struct pci_dev *pdev, bool decode, #define PCI_IRQ_MSI (1 << 1) /* Allow MSI interrupts */ #define PCI_IRQ_MSIX (1 << 2) /* Allow MSI-X interrupts */ #define PCI_IRQ_AFFINITY (1 << 3) /* Auto-assign affinity */ + +/* + * Virtual interrupts allow for more interrupts to be allocated + * than the device has interrupts for. These are not programmed + * into the device's MSI-X table and must be handled by some + * other driver means. + */ +#define PCI_IRQ_VIRTUAL (1 << 4) + #define PCI_IRQ_ALL_TYPES \ (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 88c27153a4bc..45850a8391d9 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -4170,7 +4170,7 @@ struct sta_opmode_info { u8 rx_nss; }; -#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)ERR_PTR(-ENODATA)) +#define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)(long)(-ENODATA)) /** * struct wiphy_vendor_command - vendor command definition diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index db337299e81e..b16d21636d69 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -2,8 +2,8 @@ #define _NET_FLOW_OFFLOAD_H #include <linux/kernel.h> +#include <linux/list.h> #include <net/flow_dissector.h> -#include <net/sch_generic.h> struct flow_match { struct flow_dissector *dissector; @@ -249,6 +249,10 @@ enum flow_block_binder_type { FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS, }; +struct flow_block { + struct list_head cb_list; +}; + struct netlink_ext_ack; struct flow_block_offload { @@ -256,29 +260,33 @@ struct flow_block_offload { enum flow_block_binder_type binder_type; bool block_shared; struct net *net; + struct flow_block *block; struct list_head cb_list; struct list_head *driver_block_list; struct netlink_ext_ack *extack; }; +enum tc_setup_type; +typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data, + void *cb_priv); + struct flow_block_cb { struct list_head driver_list; struct list_head list; - struct net *net; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; void *cb_ident; void *cb_priv; void (*release)(void *cb_priv); unsigned int refcnt; }; -struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, +struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)); void flow_block_cb_free(struct flow_block_cb *block_cb); -struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *offload, - tc_setup_cb_t *cb, void *cb_ident); +struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, + flow_setup_cb_t *cb, void *cb_ident); void *flow_block_cb_priv(struct flow_block_cb *block_cb); void flow_block_cb_incref(struct flow_block_cb *block_cb); @@ -296,11 +304,12 @@ static inline void flow_block_cb_remove(struct flow_block_cb *block_cb, list_move(&block_cb->list, &offload->cb_list); } -bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident, +bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list); int flow_block_cb_setup_simple(struct flow_block_offload *f, - struct list_head *driver_list, tc_setup_cb_t *cb, + struct list_head *driver_list, + flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, bool ingress_only); enum flow_cls_command { @@ -333,4 +342,9 @@ flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) return flow_cmd->rule; } +static inline void flow_block_init(struct flow_block *flow_block) +{ + INIT_LIST_HEAD(&flow_block->cb_list); +} + #endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 93ce6b0daaba..573429be4d59 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -76,6 +76,11 @@ struct nf_conntrack_expect_policy { #define NF_CT_EXPECT_CLASS_DEFAULT 0 #define NF_CT_EXPECT_MAX_CNT 255 +/* Allow to reuse expectations with the same tuples from different master + * conntracks. + */ +#define NF_CT_EXP_F_SKIP_MASTER 0x1 + int nf_conntrack_expect_pernet_init(struct net *net); void nf_conntrack_expect_pernet_fini(struct net *net); @@ -122,10 +127,11 @@ void nf_ct_expect_init(struct nf_conntrack_expect *, unsigned int, u_int8_t, u_int8_t, const __be16 *, const __be16 *); void nf_ct_expect_put(struct nf_conntrack_expect *exp); int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, - u32 portid, int report); -static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect) + u32 portid, int report, unsigned int flags); +static inline int nf_ct_expect_related(struct nf_conntrack_expect *expect, + unsigned int flags) { - return nf_ct_expect_related_report(expect, 0, 0); + return nf_ct_expect_related_report(expect, 0, 0, flags); } #endif /*_NF_CONNTRACK_EXPECT_H*/ diff --git a/include/net/netfilter/nf_conntrack_synproxy.h b/include/net/netfilter/nf_conntrack_synproxy.h index 8f00125b06f4..44513b93bd55 100644 --- a/include/net/netfilter/nf_conntrack_synproxy.h +++ b/include/net/netfilter/nf_conntrack_synproxy.h @@ -68,6 +68,7 @@ struct synproxy_options { u8 options; u8 wscale; u16 mss; + u16 mss_encode; u32 tsval; u32 tsecr; }; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 35dfdd9f69b3..9b624566b82d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -11,6 +11,7 @@ #include <linux/rhashtable.h> #include <net/netfilter/nf_flow_table.h> #include <net/netlink.h> +#include <net/flow_offload.h> struct module; @@ -951,7 +952,7 @@ struct nft_stats { * @stats: per-cpu chain stats * @chain: the chain * @dev_name: device name that this base chain is attached to (if any) - * @cb_list: list of flow block callbacks (for hardware offload) + * @flow_block: flow block (for hardware offload) */ struct nft_base_chain { struct nf_hook_ops ops; @@ -961,7 +962,7 @@ struct nft_base_chain { struct nft_stats __percpu *stats; struct nft_chain chain; char dev_name[IFNAMSIZ]; - struct list_head cb_list; + struct flow_block flow_block; }; static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 841faadceb6e..e429809ca90d 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -6,7 +6,6 @@ #include <linux/workqueue.h> #include <net/sch_generic.h> #include <net/act_api.h> -#include <net/flow_offload.h> #include <net/net_namespace.h> /* TC action not accessible from user space */ @@ -126,14 +125,14 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block) } static inline -int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb, +int tc_setup_cb_block_register(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv) { return 0; } static inline -void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb, +void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv) { } diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 855167bbc372..6b6b01234dd9 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -15,6 +15,7 @@ #include <linux/mutex.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> +#include <net/flow_offload.h> struct Qdisc_ops; struct qdisc_walker; @@ -22,9 +23,6 @@ struct tcf_walker; struct module; struct bpf_flow_keys; -typedef int tc_setup_cb_t(enum tc_setup_type type, - void *type_data, void *cb_priv); - typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv, enum tc_setup_type type, void *type_data); @@ -313,7 +311,7 @@ struct tcf_proto_ops { void (*walk)(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, - tc_setup_cb_t *cb, void *cb_priv, + flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack); void (*bind_class)(void *, u32, unsigned long); void * (*tmplt_create)(struct net *net, @@ -401,7 +399,7 @@ struct tcf_block { refcount_t refcnt; struct net *net; struct Qdisc *q; - struct list_head cb_list; + struct flow_block flow_block; struct list_head owner_list; bool keep_dst; unsigned int offloadcnt; /* Number of oddloaded filters */ diff --git a/include/net/tcp.h b/include/net/tcp.h index f42d300f0cfa..e5cf514ba118 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1709,6 +1709,11 @@ static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk) return skb_rb_first(&sk->tcp_rtx_queue); } +static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk) +{ + return skb_rb_last(&sk->tcp_rtx_queue); +} + static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) { return skb_peek(&sk->sk_write_queue); diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 75758ec26c8b..beb9a9d0c00a 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2863,7 +2863,7 @@ enum nl80211_attrs { #define NL80211_HT_CAPABILITY_LEN 26 #define NL80211_VHT_CAPABILITY_LEN 12 #define NL80211_HE_MIN_CAPABILITY_LEN 16 -#define NL80211_HE_MAX_CAPABILITY_LEN 51 +#define NL80211_HE_MAX_CAPABILITY_LEN 54 #define NL80211_MAX_NR_CIPHER_SUITES 5 #define NL80211_MAX_NR_AKM_SUITES 2 diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9d9705ceda76..2427bc4d8eba 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -518,7 +518,13 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_RGBX444 v4l2_fourcc('R', 'X', '1', '2') /* 16 rrrrgggg bbbbxxxx */ #define V4L2_PIX_FMT_ABGR444 v4l2_fourcc('A', 'B', '1', '2') /* 16 aaaabbbb ggggrrrr */ #define V4L2_PIX_FMT_XBGR444 v4l2_fourcc('X', 'B', '1', '2') /* 16 xxxxbbbb ggggrrrr */ -#define V4L2_PIX_FMT_BGRA444 v4l2_fourcc('B', 'A', '1', '2') /* 16 bbbbgggg rrrraaaa */ + +/* + * Originally this had 'BA12' as fourcc, but this clashed with the older + * V4L2_PIX_FMT_SGRBG12 which inexplicably used that same fourcc. + * So use 'GA12' instead for V4L2_PIX_FMT_BGRA444. + */ +#define V4L2_PIX_FMT_BGRA444 v4l2_fourcc('G', 'A', '1', '2') /* 16 bbbbgggg rrrraaaa */ #define V4L2_PIX_FMT_BGRX444 v4l2_fourcc('B', 'X', '1', '2') /* 16 bbbbgggg rrrrxxxx */ #define V4L2_PIX_FMT_RGB555 v4l2_fourcc('R', 'G', 'B', 'O') /* 16 RGB-5-5-5 */ #define V4L2_PIX_FMT_ARGB555 v4l2_fourcc('A', 'R', '1', '5') /* 16 ARGB-1-5-5-5 */ diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt index fc020c09b7e8..deff97217496 100644 --- a/kernel/Kconfig.preempt +++ b/kernel/Kconfig.preempt @@ -35,10 +35,10 @@ config PREEMPT_VOLUNTARY Select this if you are building a kernel for a desktop system. -config PREEMPT_LL +config PREEMPT bool "Preemptible Kernel (Low-Latency Desktop)" depends on !ARCH_NO_PREEMPT - select PREEMPT + select PREEMPTION select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK help This option reduces the latency of the kernel by making @@ -58,7 +58,7 @@ config PREEMPT_LL config PREEMPT_RT bool "Fully Preemptible Kernel (Real-Time)" depends on EXPERT && ARCH_SUPPORTS_RT - select PREEMPT + select PREEMPTION help This option turns the kernel into a real-time kernel by replacing various locking primitives (spinlocks, rwlocks, etc.) with @@ -77,6 +77,6 @@ endchoice config PREEMPT_COUNT bool -config PREEMPT +config PREEMPTION bool select PREEMPT_COUNT diff --git a/kernel/exit.c b/kernel/exit.c index a75b6a7f458a..4436158a6d30 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -720,6 +720,7 @@ static void exit_notify(struct task_struct *tsk, int group_dead) if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); + tsk->exit_state = EXIT_ZOMBIE; if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 154fa558bb90..5040fe43f4b4 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -6,7 +6,7 @@ menuconfig NF_TABLES_BRIDGE depends on BRIDGE && NETFILTER && NF_TABLES select NETFILTER_FAMILY_BRIDGE - bool "Ethernet Bridge nf_tables support" + tristate "Ethernet Bridge nf_tables support" if NF_TABLES_BRIDGE @@ -25,6 +25,8 @@ config NF_LOG_BRIDGE tristate "Bridge packet logging" select NF_LOG_COMMON +endif # NF_TABLES_BRIDGE + config NF_CONNTRACK_BRIDGE tristate "IPv4/IPV6 bridge connection tracking support" depends on NF_CONNTRACK @@ -39,8 +41,6 @@ config NF_CONNTRACK_BRIDGE To compile it as a module, choose M here. If unsure, say N. -endif # NF_TABLES_BRIDGE - menuconfig BRIDGE_NF_EBTABLES tristate "Ethernet Bridge tables (ebtables) support" depends on BRIDGE && NETFILTER && NETFILTER_XTABLES diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index 76f8db3841d7..d63b970784dc 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -165,7 +165,7 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule, } EXPORT_SYMBOL(flow_rule_match_enc_opts); -struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, +struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb, void *cb_ident, void *cb_priv, void (*release)(void *cb_priv)) { @@ -175,7 +175,6 @@ struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb, if (!block_cb) return ERR_PTR(-ENOMEM); - block_cb->net = net; block_cb->cb = cb; block_cb->cb_ident = cb_ident; block_cb->cb_priv = cb_priv; @@ -194,14 +193,13 @@ void flow_block_cb_free(struct flow_block_cb *block_cb) } EXPORT_SYMBOL(flow_block_cb_free); -struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *f, - tc_setup_cb_t *cb, void *cb_ident) +struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block, + flow_setup_cb_t *cb, void *cb_ident) { struct flow_block_cb *block_cb; - list_for_each_entry(block_cb, f->driver_block_list, driver_list) { - if (block_cb->net == f->net && - block_cb->cb == cb && + list_for_each_entry(block_cb, &block->cb_list, list) { + if (block_cb->cb == cb && block_cb->cb_ident == cb_ident) return block_cb; } @@ -228,7 +226,7 @@ unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb) } EXPORT_SYMBOL(flow_block_cb_decref); -bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident, +bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident, struct list_head *driver_block_list) { struct flow_block_cb *block_cb; @@ -245,7 +243,8 @@ EXPORT_SYMBOL(flow_block_cb_is_busy); int flow_block_cb_setup_simple(struct flow_block_offload *f, struct list_head *driver_block_list, - tc_setup_cb_t *cb, void *cb_ident, void *cb_priv, + flow_setup_cb_t *cb, + void *cb_ident, void *cb_priv, bool ingress_only) { struct flow_block_cb *block_cb; @@ -261,8 +260,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, cb_ident, - cb_priv, NULL); + block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -270,7 +268,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f, list_add_tail(&block_cb->driver_list, driver_block_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, cb_ident); + block_cb = flow_block_cb_lookup(f->block, cb, cb_ident); if (!block_cb) return -ENOENT; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 614c38ece104..33f41178afcc 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -951,7 +951,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, struct flow_block_offload *f) { struct flow_block_cb *block_cb; - tc_setup_cb_t *cb; + flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) cb = dsa_slave_setup_tc_block_cb_ig; @@ -967,7 +967,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list)) return -EBUSY; - block_cb = flow_block_cb_alloc(f->net, cb, dev, dev, NULL); + block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); if (IS_ERR(block_cb)) return PTR_ERR(block_cb); @@ -975,7 +975,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: - block_cb = flow_block_cb_lookup(f, cb, dev); + block_cb = flow_block_cb_lookup(f->block, cb, dev); if (!block_cb) return -ENOENT; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 4d6bf7ac0792..6bdb1ab8af61 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -416,8 +416,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) ctinfo == IP_CT_RELATED_REPLY)) return XT_CONTINUE; - /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, - * TIMESTAMP, INFO_REQUEST or ADDRESS type icmp packets from here + /* nf_conntrack_proto_icmp guarantees us that we only have ICMP_ECHO, + * TIMESTAMP, INFO_REQUEST or ICMP_ADDRESS type icmp packets from here * on, which all have an ID field [relevant for hashing]. */ hash = clusterip_hashfn(skb, cipinfo->config); diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 8e7f84ec783d..0e70f3f65f6f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -36,6 +36,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; + opts.mss_encode = opts.mss; + opts.mss = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 59031670b16a..cc23f1ce239c 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -78,6 +78,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; flow.flowi4_tos = RT_TOS(iph->tos); flow.flowi4_scope = RT_SCOPE_UNIVERSE; + flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par)); return rpfilter_lookup_reverse(xt_net(par), &flow, xt_in(par), info->flags) ^ invert; } diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 87b711fd5a44..3e2685c120c7 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -221,11 +221,11 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, int ret; rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - ret = nf_ct_expect_related(rtp_exp); + ret = nf_ct_expect_related(rtp_exp, 0); if (ret == 0) { rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); - ret = nf_ct_expect_related(rtcp_exp); + ret = nf_ct_expect_related(rtcp_exp, 0); if (ret == 0) break; else if (ret == -EBUSY) { @@ -296,7 +296,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -352,7 +352,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -444,7 +444,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { @@ -537,7 +537,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, int ret; exp->tuple.dst.u.tcp.port = htons(nated_port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 4af1f5dae9d3..6e4afc48d7bb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1288,6 +1288,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; + long limit; int nlen; u8 flags; @@ -1298,8 +1299,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, if (nsize < 0) nsize = 0; - if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf && - tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) { + /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. + * We need some allowance to not penalize applications setting small + * SO_SNDBUF values. + * Also allow first and last skb in retransmit queue to be split. + */ + limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE); + if (unlikely((sk->sk_wmem_queued >> 1) > limit && + tcp_queue != TCP_FRAG_IN_WRITE_QUEUE && + skb != tcp_rtx_queue_head(sk) && + skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index e77ea1ed5edd..5cdb4a69d277 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -36,6 +36,8 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; + opts.mss_encode = opts.mss; + opts.mss = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 6bcaf7357183..d800801a5dd2 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -55,7 +55,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, if (rpfilter_addr_linklocal(&iph->saddr)) { lookup_flags |= RT6_LOOKUP_F_IFACE; fl6.flowi6_oif = dev->ifindex; - } else if ((flags & XT_RPFILTER_LOOSE) == 0) + /* Set flowi6_oif for vrf devices to lookup route in l3mdev domain. */ + } else if (netif_is_l3_master(dev) || netif_is_l3_slave(dev) || + (flags & XT_RPFILTER_LOOSE) == 0) fl6.flowi6_oif = dev->ifindex; rt = (void *)ip6_route_lookup(net, &fl6, skb, lookup_flags); @@ -70,7 +72,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, goto out; } - if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE)) + if (rt->rt6i_idev->dev == dev || + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex || + (flags & XT_RPFILTER_LOOSE)) ret = true; out: ip6_rt_put(rt); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 76cc9e967fa6..4d458067d80d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -936,8 +936,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, err = ieee80211_set_probe_resp(sdata, params->probe_resp, params->probe_resp_len, csa); - if (err < 0) + if (err < 0) { + kfree(new); return err; + } if (err == 0) changed |= BSS_CHANGED_AP_PROBE_RESP; @@ -949,8 +951,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, params->civicloc, params->civicloc_len); - if (err < 0) + if (err < 0) { + kfree(new); return err; + } changed |= BSS_CHANGED_FTM_RESPONDER; } diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index acd4afb4944b..c9a8a2433e8a 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -187,11 +187,16 @@ int drv_conf_tx(struct ieee80211_local *local, if (!check_sdata_in_driver(sdata)) return -EIO; - if (WARN_ONCE(params->cw_min == 0 || - params->cw_min > params->cw_max, - "%s: invalid CW_min/CW_max: %d/%d\n", - sdata->name, params->cw_min, params->cw_max)) + if (params->cw_min == 0 || params->cw_min > params->cw_max) { + /* + * If we can't configure hardware anyway, don't warn. We may + * never have initialized the CW parameters. + */ + WARN_ONCE(local->ops->conf_tx, + "%s: invalid CW_min/CW_max: %d/%d\n", + sdata->name, params->cw_min, params->cw_max); return -EINVAL; + } trace_drv_conf_tx(local, sdata, ac, params); if (local->ops->conf_tx) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 32a45c03786e..0d65f4d39494 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -223,8 +223,6 @@ config NF_CONNTRACK_FTP of Network Address Translation on them. This is FTP support on Layer 3 independent connection tracking. - Layer 3 independent connection tracking is experimental scheme - which generalize ip_conntrack to support other layer 3 protocols. To compile it as a module, choose M here. If unsure, say N. @@ -338,7 +336,7 @@ config NF_CONNTRACK_SIP help SIP is an application-layer control protocol that can establish, modify, and terminate multimedia sessions (conferences) such as - Internet telephony calls. With the ip_conntrack_sip and + Internet telephony calls. With the nf_conntrack_sip and the nf_nat_sip modules you can support the protocol on a connection tracking/NATing firewall. @@ -1313,7 +1311,7 @@ config NETFILTER_XT_MATCH_HELPER depends on NETFILTER_ADVANCED help Helper matching allows you to match packets in dynamic connections - tracked by a conntrack-helper, ie. ip_conntrack_ftp + tracked by a conntrack-helper, ie. nf_conntrack_ftp To compile it as a module, choose M here. If unsure, say Y. diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 403541996952..08adcb222986 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -231,7 +231,7 @@ void ip_vs_nfct_expect_related(struct sk_buff *skb, struct nf_conn *ct, IP_VS_DBG_BUF(7, "%s: ct=%p, expect tuple=" FMT_TUPLE "\n", __func__, ct, ARG_TUPLE(&exp->tuple)); - nf_ct_expect_related(exp); + nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); } EXPORT_SYMBOL(ip_vs_nfct_expect_related); diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 42ee659d0d1e..d011d2eb0848 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -159,7 +159,7 @@ static int amanda_help(struct sk_buff *skb, if (nf_nat_amanda && ct->status & IPS_NAT_MASK) ret = nf_nat_amanda(skb, ctinfo, protoff, off - dataoff, len, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c index 921a7b95be68..1ba6becc3079 100644 --- a/net/netfilter/nf_conntrack_broadcast.c +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -68,7 +68,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb, exp->class = NF_CT_EXPECT_CLASS_DEFAULT; exp->helper = NULL; - nf_ct_expect_related(exp); + nf_ct_expect_related(exp, 0); nf_ct_expect_put(exp); nf_ct_refresh(ct, skb, timeout * HZ); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index bdfeacee0817..a542761e90d1 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1817,9 +1817,7 @@ EXPORT_SYMBOL_GPL(nf_ct_kill_acct); #include <linux/netfilter/nfnetlink_conntrack.h> #include <linux/mutex.h> -/* Generic function for tcp/udp/sctp/dccp and alike. This needs to be - * in ip_conntrack_core, since we don't want the protocols to autoload - * or depend on ctnetlink */ +/* Generic function for tcp/udp/sctp/dccp and alike. */ int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple) { diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index ffd1f4906c4f..65364de915d1 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -249,13 +249,22 @@ static inline int expect_clash(const struct nf_conntrack_expect *a, static inline int expect_matches(const struct nf_conntrack_expect *a, const struct nf_conntrack_expect *b) { - return a->master == b->master && - nf_ct_tuple_equal(&a->tuple, &b->tuple) && + return nf_ct_tuple_equal(&a->tuple, &b->tuple) && nf_ct_tuple_mask_equal(&a->mask, &b->mask) && net_eq(nf_ct_net(a->master), nf_ct_net(b->master)) && nf_ct_zone_equal_any(a->master, nf_ct_zone(b->master)); } +static bool master_matches(const struct nf_conntrack_expect *a, + const struct nf_conntrack_expect *b, + unsigned int flags) +{ + if (flags & NF_CT_EXP_F_SKIP_MASTER) + return true; + + return a->master == b->master; +} + /* Generally a bad idea to call this: could have matched already. */ void nf_ct_unexpect_related(struct nf_conntrack_expect *exp) { @@ -399,7 +408,8 @@ static void evict_oldest_expect(struct nf_conn *master, nf_ct_remove_expect(last); } -static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) +static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect, + unsigned int flags) { const struct nf_conntrack_expect_policy *p; struct nf_conntrack_expect *i; @@ -417,8 +427,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } h = nf_ct_expect_dst_hash(net, &expect->tuple); hlist_for_each_entry_safe(i, next, &nf_ct_expect_hash[h], hnode) { - if (expect_matches(i, expect)) { - if (i->class != expect->class) + if (master_matches(i, expect, flags) && + expect_matches(i, expect)) { + if (i->class != expect->class || + i->master != expect->master) return -EALREADY; if (nf_ct_remove_expect(i)) @@ -453,12 +465,12 @@ out: } int nf_ct_expect_related_report(struct nf_conntrack_expect *expect, - u32 portid, int report) + u32 portid, int report, unsigned int flags) { int ret; spin_lock_bh(&nf_conntrack_expect_lock); - ret = __nf_ct_expect_check(expect); + ret = __nf_ct_expect_check(expect, flags); if (ret < 0) goto out; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 8c6c11bab5b6..0ecb3e289ef2 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -525,7 +525,7 @@ skip_nl_seq: protoff, matchoff, matchlen, exp); else { /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } else diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index 8f6ba8162f0b..573cb4481481 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -1,11 +1,10 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ip_conntrack_helper_h323_asn1.c - BER and PER decoding library for H.323 - * conntrack/NAT module. + * BER and PER decoding library for H.323 conntrack/NAT module. * * Copyright (c) 2006 by Jing Min Zhao <zhaojingmin@users.sourceforge.net> * - * See ip_conntrack_helper_h323_asn1.h for details. + * See nf_conntrack_helper_h323_asn1.h for details. */ #ifdef __KERNEL__ diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 6497e5fc0871..8ba037b76ad3 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -305,8 +305,8 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, ret = nat_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, rtp_port, rtp_exp, rtcp_exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(rtp_exp) == 0) { - if (nf_ct_expect_related(rtcp_exp) == 0) { + if (nf_ct_expect_related(rtp_exp, 0) == 0) { + if (nf_ct_expect_related(rtcp_exp, 0) == 0) { pr_debug("nf_ct_h323: expect RTP "); nf_ct_dump_tuple(&rtp_exp->tuple); pr_debug("nf_ct_h323: expect RTCP "); @@ -364,7 +364,7 @@ static int expect_t120(struct sk_buff *skb, ret = nat_t120(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_h323: expect T.120 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -701,7 +701,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, ret = nat_h245(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_q931: expect H.245 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -825,7 +825,7 @@ static int expect_callforwarding(struct sk_buff *skb, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_q931: expect Call Forwarding "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1284,7 +1284,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, ret = nat_q931(skb, ct, ctinfo, protoff, data, taddr, i, port, exp); } else { /* Conntrack only */ - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); @@ -1349,7 +1349,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, IPPROTO_UDP, NULL, &port); exp->helper = nf_conntrack_helper_ras; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect RAS "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1561,7 +1561,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, exp->flags = NF_CT_EXPECT_PERMANENT; exp->helper = nf_conntrack_helper_q931; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); } else @@ -1615,7 +1615,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, exp->flags = NF_CT_EXPECT_PERMANENT; exp->helper = nf_conntrack_helper_q931; - if (nf_ct_expect_related(exp) == 0) { + if (nf_ct_expect_related(exp, 0) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); nf_ct_dump_tuple(&exp->tuple); } else diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 7ac156f1f3bc..e40988a2f22f 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -213,7 +213,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, addr_beg_p - ib_ptr, addr_end_p - addr_beg_p, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1b77444d5b52..6aa01eb6fe99 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2616,7 +2616,7 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, if (IS_ERR(exp)) return PTR_ERR(exp); - err = nf_ct_expect_related_report(exp, portid, report); + err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); return err; } @@ -3367,7 +3367,7 @@ ctnetlink_create_expect(struct net *net, goto err_rcu; } - err = nf_ct_expect_related_report(exp, portid, report); + err = nf_ct_expect_related_report(exp, portid, report, 0); nf_ct_expect_put(exp); err_rcu: rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index b22042ad0fca..a971183f11af 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -234,9 +234,9 @@ static int exp_gre(struct nf_conn *ct, __be16 callid, __be16 peer_callid) nf_nat_pptp_exp_gre = rcu_dereference(nf_nat_pptp_hook_exp_gre); if (nf_nat_pptp_exp_gre && ct->status & IPS_NAT_MASK) nf_nat_pptp_exp_gre(exp_orig, exp_reply); - if (nf_ct_expect_related(exp_orig) != 0) + if (nf_ct_expect_related(exp_orig, 0) != 0) goto out_put_both; - if (nf_ct_expect_related(exp_reply) != 0) + if (nf_ct_expect_related(exp_reply, 0) != 0) goto out_unexpect_orig; /* Add GRE keymap entries */ diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index c2eb365f1723..5b05487a60d2 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * ip_conntrack_proto_gre.c - Version 3.0 - * * Connection tracking protocol helper module for GRE. * * GRE is a generic encapsulation protocol, which is generally not very diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index dd53e2b20f6b..097deba7441a 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -215,7 +215,7 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl, return -NF_ACCEPT; } - /* See ip_conntrack_proto_tcp.c */ + /* See nf_conntrack_proto_tcp.c */ if (state->net->ct.sysctl_checksum && state->hook == NF_INET_PRE_ROUTING && nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d5fdfa00d683..85c1f8c213b0 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -472,6 +472,7 @@ static bool tcp_in_window(const struct nf_conn *ct, struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; __u32 seq, ack, sack, end, win, swin; + u16 win_raw; s32 receiver_offset; bool res, in_recv_win; @@ -480,7 +481,8 @@ static bool tcp_in_window(const struct nf_conn *ct, */ seq = ntohl(tcph->seq); ack = sack = ntohl(tcph->ack_seq); - win = ntohs(tcph->window); + win_raw = ntohs(tcph->window); + win = win_raw; end = segment_seq_plus_len(seq, skb->len, dataoff, tcph); if (receiver->flags & IP_CT_TCP_FLAG_SACK_PERM) @@ -655,14 +657,14 @@ static bool tcp_in_window(const struct nf_conn *ct, && state->last_seq == seq && state->last_ack == ack && state->last_end == end - && state->last_win == win) + && state->last_win == win_raw) state->retrans++; else { state->last_dir = dir; state->last_seq = seq; state->last_ack = ack; state->last_end = end; - state->last_win = win; + state->last_win = win_raw; state->retrans = 0; } } diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index 81448c3db661..1aebd6569d4e 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -153,7 +153,7 @@ static int help(struct sk_buff *skb, nf_ct_dump_tuple(&exp->tuple); /* Can't expect this? Best to drop packet now. */ - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 107251731809..b83dc9bf0a5d 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -977,11 +977,15 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, /* -EALREADY handling works around end-points that send * SDP messages with identical port but different media type, * we pretend expectation was set up. + * It also works in the case that SDP messages are sent with + * identical expect tuples but for different master conntracks. */ - int errp = nf_ct_expect_related(rtp_exp); + int errp = nf_ct_expect_related(rtp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (errp == 0 || errp == -EALREADY) { - int errcp = nf_ct_expect_related(rtcp_exp); + int errcp = nf_ct_expect_related(rtcp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (errcp == 0 || errcp == -EALREADY) ret = NF_ACCEPT; @@ -1296,7 +1300,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, ret = hooks->expect(skb, protoff, dataoff, dptr, datalen, exp, matchoff, matchlen); else { - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } else diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index df6d6d61bd58..80ee53f29f68 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -78,7 +78,7 @@ static int tftp_help(struct sk_buff *skb, nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook); if (nf_nat_tftp && ct->status & IPS_NAT_MASK) ret = nf_nat_tftp(skb, ctinfo, exp); - else if (nf_ct_expect_related(exp) != 0) { + else if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, ct, "cannot add expectation"); ret = NF_DROP; } diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c index a352604d6186..3bc7e0854efe 100644 --- a/net/netfilter/nf_nat_amanda.c +++ b/net/netfilter/nf_nat_amanda.c @@ -48,7 +48,7 @@ static unsigned int help(struct sk_buff *skb, int res; exp->tuple.dst.u.tcp.port = htons(port); - res = nf_ct_expect_related(exp); + res = nf_ct_expect_related(exp, 0); if (res == 0) break; else if (res != -EBUSY) { diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 9ab410455992..3f6023ed4966 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -519,7 +519,7 @@ another_round: * and NF_INET_LOCAL_OUT, we change the destination to map into the * range. It might not be possible to get a unique tuple, but we try. * At worst (or if we race), we will end up with a final duplicate in - * __ip_conntrack_confirm and drop the packet. */ + * __nf_conntrack_confirm and drop the packet. */ static void get_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig_tuple, diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c index d48484a9d52d..aace6768a64e 100644 --- a/net/netfilter/nf_nat_ftp.c +++ b/net/netfilter/nf_nat_ftp.c @@ -91,7 +91,7 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, int ret; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c index dfb7ef8845bd..c691ab8d234c 100644 --- a/net/netfilter/nf_nat_irc.c +++ b/net/netfilter/nf_nat_irc.c @@ -53,7 +53,7 @@ static unsigned int help(struct sk_buff *skb, int ret; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, 0); if (ret == 0) break; else if (ret != -EBUSY) { diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index e338d91980d8..f0a735e86851 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -414,7 +414,7 @@ static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, int ret; exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(exp); + ret = nf_ct_expect_related(exp, NF_CT_EXP_F_SKIP_MASTER); if (ret == 0) break; else if (ret != -EBUSY) { @@ -607,7 +607,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, int ret; rtp_exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(rtp_exp); + ret = nf_ct_expect_related(rtp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (ret == -EBUSY) continue; else if (ret < 0) { @@ -615,7 +616,8 @@ static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, break; } rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); - ret = nf_ct_expect_related(rtcp_exp); + ret = nf_ct_expect_related(rtcp_exp, + NF_CT_EXP_F_SKIP_MASTER); if (ret == 0) break; else if (ret == -EBUSY) { diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c index 833a11f68031..1a591132d6eb 100644 --- a/net/netfilter/nf_nat_tftp.c +++ b/net/netfilter/nf_nat_tftp.c @@ -30,7 +30,7 @@ static unsigned int help(struct sk_buff *skb, = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; exp->dir = IP_CT_DIR_REPLY; exp->expectfn = nf_nat_follow_master; - if (nf_ct_expect_related(exp) != 0) { + if (nf_ct_expect_related(exp, 0) != 0) { nf_ct_helper_log(skb, exp->master, "cannot add expectation"); return NF_DROP; } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index b101f187eda8..c769462a839e 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -470,7 +470,7 @@ synproxy_send_client_synack(struct net *net, struct iphdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; - u16 mss = opts->mss; + u16 mss = opts->mss_encode; iph = ip_hdr(skb); @@ -687,7 +687,7 @@ ipv4_synproxy_hook(void *priv, struct sk_buff *skb, state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: - if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; @@ -884,7 +884,7 @@ synproxy_send_client_synack_ipv6(struct net *net, struct ipv6hdr *iph, *niph; struct tcphdr *nth; unsigned int tcp_hdr_size; - u16 mss = opts->mss; + u16 mss = opts->mss_encode; iph = ipv6_hdr(skb); @@ -1111,7 +1111,7 @@ ipv6_synproxy_hook(void *priv, struct sk_buff *skb, state = &ct->proto.tcp; switch (state->state) { case TCP_CONNTRACK_CLOSE: - if (th->rst && !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) { + if (th->rst && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { nf_ct_seqadj_init(ct, ctinfo, synproxy->isn - ntohl(th->seq) + 1); break; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ed17a7c29b86..605a7cfe7ca7 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1662,7 +1662,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, chain->flags |= NFT_BASE_CHAIN | flags; basechain->policy = NF_ACCEPT; - INIT_LIST_HEAD(&basechain->cb_list); + flow_block_init(&basechain->flow_block); } else { chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (chain == NULL) @@ -1900,6 +1900,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, if (nla[NFTA_CHAIN_FLAGS]) flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS])); + else if (chain) + flags = chain->flags; nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 2c3302845f67..64f5fd5f240e 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -116,7 +116,7 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain, struct flow_block_cb *block_cb; int err; - list_for_each_entry(block_cb, &basechain->cb_list, list) { + list_for_each_entry(block_cb, &basechain->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err < 0) return err; @@ -154,7 +154,7 @@ static int nft_flow_offload_rule(struct nft_trans *trans, static int nft_flow_offload_bind(struct flow_block_offload *bo, struct nft_base_chain *basechain) { - list_splice(&bo->cb_list, &basechain->cb_list); + list_splice(&bo->cb_list, &basechain->flow_block.cb_list); return 0; } @@ -198,6 +198,7 @@ static int nft_flow_offload_chain(struct nft_trans *trans, return -EOPNOTSUPP; bo.command = cmd; + bo.block = &basechain->flow_block; bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; bo.extack = &extack; INIT_LIST_HEAD(&bo.cb_list); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 92077d459109..4abbb452cf6c 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -578,7 +578,7 @@ static int nfnetlink_bind(struct net *net, int group) ss = nfnetlink_get_subsys(type << 8); rcu_read_unlock(); if (!ss) - request_module("nfnetlink-subsys-%d", type); + request_module_nowait("nfnetlink-subsys-%d", type); return 0; } #endif diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 3fd540b2c6ba..b5d5d071d765 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -193,7 +193,7 @@ static inline void nft_chain_filter_inet_init(void) {} static inline void nft_chain_filter_inet_fini(void) {} #endif /* CONFIG_NF_TABLES_IPV6 */ -#ifdef CONFIG_NF_TABLES_BRIDGE +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) static unsigned int nft_do_chain_bridge(void *priv, struct sk_buff *skb, diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index 2f89bde3c61c..ff9ac8ae0031 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -142,3 +142,6 @@ MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat"); #ifdef CONFIG_NF_TABLES_IPV6 MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat"); #endif +#ifdef CONFIG_NF_TABLES_INET +MODULE_ALIAS_NFT_CHAIN(1, "nat"); /* NFPROTO_INET */ +#endif diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 827ab6196df9..46ca8bcca1bd 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -1252,7 +1252,7 @@ static void nft_ct_expect_obj_eval(struct nft_object *obj, priv->l4proto, NULL, &priv->dport); exp->timeout.expires = jiffies + priv->timeout * HZ; - if (nf_ct_expect_related(exp) != 0) + if (nf_ct_expect_related(exp, 0) != 0) regs->verdict.code = NF_DROP; } diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index fe93e731dc7f..b836d550b919 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -129,7 +129,7 @@ static int nft_symhash_init(const struct nft_ctx *ctx, priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); - if (priv->modulus <= 1) + if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 76866f77e343..f1b1d948c07b 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -546,7 +546,7 @@ nft_meta_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) return ERR_PTR(-EINVAL); -#ifdef CONFIG_NF_TABLES_BRIDGE +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META) if (ctx->family == NFPROTO_BRIDGE) return ERR_PTR(-EAGAIN); #endif diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c index 8487eeff5c0e..43eeb1f609f1 100644 --- a/net/netfilter/nft_redir.c +++ b/net/netfilter/nft_redir.c @@ -291,4 +291,4 @@ module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); -MODULE_ALIAS_NFT_EXPR("nat"); +MODULE_ALIAS_NFT_EXPR("redir"); diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 80060ade8a5b..928e661d1517 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -31,6 +31,8 @@ static void nft_synproxy_tcp_options(struct synproxy_options *opts, opts->options |= NF_SYNPROXY_OPT_ECN; opts->options &= priv->info.options; + opts->mss_encode = opts->mss; + opts->mss = info->mss; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, opts); else diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index dca3b1e2acf0..bc89e16e0505 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -59,7 +59,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies) void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, const struct sk_buff *skb) { - struct flow_stats *stats; + struct sw_flow_stats *stats; unsigned int cpu = smp_processor_id(); int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); @@ -87,7 +87,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags, if (likely(flow->stats_last_writer != -1) && likely(!rcu_access_pointer(flow->stats[cpu]))) { /* Try to allocate CPU-specific stats. */ - struct flow_stats *new_stats; + struct sw_flow_stats *new_stats; new_stats = kmem_cache_alloc_node(flow_stats_cache, @@ -134,7 +134,7 @@ void ovs_flow_stats_get(const struct sw_flow *flow, /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { - struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); + struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]); if (stats) { /* Local CPU may write on non-local stats, so we must @@ -158,7 +158,7 @@ void ovs_flow_stats_clear(struct sw_flow *flow) /* We open code this to make sure cpu 0 is always considered */ for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) { - struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]); + struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]); if (stats) { spin_lock_bh(&stats->lock); diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index 3e2cc2202d66..a5506e2d4b7a 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -194,7 +194,7 @@ struct sw_flow_actions { struct nlattr actions[]; }; -struct flow_stats { +struct sw_flow_stats { u64 packet_count; /* Number of packets matched. */ u64 byte_count; /* Number of bytes matched. */ unsigned long used; /* Last used time (in jiffies). */ @@ -216,7 +216,7 @@ struct sw_flow { struct cpumask cpu_used_mask; struct sw_flow_mask *mask; struct sw_flow_actions __rcu *sf_acts; - struct flow_stats __rcu *stats[]; /* One for each CPU. First one + struct sw_flow_stats __rcu *stats[]; /* One for each CPU. First one * is allocated at flow creation time, * the rest are allocated on demand * while holding the 'stats[0].lock'. diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 988fd8a94e43..cf3582c5ed70 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -66,7 +66,7 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src, struct sw_flow *ovs_flow_alloc(void) { struct sw_flow *flow; - struct flow_stats *stats; + struct sw_flow_stats *stats; flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL); if (!flow) @@ -110,7 +110,7 @@ static void flow_free(struct sw_flow *flow) for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) if (flow->stats[cpu]) kmem_cache_free(flow_stats_cache, - (struct flow_stats __force *)flow->stats[cpu]); + (struct sw_flow_stats __force *)flow->stats[cpu]); kmem_cache_free(flow_cache, flow); } @@ -712,13 +712,13 @@ int ovs_flow_init(void) flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow) + (nr_cpu_ids - * sizeof(struct flow_stats *)), + * sizeof(struct sw_flow_stats *)), 0, 0, NULL); if (flow_cache == NULL) return -ENOMEM; flow_stats_cache - = kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats), + = kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats), 0, SLAB_HWCACHE_ALIGN, NULL); if (flow_stats_cache == NULL) { kmem_cache_destroy(flow_cache); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index d144233423c5..efd3cfb80a2a 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -691,6 +691,8 @@ static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev, if (!indr_dev->block) return; + bo.block = &indr_dev->block->flow_block; + indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, &bo); tcf_block_setup(indr_dev->block, &bo); @@ -775,6 +777,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev, .command = command, .binder_type = ei->binder_type, .net = dev_net(dev), + .block = &block->flow_block, .block_shared = tcf_block_shared(block), .extack = extack, }; @@ -810,6 +813,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block, bo.net = dev_net(dev); bo.command = command; bo.binder_type = ei->binder_type; + bo.block = &block->flow_block; bo.block_shared = tcf_block_shared(block); bo.extack = extack; INIT_LIST_HEAD(&bo.cb_list); @@ -987,8 +991,8 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + flow_block_init(&block->flow_block); INIT_LIST_HEAD(&block->chain_list); - INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); INIT_LIST_HEAD(&block->chain0.filter_chain_list); @@ -1514,7 +1518,7 @@ void tcf_block_put(struct tcf_block *block) EXPORT_SYMBOL(tcf_block_put); static int -tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, +tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, void *cb_priv, bool add, bool offload_in_use, struct netlink_ext_ack *extack) { @@ -1570,7 +1574,7 @@ static int tcf_block_bind(struct tcf_block *block, i++; } - list_splice(&bo->cb_list, &block->cb_list); + list_splice(&bo->cb_list, &block->flow_block.cb_list); return 0; @@ -2152,7 +2156,9 @@ replay: tfilter_notify(net, skb, n, tp, block, q, parent, fh, RTM_NEWTFILTER, false, rtnl_held); tfilter_put(tp, fh); - q->flags &= ~TCQ_F_CAN_BYPASS; + /* q pointer is NULL for shared blocks */ + if (q) + q->flags &= ~TCQ_F_CAN_BYPASS; } errout: @@ -3156,7 +3162,7 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, if (block->nooffloaddevcnt && err_stop) return -EOPNOTSUPP; - list_for_each_entry(block_cb, &block->cb_list, list) { + list_for_each_entry(block_cb, &block->flow_block.cb_list, list) { err = block_cb->cb(type, type_data, block_cb->cb_priv); if (err) { if (err_stop) diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 691f71830134..3f7a9c02b70c 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -651,7 +651,7 @@ skip: } } -static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 38d6e85693fc..054123742e32 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1800,7 +1800,7 @@ fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add) return NULL; } -static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tcf_block *block = tp->chain->block; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index a30d2f8feb32..455ea2793f9b 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -282,7 +282,7 @@ skip: arg->count++; } -static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index be9e46c77e8b..8614088edd1b 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1152,7 +1152,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, } static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, - bool add, tc_setup_cb_t *cb, void *cb_priv, + bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_cls_u32_offload cls_u32 = {}; @@ -1172,7 +1172,7 @@ static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, } static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, - bool add, tc_setup_cb_t *cb, void *cb_priv, + bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); @@ -1213,7 +1213,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n, return 0; } -static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, +static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index f345662890a6..ca8ac96d22a9 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -476,7 +476,7 @@ static void tipc_topsrv_accept(struct work_struct *work) } } -/* tipc_toprsv_listener_data_ready - interrupt callback with connection request +/* tipc_topsrv_listener_data_ready - interrupt callback with connection request * The queued job is launched into tipc_topsrv_accept() */ static void tipc_topsrv_listener_data_ready(struct sock *sk) diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index 8a20e03d4cb7..9c60337317c6 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -78,10 +78,10 @@ set -e function _modprobe() { - modprobe "$@" + modprobe "$@" || return 1 if [[ "$REMOTE_HOST" != "" ]]; then - ssh "$REMOTE_HOST" modprobe "$@" + ssh "$REMOTE_HOST" modprobe "$@" || return 1 fi } @@ -442,6 +442,30 @@ function pingpong_test() echo " Passed" } +function msi_test() +{ + LOC=$1 + REM=$2 + + write_file 1 $LOC/ready + + echo "Running MSI interrupt tests on: $(subdirname $LOC) / $(subdirname $REM)" + + CNT=$(read_file "$LOC/count") + for ((i = 0; i < $CNT; i++)); do + START=$(read_file $REM/../irq${i}_occurrences) + write_file $i $LOC/trigger + END=$(read_file $REM/../irq${i}_occurrences) + + if [[ $(($END - $START)) != 1 ]]; then + echo "MSI did not trigger the interrupt on the remote side!" >&2 + exit 1 + fi + done + + echo " Passed" +} + function perf_test() { USE_DMA=$1 @@ -520,6 +544,29 @@ function ntb_pingpong_tests() _modprobe -r ntb_pingpong } +function ntb_msi_tests() +{ + LOCAL_MSI="$DEBUGFS/ntb_msi_test/$LOCAL_DEV" + REMOTE_MSI="$REMOTE_HOST:$DEBUGFS/ntb_msi_test/$REMOTE_DEV" + + echo "Starting ntb_msi_test tests..." + + if ! _modprobe ntb_msi_test 2> /dev/null; then + echo " Not doing MSI tests seeing the module is not available." + return + fi + + port_test $LOCAL_MSI $REMOTE_MSI + + LOCAL_PEER="$LOCAL_MSI/peer$LOCAL_PIDX" + REMOTE_PEER="$REMOTE_MSI/peer$REMOTE_PIDX" + + msi_test $LOCAL_PEER $REMOTE_PEER + msi_test $REMOTE_PEER $LOCAL_PEER + + _modprobe -r ntb_msi_test +} + function ntb_perf_tests() { LOCAL_PERF="$DEBUGFS/ntb_perf/$LOCAL_DEV" @@ -541,6 +588,7 @@ function cleanup() _modprobe -r ntb_perf 2> /dev/null _modprobe -r ntb_pingpong 2> /dev/null _modprobe -r ntb_transport 2> /dev/null + _modprobe -r ntb_msi_test 2> /dev/null set -e } @@ -577,5 +625,7 @@ ntb_tool_tests echo ntb_pingpong_tests echo +ntb_msi_tests +echo ntb_perf_tests echo |