diff options
471 files changed, 4861 insertions, 2678 deletions
@@ -159,6 +159,7 @@ Peter Oruba <[email protected]> Peter Oruba <[email protected]> Pratyush Anand <[email protected]> <[email protected]> Praveen BP <[email protected]> +Punit Agrawal <[email protected]> <[email protected]> Qais Yousef <[email protected]> <[email protected]> Oleksij Rempel <[email protected]> <[email protected]> Oleksij Rempel <[email protected]> <[email protected]> diff --git a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern index fb3d1e03b881..1e5d172e0646 100644 --- a/Documentation/ABI/testing/sysfs-class-led-trigger-pattern +++ b/Documentation/ABI/testing/sysfs-class-led-trigger-pattern @@ -37,8 +37,8 @@ Description: 0-| / \/ \/ +---0----1----2----3----4----5----6------------> time (s) - 2. To make the LED go instantly from one brigntess value to another, - we should use use zero-time lengths (the brightness must be same as + 2. To make the LED go instantly from one brightness value to another, + we should use zero-time lengths (the brightness must be same as the previous tuple's). So the format should be: "brightness_1 duration_1 brightness_1 0 brightness_2 duration_2 brightness_2 0 ...". For example: diff --git a/Documentation/devicetree/bindings/arm/shmobile.txt b/Documentation/devicetree/bindings/arm/shmobile.txt index f5e0f82fd503..58c4256d37a3 100644 --- a/Documentation/devicetree/bindings/arm/shmobile.txt +++ b/Documentation/devicetree/bindings/arm/shmobile.txt @@ -27,7 +27,7 @@ SoCs: compatible = "renesas,r8a77470" - RZ/G2M (R8A774A1) compatible = "renesas,r8a774a1" - - RZ/G2E (RA8774C0) + - RZ/G2E (R8A774C0) compatible = "renesas,r8a774c0" - R-Car M1A (R8A77781) compatible = "renesas,r8a7778" diff --git a/Documentation/devicetree/bindings/i2c/i2c-omap.txt b/Documentation/devicetree/bindings/i2c/i2c-omap.txt index 7e49839d4124..4b90ba9f31b7 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-omap.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-omap.txt @@ -1,8 +1,12 @@ I2C for OMAP platforms Required properties : -- compatible : Must be "ti,omap2420-i2c", "ti,omap2430-i2c", "ti,omap3-i2c" - or "ti,omap4-i2c" +- compatible : Must be + "ti,omap2420-i2c" for OMAP2420 SoCs + "ti,omap2430-i2c" for OMAP2430 SoCs + "ti,omap3-i2c" for OMAP3 SoCs + "ti,omap4-i2c" for OMAP4+ SoCs + "ti,am654-i2c", "ti,omap4-i2c" for AM654 SoCs - ti,hwmods : Must be "i2c<n>", n being the instance number (1-based) - #address-cells = <1>; - #size-cells = <0>; diff --git a/Documentation/i2c/busses/i2c-nvidia-gpu b/Documentation/i2c/busses/i2c-nvidia-gpu new file mode 100644 index 000000000000..31884d2b2eb5 --- /dev/null +++ b/Documentation/i2c/busses/i2c-nvidia-gpu @@ -0,0 +1,18 @@ +Kernel driver i2c-nvidia-gpu + +Datasheet: not publicly available. + +Authors: + Ajay Gupta <[email protected]> + +Description +----------- + +i2c-nvidia-gpu is a driver for I2C controller included in NVIDIA Turing +and later GPUs and it is used to communicate with Type-C controller on GPUs. + +If your 'lspci -v' listing shows something like the following, + +01:00.3 Serial bus controller [0c80]: NVIDIA Corporation Device 1ad9 (rev a1) + +then this driver should support the I2C controller of your GPU. diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index 73aaaa3da436..804f9426ed17 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt @@ -34,23 +34,24 @@ __________________|____________|__________________|_________|___________________ ____________________________________________________________|___________________________________________________________ | | | | ffff800000000000 | -128 TB | ffff87ffffffffff | 8 TB | ... guard hole, also reserved for hypervisor - ffff880000000000 | -120 TB | ffffc7ffffffffff | 64 TB | direct mapping of all physical memory (page_offset_base) - ffffc80000000000 | -56 TB | ffffc8ffffffffff | 1 TB | ... unused hole + ffff880000000000 | -120 TB | ffff887fffffffff | 0.5 TB | LDT remap for PTI + ffff888000000000 | -119.5 TB | ffffc87fffffffff | 64 TB | direct mapping of all physical memory (page_offset_base) + ffffc88000000000 | -55.5 TB | ffffc8ffffffffff | 0.5 TB | ... unused hole ffffc90000000000 | -55 TB | ffffe8ffffffffff | 32 TB | vmalloc/ioremap space (vmalloc_base) ffffe90000000000 | -23 TB | ffffe9ffffffffff | 1 TB | ... unused hole ffffea0000000000 | -22 TB | ffffeaffffffffff | 1 TB | virtual memory map (vmemmap_base) ffffeb0000000000 | -21 TB | ffffebffffffffff | 1 TB | ... unused hole ffffec0000000000 | -20 TB | fffffbffffffffff | 16 TB | KASAN shadow memory - fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole - | | | | vaddr_end for KASLR - fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping - fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | LDT remap for PTI - ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks __________________|____________|__________________|_________|____________________________________________________________ | - | Identical layout to the 47-bit one from here on: + | Identical layout to the 56-bit one from here on: ____________________________________________________________|____________________________________________________________ | | | | + fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole + | | | | vaddr_end for KASLR + fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping + fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole + ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks ffffff8000000000 | -512 GB | ffffffeeffffffff | 444 GB | ... unused hole ffffffef00000000 | -68 GB | fffffffeffffffff | 64 GB | EFI region mapping space ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | ... unused hole @@ -83,7 +84,7 @@ Notes: __________________|____________|__________________|_________|___________________________________________________________ | | | | 0000800000000000 | +64 PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical - | | | | virtual memory addresses up to the -128 TB + | | | | virtual memory addresses up to the -64 PB | | | | starting offset of kernel mappings. __________________|____________|__________________|_________|___________________________________________________________ | @@ -91,23 +92,24 @@ __________________|____________|__________________|_________|___________________ ____________________________________________________________|___________________________________________________________ | | | | ff00000000000000 | -64 PB | ff0fffffffffffff | 4 PB | ... guard hole, also reserved for hypervisor - ff10000000000000 | -60 PB | ff8fffffffffffff | 32 PB | direct mapping of all physical memory (page_offset_base) - ff90000000000000 | -28 PB | ff9fffffffffffff | 4 PB | LDT remap for PTI + ff10000000000000 | -60 PB | ff10ffffffffffff | 0.25 PB | LDT remap for PTI + ff11000000000000 | -59.75 PB | ff90ffffffffffff | 32 PB | direct mapping of all physical memory (page_offset_base) + ff91000000000000 | -27.75 PB | ff9fffffffffffff | 3.75 PB | ... unused hole ffa0000000000000 | -24 PB | ffd1ffffffffffff | 12.5 PB | vmalloc/ioremap space (vmalloc_base) ffd2000000000000 | -11.5 PB | ffd3ffffffffffff | 0.5 PB | ... unused hole ffd4000000000000 | -11 PB | ffd5ffffffffffff | 0.5 PB | virtual memory map (vmemmap_base) ffd6000000000000 | -10.5 PB | ffdeffffffffffff | 2.25 PB | ... unused hole ffdf000000000000 | -8.25 PB | fffffdffffffffff | ~8 PB | KASAN shadow memory - fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole - | | | | vaddr_end for KASLR - fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping - fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole - ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks __________________|____________|__________________|_________|____________________________________________________________ | | Identical layout to the 47-bit one from here on: ____________________________________________________________|____________________________________________________________ | | | | + fffffc0000000000 | -4 TB | fffffdffffffffff | 2 TB | ... unused hole + | | | | vaddr_end for KASLR + fffffe0000000000 | -2 TB | fffffe7fffffffff | 0.5 TB | cpu_entry_area mapping + fffffe8000000000 | -1.5 TB | fffffeffffffffff | 0.5 TB | ... unused hole + ffffff0000000000 | -1 TB | ffffff7fffffffff | 0.5 TB | %esp fixup stacks ffffff8000000000 | -512 GB | ffffffeeffffffff | 444 GB | ... unused hole ffffffef00000000 | -68 GB | fffffffeffffffff | 64 GB | EFI region mapping space ffffffff00000000 | -4 GB | ffffffff7fffffff | 2 GB | ... unused hole diff --git a/Documentation/x86/zero-page.txt b/Documentation/x86/zero-page.txt index 97b7adbceda4..68aed077f7b6 100644 --- a/Documentation/x86/zero-page.txt +++ b/Documentation/x86/zero-page.txt @@ -25,7 +25,7 @@ Offset Proto Name Meaning 0C8/004 ALL ext_cmd_line_ptr cmd_line_ptr high 32bits 140/080 ALL edid_info Video mode setup (struct edid_info) 1C0/020 ALL efi_info EFI 32 information (struct efi_info) -1E0/004 ALL alk_mem_k Alternative mem check, in KB +1E0/004 ALL alt_mem_k Alternative mem check, in KB 1E4/004 ALL scratch Scratch field for the kernel setup code 1E8/001 ALL e820_entries Number of entries in e820_table (below) 1E9/001 ALL eddbuf_entries Number of entries in eddbuf (below) diff --git a/MAINTAINERS b/MAINTAINERS index f4855974f325..0abecc528dac 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6607,9 +6607,9 @@ F: arch/*/include/asm/suspend*.h HID CORE LAYER M: Jiri Kosina <[email protected]> -R: Benjamin Tissoires <[email protected]> +M: Benjamin Tissoires <[email protected]> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git S: Maintained F: drivers/hid/ F: include/linux/hid* @@ -6861,6 +6861,13 @@ L: [email protected] S: Maintained F: drivers/i2c/i2c-core-acpi.c +I2C CONTROLLER DRIVER FOR NVIDIA GPU +M: Ajay Gupta <[email protected]> +S: Maintained +F: Documentation/i2c/busses/i2c-nvidia-gpu +F: drivers/i2c/busses/i2c-nvidia-gpu.c + I2C MUXES M: Peter Rosin <[email protected]> @@ -8367,7 +8374,7 @@ F: drivers/media/dvb-frontends/lgdt3305.* LIBATA PATA ARASAN COMPACT FLASH CONTROLLER M: Viresh Kumar <[email protected]> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: include/linux/pata_arasan_cf_data.h F: drivers/ata/pata_arasan_cf.c @@ -8384,7 +8391,7 @@ F: drivers/ata/ata_generic.c LIBATA PATA FARADAY FTIDE010 AND GEMINI SATA BRIDGE DRIVERS M: Linus Walleij <[email protected]> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/pata_ftide010.c F: drivers/ata/sata_gemini.c @@ -8403,7 +8410,7 @@ F: include/linux/ahci_platform.h LIBATA SATA PROMISE TX2/TX4 CONTROLLER DRIVER M: Mikael Pettersson <[email protected]> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/sata_promise.* @@ -10784,6 +10791,14 @@ L: [email protected] S: Maintained F: arch/arm/mach-omap2/omap_hwmod.* +OMAP I2C DRIVER +M: Vignesh R <[email protected]> +S: Maintained +F: Documentation/devicetree/bindings/i2c/i2c-omap.txt +F: drivers/i2c/busses/i2c-omap.c + OMAP IMAGING SUBSYSTEM (OMAP3 ISP and OMAP4 ISS) M: Laurent Pinchart <[email protected]> @@ -15436,9 +15451,9 @@ F: include/linux/usb/gadget* USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...) M: Jiri Kosina <[email protected]> -R: Benjamin Tissoires <[email protected]> +M: Benjamin Tissoires <[email protected]> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git S: Maintained F: Documentation/hid/hiddev.txt F: drivers/hid/usbhid/ @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 20 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = "People's Front" # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/termios.h b/arch/alpha/include/asm/termios.h index 6a8c53dec57e..b7c77bb1bfd2 100644 --- a/arch/alpha/include/asm/termios.h +++ b/arch/alpha/include/asm/termios.h @@ -73,9 +73,15 @@ }) #define user_termios_to_kernel_termios(k, u) \ - copy_from_user(k, u, sizeof(struct termios)) + copy_from_user(k, u, sizeof(struct termios2)) #define kernel_termios_to_user_termios(u, k) \ + copy_to_user(u, k, sizeof(struct termios2)) + +#define user_termios_to_kernel_termios_1(k, u) \ + copy_from_user(k, u, sizeof(struct termios)) + +#define kernel_termios_to_user_termios_1(u, k) \ copy_to_user(u, k, sizeof(struct termios)) #endif /* _ALPHA_TERMIOS_H */ diff --git a/arch/alpha/include/uapi/asm/ioctls.h b/arch/alpha/include/uapi/asm/ioctls.h index 1e9121c9b3c7..971311605288 100644 --- a/arch/alpha/include/uapi/asm/ioctls.h +++ b/arch/alpha/include/uapi/asm/ioctls.h @@ -32,6 +32,11 @@ #define TCXONC _IO('t', 30) #define TCFLSH _IO('t', 31) +#define TCGETS2 _IOR('T', 42, struct termios2) +#define TCSETS2 _IOW('T', 43, struct termios2) +#define TCSETSW2 _IOW('T', 44, struct termios2) +#define TCSETSF2 _IOW('T', 45, struct termios2) + #define TIOCSWINSZ _IOW('t', 103, struct winsize) #define TIOCGWINSZ _IOR('t', 104, struct winsize) #define TIOCSTART _IO('t', 110) /* start output, like ^Q */ diff --git a/arch/alpha/include/uapi/asm/termbits.h b/arch/alpha/include/uapi/asm/termbits.h index de6c8360fbe3..4575ba34a0ea 100644 --- a/arch/alpha/include/uapi/asm/termbits.h +++ b/arch/alpha/include/uapi/asm/termbits.h @@ -26,6 +26,19 @@ struct termios { speed_t c_ospeed; /* output speed */ }; +/* Alpha has identical termios and termios2 */ + +struct termios2 { + tcflag_t c_iflag; /* input mode flags */ + tcflag_t c_oflag; /* output mode flags */ + tcflag_t c_cflag; /* control mode flags */ + tcflag_t c_lflag; /* local mode flags */ + cc_t c_cc[NCCS]; /* control characters */ + cc_t c_line; /* line discipline (== c_cc[19]) */ + speed_t c_ispeed; /* input speed */ + speed_t c_ospeed; /* output speed */ +}; + /* Alpha has matching termios and ktermios */ struct ktermios { @@ -152,6 +165,7 @@ struct ktermios { #define B3000000 00034 #define B3500000 00035 #define B4000000 00036 +#define BOTHER 00037 #define CSIZE 00001400 #define CS5 00000000 @@ -169,6 +183,9 @@ struct ktermios { #define CMSPAR 010000000000 /* mark or space (stick) parity */ #define CRTSCTS 020000000000 /* flow control */ +#define CIBAUD 07600000 +#define IBSHIFT 16 + /* c_lflag bits */ #define ISIG 0x00000080 #define ICANON 0x00000100 diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index b560ff88459b..5ff9a179c83c 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -55,7 +55,7 @@ }; chosen { - stdout-path = "&uart1:115200n8"; + stdout-path = "serial0:115200n8"; }; memory@70000000 { diff --git a/arch/arm/boot/dts/imx6sll.dtsi b/arch/arm/boot/dts/imx6sll.dtsi index ed9a980bce85..beefa1b2049d 100644 --- a/arch/arm/boot/dts/imx6sll.dtsi +++ b/arch/arm/boot/dts/imx6sll.dtsi @@ -740,7 +740,7 @@ i2c1: i2c@21a0000 { #address-cells = <1>; #size-cells = <0>; - compatible = "fs,imx6sll-i2c", "fsl,imx21-i2c"; + compatible = "fsl,imx6sll-i2c", "fsl,imx21-i2c"; reg = <0x021a0000 0x4000>; interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SLL_CLK_I2C1>; diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi index 53b3408b5fab..7d7d679945d2 100644 --- a/arch/arm/boot/dts/imx6sx-sdb.dtsi +++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi @@ -117,7 +117,9 @@ regulator-name = "enet_3v3"; regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpios = <&gpio2 6 GPIO_ACTIVE_LOW>; + gpio = <&gpio2 6 GPIO_ACTIVE_LOW>; + regulator-boot-on; + regulator-always-on; }; reg_pcie_gpio: regulator-pcie-gpio { @@ -180,6 +182,7 @@ phy-supply = <®_enet_3v3>; phy-mode = "rgmii"; phy-handle = <ðphy1>; + phy-reset-gpios = <&gpio2 7 GPIO_ACTIVE_LOW>; status = "okay"; mdio { @@ -373,6 +376,8 @@ MX6SX_PAD_RGMII1_RD3__ENET1_RX_DATA_3 0x3081 MX6SX_PAD_RGMII1_RX_CTL__ENET1_RX_EN 0x3081 MX6SX_PAD_ENET2_RX_CLK__ENET2_REF_CLK_25M 0x91 + /* phy reset */ + MX6SX_PAD_ENET2_CRS__GPIO2_IO_7 0x10b0 >; }; diff --git a/arch/arm/boot/dts/vf610m4-colibri.dts b/arch/arm/boot/dts/vf610m4-colibri.dts index 41ec66a96990..ca6249558760 100644 --- a/arch/arm/boot/dts/vf610m4-colibri.dts +++ b/arch/arm/boot/dts/vf610m4-colibri.dts @@ -50,8 +50,8 @@ compatible = "fsl,vf610m4"; chosen { - bootargs = "console=ttyLP2,115200 clk_ignore_unused init=/linuxrc rw"; - stdout-path = "&uart2"; + bootargs = "clk_ignore_unused init=/linuxrc rw"; + stdout-path = "serial2:115200"; }; memory@8c000000 { diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index 1c7616815a86..63af6234c1b6 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -1,7 +1,6 @@ CONFIG_SYSVIPC=y CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y -CONFIG_PREEMPT=y CONFIG_CGROUPS=y CONFIG_BLK_DEV_INITRD=y CONFIG_EMBEDDED=y diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h index 92fd2c8a9af0..12659ce5c1f3 100644 --- a/arch/arm/include/asm/pgtable-2level.h +++ b/arch/arm/include/asm/pgtable-2level.h @@ -10,7 +10,7 @@ #ifndef _ASM_PGTABLE_2LEVEL_H #define _ASM_PGTABLE_2LEVEL_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Hardware-wise, we have a two level page table structure, where the first diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 6fe52819e014..339eb17c9808 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -112,7 +112,7 @@ ENTRY(cpu_v7_hvc_switch_mm) hvc #0 ldmfd sp!, {r0 - r3} b cpu_v7_switch_mm -ENDPROC(cpu_v7_smc_switch_mm) +ENDPROC(cpu_v7_hvc_switch_mm) #endif ENTRY(cpu_v7_iciallu_switch_mm) mov r3, #0 diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi index 8253a1a9e985..fef7351e9f67 100644 --- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi +++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi @@ -139,6 +139,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; @@ -154,6 +155,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; @@ -169,6 +171,7 @@ clock-names = "stmmaceth"; tx-fifo-depth = <16384>; rx-fifo-depth = <16384>; + snps,multicast-filter-bins = <256>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/renesas/r8a7795.dtsi b/arch/arm64/boot/dts/renesas/r8a7795.dtsi index b5f2273caca4..a79c8d369e0b 100644 --- a/arch/arm64/boot/dts/renesas/r8a7795.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7795.dtsi @@ -652,7 +652,7 @@ clock-names = "fck", "brg_int", "scif_clk"; dmas = <&dmac1 0x35>, <&dmac1 0x34>, <&dmac2 0x35>, <&dmac2 0x34>; - dma-names = "tx", "rx"; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7795_PD_ALWAYS_ON>; resets = <&cpg 518>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts index fe2e2c051cc9..5a7012be0d6a 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts +++ b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts @@ -15,7 +15,7 @@ aliases { serial0 = &scif0; - ethernet0 = &avb; + ethernet0 = &gether; }; chosen { @@ -97,23 +97,6 @@ }; }; -&avb { - pinctrl-0 = <&avb_pins>; - pinctrl-names = "default"; - - phy-mode = "rgmii-id"; - phy-handle = <&phy0>; - renesas,no-ether-link; - status = "okay"; - - phy0: ethernet-phy@0 { - rxc-skew-ps = <1500>; - reg = <0>; - interrupt-parent = <&gpio1>; - interrupts = <17 IRQ_TYPE_LEVEL_LOW>; - }; -}; - &canfd { pinctrl-0 = <&canfd0_pins>; pinctrl-names = "default"; @@ -139,6 +122,23 @@ clock-frequency = <32768>; }; +&gether { + pinctrl-0 = <&gether_pins>; + pinctrl-names = "default"; + + phy-mode = "rgmii-id"; + phy-handle = <&phy0>; + renesas,no-ether-link; + status = "okay"; + + phy0: ethernet-phy@0 { + rxc-skew-ps = <1500>; + reg = <0>; + interrupt-parent = <&gpio4>; + interrupts = <23 IRQ_TYPE_LEVEL_LOW>; + }; +}; + &i2c0 { pinctrl-0 = <&i2c0_pins>; pinctrl-names = "default"; @@ -236,16 +236,17 @@ }; &pfc { - avb_pins: avb { - groups = "avb_mdio", "avb_rgmii"; - function = "avb"; - }; - canfd0_pins: canfd0 { groups = "canfd0_data_a"; function = "canfd0"; }; + gether_pins: gether { + groups = "gether_mdio_a", "gether_rgmii", + "gether_txcrefclk", "gether_txcrefclk_mega"; + function = "gether"; + }; + i2c0_pins: i2c0 { groups = "i2c0"; function = "i2c0"; diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 3e2091708b8e..6b0d4dff5012 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -24,6 +24,14 @@ #define KERNEL_DS UL(-1) #define USER_DS (TASK_SIZE_64 - 1) +/* + * On arm64 systems, unaligned accesses by the CPU are cheap, and so there is + * no point in shifting all network buffers by 2 bytes just to make some IP + * header fields appear aligned in memory, potentially sacrificing some DMA + * performance on some platforms. + */ +#define NET_IP_ALIGN 0 + #ifndef __ASSEMBLY__ #ifdef __KERNEL__ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 9d9582cac6c4..9b432d9fcada 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -483,8 +483,6 @@ void __init arm64_memblock_init(void) high_memory = __va(memblock_end_of_DRAM() - 1) + 1; dma_contiguous_reserve(arm64_dma_phys_limit); - - memblock_allow_resize(); } void __init bootmem_init(void) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 394b8d554def..d1d6601b385d 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -659,6 +659,8 @@ void __init paging_init(void) memblock_free(__pa_symbol(init_pg_dir), __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + + memblock_allow_resize(); } /* diff --git a/arch/m68k/include/asm/pgtable_mm.h b/arch/m68k/include/asm/pgtable_mm.h index 6181e4134483..fe3ddd73a0cc 100644 --- a/arch/m68k/include/asm/pgtable_mm.h +++ b/arch/m68k/include/asm/pgtable_mm.h @@ -55,12 +55,12 @@ */ #ifdef CONFIG_SUN3 #define PTRS_PER_PTE 16 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 2048 #elif defined(CONFIG_COLDFIRE) #define PTRS_PER_PTE 512 -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define PTRS_PER_PMD 1 #define PTRS_PER_PGD 1024 #else diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h index f64ebb9c9a41..e14b6621c933 100644 --- a/arch/microblaze/include/asm/pgtable.h +++ b/arch/microblaze/include/asm/pgtable.h @@ -63,7 +63,7 @@ extern int mem_init_done; #include <asm-generic/4level-fixup.h> -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #ifdef __KERNEL__ #ifndef __ASSEMBLY__ diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper.c b/arch/mips/cavium-octeon/executive/cvmx-helper.c index 75108ec669eb..6c79e8a16a26 100644 --- a/arch/mips/cavium-octeon/executive/cvmx-helper.c +++ b/arch/mips/cavium-octeon/executive/cvmx-helper.c @@ -67,7 +67,7 @@ void (*cvmx_override_pko_queue_priority) (int pko_port, void (*cvmx_override_ipd_port_setup) (int ipd_port); /* Port count per interface */ -static int interface_port_count[5]; +static int interface_port_count[9]; /** * Return the number of interfaces the chip has. Each interface diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c index e6c9485cadcf..cb38461391cb 100644 --- a/arch/mips/mm/dma-noncoherent.c +++ b/arch/mips/mm/dma-noncoherent.c @@ -50,7 +50,7 @@ void *arch_dma_alloc(struct device *dev, size_t size, void *ret; ret = dma_direct_alloc_pages(dev, size, dma_handle, gfp, attrs); - if (!ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { + if (ret && !(attrs & DMA_ATTR_NON_CONSISTENT)) { dma_cache_wback_inv((unsigned long) ret, size); ret = (void *)UNCAC_ADDR(ret); } diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h index d3e19a55cf53..9f52db930c00 100644 --- a/arch/nds32/include/asm/pgtable.h +++ b/arch/nds32/include/asm/pgtable.h @@ -4,7 +4,7 @@ #ifndef _ASMNDS32_PGTABLE_H #define _ASMNDS32_PGTABLE_H -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #include <asm-generic/4level-fixup.h> #include <asm-generic/sizes.h> diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h index b941ac7d4e70..c7bb74e22436 100644 --- a/arch/parisc/include/asm/pgtable.h +++ b/arch/parisc/include/asm/pgtable.h @@ -111,7 +111,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr) #if CONFIG_PGTABLE_LEVELS == 3 #define BITS_PER_PMD (PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY) #else -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 #define BITS_PER_PMD 0 #endif #define PTRS_PER_PMD (1UL << BITS_PER_PMD) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 8be31261aec8..8ea7c2c02cbf 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -556,7 +556,7 @@ config RELOCATABLE_TEST config CRASH_DUMP bool "Build a dump capture kernel" - depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP) + depends on PPC64 || PPC_BOOK3S_32 || FSL_BOOKE || (44x && !SMP) select RELOCATABLE if PPC64 || 44x || FSL_BOOKE help Build a kernel suitable for use as a dump capture kernel. @@ -1096,7 +1096,7 @@ config PHYSICAL_START_BOOL config PHYSICAL_START hex "Physical address where the kernel is loaded" if PHYSICAL_START_BOOL - default "0x02000000" if PPC_STD_MMU && CRASH_DUMP && !NONSTATIC_KERNEL + default "0x02000000" if PPC_BOOK3S && CRASH_DUMP && !NONSTATIC_KERNEL default "0x00000000" config PHYSICAL_ALIGN diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 8a2ce14d68d0..40bbeeeb5b4a 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -241,7 +241,7 @@ KBUILD_CFLAGS += $(call cc-option,-fno-dwarf2-cfi-asm) # often slow when they are implemented at all KBUILD_CFLAGS += $(call cc-option,-mno-string) -ifdef CONFIG_6xx +ifdef CONFIG_PPC_BOOK3S_32 KBUILD_CFLAGS += -mcpu=powerpc endif @@ -317,6 +317,14 @@ PHONY += ppc64le_defconfig ppc64le_defconfig: $(call merge_into_defconfig,ppc64_defconfig,le) +PHONY += ppc64le_guest_defconfig +ppc64le_guest_defconfig: + $(call merge_into_defconfig,ppc64_defconfig,le guest) + +PHONY += ppc64_guest_defconfig +ppc64_guest_defconfig: + $(call merge_into_defconfig,ppc64_defconfig,be guest) + PHONY += powernv_be_defconfig powernv_be_defconfig: $(call merge_into_defconfig,powernv_defconfig,be) diff --git a/arch/powerpc/configs/guest.config b/arch/powerpc/configs/guest.config new file mode 100644 index 000000000000..8b8cd18ecd7c --- /dev/null +++ b/arch/powerpc/configs/guest.config @@ -0,0 +1,13 @@ +CONFIG_VIRTIO_BLK=y +CONFIG_VIRTIO_BLK_SCSI=y +CONFIG_SCSI_VIRTIO=y +CONFIG_VIRTIO_NET=y +CONFIG_NET_FAILOVER=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_VIRTIO=y +CONFIG_VIRTIO_PCI=y +CONFIG_KVM_GUEST=y +CONFIG_EPAPR_PARAVIRT=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VHOST_NET=y +CONFIG_VHOST=y diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig index f2515674a1e2..294a0b9d6038 100644 --- a/arch/powerpc/configs/ppc64_defconfig +++ b/arch/powerpc/configs/ppc64_defconfig @@ -1,4 +1,3 @@ -CONFIG_PPC64=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_NO_HZ=y @@ -9,21 +8,22 @@ CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=18 CONFIG_LOG_CPU_MAX_BUF_SHIFT=13 +CONFIG_NUMA_BALANCING=y CONFIG_CGROUPS=y +CONFIG_MEMCG=y +CONFIG_CGROUP_SCHED=y +CONFIG_CGROUP_FREEZER=y CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y CONFIG_CGROUP_BPF=y CONFIG_BLK_DEV_INITRD=y CONFIG_BPF_SYSCALL=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y -CONFIG_OPROFILE=m -CONFIG_KPROBES=y -CONFIG_JUMP_LABEL=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_MODVERSIONS=y -CONFIG_MODULE_SRCVERSION_ALL=y -CONFIG_PARTITION_ADVANCED=y +CONFIG_PPC64=y +CONFIG_NR_CPUS=2048 CONFIG_PPC_SPLPAR=y CONFIG_DTL=y CONFIG_SCANLOG=m @@ -45,14 +45,11 @@ CONFIG_CPU_FREQ_GOV_USERSPACE=y CONFIG_CPU_FREQ_GOV_CONSERVATIVE=y CONFIG_CPU_FREQ_PMAC64=y CONFIG_HZ_100=y -CONFIG_BINFMT_MISC=m CONFIG_PPC_TRANSACTIONAL_MEM=y CONFIG_KEXEC=y CONFIG_KEXEC_FILE=y CONFIG_CRASH_DUMP=y CONFIG_IRQ_ALL_CPUS=y -CONFIG_KSM=y -CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_PPC_64K_PAGES=y CONFIG_SCHED_SMT=y CONFIG_HOTPLUG_PCI=y @@ -60,6 +57,23 @@ CONFIG_HOTPLUG_PCI_RPA=m CONFIG_HOTPLUG_PCI_RPA_DLPAR=m CONFIG_PCCARD=y CONFIG_ELECTRA_CF=y +CONFIG_VIRTUALIZATION=y +CONFIG_KVM_BOOK3S_64=m +CONFIG_KVM_BOOK3S_64_HV=m +CONFIG_VHOST_NET=m +CONFIG_OPROFILE=m +CONFIG_KPROBES=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_MODVERSIONS=y +CONFIG_MODULE_SRCVERSION_ALL=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_BINFMT_MISC=m +CONFIG_MEMORY_HOTPLUG=y +CONFIG_MEMORY_HOTREMOVE=y +CONFIG_KSM=y +CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -163,7 +177,6 @@ CONFIG_TIGON3=y CONFIG_BNX2X=m CONFIG_CHELSIO_T1=m CONFIG_BE2NET=m -CONFIG_S2IO=m CONFIG_IBMVETH=m CONFIG_EHEA=m CONFIG_E100=y @@ -174,6 +187,7 @@ CONFIG_IXGBE=m CONFIG_I40E=m CONFIG_MLX4_EN=m CONFIG_MYRI10GE=m +CONFIG_S2IO=m CONFIG_PASEMI_MAC=y CONFIG_QLGE=m CONFIG_NETXEN_NIC=m @@ -284,7 +298,7 @@ CONFIG_REISERFS_FS_SECURITY=y CONFIG_JFS_FS=m CONFIG_JFS_POSIX_ACL=y CONFIG_JFS_SECURITY=y -CONFIG_XFS_FS=m +CONFIG_XFS_FS=y CONFIG_XFS_POSIX_ACL=y CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y @@ -323,25 +337,6 @@ CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ASCII=y CONFIG_NLS_ISO8859_1=y CONFIG_NLS_UTF8=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_KERNEL=y -CONFIG_DEBUG_STACK_USAGE=y -CONFIG_DEBUG_STACKOVERFLOW=y -CONFIG_SOFTLOCKUP_DETECTOR=y -CONFIG_HARDLOCKUP_DETECTOR=y -CONFIG_DEBUG_MUTEXES=y -CONFIG_LATENCYTOP=y -CONFIG_FTRACE=y -CONFIG_FUNCTION_TRACER=y -CONFIG_FUNCTION_GRAPH_TRACER=y -CONFIG_SCHED_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_CODE_PATCHING_SELFTEST=y -CONFIG_FTR_FIXUP_SELFTEST=y -CONFIG_MSI_BITMAP_SELFTEST=y -CONFIG_XMON=y -CONFIG_BOOTX_TEXT=y -CONFIG_PPC_EARLY_DEBUG=y CONFIG_CRYPTO_TEST=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_HMAC=y @@ -364,8 +359,21 @@ CONFIG_CRYPTO_LZO=m CONFIG_CRYPTO_DEV_NX=y CONFIG_CRYPTO_DEV_NX_ENCRYPT=m CONFIG_CRYPTO_DEV_VMX=y -CONFIG_VIRTUALIZATION=y -CONFIG_KVM_BOOK3S_64=m -CONFIG_KVM_BOOK3S_64_HV=m -CONFIG_VHOST_NET=m CONFIG_PRINTK_TIME=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_STACK_USAGE=y +CONFIG_DEBUG_STACKOVERFLOW=y +CONFIG_SOFTLOCKUP_DETECTOR=y +CONFIG_HARDLOCKUP_DETECTOR=y +CONFIG_DEBUG_MUTEXES=y +CONFIG_LATENCYTOP=y +CONFIG_FUNCTION_TRACER=y +CONFIG_SCHED_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_CODE_PATCHING_SELFTEST=y +CONFIG_FTR_FIXUP_SELFTEST=y +CONFIG_MSI_BITMAP_SELFTEST=y +CONFIG_XMON=y +CONFIG_BOOTX_TEXT=y +CONFIG_PPC_EARLY_DEBUG=y diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig index 5e09a40cbcbf..ea79c519863d 100644 --- a/arch/powerpc/configs/pseries_defconfig +++ b/arch/powerpc/configs/pseries_defconfig @@ -290,9 +290,7 @@ CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_SOFTLOCKUP_DETECTOR=y CONFIG_HARDLOCKUP_DETECTOR=y CONFIG_LATENCYTOP=y -CONFIG_FTRACE=y CONFIG_FUNCTION_TRACER=y -CONFIG_FUNCTION_GRAPH_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y CONFIG_CODE_PATCHING_SELFTEST=y diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h index ec691d489656..6f201b199c02 100644 --- a/arch/powerpc/include/asm/asm-prototypes.h +++ b/arch/powerpc/include/asm/asm-prototypes.h @@ -61,7 +61,6 @@ void RunModeException(struct pt_regs *regs); void single_step_exception(struct pt_regs *regs); void program_check_exception(struct pt_regs *regs); void alignment_exception(struct pt_regs *regs); -void slb_miss_bad_addr(struct pt_regs *regs); void StackOverflow(struct pt_regs *regs); void kernel_fp_unavailable_exception(struct pt_regs *regs); void altivec_unavailable_exception(struct pt_regs *regs); diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h index e38c91388c40..7cf4ae8aed9e 100644 --- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h +++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_ #define _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_ + /* * 32-bit hash table MMU support */ @@ -9,6 +10,8 @@ * BATs */ +#include <asm/page.h> + /* Block size masks */ #define BL_128K 0x000 #define BL_256K 0x001 @@ -34,14 +37,20 @@ #define BAT_PHYS_ADDR(x) ((u32)((x & 0x00000000fffe0000ULL) | \ ((x & 0x0000000e00000000ULL) >> 24) | \ ((x & 0x0000000100000000ULL) >> 30))) +#define PHYS_BAT_ADDR(x) (((u64)(x) & 0x00000000fffe0000ULL) | \ + (((u64)(x) << 24) & 0x0000000e00000000ULL) | \ + (((u64)(x) << 30) & 0x0000000100000000ULL)) #else #define BAT_PHYS_ADDR(x) (x) +#define PHYS_BAT_ADDR(x) ((x) & 0xfffe0000) #endif struct ppc_bat { u32 batu; u32 batl; }; + +typedef pte_t *pgtable_t; #endif /* !__ASSEMBLY__ */ /* diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h index 82e44b1a00ae..b5b955eb2fb7 100644 --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h @@ -25,10 +25,7 @@ extern void __bad_pte(pmd_t *pmd); extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] static inline pgd_t *pgd_alloc(struct mm_struct *mm) { @@ -50,8 +47,6 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd) #define __pmd_free_tlb(tlb,x,a) do { } while (0) /* #define pgd_populate(mm, pmd, pte) BUG() */ -#ifndef CONFIG_BOOKE - static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *pte) { @@ -61,46 +56,31 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pte_page) { - *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_PRESENT); -} - -#define pmd_pgtable(pmd) pmd_page(pmd) -#else - -static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, - pte_t *pte) -{ - *pmdp = __pmd((unsigned long)pte | _PMD_PRESENT); -} - -static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, - pgtable_t pte_page) -{ - *pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT); + *pmdp = __pmd(__pa(pte_page) | _PMD_PRESENT); } -#define pmd_pgtable(pmd) pmd_page(pmd) -#endif +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr); extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr); +void pte_frag_destroy(void *pte_frag); +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel); +void pte_fragment_free(unsigned long *table, int kernel); static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - free_page((unsigned long)pte); + pte_fragment_free((unsigned long *)pte, 1); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) { - pgtable_page_dtor(ptepage); - __free_page(ptepage); + pte_fragment_free((unsigned long *)ptepage, 0); } static inline void pgtable_free(void *table, unsigned index_size) { if (!index_size) { - pgtable_page_dtor(virt_to_page(table)); - free_page((unsigned long)table); + pte_fragment_free((unsigned long *)table, 0); } else { BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); kmem_cache_free(PGT_CACHE(index_size), table); @@ -138,6 +118,6 @@ static inline void pgtable_free_tlb(struct mmu_gather *tlb, static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { - pgtable_free_tlb(tlb, page_address(table), 0); + pgtable_free_tlb(tlb, table, 0); } #endif /* _ASM_POWERPC_BOOK3S_32_PGALLOC_H */ diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h index c21d33704633..727692fd6bca 100644 --- a/arch/powerpc/include/asm/book3s/32/pgtable.h +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h @@ -328,24 +328,10 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define __HAVE_ARCH_PTE_SAME #define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0) -/* - * Note that on Book E processors, the pmd contains the kernel virtual - * (lowmem) address of the pte page. The physical address is less useful - * because everything runs with translation enabled (even the TLB miss - * handler). On everything else the pmd contains the physical address - * of the pte page. -- paulus - */ -#ifndef CONFIG_BOOKE #define pmd_page_vaddr(pmd) \ - ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) + ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) #define pmd_page(pmd) \ pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) -#else -#define pmd_page_vaddr(pmd) \ - ((unsigned long) (pmd_val(pmd) & PAGE_MASK)) -#define pmd_page(pmd) \ - pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT)) -#endif /* to find an entry in a kernel page-table-directory */ #define pgd_offset_k(address) pgd_offset(&init_mm, address) @@ -360,7 +346,8 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define pte_offset_kernel(dir, addr) \ ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr)) #define pte_offset_map(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) + ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \ + (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr)) #define pte_unmap(pte) kunmap_atomic(pte) /* @@ -524,7 +511,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, int percpu) { -#if defined(CONFIG_PPC_STD_MMU_32) && defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) +#if defined(CONFIG_SMP) && !defined(CONFIG_PTE_64BIT) /* First case is 32-bit Hash MMU in SMP mode with 32-bit PTEs. We use the * helper pte_update() which does an atomic update. We need to do that * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a @@ -537,7 +524,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, else pte_update(ptep, ~_PAGE_HASHPTE, pte_val(pte)); -#elif defined(CONFIG_PPC32) && defined(CONFIG_PTE_64BIT) +#elif defined(CONFIG_PTE_64BIT) /* Second case is 32-bit with 64-bit PTE. In this case, we * can just store as long as we do the two halves in the right order * with a barrier in between. This is possible because we take care, @@ -560,7 +547,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, : "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) : "r" (pte) : "memory"); -#elif defined(CONFIG_PPC_STD_MMU_32) +#else /* Third case is 32-bit hash table in UP mode, we need to preserve * the _PAGE_HASHPTE bit since we may not have invalidated the previous * translation in the hash yet (done in a subsequent flush_tlb_xxx()) @@ -568,9 +555,6 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, */ *ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) | (pte_val(pte) & ~_PAGE_HASHPTE)); - -#else -#error "Not supported " #endif } diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index 6328857f259f..1ceee000c18d 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -2,6 +2,8 @@ #ifndef _ASM_POWERPC_BOOK3S_64_MMU_H_ #define _ASM_POWERPC_BOOK3S_64_MMU_H_ +#include <asm/page.h> + #ifndef __ASSEMBLY__ /* * Page size definition @@ -24,6 +26,13 @@ struct mmu_psize_def { }; extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT]; +/* + * For BOOK3s 64 with 4k and 64K linux page size + * we want to use pointers, because the page table + * actually store pfn + */ +typedef pte_t *pgtable_t; + #endif /* __ASSEMBLY__ */ /* 64-bit classic hash table MMU */ diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h index 391ed2c3b697..4aba625389c4 100644 --- a/arch/powerpc/include/asm/book3s/64/pgalloc.h +++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h @@ -37,10 +37,7 @@ extern struct vmemmap_backing *vmemmap_list; #define MAX_PGTABLE_INDEX_SIZE 0xf extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] extern pte_t *pte_fragment_alloc(struct mm_struct *, unsigned long, int); extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long); @@ -50,6 +47,7 @@ extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift); #ifdef CONFIG_SMP extern void __tlb_remove_table(void *_table); #endif +void pte_frag_destroy(void *pte_frag); static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 6c99e846a8c9..2e6ada28da64 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1304,7 +1304,7 @@ static inline int pgd_devmap(pgd_t pgd) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static inline const int pud_pfn(pud_t pud) +static inline int pud_pfn(pud_t pud) { /* * Currently all calls to pud_pfn() are gated around a pud_devmap() diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h index 66298461b640..40ea5b3781c6 100644 --- a/arch/powerpc/include/asm/cache.h +++ b/arch/powerpc/include/asm/cache.h @@ -71,7 +71,7 @@ extern struct ppc64_caches ppc64_caches; #else #define __read_mostly __attribute__((__section__(".data..read_mostly"))) -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 extern long _get_L2CR(void); extern long _get_L3CR(void); extern void _set_L2CR(unsigned long); diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 383da1ab9e23..62a0ca02ca7d 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -5,8 +5,6 @@ #ifdef CONFIG_HUGETLB_PAGE #include <asm/page.h> -extern struct kmem_cache *hugepte_cache; - #ifdef CONFIG_PPC_BOOK3S_64 #include <asm/book3s/64/hugetlb.h> @@ -76,7 +74,9 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr, unsigned long idx = 0; pte_t *dir = hugepd_page(hpd); -#ifndef CONFIG_PPC_FSL_BOOK3E +#ifdef CONFIG_PPC_8xx + idx = (addr & ((1UL << pdshift) - 1)) >> PAGE_SHIFT; +#elif !defined(CONFIG_PPC_FSL_BOOK3E) idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(hpd); #endif @@ -135,9 +135,9 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, } #define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS -extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty); +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty); static inline void arch_clear_hugepage_flags(struct page *page) { diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index eb20eb3b8fb0..9667921bf420 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -48,7 +48,7 @@ #define MMU_FTR_USE_HIGH_BATS ASM_CONST(0x00010000) /* Enable >32-bit physical addresses on 32-bit processor, only used - * by CONFIG_6xx currently as BookE supports that from day 1 + * by CONFIG_PPC_BOOK3S_32 currently as BookE supports that from day 1 */ #define MMU_FTR_BIG_PHYS ASM_CONST(0x00020000) @@ -338,21 +338,11 @@ static inline void mmu_early_init_devtree(void) { } #endif /* __ASSEMBLY__ */ #endif -#if defined(CONFIG_PPC_STD_MMU_32) +#if defined(CONFIG_PPC_BOOK3S_32) /* 32-bit classic hash table MMU */ #include <asm/book3s/32/mmu-hash.h> -#elif defined(CONFIG_40x) -/* 40x-style software loaded TLB */ -# include <asm/mmu-40x.h> -#elif defined(CONFIG_44x) -/* 44x-style software loaded TLB */ -# include <asm/mmu-44x.h> -#elif defined(CONFIG_PPC_BOOK3E_MMU) -/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ -# include <asm/mmu-book3e.h> -#elif defined (CONFIG_PPC_8xx) -/* Motorola/Freescale 8xx software loaded TLB */ -# include <asm/mmu-8xx.h> +#elif defined(CONFIG_PPC_MMU_NOHASH) +#include <asm/nohash/mmu.h> #endif #endif /* __KERNEL__ */ diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 0381394a425b..c05efd2e8736 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -223,7 +223,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, return 0; } -#ifndef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_BOOK3E_64 static inline void arch_exit_mmap(struct mm_struct *mm) { } diff --git a/arch/powerpc/include/asm/mmu-40x.h b/arch/powerpc/include/asm/nohash/32/mmu-40x.h index 74f4edb5916e..74f4edb5916e 100644 --- a/arch/powerpc/include/asm/mmu-40x.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-40x.h diff --git a/arch/powerpc/include/asm/mmu-44x.h b/arch/powerpc/include/asm/nohash/32/mmu-44x.h index 295b3dbb2698..295b3dbb2698 100644 --- a/arch/powerpc/include/asm/mmu-44x.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-44x.h diff --git a/arch/powerpc/include/asm/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h index fa05aa566ece..b0f764c827c0 100644 --- a/arch/powerpc/include/asm/mmu-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h @@ -190,6 +190,7 @@ typedef struct { struct slice_mask mask_8m; # endif #endif + void *pte_frag; } mm_context_t; #define PHYS_IMMR_BASE (mfspr(SPRN_IMMR) & 0xfff80000) @@ -244,6 +245,9 @@ extern s32 patch__itlbmiss_perf, patch__dtlbmiss_perf; #define mmu_virtual_psize MMU_PAGE_4K #elif defined(CONFIG_PPC_16K_PAGES) #define mmu_virtual_psize MMU_PAGE_16K +#define PTE_FRAG_NR 4 +#define PTE_FRAG_SIZE_SHIFT 12 +#define PTE_FRAG_SIZE (1UL << 12) #else #error "Unsupported PAGE_SIZE" #endif diff --git a/arch/powerpc/include/asm/nohash/32/mmu.h b/arch/powerpc/include/asm/nohash/32/mmu.h new file mode 100644 index 000000000000..7d94a36d57d2 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/32/mmu.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_32_MMU_H_ +#define _ASM_POWERPC_NOHASH_32_MMU_H_ + +#include <asm/page.h> + +#if defined(CONFIG_40x) +/* 40x-style software loaded TLB */ +#include <asm/nohash/32/mmu-40x.h> +#elif defined(CONFIG_44x) +/* 44x-style software loaded TLB */ +#include <asm/nohash/32/mmu-44x.h> +#elif defined(CONFIG_PPC_BOOK3E_MMU) +/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ +#include <asm/nohash/mmu-book3e.h> +#elif defined (CONFIG_PPC_8xx) +/* Motorola/Freescale 8xx software loaded TLB */ +#include <asm/nohash/32/mmu-8xx.h> +#endif + +#ifndef __ASSEMBLY__ +typedef pte_t *pgtable_t; +#endif + +#endif /* _ASM_POWERPC_NOHASH_32_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h index 8825953c225b..17963951bdb0 100644 --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h @@ -25,10 +25,7 @@ extern void __bad_pte(pmd_t *pmd); extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] static inline pgd_t *pgd_alloc(struct mm_struct *mm) { @@ -61,11 +58,10 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pte_page) { - *pmdp = __pmd((page_to_pfn(pte_page) << PAGE_SHIFT) | _PMD_USER | - _PMD_PRESENT); + *pmdp = __pmd(__pa(pte_page) | _PMD_USER | _PMD_PRESENT); } -#define pmd_pgtable(pmd) pmd_page(pmd) +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) #else static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, @@ -77,31 +73,32 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t pte_page) { - *pmdp = __pmd((unsigned long)lowmem_page_address(pte_page) | _PMD_PRESENT); + *pmdp = __pmd((unsigned long)pte_page | _PMD_PRESENT); } -#define pmd_pgtable(pmd) pmd_page(pmd) +#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd)) #endif extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr); extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr); +void pte_frag_destroy(void *pte_frag); +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel); +void pte_fragment_free(unsigned long *table, int kernel); static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte) { - free_page((unsigned long)pte); + pte_fragment_free((unsigned long *)pte, 1); } static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage) { - pgtable_page_dtor(ptepage); - __free_page(ptepage); + pte_fragment_free((unsigned long *)ptepage, 0); } static inline void pgtable_free(void *table, unsigned index_size) { if (!index_size) { - pgtable_page_dtor(virt_to_page(table)); - free_page((unsigned long)table); + pte_fragment_free((unsigned long *)table, 0); } else { BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE); kmem_cache_free(PGT_CACHE(index_size), table); @@ -140,6 +137,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table, unsigned long address) { tlb_flush_pgtable(tlb, address); - pgtable_free_tlb(tlb, page_address(table), 0); + pgtable_free_tlb(tlb, table, 0); } #endif /* _ASM_POWERPC_PGALLOC_32_H */ diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h index 3ffb0ff5a038..bed433358260 100644 --- a/arch/powerpc/include/asm/nohash/32/pgtable.h +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h @@ -232,7 +232,13 @@ static inline unsigned long pte_update(pte_t *p, : "cc" ); #else /* PTE_ATOMIC_UPDATES */ unsigned long old = pte_val(*p); - *p = __pte((old & ~clr) | set); + unsigned long new = (old & ~clr) | set; + +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) + p->pte = p->pte1 = p->pte2 = p->pte3 = new; +#else + *p = __pte(new); +#endif #endif /* !PTE_ATOMIC_UPDATES */ #ifdef CONFIG_44x @@ -333,12 +339,12 @@ static inline int pte_young(pte_t pte) */ #ifndef CONFIG_BOOKE #define pmd_page_vaddr(pmd) \ - ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK)) + ((unsigned long)__va(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) #define pmd_page(pmd) \ pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT) #else #define pmd_page_vaddr(pmd) \ - ((unsigned long) (pmd_val(pmd) & PAGE_MASK)) + ((unsigned long)(pmd_val(pmd) & ~(PTE_TABLE_SIZE - 1))) #define pmd_page(pmd) \ pfn_to_page((__pa(pmd_val(pmd)) >> PAGE_SHIFT)) #endif @@ -357,7 +363,8 @@ static inline int pte_young(pte_t pte) (pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \ pte_index(addr)) #define pte_offset_map(dir, addr) \ - ((pte_t *) kmap_atomic(pmd_page(*(dir))) + pte_index(addr)) + ((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \ + (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr)) #define pte_unmap(pte) kunmap_atomic(pte) /* diff --git a/arch/powerpc/include/asm/nohash/32/pte-40x.h b/arch/powerpc/include/asm/nohash/32/pte-40x.h index 661f4599f2fc..12c6811e344b 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-40x.h +++ b/arch/powerpc/include/asm/nohash/32/pte-40x.h @@ -33,7 +33,7 @@ * is cleared in the TLB miss handler before the TLB entry is loaded. * - All other bits of the PTE are loaded into TLBLO without * modification, leaving us only the bits 20, 21, 24, 25, 26, 30 for - * software PTE bits. We actually use use bits 21, 24, 25, and + * software PTE bits. We actually use bits 21, 24, 25, and * 30 respectively for the software bits: ACCESSED, DIRTY, RW, and * PRESENT. */ diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 6bfe041ef59d..c9e4b2d90f65 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -65,9 +65,6 @@ #define _PTE_NONE_MASK 0 -/* Until my rework is finished, 8xx still needs atomic PTE updates */ -#define PTE_ATOMIC_UPDATES 1 - #ifdef CONFIG_PPC_16K_PAGES #define _PAGE_PSIZE _PAGE_SPS #else diff --git a/arch/powerpc/include/asm/nohash/64/mmu.h b/arch/powerpc/include/asm/nohash/64/mmu.h new file mode 100644 index 000000000000..e6585480dfc4 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/64/mmu.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_64_MMU_H_ +#define _ASM_POWERPC_NOHASH_64_MMU_H_ + +/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */ +#include <asm/nohash/mmu-book3e.h> + +#ifndef __ASSEMBLY__ +typedef struct page *pgtable_t; +#endif + +#endif /* _ASM_POWERPC_NOHASH_64_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h index e2d62d033708..e95eb499a174 100644 --- a/arch/powerpc/include/asm/nohash/64/pgalloc.h +++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h @@ -36,10 +36,7 @@ extern struct vmemmap_backing *vmemmap_list; #define MAX_PGTABLE_INDEX_SIZE 0xf extern struct kmem_cache *pgtable_cache[]; -#define PGT_CACHE(shift) ({ \ - BUG_ON(!(shift)); \ - pgtable_cache[(shift) - 1]; \ - }) +#define PGT_CACHE(shift) pgtable_cache[shift] static inline pgd_t *pgd_alloc(struct mm_struct *mm) { diff --git a/arch/powerpc/include/asm/mmu-book3e.h b/arch/powerpc/include/asm/nohash/mmu-book3e.h index e20072972e35..e20072972e35 100644 --- a/arch/powerpc/include/asm/mmu-book3e.h +++ b/arch/powerpc/include/asm/nohash/mmu-book3e.h diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h new file mode 100644 index 000000000000..a037cb1efb57 --- /dev/null +++ b/arch/powerpc/include/asm/nohash/mmu.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_NOHASH_MMU_H_ +#define _ASM_POWERPC_NOHASH_MMU_H_ + +#ifdef CONFIG_PPC64 +#include <asm/nohash/64/mmu.h> +#else +#include <asm/nohash/32/mmu.h> +#endif + +#endif /* _ASM_POWERPC_NOHASH_MMU_H_ */ diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 70ff23974b59..1ca1c1864b32 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -209,7 +209,11 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, /* Anything else just stores the PTE normally. That covers all 64-bit * cases, and 32-bit non-hash with 32-bit PTEs. */ +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) + ptep->pte = ptep->pte1 = ptep->pte2 = ptep->pte3 = pte_val(pte); +#else *ptep = pte; +#endif /* * With hardware tablewalk, a sync is needed to ensure that diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index f6a1265face2..a7624a3b1435 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -289,7 +289,7 @@ static inline bool pfn_valid(unsigned long pfn) * page tables at arbitrary addresses, this breaks and will have to change. */ #ifdef CONFIG_PPC64 -#define PD_HUGE 0x8000000000000000 +#define PD_HUGE 0x8000000000000000UL #else #define PD_HUGE 0x80000000 #endif @@ -335,20 +335,6 @@ void arch_free_page(struct page *page, int order); #endif struct vm_area_struct; -#ifdef CONFIG_PPC_BOOK3S_64 -/* - * For BOOK3s 64 with 4k and 64K linux page size - * we want to use pointers, because the page table - * actually store pfn - */ -typedef pte_t *pgtable_t; -#else -#if defined(CONFIG_PPC_64K_PAGES) && defined(CONFIG_PPC64) -typedef pte_t *pgtable_t; -#else -typedef struct page *pgtable_t; -#endif -#endif #include <asm-generic/memory_model.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/powerpc/include/asm/page_32.h b/arch/powerpc/include/asm/page_32.h index 5c378e9b78c8..683dfbc67ca8 100644 --- a/arch/powerpc/include/asm/page_32.h +++ b/arch/powerpc/include/asm/page_32.h @@ -22,7 +22,8 @@ #define PTE_FLAGS_OFFSET 0 #endif -#ifdef CONFIG_PPC_256K_PAGES +#if defined(CONFIG_PPC_256K_PAGES) || \ + (defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES)) #define PTE_SHIFT (PAGE_SHIFT - PTE_T_LOG2 - 2) /* 1/4 of a page */ #else #define PTE_SHIFT (PAGE_SHIFT - PTE_T_LOG2) /* full page */ diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index eccb30b38b47..3b0edf041b2e 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -3,7 +3,11 @@ #define _ASM_POWERPC_PGTABLE_TYPES_H /* PTE level */ +#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PPC_16K_PAGES) +typedef struct { pte_basic_t pte, pte1, pte2, pte3; } pte_t; +#else typedef struct { pte_basic_t pte; } pte_t; +#endif #define __pte(x) ((pte_t) { (x) }) static inline pte_basic_t pte_val(pte_t x) { diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h index 9679b7519a35..f2bfaf674674 100644 --- a/arch/powerpc/include/asm/pgtable.h +++ b/arch/powerpc/include/asm/pgtable.h @@ -101,7 +101,7 @@ extern int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, /* can we use this in kvm */ unsigned long vmalloc_to_phys(void *vmalloc_addr); -void pgtable_cache_add(unsigned shift, void (*ctor)(void *)); +void pgtable_cache_add(unsigned int shift); void pgtable_cache_init(void); #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_PPC32) @@ -110,6 +110,35 @@ void mark_initmem_nx(void); static inline void mark_initmem_nx(void) { } #endif +/* + * When used, PTE_FRAG_NR is defined in subarch pgtable.h + * so we are sure it is included when arriving here. + */ +#ifdef PTE_FRAG_NR +static inline void *pte_frag_get(mm_context_t *ctx) +{ + return ctx->pte_frag; +} + +static inline void pte_frag_set(mm_context_t *ctx, void *p) +{ + ctx->pte_frag = p; +} +#else +#define PTE_FRAG_NR 1 +#define PTE_FRAG_SIZE_SHIFT PAGE_SHIFT +#define PTE_FRAG_SIZE (1UL << PTE_FRAG_SIZE_SHIFT) + +static inline void *pte_frag_get(mm_context_t *ctx) +{ + return NULL; +} + +static inline void pte_frag_set(mm_context_t *ctx, void *p) +{ +} +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_POWERPC_PGTABLE_H */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index de52c3166ba4..0d2139a0d5b9 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -582,7 +582,7 @@ #define HID0_POWER9_RADIX __MASK(63 - 8) #define SPRN_HID1 0x3F1 /* Hardware Implementation Register 1 */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 #define HID1_EMCP (1<<31) /* 7450 Machine Check Pin Enable */ #define HID1_DFS (1<<22) /* 7447A Dynamic Frequency Scaling */ #define HID1_PC0 (1<<16) /* 7450 PLL_CFG[0] */ diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h index d89beaba26ff..8b957aabb826 100644 --- a/arch/powerpc/include/asm/sfp-machine.h +++ b/arch/powerpc/include/asm/sfp-machine.h @@ -213,30 +213,18 @@ * respectively. The result is placed in HIGH_SUM and LOW_SUM. Overflow * (i.e. carry out) is not stored anywhere, and is lost. */ -#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ +#define add_ssaaaa(sh, sl, ah, al, bh, bl) \ do { \ if (__builtin_constant_p (bh) && (bh) == 0) \ - __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ - else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \ - __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ + __asm__ ("add%I4c %1,%3,%4\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("add%I4c %1,%3,%4\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "%r" (al), "rI" (bl));\ else \ - __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "%r" ((USItype)(ah)), \ - "r" ((USItype)(bh)), \ - "%r" ((USItype)(al)), \ - "rI" ((USItype)(bl))); \ + __asm__ ("add%I5c %1,%4,%5\n\tadde %0,%2,%3" \ + : "=r" (sh), "=&r" (sl) \ + : "%r" (ah), "r" (bh), "%r" (al), "rI" (bl)); \ } while (0) /* sub_ddmmss is used in op-2.h and udivmodti4.c and should be equivalent to @@ -248,44 +236,24 @@ * and LOW_DIFFERENCE. Overflow (i.e. carry out) is not stored anywhere, * and is lost. */ -#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ +#define sub_ddmmss(sh, sl, ah, al, bh, bl) \ do { \ if (__builtin_constant_p (ah) && (ah) == 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ - else if (__builtin_constant_p (ah) && (ah) ==~(USItype) 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (ah) && (ah) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\tsubfme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (bh), "rI" (al), "r" (bl));\ else if (__builtin_constant_p (bh) && (bh) == 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ - else if (__builtin_constant_p (bh) && (bh) ==~(USItype) 0) \ - __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I3c %1,%4,%3\n\taddme %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ + else if (__builtin_constant_p (bh) && (bh) == ~(USItype) 0) \ + __asm__ ("subf%I3c %1,%4,%3\n\taddze %0,%2" \ + : "=r" (sh), "=&r" (sl) : "r" (ah), "rI" (al), "r" (bl));\ else \ - __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2" \ - : "=r" ((USItype)(sh)), \ - "=&r" ((USItype)(sl)) \ - : "r" ((USItype)(ah)), \ - "r" ((USItype)(bh)), \ - "rI" ((USItype)(al)), \ - "r" ((USItype)(bl))); \ + __asm__ ("subf%I4c %1,%5,%4\n\tsubfe %0,%3,%2" \ + : "=r" (sh), "=&r" (sl) \ + : "r" (ah), "r" (bh), "rI" (al), "r" (bl)); \ } while (0) /* asm fragments for mul and div */ @@ -294,13 +262,10 @@ * UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype * word product in HIGH_PROD and LOW_PROD. */ -#define umul_ppmm(ph, pl, m0, m1) \ +#define umul_ppmm(ph, pl, m0, m1) \ do { \ USItype __m0 = (m0), __m1 = (m1); \ - __asm__ ("mulhwu %0,%1,%2" \ - : "=r" ((USItype)(ph)) \ - : "%r" (__m0), \ - "r" (__m1)); \ + __asm__ ("mulhwu %0,%1,%2" : "=r" (ph) : "%r" (m0), "r" (m1)); \ (pl) = __m0 * __m1; \ } while (0) @@ -312,9 +277,10 @@ * significant bit of DENOMINATOR must be 1, then the pre-processor symbol * UDIV_NEEDS_NORMALIZATION is defined to 1. */ -#define udiv_qrnnd(q, r, n1, n0, d) \ +#define udiv_qrnnd(q, r, n1, n0, d) \ do { \ - UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m; \ + UWtype __d1, __d0, __q1, __q0; \ + UWtype __r1, __r0, __m; \ __d1 = __ll_highpart (d); \ __d0 = __ll_lowpart (d); \ \ @@ -325,7 +291,7 @@ if (__r1 < __m) \ { \ __q1--, __r1 += (d); \ - if (__r1 >= (d)) /* we didn't get carry when adding to __r1 */ \ + if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */\ if (__r1 < __m) \ __q1--, __r1 += (d); \ } \ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index b80d492ceb29..54bf7e68a7e1 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -43,7 +43,7 @@ struct div_result { /* Accessor functions for the timebase (RTC on 601) registers. */ /* If one day CONFIG_POWER is added just define __USE_RTC as 1 */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 #define __USE_RTC() (cpu_has_feature(CPU_FTR_USE_RTC)) #else #define __USE_RTC() 0 diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h index f0e571b2dc7c..e24c67d5ba75 100644 --- a/arch/powerpc/include/asm/tlb.h +++ b/arch/powerpc/include/asm/tlb.h @@ -40,7 +40,7 @@ extern void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address) { -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 if (pte_val(*ptep) & _PAGE_HASHPTE) flush_hash_entry(tlb->mm, ptep, address); #endif diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 53d4b8d5b54d..a5a6a243f3cf 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -69,7 +69,7 @@ obj-$(CONFIG_FA_DUMP) += fadump.o ifdef CONFIG_PPC32 obj-$(CONFIG_E500) += idle_e500.o endif -obj-$(CONFIG_6xx) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o +obj-$(CONFIG_PPC_BOOK3S_32) += idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o obj-$(CONFIG_TAU) += tau_6xx.o obj-$(CONFIG_HIBERNATION) += swsusp.o suspend.o ifdef CONFIG_FSL_BOOKE diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c index b4241ed1456e..6dfceaa820e4 100644 --- a/arch/powerpc/kernel/btext.c +++ b/arch/powerpc/kernel/btext.c @@ -232,20 +232,12 @@ static int btext_initialize(struct device_node *np) int __init btext_find_display(int allow_nonstdout) { - const char *name; - struct device_node *np = NULL; + struct device_node *np = of_stdout; int rc = -ENODEV; - name = of_get_property(of_chosen, "linux,stdout-path", NULL); - if (name != NULL) { - np = of_find_node_by_path(name); - if (np != NULL) { - if (strcmp(np->type, "display") != 0) { - printk("boot stdout isn't a display !\n"); - of_node_put(np); - np = NULL; - } - } + if (!of_node_is_type(np, "display")) { + printk("boot stdout isn't a display !\n"); + np = NULL; } if (np) rc = btext_initialize(np); diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c index be57bd07596d..53102764fd2f 100644 --- a/arch/powerpc/kernel/cacheinfo.c +++ b/arch/powerpc/kernel/cacheinfo.c @@ -428,7 +428,7 @@ static void link_cache_lists(struct cache *smaller, struct cache *bigger) static void do_subsidiary_caches_debugcheck(struct cache *cache) { WARN_ON_ONCE(cache->level != 1); - WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu")); + WARN_ON_ONCE(!of_node_is_type(cache->ofnode, "cpu")); } static void do_subsidiary_caches(struct cache *cache) diff --git a/arch/powerpc/kernel/cpu_setup_6xx.S b/arch/powerpc/kernel/cpu_setup_6xx.S index fa3c2c91290c..8c069e96c478 100644 --- a/arch/powerpc/kernel/cpu_setup_6xx.S +++ b/arch/powerpc/kernel/cpu_setup_6xx.S @@ -326,7 +326,7 @@ _GLOBAL(__save_cpu_setup) lis r5,cpu_state_storage@h ori r5,r5,cpu_state_storage@l - /* Save HID0 (common to all CONFIG_6xx cpus) */ + /* Save HID0 (common to all CONFIG_PPC_BOOK3S_32 cpus) */ mfspr r3,SPRN_HID0 stw r3,CS_HID0(r5) diff --git a/arch/powerpc/kernel/cpu_setup_fsl_booke.S b/arch/powerpc/kernel/cpu_setup_fsl_booke.S index 8d142e5d84cd..5fbc890d1094 100644 --- a/arch/powerpc/kernel/cpu_setup_fsl_booke.S +++ b/arch/powerpc/kernel/cpu_setup_fsl_booke.S @@ -17,7 +17,7 @@ #include <asm/processor.h> #include <asm/cputable.h> #include <asm/ppc_asm.h> -#include <asm/mmu-book3e.h> +#include <asm/nohash/mmu-book3e.h> #include <asm/asm-offsets.h> #include <asm/mpc85xx.h> diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 9446248eb6b8..99eab7bc7edc 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -60,7 +60,7 @@ static int eeh_result_priority(enum pci_ers_result result) } }; -const char *pci_ers_result_name(enum pci_ers_result result) +static const char *pci_ers_result_name(enum pci_ers_result result) { switch (result) { case PCI_ERS_RESULT_NONE: diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 77decded1175..0768dfd8a64e 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -200,14 +200,14 @@ transfer_to_handler: cmplw r1,r9 /* if r1 <= ksp_limit */ ble- stack_ovf /* then the kernel stack overflowed */ 5: -#if defined(CONFIG_6xx) || defined(CONFIG_E500) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) CURRENT_THREAD_INFO(r9, r1) tophys(r9,r9) /* check local flags */ lwz r12,TI_LOCAL_FLAGS(r9) mtcrf 0x01,r12 bt- 31-TLF_NAPPING,4f bt- 31-TLF_SLEEPING,7f -#endif /* CONFIG_6xx || CONFIG_E500 */ +#endif /* CONFIG_PPC_BOOK3S_32 || CONFIG_E500 */ .globl transfer_to_handler_cont transfer_to_handler_cont: 3: @@ -273,7 +273,7 @@ reenable_mmu: /* re-enable mmu so we can */ RFI /* jump to handler, enable MMU */ #endif /* CONFIG_TRACE_IRQFLAGS */ -#if defined (CONFIG_6xx) || defined(CONFIG_E500) +#if defined (CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500) 4: rlwinm r12,r12,0,~_TLF_NAPPING stw r12,TI_LOCAL_FLAGS(r9) b power_save_ppc32_restore @@ -612,7 +612,7 @@ ppc_swapcontext: handle_page_fault: stw r4,_DAR(r1) addi r3,r1,STACK_FRAME_OVERHEAD -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 andis. r0,r5,DSISR_DABRMATCH@h bne- handle_dabr_fault #endif @@ -629,7 +629,7 @@ handle_page_fault: bl bad_page_fault b ret_from_except_full -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 /* We have a data breakpoint exception - handle it */ handle_dabr_fault: SAVE_NVGPRS(r1) diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c index 761b28b1427d..7a0da83bf883 100644 --- a/arch/powerpc/kernel/fadump.c +++ b/arch/powerpc/kernel/fadump.c @@ -1531,17 +1531,7 @@ static struct kobj_attribute fadump_register_attr = __ATTR(fadump_registered, 0644, fadump_register_show, fadump_register_store); -static int fadump_region_open(struct inode *inode, struct file *file) -{ - return single_open(file, fadump_region_show, inode->i_private); -} - -static const struct file_operations fadump_region_fops = { - .open = fadump_region_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(fadump_region); static void fadump_init_files(void) { diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S index 61ca27929355..118c3b216e60 100644 --- a/arch/powerpc/kernel/head_32.S +++ b/arch/powerpc/kernel/head_32.S @@ -176,10 +176,10 @@ __after_mmu_off: bl reloc_offset li r24,0 /* cpu# */ bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 bl reloc_offset bl init_idle_6xx -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ /* @@ -836,10 +836,10 @@ __secondary_start: lis r3,-KERNELBASE@h mr r4,r24 bl call_setup_cpu /* Call setup_cpu for this CPU */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 lis r3,-KERNELBASE@h bl init_idle_6xx -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ /* get current_thread_info and current */ lis r1,secondary_ti@ha @@ -880,14 +880,14 @@ __secondary_start: /* * Those generic dummy functions are kept for CPUs not - * included in CONFIG_6xx + * included in CONFIG_PPC_BOOK3S_32 */ -#if !defined(CONFIG_6xx) +#if !defined(CONFIG_PPC_BOOK3S_32) _ENTRY(__save_cpu_setup) blr _ENTRY(__restore_cpu_setup) blr -#endif /* !defined(CONFIG_6xx) */ +#endif /* !defined(CONFIG_PPC_BOOK3S_32) */ /* diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 3b67b9533c82..b171b7c0a0e7 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -106,6 +106,23 @@ turn_on_mmu: mtspr SPRN_SRR0,r0 rfi /* enables MMU */ + +#ifdef CONFIG_PERF_EVENTS + .align 4 + + .globl itlb_miss_counter +itlb_miss_counter: + .space 4 + + .globl dtlb_miss_counter +dtlb_miss_counter: + .space 4 + + .globl instruction_counter +instruction_counter: + .space 4 +#endif + /* * Exception entry code. This code runs with address translation * turned off, i.e. using physical addresses. @@ -275,7 +292,7 @@ SystemCall: . = 0x1100 /* * For the MPC8xx, this is a software tablewalk to load the instruction - * TLB. The task switch loads the M_TW register with the pointer to the first + * TLB. The task switch loads the M_TWB register with the pointer to the first * level table. * If we discover there is no second level table (value is zero) or if there * is an invalid pte, we load that into the TLB, which causes another fault @@ -285,186 +302,154 @@ SystemCall: */ #ifdef CONFIG_8xx_CPU15 -#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr) \ - addi tmp, addr, PAGE_SIZE; \ - tlbie tmp; \ - addi tmp, addr, -PAGE_SIZE; \ - tlbie tmp +#define INVALIDATE_ADJACENT_PAGES_CPU15(addr) \ + addi addr, addr, PAGE_SIZE; \ + tlbie addr; \ + addi addr, addr, -(PAGE_SIZE << 1); \ + tlbie addr; \ + addi addr, addr, PAGE_SIZE #else -#define INVALIDATE_ADJACENT_PAGES_CPU15(tmp, addr) +#define INVALIDATE_ADJACENT_PAGES_CPU15(addr) #endif InstructionTLBMiss: mtspr SPRN_SPRG_SCRATCH0, r10 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mtspr SPRN_SPRG_SCRATCH1, r11 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mtspr SPRN_SPRG_SCRATCH2, r12 #endif /* If we are faulting a kernel address, we have to use the * kernel page tables. */ mfspr r10, SPRN_SRR0 /* Get effective address of fault */ - INVALIDATE_ADJACENT_PAGES_CPU15(r11, r10) + INVALIDATE_ADJACENT_PAGES_CPU15(r10) + mtspr SPRN_MD_EPN, r10 /* Only modules will cause ITLB Misses as we always * pin the first 8MB of kernel memory */ -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfcr r12 -#endif #ifdef ITLB_MISS_KERNEL + mfcr r11 #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT) - andis. r11, r10, 0x8000 /* Address >= 0x80000000 */ + cmpi cr0, r10, 0 /* Address >= 0x80000000 */ #else - rlwinm r11, r10, 16, 0xfff8 - cmpli cr0, r11, PAGE_OFFSET@h + rlwinm r10, r10, 16, 0xfff8 + cmpli cr0, r10, PAGE_OFFSET@h #ifndef CONFIG_PIN_TLB_TEXT /* It is assumed that kernel code fits into the first 8M page */ -0: cmpli cr7, r11, (PAGE_OFFSET + 0x0800000)@h +0: cmpli cr7, r10, (PAGE_OFFSET + 0x0800000)@h patch_site 0b, patch__itlbmiss_linmem_top #endif #endif #endif - mfspr r11, SPRN_M_TW /* Get level 1 table */ + mfspr r10, SPRN_M_TWB /* Get level 1 table */ #ifdef ITLB_MISS_KERNEL #if defined(SIMPLE_KERNEL_ADDRESS) && defined(CONFIG_PIN_TLB_TEXT) - beq+ 3f + bge+ 3f #else blt+ 3f #endif #ifndef CONFIG_PIN_TLB_TEXT blt cr7, ITLBMissLinear #endif - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha + rlwinm r10, r10, 0, 20, 31 + oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha 3: #endif - /* Insert level 1 index */ - rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 - lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + lwz r10, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ + mtspr SPRN_MI_TWC, r10 /* Set segment attributes */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 -#ifdef CONFIG_HUGETLB_PAGE - mtcr r11 - bt- 28, 10f /* bit 28 = Large page (8M) */ - bt- 29, 20f /* bit 29 = Large page (8M or 512k) */ -#endif - rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ + mtspr SPRN_MD_TWC, r10 + mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ -4: -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mtcr r12 +#ifdef ITLB_MISS_KERNEL + mtcr r11 #endif - /* Load the MI_TWC with the attributes for this "segment." */ - mtspr SPRN_MI_TWC, r11 /* Set segment attributes */ - #ifdef CONFIG_SWAP rlwinm r11, r10, 32-5, _PAGE_PRESENT and r11, r11, r10 rlwimi r10, r11, 0, _PAGE_PRESENT #endif - li r11, RPN_PATTERN | 0x200 /* The Linux PTE won't go exactly into the MMU TLB. * Software indicator bits 20 and 23 must be clear. * Software indicator bits 22, 24, 25, 26, and 27 must be * set. All other Linux PTE bits control the behavior * of the MMU. */ - rlwimi r11, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ - rlwimi r10, r11, 0, 0x0ff0 /* Set 22, 24-27, clear 20,23 */ + rlwimi r10, r10, 0, 0x0f00 /* Clear bits 20-23 */ + rlwimi r10, r10, 4, 0x0400 /* Copy _PAGE_EXEC into bit 21 */ + ori r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */ mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ /* Restore registers */ 0: mfspr r10, SPRN_SPRG_SCRATCH0 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mfspr r11, SPRN_SPRG_SCRATCH1 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfspr r12, SPRN_SPRG_SCRATCH2 #endif rfi patch_site 0b, patch__itlbmiss_exit_1 #ifdef CONFIG_PERF_EVENTS patch_site 0f, patch__itlbmiss_perf -0: lis r10, (itlb_miss_counter - PAGE_OFFSET)@ha - lwz r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, 1 - stw r11, (itlb_miss_counter - PAGE_OFFSET)@l(r10) -#endif +0: lwz r10, (itlb_miss_counter - PAGE_OFFSET)@l(0) + addi r10, r10, 1 + stw r10, (itlb_miss_counter - PAGE_OFFSET)@l(0) mfspr r10, SPRN_SPRG_SCRATCH0 +#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_SWAP) mfspr r11, SPRN_SPRG_SCRATCH1 -#if defined(ITLB_MISS_KERNEL) || defined(CONFIG_HUGETLB_PAGE) - mfspr r12, SPRN_SPRG_SCRATCH2 #endif rfi - -#ifdef CONFIG_HUGETLB_PAGE -10: /* 8M pages */ -#ifdef CONFIG_PPC_16K_PAGES - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 -#else - /* Level 2 base */ - rlwinm r10, r11, 0, ~HUGEPD_SHIFT_MASK #endif - lwz r10, 0(r10) /* Get the pte */ - b 4b -20: /* 512k pages */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 - lwz r10, 0(r10) /* Get the pte */ - b 4b +#ifndef CONFIG_PIN_TLB_TEXT +ITLBMissLinear: + mtcr r11 + /* Set 8M byte page and mark it valid */ + li r11, MI_PS8MEG | MI_SVALID + mtspr SPRN_MI_TWC, r11 + rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */ + ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ + _PAGE_PRESENT + mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ + +0: mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + rfi + patch_site 0b, patch__itlbmiss_exit_2 #endif . = 0x1200 DataStoreTLBMiss: mtspr SPRN_SPRG_SCRATCH0, r10 mtspr SPRN_SPRG_SCRATCH1, r11 - mtspr SPRN_SPRG_SCRATCH2, r12 - mfcr r12 + mfcr r11 /* If we are faulting a kernel address, we have to use the * kernel page tables. */ mfspr r10, SPRN_MD_EPN - rlwinm r11, r10, 16, 0xfff8 - cmpli cr0, r11, PAGE_OFFSET@h - mfspr r11, SPRN_M_TW /* Get level 1 table */ - blt+ 3f - rlwinm r11, r10, 16, 0xfff8 + rlwinm r10, r10, 16, 0xfff8 + cmpli cr0, r10, PAGE_OFFSET@h #ifndef CONFIG_PIN_TLB_IMMR - cmpli cr0, r11, VIRT_IMMR_BASE@h + cmpli cr6, r10, VIRT_IMMR_BASE@h #endif -0: cmpli cr7, r11, (PAGE_OFFSET + 0x1800000)@h +0: cmpli cr7, r10, (PAGE_OFFSET + 0x1800000)@h patch_site 0b, patch__dtlbmiss_linmem_top + + mfspr r10, SPRN_M_TWB /* Get level 1 table */ + blt+ 3f #ifndef CONFIG_PIN_TLB_IMMR -0: beq- DTLBMissIMMR +0: beq- cr6, DTLBMissIMMR patch_site 0b, patch__dtlbmiss_immr_jmp #endif blt cr7, DTLBMissLinear - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha + rlwinm r10, r10, 0, 20, 31 + oris r10, r10, (swapper_pg_dir - PAGE_OFFSET)@ha 3: - - /* Insert level 1 index */ - rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 - lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ - - /* We have a pte table, so load fetch the pte from the table. - */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 -#ifdef CONFIG_HUGETLB_PAGE mtcr r11 - bt- 28, 10f /* bit 28 = Large page (8M) */ - bt- 29, 20f /* bit 29 = Large page (8M or 512k) */ -#endif - rlwimi r10, r11, 0, 0, 32 - PAGE_SHIFT - 1 /* Add level 2 base */ + lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r10) /* Get level 1 entry */ + + mtspr SPRN_MD_TWC, r11 + mfspr r10, SPRN_MD_TWC lwz r10, 0(r10) /* Get the pte */ -4: - mtcr r12 /* Insert the Guarded flag into the TWC from the Linux PTE. * It is bit 27 of both the Linux PTE and the TWC (at least @@ -503,44 +488,55 @@ DataStoreTLBMiss: 0: mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 rfi patch_site 0b, patch__dtlbmiss_exit_1 #ifdef CONFIG_PERF_EVENTS patch_site 0f, patch__dtlbmiss_perf -0: lis r10, (dtlb_miss_counter - PAGE_OFFSET)@ha - lwz r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, 1 - stw r11, (dtlb_miss_counter - PAGE_OFFSET)@l(r10) -#endif +0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) + addi r10, r10, 1 + stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0) mfspr r10, SPRN_SPRG_SCRATCH0 mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 rfi - -#ifdef CONFIG_HUGETLB_PAGE -10: /* 8M pages */ - /* Extract level 2 index */ -#ifdef CONFIG_PPC_16K_PAGES - rlwinm r10, r10, 32 - (PAGE_SHIFT_8M - PAGE_SHIFT), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 -#else - /* Level 2 base */ - rlwinm r10, r11, 0, ~HUGEPD_SHIFT_MASK #endif - lwz r10, 0(r10) /* Get the pte */ - b 4b -20: /* 512k pages */ - /* Extract level 2 index */ - rlwinm r10, r10, 32 - (PAGE_SHIFT_512K - PAGE_SHIFT), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 - /* Add level 2 base */ - rlwimi r10, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 - lwz r10, 0(r10) /* Get the pte */ - b 4b -#endif +DTLBMissIMMR: + mtcr r11 + /* Set 512k byte guarded page and mark it valid */ + li r10, MD_PS512K | MD_GUARDED | MD_SVALID + mtspr SPRN_MD_TWC, r10 + mfspr r10, SPRN_IMMR /* Get current IMMR */ + rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */ + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ + _PAGE_PRESENT | _PAGE_NO_CACHE + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + + li r11, RPN_PATTERN + mtspr SPRN_DAR, r11 /* Tag DAR */ + +0: mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + rfi + patch_site 0b, patch__dtlbmiss_exit_2 + +DTLBMissLinear: + mtcr r11 + /* Set 8M byte page and mark it valid */ + li r11, MD_PS8MEG | MD_SVALID + mtspr SPRN_MD_TWC, r11 + rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */ + ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ + _PAGE_PRESENT + mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ + + li r11, RPN_PATTERN + mtspr SPRN_DAR, r11 /* Tag DAR */ + +0: mfspr r10, SPRN_SPRG_SCRATCH0 + mfspr r11, SPRN_SPRG_SCRATCH1 + rfi + patch_site 0b, patch__dtlbmiss_exit_3 /* This is an instruction TLB error on the MPC8xx. This could be due * to many reasons, such as executing guarded memory or illegal instruction @@ -625,16 +621,13 @@ DataBreakpoint: . = 0x1d00 InstructionBreakpoint: mtspr SPRN_SPRG_SCRATCH0, r10 - mtspr SPRN_SPRG_SCRATCH1, r11 - lis r10, (instruction_counter - PAGE_OFFSET)@ha - lwz r11, (instruction_counter - PAGE_OFFSET)@l(r10) - addi r11, r11, -1 - stw r11, (instruction_counter - PAGE_OFFSET)@l(r10) + lwz r10, (instruction_counter - PAGE_OFFSET)@l(0) + addi r10, r10, -1 + stw r10, (instruction_counter - PAGE_OFFSET)@l(0) lis r10, 0xffff ori r10, r10, 0x01 mtspr SPRN_COUNTA, r10 mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 rfi #else EXCEPTION(0x1d00, Trap_1d, unknown_exception, EXC_XFER_EE) @@ -644,67 +637,6 @@ InstructionBreakpoint: . = 0x2000 -/* - * Bottom part of DataStoreTLBMiss handlers for IMMR area and linear RAM. - * not enough space in the DataStoreTLBMiss area. - */ -DTLBMissIMMR: - mtcr r12 - /* Set 512k byte guarded page and mark it valid */ - li r10, MD_PS512K | MD_GUARDED | MD_SVALID - mtspr SPRN_MD_TWC, r10 - mfspr r10, SPRN_IMMR /* Get current IMMR */ - rlwinm r10, r10, 0, 0xfff80000 /* Get 512 kbytes boundary */ - ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ - _PAGE_PRESENT | _PAGE_NO_CACHE - mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ - - li r11, RPN_PATTERN - mtspr SPRN_DAR, r11 /* Tag DAR */ - -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 - rfi - patch_site 0b, patch__dtlbmiss_exit_2 - -DTLBMissLinear: - mtcr r12 - /* Set 8M byte page and mark it valid */ - li r11, MD_PS8MEG | MD_SVALID - mtspr SPRN_MD_TWC, r11 - rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ - ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ - _PAGE_PRESENT - mtspr SPRN_MD_RPN, r10 /* Update TLB entry */ - - li r11, RPN_PATTERN - mtspr SPRN_DAR, r11 /* Tag DAR */ - -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 - rfi - patch_site 0b, patch__dtlbmiss_exit_3 - -#ifndef CONFIG_PIN_TLB_TEXT -ITLBMissLinear: - mtcr r12 - /* Set 8M byte page and mark it valid */ - li r11, MI_PS8MEG | MI_SVALID - mtspr SPRN_MI_TWC, r11 - rlwinm r10, r10, 0, 0x0f800000 /* 8xx supports max 256Mb RAM */ - ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \ - _PAGE_PRESENT - mtspr SPRN_MI_RPN, r10 /* Update TLB entry */ - -0: mfspr r10, SPRN_SPRG_SCRATCH0 - mfspr r11, SPRN_SPRG_SCRATCH1 - mfspr r12, SPRN_SPRG_SCRATCH2 - rfi - patch_site 0b, patch__itlbmiss_exit_2 -#endif - /* This is the procedure to calculate the data EA for buggy dcbx,dcbi instructions * by decoding the registers used by the dcbx instruction and adding them. * DAR is set to the calculated address. @@ -712,12 +644,13 @@ ITLBMissLinear: /* define if you don't want to use self modifying code */ #define NO_SELF_MODIFYING_CODE FixupDAR:/* Entry point for dcbx workaround. */ - mtspr SPRN_SPRG_SCRATCH2, r10 + mtspr SPRN_M_TW, r10 /* fetch instruction from memory. */ mfspr r10, SPRN_SRR0 + mtspr SPRN_MD_EPN, r10 rlwinm r11, r10, 16, 0xfff8 cmpli cr0, r11, PAGE_OFFSET@h - mfspr r11, SPRN_M_TW /* Get level 1 table */ + mfspr r11, SPRN_M_TWB /* Get level 1 table */ blt+ 3f rlwinm r11, r10, 16, 0xfff8 @@ -727,17 +660,17 @@ FixupDAR:/* Entry point for dcbx workaround. */ /* create physical page address from effective address */ tophys(r11, r10) blt- cr7, 201f - lis r11, (swapper_pg_dir-PAGE_OFFSET)@ha - /* Insert level 1 index */ -3: rlwimi r11, r10, 32 - ((PAGE_SHIFT - 2) << 1), (PAGE_SHIFT - 2) << 1, 29 + mfspr r11, SPRN_M_TWB /* Get level 1 table */ + rlwinm r11, r11, 0, 20, 31 + oris r11, r11, (swapper_pg_dir - PAGE_OFFSET)@ha +3: lwz r11, (swapper_pg_dir-PAGE_OFFSET)@l(r11) /* Get the level 1 entry */ + mtspr SPRN_MD_TWC, r11 mtcr r11 + mfspr r11, SPRN_MD_TWC + lwz r11, 0(r11) /* Get the pte */ bt 28,200f /* bit 28 = Large page (8M) */ bt 29,202f /* bit 29 = Large page (8M or 512K) */ - rlwinm r11, r11,0,0,19 /* Extract page descriptor page address */ - /* Insert level 2 index */ - rlwimi r11, r10, 32 - (PAGE_SHIFT - 2), 32 - PAGE_SHIFT, 29 - lwz r11, 0(r11) /* Get the pte */ /* concat physical page address(r11) and page offset(r10) */ rlwimi r11, r10, 0, 32 - PAGE_SHIFT, 31 201: lwz r11,0(r11) @@ -756,26 +689,15 @@ FixupDAR:/* Entry point for dcbx workaround. */ beq+ 142f cmpwi cr0, r10, 1964 /* Is icbi? */ beq+ 142f -141: mfspr r10,SPRN_SPRG_SCRATCH2 +141: mfspr r10,SPRN_M_TW b DARFixed /* Nope, go back to normal TLB processing */ - /* concat physical page address(r11) and page offset(r10) */ 200: -#ifdef CONFIG_PPC_16K_PAGES - rlwinm r11, r11, 0, 0, 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1) - 1 - rlwimi r11, r10, 32 - (PAGE_SHIFT_8M - 2), 32 + PAGE_SHIFT_8M - (PAGE_SHIFT << 1), 29 -#else - rlwinm r11, r10, 0, ~HUGEPD_SHIFT_MASK -#endif - lwz r11, 0(r11) /* Get the pte */ /* concat physical page address(r11) and page offset(r10) */ rlwimi r11, r10, 0, 32 - PAGE_SHIFT_8M, 31 b 201b 202: - rlwinm r11, r11, 0, 0, 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1) - 1 - rlwimi r11, r10, 32 - (PAGE_SHIFT_512K - 2), 32 + PAGE_SHIFT_512K - (PAGE_SHIFT << 1), 29 - lwz r11, 0(r11) /* Get the pte */ /* concat physical page address(r11) and page offset(r10) */ rlwimi r11, r10, 0, 32 - PAGE_SHIFT_512K, 31 b 201b @@ -802,7 +724,7 @@ modified_instr: bne+ 143f subf r10,r0,r10 /* r10=r10-r0, only if reg RA is r0 */ 143: mtdar r10 /* store faulting EA in DAR */ - mfspr r10,SPRN_SPRG_SCRATCH2 + mfspr r10,SPRN_M_TW b DARFixed /* Go back to normal TLB handling */ #else mfctr r10 @@ -856,7 +778,7 @@ modified_instr: mfdar r11 mtctr r11 /* restore ctr reg from DAR */ mtdar r10 /* save fault EA to DAR */ - mfspr r10,SPRN_SPRG_SCRATCH2 + mfspr r10,SPRN_M_TW b DARFixed /* Go back to normal TLB handling */ /* special handling for r10,r11 since these are modified already */ @@ -891,7 +813,7 @@ start_here: lis r6, swapper_pg_dir@ha tophys(r6,r6) - mtspr SPRN_M_TW, r6 + mtspr SPRN_M_TWB, r6 bl early_init /* We have to do this with MMU on */ @@ -1065,17 +987,3 @@ swapper_pg_dir: */ abatron_pteptrs: .space 8 - -#ifdef CONFIG_PERF_EVENTS - .globl itlb_miss_counter -itlb_miss_counter: - .space 4 - - .globl dtlb_miss_counter -dtlb_miss_counter: - .space 4 - - .globl instruction_counter -instruction_counter: - .space 4 -#endif diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c index fda3ae48480c..0e7099da4f25 100644 --- a/arch/powerpc/kernel/isa-bridge.c +++ b/arch/powerpc/kernel/isa-bridge.c @@ -327,8 +327,7 @@ static int isa_bridge_notify(struct notifier_block *nb, unsigned long action, /* Check if we have no ISA device, and this happens to be one, * register it as such if it has an OF device */ - if (!isa_bridge_devnode && devnode && devnode->type && - !strcmp(devnode->type, "isa")) + if (!isa_bridge_devnode && of_node_is_type(devnode, "isa")) isa_bridge_find_late(pdev, devnode); return 0; diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c index 5b9dce17f0c9..fde632335a97 100644 --- a/arch/powerpc/kernel/legacy_serial.c +++ b/arch/powerpc/kernel/legacy_serial.c @@ -192,7 +192,7 @@ static int __init add_legacy_soc_port(struct device_node *np, /* Add port, irq will be dealt with later. We passed a translated * IO port value. It will be fixed up later along with the irq */ - if (tsi && !strcmp(tsi->type, "tsi-bridge")) + if (of_node_is_type(tsi, "tsi-bridge")) return add_legacy_port(np, -1, UPIO_TSI, addr, addr, 0, legacy_port_flags, 0); else @@ -419,7 +419,8 @@ void __init find_legacy_serial_ports(void) of_node_put(parent); continue; } - if (strcmp(np->name, "serial") && strcmp(np->type, "serial")) { + if (strcmp(np->name, "serial") && + !of_node_is_type(np, "serial")) { of_node_put(parent); continue; } diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 695b24a2d954..57d2ffb2d45c 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -153,7 +153,7 @@ _GLOBAL(call_setup_cpu) mtctr r5 bctr -#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_6xx) +#if defined(CONFIG_CPU_FREQ_PMAC) && defined(CONFIG_PPC_BOOK3S_32) /* This gets called by via-pmu.c to switch the PLL selection * on 750fx CPU. This function should really be moved to some @@ -223,7 +223,7 @@ _GLOBAL(low_choose_7447a_dfs) mtmsr r7 blr -#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_6xx */ +#endif /* CONFIG_CPU_FREQ_PMAC && CONFIG_PPC_BOOK3S_32 */ /* * complement mask on the msr then "or" some values on. diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 22e9d281324d..06e2eda2430e 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -809,6 +809,7 @@ static long dev_nvram_ioctl(struct file *file, unsigned int cmd, #ifdef CONFIG_PPC_PMAC case OBSOLETE_PMAC_NVRAM_GET_OFFSET: printk(KERN_WARNING "nvram: Using obsolete PMAC_NVRAM_GET_OFFSET ioctl\n"); + /* fall through */ case IOC_NVRAM_GET_OFFSET: { int part, offset; diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c index 98f04725def7..24191ea2d9a7 100644 --- a/arch/powerpc/kernel/pci_of_scan.c +++ b/arch/powerpc/kernel/pci_of_scan.c @@ -125,16 +125,13 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, struct pci_bus *bus, int devfn) { struct pci_dev *dev; - const char *type; dev = pci_alloc_dev(bus); if (!dev) return NULL; - type = of_get_property(node, "device_type", NULL); - if (type == NULL) - type = ""; - pr_debug(" create device, devfn: %x, type: %s\n", devfn, type); + pr_debug(" create device, devfn: %x, type: %s\n", devfn, + of_node_get_device_type(node)); dev->dev.of_node = of_node_get(node); dev->dev.parent = bus->bridge; @@ -167,12 +164,12 @@ struct pci_dev *of_create_pci_dev(struct device_node *node, /* Early fixups, before probing the BARs */ pci_fixup_device(pci_fixup_early, dev); - if (!strcmp(type, "pci") || !strcmp(type, "pciex")) { + if (of_node_is_type(node, "pci") || of_node_is_type(node, "pciex")) { /* a PCI-PCI bridge */ dev->hdr_type = PCI_HEADER_TYPE_BRIDGE; dev->rom_base_reg = PCI_ROM_ADDRESS1; set_pcie_hotplug_bridge(dev); - } else if (!strcmp(type, "cardbus")) { + } else if (of_node_is_type(node, "cardbus")) { dev->hdr_type = PCI_HEADER_TYPE_CARDBUS; } else { dev->hdr_type = PCI_HEADER_TYPE_NORMAL; diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c index 58eaa3ddf7b9..2de71faca911 100644 --- a/arch/powerpc/kernel/pmc.c +++ b/arch/powerpc/kernel/pmc.c @@ -29,7 +29,7 @@ static void dummy_perf(struct pt_regs *regs) { #if defined(CONFIG_FSL_EMB_PERFMON) mtpmr(PMRN_PMGC0, mfpmr(PMRN_PMGC0) & ~PMGC0_PMIE); -#elif defined(CONFIG_PPC64) || defined(CONFIG_6xx) +#elif defined(CONFIG_PPC64) || defined(CONFIG_PPC_BOOK3S_32) if (cur_cpu_spec->pmc_type == PPC_PMC_IBM) mtspr(SPRN_MMCR0, mfspr(SPRN_MMCR0) & ~(MMCR0_PMXE|MMCR0_PMAO)); #else diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index f6f469fc4073..9703dce36307 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -4,6 +4,7 @@ // // Copyright 2018, Michael Ellerman, IBM Corporation. +#include <linux/cpu.h> #include <linux/kernel.h> #include <linux/device.h> #include <linux/seq_buf.h> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 93ee3703b42f..4fe7740917a7 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -687,7 +687,7 @@ int check_legacy_ioport(unsigned long base_port) return ret; parent = of_get_parent(np); if (parent) { - if (strcmp(parent->type, "isa") == 0) + if (of_node_is_type(parent, "isa")) ret = 0; of_node_put(parent); } @@ -800,7 +800,7 @@ static __init void print_system_info(void) #ifdef CONFIG_PPC_BOOK3S_64 pr_info("ppc64_pft_size = 0x%llx\n", ppc64_pft_size); #endif -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 pr_info("Hash_size = 0x%lx\n", Hash_size); #endif pr_info("phys_mem_size = 0x%llx\n", @@ -830,7 +830,7 @@ static __init void print_system_info(void) if (htab_hash_mask) pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask); #endif -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 if (Hash) pr_info("Hash = 0x%p\n", Hash); if (Hash_mask) diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 81909600013a..972c98d1e208 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -240,7 +240,7 @@ void __init exc_lvl_early_init(void) void __init setup_power_save(void) { -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 if (cpu_has_feature(CPU_FTR_CAN_DOZE) || cpu_has_feature(CPU_FTR_CAN_NAP)) ppc_md.power_save = ppc6xx_idle; diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c index 755dc98a57ae..e8e93c2c7d03 100644 --- a/arch/powerpc/kernel/sysfs.c +++ b/arch/powerpc/kernel/sysfs.c @@ -457,7 +457,7 @@ static ssize_t __used \ #define HAS_PPC_PMC_CLASSIC 1 #define HAS_PPC_PMC_IBM 1 #define HAS_PPC_PMC_PA6T 1 -#elif defined(CONFIG_6xx) +#elif defined(CONFIG_PPC_BOOK3S_32) #define HAS_PPC_PMC_CLASSIC 1 #define HAS_PPC_PMC_IBM 1 #define HAS_PPC_PMC_G4 1 diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 4bf051d3e21e..65248d471ef7 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -107,7 +107,7 @@ static int is_b_op(unsigned int op) static unsigned long find_bl_target(unsigned long ip, unsigned int op) { - static int offset; + int offset; offset = (op & 0x03fffffc); /* make it signed */ diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 434581bcd5b4..1148c3c60c3b 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -308,6 +308,10 @@ SECTIONS #ifdef CONFIG_PPC32 .data : AT(ADDR(.data) - LOAD_OFFSET) { DATA_DATA +#ifdef CONFIG_UBSAN + *(.data..Lubsan_data*) + *(.data..Lubsan_type*) +#endif *(.data.rel*) *(SDATA_MAIN) *(.sdata2) diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 94f04fcb373e..962ee90a0dfe 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -20,7 +20,7 @@ #define KVM_E500_H #include <linux/kvm_host.h> -#include <asm/mmu-book3e.h> +#include <asm/nohash/mmu-book3e.h> #include <asm/tlb.h> #include <asm/cputhreads.h> diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index e613b02bb2f0..ca8478503f18 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -118,7 +118,7 @@ void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end) } #ifdef CONFIG_PPC_BOOK3S_64 -void do_stf_entry_barrier_fixups(enum stf_barrier_type types) +static void do_stf_entry_barrier_fixups(enum stf_barrier_type types) { unsigned int instrs[3], *dest; long *start, *end; @@ -168,7 +168,7 @@ void do_stf_entry_barrier_fixups(enum stf_barrier_type types) : "unknown"); } -void do_stf_exit_barrier_fixups(enum stf_barrier_type types) +static void do_stf_exit_barrier_fixups(enum stf_barrier_type types) { unsigned int instrs[6], *dest; long *start, *end; diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c index 01b7f5107c3a..e2b6687ebb50 100644 --- a/arch/powerpc/mm/8xx_mmu.c +++ b/arch/powerpc/mm/8xx_mmu.c @@ -175,12 +175,12 @@ void set_context(unsigned long id, pgd_t *pgd) *(ptr + 1) = pgd; #endif - /* Register M_TW will contain base address of level 1 table minus the + /* Register M_TWB will contain base address of level 1 table minus the * lower part of the kernel PGDIR base address, so that all accesses to * level 1 table are done relative to lower part of kernel PGDIR base * address. */ - mtspr(SPRN_M_TW, __pa(pgd) - offset); + mtspr(SPRN_M_TWB, __pa(pgd) - offset); /* Update context */ mtspr(SPRN_M_CASID, id - 1); diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile index ca96e7be4d0e..f965fc33a8b7 100644 --- a/arch/powerpc/mm/Makefile +++ b/arch/powerpc/mm/Makefile @@ -15,10 +15,13 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \ obj-$(CONFIG_PPC_BOOK3E) += tlb_low_$(BITS)e.o hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o -obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o $(hash64-y) mmu_context_book3s64.o pgtable-book3s64.o +obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o \ + $(hash64-y) mmu_context_book3s64.o \ + pgtable-book3s64.o pgtable-frag.o +obj-$(CONFIG_PPC32) += pgtable-frag.o obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o -obj-$(CONFIG_PPC_STD_MMU_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o -obj-$(CONFIG_PPC_STD_MMU) += tlb_hash$(BITS).o +obj-$(CONFIG_PPC_BOOK3S_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o +obj-$(CONFIG_PPC_BOOK3S) += tlb_hash$(BITS).o ifdef CONFIG_PPC_BOOK3S_64 obj-$(CONFIG_PPC_4K_PAGES) += hash64_4k.o obj-$(CONFIG_PPC_64K_PAGES) += hash64_64k.o @@ -47,7 +50,7 @@ ifdef CONFIG_PPC_PTDUMP obj-$(CONFIG_4xx) += dump_linuxpagetables-generic.o obj-$(CONFIG_PPC_8xx) += dump_linuxpagetables-8xx.o obj-$(CONFIG_PPC_BOOK3E_MMU) += dump_linuxpagetables-generic.o -obj-$(CONFIG_PPC_BOOK3S_32) += dump_linuxpagetables-generic.o +obj-$(CONFIG_PPC_BOOK3S_32) += dump_linuxpagetables-generic.o dump_bats.o dump_sr.o obj-$(CONFIG_PPC_BOOK3S_64) += dump_linuxpagetables-book3s64.o endif obj-$(CONFIG_PPC_HTDUMP) += dump_hashpagetable.o diff --git a/arch/powerpc/mm/dump_bats.c b/arch/powerpc/mm/dump_bats.c new file mode 100644 index 000000000000..a0d23e96e841 --- /dev/null +++ b/arch/powerpc/mm/dump_bats.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * <[email protected]> + * + * This dumps the content of BATS + */ + +#include <asm/debugfs.h> +#include <asm/pgtable.h> +#include <asm/cpu_has_feature.h> + +static char *pp_601(int k, int pp) +{ + if (pp == 0) + return k ? "NA" : "RWX"; + if (pp == 1) + return k ? "ROX" : "RWX"; + if (pp == 2) + return k ? "RWX" : "RWX"; + return k ? "ROX" : "ROX"; +} + +static void bat_show_601(struct seq_file *m, int idx, u32 lower, u32 upper) +{ + u32 blpi = upper & 0xfffe0000; + u32 k = (upper >> 2) & 3; + u32 pp = upper & 3; + phys_addr_t pbn = PHYS_BAT_ADDR(lower); + u32 bsm = lower & 0x3ff; + u32 size = (bsm + 1) << 17; + + seq_printf(m, "%d: ", idx); + if (!(lower & 0x40)) { + seq_puts(m, " -\n"); + return; + } + + seq_printf(m, "0x%08x-0x%08x ", blpi, blpi + size - 1); +#ifdef CONFIG_PHYS_64BIT + seq_printf(m, "0x%016llx ", pbn); +#else + seq_printf(m, "0x%08x ", pbn); +#endif + + seq_printf(m, "Kernel %s User %s", pp_601(k & 2, pp), pp_601(k & 1, pp)); + + if (lower & _PAGE_WRITETHRU) + seq_puts(m, "write through "); + if (lower & _PAGE_NO_CACHE) + seq_puts(m, "no cache "); + if (lower & _PAGE_COHERENT) + seq_puts(m, "coherent "); + seq_puts(m, "\n"); +} + +#define BAT_SHOW_601(_m, _n, _l, _u) bat_show_601(_m, _n, mfspr(_l), mfspr(_u)) + +static int bats_show_601(struct seq_file *m, void *v) +{ + seq_puts(m, "---[ Block Address Translation ]---\n"); + + BAT_SHOW_601(m, 0, SPRN_IBAT0L, SPRN_IBAT0U); + BAT_SHOW_601(m, 1, SPRN_IBAT1L, SPRN_IBAT1U); + BAT_SHOW_601(m, 2, SPRN_IBAT2L, SPRN_IBAT2U); + BAT_SHOW_601(m, 3, SPRN_IBAT3L, SPRN_IBAT3U); + + return 0; +} + +static void bat_show_603(struct seq_file *m, int idx, u32 lower, u32 upper, bool is_d) +{ + u32 bepi = upper & 0xfffe0000; + u32 bl = (upper >> 2) & 0x7ff; + u32 k = upper & 3; + phys_addr_t brpn = PHYS_BAT_ADDR(lower); + u32 size = (bl + 1) << 17; + + seq_printf(m, "%d: ", idx); + if (k == 0) { + seq_puts(m, " -\n"); + return; + } + + seq_printf(m, "0x%08x-0x%08x ", bepi, bepi + size - 1); +#ifdef CONFIG_PHYS_64BIT + seq_printf(m, "0x%016llx ", brpn); +#else + seq_printf(m, "0x%08x ", brpn); +#endif + + if (k == 1) + seq_puts(m, "User "); + else if (k == 2) + seq_puts(m, "Kernel "); + else + seq_puts(m, "Kernel/User "); + + if (lower & BPP_RX) + seq_puts(m, is_d ? "RO " : "EXEC "); + else if (lower & BPP_RW) + seq_puts(m, is_d ? "RW " : "EXEC "); + else + seq_puts(m, is_d ? "NA " : "NX "); + + if (lower & _PAGE_WRITETHRU) + seq_puts(m, "write through "); + if (lower & _PAGE_NO_CACHE) + seq_puts(m, "no cache "); + if (lower & _PAGE_COHERENT) + seq_puts(m, "coherent "); + if (lower & _PAGE_GUARDED) + seq_puts(m, "guarded "); + seq_puts(m, "\n"); +} + +#define BAT_SHOW_603(_m, _n, _l, _u, _d) bat_show_603(_m, _n, mfspr(_l), mfspr(_u), _d) + +static int bats_show_603(struct seq_file *m, void *v) +{ + seq_puts(m, "---[ Instruction Block Address Translation ]---\n"); + + BAT_SHOW_603(m, 0, SPRN_IBAT0L, SPRN_IBAT0U, false); + BAT_SHOW_603(m, 1, SPRN_IBAT1L, SPRN_IBAT1U, false); + BAT_SHOW_603(m, 2, SPRN_IBAT2L, SPRN_IBAT2U, false); + BAT_SHOW_603(m, 3, SPRN_IBAT3L, SPRN_IBAT3U, false); + if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) { + BAT_SHOW_603(m, 4, SPRN_IBAT4L, SPRN_IBAT4U, false); + BAT_SHOW_603(m, 5, SPRN_IBAT5L, SPRN_IBAT5U, false); + BAT_SHOW_603(m, 6, SPRN_IBAT6L, SPRN_IBAT6U, false); + BAT_SHOW_603(m, 7, SPRN_IBAT7L, SPRN_IBAT7U, false); + } + + seq_puts(m, "\n---[ Data Block Address Translation ]---\n"); + + BAT_SHOW_603(m, 0, SPRN_DBAT0L, SPRN_DBAT0U, true); + BAT_SHOW_603(m, 1, SPRN_DBAT1L, SPRN_DBAT1U, true); + BAT_SHOW_603(m, 2, SPRN_DBAT2L, SPRN_DBAT2U, true); + BAT_SHOW_603(m, 3, SPRN_DBAT3L, SPRN_DBAT3U, true); + if (mmu_has_feature(MMU_FTR_USE_HIGH_BATS)) { + BAT_SHOW_603(m, 4, SPRN_DBAT4L, SPRN_DBAT4U, true); + BAT_SHOW_603(m, 5, SPRN_DBAT5L, SPRN_DBAT5U, true); + BAT_SHOW_603(m, 6, SPRN_DBAT6L, SPRN_DBAT6U, true); + BAT_SHOW_603(m, 7, SPRN_DBAT7L, SPRN_DBAT7U, true); + } + + return 0; +} + +static int bats_open(struct inode *inode, struct file *file) +{ + if (cpu_has_feature(CPU_FTR_601)) + return single_open(file, bats_show_601, NULL); + + return single_open(file, bats_show_603, NULL); +} + +static const struct file_operations bats_fops = { + .open = bats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init bats_init(void) +{ + struct dentry *debugfs_file; + + debugfs_file = debugfs_create_file("block_address_translation", 0400, + powerpc_debugfs_root, NULL, &bats_fops); + return debugfs_file ? 0 : -ENOMEM; +} +device_initcall(bats_init); diff --git a/arch/powerpc/mm/dump_sr.c b/arch/powerpc/mm/dump_sr.c new file mode 100644 index 000000000000..501843664bb9 --- /dev/null +++ b/arch/powerpc/mm/dump_sr.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2018, Christophe Leroy CS S.I. + * <[email protected]> + * + * This dumps the content of Segment Registers + */ + +#include <asm/debugfs.h> + +static void seg_show(struct seq_file *m, int i) +{ + u32 val = mfsrin(i << 28); + + seq_printf(m, "0x%01x0000000-0x%01xfffffff ", i, i); + seq_printf(m, "Kern key %d ", (val >> 30) & 1); + seq_printf(m, "User key %d ", (val >> 29) & 1); + if (val & 0x80000000) { + seq_printf(m, "Device 0x%03x", (val >> 20) & 0x1ff); + seq_printf(m, "-0x%05x", val & 0xfffff); + } else { + if (val & 0x10000000) + seq_puts(m, "No Exec "); + seq_printf(m, "VSID 0x%06x", val & 0xffffff); + } + seq_puts(m, "\n"); +} + +static int sr_show(struct seq_file *m, void *v) +{ + int i; + + seq_puts(m, "---[ User Segments ]---\n"); + for (i = 0; i < TASK_SIZE >> 28; i++) + seg_show(m, i); + + seq_puts(m, "\n---[ Kernel Segments ]---\n"); + for (; i < 16; i++) + seg_show(m, i); + + return 0; +} + +static int sr_open(struct inode *inode, struct file *file) +{ + return single_open(file, sr_show, NULL); +} + +static const struct file_operations sr_fops = { + .open = sr_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init sr_init(void) +{ + struct dentry *debugfs_file; + + debugfs_file = debugfs_create_file("segment_registers", 0400, + powerpc_debugfs_root, NULL, &sr_fops); + return debugfs_file ? 0 : -ENOMEM; +} +device_initcall(sr_init); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 1697e903bbf2..01b9bcc7fa85 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -341,7 +341,7 @@ static inline void cmo_account_page_fault(void) static inline void cmo_account_page_fault(void) { } #endif /* CONFIG_PPC_SMLPAR */ -#ifdef CONFIG_PPC_STD_MMU +#ifdef CONFIG_PPC_BOOK3S static void sanity_check_fault(bool is_write, unsigned long error_code) { /* @@ -378,7 +378,7 @@ static void sanity_check_fault(bool is_write, unsigned long error_code) } #else static void sanity_check_fault(bool is_write, unsigned long error_code) { } -#endif /* CONFIG_PPC_STD_MMU */ +#endif /* CONFIG_PPC_BOOK3S */ /* * Define the correct "is_write" bit in error_code based diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index 8cf035e68378..5b236621d302 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -42,6 +42,8 @@ EXPORT_SYMBOL(HPAGE_SHIFT); #define hugepd_none(hpd) (hpd_val(hpd) == 0) +#define PTE_T_ORDER (__builtin_ffs(sizeof(pte_t)) - __builtin_ffs(sizeof(void *))) + pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { /* @@ -61,14 +63,17 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp, int num_hugepd; if (pshift >= pdshift) { - cachep = hugepte_cache; + cachep = PGT_CACHE(PTE_T_ORDER); num_hugepd = 1 << (pshift - pdshift); + } else if (IS_ENABLED(CONFIG_PPC_8xx)) { + cachep = PGT_CACHE(PTE_INDEX_SIZE); + num_hugepd = 1; } else { cachep = PGT_CACHE(pdshift - pshift); num_hugepd = 1; } - new = kmem_cache_zalloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); + new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL)); BUG_ON(pshift > HUGEPD_SHIFT_MASK); BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK); @@ -264,7 +269,7 @@ static void hugepd_free_rcu_callback(struct rcu_head *head) unsigned int i; for (i = 0; i < batch->index; i++) - kmem_cache_free(hugepte_cache, batch->ptes[i]); + kmem_cache_free(PGT_CACHE(PTE_T_ORDER), batch->ptes[i]); free_page((unsigned long)batch); } @@ -277,7 +282,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte) if (atomic_read(&tlb->mm->mm_users) < 2 || mm_is_thread_local(tlb->mm)) { - kmem_cache_free(hugepte_cache, hugepte); + kmem_cache_free(PGT_CACHE(PTE_T_ORDER), hugepte); put_cpu_var(hugepd_freelist_cur); return; } @@ -329,6 +334,9 @@ static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshif if (shift >= pdshift) hugepd_free(tlb, hugepte); + else if (IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_free_tlb(tlb, hugepte, + get_hugepd_cache_index(PTE_INDEX_SIZE)); else pgtable_free_tlb(tlb, hugepte, get_hugepd_cache_index(pdshift - shift)); @@ -652,7 +660,6 @@ static int __init hugepage_setup_sz(char *str) } __setup("hugepagesz=", hugepage_setup_sz); -struct kmem_cache *hugepte_cache; static int __init hugetlbpage_init(void) { int psize; @@ -699,24 +706,13 @@ static int __init hugetlbpage_init(void) * if we have pdshift and shift value same, we don't * use pgt cache for hugepd. */ - if (pdshift > shift) - pgtable_cache_add(pdshift - shift, NULL); + if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx)) + pgtable_cache_add(PTE_INDEX_SIZE); + else if (pdshift > shift) + pgtable_cache_add(pdshift - shift); #if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_8xx) - else if (!hugepte_cache) { - /* - * Create a kmem cache for hugeptes. The bottom bits in - * the pte have size information encoded in them, so - * align them to allow this - */ - hugepte_cache = kmem_cache_create("hugepte-cache", - sizeof(pte_t), - HUGEPD_SHIFT_MASK + 1, - 0, NULL); - if (hugepte_cache == NULL) - panic("%s: Unable to create kmem cache " - "for hugeptes\n", __func__); - - } + else + pgtable_cache_add(PTE_T_ORDER); #endif } diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c index 2b656e67f2ea..1e6910eb70ed 100644 --- a/arch/powerpc/mm/init-common.c +++ b/arch/powerpc/mm/init-common.c @@ -25,22 +25,40 @@ #include <asm/pgalloc.h> #include <asm/pgtable.h> -static void pgd_ctor(void *addr) -{ - memset(addr, 0, PGD_TABLE_SIZE); +#define CTOR(shift) static void ctor_##shift(void *addr) \ +{ \ + memset(addr, 0, sizeof(void *) << (shift)); \ } -static void pud_ctor(void *addr) -{ - memset(addr, 0, PUD_TABLE_SIZE); -} +CTOR(0); CTOR(1); CTOR(2); CTOR(3); CTOR(4); CTOR(5); CTOR(6); CTOR(7); +CTOR(8); CTOR(9); CTOR(10); CTOR(11); CTOR(12); CTOR(13); CTOR(14); CTOR(15); -static void pmd_ctor(void *addr) +static inline void (*ctor(int shift))(void *) { - memset(addr, 0, PMD_TABLE_SIZE); + BUILD_BUG_ON(MAX_PGTABLE_INDEX_SIZE != 15); + + switch (shift) { + case 0: return ctor_0; + case 1: return ctor_1; + case 2: return ctor_2; + case 3: return ctor_3; + case 4: return ctor_4; + case 5: return ctor_5; + case 6: return ctor_6; + case 7: return ctor_7; + case 8: return ctor_8; + case 9: return ctor_9; + case 10: return ctor_10; + case 11: return ctor_11; + case 12: return ctor_12; + case 13: return ctor_13; + case 14: return ctor_14; + case 15: return ctor_15; + } + return NULL; } -struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE]; +struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE + 1]; EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */ /* @@ -50,7 +68,7 @@ EXPORT_SYMBOL_GPL(pgtable_cache); /* used by kvm_hv module */ * everything else. Caches created by this function are used for all * the higher level pagetables, and for hugepage pagetables. */ -void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) +void pgtable_cache_add(unsigned int shift) { char *name; unsigned long table_size = sizeof(void *) << shift; @@ -71,19 +89,19 @@ void pgtable_cache_add(unsigned shift, void (*ctor)(void *)) * moment, gcc doesn't seem to recognize is_power_of_2 as a * constant expression, so so much for that. */ BUG_ON(!is_power_of_2(minalign)); - BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE)); + BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE); if (PGT_CACHE(shift)) return; /* Already have a cache of this size */ align = max_t(unsigned long, align, minalign); name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift); - new = kmem_cache_create(name, table_size, align, 0, ctor); + new = kmem_cache_create(name, table_size, align, 0, ctor(shift)); if (!new) panic("Could not allocate pgtable cache for order %d", shift); kfree(name); - pgtable_cache[shift - 1] = new; + pgtable_cache[shift] = new; pr_debug("Allocated pgtable cache for order %d\n", shift); } @@ -91,15 +109,15 @@ EXPORT_SYMBOL_GPL(pgtable_cache_add); /* used by kvm_hv module */ void pgtable_cache_init(void) { - pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor); + pgtable_cache_add(PGD_INDEX_SIZE); - if (PMD_CACHE_INDEX && !PGT_CACHE(PMD_CACHE_INDEX)) - pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor); + if (PMD_CACHE_INDEX) + pgtable_cache_add(PMD_CACHE_INDEX); /* * In all current configs, when the PUD index exists it's the * same size as either the pgd or pmd index except with THP enabled * on book3s 64 */ - if (PUD_CACHE_INDEX && !PGT_CACHE(PUD_CACHE_INDEX)) - pgtable_cache_add(PUD_CACHE_INDEX, pud_ctor); + if (PUD_CACHE_INDEX) + pgtable_cache_add(PUD_CACHE_INDEX); } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 0a64fffabee1..065c37d54b49 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -503,7 +503,7 @@ EXPORT_SYMBOL(flush_icache_user_range); void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { -#ifdef CONFIG_PPC_STD_MMU +#ifdef CONFIG_PPC_BOOK3S /* * We don't need to worry about _PAGE_PRESENT here because we are * called with either mm->page_table_lock held or ptl lock held @@ -541,7 +541,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, } hash_preload(vma->vm_mm, address, is_exec, trap); -#endif /* CONFIG_PPC_STD_MMU */ +#endif /* CONFIG_PPC_BOOK3S */ #if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \ && defined(CONFIG_HUGETLB_PAGE) if (is_vm_hugetlb_page(vma)) diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c index f84e14f23e50..bb52320b7369 100644 --- a/arch/powerpc/mm/mmu_context.c +++ b/arch/powerpc/mm/mmu_context.c @@ -15,6 +15,7 @@ #include <linux/sched/mm.h> #include <asm/mmu_context.h> +#include <asm/pgalloc.h> #if defined(CONFIG_PPC32) static inline void switch_mm_pgdir(struct task_struct *tsk, @@ -97,3 +98,12 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, switch_mmu_context(prev, next, tsk); } +#ifdef CONFIG_PPC32 +void arch_exit_mmap(struct mm_struct *mm) +{ + void *frag = pte_frag_get(&mm->context); + + if (frag) + pte_frag_destroy(frag); +} +#endif diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c index 510f103d7813..f720c5cc0b5e 100644 --- a/arch/powerpc/mm/mmu_context_book3s64.c +++ b/arch/powerpc/mm/mmu_context_book3s64.c @@ -164,21 +164,6 @@ static void destroy_contexts(mm_context_t *ctx) } } -static void pte_frag_destroy(void *pte_frag) -{ - int count; - struct page *page; - - page = virt_to_page(pte_frag); - /* drop all the pending references */ - count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; - /* We allow PTE_FRAG_NR fragments from a PTE page */ - if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { - pgtable_page_dtor(page); - __free_page(page); - } -} - static void pmd_frag_destroy(void *pmd_frag) { int count; diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 2faca46ad720..431ecf37f17c 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -385,6 +385,7 @@ int init_new_context(struct task_struct *t, struct mm_struct *mm) #endif mm->context.id = MMU_NO_CONTEXT; mm->context.active = 0; + pte_frag_set(&mm->context, NULL); return 0; } @@ -487,4 +488,3 @@ void __init mmu_context_init(void) next_context = FIRST_CONTEXT; nr_free_contexts = LAST_CONTEXT - FIRST_CONTEXT + 1; } - diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h index 8574fbbc45e0..c4a717da65eb 100644 --- a/arch/powerpc/mm/mmu_decl.h +++ b/arch/powerpc/mm/mmu_decl.h @@ -155,7 +155,7 @@ struct tlbcam { }; #endif -#if defined(CONFIG_6xx) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx) +#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_FSL_BOOKE) || defined(CONFIG_PPC_8xx) /* 6xx have BATS */ /* FSL_BOOKE have TLBCAM */ /* 8xx have LTLB */ diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index ce28ae5ca080..87f0dd004295 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -1475,7 +1475,7 @@ static int dt_update_callback(struct notifier_block *nb, switch (action) { case OF_RECONFIG_UPDATE_PROPERTY: - if (!of_prop_cmp(update->dn->type, "cpu") && + if (of_node_is_type(update->dn, "cpu") && !of_prop_cmp(update->prop->name, "ibm,associativity")) { u32 core_id; of_property_read_u32(update->dn, "reg", &core_id); diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index 9f93c9f985c5..f3c31f5e1026 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -244,6 +244,9 @@ static pmd_t *get_pmd_from_cache(struct mm_struct *mm) { void *pmd_frag, *ret; + if (PMD_FRAG_NR == 1) + return NULL; + spin_lock(&mm->page_table_lock); ret = mm->context.pmd_frag; if (ret) { @@ -322,91 +325,6 @@ void pmd_fragment_free(unsigned long *pmd) } } -static pte_t *get_pte_from_cache(struct mm_struct *mm) -{ - void *pte_frag, *ret; - - spin_lock(&mm->page_table_lock); - ret = mm->context.pte_frag; - if (ret) { - pte_frag = ret + PTE_FRAG_SIZE; - /* - * If we have taken up all the fragments mark PTE page NULL - */ - if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) - pte_frag = NULL; - mm->context.pte_frag = pte_frag; - } - spin_unlock(&mm->page_table_lock); - return (pte_t *)ret; -} - -static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) -{ - void *ret = NULL; - struct page *page; - - if (!kernel) { - page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); - if (!page) - return NULL; - if (!pgtable_page_ctor(page)) { - __free_page(page); - return NULL; - } - } else { - page = alloc_page(PGALLOC_GFP); - if (!page) - return NULL; - } - - atomic_set(&page->pt_frag_refcount, 1); - - ret = page_address(page); - /* - * if we support only one fragment just return the - * allocated page. - */ - if (PTE_FRAG_NR == 1) - return ret; - spin_lock(&mm->page_table_lock); - /* - * If we find pgtable_page set, we return - * the allocated page with single fragement - * count. - */ - if (likely(!mm->context.pte_frag)) { - atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); - mm->context.pte_frag = ret + PTE_FRAG_SIZE; - } - spin_unlock(&mm->page_table_lock); - - return (pte_t *)ret; -} - -pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) -{ - pte_t *pte; - - pte = get_pte_from_cache(mm); - if (pte) - return pte; - - return __alloc_for_ptecache(mm, kernel); -} - -void pte_fragment_free(unsigned long *table, int kernel) -{ - struct page *page = virt_to_page(table); - - BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); - if (atomic_dec_and_test(&page->pt_frag_refcount)) { - if (!kernel) - pgtable_page_dtor(page); - __free_page(page); - } -} - static inline void pgtable_free(void *table, int index) { switch (index) { diff --git a/arch/powerpc/mm/pgtable-frag.c b/arch/powerpc/mm/pgtable-frag.c new file mode 100644 index 000000000000..af23a587f019 --- /dev/null +++ b/arch/powerpc/mm/pgtable-frag.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Handling Page Tables through page fragments + * + */ + +#include <linux/kernel.h> +#include <linux/gfp.h> +#include <linux/mm.h> +#include <linux/percpu.h> +#include <linux/hardirq.h> +#include <linux/hugetlb.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/tlb.h> + +void pte_frag_destroy(void *pte_frag) +{ + int count; + struct page *page; + + page = virt_to_page(pte_frag); + /* drop all the pending references */ + count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT; + /* We allow PTE_FRAG_NR fragments from a PTE page */ + if (atomic_sub_and_test(PTE_FRAG_NR - count, &page->pt_frag_refcount)) { + pgtable_page_dtor(page); + __free_page(page); + } +} + +static pte_t *get_pte_from_cache(struct mm_struct *mm) +{ + void *pte_frag, *ret; + + if (PTE_FRAG_NR == 1) + return NULL; + + spin_lock(&mm->page_table_lock); + ret = pte_frag_get(&mm->context); + if (ret) { + pte_frag = ret + PTE_FRAG_SIZE; + /* + * If we have taken up all the fragments mark PTE page NULL + */ + if (((unsigned long)pte_frag & ~PAGE_MASK) == 0) + pte_frag = NULL; + pte_frag_set(&mm->context, pte_frag); + } + spin_unlock(&mm->page_table_lock); + return (pte_t *)ret; +} + +static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel) +{ + void *ret = NULL; + struct page *page; + + if (!kernel) { + page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT); + if (!page) + return NULL; + if (!pgtable_page_ctor(page)) { + __free_page(page); + return NULL; + } + } else { + page = alloc_page(PGALLOC_GFP); + if (!page) + return NULL; + } + + atomic_set(&page->pt_frag_refcount, 1); + + ret = page_address(page); + /* + * if we support only one fragment just return the + * allocated page. + */ + if (PTE_FRAG_NR == 1) + return ret; + spin_lock(&mm->page_table_lock); + /* + * If we find pgtable_page set, we return + * the allocated page with single fragement + * count. + */ + if (likely(!pte_frag_get(&mm->context))) { + atomic_set(&page->pt_frag_refcount, PTE_FRAG_NR); + pte_frag_set(&mm->context, ret + PTE_FRAG_SIZE); + } + spin_unlock(&mm->page_table_lock); + + return (pte_t *)ret; +} + +pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel) +{ + pte_t *pte; + + pte = get_pte_from_cache(mm); + if (pte) + return pte; + + return __alloc_for_ptecache(mm, kernel); +} + +void pte_fragment_free(unsigned long *table, int kernel) +{ + struct page *page = virt_to_page(table); + + BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0); + if (atomic_dec_and_test(&page->pt_frag_refcount)) { + if (!kernel) + pgtable_page_dtor(page); + __free_page(page); + } +} diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c index 010e1c616cb2..1e33dccbd176 100644 --- a/arch/powerpc/mm/pgtable.c +++ b/arch/powerpc/mm/pgtable.c @@ -221,9 +221,9 @@ int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, } #ifdef CONFIG_HUGETLB_PAGE -extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) { #ifdef HUGETLB_NEED_PRELOAD /* diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index bda3c6f1bd32..4fc77a99c9bf 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -45,32 +45,15 @@ extern char etext[], _stext[], _sinittext[], _einittext[]; __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) { - pte_t *pte; + if (!slab_is_available()) + return memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE); - if (slab_is_available()) { - pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); - } else { - pte = __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); - if (pte) - clear_page(pte); - } - return pte; + return (pte_t *)pte_fragment_alloc(mm, address, 1); } pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address) { - struct page *ptepage; - - gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT; - - ptepage = alloc_pages(flags, 0); - if (!ptepage) - return NULL; - if (!pgtable_page_ctor(ptepage)) { - __free_page(ptepage); - return NULL; - } - return ptepage; + return (pgtable_t)pte_fragment_alloc(mm, address, 0); } void __iomem * @@ -260,7 +243,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top) ktext = ((char *)v >= _stext && (char *)v < etext) || ((char *)v >= _sinittext && (char *)v < _einittext); map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL); -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 if (ktext) hash_preload(&init_mm, v, false, 0x300); #endif diff --git a/arch/powerpc/mm/pkeys.c b/arch/powerpc/mm/pkeys.c index b271b283c785..04b60a8f6e69 100644 --- a/arch/powerpc/mm/pkeys.c +++ b/arch/powerpc/mm/pkeys.c @@ -6,20 +6,21 @@ */ #include <asm/mman.h> +#include <asm/mmu_context.h> #include <asm/setup.h> #include <linux/pkeys.h> #include <linux/of_device.h> DEFINE_STATIC_KEY_TRUE(pkey_disabled); -bool pkey_execute_disable_supported; int pkeys_total; /* Total pkeys as per device tree */ -bool pkeys_devtree_defined; /* pkey property exported by device tree */ u32 initial_allocation_mask; /* Bits set for the initially allocated keys */ u32 reserved_allocation_mask; /* Bits set for reserved keys */ -u64 pkey_amr_mask; /* Bits in AMR not to be touched */ -u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ -u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ -int execute_only_key = 2; +static bool pkey_execute_disable_supported; +static bool pkeys_devtree_defined; /* property exported by device tree */ +static u64 pkey_amr_mask; /* Bits in AMR not to be touched */ +static u64 pkey_iamr_mask; /* Bits in AMR not to be touched */ +static u64 pkey_uamor_mask; /* Bits in UMOR not to be touched */ +static int execute_only_key = 2; #define AMR_BITS_PER_PKEY 2 #define AMR_RD_BIT 0x1UL @@ -57,7 +58,7 @@ static inline bool pkey_mmu_enabled(void) return cpu_has_feature(CPU_FTR_PKEY); } -int pkey_initialize(void) +static int pkey_initialize(void) { int os_reserved, i; diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile index 8d26d7416481..bb2d94c8cbe6 100644 --- a/arch/powerpc/oprofile/Makefile +++ b/arch/powerpc/oprofile/Makefile @@ -16,4 +16,4 @@ oprofile-$(CONFIG_OPROFILE_CELL) += op_model_cell.o \ cell/spu_task_sync.o oprofile-$(CONFIG_PPC_BOOK3S_64) += op_model_power4.o op_model_pa6t.o oprofile-$(CONFIG_FSL_EMB_PERFMON) += op_model_fsl_emb.o -oprofile-$(CONFIG_6xx) += op_model_7450.o +oprofile-$(CONFIG_PPC_BOOK3S_32) += op_model_7450.o diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c index bf094c5a4bd9..a11132865504 100644 --- a/arch/powerpc/oprofile/common.c +++ b/arch/powerpc/oprofile/common.c @@ -212,7 +212,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) model = &op_model_pa6t; break; #endif -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 case PPC_OPROFILE_G4: model = &op_model_7450; break; diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index 6954636b16d1..f292a3f284f1 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -28,13 +28,13 @@ static DEFINE_MUTEX(nest_init_lock); static DEFINE_PER_CPU(struct imc_pmu_ref *, local_nest_imc_refc); static struct imc_pmu **per_nest_pmu_arr; static cpumask_t nest_imc_cpumask; -struct imc_pmu_ref *nest_imc_refc; +static struct imc_pmu_ref *nest_imc_refc; static int nest_pmus; /* Core IMC data structures and variables */ static cpumask_t core_imc_cpumask; -struct imc_pmu_ref *core_imc_refc; +static struct imc_pmu_ref *core_imc_refc; static struct imc_pmu *core_imc_pmu; /* Thread IMC data structures and variables */ @@ -43,7 +43,7 @@ static DEFINE_PER_CPU(u64 *, thread_imc_mem); static struct imc_pmu *thread_imc_pmu; static int thread_imc_mem_size; -struct imc_pmu *imc_event_to_pmu(struct perf_event *event) +static struct imc_pmu *imc_event_to_pmu(struct perf_event *event) { return container_of(event->pmu, struct imc_pmu, pmu); } diff --git a/arch/powerpc/platforms/4xx/pci.c b/arch/powerpc/platforms/4xx/pci.c index 5aca523551ae..d0825f5c5b1b 100644 --- a/arch/powerpc/platforms/4xx/pci.c +++ b/arch/powerpc/platforms/4xx/pci.c @@ -2081,7 +2081,6 @@ static void __init ppc4xx_probe_pciex_bridge(struct device_node *np) const u32 *pval; int portno; unsigned int dcrs; - const char *val; /* First, proceed to core initialization as we assume there's * only one PCIe core in the system @@ -2127,10 +2126,9 @@ static void __init ppc4xx_probe_pciex_bridge(struct device_node *np) * Resulting from this setup this PCIe port will be configured * as root-complex or as endpoint. */ - val = of_get_property(port->node, "device_type", NULL); - if (!strcmp(val, "pci-endpoint")) { + if (of_node_is_type(port->node, "pci-endpoint")) { port->endpoint = 1; - } else if (!strcmp(val, "pci")) { + } else if (of_node_is_type(port->node, "pci")) { port->endpoint = 0; } else { printk(KERN_ERR "PCIE: missing or incorrect device_type for %pOF\n", diff --git a/arch/powerpc/platforms/512x/Kconfig b/arch/powerpc/platforms/512x/Kconfig index b59eab6cbb1b..0c495823152c 100644 --- a/arch/powerpc/platforms/512x/Kconfig +++ b/arch/powerpc/platforms/512x/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_MPC512x bool "512x-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select COMMON_CLK select FSL_SOC select IPIC diff --git a/arch/powerpc/platforms/52xx/Kconfig b/arch/powerpc/platforms/52xx/Kconfig index 55a587070342..67f8c2d8fc0e 100644 --- a/arch/powerpc/platforms/52xx/Kconfig +++ b/arch/powerpc/platforms/52xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_MPC52xx bool "52xx-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select COMMON_CLK select PPC_PCI_CHOICE diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig index 1947a88bc69f..1af81de1c4e6 100644 --- a/arch/powerpc/platforms/82xx/Kconfig +++ b/arch/powerpc/platforms/82xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 menuconfig PPC_82xx bool "82xx-based boards (PQ II)" - depends on 6xx + depends on PPC_BOOK3S_32 if PPC_82xx @@ -54,7 +54,7 @@ config PQ2ADS config 8260 bool - depends on 6xx + depends on PPC_BOOK3S_32 select CPM2 help The MPC8260 is a typical embedded CPU made by Freescale. Selecting diff --git a/arch/powerpc/platforms/83xx/Kconfig b/arch/powerpc/platforms/83xx/Kconfig index 071f53b0c0a0..ff0c69dfdf1a 100644 --- a/arch/powerpc/platforms/83xx/Kconfig +++ b/arch/powerpc/platforms/83xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 menuconfig PPC_83xx bool "83xx-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select PPC_UDBG_16550 select PPC_PCI_CHOICE select FSL_PCI if PCI diff --git a/arch/powerpc/platforms/85xx/t1042rdb_diu.c b/arch/powerpc/platforms/85xx/t1042rdb_diu.c index dac36ba82fea..2d1652108ba1 100644 --- a/arch/powerpc/platforms/85xx/t1042rdb_diu.c +++ b/arch/powerpc/platforms/85xx/t1042rdb_diu.c @@ -39,7 +39,7 @@ struct device_node *cpld_node; */ static void t1042rdb_set_monitor_port(enum fsl_diu_monitor_port port) { - static void __iomem *cpld_base; + void __iomem *cpld_base; cpld_base = of_iomap(cpld_node, 0); if (!cpld_base) { diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig index bcd179d3ed92..df692aa6b578 100644 --- a/arch/powerpc/platforms/86xx/Kconfig +++ b/arch/powerpc/platforms/86xx/Kconfig @@ -2,7 +2,7 @@ config PPC_86xx menuconfig PPC_86xx bool "86xx-based boards" - depends on 6xx + depends on PPC_BOOK3S_32 select FSL_SOC select ALTIVEC help diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig index 260a56b7602d..5c48dd823e15 100644 --- a/arch/powerpc/platforms/Kconfig +++ b/arch/powerpc/platforms/Kconfig @@ -40,7 +40,7 @@ config EPAPR_PARAVIRT config PPC_NATIVE bool - depends on 6xx || PPC64 + depends on PPC_BOOK3S_32 || PPC64 help Support for running natively on the hardware, i.e. without a hypervisor. This option is not user-selectable but should @@ -48,7 +48,7 @@ config PPC_NATIVE config PPC_OF_BOOT_TRAMPOLINE bool "Support booting from Open Firmware or yaboot" - depends on 6xx || PPC64 + depends on PPC_BOOK3S_32 || PPC64 default y help Support from booting from Open Firmware or yaboot using an @@ -197,7 +197,7 @@ endmenu config PPC601_SYNC_FIX bool "Workarounds for PPC601 bugs" - depends on 6xx && PPC_PMAC + depends on PPC_BOOK3S_32 && PPC_PMAC help Some versions of the PPC601 (the first PowerPC chip) have bugs which mean that extra synchronization instructions are required near @@ -211,7 +211,7 @@ config PPC601_SYNC_FIX config TAU bool "On-chip CPU temperature sensor support" - depends on 6xx + depends on PPC_BOOK3S_32 help G3 and G4 processors have an on-chip temperature sensor called the 'Thermal Assist Unit (TAU)', which, in theory, can measure the on-die diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index f4e2c5729374..7e130035bbba 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -24,6 +24,7 @@ choice config PPC_BOOK3S_32 bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx" select PPC_FPU + select PPC_HAVE_PMU_SUPPORT config PPC_85xx bool "Freescale 85xx" @@ -179,11 +180,6 @@ config PPC_BOOK3E def_bool y depends on PPC_BOOK3E_64 -config 6xx - def_bool y - depends on PPC32 && PPC_BOOK3S - select PPC_HAVE_PMU_SUPPORT - config E500 select FSL_EMB_PERFMON select PPC_FSL_BOOK3E @@ -266,7 +262,7 @@ config PHYS_64BIT config ALTIVEC bool "AltiVec Support" - depends on 6xx || PPC_BOOK3S_64 || (PPC_E500MC && PPC64) + depends on PPC_BOOK3S_32 || PPC_BOOK3S_64 || (PPC_E500MC && PPC64) ---help--- This option enables kernel support for the Altivec extensions to the PowerPC processor. The kernel currently supports saving and restoring @@ -316,14 +312,6 @@ config SPE If in doubt, say Y here. -config PPC_STD_MMU - def_bool y - depends on PPC_BOOK3S - -config PPC_STD_MMU_32 - def_bool y - depends on PPC_STD_MMU && PPC32 - config ARCH_ENABLE_SPLIT_PMD_PTLOCK def_bool y depends on PPC_BOOK3S_64 @@ -358,7 +346,7 @@ config ARCH_ENABLE_HUGEPAGE_MIGRATION config PPC_MMU_NOHASH def_bool y - depends on !PPC_STD_MMU + depends on !PPC_BOOK3S config PPC_BOOK3E_MMU def_bool y diff --git a/arch/powerpc/platforms/amigaone/Kconfig b/arch/powerpc/platforms/amigaone/Kconfig index 03dc1e37c25b..e03d26d41957 100644 --- a/arch/powerpc/platforms/amigaone/Kconfig +++ b/arch/powerpc/platforms/amigaone/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config AMIGAONE bool "Eyetech AmigaOne/MAI Teron" - depends on 6xx && BROKEN_ON_SMP + depends on PPC_BOOK3S_32 && BROKEN_ON_SMP select PPC_I8259 select PPC_INDIRECT_PCI select PPC_UDBG_16550 diff --git a/arch/powerpc/platforms/cell/cbe_regs.c b/arch/powerpc/platforms/cell/cbe_regs.c index b926438d73af..27ee65b89099 100644 --- a/arch/powerpc/platforms/cell/cbe_regs.c +++ b/arch/powerpc/platforms/cell/cbe_regs.c @@ -53,7 +53,7 @@ static struct cbe_regs_map *cbe_find_map(struct device_node *np) int i; struct device_node *tmp_np; - if (strcasecmp(np->type, "spe")) { + if (!of_node_is_type(np, "spe")) { for (i = 0; i < cbe_regs_map_count; i++) if (cbe_regs_maps[i].cpu_node == np || cbe_regs_maps[i].be_node == np) @@ -70,8 +70,8 @@ static struct cbe_regs_map *cbe_find_map(struct device_node *np) tmp_np = tmp_np->parent; /* on a correct devicetree we wont get up to root */ BUG_ON(!tmp_np); - } while (strcasecmp(tmp_np->type, "cpu") && - strcasecmp(tmp_np->type, "be")); + } while (!of_node_is_type(tmp_np, "cpu") || + !of_node_is_type(tmp_np, "be")); np->data = cbe_find_map(tmp_np); diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c index 7d31b8d14661..902d527d043f 100644 --- a/arch/powerpc/platforms/cell/setup.c +++ b/arch/powerpc/platforms/cell/setup.c @@ -168,8 +168,7 @@ static int __init cell_publish_devices(void) * platform devices for the PCI host bridges */ for_each_child_of_node(root, np) { - if (np->type == NULL || (strcmp(np->type, "pci") != 0 && - strcmp(np->type, "pciex") != 0)) + if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "pciex")) continue; of_platform_device_create(np, NULL, NULL); } diff --git a/arch/powerpc/platforms/chrp/Kconfig b/arch/powerpc/platforms/chrp/Kconfig index ead99eff875a..43a2484aad49 100644 --- a/arch/powerpc/platforms/chrp/Kconfig +++ b/arch/powerpc/platforms/chrp/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config PPC_CHRP bool "Common Hardware Reference Platform (CHRP) based machines" - depends on 6xx + depends on PPC_BOOK3S_32 select HAVE_PCSPKR_PLATFORM select MPIC select PPC_I8259 diff --git a/arch/powerpc/platforms/chrp/pci.c b/arch/powerpc/platforms/chrp/pci.c index 5ddb57b82921..b020c757d2bf 100644 --- a/arch/powerpc/platforms/chrp/pci.c +++ b/arch/powerpc/platforms/chrp/pci.c @@ -230,8 +230,8 @@ chrp_find_bridges(void) else if (strncmp(machine, "Pegasos", 7) == 0) is_pegasos = 1; } - for (dev = root->child; dev != NULL; dev = dev->sibling) { - if (dev->type == NULL || strcmp(dev->type, "pci") != 0) + for_each_child_of_node(root, dev) { + if (!of_node_is_type(dev, "pci")) continue; ++index; /* The GG2 bridge on the LongTrail doesn't have an address */ diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c index d6d8ffc0271e..3c21f046e20c 100644 --- a/arch/powerpc/platforms/chrp/setup.c +++ b/arch/powerpc/platforms/chrp/setup.c @@ -280,10 +280,7 @@ static __init void chrp_init(void) node = of_find_node_by_path(property); if (!node) return; - property = of_get_property(node, "device_type", NULL); - if (!property) - goto out_put; - if (strcmp(property, "serial")) + if (!of_node_is_type(node, "serial")) goto out_put; /* * The 9pin connector is either /failsafe diff --git a/arch/powerpc/platforms/embedded6xx/Kconfig b/arch/powerpc/platforms/embedded6xx/Kconfig index 8ea16db5ff48..527d4aa46537 100644 --- a/arch/powerpc/platforms/embedded6xx/Kconfig +++ b/arch/powerpc/platforms/embedded6xx/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 config EMBEDDED6xx bool "Embedded 6xx/7xx/7xxx-based boards" - depends on 6xx && BROKEN_ON_SMP + depends on PPC_BOOK3S_32 && BROKEN_ON_SMP config LINKSTATION bool "Linkstation / Kurobox(HG) from Buffalo" diff --git a/arch/powerpc/platforms/maple/pci.c b/arch/powerpc/platforms/maple/pci.c index e3821379e86f..13fba004b7e7 100644 --- a/arch/powerpc/platforms/maple/pci.c +++ b/arch/powerpc/platforms/maple/pci.c @@ -604,10 +604,8 @@ void __init maple_pci_init(void) printk(KERN_CRIT "maple_find_bridges: can't find root of device tree\n"); return; } - for (np = NULL; (np = of_get_next_child(root, np)) != NULL;) { - if (!np->type) - continue; - if (strcmp(np->type, "pci") && strcmp(np->type, "ht")) + for_each_child_of_node(root, np) { + if (!of_node_is_type(np, "pci") && !of_node_is_type(np, "ht")) continue; if ((of_device_is_compatible(np, "u4-pcie") || of_device_is_compatible(np, "u3-agp")) && diff --git a/arch/powerpc/platforms/pasemi/dma_lib.c b/arch/powerpc/platforms/pasemi/dma_lib.c index 53384eb42a76..d18d16489a15 100644 --- a/arch/powerpc/platforms/pasemi/dma_lib.c +++ b/arch/powerpc/platforms/pasemi/dma_lib.c @@ -255,15 +255,13 @@ int pasemi_dma_alloc_ring(struct pasemi_dmachan *chan, int ring_size) chan->ring_size = ring_size; - chan->ring_virt = dma_alloc_coherent(&dma_pdev->dev, + chan->ring_virt = dma_zalloc_coherent(&dma_pdev->dev, ring_size * sizeof(u64), &chan->ring_dma, GFP_KERNEL); if (!chan->ring_virt) return -ENOMEM; - memset(chan->ring_virt, 0, ring_size * sizeof(u64)); - return 0; } EXPORT_SYMBOL(pasemi_dma_alloc_ring); diff --git a/arch/powerpc/platforms/powermac/cache.S b/arch/powerpc/platforms/powermac/cache.S index 27862feee4a5..f0641b6e6075 100644 --- a/arch/powerpc/platforms/powermac/cache.S +++ b/arch/powerpc/platforms/powermac/cache.S @@ -28,7 +28,7 @@ */ _GLOBAL(flush_disable_caches) -#ifndef CONFIG_6xx +#ifndef CONFIG_PPC_BOOK3S_32 blr #else BEGIN_FTR_SECTION @@ -356,4 +356,4 @@ END_FTR_SECTION_IFSET(CPU_FTR_L3CR) mtmsr r11 /* restore DR and EE */ isync blr -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ diff --git a/arch/powerpc/platforms/powermac/feature.c b/arch/powerpc/platforms/powermac/feature.c index ed2f54b3f173..bdb3316337b6 100644 --- a/arch/powerpc/platforms/powermac/feature.c +++ b/arch/powerpc/platforms/powermac/feature.c @@ -51,7 +51,7 @@ #define DBG(fmt...) #endif -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 extern int powersave_lowspeed; #endif @@ -1471,6 +1471,7 @@ static long g5_i2s_enable(struct device_node *node, long param, long value) case 2: if (macio->type == macio_shasta) break; + /* fall through */ default: return -ENODEV; } diff --git a/arch/powerpc/platforms/powermac/low_i2c.c b/arch/powerpc/platforms/powermac/low_i2c.c index d4d411820597..84bace3b546a 100644 --- a/arch/powerpc/platforms/powermac/low_i2c.c +++ b/arch/powerpc/platforms/powermac/low_i2c.c @@ -917,10 +917,9 @@ static void __init smu_i2c_probe(void) * type as older device trees mix i2c busses and other things * at the same level */ - for (busnode = NULL; - (busnode = of_get_next_child(controller, busnode)) != NULL;) { - if (strcmp(busnode->type, "i2c") && - strcmp(busnode->type, "i2c-bus")) + for_each_child_of_node(controller, busnode) { + if (!of_node_is_type(busnode, "i2c") && + !of_node_is_type(busnode, "i2c-bus")) continue; reg = of_get_property(busnode, "reg", NULL); if (reg == NULL) diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c index 57bbff465964..5a71395e535e 100644 --- a/arch/powerpc/platforms/powermac/pic.c +++ b/arch/powerpc/platforms/powermac/pic.c @@ -417,7 +417,7 @@ int of_irq_parse_oldworld(struct device_node *device, int index, if (ints != NULL) break; device = device->parent; - if (device && strcmp(device->type, "pci") != 0) + if (!of_node_is_type(device, "pci")) break; } if (ints == NULL) diff --git a/arch/powerpc/platforms/powermac/sleep.S b/arch/powerpc/platforms/powermac/sleep.S index f89808b9713d..fb64b09cad9d 100644 --- a/arch/powerpc/platforms/powermac/sleep.S +++ b/arch/powerpc/platforms/powermac/sleep.S @@ -56,7 +56,7 @@ * vector that will be called by the ROM on wakeup */ _GLOBAL(low_sleep_handler) -#ifndef CONFIG_6xx +#ifndef CONFIG_PPC_BOOK3S_32 blr #else mflr r0 @@ -394,5 +394,5 @@ sleep_storage: .long 0 .balign L1_CACHE_BYTES, 0 -#endif /* CONFIG_6xx */ +#endif /* CONFIG_PPC_BOOK3S_32 */ .section .text diff --git a/arch/powerpc/platforms/powermac/udbg_adb.c b/arch/powerpc/platforms/powermac/udbg_adb.c index 64f38f0d15ed..12158bb4fed7 100644 --- a/arch/powerpc/platforms/powermac/udbg_adb.c +++ b/arch/powerpc/platforms/powermac/udbg_adb.c @@ -194,7 +194,7 @@ int __init udbg_adb_init(int force_btext) */ for_each_node_by_name(np, "keyboard") { struct device_node *parent = of_get_parent(np); - int found = (parent && strcmp(parent->type, "adb") == 0); + int found = of_node_is_type(parent, "adb"); of_node_put(parent); if (found) break; diff --git a/arch/powerpc/platforms/powernv/vas-debug.c b/arch/powerpc/platforms/powernv/vas-debug.c index 4f7276ebdf9c..4d3929fbc08f 100644 --- a/arch/powerpc/platforms/powernv/vas-debug.c +++ b/arch/powerpc/platforms/powernv/vas-debug.c @@ -30,7 +30,7 @@ static char *cop_to_str(int cop) } } -static int info_dbg_show(struct seq_file *s, void *private) +static int info_show(struct seq_file *s, void *private) { struct vas_window *window = s->private; @@ -49,17 +49,7 @@ unlock: return 0; } -static int info_dbg_open(struct inode *inode, struct file *file) -{ - return single_open(file, info_dbg_show, inode->i_private); -} - -static const struct file_operations info_fops = { - .open = info_dbg_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(info); static inline void print_reg(struct seq_file *s, struct vas_window *win, char *name, u32 reg) @@ -67,7 +57,7 @@ static inline void print_reg(struct seq_file *s, struct vas_window *win, seq_printf(s, "0x%016llx %s\n", read_hvwc_reg(win, name, reg), name); } -static int hvwc_dbg_show(struct seq_file *s, void *private) +static int hvwc_show(struct seq_file *s, void *private) { struct vas_window *window = s->private; @@ -115,17 +105,7 @@ unlock: return 0; } -static int hvwc_dbg_open(struct inode *inode, struct file *file) -{ - return single_open(file, hvwc_dbg_show, inode->i_private); -} - -static const struct file_operations hvwc_fops = { - .open = hvwc_dbg_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(hvwc); void vas_window_free_dbgdir(struct vas_window *window) { diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2a983b5a52e1..3b881ac66d9a 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -313,7 +313,6 @@ out: static int pseries_remove_mem_node(struct device_node *np) { - const char *type; const __be32 *regs; unsigned long base; unsigned int lmb_size; @@ -322,8 +321,7 @@ static int pseries_remove_mem_node(struct device_node *np) /* * Check to see if we are actually removing memory */ - type = of_get_property(np, "device_type", NULL); - if (type == NULL || strcmp(type, "memory") != 0) + if (!of_node_is_type(np, "memory")) return 0; /* @@ -936,7 +934,6 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) static int pseries_add_mem_node(struct device_node *np) { - const char *type; const __be32 *regs; unsigned long base; unsigned int lmb_size; @@ -945,8 +942,7 @@ static int pseries_add_mem_node(struct device_node *np) /* * Check to see if we are actually adding memory */ - type = of_get_property(np, "device_type", NULL); - if (type == NULL || strcmp(type, "memory") != 0) + if (!of_node_is_type(np, "memory")) return 0; /* diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index 0f553dcfa548..4078a05fa5c0 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -469,8 +469,8 @@ static void __init find_and_init_phbs(void) struct device_node *root = of_find_node_by_path("/"); for_each_child_of_node(root, node) { - if (node->type == NULL || (strcmp(node->type, "pci") != 0 && - strcmp(node->type, "pciex") != 0)) + if (!of_node_is_type(node, "pci") && + !of_node_is_type(node, "pciex")) continue; phb = pcibios_alloc_controller(node); @@ -978,11 +978,7 @@ static void pseries_power_off(void) static int __init pSeries_probe(void) { - const char *dtype = of_get_property(of_root, "device_type", NULL); - - if (dtype == NULL) - return 0; - if (strcmp(dtype, "chrp")) + if (!of_node_is_type(of_root, "chrp")) return 0; /* Cell blades firmware claims to be chrp while it's not. Until this diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c index 88f1ad1d6309..93cc9eec6601 100644 --- a/arch/powerpc/platforms/pseries/vio.c +++ b/arch/powerpc/platforms/pseries/vio.c @@ -1356,9 +1356,9 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) */ parent_node = of_get_parent(of_node); if (parent_node) { - if (!strcmp(parent_node->type, "ibm,platform-facilities")) + if (of_node_is_type(parent_node, "ibm,platform-facilities")) family = PFO; - else if (!strcmp(parent_node->type, "vdevice")) + else if (of_node_is_type(parent_node, "vdevice")) family = VDEVICE; else { pr_warn("%s: parent(%pOF) of %pOFn not recognized.\n", @@ -1395,9 +1395,8 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node) if (viodev->family == VDEVICE) { unsigned int unit_address; - if (of_node->type != NULL) - viodev->type = of_node->type; - else { + viodev->type = of_node_get_device_type(of_node); + if (!viodev->type) { pr_warn("%s: node %pOFn is missing the 'device_type' " "property.\n", __func__, of_node); goto out; @@ -1672,32 +1671,30 @@ struct vio_dev *vio_find_node(struct device_node *vnode) { char kobj_name[20]; struct device_node *vnode_parent; - const char *dev_type; vnode_parent = of_get_parent(vnode); if (!vnode_parent) return NULL; - dev_type = of_get_property(vnode_parent, "device_type", NULL); - of_node_put(vnode_parent); - if (!dev_type) - return NULL; - /* construct the kobject name from the device node */ - if (!strcmp(dev_type, "vdevice")) { + if (of_node_is_type(vnode_parent, "vdevice")) { const __be32 *prop; prop = of_get_property(vnode, "reg", NULL); if (!prop) - return NULL; + goto out; snprintf(kobj_name, sizeof(kobj_name), "%x", (uint32_t)of_read_number(prop, 1)); - } else if (!strcmp(dev_type, "ibm,platform-facilities")) + } else if (of_node_is_type(vnode_parent, "ibm,platform-facilities")) snprintf(kobj_name, sizeof(kobj_name), "%pOFn", vnode); else - return NULL; + goto out; + of_node_put(vnode_parent); return vio_find_name(kobj_name); +out: + of_node_put(vnode_parent); + return NULL; } EXPORT_SYMBOL(vio_find_node); diff --git a/arch/powerpc/sysdev/Makefile b/arch/powerpc/sysdev/Makefile index 2caa4defdfb6..aaf23283ba0c 100644 --- a/arch/powerpc/sysdev/Makefile +++ b/arch/powerpc/sysdev/Makefile @@ -48,7 +48,7 @@ obj-$(CONFIG_PPC_MPC512x) += mpc5xxx_clocks.o obj-$(CONFIG_PPC_MPC52xx) += mpc5xxx_clocks.o ifdef CONFIG_SUSPEND -obj-$(CONFIG_6xx) += 6xx-suspend.o +obj-$(CONFIG_PPC_BOOK3S_32) += 6xx-suspend.o endif obj-$(CONFIG_PPC_SCOM) += scom.o diff --git a/arch/powerpc/sysdev/scom.c b/arch/powerpc/sysdev/scom.c index 0f6fd5d04d33..a707b24a7ddb 100644 --- a/arch/powerpc/sysdev/scom.c +++ b/arch/powerpc/sysdev/scom.c @@ -60,7 +60,7 @@ scom_map_t scom_map_device(struct device_node *dev, int index) parent = scom_find_parent(dev); if (parent == NULL) - return 0; + return NULL; /* * We support "scom-reg" properties for adding scom registers @@ -83,7 +83,7 @@ scom_map_t scom_map_device(struct device_node *dev, int index) size >>= 2; if (index >= (size / (2*cells))) - return 0; + return NULL; reg = of_read_number(&prop[index * cells * 2], cells); cnt = of_read_number(&prop[index * cells * 2 + cells], cells); diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c index 9824074ec1b5..94a69a62f5db 100644 --- a/arch/powerpc/sysdev/xive/common.c +++ b/arch/powerpc/sysdev/xive/common.c @@ -309,7 +309,7 @@ static void xive_do_queue_eoi(struct xive_cpu *xc) * EOI an interrupt at the source. There are several methods * to do this depending on the HW version and source type */ -void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) +static void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd) { /* If the XIVE supports the new "store EOI facility, use it */ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI) diff --git a/arch/powerpc/tools/checkpatch.sh b/arch/powerpc/tools/checkpatch.sh index 1fad3fb90e7c..3ce5c093b19d 100755 --- a/arch/powerpc/tools/checkpatch.sh +++ b/arch/powerpc/tools/checkpatch.sh @@ -19,4 +19,5 @@ exec $script_base/../../../scripts/checkpatch.pl \ --ignore GLOBAL_INITIALISERS \ --ignore LINE_SPACING \ --ignore MULTIPLE_ASSIGNMENTS \ + --ignore DT_SPLIT_BINDING_PATCH \ $@ diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index 36b8dc47a3c3..372f4d80bcd6 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -75,6 +75,9 @@ static int xmon_gate; #define xmon_owner 0 #endif /* CONFIG_SMP */ +#ifdef CONFIG_PPC_PSERIES +static int set_indicator_token = RTAS_UNKNOWN_SERVICE; +#endif static unsigned long in_xmon __read_mostly = 0; static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT); @@ -273,7 +276,7 @@ Commands:\n\ X exit monitor and don't recover\n" #if defined(CONFIG_PPC64) && !defined(CONFIG_PPC_BOOK3E) " u dump segment table or SLB\n" -#elif defined(CONFIG_PPC_STD_MMU_32) +#elif defined(CONFIG_PPC_BOOK3S_32) " u dump segment registers\n" #elif defined(CONFIG_44x) || defined(CONFIG_PPC_BOOK3E) " u dump TLB\n" @@ -358,7 +361,6 @@ static inline void disable_surveillance(void) #ifdef CONFIG_PPC_PSERIES /* Since this can't be a module, args should end up below 4GB. */ static struct rtas_args args; - int token; /* * At this point we have got all the cpus we can into @@ -367,11 +369,11 @@ static inline void disable_surveillance(void) * If we did try to take rtas.lock there would be a * real possibility of deadlock. */ - token = rtas_token("set-indicator"); - if (token == RTAS_UNKNOWN_SERVICE) + if (set_indicator_token == RTAS_UNKNOWN_SERVICE) return; - rtas_call_unlocked(&args, token, 3, 1, NULL, SURVEILLANCE_TOKEN, 0, 0); + rtas_call_unlocked(&args, set_indicator_token, 3, 1, NULL, + SURVEILLANCE_TOKEN, 0, 0); #endif /* CONFIG_PPC_PSERIES */ } @@ -1058,7 +1060,7 @@ cmds(struct pt_regs *excp) case 'P': show_tasks(); break; -#ifdef CONFIG_PPC_STD_MMU +#ifdef CONFIG_PPC_BOOK3S case 'u': dump_segments(); break; @@ -2793,7 +2795,7 @@ print_address(unsigned long addr) xmon_print_symbol(addr, "\t# ", ""); } -void +static void dump_log_buf(void) { struct kmsg_dumper dumper = { .active = 1 }; @@ -2994,13 +2996,13 @@ static void show_task(struct task_struct *tsk) printf("%px %016lx %6d %6d %c %2d %s\n", tsk, tsk->thread.ksp, - tsk->pid, tsk->parent->pid, + tsk->pid, rcu_dereference(tsk->parent)->pid, state, task_thread_info(tsk)->cpu, tsk->comm); } #ifdef CONFIG_PPC_BOOK3S_64 -void format_pte(void *ptep, unsigned long pte) +static void format_pte(void *ptep, unsigned long pte) { pte_t entry = __pte(pte); @@ -3495,7 +3497,7 @@ void dump_segments(void) } #endif -#ifdef CONFIG_PPC_STD_MMU_32 +#ifdef CONFIG_PPC_BOOK3S_32 void dump_segments(void) { int i; @@ -3688,6 +3690,14 @@ static void xmon_init(int enable) __debugger_iabr_match = xmon_iabr_match; __debugger_break_match = xmon_break_match; __debugger_fault_handler = xmon_fault_handler; + +#ifdef CONFIG_PPC_PSERIES + /* + * Get the token here to avoid trying to get a lock + * during the crash, causing a deadlock. + */ + set_indicator_token = rtas_token("set-indicator"); +#endif } else { __debugger = NULL; __debugger_ipi = NULL; @@ -4033,6 +4043,7 @@ static int do_spu_cmd(void) subcmd = inchar(); if (isxdigit(subcmd) || subcmd == '\n') termch = subcmd; + /* fall through */ case 'f': scanhex(&num); if (num >= XMON_NUM_SPUS || !spu_info[num].spu) { diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 0b33577932c3..e21053e5e0da 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -27,7 +27,7 @@ KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g) KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,)) UTS_MACHINE := s390x -STACK_SIZE := $(if $(CONFIG_KASAN),32768,16384) +STACK_SIZE := $(if $(CONFIG_KASAN),65536,16384) CHECKFLAGS += -D__s390__ -D__s390x__ export LD_BFD diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile index 593039620487..b1bdd15e3429 100644 --- a/arch/s390/boot/compressed/Makefile +++ b/arch/s390/boot/compressed/Makefile @@ -22,10 +22,10 @@ OBJCOPYFLAGS := OBJECTS := $(addprefix $(obj)/,$(obj-y)) LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T -$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) +$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS) FORCE $(call if_changed,ld) -OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info +OBJCOPYFLAGS_info.bin := -O binary --only-section=.vmlinux.info --set-section-flags .vmlinux.info=load $(obj)/info.bin: vmlinux FORCE $(call if_changed,objcopy) @@ -46,17 +46,17 @@ suffix-$(CONFIG_KERNEL_LZMA) := .lzma suffix-$(CONFIG_KERNEL_LZO) := .lzo suffix-$(CONFIG_KERNEL_XZ) := .xz -$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE $(call if_changed,gzip) -$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE $(call if_changed,bzip2) -$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE $(call if_changed,lz4) -$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzma) -$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE $(call if_changed,lzo) -$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) +$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE $(call if_changed,xzkern) OBJCOPYFLAGS_piggy.o := -I binary -O elf64-s390 -B s390:64-bit --rename-section .data=.vmlinux.bin.compressed diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 259d1698ac50..c69cb04b7a59 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -64,6 +64,8 @@ CONFIG_NUMA=y CONFIG_PREEMPT=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -84,9 +86,11 @@ CONFIG_PCI_DEBUG=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -161,8 +165,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -365,6 +367,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -461,6 +465,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -486,9 +491,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -615,7 +623,6 @@ CONFIG_DEBUG_CREDENTIALS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=300 CONFIG_NOTIFIER_ERROR_INJECTION=m -CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_NETDEV_NOTIFIER_ERROR_INJECT=m CONFIG_FAULT_INJECTION=y CONFIG_FAILSLAB=y @@ -727,3 +734,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 37fd60c20e22..32f539dc9c19 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -65,6 +65,8 @@ CONFIG_NR_CPUS=512 CONFIG_NUMA=y CONFIG_HZ_100=y CONFIG_KEXEC_FILE=y +CONFIG_EXPOLINE=y +CONFIG_EXPOLINE_AUTO=y CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -82,9 +84,11 @@ CONFIG_PCI=y CONFIG_HOTPLUG_PCI=y CONFIG_HOTPLUG_PCI_S390=y CONFIG_CHSC_SCH=y +CONFIG_VFIO_AP=m CONFIG_CRASH_DUMP=y CONFIG_BINFMT_MISC=m CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=m @@ -159,8 +163,6 @@ CONFIG_NF_CONNTRACK_TFTP=m CONFIG_NF_CT_NETLINK=m CONFIG_NF_CT_NETLINK_TIMEOUT=m CONFIG_NF_TABLES=m -CONFIG_NFT_EXTHDR=m -CONFIG_NFT_META=m CONFIG_NFT_CT=m CONFIG_NFT_COUNTER=m CONFIG_NFT_LOG=m @@ -362,6 +364,8 @@ CONFIG_NET_ACT_SKBEDIT=m CONFIG_NET_ACT_CSUM=m CONFIG_DNS_RESOLVER=y CONFIG_OPENVSWITCH=m +CONFIG_VSOCKETS=m +CONFIG_VIRTIO_VSOCKETS=m CONFIG_NETLINK_DIAG=m CONFIG_CGROUP_NET_PRIO=y CONFIG_BPF_JIT=y @@ -458,6 +462,7 @@ CONFIG_PPTP=m CONFIG_PPPOL2TP=m CONFIG_PPP_ASYNC=m CONFIG_PPP_SYNC_TTY=m +CONFIG_ISM=m CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set @@ -483,9 +488,12 @@ CONFIG_MLX4_INFINIBAND=m CONFIG_MLX5_INFINIBAND=m CONFIG_VFIO=m CONFIG_VFIO_PCI=m +CONFIG_VFIO_MDEV=m +CONFIG_VFIO_MDEV_DEVICE=m CONFIG_VIRTIO_PCI=m CONFIG_VIRTIO_BALLOON=m CONFIG_VIRTIO_INPUT=y +CONFIG_S390_AP_IOMMU=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_EXT4_FS_SECURITY=y @@ -666,3 +674,4 @@ CONFIG_APPLDATA_BASE=y CONFIG_KVM=m CONFIG_KVM_S390_UCONTROL=y CONFIG_VHOST_NET=m +CONFIG_VHOST_VSOCK=m diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 7cb6a52f727d..4d58a92b5d97 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -26,14 +26,23 @@ CONFIG_CGROUP_CPUACCT=y CONFIG_CGROUP_PERF=y CONFIG_NAMESPACES=y CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y # CONFIG_SYSFS_SYSCALL is not set -CONFIG_CHECKPOINT_RESTORE=y CONFIG_BPF_SYSCALL=y CONFIG_USERFAULTFD=y # CONFIG_COMPAT_BRK is not set CONFIG_PROFILING=y +CONFIG_LIVEPATCH=y +CONFIG_NR_CPUS=256 +CONFIG_NUMA=y +CONFIG_HZ_100=y +CONFIG_KEXEC_FILE=y +CONFIG_CRASH_DUMP=y +CONFIG_HIBERNATION=y +CONFIG_PM_DEBUG=y +CONFIG_CMM=m CONFIG_OPROFILE=y CONFIG_KPROBES=y CONFIG_JUMP_LABEL=y @@ -44,11 +53,7 @@ CONFIG_BLK_DEV_INTEGRITY=y CONFIG_PARTITION_ADVANCED=y CONFIG_IBM_PARTITION=y CONFIG_DEFAULT_DEADLINE=y -CONFIG_LIVEPATCH=y -CONFIG_NR_CPUS=256 -CONFIG_NUMA=y -CONFIG_HZ_100=y -CONFIG_KEXEC_FILE=y +CONFIG_BINFMT_MISC=m CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y @@ -60,9 +65,6 @@ CONFIG_ZBUD=m CONFIG_ZSMALLOC=m CONFIG_ZSMALLOC_STAT=y CONFIG_IDLE_PAGE_TRACKING=y -CONFIG_CRASH_DUMP=y -CONFIG_BINFMT_MISC=m -CONFIG_HIBERNATION=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -98,6 +100,7 @@ CONFIG_BLK_DEV_NBD=m CONFIG_BLK_DEV_RAM=y CONFIG_VIRTIO_BLK=y CONFIG_SCSI=y +# CONFIG_SCSI_MQ_DEFAULT is not set CONFIG_BLK_DEV_SD=y CONFIG_CHR_DEV_ST=y CONFIG_BLK_DEV_SR=y @@ -131,6 +134,7 @@ CONFIG_EQUALIZER=m CONFIG_TUN=m CONFIG_VIRTIO_NET=y # CONFIG_NET_VENDOR_ALACRITECH is not set +# CONFIG_NET_VENDOR_AURORA is not set # CONFIG_NET_VENDOR_CORTINA is not set # CONFIG_NET_VENDOR_SOLARFLARE is not set # CONFIG_NET_VENDOR_SOCIONEXT is not set @@ -157,33 +161,6 @@ CONFIG_TMPFS=y CONFIG_TMPFS_POSIX_ACL=y CONFIG_HUGETLBFS=y # CONFIG_NETWORK_FILESYSTEMS is not set -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_INFO_DWARF4=y -CONFIG_GDB_SCRIPTS=y -CONFIG_UNUSED_SYMBOLS=y -CONFIG_DEBUG_SECTION_MISMATCH=y -CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y -CONFIG_MAGIC_SYSRQ=y -CONFIG_DEBUG_PAGEALLOC=y -CONFIG_DETECT_HUNG_TASK=y -CONFIG_PANIC_ON_OOPS=y -CONFIG_PROVE_LOCKING=y -CONFIG_LOCK_STAT=y -CONFIG_DEBUG_LOCKDEP=y -CONFIG_DEBUG_ATOMIC_SLEEP=y -CONFIG_DEBUG_LIST=y -CONFIG_DEBUG_SG=y -CONFIG_DEBUG_NOTIFIERS=y -CONFIG_RCU_CPU_STALL_TIMEOUT=60 -CONFIG_LATENCYTOP=y -CONFIG_SCHED_TRACER=y -CONFIG_FTRACE_SYSCALLS=y -CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y -CONFIG_STACK_TRACER=y -CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_FUNCTION_PROFILER=y -# CONFIG_RUNTIME_TESTING_MENU is not set -CONFIG_S390_PTDUMP=y CONFIG_CRYPTO_CRYPTD=m CONFIG_CRYPTO_AUTHENC=m CONFIG_CRYPTO_TEST=m @@ -193,6 +170,7 @@ CONFIG_CRYPTO_CBC=y CONFIG_CRYPTO_CFB=m CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m +CONFIG_CRYPTO_OFB=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m CONFIG_CRYPTO_CMAC=m @@ -231,7 +209,6 @@ CONFIG_CRYPTO_USER_API_HASH=m CONFIG_CRYPTO_USER_API_SKCIPHER=m CONFIG_CRYPTO_USER_API_RNG=m CONFIG_ZCRYPT=m -CONFIG_ZCRYPT_MULTIDEVNODES=y CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_SHA1_S390=m @@ -247,4 +224,30 @@ CONFIG_CRC7=m # CONFIG_XZ_DEC_ARM is not set # CONFIG_XZ_DEC_ARMTHUMB is not set # CONFIG_XZ_DEC_SPARC is not set -CONFIG_CMM=m +CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF4=y +CONFIG_GDB_SCRIPTS=y +CONFIG_UNUSED_SYMBOLS=y +CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_PAGEALLOC=y +CONFIG_DETECT_HUNG_TASK=y +CONFIG_PANIC_ON_OOPS=y +CONFIG_PROVE_LOCKING=y +CONFIG_LOCK_STAT=y +CONFIG_DEBUG_LOCKDEP=y +CONFIG_DEBUG_ATOMIC_SLEEP=y +CONFIG_DEBUG_LIST=y +CONFIG_DEBUG_SG=y +CONFIG_DEBUG_NOTIFIERS=y +CONFIG_RCU_CPU_STALL_TIMEOUT=60 +CONFIG_LATENCYTOP=y +CONFIG_SCHED_TRACER=y +CONFIG_FTRACE_SYSCALLS=y +CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y +CONFIG_STACK_TRACER=y +CONFIG_BLK_DEV_IO_TRACE=y +CONFIG_FUNCTION_PROFILER=y +# CONFIG_RUNTIME_TESTING_MENU is not set +CONFIG_S390_PTDUMP=y diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index dbd689d556ce..ccbb53e22024 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -46,8 +46,6 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.asce_limit = STACK_TOP_MAX; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION3; - /* pgd_alloc() did not account this pud */ - mm_inc_nr_puds(mm); break; case -PAGE_SIZE: /* forked 5-level task, set new asce with new_mm->pgd */ @@ -63,9 +61,6 @@ static inline int init_new_context(struct task_struct *tsk, /* forked 2-level compat task, set new asce with new mm->pgd */ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_SEGMENT; - /* pgd_alloc() did not account this pmd */ - mm_inc_nr_pmds(mm); - mm_inc_nr_puds(mm); } crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index f0f9bcf94c03..5ee733720a57 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -36,11 +36,11 @@ static inline void crst_table_init(unsigned long *crst, unsigned long entry) static inline unsigned long pgd_entry_type(struct mm_struct *mm) { - if (mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(mm)) return _SEGMENT_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(mm)) return _REGION3_ENTRY_EMPTY; - if (mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(mm)) return _REGION2_ENTRY_EMPTY; return _REGION1_ENTRY_EMPTY; } diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 411d435e7a7d..063732414dfb 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -493,6 +493,24 @@ static inline int is_module_addr(void *addr) _REGION_ENTRY_PROTECT | \ _REGION_ENTRY_NOEXEC) +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION1_SIZE; +} +#define mm_p4d_folded(mm) mm_p4d_folded(mm) + +static inline bool mm_pud_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION2_SIZE; +} +#define mm_pud_folded(mm) mm_pud_folded(mm) + +static inline bool mm_pmd_folded(struct mm_struct *mm) +{ + return mm->context.asce_limit <= _REGION3_SIZE; +} +#define mm_pmd_folded(mm) mm_pmd_folded(mm) + static inline int mm_has_pgste(struct mm_struct *mm) { #ifdef CONFIG_PGSTE diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 302795c47c06..81038ab357ce 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -236,7 +236,7 @@ static inline unsigned long current_stack_pointer(void) return sp; } -static __no_sanitize_address_or_inline unsigned short stap(void) +static __no_kasan_or_inline unsigned short stap(void) { unsigned short cpu_address; @@ -330,7 +330,7 @@ static inline void __load_psw(psw_t psw) * Set PSW mask to specified value, while leaving the * PSW addr pointing to the next instruction. */ -static __no_sanitize_address_or_inline void __load_psw_mask(unsigned long mask) +static __no_kasan_or_inline void __load_psw_mask(unsigned long mask) { unsigned long addr; psw_t psw; diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 27248f42a03c..ce4e17c9aad6 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -14,7 +14,7 @@ * General size of kernel stacks */ #ifdef CONFIG_KASAN -#define THREAD_SIZE_ORDER 3 +#define THREAD_SIZE_ORDER 4 #else #define THREAD_SIZE_ORDER 2 #endif diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 457b7ba0fbb6..b31c779cf581 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -136,7 +136,7 @@ static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION3_SIZE) + if (mm_pmd_folded(tlb->mm)) return; pgtable_pmd_page_dtor(virt_to_page(pmd)); tlb_remove_table(tlb, pmd); @@ -152,7 +152,7 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION1_SIZE) + if (mm_p4d_folded(tlb->mm)) return; tlb_remove_table(tlb, p4d); } @@ -167,7 +167,7 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, unsigned long address) { - if (tlb->mm->context.asce_limit <= _REGION2_SIZE) + if (mm_pud_folded(tlb->mm)) return; tlb_remove_table(tlb, pud); } diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 724fba4d09d2..39191a0feed1 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -236,10 +236,10 @@ ENTRY(__switch_to) stmg %r6,%r15,__SF_GPRS(%r15) # store gprs of prev task lghi %r4,__TASK_stack lghi %r1,__TASK_thread - lg %r5,0(%r4,%r3) # start of kernel stack of next + llill %r5,STACK_INIT stg %r15,__THREAD_ksp(%r1,%r2) # store kernel stack of prev - lgr %r15,%r5 - aghi %r15,STACK_INIT # end of kernel stack of next + lg %r15,0(%r4,%r3) # start of kernel stack of next + agr %r15,%r5 # end of kernel stack of next stg %r3,__LC_CURRENT # store task struct of next stg %r15,__LC_KERNEL_STACK # store end of kernel stack lg %r15,__THREAD_ksp(%r1,%r3) # load kernel stack of next diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index cc085e2d2ce9..74091fd3101e 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -373,7 +373,7 @@ static int __hw_perf_event_init(struct perf_event *event) return -ENOENT; if (ev > PERF_CPUM_CF_MAX_CTR) - return -EINVAL; + return -ENOENT; /* Obtain the counter set to which the specified counter belongs */ set = get_counter_set(ev); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 7bf604ff50a1..bfabeb1889cc 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1842,10 +1842,30 @@ static void cpumsf_pmu_del(struct perf_event *event, int flags) CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC, PERF_EVENT_CPUM_SF); CPUMF_EVENT_ATTR(SF, SF_CYCLES_BASIC_DIAG, PERF_EVENT_CPUM_SF_DIAG); -static struct attribute *cpumsf_pmu_events_attr[] = { - CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC), - NULL, - NULL, +/* Attribute list for CPU_SF. + * + * The availablitiy depends on the CPU_MF sampling facility authorization + * for basic + diagnositic samples. This is determined at initialization + * time by the sampling facility device driver. + * If the authorization for basic samples is turned off, it should be + * also turned off for diagnostic sampling. + * + * During initialization of the device driver, check the authorization + * level for diagnostic sampling and installs the attribute + * file for diagnostic sampling if necessary. + * + * For now install a placeholder to reference all possible attributes: + * SF_CYCLES_BASIC and SF_CYCLES_BASIC_DIAG. + * Add another entry for the final NULL pointer. + */ +enum { + SF_CYCLES_BASIC_ATTR_IDX = 0, + SF_CYCLES_BASIC_DIAG_ATTR_IDX, + SF_CYCLES_ATTR_MAX +}; + +static struct attribute *cpumsf_pmu_events_attr[SF_CYCLES_ATTR_MAX + 1] = { + [SF_CYCLES_BASIC_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC) }; PMU_FORMAT_ATTR(event, "config:0-63"); @@ -2040,7 +2060,10 @@ static int __init init_cpum_sampling_pmu(void) if (si.ad) { sfb_set_limits(CPUM_SF_MIN_SDB, CPUM_SF_MAX_SDB); - cpumsf_pmu_events_attr[1] = + /* Sampling of diagnostic data authorized, + * install event into attribute list of PMU device. + */ + cpumsf_pmu_events_attr[SF_CYCLES_BASIC_DIAG_ATTR_IDX] = CPUMF_EVENT_PTR(SF, SF_CYCLES_BASIC_DIAG); } diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index eb8aebea3ea7..e76309fbbcb3 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index a22b2cf86eec..f849ac61c5da 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -37,7 +37,7 @@ KASAN_SANITIZE := n $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -46,12 +46,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $(filter %.lds %.o,$^) -o $@ quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 21eb7407d51b..8429ab079715 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -154,14 +154,14 @@ SECTIONS * uncompressed image info used by the decompressor * it should match struct vmlinux_info */ - .vmlinux.info 0 : { + .vmlinux.info 0 (INFO) : { QUAD(_stext) /* default_lma */ QUAD(startup_continue) /* entry */ QUAD(__bss_start - _stext) /* image_size */ QUAD(__bss_stop - __bss_start) /* bss_size */ QUAD(__boot_data_start) /* bootdata_off */ QUAD(__boot_data_end - __boot_data_start) /* bootdata_size */ - } + } :NONE /* Debugging sections. */ STABS_DEBUG diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c index 76d89ee8b428..814f26520aa2 100644 --- a/arch/s390/mm/pgalloc.c +++ b/arch/s390/mm/pgalloc.c @@ -101,6 +101,7 @@ int crst_table_upgrade(struct mm_struct *mm, unsigned long end) mm->context.asce_limit = _REGION1_SIZE; mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION2; + mm_inc_nr_puds(mm); } else { crst_table_init(table, _REGION1_ENTRY_EMPTY); pgd_populate(mm, (pgd_t *) table, (p4d_t *) pgd); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index ae0d9e889534..d31bde0870d8 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -53,6 +53,7 @@ int __node_distance(int a, int b) { return mode->distance ? mode->distance(a, b) : 0; } +EXPORT_SYMBOL(__node_distance); int numa_debug_enabled; diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 74c002ddc0ce..28c40624bcb6 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1305,6 +1305,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->fds[0] = dev->cow.fd; else io_req->fds[0] = dev->fd; + io_req->error = 0; if (req_op(req) == REQ_OP_FLUSH) { io_req->op = UBD_FLUSH; @@ -1313,9 +1314,7 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, io_req->cow_offset = -1; io_req->offset = off; io_req->length = bvec->bv_len; - io_req->error = 0; io_req->sector_mask = 0; - io_req->op = rq_data_dir(req) == READ ? UBD_READ : UBD_WRITE; io_req->offsets[0] = 0; io_req->offsets[1] = dev->cow.data_offset; @@ -1341,11 +1340,14 @@ static int ubd_queue_one_vec(struct blk_mq_hw_ctx *hctx, struct request *req, static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { + struct ubd *ubd_dev = hctx->queue->queuedata; struct request *req = bd->rq; int ret = 0; blk_mq_start_request(req); + spin_lock_irq(&ubd_dev->lock); + if (req_op(req) == REQ_OP_FLUSH) { ret = ubd_queue_one_vec(hctx, req, 0, NULL); } else { @@ -1361,9 +1363,11 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx, } } out: - if (ret < 0) { + spin_unlock_irq(&ubd_dev->lock); + + if (ret < 0) blk_mq_requeue_request(req, true); - } + return BLK_STS_OK; } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ba7e3464ee92..9d734f3c8234 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -525,7 +525,6 @@ config X86_VSMP bool "ScaleMP vSMP" select HYPERVISOR_GUEST select PARAVIRT - select PARAVIRT_XXL depends on X86_64 && PCI depends on X86_EXTENDED_PLATFORM depends on SMP diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5b562e464009..88398fdf8129 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -213,8 +213,6 @@ ifdef CONFIG_X86_64 KBUILD_LDFLAGS += $(call ld-option, -z max-page-size=0x200000) endif -# Speed up the build -KBUILD_CFLAGS += -pipe # Workaround for a gcc prelease that unfortunately was shipped in a suse release KBUILD_CFLAGS += -Wno-sign-compare # @@ -239,7 +237,7 @@ archheaders: archmacros: $(Q)$(MAKE) $(build)=arch/x86/kernel arch/x86/kernel/macros.s -ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s -Wa,- +ASM_MACRO_FLAGS = -Wa,arch/x86/kernel/macros.s export ASM_MACRO_FLAGS KBUILD_CFLAGS += $(ASM_MACRO_FLAGS) diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4da9b1c58d28..c1a812bd5a27 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -221,6 +221,8 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); +bool mce_is_correctable(struct mce *m); +int mce_usable_address(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 0d6271cce198..1d0a7778e163 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -232,7 +232,7 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) : "cc"); } #endif - return hv_status; + return hv_status; } /* diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index cd0cf1c568b4..8f657286d599 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -33,12 +33,14 @@ /* * Set __PAGE_OFFSET to the most negative possible address + - * PGDIR_SIZE*16 (pgd slot 272). The gap is to allow a space for a - * hypervisor to fit. Choosing 16 slots here is arbitrary, but it's - * what Xen requires. + * PGDIR_SIZE*17 (pgd slot 273). + * + * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for + * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary, + * but it's what Xen requires. */ -#define __PAGE_OFFSET_BASE_L5 _AC(0xff10000000000000, UL) -#define __PAGE_OFFSET_BASE_L4 _AC(0xffff880000000000, UL) +#define __PAGE_OFFSET_BASE_L5 _AC(0xff11000000000000, UL) +#define __PAGE_OFFSET_BASE_L4 _AC(0xffff888000000000, UL) #ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT #define __PAGE_OFFSET page_offset_base diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 04edd2d58211..84bd9bdc1987 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -111,9 +111,7 @@ extern unsigned int ptrs_per_p4d; */ #define MAXMEM (1UL << MAX_PHYSMEM_BITS) -#define LDT_PGD_ENTRY_L4 -3UL -#define LDT_PGD_ENTRY_L5 -112UL -#define LDT_PGD_ENTRY (pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4) +#define LDT_PGD_ENTRY -240UL #define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) #define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index 87623c6b13db..bd5ac6cc37db 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -13,12 +13,15 @@ #define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) { - u32 val = 0; - - if (GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, - "I", _Q_PENDING_OFFSET)) - val |= _Q_PENDING_VAL; + u32 val; + /* + * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto + * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a + * statement expression, which GCC doesn't like. + */ + val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, + "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL; val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK; return val; diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 123e669bf363..790ce08e41f2 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -9,7 +9,7 @@ #include <linux/mm.h> #include <linux/device.h> -#include <linux/uaccess.h> +#include <asm/extable.h> #include <asm/page.h> #include <asm/pgtable.h> @@ -93,12 +93,39 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, */ static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val) { - return __put_user(val, (unsigned long __user *)addr); + int ret = 0; + + asm volatile("1: mov %[val], %[ptr]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [ptr] "=m" (*addr) + : [val] "r" (val)); + + return ret; } -static inline int xen_safe_read_ulong(unsigned long *addr, unsigned long *val) +static inline int xen_safe_read_ulong(const unsigned long *addr, + unsigned long *val) { - return __get_user(*val, (unsigned long __user *)addr); + int ret = 0; + unsigned long rval = ~0ul; + + asm volatile("1: mov %[ptr], %[rval]\n" + "2:\n" + ".section .fixup, \"ax\"\n" + "3: sub $1, %[ret]\n" + " jmp 2b\n" + ".previous\n" + _ASM_EXTABLE(1b, 3b) + : [ret] "+r" (ret), [rval] "+r" (rval) + : [ptr] "m" (*addr)); + *val = rval; + + return ret; } #ifdef CONFIG_XEN_PV diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 8c66d2fc8f81..36d2696c9563 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -485,7 +485,7 @@ static void mce_report_event(struct pt_regs *regs) * be somewhat complicated (e.g. segment offset would require an instruction * parser). So only support physical addresses up to page granuality for now. */ -static int mce_usable_address(struct mce *m) +int mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_ADDRV)) return 0; @@ -505,6 +505,7 @@ static int mce_usable_address(struct mce *m) return 1; } +EXPORT_SYMBOL_GPL(mce_usable_address); bool mce_is_memory_error(struct mce *m) { @@ -534,7 +535,7 @@ bool mce_is_memory_error(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_memory_error); -static bool mce_is_correctable(struct mce *m) +bool mce_is_correctable(struct mce *m) { if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) return false; @@ -547,6 +548,7 @@ static bool mce_is_correctable(struct mce *m) return true; } +EXPORT_SYMBOL_GPL(mce_is_correctable); static bool cec_add_mce(struct mce *m) { diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 1c72f3819eb1..e81a2db42df7 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -20,6 +20,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kexec.h> +#include <linux/i8253.h> #include <asm/processor.h> #include <asm/hypervisor.h> #include <asm/hyperv-tlfs.h> @@ -295,6 +296,16 @@ static void __init ms_hyperv_init_platform(void) if (efi_enabled(EFI_BOOT)) x86_platform.get_nmi_reason = hv_get_nmi_reason; + /* + * Hyper-V VMs have a PIT emulation quirk such that zeroing the + * counter register during PIT shutdown restarts the PIT. So it + * continues to interrupt @18.2 HZ. Setting i8253_clear_counter + * to false tells pit_shutdown() not to zero the counter so that + * the PIT really is shutdown. Generation 2 VMs don't have a PIT, + * and setting this value has no effect. + */ + i8253_clear_counter_on_shutdown = false; + #if IS_ENABLED(CONFIG_HYPERV) /* * Setup the hook to get control post apic initialization. diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index d9ab49bed8af..0eda91f8eeac 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -77,7 +77,7 @@ static __init int setup_vmw_sched_clock(char *s) } early_param("no-vmw-sched-clock", setup_vmw_sched_clock); -static unsigned long long vmware_sched_clock(void) +static unsigned long long notrace vmware_sched_clock(void) { unsigned long long ns; diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index ab18e0884dc6..6135ae8ce036 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -199,14 +199,6 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm) /* * If PTI is enabled, this maps the LDT into the kernelmode and * usermode tables for the given mm. - * - * There is no corresponding unmap function. Even if the LDT is freed, we - * leave the PTEs around until the slot is reused or the mm is destroyed. - * This is harmless: the LDT is always in ordinary memory, and no one will - * access the freed slot. - * - * If we wanted to unmap freed LDTs, we'd also need to do a flush to make - * it useful, and the flush would slow down modify_ldt(). */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) @@ -214,8 +206,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) unsigned long va; bool is_vmalloc; spinlock_t *ptl; - pgd_t *pgd; - int i; + int i, nr_pages; if (!static_cpu_has(X86_FEATURE_PTI)) return 0; @@ -229,16 +220,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Check if the current mappings are sane */ sanity_check_ldt_mapping(mm); - /* - * Did we already have the top level entry allocated? We can't - * use pgd_none() for this because it doens't do anything on - * 4-level page table kernels. - */ - pgd = pgd_offset(mm, LDT_BASE_ADDR); - is_vmalloc = is_vmalloc_addr(ldt->entries); - for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) { + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { unsigned long offset = i << PAGE_SHIFT; const void *src = (char *)ldt->entries + offset; unsigned long pfn; @@ -272,13 +258,39 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) /* Propagate LDT mapping to the user page-table */ map_ldt_struct_to_user(mm); - va = (unsigned long)ldt_slot_va(slot); - flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT, false); - ldt->slot = slot; return 0; } +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ + unsigned long va; + int i, nr_pages; + + if (!ldt) + return; + + /* LDT map/unmap is only required for PTI */ + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE); + + for (i = 0; i < nr_pages; i++) { + unsigned long offset = i << PAGE_SHIFT; + spinlock_t *ptl; + pte_t *ptep; + + va = (unsigned long)ldt_slot_va(ldt->slot) + offset; + ptep = get_locked_pte(mm, va, &ptl); + pte_clear(mm, va, ptep); + pte_unmap_unlock(ptep, ptl); + } + + va = (unsigned long)ldt_slot_va(ldt->slot); + flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); +} + #else /* !CONFIG_PAGE_TABLE_ISOLATION */ static int @@ -286,6 +298,10 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) { return 0; } + +static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) +{ +} #endif /* CONFIG_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) @@ -524,6 +540,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } install_ldt(mm, new_ldt); + unmap_ldt_struct(mm, old_ldt); free_ldt_struct(old_ldt); error = 0; diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 1eae5af491c2..891a75dbc131 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -26,65 +26,8 @@ #define TOPOLOGY_REGISTER_OFFSET 0x10 -#if defined CONFIG_PCI && defined CONFIG_PARAVIRT_XXL -/* - * Interrupt control on vSMPowered systems: - * ~AC is a shadow of IF. If IF is 'on' AC should be 'off' - * and vice versa. - */ - -asmlinkage __visible unsigned long vsmp_save_fl(void) -{ - unsigned long flags = native_save_fl(); - - if (!(flags & X86_EFLAGS_IF) || (flags & X86_EFLAGS_AC)) - flags &= ~X86_EFLAGS_IF; - return flags; -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_save_fl); - -__visible void vsmp_restore_fl(unsigned long flags) -{ - if (flags & X86_EFLAGS_IF) - flags &= ~X86_EFLAGS_AC; - else - flags |= X86_EFLAGS_AC; - native_restore_fl(flags); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl); - -asmlinkage __visible void vsmp_irq_disable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags & ~X86_EFLAGS_IF) | X86_EFLAGS_AC); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable); - -asmlinkage __visible void vsmp_irq_enable(void) -{ - unsigned long flags = native_save_fl(); - - native_restore_fl((flags | X86_EFLAGS_IF) & (~X86_EFLAGS_AC)); -} -PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_enable); - -static unsigned __init vsmp_patch(u8 type, void *ibuf, - unsigned long addr, unsigned len) -{ - switch (type) { - case PARAVIRT_PATCH(irq.irq_enable): - case PARAVIRT_PATCH(irq.irq_disable): - case PARAVIRT_PATCH(irq.save_fl): - case PARAVIRT_PATCH(irq.restore_fl): - return paravirt_patch_default(type, ibuf, addr, len); - default: - return native_patch(type, ibuf, addr, len); - } - -} - -static void __init set_vsmp_pv_ops(void) +#ifdef CONFIG_PCI +static void __init set_vsmp_ctl(void) { void __iomem *address; unsigned int cap, ctl, cfg; @@ -109,28 +52,12 @@ static void __init set_vsmp_pv_ops(void) } #endif - if (cap & ctl & (1 << 4)) { - /* Setup irq ops and turn on vSMP IRQ fastpath handling */ - pv_ops.irq.irq_disable = PV_CALLEE_SAVE(vsmp_irq_disable); - pv_ops.irq.irq_enable = PV_CALLEE_SAVE(vsmp_irq_enable); - pv_ops.irq.save_fl = PV_CALLEE_SAVE(vsmp_save_fl); - pv_ops.irq.restore_fl = PV_CALLEE_SAVE(vsmp_restore_fl); - pv_ops.init.patch = vsmp_patch; - ctl &= ~(1 << 4); - } writel(ctl, address + 4); ctl = readl(address + 4); pr_info("vSMP CTL: control set to:0x%08x\n", ctl); early_iounmap(address, 8); } -#else -static void __init set_vsmp_pv_ops(void) -{ -} -#endif - -#ifdef CONFIG_PCI static int is_vsmp = -1; static void __init detect_vsmp_box(void) @@ -164,11 +91,14 @@ static int is_vsmp_box(void) { return 0; } +static void __init set_vsmp_ctl(void) +{ +} #endif static void __init vsmp_cap_cpus(void) { -#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) +#if !defined(CONFIG_X86_VSMP) && defined(CONFIG_SMP) && defined(CONFIG_PCI) void __iomem *address; unsigned int cfg, topology, node_shift, maxcpus; @@ -221,6 +151,6 @@ void __init vsmp_init(void) vsmp_cap_cpus(); - set_vsmp_pv_ops(); + set_vsmp_ctl(); return; } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 0d7b3ae4960b..a5d7ed125337 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -1905,7 +1905,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) init_top_pgt[0] = __pgd(0); /* Pre-constructed entries are in pfn, so convert to mfn */ - /* L4[272] -> level3_ident_pgt */ + /* L4[273] -> level3_ident_pgt */ /* L4[511] -> level3_kernel_pgt */ convert_pfn_mfn(init_top_pgt); @@ -1925,8 +1925,8 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn) addr[0] = (unsigned long)pgd; addr[1] = (unsigned long)l3; addr[2] = (unsigned long)l2; - /* Graft it onto L4[272][0]. Note that we creating an aliasing problem: - * Both L4[272][0] and L4[511][510] have entries that point to the same + /* Graft it onto L4[273][0]. Note that we creating an aliasing problem: + * Both L4[273][0] and L4[511][510] have entries that point to the same * L2 (PMD) tables. Meaning that if you modify it in __va space * it will be also modified in the __ka space! (But if you just * modify the PMD table to point to other PTE's or none, then you diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b06731705529..055e37e43541 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -656,8 +656,7 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* * The interface requires atomic updates on p2m elements. - * xen_safe_write_ulong() is using __put_user which does an atomic - * store via asm(). + * xen_safe_write_ulong() is using an atomic store via asm(). */ if (likely(!xen_safe_write_ulong(xen_p2m_addr + pfn, mfn))) return true; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 441c88262169..1c8a8816a402 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -9,6 +9,7 @@ #include <linux/log2.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/atomic.h> #include <asm/paravirt.h> #include <asm/qspinlock.h> @@ -21,6 +22,7 @@ static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; static DEFINE_PER_CPU(char *, irq_name); +static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest); static bool xen_pvspin = true; static void xen_qlock_kick(int cpu) @@ -39,25 +41,25 @@ static void xen_qlock_kick(int cpu) */ static void xen_qlock_wait(u8 *byte, u8 val) { - unsigned long flags; int irq = __this_cpu_read(lock_kicker_irq); + atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest); /* If kicker interrupts not initialized yet, just spin */ if (irq == -1 || in_nmi()) return; - /* Guard against reentry. */ - local_irq_save(flags); + /* Detect reentry. */ + atomic_inc(nest_cnt); - /* If irq pending already clear it. */ - if (xen_test_irq_pending(irq)) { + /* If irq pending already and no nested call clear it. */ + if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) { xen_clear_irq_pending(irq); } else if (READ_ONCE(*byte) == val) { /* Block until irq becomes pending (or a spurious wakeup) */ xen_poll_irq(irq); } - local_irq_restore(flags); + atomic_dec(nest_cnt); } static irqreturn_t dummy_handler(int irq, void *dev_id) diff --git a/block/bio.c b/block/bio.c index d5368a445561..a50d59236b19 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1260,6 +1260,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (ret) goto cleanup; } else { + zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } diff --git a/block/blk-lib.c b/block/blk-lib.c index 76f867ea9a9b..e8b3bb9bf375 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -51,16 +51,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if ((sector | nr_sects) & bs_mask) return -EINVAL; - while (nr_sects) { - unsigned int req_sects = nr_sects; - sector_t end_sect; - - if (!req_sects) - goto fail; - if (req_sects > UINT_MAX >> 9) - req_sects = UINT_MAX >> 9; + if (!nr_sects) + return -EINVAL; - end_sect = sector + req_sects; + while (nr_sects) { + unsigned int req_sects = min_t(unsigned int, nr_sects, + bio_allowed_max_sectors(q)); bio = blk_next_bio(bio, 0, gfp_mask); bio->bi_iter.bi_sector = sector; @@ -68,8 +64,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_set_op_attrs(bio, op, 0); bio->bi_iter.bi_size = req_sects << 9; + sector += req_sects; nr_sects -= req_sects; - sector = end_sect; /* * We can loop for a long time in here, if someone does @@ -82,14 +78,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, *biop = bio; return 0; - -fail: - if (bio) { - submit_bio_wait(bio); - bio_put(bio); - } - *biop = NULL; - return -EOPNOTSUPP; } EXPORT_SYMBOL(__blkdev_issue_discard); @@ -161,7 +149,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector, return -EOPNOTSUPP; /* Ensure that max_write_same_sectors doesn't overflow bi_size */ - max_write_same_sectors = UINT_MAX >> 9; + max_write_same_sectors = bio_allowed_max_sectors(q); while (nr_sects) { bio = blk_next_bio(bio, 1, gfp_mask); diff --git a/block/blk-merge.c b/block/blk-merge.c index 6b5ad275ed56..e7696c47489a 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -46,7 +46,7 @@ static inline bool bio_will_gap(struct request_queue *q, bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) + if (pb.bv_offset & queue_virt_boundary(q)) return true; /* @@ -90,7 +90,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); - max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); + max_discard_sectors = min(q->limits.max_discard_sectors, + bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { diff --git a/block/blk.h b/block/blk.h index a1841b8ff129..0089fefdf771 100644 --- a/block/blk.h +++ b/block/blk.h @@ -169,7 +169,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, static inline bool __bvec_gap_to_prev(struct request_queue *q, struct bio_vec *bprv, unsigned int offset) { - return offset || + return (offset & queue_virt_boundary(q)) || ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } @@ -396,6 +396,16 @@ static inline unsigned long blk_rq_deadline(struct request *rq) } /* + * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size + * is defined as 'unsigned int', meantime it has to aligned to with logical + * block size which is the minimum accepted unit by hardware. + */ +static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) +{ + return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; +} + +/* * Internal io_context interface */ void get_io_context(struct io_context *ioc); diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c index e9626bf6ca29..d6c1b10f6c25 100644 --- a/drivers/acpi/nfit/mce.c +++ b/drivers/acpi/nfit/mce.c @@ -25,8 +25,12 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val, struct acpi_nfit_desc *acpi_desc; struct nfit_spa *nfit_spa; - /* We only care about memory errors */ - if (!mce_is_memory_error(mce)) + /* We only care about uncorrectable memory errors */ + if (!mce_is_memory_error(mce) || mce_is_correctable(mce)) + return NOTIFY_DONE; + + /* Verify the address reported in the MCE is valid. */ + if (!mce_usable_address(mce)) return NOTIFY_DONE; /* diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c index 10ecb232245d..4b1ff5bc256a 100644 --- a/drivers/ata/sata_rcar.c +++ b/drivers/ata/sata_rcar.c @@ -1,14 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Renesas R-Car SATA driver * * Author: Vladimir Barinov <[email protected]> * Copyright (C) 2013-2015 Cogent Embedded, Inc. * Copyright (C) 2013-2015 Renesas Solutions Corp. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms of the GNU General Public License as published by the - * Free Software Foundation; either version 2 of the License, or (at your - * option) any later version. */ #include <linux/kernel.h> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 56452cabce5b..0ed4b200fa58 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1919,6 +1919,7 @@ static int negotiate_mq(struct blkfront_info *info) GFP_KERNEL); if (!info->rinfo) { xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); + info->nr_rings = 0; return -ENOMEM; } diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index ef0ca9414f37..ff83e899df71 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -210,6 +210,7 @@ static int of_fixed_factor_clk_remove(struct platform_device *pdev) { struct clk *clk = platform_get_drvdata(pdev); + of_clk_del_provider(pdev->dev.of_node); clk_unregister_fixed_factor(clk); return 0; diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c index c981159b02c0..792735d7e46e 100644 --- a/drivers/clk/meson/axg.c +++ b/drivers/clk/meson/axg.c @@ -325,6 +325,7 @@ static struct clk_regmap axg_fclk_div2 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div2_div" }, .num_parents = 1, + .flags = CLK_IS_CRITICAL, }, }; @@ -349,6 +350,18 @@ static struct clk_regmap axg_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c index 9309cfaaa464..4ada9668fd49 100644 --- a/drivers/clk/meson/gxbb.c +++ b/drivers/clk/meson/gxbb.c @@ -506,6 +506,18 @@ static struct clk_regmap gxbb_fclk_div3 = { .ops = &clk_regmap_gate_ops, .parent_names = (const char *[]){ "fclk_div3_div" }, .num_parents = 1, + /* + * FIXME: + * This clock, as fdiv2, is used by the SCPI FW and is required + * by the platform to operate correctly. + * Until the following condition are met, we need this clock to + * be marked as critical: + * a) The SCPI generic driver claims and enable all the clocks + * it needs + * b) CCF has a clock hand-off mechanism to make the sure the + * clock stays on until the proper driver comes along + */ + .flags = CLK_IS_CRITICAL, }, }; diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index e4ca6a45f313..ef1b267cb058 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -265,7 +265,7 @@ static struct clk_fixed_factor cxo = { .div = 1, .hw.init = &(struct clk_init_data){ .name = "cxo", - .parent_names = (const char *[]){ "xo_board" }, + .parent_names = (const char *[]){ "xo-board" }, .num_parents = 1, .ops = &clk_fixed_factor_ops, }, diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 9c38895542f4..d4350bb10b83 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -20,6 +20,13 @@ DEFINE_RAW_SPINLOCK(i8253_lock); EXPORT_SYMBOL(i8253_lock); +/* + * Handle PIT quirk in pit_shutdown() where zeroing the counter register + * restarts the PIT, negating the shutdown. On platforms with the quirk, + * platform specific code can set this to false. + */ +bool i8253_clear_counter_on_shutdown __ro_after_init = true; + #ifdef CONFIG_CLKSRC_I8253 /* * Since the PIT overflows every tick, its not very useful @@ -109,8 +116,11 @@ static int pit_shutdown(struct clock_event_device *evt) raw_spin_lock(&i8253_lock); outb_p(0x30, PIT_MODE); - outb_p(0, PIT_CH0); - outb_p(0, PIT_CH0); + + if (i8253_clear_counter_on_shutdown) { + outb_p(0, PIT_CH0); + outb_p(0, PIT_CH0); + } raw_spin_unlock(&i8253_lock); return 0; diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index 61ae06ca008e..52f0d91d30c1 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -128,7 +128,7 @@ static int cpu_750fx_cpu_speed(int low_speed) mtspr(SPRN_HID2, hid2); } } -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 low_choose_750fx_pll(low_speed); #endif if (low_speed == 1) { @@ -166,7 +166,7 @@ static int dfs_set_cpu_speed(int low_speed) } /* set frequency */ -#ifdef CONFIG_6xx +#ifdef CONFIG_PPC_BOOK3S_32 low_choose_7447a_dfs(low_speed); #endif udelay(100); diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c index 9e56bc411061..74c247972bb3 100644 --- a/drivers/cpuidle/cpuidle-pseries.c +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -247,7 +247,13 @@ static int pseries_idle_probe(void) return -ENODEV; if (firmware_has_feature(FW_FEATURE_SPLPAR)) { - if (lppaca_shared_proc(get_lppaca())) { + /* + * Use local_paca instead of get_lppaca() since + * preemption is not disabled, and it is not required in + * fact, since lppaca_ptr does not need to be the value + * associated to the current CPU, it can be from any CPU. + */ + if (lppaca_shared_proc(local_paca->lppaca_ptr)) { cpuidle_state_table = shared_states; max_idle_state = ARRAY_SIZE(shared_states); } else { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index d0102cfc8efb..104b2e0d893b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -151,6 +151,7 @@ extern int amdgpu_compute_multipipe; extern int amdgpu_gpu_recovery; extern int amdgpu_emu_mode; extern uint amdgpu_smu_memory_pool_size; +extern uint amdgpu_dc_feature_mask; extern struct amdgpu_mgpu_info mgpu_info; #ifdef CONFIG_DRM_AMDGPU_SI diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 943dbf3c5da1..8de55f7f1a3a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -127,6 +127,9 @@ int amdgpu_compute_multipipe = -1; int amdgpu_gpu_recovery = -1; /* auto */ int amdgpu_emu_mode = 0; uint amdgpu_smu_memory_pool_size = 0; +/* FBC (bit 0) disabled by default*/ +uint amdgpu_dc_feature_mask = 0; + struct amdgpu_mgpu_info mgpu_info = { .mutex = __MUTEX_INITIALIZER(mgpu_info.mutex), }; @@ -631,6 +634,14 @@ module_param(halt_if_hws_hang, int, 0644); MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)"); #endif +/** + * DOC: dcfeaturemask (uint) + * Override display features enabled. See enum DC_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h. + * The default is the current set of stable display features. + */ +MODULE_PARM_DESC(dcfeaturemask, "all stable DC features enabled (default))"); +module_param_named(dcfeaturemask, amdgpu_dc_feature_mask, uint, 0444); + static const struct pci_device_id pciidlist[] = { #ifdef CONFIG_DRM_AMDGPU_SI {0x1002, 0x6780, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TAHITI}, diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c index 2d4473557b0d..d13fc4fcb517 100644 --- a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c +++ b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c @@ -49,6 +49,7 @@ int vega20_reg_base_init(struct amdgpu_device *adev) adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i])); adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIO_BASE.instance[i])); adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i])); + adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i])); } return 0; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b0df6dc9a775..c1262f62cd9f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -429,6 +429,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) adev->asic_type < CHIP_RAVEN) init_data.flags.gpu_vm_support = true; + if (amdgpu_dc_feature_mask & DC_FBC_MASK) + init_data.flags.fbc_support = true; + /* Display Core create. */ adev->dm.dc = dc_create(&init_data); @@ -1524,13 +1527,6 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd) { struct amdgpu_display_manager *dm = bl_get_data(bd); - /* - * PWM interperts 0 as 100% rather than 0% because of HW - * limitation for level 0.So limiting minimum brightness level - * to 1. - */ - if (bd->props.brightness < 1) - return 1; if (dc_link_set_backlight_level(dm->backlight_link, bd->props.brightness, 0, 0)) return 0; @@ -2707,18 +2703,11 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, drm_connector = &aconnector->base; if (!aconnector->dc_sink) { - /* - * Create dc_sink when necessary to MST - * Don't apply fake_sink to MST - */ - if (aconnector->mst_port) { - dm_dp_mst_dc_sink_create(drm_connector); - return stream; + if (!aconnector->mst_port) { + sink = create_fake_sink(aconnector); + if (!sink) + return stream; } - - sink = create_fake_sink(aconnector); - if (!sink) - return stream; } else { sink = aconnector->dc_sink; } @@ -3308,7 +3297,7 @@ void dm_drm_plane_destroy_state(struct drm_plane *plane, static const struct drm_plane_funcs dm_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, .disable_plane = drm_atomic_helper_disable_plane, - .destroy = drm_plane_cleanup, + .destroy = drm_primary_helper_destroy, .reset = dm_drm_plane_reset, .atomic_duplicate_state = dm_drm_plane_duplicate_state, .atomic_destroy_state = dm_drm_plane_destroy_state, diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 978b34a5011c..924a38a1fc44 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -160,8 +160,6 @@ struct amdgpu_dm_connector { struct mutex hpd_lock; bool fake_enable; - - bool mst_connected; }; #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 03601d717fed..d02c32a1039c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -205,40 +205,6 @@ static const struct drm_connector_funcs dm_dp_mst_connector_funcs = { .atomic_get_property = amdgpu_dm_connector_atomic_get_property }; -void dm_dp_mst_dc_sink_create(struct drm_connector *connector) -{ - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); - struct dc_sink *dc_sink; - struct dc_sink_init_data init_params = { - .link = aconnector->dc_link, - .sink_signal = SIGNAL_TYPE_DISPLAY_PORT_MST }; - - /* FIXME none of this is safe. we shouldn't touch aconnector here in - * atomic_check - */ - - /* - * TODO: Need to further figure out why ddc.algo is NULL while MST port exists - */ - if (!aconnector->port || !aconnector->port->aux.ddc.algo) - return; - - ASSERT(aconnector->edid); - - dc_sink = dc_link_add_remote_sink( - aconnector->dc_link, - (uint8_t *)aconnector->edid, - (aconnector->edid->extensions + 1) * EDID_LENGTH, - &init_params); - - dc_sink->priv = aconnector; - aconnector->dc_sink = dc_sink; - - if (aconnector->dc_sink) - amdgpu_dm_update_freesync_caps( - connector, aconnector->edid); -} - static int dm_dp_mst_get_modes(struct drm_connector *connector) { struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); @@ -319,12 +285,7 @@ dm_dp_create_fake_mst_encoder(struct amdgpu_dm_connector *connector) struct amdgpu_device *adev = dev->dev_private; struct amdgpu_encoder *amdgpu_encoder; struct drm_encoder *encoder; - const struct drm_connector_helper_funcs *connector_funcs = - connector->base.helper_private; - struct drm_encoder *enc_master = - connector_funcs->best_encoder(&connector->base); - DRM_DEBUG_KMS("enc master is %p\n", enc_master); amdgpu_encoder = kzalloc(sizeof(*amdgpu_encoder), GFP_KERNEL); if (!amdgpu_encoder) return NULL; @@ -354,25 +315,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector; struct drm_connector *connector; - struct drm_connector_list_iter conn_iter; - - drm_connector_list_iter_begin(dev, &conn_iter); - drm_for_each_connector_iter(connector, &conn_iter) { - aconnector = to_amdgpu_dm_connector(connector); - if (aconnector->mst_port == master - && !aconnector->port) { - DRM_INFO("DM_MST: reusing connector: %p [id: %d] [master: %p]\n", - aconnector, connector->base.id, aconnector->mst_port); - - aconnector->port = port; - drm_connector_set_path_property(connector, pathprop); - - drm_connector_list_iter_end(&conn_iter); - aconnector->mst_connected = true; - return &aconnector->base; - } - } - drm_connector_list_iter_end(&conn_iter); aconnector = kzalloc(sizeof(*aconnector), GFP_KERNEL); if (!aconnector) @@ -421,8 +363,6 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, */ amdgpu_dm_connector_funcs_reset(connector); - aconnector->mst_connected = true; - DRM_INFO("DM_MST: added connector: %p [id: %d] [master: %p]\n", aconnector, connector->base.id, aconnector->mst_port); @@ -434,6 +374,9 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr, static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, struct drm_connector *connector) { + struct amdgpu_dm_connector *master = container_of(mgr, struct amdgpu_dm_connector, mst_mgr); + struct drm_device *dev = master->base.dev; + struct amdgpu_device *adev = dev->dev_private; struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); DRM_INFO("DM_MST: Disabling connector: %p [id: %d] [master: %p]\n", @@ -447,7 +390,10 @@ static void dm_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr, aconnector->dc_sink = NULL; } - aconnector->mst_connected = false; + drm_connector_unregister(connector); + if (adev->mode_info.rfbdev) + drm_fb_helper_remove_one_connector(&adev->mode_info.rfbdev->helper, connector); + drm_connector_put(connector); } static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) @@ -458,18 +404,10 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr) drm_kms_helper_hotplug_event(dev); } -static void dm_dp_mst_link_status_reset(struct drm_connector *connector) -{ - mutex_lock(&connector->dev->mode_config.mutex); - drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD); - mutex_unlock(&connector->dev->mode_config.mutex); -} - static void dm_dp_mst_register_connector(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = dev->dev_private; - struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); if (adev->mode_info.rfbdev) drm_fb_helper_add_one_connector(&adev->mode_info.rfbdev->helper, connector); @@ -477,9 +415,6 @@ static void dm_dp_mst_register_connector(struct drm_connector *connector) DRM_ERROR("adev->mode_info.rfbdev is NULL\n"); drm_connector_register(connector); - - if (aconnector->mst_connected) - dm_dp_mst_link_status_reset(connector); } static const struct drm_dp_mst_topology_cbs dm_mst_cbs = { diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h index 8cf51da26657..2da851b40042 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.h @@ -31,6 +31,5 @@ struct amdgpu_dm_connector; void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, struct amdgpu_dm_connector *aconnector); -void dm_dp_mst_dc_sink_create(struct drm_connector *connector); #endif diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index fb04a4ad141f..5da2186b3615 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1722,7 +1722,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ @@ -1734,7 +1734,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); RETIMER_REDRIVER_INFO("retimer write to slave_address = 0x%x,\ - offset = 0x%d, reg_val = 0x%d, i2c_success = %d\n", + offset = 0x%x, reg_val = 0x%x, i2c_success = %d\n", slave_address, buffer[0], buffer[1], i2c_success?1:0); if (!i2c_success) /* Write failure */ diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 199527171100..b57fa61b3034 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -169,6 +169,7 @@ struct link_training_settings; struct dc_config { bool gpu_vm_support; bool disable_disp_pll_sharing; + bool fbc_support; }; enum visual_confirm { diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index b75ede5f84f7..b459867a05b2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1736,7 +1736,12 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx, if (events->force_trigger) value |= 0x1; - value |= 0x84; + if (num_pipes) { + struct dc *dc = pipe_ctx[0]->stream->ctx->dc; + + if (dc->fbc_compressor) + value |= 0x84; + } for (i = 0; i < num_pipes; i++) pipe_ctx[i]->stream_res.tg->funcs-> diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c index e3624ca24574..7c9fd9052ee2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c @@ -1362,7 +1362,8 @@ static bool construct( pool->base.sw_i2cs[i] = NULL; } - dc->fbc_compressor = dce110_compressor_create(ctx); + if (dc->config.fbc_support) + dc->fbc_compressor = dce110_compressor_create(ctx); if (!underlay_create(ctx, &pool->base)) goto res_create_fail; diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 2083c308007c..470d7b89071a 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -133,6 +133,10 @@ enum PP_FEATURE_MASK { PP_AVFS_MASK = 0x40000, }; +enum DC_FEATURE_MASK { + DC_FBC_MASK = 0x1, +}; + /** * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks */ diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index d2e7c0fa96c2..8eb0bb241210 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1325,7 +1325,7 @@ struct atom_smu_info_v3_3 { struct atom_common_table_header table_header; uint8_t smuip_min_ver; uint8_t smuip_max_ver; - uint8_t smu_rsd1; + uint8_t waflclk_ss_mode; uint8_t gpuclk_ss_mode; uint16_t sclk_ss_percentage; uint16_t sclk_ss_rate_10hz; @@ -1355,7 +1355,10 @@ struct atom_smu_info_v3_3 { uint32_t syspll3_1_vco_freq_10khz; uint32_t bootup_fclk_10khz; uint32_t bootup_waflclk_10khz; - uint32_t reserved[3]; + uint32_t smu_info_caps; + uint16_t waflclk_ss_percentage; // in unit of 0.001% + uint16_t smuinitoffset; + uint32_t reserved; }; /* diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 57143d51e3ee..99861f32b1f9 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -120,6 +120,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.disable_auto_wattman = 1; data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; + data->registry_data.fclk_gfxclk_ratio = 0x3F6CCCCD; data->registry_data.auto_wattman_threshold = 50; data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; @@ -829,6 +830,28 @@ static int vega20_enable_all_smu_features(struct pp_hwmgr *hwmgr) return 0; } +static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); + + if (data->smu_features[GNLD_DPM_UCLK].enabled) + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetUclkFastSwitch, + 1); + + return 0; +} + +static int vega20_send_clock_ratio(struct pp_hwmgr *hwmgr) +{ + struct vega20_hwmgr *data = + (struct vega20_hwmgr *)(hwmgr->backend); + + return smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_SetFclkGfxClkRatio, + data->registry_data.fclk_gfxclk_ratio); +} + static int vega20_disable_all_smu_features(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = @@ -1532,6 +1555,16 @@ static int vega20_enable_dpm_tasks(struct pp_hwmgr *hwmgr) "[EnableDPMTasks] Failed to enable all smu features!", return result); + result = vega20_notify_smc_display_change(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to notify smc display change!", + return result); + + result = vega20_send_clock_ratio(hwmgr); + PP_ASSERT_WITH_CODE(!result, + "[EnableDPMTasks] Failed to send clock ratio!", + return result); + /* Initialize UVD/VCE powergating state */ vega20_init_powergate_state(hwmgr); @@ -1972,19 +2005,6 @@ static int vega20_read_sensor(struct pp_hwmgr *hwmgr, int idx, return ret; } -static int vega20_notify_smc_display_change(struct pp_hwmgr *hwmgr, - bool has_disp) -{ - struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - - if (data->smu_features[GNLD_DPM_UCLK].enabled) - return smum_send_msg_to_smc_with_parameter(hwmgr, - PPSMC_MSG_SetUclkFastSwitch, - has_disp ? 1 : 0); - - return 0; -} - int vega20_display_clock_voltage_request(struct pp_hwmgr *hwmgr, struct pp_display_clock_request *clock_req) { @@ -2044,13 +2064,6 @@ static int vega20_notify_smc_display_config_after_ps_adjustment( struct pp_display_clock_request clock_req; int ret = 0; - if ((hwmgr->display_config->num_display > 1) && - !hwmgr->display_config->multi_monitor_in_sync && - !hwmgr->display_config->nb_pstate_switch_disable) - vega20_notify_smc_display_change(hwmgr, false); - else - vega20_notify_smc_display_change(hwmgr, true); - min_clocks.dcefClock = hwmgr->display_config->min_dcef_set_clk; min_clocks.dcefClockInSR = hwmgr->display_config->min_dcef_deep_sleep_set_clk; min_clocks.memoryClock = hwmgr->display_config->min_mem_set_clock; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h index 56fe6a0d42e8..25faaa5c5b10 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h @@ -328,6 +328,7 @@ struct vega20_registry_data { uint8_t disable_auto_wattman; uint32_t auto_wattman_debug; uint32_t auto_wattman_sample_period; + uint32_t fclk_gfxclk_ratio; uint8_t auto_wattman_threshold; uint8_t log_avfs_param; uint8_t enable_enginess; diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h index 45d64a81e945..4f63a736ea0e 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h @@ -105,7 +105,8 @@ #define PPSMC_MSG_SetSystemVirtualDramAddrHigh 0x4B #define PPSMC_MSG_SetSystemVirtualDramAddrLow 0x4C #define PPSMC_MSG_WaflTest 0x4D -// Unused ID 0x4E to 0x50 +#define PPSMC_MSG_SetFclkGfxClkRatio 0x4E +// Unused ID 0x4F to 0x50 #define PPSMC_MSG_AllowGfxOff 0x51 #define PPSMC_MSG_DisallowGfxOff 0x52 #define PPSMC_MSG_GetPptLimit 0x53 diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index e7c3ed6c9a2e..9b476368aa31 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -93,7 +93,7 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job) * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. */ - if (fence_completed(gpu, submit->out_fence->seqno)) + if (dma_fence_is_signaled(submit->out_fence)) return; /* diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 94529aa82339..aef487dd8731 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -164,13 +164,6 @@ static u32 decon_get_frame_count(struct decon_context *ctx, bool end) return frm; } -static u32 decon_get_vblank_counter(struct exynos_drm_crtc *crtc) -{ - struct decon_context *ctx = crtc->ctx; - - return decon_get_frame_count(ctx, false); -} - static void decon_setup_trigger(struct decon_context *ctx) { if (!ctx->crtc->i80_mode && !(ctx->out_type & I80_HW_TRG)) @@ -536,7 +529,6 @@ static const struct exynos_drm_crtc_ops decon_crtc_ops = { .disable = decon_disable, .enable_vblank = decon_enable_vblank, .disable_vblank = decon_disable_vblank, - .get_vblank_counter = decon_get_vblank_counter, .atomic_begin = decon_atomic_begin, .update_plane = decon_update_plane, .disable_plane = decon_disable_plane, @@ -554,7 +546,6 @@ static int decon_bind(struct device *dev, struct device *master, void *data) int ret; ctx->drm_dev = drm_dev; - drm_dev->max_vblank_count = 0xffffffff; for (win = ctx->first_win; win < WINDOWS_NR; win++) { ctx->configs[win].pixel_formats = decon_formats; diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c index eea90251808f..2696289ecc78 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c @@ -162,16 +162,6 @@ static void exynos_drm_crtc_disable_vblank(struct drm_crtc *crtc) exynos_crtc->ops->disable_vblank(exynos_crtc); } -static u32 exynos_drm_crtc_get_vblank_counter(struct drm_crtc *crtc) -{ - struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc); - - if (exynos_crtc->ops->get_vblank_counter) - return exynos_crtc->ops->get_vblank_counter(exynos_crtc); - - return 0; -} - static const struct drm_crtc_funcs exynos_crtc_funcs = { .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -181,7 +171,6 @@ static const struct drm_crtc_funcs exynos_crtc_funcs = { .atomic_destroy_state = drm_atomic_helper_crtc_destroy_state, .enable_vblank = exynos_drm_crtc_enable_vblank, .disable_vblank = exynos_drm_crtc_disable_vblank, - .get_vblank_counter = exynos_drm_crtc_get_vblank_counter, }; struct exynos_drm_crtc *exynos_drm_crtc_create(struct drm_device *drm_dev, diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h index ec9604f1272b..5e61e707f955 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_drv.h +++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h @@ -135,7 +135,6 @@ struct exynos_drm_crtc_ops { void (*disable)(struct exynos_drm_crtc *crtc); int (*enable_vblank)(struct exynos_drm_crtc *crtc); void (*disable_vblank)(struct exynos_drm_crtc *crtc); - u32 (*get_vblank_counter)(struct exynos_drm_crtc *crtc); enum drm_mode_status (*mode_valid)(struct exynos_drm_crtc *crtc, const struct drm_display_mode *mode); bool (*mode_fixup)(struct exynos_drm_crtc *crtc, diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 07af7758066d..d81e62ae286a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -14,6 +14,7 @@ #include <drm/drmP.h> #include <drm/drm_crtc_helper.h> +#include <drm/drm_fb_helper.h> #include <drm/drm_mipi_dsi.h> #include <drm/drm_panel.h> #include <drm/drm_atomic_helper.h> @@ -1474,12 +1475,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) { struct exynos_dsi *dsi = encoder_to_dsi(encoder); struct drm_connector *connector = &dsi->connector; + struct drm_device *drm = encoder->dev; int ret; connector->polled = DRM_CONNECTOR_POLL_HPD; - ret = drm_connector_init(encoder->dev, connector, - &exynos_dsi_connector_funcs, + ret = drm_connector_init(drm, connector, &exynos_dsi_connector_funcs, DRM_MODE_CONNECTOR_DSI); if (ret) { DRM_ERROR("Failed to initialize connector with drm\n"); @@ -1489,7 +1490,12 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder) connector->status = connector_status_disconnected; drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs); drm_connector_attach_encoder(connector, encoder); + if (!drm->registered) + return 0; + connector->funcs->reset(connector); + drm_fb_helper_add_one_connector(drm->fb_helper, connector); + drm_connector_register(connector); return 0; } @@ -1527,7 +1533,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host, } dsi->panel = of_drm_find_panel(device->dev.of_node); - if (dsi->panel) { + if (IS_ERR(dsi->panel)) { + dsi->panel = NULL; + } else { drm_panel_attach(dsi->panel, &dsi->connector); dsi->connector.status = connector_status_connected; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index 918dd2c82209..01d182289efa 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -192,7 +192,7 @@ int exynos_drm_fbdev_init(struct drm_device *dev) struct drm_fb_helper *helper; int ret; - if (!dev->mode_config.num_crtc || !dev->mode_config.num_connector) + if (!dev->mode_config.num_crtc) return 0; fbdev = kzalloc(sizeof(*fbdev), GFP_KERNEL); diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 2402395a068d..58e166effa45 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1905,7 +1905,6 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu) vgpu_free_mm(mm); return ERR_PTR(-ENOMEM); } - mm->ggtt_mm.last_partial_off = -1UL; return mm; } @@ -1930,7 +1929,6 @@ void _intel_vgpu_mm_release(struct kref *mm_ref) invalidate_ppgtt_mm(mm); } else { vfree(mm->ggtt_mm.virtual_ggtt); - mm->ggtt_mm.last_partial_off = -1UL; } vgpu_free_mm(mm); @@ -2168,6 +2166,8 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, struct intel_gvt_gtt_entry e, m; dma_addr_t dma_addr; int ret; + struct intel_gvt_partial_pte *partial_pte, *pos, *n; + bool partial_update = false; if (bytes != 4 && bytes != 8) return -EINVAL; @@ -2178,68 +2178,57 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, if (!vgpu_gmadr_is_valid(vgpu, gma)) return 0; - ggtt_get_guest_entry(ggtt_mm, &e, g_gtt_index); - + e.type = GTT_TYPE_GGTT_PTE; memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data, bytes); /* If ggtt entry size is 8 bytes, and it's split into two 4 bytes - * write, we assume the two 4 bytes writes are consecutive. - * Otherwise, we abort and report error + * write, save the first 4 bytes in a list and update virtual + * PTE. Only update shadow PTE when the second 4 bytes comes. */ if (bytes < info->gtt_entry_size) { - if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) { - /* the first partial part*/ - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; - return 0; - } else if ((g_gtt_index == - (ggtt_mm->ggtt_mm.last_partial_off >> - info->gtt_entry_size_shift)) && - (off != ggtt_mm->ggtt_mm.last_partial_off)) { - /* the second partial part */ - - int last_off = ggtt_mm->ggtt_mm.last_partial_off & - (info->gtt_entry_size - 1); - - memcpy((void *)&e.val64 + last_off, - (void *)&ggtt_mm->ggtt_mm.last_partial_data + - last_off, bytes); - - ggtt_mm->ggtt_mm.last_partial_off = -1UL; - } else { - int last_offset; - - gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n", - ggtt_mm->ggtt_mm.last_partial_off, off, - bytes, info->gtt_entry_size); - - /* set host ggtt entry to scratch page and clear - * virtual ggtt entry as not present for last - * partially write offset - */ - last_offset = ggtt_mm->ggtt_mm.last_partial_off & - (~(info->gtt_entry_size - 1)); - - ggtt_get_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate_pte(vgpu, &m); - ops->set_pfn(&m, gvt->gtt.scratch_mfn); - ops->clear_present(&m); - ggtt_set_host_entry(ggtt_mm, &m, last_offset); - ggtt_invalidate(gvt->dev_priv); - - ggtt_get_guest_entry(ggtt_mm, &e, last_offset); - ops->clear_present(&e); - ggtt_set_guest_entry(ggtt_mm, &e, last_offset); - - ggtt_mm->ggtt_mm.last_partial_off = off; - ggtt_mm->ggtt_mm.last_partial_data = e.val64; + bool found = false; + + list_for_each_entry_safe(pos, n, + &ggtt_mm->ggtt_mm.partial_pte_list, list) { + if (g_gtt_index == pos->offset >> + info->gtt_entry_size_shift) { + if (off != pos->offset) { + /* the second partial part*/ + int last_off = pos->offset & + (info->gtt_entry_size - 1); + + memcpy((void *)&e.val64 + last_off, + (void *)&pos->data + last_off, + bytes); + + list_del(&pos->list); + kfree(pos); + found = true; + break; + } + + /* update of the first partial part */ + pos->data = e.val64; + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + return 0; + } + } - return 0; + if (!found) { + /* the first partial part */ + partial_pte = kzalloc(sizeof(*partial_pte), GFP_KERNEL); + if (!partial_pte) + return -ENOMEM; + partial_pte->offset = off; + partial_pte->data = e.val64; + list_add_tail(&partial_pte->list, + &ggtt_mm->ggtt_mm.partial_pte_list); + partial_update = true; } } - if (ops->test_present(&e)) { + if (!partial_update && (ops->test_present(&e))) { gfn = ops->get_pfn(&e); m = e; @@ -2263,16 +2252,18 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, } else ops->set_pfn(&m, dma_addr >> PAGE_SHIFT); } else { - ggtt_get_host_entry(ggtt_mm, &m, g_gtt_index); - ggtt_invalidate_pte(vgpu, &m); ops->set_pfn(&m, gvt->gtt.scratch_mfn); ops->clear_present(&m); } out: + ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); + + ggtt_get_host_entry(ggtt_mm, &e, g_gtt_index); + ggtt_invalidate_pte(vgpu, &e); + ggtt_set_host_entry(ggtt_mm, &m, g_gtt_index); ggtt_invalidate(gvt->dev_priv); - ggtt_set_guest_entry(ggtt_mm, &e, g_gtt_index); return 0; } @@ -2430,6 +2421,8 @@ int intel_vgpu_init_gtt(struct intel_vgpu *vgpu) intel_vgpu_reset_ggtt(vgpu, false); + INIT_LIST_HEAD(>t->ggtt_mm->ggtt_mm.partial_pte_list); + return create_scratch_page_tree(vgpu); } @@ -2454,6 +2447,14 @@ static void intel_vgpu_destroy_all_ppgtt_mm(struct intel_vgpu *vgpu) static void intel_vgpu_destroy_ggtt_mm(struct intel_vgpu *vgpu) { + struct intel_gvt_partial_pte *pos; + + list_for_each_entry(pos, + &vgpu->gtt.ggtt_mm->ggtt_mm.partial_pte_list, list) { + gvt_dbg_mm("partial PTE update on hold 0x%lx : 0x%llx\n", + pos->offset, pos->data); + kfree(pos); + } intel_vgpu_destroy_mm(vgpu->gtt.ggtt_mm); vgpu->gtt.ggtt_mm = NULL; } diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h index 7a9b36176efb..d8cb04cc946d 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.h +++ b/drivers/gpu/drm/i915/gvt/gtt.h @@ -35,7 +35,6 @@ #define _GVT_GTT_H_ #define I915_GTT_PAGE_SHIFT 12 -#define I915_GTT_PAGE_MASK (~(I915_GTT_PAGE_SIZE - 1)) struct intel_vgpu_mm; @@ -133,6 +132,12 @@ enum intel_gvt_mm_type { #define GVT_RING_CTX_NR_PDPS GEN8_3LVL_PDPES +struct intel_gvt_partial_pte { + unsigned long offset; + u64 data; + struct list_head list; +}; + struct intel_vgpu_mm { enum intel_gvt_mm_type type; struct intel_vgpu *vgpu; @@ -157,8 +162,7 @@ struct intel_vgpu_mm { } ppgtt_mm; struct { void *virtual_ggtt; - unsigned long last_partial_off; - u64 last_partial_data; + struct list_head partial_pte_list; } ggtt_mm; }; }; diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 90f50f67909a..aa280bb07125 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1609,7 +1609,7 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu, return 0; } -static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu, +static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { vgpu_vreg(vgpu, offset) = 0; @@ -2607,6 +2607,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt) MMIO_DFH(_MMIO(0x1a178), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x1a17c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(_MMIO(0x2217c), D_BDW_PLUS, F_CMD_ACCESS, NULL, NULL); + + MMIO_DH(EDP_PSR_IMR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); + MMIO_DH(EDP_PSR_IIR, D_BDW_PLUS, NULL, edp_psr_imr_iir_write); return 0; } @@ -3205,9 +3208,6 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT); MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT); - MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write); - MMIO_D(RC6_CTX_BASE, D_BXT); MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 10e63eea5492..36a5147cd01e 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -131,7 +131,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = { {RCS, GAMT_CHKN_BIT_REG, 0x0, false}, /* 0x4ab8 */ {RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */ - {RCS, GEN9_CSFE_CHICKEN1_RCS, 0x0, false}, /* 0x20d4 */ + {RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */ {RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */ {RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */ diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index 44e2c0f5ec50..ffdbbac4400e 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1175,8 +1175,6 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; - /* * If any of the channel is single rank channel, worst case output * will be same as if single rank memory, so consider single rank @@ -1193,8 +1191,7 @@ skl_dram_get_channels_info(struct drm_i915_private *dev_priv) return -EINVAL; } - if (ch0.is_16gb_dimm || ch1.is_16gb_dimm) - dram_info->is_16gb_dimm = true; + dram_info->is_16gb_dimm = ch0.is_16gb_dimm || ch1.is_16gb_dimm; dev_priv->dram_info.symmetric_memory = intel_is_dram_symmetric(val_ch0, val_ch1, @@ -1314,7 +1311,6 @@ bxt_get_dram_info(struct drm_i915_private *dev_priv) return -EINVAL; } - dram_info->valid_dimm = true; dram_info->valid = true; return 0; } @@ -1327,12 +1323,17 @@ intel_get_dram_info(struct drm_i915_private *dev_priv) int ret; dram_info->valid = false; - dram_info->valid_dimm = false; - dram_info->is_16gb_dimm = false; dram_info->rank = I915_DRAM_RANK_INVALID; dram_info->bandwidth_kbps = 0; dram_info->num_channels = 0; + /* + * Assume 16Gb DIMMs are present until proven otherwise. + * This is only used for the level 0 watermark latency + * w/a which does not apply to bxt/glk. + */ + dram_info->is_16gb_dimm = !IS_GEN9_LP(dev_priv); + if (INTEL_GEN(dev_priv) < 9 || IS_GEMINILAKE(dev_priv)) return; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 8624b4bdc242..9102571e9692 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -1948,7 +1948,6 @@ struct drm_i915_private { struct dram_info { bool valid; - bool valid_dimm; bool is_16gb_dimm; u8 num_channels; enum dram_rank { diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 09187286d346..1aaccbe7e1de 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -460,7 +460,7 @@ eb_validate_vma(struct i915_execbuffer *eb, * any non-page-aligned or non-canonical addresses. */ if (unlikely(entry->flags & EXEC_OBJECT_PINNED && - entry->offset != gen8_canonical_addr(entry->offset & PAGE_MASK))) + entry->offset != gen8_canonical_addr(entry->offset & I915_GTT_PAGE_MASK))) return -EINVAL; /* pad_to_size was once a reserved field, so sanitize it */ diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 56c7f8637311..47c302543799 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -1757,7 +1757,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m) if (i == 4) continue; - seq_printf(m, "\t\t(%03d, %04d) %08lx: ", + seq_printf(m, "\t\t(%03d, %04d) %08llx: ", pde, pte, (pde * GEN6_PTES + pte) * I915_GTT_PAGE_SIZE); for (i = 0; i < 4; i++) { diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h index 7e2af5f4f39b..28039290655c 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.h +++ b/drivers/gpu/drm/i915/i915_gem_gtt.h @@ -42,13 +42,15 @@ #include "i915_selftest.h" #include "i915_timeline.h" -#define I915_GTT_PAGE_SIZE_4K BIT(12) -#define I915_GTT_PAGE_SIZE_64K BIT(16) -#define I915_GTT_PAGE_SIZE_2M BIT(21) +#define I915_GTT_PAGE_SIZE_4K BIT_ULL(12) +#define I915_GTT_PAGE_SIZE_64K BIT_ULL(16) +#define I915_GTT_PAGE_SIZE_2M BIT_ULL(21) #define I915_GTT_PAGE_SIZE I915_GTT_PAGE_SIZE_4K #define I915_GTT_MAX_PAGE_SIZE I915_GTT_PAGE_SIZE_2M +#define I915_GTT_PAGE_MASK -I915_GTT_PAGE_SIZE + #define I915_GTT_MIN_ALIGNMENT I915_GTT_PAGE_SIZE #define I915_FENCE_REG_NONE -1 @@ -659,20 +661,20 @@ int i915_gem_gtt_insert(struct i915_address_space *vm, u64 start, u64 end, unsigned int flags); /* Flags used by pin/bind&friends. */ -#define PIN_NONBLOCK BIT(0) -#define PIN_MAPPABLE BIT(1) -#define PIN_ZONE_4G BIT(2) -#define PIN_NONFAULT BIT(3) -#define PIN_NOEVICT BIT(4) - -#define PIN_MBZ BIT(5) /* I915_VMA_PIN_OVERFLOW */ -#define PIN_GLOBAL BIT(6) /* I915_VMA_GLOBAL_BIND */ -#define PIN_USER BIT(7) /* I915_VMA_LOCAL_BIND */ -#define PIN_UPDATE BIT(8) - -#define PIN_HIGH BIT(9) -#define PIN_OFFSET_BIAS BIT(10) -#define PIN_OFFSET_FIXED BIT(11) +#define PIN_NONBLOCK BIT_ULL(0) +#define PIN_MAPPABLE BIT_ULL(1) +#define PIN_ZONE_4G BIT_ULL(2) +#define PIN_NONFAULT BIT_ULL(3) +#define PIN_NOEVICT BIT_ULL(4) + +#define PIN_MBZ BIT_ULL(5) /* I915_VMA_PIN_OVERFLOW */ +#define PIN_GLOBAL BIT_ULL(6) /* I915_VMA_GLOBAL_BIND */ +#define PIN_USER BIT_ULL(7) /* I915_VMA_LOCAL_BIND */ +#define PIN_UPDATE BIT_ULL(8) + +#define PIN_HIGH BIT_ULL(9) +#define PIN_OFFSET_BIAS BIT_ULL(10) +#define PIN_OFFSET_FIXED BIT_ULL(11) #define PIN_OFFSET_MASK (-I915_GTT_PAGE_SIZE) #endif diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 7c491ea3d052..e31c27e45734 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -2095,8 +2095,12 @@ enum i915_power_well_id { /* ICL PHY DFLEX registers */ #define PORT_TX_DFLEXDPMLE1 _MMIO(0x1638C0) -#define DFLEXDPMLE1_DPMLETC_MASK(n) (0xf << (4 * (n))) -#define DFLEXDPMLE1_DPMLETC(n, x) ((x) << (4 * (n))) +#define DFLEXDPMLE1_DPMLETC_MASK(tc_port) (0xf << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML0(tc_port) (1 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML1_0(tc_port) (3 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3(tc_port) (8 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_2(tc_port) (12 << (4 * (tc_port))) +#define DFLEXDPMLE1_DPMLETC_ML3_0(tc_port) (15 << (4 * (tc_port))) /* BXT PHY Ref registers */ #define _PORT_REF_DW3_A 0x16218C @@ -4593,12 +4597,12 @@ enum { #define DRM_DIP_ENABLE (1 << 28) #define PSR_VSC_BIT_7_SET (1 << 27) -#define VSC_SELECT_MASK (0x3 << 26) -#define VSC_SELECT_SHIFT 26 -#define VSC_DIP_HW_HEA_DATA (0 << 26) -#define VSC_DIP_HW_HEA_SW_DATA (1 << 26) -#define VSC_DIP_HW_DATA_SW_HEA (2 << 26) -#define VSC_DIP_SW_HEA_DATA (3 << 26) +#define VSC_SELECT_MASK (0x3 << 25) +#define VSC_SELECT_SHIFT 25 +#define VSC_DIP_HW_HEA_DATA (0 << 25) +#define VSC_DIP_HW_HEA_SW_DATA (1 << 25) +#define VSC_DIP_HW_DATA_SW_HEA (2 << 25) +#define VSC_DIP_SW_HEA_DATA (3 << 25) #define VDIP_ENABLE_PPS (1 << 24) /* Panel power sequencing */ diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 769f3f586661..ee3ca2de983b 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -144,6 +144,9 @@ static const struct { /* HDMI N/CTS table */ #define TMDS_297M 297000 #define TMDS_296M 296703 +#define TMDS_594M 594000 +#define TMDS_593M 593407 + static const struct { int sample_rate; int clock; @@ -164,6 +167,20 @@ static const struct { { 176400, TMDS_297M, 18816, 247500 }, { 192000, TMDS_296M, 23296, 281250 }, { 192000, TMDS_297M, 20480, 247500 }, + { 44100, TMDS_593M, 8918, 937500 }, + { 44100, TMDS_594M, 9408, 990000 }, + { 48000, TMDS_593M, 5824, 562500 }, + { 48000, TMDS_594M, 6144, 594000 }, + { 32000, TMDS_593M, 5824, 843750 }, + { 32000, TMDS_594M, 3072, 445500 }, + { 88200, TMDS_593M, 17836, 937500 }, + { 88200, TMDS_594M, 18816, 990000 }, + { 96000, TMDS_593M, 11648, 562500 }, + { 96000, TMDS_594M, 12288, 594000 }, + { 176400, TMDS_593M, 35672, 937500 }, + { 176400, TMDS_594M, 37632, 990000 }, + { 192000, TMDS_593M, 23296, 562500 }, + { 192000, TMDS_594M, 24576, 594000 }, }; /* get AUD_CONFIG_PIXEL_CLOCK_HDMI_* value for mode */ diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c index 29075c763428..8d74276029e6 100644 --- a/drivers/gpu/drm/i915/intel_cdclk.c +++ b/drivers/gpu/drm/i915/intel_cdclk.c @@ -2138,16 +2138,8 @@ void intel_set_cdclk(struct drm_i915_private *dev_priv, static int intel_pixel_rate_to_cdclk(struct drm_i915_private *dev_priv, int pixel_rate) { - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return DIV_ROUND_UP(pixel_rate, 2); - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Avoid using a pixel clock that is more than 99% of the cdclk - * as a temporary workaround. Use a higher cdclk instead. (Note that - * intel_compute_max_dotclk() limits the max pixel clock to 99% of max - * cdclk.) - */ - return DIV_ROUND_UP(pixel_rate * 100, 2 * 99); else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return pixel_rate; @@ -2543,14 +2535,8 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) { int max_cdclk_freq = dev_priv->max_cdclk_freq; - if (INTEL_GEN(dev_priv) >= 10) + if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) return 2 * max_cdclk_freq; - else if (IS_GEMINILAKE(dev_priv)) - /* - * FIXME: Limiting to 99% as a temporary workaround. See - * intel_min_cdclk() for details. - */ - return 2 * max_cdclk_freq * 99 / 100; else if (IS_GEN9(dev_priv) || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) return max_cdclk_freq; diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 9741cc419e1b..23d8008a93bb 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -12768,17 +12768,12 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_check_cpu_fifo_underruns(dev_priv); intel_check_pch_fifo_underruns(dev_priv); - if (!new_crtc_state->active) { - /* - * Make sure we don't call initial_watermarks - * for ILK-style watermark updates. - * - * No clue what this is supposed to achieve. - */ - if (INTEL_GEN(dev_priv) >= 9) - dev_priv->display.initial_watermarks(intel_state, - to_intel_crtc_state(new_crtc_state)); - } + /* FIXME unify this for all platforms */ + if (!new_crtc_state->active && + !HAS_GMCH_DISPLAY(dev_priv) && + dev_priv->display.initial_watermarks) + dev_priv->display.initial_watermarks(intel_state, + to_intel_crtc_state(new_crtc_state)); } } @@ -14646,7 +14641,7 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb, fb->height < SKL_MIN_YUV_420_SRC_H || (fb->width % 4) != 0 || (fb->height % 4) != 0)) { DRM_DEBUG_KMS("src dimensions not correct for NV12\n"); - return -EINVAL; + goto err; } for (i = 0; i < fb->format->num_planes; i++) { diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c index cdf19553ffac..5d5336fbe7b0 100644 --- a/drivers/gpu/drm/i915/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/intel_lpe_audio.c @@ -297,8 +297,10 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv) lpe_audio_platdev_destroy(dev_priv); irq_free_desc(dev_priv->lpe_audio.irq); -} + dev_priv->lpe_audio.irq = -1; + dev_priv->lpe_audio.platdev = NULL; +} /** * intel_lpe_audio_notify() - notify lpe audio event diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 1db9b8328275..245f0022bcfd 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2881,8 +2881,7 @@ static void intel_read_wm_latency(struct drm_i915_private *dev_priv, * any underrun. If not able to get Dimm info assume 16GB dimm * to avoid any underrun. */ - if (!dev_priv->dram_info.valid_dimm || - dev_priv->dram_info.is_16gb_dimm) + if (dev_priv->dram_info.is_16gb_dimm) wm[0] += 1; } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c index 8d03f64eabd7..5c22f2c8d4cf 100644 --- a/drivers/gpu/drm/i915/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/selftests/huge_pages.c @@ -551,7 +551,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) err = igt_check_page_sizes(vma); if (vma->page_sizes.gtt != I915_GTT_PAGE_SIZE_4K) { - pr_err("page_sizes.gtt=%u, expected %lu\n", + pr_err("page_sizes.gtt=%u, expected %llu\n", vma->page_sizes.gtt, I915_GTT_PAGE_SIZE_4K); err = -EINVAL; } diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c index 8e2e269db97e..127d81513671 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c @@ -1337,7 +1337,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 1) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1386,7 +1386,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != total || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 2) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, total, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; @@ -1430,7 +1430,7 @@ static int igt_gtt_reserve(void *arg) GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); if (vma->node.start != offset || vma->node.size != 2*I915_GTT_PAGE_SIZE) { - pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %lx)\n", + pr_err("i915_gem_gtt_reserve (pass 3) placement failed, found (%llx + %llx), expected (%llx + %llx)\n", vma->node.start, vma->node.size, offset, 2*I915_GTT_PAGE_SIZE); err = -EINVAL; diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c index af7dcb6da351..e7eb0d1e17be 100644 --- a/drivers/gpu/drm/sun4i/sun4i_lvds.c +++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c @@ -75,7 +75,7 @@ static void sun4i_lvds_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -88,7 +88,7 @@ static void sun4i_lvds_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling LVDS output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c index bf068da6b12e..f4a22689eb54 100644 --- a/drivers/gpu/drm/sun4i/sun4i_rgb.c +++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c @@ -135,7 +135,7 @@ static void sun4i_rgb_encoder_enable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Enabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_prepare(tcon->panel); drm_panel_enable(tcon->panel); } @@ -148,7 +148,7 @@ static void sun4i_rgb_encoder_disable(struct drm_encoder *encoder) DRM_DEBUG_DRIVER("Disabling RGB output\n"); - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { drm_panel_disable(tcon->panel); drm_panel_unprepare(tcon->panel); } diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index c78cd35a1294..f949287d926c 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -491,7 +491,8 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, sun4i_tcon0_mode_set_common(tcon, mode); /* Set dithering if needed */ - sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); + if (tcon->panel) + sun4i_tcon0_mode_set_dithering(tcon, tcon->panel->connector); /* Adjust clock delay */ clk_delay = sun4i_tcon_get_clk_delay(mode, 0); @@ -555,7 +556,7 @@ static void sun4i_tcon0_mode_set_rgb(struct sun4i_tcon *tcon, * Following code is a way to avoid quirks all around TCON * and DOTCLOCK drivers. */ - if (!IS_ERR(tcon->panel)) { + if (tcon->panel) { struct drm_panel *panel = tcon->panel; struct drm_connector *connector = panel->connector; struct drm_display_info display_info = connector->display_info; diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c index cf2a18571d48..a132c37d7334 100644 --- a/drivers/gpu/vga/vga_switcheroo.c +++ b/drivers/gpu/vga/vga_switcheroo.c @@ -380,6 +380,9 @@ int vga_switcheroo_register_audio_client(struct pci_dev *pdev, mutex_unlock(&vgasr_mutex); return -EINVAL; } + /* notify if GPU has been already bound */ + if (ops->gpu_bound) + ops->gpu_bound(pdev, id); } mutex_unlock(&vgasr_mutex); diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index aec253b44156..3cd7229b6e54 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -660,6 +660,20 @@ exit: return ret; } +static int alps_sp_open(struct input_dev *dev) +{ + struct hid_device *hid = input_get_drvdata(dev); + + return hid_hw_open(hid); +} + +static void alps_sp_close(struct input_dev *dev) +{ + struct hid_device *hid = input_get_drvdata(dev); + + hid_hw_close(hid); +} + static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) { struct alps_dev *data = hid_get_drvdata(hdev); @@ -733,6 +747,10 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) input2->id.version = input->id.version; input2->dev.parent = input->dev.parent; + input_set_drvdata(input2, hdev); + input2->open = alps_sp_open; + input2->close = alps_sp_close; + __set_bit(EV_KEY, input2->evbit); data->sp_btn_cnt = (data->sp_btn_info & 0x0F); for (i = 0; i < data->sp_btn_cnt; i++) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index dc6d6477e961..a1fa2fc8c9b5 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -359,6 +359,9 @@ static bool asus_kbd_wmi_led_control_present(struct hid_device *hdev) u32 value; int ret; + if (!IS_ENABLED(CONFIG_ASUS_WMI)) + return false; + ret = asus_wmi_evaluate_method(ASUS_WMI_METHODID_DSTS2, ASUS_WMI_DEVID_KBD_BACKLIGHT, 0, &value); hid_dbg(hdev, "WMI backlight check: rc %d value %x", ret, value); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index f63489c882bb..c0d668944dbe 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -927,6 +927,9 @@ #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003 0x3003 #define USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008 0x3008 +#define I2C_VENDOR_ID_RAYDIUM 0x2386 +#define I2C_PRODUCT_ID_RAYDIUM_4B33 0x4b33 + #define USB_VENDOR_ID_RAZER 0x1532 #define USB_DEVICE_ID_RAZER_BLADE_14 0x011D diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 52c3b01917e7..8237dd86fb17 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -107,7 +107,6 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_MCS, USB_DEVICE_ID_MCS_GAMEPADBLOCK), HID_QUIRK_MULTI_INPUT }, - { HID_USB_DEVICE(USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2), HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 4aab96cf0818..3cde7c1b9c33 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -49,6 +49,7 @@ #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0) #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1) #define I2C_HID_QUIRK_NO_RUNTIME_PM BIT(2) +#define I2C_HID_QUIRK_DELAY_AFTER_SLEEP BIT(3) /* flags */ #define I2C_HID_STARTED 0 @@ -158,6 +159,8 @@ struct i2c_hid { bool irq_wake_enabled; struct mutex reset_lock; + + unsigned long sleep_delay; }; static const struct i2c_hid_quirks { @@ -172,6 +175,8 @@ static const struct i2c_hid_quirks { { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, I2C_HID_QUIRK_NO_IRQ_AFTER_RESET | I2C_HID_QUIRK_NO_RUNTIME_PM }, + { I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_4B33, + I2C_HID_QUIRK_DELAY_AFTER_SLEEP }, { 0, 0 } }; @@ -387,6 +392,7 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) { struct i2c_hid *ihid = i2c_get_clientdata(client); int ret; + unsigned long now, delay; i2c_hid_dbg(ihid, "%s\n", __func__); @@ -404,9 +410,22 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state) goto set_pwr_exit; } + if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && + power_state == I2C_HID_PWR_ON) { + now = jiffies; + if (time_after(ihid->sleep_delay, now)) { + delay = jiffies_to_usecs(ihid->sleep_delay - now); + usleep_range(delay, delay + 1); + } + } + ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state, 0, NULL, 0, NULL, 0); + if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP && + power_state == I2C_HID_PWR_SLEEP) + ihid->sleep_delay = jiffies + msecs_to_jiffies(20); + if (ret) dev_err(&client->dev, "failed to change power setting.\n"); diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c index cac262a912c1..89f2976f9c53 100644 --- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c +++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c @@ -331,6 +331,14 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = { .driver_data = (void *)&sipodev_desc }, { + .ident = "Direkt-Tek DTLAPY133-1", + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "DTLAPY133-1"), + }, + .driver_data = (void *)&sipodev_desc + }, + { .ident = "Mediacom Flexbook Edge 11", .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "MEDIACOM"), diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c index 23872d08308c..a746017fac17 100644 --- a/drivers/hid/usbhid/hiddev.c +++ b/drivers/hid/usbhid/hiddev.c @@ -512,14 +512,24 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd, if (cmd == HIDIOCGCOLLECTIONINDEX) { if (uref->usage_index >= field->maxusage) goto inval; + uref->usage_index = + array_index_nospec(uref->usage_index, + field->maxusage); } else if (uref->usage_index >= field->report_count) goto inval; } - if ((cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) && - (uref_multi->num_values > HID_MAX_MULTI_USAGES || - uref->usage_index + uref_multi->num_values > field->report_count)) - goto inval; + if (cmd == HIDIOCGUSAGES || cmd == HIDIOCSUSAGES) { + if (uref_multi->num_values > HID_MAX_MULTI_USAGES || + uref->usage_index + uref_multi->num_values > + field->report_count) + goto inval; + + uref->usage_index = + array_index_nospec(uref->usage_index, + field->report_count - + uref_multi->num_values); + } switch (cmd) { case HIDIOCGUSAGE: diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 975c95169884..84f61cec6319 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -649,8 +649,10 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, if (info[i]->config[j] & HWMON_T_INPUT) { err = hwmon_thermal_add_sensor(dev, hwdev, j); - if (err) - goto free_device; + if (err) { + device_unregister(hdev); + goto ida_remove; + } } } } @@ -658,8 +660,6 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, return hdev; -free_device: - device_unregister(hdev); free_hwmon: kfree(hwdev); ida_remove: diff --git a/drivers/hwmon/ibmpowernv.c b/drivers/hwmon/ibmpowernv.c index 0ccca87f5271..293dd1c6c7b3 100644 --- a/drivers/hwmon/ibmpowernv.c +++ b/drivers/hwmon/ibmpowernv.c @@ -181,7 +181,7 @@ static ssize_t show_label(struct device *dev, struct device_attribute *devattr, return sprintf(buf, "%s\n", sdata->label); } -static int __init get_logical_cpu(int hwcpu) +static int get_logical_cpu(int hwcpu) { int cpu; @@ -192,9 +192,8 @@ static int __init get_logical_cpu(int hwcpu) return -ENOENT; } -static void __init make_sensor_label(struct device_node *np, - struct sensor_data *sdata, - const char *label) +static void make_sensor_label(struct device_node *np, + struct sensor_data *sdata, const char *label) { u32 id; size_t n; diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig index 56ccb1ea7da5..f2c681971201 100644 --- a/drivers/i2c/busses/Kconfig +++ b/drivers/i2c/busses/Kconfig @@ -224,6 +224,15 @@ config I2C_NFORCE2_S4985 This driver can also be built as a module. If so, the module will be called i2c-nforce2-s4985. +config I2C_NVIDIA_GPU + tristate "NVIDIA GPU I2C controller" + depends on PCI + help + If you say yes to this option, support will be included for the + NVIDIA GPU I2C controller which is used to communicate with the GPU's + Type-C controller. This driver can also be built as a module called + i2c-nvidia-gpu. + config I2C_SIS5595 tristate "SiS 5595" depends on PCI @@ -752,7 +761,7 @@ config I2C_OCORES config I2C_OMAP tristate "OMAP I2C adapter" - depends on ARCH_OMAP + depends on ARCH_OMAP || ARCH_K3 default y if MACH_OMAP_H3 || MACH_OMAP_OSK help If you say yes to this option, support will be included for the diff --git a/drivers/i2c/busses/Makefile b/drivers/i2c/busses/Makefile index 18b26af82b1c..5f0cb6915969 100644 --- a/drivers/i2c/busses/Makefile +++ b/drivers/i2c/busses/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_I2C_ISCH) += i2c-isch.o obj-$(CONFIG_I2C_ISMT) += i2c-ismt.o obj-$(CONFIG_I2C_NFORCE2) += i2c-nforce2.o obj-$(CONFIG_I2C_NFORCE2_S4985) += i2c-nforce2-s4985.o +obj-$(CONFIG_I2C_NVIDIA_GPU) += i2c-nvidia-gpu.o obj-$(CONFIG_I2C_PIIX4) += i2c-piix4.o obj-$(CONFIG_I2C_SIS5595) += i2c-sis5595.o obj-$(CONFIG_I2C_SIS630) += i2c-sis630.o diff --git a/drivers/i2c/busses/i2c-nvidia-gpu.c b/drivers/i2c/busses/i2c-nvidia-gpu.c new file mode 100644 index 000000000000..8822357bca0c --- /dev/null +++ b/drivers/i2c/busses/i2c-nvidia-gpu.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Nvidia GPU I2C controller Driver + * + * Copyright (C) 2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta <[email protected]> + */ +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> + +#include <asm/unaligned.h> + +/* I2C definitions */ +#define I2C_MST_CNTL 0x00 +#define I2C_MST_CNTL_GEN_START BIT(0) +#define I2C_MST_CNTL_GEN_STOP BIT(1) +#define I2C_MST_CNTL_CMD_READ (1 << 2) +#define I2C_MST_CNTL_CMD_WRITE (2 << 2) +#define I2C_MST_CNTL_BURST_SIZE_SHIFT 6 +#define I2C_MST_CNTL_GEN_NACK BIT(28) +#define I2C_MST_CNTL_STATUS GENMASK(30, 29) +#define I2C_MST_CNTL_STATUS_OKAY (0 << 29) +#define I2C_MST_CNTL_STATUS_NO_ACK (1 << 29) +#define I2C_MST_CNTL_STATUS_TIMEOUT (2 << 29) +#define I2C_MST_CNTL_STATUS_BUS_BUSY (3 << 29) +#define I2C_MST_CNTL_CYCLE_TRIGGER BIT(31) + +#define I2C_MST_ADDR 0x04 + +#define I2C_MST_I2C0_TIMING 0x08 +#define I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ 0x10e +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT 16 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX 255 +#define I2C_MST_I2C0_TIMING_TIMEOUT_CHECK BIT(24) + +#define I2C_MST_DATA 0x0c + +#define I2C_MST_HYBRID_PADCTL 0x20 +#define I2C_MST_HYBRID_PADCTL_MODE_I2C BIT(0) +#define I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV BIT(14) +#define I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV BIT(15) + +struct gpu_i2c_dev { + struct device *dev; + void __iomem *regs; + struct i2c_adapter adapter; + struct i2c_board_info *gpu_ccgx_ucsi; +}; + +static void gpu_enable_i2c_bus(struct gpu_i2c_dev *i2cd) +{ + u32 val; + + /* enable I2C */ + val = readl(i2cd->regs + I2C_MST_HYBRID_PADCTL); + val |= I2C_MST_HYBRID_PADCTL_MODE_I2C | + I2C_MST_HYBRID_PADCTL_I2C_SCL_INPUT_RCV | + I2C_MST_HYBRID_PADCTL_I2C_SDA_INPUT_RCV; + writel(val, i2cd->regs + I2C_MST_HYBRID_PADCTL); + + /* enable 100KHZ mode */ + val = I2C_MST_I2C0_TIMING_SCL_PERIOD_100KHZ; + val |= (I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT_MAX + << I2C_MST_I2C0_TIMING_TIMEOUT_CLK_CNT); + val |= I2C_MST_I2C0_TIMING_TIMEOUT_CHECK; + writel(val, i2cd->regs + I2C_MST_I2C0_TIMING); +} + +static int gpu_i2c_check_status(struct gpu_i2c_dev *i2cd) +{ + unsigned long target = jiffies + msecs_to_jiffies(1000); + u32 val; + + do { + val = readl(i2cd->regs + I2C_MST_CNTL); + if (!(val & I2C_MST_CNTL_CYCLE_TRIGGER)) + break; + if ((val & I2C_MST_CNTL_STATUS) != + I2C_MST_CNTL_STATUS_BUS_BUSY) + break; + usleep_range(500, 600); + } while (time_is_after_jiffies(target)); + + if (time_is_before_jiffies(target)) { + dev_err(i2cd->dev, "i2c timeout error %x\n", val); + return -ETIME; + } + + val = readl(i2cd->regs + I2C_MST_CNTL); + switch (val & I2C_MST_CNTL_STATUS) { + case I2C_MST_CNTL_STATUS_OKAY: + return 0; + case I2C_MST_CNTL_STATUS_NO_ACK: + return -EIO; + case I2C_MST_CNTL_STATUS_TIMEOUT: + return -ETIME; + default: + return 0; + } +} + +static int gpu_i2c_read(struct gpu_i2c_dev *i2cd, u8 *data, u16 len) +{ + int status; + u32 val; + + val = I2C_MST_CNTL_GEN_START | I2C_MST_CNTL_CMD_READ | + (len << I2C_MST_CNTL_BURST_SIZE_SHIFT) | + I2C_MST_CNTL_CYCLE_TRIGGER | I2C_MST_CNTL_GEN_NACK; + writel(val, i2cd->regs + I2C_MST_CNTL); + + status = gpu_i2c_check_status(i2cd); + if (status < 0) + return status; + + val = readl(i2cd->regs + I2C_MST_DATA); + switch (len) { + case 1: + data[0] = val; + break; + case 2: + put_unaligned_be16(val, data); + break; + case 3: + put_unaligned_be16(val >> 8, data); + data[2] = val; + break; + case 4: + put_unaligned_be32(val, data); + break; + default: + break; + } + return status; +} + +static int gpu_i2c_start(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_START, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_stop(struct gpu_i2c_dev *i2cd) +{ + writel(I2C_MST_CNTL_GEN_STOP, i2cd->regs + I2C_MST_CNTL); + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_write(struct gpu_i2c_dev *i2cd, u8 data) +{ + u32 val; + + writel(data, i2cd->regs + I2C_MST_DATA); + + val = I2C_MST_CNTL_CMD_WRITE | (1 << I2C_MST_CNTL_BURST_SIZE_SHIFT); + writel(val, i2cd->regs + I2C_MST_CNTL); + + return gpu_i2c_check_status(i2cd); +} + +static int gpu_i2c_master_xfer(struct i2c_adapter *adap, + struct i2c_msg *msgs, int num) +{ + struct gpu_i2c_dev *i2cd = i2c_get_adapdata(adap); + int status, status2; + int i, j; + + /* + * The controller supports maximum 4 byte read due to known + * limitation of sending STOP after every read. + */ + for (i = 0; i < num; i++) { + if (msgs[i].flags & I2C_M_RD) { + /* program client address before starting read */ + writel(msgs[i].addr, i2cd->regs + I2C_MST_ADDR); + /* gpu_i2c_read has implicit start */ + status = gpu_i2c_read(i2cd, msgs[i].buf, msgs[i].len); + if (status < 0) + goto stop; + } else { + u8 addr = i2c_8bit_addr_from_msg(msgs + i); + + status = gpu_i2c_start(i2cd); + if (status < 0) { + if (i == 0) + return status; + goto stop; + } + + status = gpu_i2c_write(i2cd, addr); + if (status < 0) + goto stop; + + for (j = 0; j < msgs[i].len; j++) { + status = gpu_i2c_write(i2cd, msgs[i].buf[j]); + if (status < 0) + goto stop; + } + } + } + status = gpu_i2c_stop(i2cd); + if (status < 0) + return status; + + return i; +stop: + status2 = gpu_i2c_stop(i2cd); + if (status2 < 0) + dev_err(i2cd->dev, "i2c stop failed %d\n", status2); + return status; +} + +static const struct i2c_adapter_quirks gpu_i2c_quirks = { + .max_read_len = 4, + .flags = I2C_AQ_COMB_WRITE_THEN_READ, +}; + +static u32 gpu_i2c_functionality(struct i2c_adapter *adap) +{ + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; +} + +static const struct i2c_algorithm gpu_i2c_algorithm = { + .master_xfer = gpu_i2c_master_xfer, + .functionality = gpu_i2c_functionality, +}; + +/* + * This driver is for Nvidia GPU cards with USB Type-C interface. + * We want to identify the cards using vendor ID and class code only + * to avoid dependency of adding product id for any new card which + * requires this driver. + * Currently there is no class code defined for UCSI device over PCI + * so using UNKNOWN class for now and it will be updated when UCSI + * over PCI gets a class code. + * There is no other NVIDIA cards with UNKNOWN class code. Even if the + * driver gets loaded for an undesired card then eventually i2c_read() + * (initiated from UCSI i2c_client) will timeout or UCSI commands will + * timeout. + */ +#define PCI_CLASS_SERIAL_UNKNOWN 0x0c80 +static const struct pci_device_id gpu_i2c_ids[] = { + { PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID, + PCI_CLASS_SERIAL_UNKNOWN << 8, 0xffffff00}, + { } +}; +MODULE_DEVICE_TABLE(pci, gpu_i2c_ids); + +static int gpu_populate_client(struct gpu_i2c_dev *i2cd, int irq) +{ + struct i2c_client *ccgx_client; + + i2cd->gpu_ccgx_ucsi = devm_kzalloc(i2cd->dev, + sizeof(*i2cd->gpu_ccgx_ucsi), + GFP_KERNEL); + if (!i2cd->gpu_ccgx_ucsi) + return -ENOMEM; + + strlcpy(i2cd->gpu_ccgx_ucsi->type, "ccgx-ucsi", + sizeof(i2cd->gpu_ccgx_ucsi->type)); + i2cd->gpu_ccgx_ucsi->addr = 0x8; + i2cd->gpu_ccgx_ucsi->irq = irq; + ccgx_client = i2c_new_device(&i2cd->adapter, i2cd->gpu_ccgx_ucsi); + if (!ccgx_client) + return -ENODEV; + + return 0; +} + +static int gpu_i2c_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct gpu_i2c_dev *i2cd; + int status; + + i2cd = devm_kzalloc(&pdev->dev, sizeof(*i2cd), GFP_KERNEL); + if (!i2cd) + return -ENOMEM; + + i2cd->dev = &pdev->dev; + dev_set_drvdata(&pdev->dev, i2cd); + + status = pcim_enable_device(pdev); + if (status < 0) { + dev_err(&pdev->dev, "pcim_enable_device failed %d\n", status); + return status; + } + + pci_set_master(pdev); + + i2cd->regs = pcim_iomap(pdev, 0, 0); + if (!i2cd->regs) { + dev_err(&pdev->dev, "pcim_iomap failed\n"); + return -ENOMEM; + } + + status = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (status < 0) { + dev_err(&pdev->dev, "pci_alloc_irq_vectors err %d\n", status); + return status; + } + + gpu_enable_i2c_bus(i2cd); + + i2c_set_adapdata(&i2cd->adapter, i2cd); + i2cd->adapter.owner = THIS_MODULE; + strlcpy(i2cd->adapter.name, "NVIDIA GPU I2C adapter", + sizeof(i2cd->adapter.name)); + i2cd->adapter.algo = &gpu_i2c_algorithm; + i2cd->adapter.quirks = &gpu_i2c_quirks; + i2cd->adapter.dev.parent = &pdev->dev; + status = i2c_add_adapter(&i2cd->adapter); + if (status < 0) + goto free_irq_vectors; + + status = gpu_populate_client(i2cd, pdev->irq); + if (status < 0) { + dev_err(&pdev->dev, "gpu_populate_client failed %d\n", status); + goto del_adapter; + } + + return 0; + +del_adapter: + i2c_del_adapter(&i2cd->adapter); +free_irq_vectors: + pci_free_irq_vectors(pdev); + return status; +} + +static void gpu_i2c_remove(struct pci_dev *pdev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(&pdev->dev); + + i2c_del_adapter(&i2cd->adapter); + pci_free_irq_vectors(pdev); +} + +static int gpu_i2c_resume(struct device *dev) +{ + struct gpu_i2c_dev *i2cd = dev_get_drvdata(dev); + + gpu_enable_i2c_bus(i2cd); + return 0; +} + +static UNIVERSAL_DEV_PM_OPS(gpu_i2c_driver_pm, NULL, gpu_i2c_resume, NULL); + +static struct pci_driver gpu_i2c_driver = { + .name = "nvidia-gpu", + .id_table = gpu_i2c_ids, + .probe = gpu_i2c_probe, + .remove = gpu_i2c_remove, + .driver = { + .pm = &gpu_i2c_driver_pm, + }, +}; + +module_pci_driver(gpu_i2c_driver); + +MODULE_AUTHOR("Ajay Gupta <[email protected]>"); +MODULE_DESCRIPTION("Nvidia GPU I2C controller Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c index 527f55c8c4c7..db075bc0d952 100644 --- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -571,18 +571,19 @@ static int geni_i2c_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "i2c fifo/se-dma mode. fifo depth:%d\n", tx_depth); - ret = i2c_add_adapter(&gi2c->adap); - if (ret) { - dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); - return ret; - } - gi2c->suspended = 1; pm_runtime_set_suspended(gi2c->se.dev); pm_runtime_set_autosuspend_delay(gi2c->se.dev, I2C_AUTO_SUSPEND_DELAY); pm_runtime_use_autosuspend(gi2c->se.dev); pm_runtime_enable(gi2c->se.dev); + ret = i2c_add_adapter(&gi2c->adap); + if (ret) { + dev_err(&pdev->dev, "Error adding i2c adapter %d\n", ret); + pm_runtime_disable(gi2c->se.dev); + return ret; + } + return 0; } @@ -590,8 +591,8 @@ static int geni_i2c_remove(struct platform_device *pdev) { struct geni_i2c_dev *gi2c = platform_get_drvdata(pdev); - pm_runtime_disable(gi2c->se.dev); i2c_del_adapter(&gi2c->adap); + pm_runtime_disable(gi2c->se.dev); return 0; } diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c index ce7acd115dd8..1870cf87afe1 100644 --- a/drivers/leds/trigger/ledtrig-pattern.c +++ b/drivers/leds/trigger/ledtrig-pattern.c @@ -75,8 +75,6 @@ static void pattern_trig_timer_function(struct timer_list *t) { struct pattern_trig_data *data = from_timer(data, t, timer); - mutex_lock(&data->lock); - for (;;) { if (!data->is_indefinite && !data->repeat) break; @@ -87,9 +85,10 @@ static void pattern_trig_timer_function(struct timer_list *t) data->curr->brightness); mod_timer(&data->timer, jiffies + msecs_to_jiffies(data->curr->delta_t)); - - /* Skip the tuple with zero duration */ - pattern_trig_update_patterns(data); + if (!data->next->delta_t) { + /* Skip the tuple with zero duration */ + pattern_trig_update_patterns(data); + } /* Select next tuple */ pattern_trig_update_patterns(data); } else { @@ -116,8 +115,6 @@ static void pattern_trig_timer_function(struct timer_list *t) break; } - - mutex_unlock(&data->lock); } static int pattern_trig_start_pattern(struct led_classdev *led_cdev) @@ -176,14 +173,10 @@ static ssize_t repeat_store(struct device *dev, struct device_attribute *attr, if (res < -1 || res == 0) return -EINVAL; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); @@ -234,14 +227,10 @@ static ssize_t pattern_trig_store_patterns(struct led_classdev *led_cdev, struct pattern_trig_data *data = led_cdev->trigger_data; int ccount, cr, offset = 0, err = 0; - /* - * Clear previous patterns' performence firstly, and remove the timer - * without mutex lock to avoid dead lock. - */ - del_timer_sync(&data->timer); - mutex_lock(&data->lock); + del_timer_sync(&data->timer); + if (data->is_hw_pattern) led_cdev->pattern_clear(led_cdev); diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c index 17d3bc917562..bc8418801224 100644 --- a/drivers/macintosh/macio_asic.c +++ b/drivers/macintosh/macio_asic.c @@ -220,8 +220,8 @@ static int macio_resource_quirks(struct device_node *np, struct resource *res, return 1; /* Some older IDE resources have bogus sizes */ - if (!(strcmp(np->name, "IDE") && strcmp(np->name, "ATA") && - strcmp(np->type, "ide") && strcmp(np->type, "ata"))) { + if (!strcmp(np->name, "IDE") || !strcmp(np->name, "ATA") || + of_node_is_type(np, "ide") || of_node_is_type(np, "ata")) { if (index == 0 && (res->end - res->start) > 0xfff) res->end = res->start + 0xfff; if (index == 1 && (res->end - res->start) > 0xff) diff --git a/drivers/macintosh/macio_sysfs.c b/drivers/macintosh/macio_sysfs.c index d2451e58acb9..27f5eefc508f 100644 --- a/drivers/macintosh/macio_sysfs.c +++ b/drivers/macintosh/macio_sysfs.c @@ -3,17 +3,6 @@ #include <linux/stat.h> #include <asm/macio.h> - -#define macio_config_of_attr(field, format_string) \ -static ssize_t \ -field##_show (struct device *dev, struct device_attribute *attr, \ - char *buf) \ -{ \ - struct macio_dev *mdev = to_macio_device (dev); \ - return sprintf (buf, format_string, mdev->ofdev.dev.of_node->field); \ -} \ -static DEVICE_ATTR_RO(field); - static ssize_t compatible_show (struct device *dev, struct device_attribute *attr, char *buf) { @@ -65,7 +54,12 @@ static ssize_t name_show(struct device *dev, } static DEVICE_ATTR_RO(name); -macio_config_of_attr (type, "%s\n"); +static ssize_t type_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", of_node_get_device_type(dev->of_node)); +} +static DEVICE_ATTR_RO(type); static struct attribute *macio_dev_attrs[] = { &dev_attr_name.attr, diff --git a/drivers/macintosh/windfarm_fcu_controls.c b/drivers/macintosh/windfarm_fcu_controls.c index fab7a21e9577..629f19875d7f 100644 --- a/drivers/macintosh/windfarm_fcu_controls.c +++ b/drivers/macintosh/windfarm_fcu_controls.c @@ -425,25 +425,25 @@ static void wf_fcu_lookup_fans(struct wf_fcu_priv *pv) { "CPU B 2", "cpu-fan-b-1", }, { "CPU B 3", "cpu-fan-c-1", }, }; - struct device_node *np = NULL, *fcu = pv->i2c->dev.of_node; + struct device_node *np, *fcu = pv->i2c->dev.of_node; int i; DBG("Looking up FCU controls in device-tree...\n"); - while ((np = of_get_next_child(fcu, np)) != NULL) { + for_each_child_of_node(fcu, np) { int id, type = -1; const char *loc; const char *name; const u32 *reg; - DBG(" control: %s, type: %s\n", np->name, np->type); + DBG(" control: %pOFn, type: %s\n", np, of_node_get_device_type(np)); /* Detect control type */ - if (!strcmp(np->type, "fan-rpm-control") || - !strcmp(np->type, "fan-rpm")) + if (of_node_is_type(np, "fan-rpm-control") || + of_node_is_type(np, "fan-rpm")) type = FCU_FAN_RPM; - if (!strcmp(np->type, "fan-pwm-control") || - !strcmp(np->type, "fan-pwm")) + if (of_node_is_type(np, "fan-pwm-control") || + of_node_is_type(np, "fan-pwm")) type = FCU_FAN_PWM; /* Only care about fans for now */ if (type == -1) diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c index a0f61eb853c5..b4be718beba8 100644 --- a/drivers/macintosh/windfarm_smu_sat.c +++ b/drivers/macintosh/windfarm_smu_sat.c @@ -197,7 +197,7 @@ static int wf_sat_probe(struct i2c_client *client, struct wf_sat *sat; struct wf_sat_sensor *sens; const u32 *reg; - const char *loc, *type; + const char *loc; u8 chip, core; struct device_node *child; int shift, cpu, index; @@ -220,7 +220,6 @@ static int wf_sat_probe(struct i2c_client *client, child = NULL; while ((child = of_get_next_child(dev, child)) != NULL) { reg = of_get_property(child, "reg", NULL); - type = of_get_property(child, "device_type", NULL); loc = of_get_property(child, "location", NULL); if (reg == NULL || loc == NULL) continue; @@ -249,15 +248,15 @@ static int wf_sat_probe(struct i2c_client *client, continue; } - if (strcmp(type, "voltage-sensor") == 0) { + if (of_node_is_type(child, "voltage-sensor")) { name = "cpu-voltage"; shift = 4; vsens[core] = index; - } else if (strcmp(type, "current-sensor") == 0) { + } else if (of_node_is_type(child, "current-sensor")) { name = "cpu-current"; shift = 8; isens[core] = index; - } else if (strcmp(type, "temp-sensor") == 0) { + } else if (of_node_is_type(child, "temp-sensor")) { name = "cpu-temp"; shift = 10; } else diff --git a/drivers/macintosh/windfarm_smu_sensors.c b/drivers/macintosh/windfarm_smu_sensors.c index 172fd267dcf6..1ba86de93f92 100644 --- a/drivers/macintosh/windfarm_smu_sensors.c +++ b/drivers/macintosh/windfarm_smu_sensors.c @@ -197,15 +197,14 @@ static const struct wf_sensor_ops smu_slotspow_ops = { static struct smu_ad_sensor *smu_ads_create(struct device_node *node) { struct smu_ad_sensor *ads; - const char *c, *l; + const char *l; const u32 *v; ads = kmalloc(sizeof(struct smu_ad_sensor), GFP_KERNEL); if (ads == NULL) return NULL; - c = of_get_property(node, "device_type", NULL); l = of_get_property(node, "location", NULL); - if (c == NULL || l == NULL) + if (l == NULL) goto fail; /* We currently pick the sensors based on the OF name and location @@ -215,7 +214,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) * the names and locations consistents so I'll stick with the names * and locations for now. */ - if (!strcmp(c, "temp-sensor") && + if (of_node_is_type(node, "temp-sensor") && !strcmp(l, "CPU T-Diode")) { ads->sens.ops = &smu_cputemp_ops; ads->sens.name = "cpu-temp"; @@ -224,7 +223,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) SMU_SDB_CPUDIODE_ID); goto fail; } - } else if (!strcmp(c, "current-sensor") && + } else if (of_node_is_type(node, "current-sensor") && !strcmp(l, "CPU Current")) { ads->sens.ops = &smu_cpuamp_ops; ads->sens.name = "cpu-current"; @@ -233,7 +232,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) SMU_SDB_CPUVCP_ID); goto fail; } - } else if (!strcmp(c, "voltage-sensor") && + } else if (of_node_is_type(node, "voltage-sensor") && !strcmp(l, "CPU Voltage")) { ads->sens.ops = &smu_cpuvolt_ops; ads->sens.name = "cpu-voltage"; @@ -242,7 +241,7 @@ static struct smu_ad_sensor *smu_ads_create(struct device_node *node) SMU_SDB_CPUVCP_ID); goto fail; } - } else if (!strcmp(c, "power-sensor") && + } else if (of_node_is_type(node, "power-sensor") && !strcmp(l, "Slots Power")) { ads->sens.ops = &smu_slotspow_ops; ads->sens.name = "slots-power"; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index b66d832d3233..c79ba1c699ad 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1718,7 +1718,6 @@ int cxl_slot_is_switched(struct pci_dev *dev) { struct device_node *np; int depth = 0; - const __be32 *prop; if (!(np = pci_device_to_OF_node(dev))) { pr_err("cxl: np = NULL\n"); @@ -1727,8 +1726,7 @@ int cxl_slot_is_switched(struct pci_dev *dev) of_node_get(np); while (np) { np = of_get_next_parent(np); - prop = of_get_property(np, "device_type", NULL); - if (!prop || strcmp((char *)prop, "pciex")) + if (!of_node_is_type(np, "pciex")) break; depth++; } diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index e514d57a0419..aa983422aa97 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -207,7 +207,7 @@ comment "Disk-On-Chip Device Drivers" config MTD_DOCG3 tristate "M-Systems Disk-On-Chip G3" select BCH - select BCH_CONST_PARAMS + select BCH_CONST_PARAMS if !MTD_NAND_BCH select BITREVERSE help This provides an MTD device driver for the M-Systems DiskOnChip diff --git a/drivers/mtd/maps/sa1100-flash.c b/drivers/mtd/maps/sa1100-flash.c index 784c6e1a0391..fd5fe12d7461 100644 --- a/drivers/mtd/maps/sa1100-flash.c +++ b/drivers/mtd/maps/sa1100-flash.c @@ -221,7 +221,14 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = info->subdev[0].mtd; ret = 0; } else if (info->num_subdev > 1) { - struct mtd_info *cdev[nr]; + struct mtd_info **cdev; + + cdev = kmalloc_array(nr, sizeof(*cdev), GFP_KERNEL); + if (!cdev) { + ret = -ENOMEM; + goto err; + } + /* * We detected multiple devices. Concatenate them together. */ @@ -230,6 +237,7 @@ static struct sa_info *sa1100_setup_mtd(struct platform_device *pdev, info->mtd = mtd_concat_create(cdev, info->num_subdev, plat->name); + kfree(cdev); if (info->mtd == NULL) { ret = -ENXIO; goto err; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index 05bd0779fe9b..71050a0b31df 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -590,7 +590,6 @@ retry: /** * panic_nand_wait - [GENERIC] wait until the command is done - * @mtd: MTD device structure * @chip: NAND chip structure * @timeo: timeout * diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c index e24db817154e..d846428ef038 100644 --- a/drivers/mtd/spi-nor/cadence-quadspi.c +++ b/drivers/mtd/spi-nor/cadence-quadspi.c @@ -996,7 +996,7 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf, err_unmap: dma_unmap_single(nor->dev, dma_dst, len, DMA_FROM_DEVICE); - return 0; + return ret; } static ssize_t cqspi_read(struct spi_nor *nor, loff_t from, diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 9407ca5f9443..3e54e31889c7 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -3250,12 +3250,14 @@ static int spi_nor_init_params(struct spi_nor *nor, memcpy(&sfdp_params, params, sizeof(sfdp_params)); memcpy(&prev_map, &nor->erase_map, sizeof(prev_map)); - if (spi_nor_parse_sfdp(nor, &sfdp_params)) + if (spi_nor_parse_sfdp(nor, &sfdp_params)) { + nor->addr_width = 0; /* restore previous erase map */ memcpy(&nor->erase_map, &prev_map, sizeof(nor->erase_map)); - else + } else { memcpy(params, &sfdp_params, sizeof(*params)); + } } return 0; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ffa37adb7681..333387f1f1fe 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3112,13 +3112,13 @@ static int bond_slave_netdev_event(unsigned long event, case NETDEV_CHANGE: /* For 802.3ad mode only: * Getting invalid Speed/Duplex values here will put slave - * in weird state. So mark it as link-down for the time + * in weird state. So mark it as link-fail for the time * being and let link-monitoring (miimon) set it right when * correct speeds/duplex are available. */ if (bond_update_speed_duplex(slave) && BOND_MODE(bond) == BOND_MODE_8023AD) - slave->link = BOND_LINK_DOWN; + slave->link = BOND_LINK_FAIL; if (BOND_MODE(bond) == BOND_MODE_8023AD) bond_3ad_adapter_speed_duplex_changed(slave); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 54e0ca6ed730..86b6464b4525 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -1117,11 +1117,6 @@ static int ksz_switch_init(struct ksz_device *dev) { int i; - mutex_init(&dev->reg_mutex); - mutex_init(&dev->stats_mutex); - mutex_init(&dev->alu_mutex); - mutex_init(&dev->vlan_mutex); - dev->ds->ops = &ksz_switch_ops; for (i = 0; i < ARRAY_SIZE(ksz_switch_chips); i++) { @@ -1206,6 +1201,11 @@ int ksz_switch_register(struct ksz_device *dev) if (dev->pdata) dev->chip_id = dev->pdata->chip_id; + mutex_init(&dev->reg_mutex); + mutex_init(&dev->stats_mutex); + mutex_init(&dev->alu_mutex); + mutex_init(&dev->vlan_mutex); + if (ksz_switch_detect(dev)) return -EINVAL; diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index d721ccf7d8be..38e399e0f30e 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -567,6 +567,8 @@ int mv88e6xxx_g1_stats_clear(struct mv88e6xxx_chip *chip) if (err) return err; + /* Keep the histogram mode bits */ + val &= MV88E6XXX_G1_STATS_OP_HIST_RX_TX; val |= MV88E6XXX_G1_STATS_OP_BUSY | MV88E6XXX_G1_STATS_OP_FLUSH_ALL; err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_STATS_OP, val); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 6a633c70f603..99ef1daaa4d8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -407,13 +407,13 @@ static void aq_ethtool_get_pauseparam(struct net_device *ndev, struct ethtool_pauseparam *pause) { struct aq_nic_s *aq_nic = netdev_priv(ndev); + u32 fc = aq_nic->aq_nic_cfg.flow_control; pause->autoneg = 0; - if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_RX) - pause->rx_pause = 1; - if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_TX) - pause->tx_pause = 1; + pause->rx_pause = !!(fc & AQ_NIC_FC_RX); + pause->tx_pause = !!(fc & AQ_NIC_FC_TX); + } static int aq_ethtool_set_pauseparam(struct net_device *ndev, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index e8689241204e..a1e70da358ca 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -204,6 +204,10 @@ struct aq_hw_ops { int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version); + int (*hw_set_offload)(struct aq_hw_s *self, + struct aq_nic_cfg_s *aq_nic_cfg); + + int (*hw_set_fc)(struct aq_hw_s *self, u32 fc, u32 tc); }; struct aq_fw_ops { @@ -226,6 +230,8 @@ struct aq_fw_ops { int (*update_stats)(struct aq_hw_s *self); + u32 (*get_flow_control)(struct aq_hw_s *self, u32 *fcmode); + int (*set_flow_control)(struct aq_hw_s *self); int (*set_power)(struct aq_hw_s *self, unsigned int power_state, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index e3ae29e523f0..7c07eef275eb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -99,8 +99,11 @@ static int aq_ndev_set_features(struct net_device *ndev, struct aq_nic_s *aq_nic = netdev_priv(ndev); struct aq_nic_cfg_s *aq_cfg = aq_nic_get_cfg(aq_nic); bool is_lro = false; + int err = 0; + + aq_cfg->features = features; - if (aq_cfg->hw_features & NETIF_F_LRO) { + if (aq_cfg->aq_hw_caps->hw_features & NETIF_F_LRO) { is_lro = features & NETIF_F_LRO; if (aq_cfg->is_lro != is_lro) { @@ -112,8 +115,11 @@ static int aq_ndev_set_features(struct net_device *ndev, } } } + if ((aq_nic->ndev->features ^ features) & NETIF_F_RXCSUM) + err = aq_nic->aq_hw_ops->hw_set_offload(aq_nic->aq_hw, + aq_cfg); - return 0; + return err; } static int aq_ndev_set_mac_address(struct net_device *ndev, void *addr) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 5fed24446687..7abdc0952425 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -118,12 +118,13 @@ void aq_nic_cfg_start(struct aq_nic_s *self) } cfg->link_speed_msk &= cfg->aq_hw_caps->link_speed_msk; - cfg->hw_features = cfg->aq_hw_caps->hw_features; + cfg->features = cfg->aq_hw_caps->hw_features; } static int aq_nic_update_link_status(struct aq_nic_s *self) { int err = self->aq_fw_ops->update_link_status(self->aq_hw); + u32 fc = 0; if (err) return err; @@ -133,6 +134,15 @@ static int aq_nic_update_link_status(struct aq_nic_s *self) AQ_CFG_DRV_NAME, self->link_status.mbps, self->aq_hw->aq_link_status.mbps); aq_nic_update_interrupt_moderation_settings(self); + + /* Driver has to update flow control settings on RX block + * on any link event. + * We should query FW whether it negotiated FC. + */ + if (self->aq_fw_ops->get_flow_control) + self->aq_fw_ops->get_flow_control(self->aq_hw, &fc); + if (self->aq_hw_ops->hw_set_fc) + self->aq_hw_ops->hw_set_fc(self->aq_hw, fc, 0); } self->link_status = self->aq_hw->aq_link_status; @@ -590,7 +600,7 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) } } - if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) { + if (i > 0 && i <= AQ_HW_MULTICAST_ADDRESS_MAX) { packet_filter |= IFF_MULTICAST; self->mc_list.count = i; self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, @@ -772,7 +782,9 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self, ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); - if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX) + /* Asym is when either RX or TX, but not both */ + if (!!(self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX) ^ + !!(self->aq_nic_cfg.flow_control & AQ_NIC_FC_RX)) ethtool_link_ksettings_add_link_mode(cmd, advertising, Asym_Pause); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index c1582f4e8e1b..44ec47a3d60a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -23,7 +23,7 @@ struct aq_vec_s; struct aq_nic_cfg_s { const struct aq_hw_caps_s *aq_hw_caps; - u64 hw_features; + u64 features; u32 rxds; /* rx ring size, descriptors # */ u32 txds; /* tx ring size, descriptors # */ u32 vecs; /* vecs==allocated irqs */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 3db91446cc67..74550ccc7a20 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -172,6 +172,27 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) return !!budget; } +static void aq_rx_checksum(struct aq_ring_s *self, + struct aq_ring_buff_s *buff, + struct sk_buff *skb) +{ + if (!(self->aq_nic->ndev->features & NETIF_F_RXCSUM)) + return; + + if (unlikely(buff->is_cso_err)) { + ++self->stats.rx.errors; + skb->ip_summed = CHECKSUM_NONE; + return; + } + if (buff->is_ip_cso) { + __skb_incr_checksum_unnecessary(skb); + if (buff->is_udp_cso || buff->is_tcp_cso) + __skb_incr_checksum_unnecessary(skb); + } else { + skb->ip_summed = CHECKSUM_NONE; + } +} + #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) int aq_ring_rx_clean(struct aq_ring_s *self, struct napi_struct *napi, @@ -267,18 +288,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, } skb->protocol = eth_type_trans(skb, ndev); - if (unlikely(buff->is_cso_err)) { - ++self->stats.rx.errors; - skb->ip_summed = CHECKSUM_NONE; - } else { - if (buff->is_ip_cso) { - __skb_incr_checksum_unnecessary(skb); - if (buff->is_udp_cso || buff->is_tcp_cso) - __skb_incr_checksum_unnecessary(skb); - } else { - skb->ip_summed = CHECKSUM_NONE; - } - } + + aq_rx_checksum(self, buff, skb); skb_set_hash(skb, buff->rss_hash, buff->is_hash_l4 ? PKT_HASH_TYPE_L4 : diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 76d25d594a0f..f02592f43fe3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -100,12 +100,17 @@ static int hw_atl_b0_hw_reset(struct aq_hw_s *self) return err; } +static int hw_atl_b0_set_fc(struct aq_hw_s *self, u32 fc, u32 tc) +{ + hw_atl_rpb_rx_xoff_en_per_tc_set(self, !!(fc & AQ_NIC_FC_RX), tc); + return 0; +} + static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) { u32 tc = 0U; u32 buff_size = 0U; unsigned int i_priority = 0U; - bool is_rx_flow_control = false; /* TPS Descriptor rate init */ hw_atl_tps_tx_pkt_shed_desc_rate_curr_time_res_set(self, 0x0U); @@ -138,7 +143,6 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) /* QoS Rx buf size per TC */ tc = 0; - is_rx_flow_control = (AQ_NIC_FC_RX & self->aq_nic_cfg->flow_control); buff_size = HW_ATL_B0_RXBUF_MAX; hw_atl_rpb_rx_pkt_buff_size_per_tc_set(self, buff_size, tc); @@ -150,7 +154,8 @@ static int hw_atl_b0_hw_qos_set(struct aq_hw_s *self) (buff_size * (1024U / 32U) * 50U) / 100U, tc); - hw_atl_rpb_rx_xoff_en_per_tc_set(self, is_rx_flow_control ? 1U : 0U, tc); + + hw_atl_b0_set_fc(self, self->aq_nic_cfg->flow_control, tc); /* QoS 802.1p priority -> TC mapping */ for (i_priority = 8U; i_priority--;) @@ -229,8 +234,10 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self, hw_atl_tpo_tcp_udp_crc_offload_en_set(self, 1); /* RX checksums offloads*/ - hw_atl_rpo_ipv4header_crc_offload_en_set(self, 1); - hw_atl_rpo_tcp_udp_crc_offload_en_set(self, 1); + hw_atl_rpo_ipv4header_crc_offload_en_set(self, !!(aq_nic_cfg->features & + NETIF_F_RXCSUM)); + hw_atl_rpo_tcp_udp_crc_offload_en_set(self, !!(aq_nic_cfg->features & + NETIF_F_RXCSUM)); /* LSO offloads*/ hw_atl_tdm_large_send_offload_en_set(self, 0xFFFFFFFFU); @@ -655,9 +662,9 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, struct hw_atl_rxd_wb_s *rxd_wb = (struct hw_atl_rxd_wb_s *) &ring->dx_ring[ring->hw_head * HW_ATL_B0_RXD_SIZE]; - unsigned int is_err = 1U; unsigned int is_rx_check_sum_enabled = 0U; unsigned int pkt_type = 0U; + u8 rx_stat = 0U; if (!(rxd_wb->status & 0x1U)) { /* RxD is not done */ break; @@ -665,35 +672,35 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, buff = &ring->buff_ring[ring->hw_head]; - is_err = (0x0000003CU & rxd_wb->status); + rx_stat = (0x0000003CU & rxd_wb->status) >> 2; is_rx_check_sum_enabled = (rxd_wb->type) & (0x3U << 19); - is_err &= ~0x20U; /* exclude validity bit */ pkt_type = 0xFFU & (rxd_wb->type >> 4); - if (is_rx_check_sum_enabled) { - if (0x0U == (pkt_type & 0x3U)) - buff->is_ip_cso = (is_err & 0x08U) ? 0U : 1U; + if (is_rx_check_sum_enabled & BIT(0) && + (0x0U == (pkt_type & 0x3U))) + buff->is_ip_cso = (rx_stat & BIT(1)) ? 0U : 1U; + if (is_rx_check_sum_enabled & BIT(1)) { if (0x4U == (pkt_type & 0x1CU)) - buff->is_udp_cso = buff->is_cso_err ? 0U : 1U; + buff->is_udp_cso = (rx_stat & BIT(2)) ? 0U : + !!(rx_stat & BIT(3)); else if (0x0U == (pkt_type & 0x1CU)) - buff->is_tcp_cso = buff->is_cso_err ? 0U : 1U; - - /* Checksum offload workaround for small packets */ - if (rxd_wb->pkt_len <= 60) { - buff->is_ip_cso = 0U; - buff->is_cso_err = 0U; - } + buff->is_tcp_cso = (rx_stat & BIT(2)) ? 0U : + !!(rx_stat & BIT(3)); + } + buff->is_cso_err = !!(rx_stat & 0x6); + /* Checksum offload workaround for small packets */ + if (unlikely(rxd_wb->pkt_len <= 60)) { + buff->is_ip_cso = 0U; + buff->is_cso_err = 0U; } - - is_err &= ~0x18U; dma_unmap_page(ndev, buff->pa, buff->len, DMA_FROM_DEVICE); - if (is_err || rxd_wb->type & 0x1000U) { - /* status error or DMA error */ + if ((rx_stat & BIT(0)) || rxd_wb->type & 0x1000U) { + /* MAC error or DMA error */ buff->is_error = 1U; } else { if (self->aq_nic_cfg->is_rss) { @@ -915,6 +922,12 @@ static int hw_atl_b0_hw_interrupt_moderation_set(struct aq_hw_s *self) static int hw_atl_b0_hw_stop(struct aq_hw_s *self) { hw_atl_b0_hw_irq_disable(self, HW_ATL_B0_INT_MASK); + + /* Invalidate Descriptor Cache to prevent writing to the cached + * descriptors and to the data pointer of those descriptors + */ + hw_atl_rdm_rx_dma_desc_cache_init_set(self, 1); + return aq_hw_err_from_flags(self); } @@ -963,4 +976,6 @@ const struct aq_hw_ops hw_atl_ops_b0 = { .hw_get_regs = hw_atl_utils_hw_get_regs, .hw_get_hw_stats = hw_atl_utils_get_hw_stats, .hw_get_fw_version = hw_atl_utils_get_fw_version, + .hw_set_offload = hw_atl_b0_hw_offload_set, + .hw_set_fc = hw_atl_b0_set_fc, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index be0a3a90dfad..5502ec5f0f69 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -619,6 +619,14 @@ void hw_atl_rpb_rx_flow_ctl_mode_set(struct aq_hw_s *aq_hw, u32 rx_flow_ctl_mode HW_ATL_RPB_RX_FC_MODE_SHIFT, rx_flow_ctl_mode); } +void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init) +{ + aq_hw_write_reg_bit(aq_hw, HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK, + HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT, + init); +} + void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer) { diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index 7056c7342afc..41f239928c15 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -325,6 +325,9 @@ void hw_atl_rpb_rx_pkt_buff_size_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_pkt_buff_size_per_tc, u32 buffer); +/* set rdm rx dma descriptor cache init */ +void hw_atl_rdm_rx_dma_desc_cache_init_set(struct aq_hw_s *aq_hw, u32 init); + /* set rx xoff enable (per tc) */ void hw_atl_rpb_rx_xoff_en_per_tc_set(struct aq_hw_s *aq_hw, u32 rx_xoff_en_per_tc, u32 buffer); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index 716674a9b729..a715fa317b1c 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -293,6 +293,24 @@ /* default value of bitfield desc{d}_reset */ #define HW_ATL_RDM_DESCDRESET_DEFAULT 0x0 +/* rdm_desc_init_i bitfield definitions + * preprocessor definitions for the bitfield rdm_desc_init_i. + * port="pif_rdm_desc_init_i" + */ + +/* register address for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_ADR 0x00005a00 +/* bitmask for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSK 0xffffffff +/* inverted bitmask for bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_MSKN 0x00000000 +/* lower bit position of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_SHIFT 0 +/* width of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_WIDTH 32 +/* default value of bitfield rdm_desc_init_i */ +#define HW_ATL_RDM_RX_DMA_DESC_CACHE_INIT_DEFAULT 0x0 + /* rx int_desc_wrb_en bitfield definitions * preprocessor definitions for the bitfield "int_desc_wrb_en". * port="pif_rdm_int_desc_wrb_en_i" diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index 096ca5730887..7de3220d9cab 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -30,6 +30,8 @@ #define HW_ATL_FW2X_MPI_STATE_ADDR 0x370 #define HW_ATL_FW2X_MPI_STATE2_ADDR 0x374 +#define HW_ATL_FW2X_CAP_PAUSE BIT(CAPS_HI_PAUSE) +#define HW_ATL_FW2X_CAP_ASYM_PAUSE BIT(CAPS_HI_ASYMMETRIC_PAUSE) #define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) #define HW_ATL_FW2X_CAP_WOL BIT(CAPS_HI_WOL) @@ -451,6 +453,24 @@ static int aq_fw2x_set_flow_control(struct aq_hw_s *self) return 0; } +static u32 aq_fw2x_get_flow_control(struct aq_hw_s *self, u32 *fcmode) +{ + u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR); + + if (mpi_state & HW_ATL_FW2X_CAP_PAUSE) + if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE) + *fcmode = AQ_NIC_FC_RX; + else + *fcmode = AQ_NIC_FC_RX | AQ_NIC_FC_TX; + else + if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE) + *fcmode = AQ_NIC_FC_TX; + else + *fcmode = 0; + + return 0; +} + const struct aq_fw_ops aq_fw_2x_ops = { .init = aq_fw2x_init, .deinit = aq_fw2x_deinit, @@ -465,4 +485,5 @@ const struct aq_fw_ops aq_fw_2x_ops = { .set_eee_rate = aq_fw2x_set_eee_rate, .get_eee_rate = aq_fw2x_get_eee_rate, .set_flow_control = aq_fw2x_set_flow_control, + .get_flow_control = aq_fw2x_get_flow_control }; diff --git a/drivers/net/ethernet/atheros/alx/alx.h b/drivers/net/ethernet/atheros/alx/alx.h index 78c5de467426..9d0e74f6b089 100644 --- a/drivers/net/ethernet/atheros/alx/alx.h +++ b/drivers/net/ethernet/atheros/alx/alx.h @@ -140,6 +140,5 @@ struct alx_priv { }; extern const struct ethtool_ops alx_ethtool_ops; -extern const char alx_drv_name[]; #endif diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index 7968c644ad86..c131cfc1b79d 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -49,7 +49,7 @@ #include "hw.h" #include "reg.h" -const char alx_drv_name[] = "alx"; +static const char alx_drv_name[] = "alx"; static void alx_free_txbuf(struct alx_tx_queue *txq, int entry) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 4122553e224b..0e2d99c737e3 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1902,9 +1902,6 @@ static void bcm_sysport_netif_start(struct net_device *dev) intrl2_1_mask_clear(priv, 0xffffffff); else intrl2_0_mask_clear(priv, INTRL2_0_TDMA_MBDONE_MASK); - - /* Last call before we start the real business */ - netif_tx_start_all_queues(dev); } static void rbuf_init(struct bcm_sysport_priv *priv) @@ -2048,6 +2045,8 @@ static int bcm_sysport_open(struct net_device *dev) bcm_sysport_netif_start(dev); + netif_tx_start_all_queues(dev); + return 0; out_clear_rx_int: @@ -2071,7 +2070,7 @@ static void bcm_sysport_netif_stop(struct net_device *dev) struct bcm_sysport_priv *priv = netdev_priv(dev); /* stop all software from updating hardware */ - netif_tx_stop_all_queues(dev); + netif_tx_disable(dev); napi_disable(&priv->napi); cancel_work_sync(&priv->dim.dim.work); phy_stop(dev->phydev); @@ -2658,12 +2657,12 @@ static int __maybe_unused bcm_sysport_suspend(struct device *d) if (!netif_running(dev)) return 0; + netif_device_detach(dev); + bcm_sysport_netif_stop(dev); phy_suspend(dev->phydev); - netif_device_detach(dev); - /* Disable UniMAC RX */ umac_enable_set(priv, CMD_RX_EN, 0); @@ -2746,8 +2745,6 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) goto out_free_rx_ring; } - netif_device_attach(dev); - /* RX pipe enable */ topctrl_writel(priv, 0, RX_FLUSH_CNTL); @@ -2788,6 +2785,8 @@ static int __maybe_unused bcm_sysport_resume(struct device *d) bcm_sysport_netif_start(dev); + netif_device_attach(dev); + return 0; out_free_rx_ring: diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 20c1681bb1af..2d6f090bf644 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2855,7 +2855,6 @@ static void bcmgenet_netif_start(struct net_device *dev) umac_enable_set(priv, CMD_TX_EN | CMD_RX_EN, true); - netif_tx_start_all_queues(dev); bcmgenet_enable_tx_napi(priv); /* Monitor link interrupts now */ @@ -2937,6 +2936,8 @@ static int bcmgenet_open(struct net_device *dev) bcmgenet_netif_start(dev); + netif_tx_start_all_queues(dev); + return 0; err_irq1: @@ -2958,7 +2959,7 @@ static void bcmgenet_netif_stop(struct net_device *dev) struct bcmgenet_priv *priv = netdev_priv(dev); bcmgenet_disable_tx_napi(priv); - netif_tx_stop_all_queues(dev); + netif_tx_disable(dev); /* Disable MAC receive */ umac_enable_set(priv, CMD_RX_EN, false); @@ -3620,13 +3621,13 @@ static int bcmgenet_suspend(struct device *d) if (!netif_running(dev)) return 0; + netif_device_detach(dev); + bcmgenet_netif_stop(dev); if (!device_may_wakeup(d)) phy_suspend(dev->phydev); - netif_device_detach(dev); - /* Prepare the device for Wake-on-LAN and switch to the slow clock */ if (device_may_wakeup(d) && priv->wolopts) { ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC); @@ -3700,8 +3701,6 @@ static int bcmgenet_resume(struct device *d) /* Always enable ring 16 - descriptor ring */ bcmgenet_enable_dma(priv, dma_ctrl); - netif_device_attach(dev); - if (!device_may_wakeup(d)) phy_resume(dev->phydev); @@ -3710,6 +3709,8 @@ static int bcmgenet_resume(struct device *d) bcmgenet_netif_start(dev); + netif_device_attach(dev); + return 0; out_clk_disable: diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 3f96aa30068e..20fcf0d1c2ce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3760,7 +3760,8 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) /* Hardware table is only clear when pf resets */ if (!(handle->flags & HNAE3_SUPPORT_VF)) { ret = hns3_restore_vlan(netdev); - return ret; + if (ret) + return ret; } ret = hns3_restore_fd_rules(netdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index aa5cb9834d73..494e562fe8c7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -1168,14 +1168,14 @@ static int hclge_pfc_setup_hw(struct hclge_dev *hdev) */ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) { - struct hclge_vport *vport = hdev->vport; - u32 i, k, qs_bitmap; - int ret; + int i; for (i = 0; i < HCLGE_BP_GRP_NUM; i++) { - qs_bitmap = 0; + u32 qs_bitmap = 0; + int k, ret; for (k = 0; k < hdev->num_alloc_vport; k++) { + struct hclge_vport *vport = &hdev->vport[k]; u16 qs_id = vport->qs_offset + tc; u8 grp, sub_grp; @@ -1185,8 +1185,6 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc) HCLGE_BP_SUB_GRP_ID_S); if (i == grp) qs_bitmap |= (1 << sub_grp); - - vport++; } ret = hclge_tm_qs_bp_cfg(hdev, tc, i, qs_bitmap); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 7893beffcc71..c9d5d0a7fbf1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1545,7 +1545,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_crq.v1.sge_len = cpu_to_be32(skb->len); tx_crq.v1.ioba = cpu_to_be64(data_dma_addr); - if (adapter->vlan_header_insertion) { + if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) { tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT; tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index bc71a21c1dc2..21c2688d6308 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -12249,6 +12249,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC | @@ -12266,13 +12268,13 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) /* record features VLANs can make use of */ netdev->vlan_features |= hw_enc_features | NETIF_F_TSO_MANGLEID; - if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) - netdev->hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; - hw_features = hw_enc_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + if (!(pf->flags & I40E_FLAG_MFP_ENABLED)) + hw_features |= NETIF_F_NTUPLE | NETIF_F_HW_TC; + netdev->hw_features |= hw_features; netdev->features |= hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 4c4b5717a627..b8548370f1c7 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -76,6 +76,8 @@ extern const char ice_drv_ver[]; #define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) #define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) +#define ICE_MAX_RESET_WAIT 20 + #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) #define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) @@ -189,7 +191,6 @@ struct ice_vsi { u64 tx_linearize; DECLARE_BITMAP(state, __ICE_STATE_NBITS); DECLARE_BITMAP(flags, ICE_VSI_FLAG_NBITS); - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; unsigned int current_netdev_flags; u32 tx_restart; u32 tx_busy; @@ -369,5 +370,6 @@ int ice_set_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size); void ice_fill_rss_lut(u8 *lut, u16 rss_table_size, u16 rss_size); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); +void ice_napi_del(struct ice_vsi *vsi); #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 8cd6a2401fd9..554fd707a6d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -811,6 +811,9 @@ void ice_deinit_hw(struct ice_hw *hw) /* Attempt to disable FW logging before shutting down control queues */ ice_cfg_fw_log(hw, false); ice_shutdown_all_ctrlq(hw); + + /* Clear VSI contexts if not already cleared */ + ice_clear_all_vsi_ctx(hw); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 96923580f2a6..648acdb4c644 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -1517,10 +1517,15 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) } if (!test_bit(__ICE_DOWN, pf->state)) { - /* Give it a little more time to try to come back */ + /* Give it a little more time to try to come back. If still + * down, restart autoneg link or reinitialize the interface. + */ msleep(75); if (!test_bit(__ICE_DOWN, pf->state)) return ice_nway_reset(netdev); + + ice_down(vsi); + ice_up(vsi); } return err; diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 5fdea6ec7675..596b9fb1c510 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -242,6 +242,8 @@ #define GLNVM_ULD 0x000B6008 #define GLNVM_ULD_CORER_DONE_M BIT(3) #define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define GLPCI_CNF2 0x000BE004 +#define GLPCI_CNF2_CACHELINE_SIZE_M BIT(1) #define PF_FUNC_RID 0x0009E880 #define PF_FUNC_RID_FUNC_NUM_S 0 #define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 5bacad01f0c9..1041fa2a7767 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1997,7 +1997,7 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) status = ice_update_vsi(&vsi->back->hw, vsi->idx, ctxt, NULL); if (status) { netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI handle: %d, VSI HW ID: %d failed, err = %d, aq_err = %d\n", - ena ? "Ena" : "Dis", vsi->idx, vsi->vsi_num, status, + ena ? "En" : "Dis", vsi->idx, vsi->vsi_num, status, vsi->back->hw.adminq.sq_last_status); goto err_out; } @@ -2458,6 +2458,7 @@ int ice_vsi_release(struct ice_vsi *vsi) * on this wq */ if (vsi->netdev && !ice_is_reset_in_progress(pf->state)) { + ice_napi_del(vsi); unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); vsi->netdev = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 05993451147a..333312a1d595 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1465,7 +1465,7 @@ skip_req_irq: * ice_napi_del - Remove NAPI handler for the VSI * @vsi: VSI for which NAPI handler is to be removed */ -static void ice_napi_del(struct ice_vsi *vsi) +void ice_napi_del(struct ice_vsi *vsi) { int v_idx; @@ -1622,7 +1622,6 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - int ret; if (vid >= VLAN_N_VID) { netdev_err(netdev, "VLAN id requested %d is out of range %d\n", @@ -1635,7 +1634,8 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, /* Enable VLAN pruning when VLAN 0 is added */ if (unlikely(!vid)) { - ret = ice_cfg_vlan_pruning(vsi, true); + int ret = ice_cfg_vlan_pruning(vsi, true); + if (ret) return ret; } @@ -1644,12 +1644,7 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, * needed to continue allowing all untagged packets since VLAN prune * list is applied to all packets by the switch */ - ret = ice_vsi_add_vlan(vsi, vid); - - if (!ret) - set_bit(vid, vsi->active_vlans); - - return ret; + return ice_vsi_add_vlan(vsi, vid); } /** @@ -1677,8 +1672,6 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev, if (status) return status; - clear_bit(vid, vsi->active_vlans); - /* Disable VLAN pruning when VLAN 0 is removed */ if (unlikely(!vid)) status = ice_cfg_vlan_pruning(vsi, false); @@ -2002,6 +1995,22 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) } /** + * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines + * @pf: pointer to the PF structure + * + * There is no error returned here because the driver should be able to handle + * 128 Byte cache lines, so we only print a warning in case issues are seen, + * specifically with Tx. + */ +static void ice_verify_cacheline_size(struct ice_pf *pf) +{ + if (rd32(&pf->hw, GLPCI_CNF2) & GLPCI_CNF2_CACHELINE_SIZE_M) + dev_warn(&pf->pdev->dev, + "%d Byte cache line assumption is invalid, driver may have Tx timeouts!\n", + ICE_CACHE_LINE_BYTES); +} + +/** * ice_probe - Device initialization routine * @pdev: PCI device information struct * @ent: entry in ice_pci_tbl @@ -2151,6 +2160,8 @@ static int ice_probe(struct pci_dev *pdev, /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); + ice_verify_cacheline_size(pf); + return 0; err_alloc_sw_unroll: @@ -2182,6 +2193,12 @@ static void ice_remove(struct pci_dev *pdev) if (!pf) return; + for (i = 0; i < ICE_MAX_RESET_WAIT; i++) { + if (!ice_is_reset_in_progress(pf->state)) + break; + msleep(100); + } + set_bit(__ICE_DOWN, pf->state); ice_service_task_stop(pf); @@ -2510,31 +2527,6 @@ static int ice_vsi_vlan_setup(struct ice_vsi *vsi) } /** - * ice_restore_vlan - Reinstate VLANs when vsi/netdev comes back up - * @vsi: the VSI being brought back up - */ -static int ice_restore_vlan(struct ice_vsi *vsi) -{ - int err; - u16 vid; - - if (!vsi->netdev) - return -EINVAL; - - err = ice_vsi_vlan_setup(vsi); - if (err) - return err; - - for_each_set_bit(vid, vsi->active_vlans, VLAN_N_VID) { - err = ice_vlan_rx_add_vid(vsi->netdev, htons(ETH_P_8021Q), vid); - if (err) - break; - } - - return err; -} - -/** * ice_vsi_cfg - Setup the VSI * @vsi: the VSI being configured * @@ -2546,7 +2538,9 @@ static int ice_vsi_cfg(struct ice_vsi *vsi) if (vsi->netdev) { ice_set_rx_mode(vsi->netdev); - err = ice_restore_vlan(vsi); + + err = ice_vsi_vlan_setup(vsi); + if (err) return err; } @@ -3296,7 +3290,7 @@ static void ice_rebuild(struct ice_pf *pf) struct device *dev = &pf->pdev->dev; struct ice_hw *hw = &pf->hw; enum ice_status ret; - int err; + int err, i; if (test_bit(__ICE_DOWN, pf->state)) goto clear_recovery; @@ -3370,6 +3364,22 @@ static void ice_rebuild(struct ice_pf *pf) } ice_reset_all_vfs(pf, true); + + for (i = 0; i < pf->num_alloc_vsi; i++) { + bool link_up; + + if (!pf->vsi[i] || pf->vsi[i]->type != ICE_VSI_PF) + continue; + ice_get_link_status(pf->vsi[i]->port_info, &link_up); + if (link_up) { + netif_carrier_on(pf->vsi[i]->netdev); + netif_tx_wake_all_queues(pf->vsi[i]->netdev); + } else { + netif_carrier_off(pf->vsi[i]->netdev); + netif_tx_stop_all_queues(pf->vsi[i]->netdev); + } + } + /* if we get here, reset flow is successful */ clear_bit(__ICE_RESET_FAILED, pf->state); return; diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 33403f39f1b3..40c9c6558956 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -348,6 +348,18 @@ static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) } /** + * ice_clear_all_vsi_ctx - clear all the VSI context entries + * @hw: pointer to the hw struct + */ +void ice_clear_all_vsi_ctx(struct ice_hw *hw) +{ + u16 i; + + for (i = 0; i < ICE_MAX_VSI; i++) + ice_clear_vsi_ctx(hw, i); +} + +/** * ice_add_vsi - add VSI context to the hardware and VSI handle list * @hw: pointer to the hw struct * @vsi_handle: unique VSI handle provided by drivers diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index b88d96a1ef69..d5ef0bd58bf9 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -190,6 +190,8 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle); struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle); +void ice_clear_all_vsi_ctx(struct ice_hw *hw); +/* Switch config */ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 5dae968d853e..fe5bbabbb41e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1520,7 +1520,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) /* update gso_segs and bytecount */ first->gso_segs = skb_shinfo(skb)->gso_segs; - first->bytecount = (first->gso_segs - 1) * off->header_len; + first->bytecount += (first->gso_segs - 1) * off->header_len; cd_tso_len = skb->len - off->header_len; cd_mss = skb_shinfo(skb)->gso_size; @@ -1556,15 +1556,15 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) * magnitude greater than our largest possible GSO size. * * This would then be implemented as: - * return (((size >> 12) * 85) >> 8) + 1; + * return (((size >> 12) * 85) >> 8) + ICE_DESCS_FOR_SKB_DATA_PTR; * * Since multiplication and division are commutative, we can reorder * operations into: - * return ((size * 85) >> 20) + 1; + * return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR; */ static unsigned int ice_txd_use_count(unsigned int size) { - return ((size * 85) >> 20) + 1; + return ((size * 85) >> 20) + ICE_DESCS_FOR_SKB_DATA_PTR; } /** @@ -1706,7 +1706,8 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) * + 1 desc for context descriptor, * otherwise try next time */ - if (ice_maybe_stop_tx(tx_ring, count + 4 + 1)) { + if (ice_maybe_stop_tx(tx_ring, count + ICE_DESCS_PER_CACHE_LINE + + ICE_DESCS_FOR_CTX_DESC)) { tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 1d0f58bd389b..75d0eaf6c9dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -22,8 +22,21 @@ #define ICE_RX_BUF_WRITE 16 /* Must be power of 2 */ #define ICE_MAX_TXQ_PER_TXQG 128 -/* Tx Descriptors needed, worst case */ -#define DESC_NEEDED (MAX_SKB_FRAGS + 4) +/* We are assuming that the cache line is always 64 Bytes here for ice. + * In order to make sure that is a correct assumption there is a check in probe + * to print a warning if the read from GLPCI_CNF2 tells us that the cache line + * size is 128 bytes. We do it this way because we do not want to read the + * GLPCI_CNF2 register or a variable containing the value on every pass through + * the Tx path. + */ +#define ICE_CACHE_LINE_BYTES 64 +#define ICE_DESCS_PER_CACHE_LINE (ICE_CACHE_LINE_BYTES / \ + sizeof(struct ice_tx_desc)) +#define ICE_DESCS_FOR_CTX_DESC 1 +#define ICE_DESCS_FOR_SKB_DATA_PTR 1 +/* Tx descriptors needed, worst case */ +#define DESC_NEEDED (MAX_SKB_FRAGS + ICE_DESCS_FOR_CTX_DESC + \ + ICE_DESCS_PER_CACHE_LINE + ICE_DESCS_FOR_SKB_DATA_PTR) #define ICE_DESC_UNUSED(R) \ ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 12f9432abf11..f4dbc81c1988 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -92,12 +92,12 @@ struct ice_link_status { u64 phy_type_low; u16 max_frame_size; u16 link_speed; + u16 req_speeds; u8 lse_ena; /* Link Status Event notification */ u8 link_info; u8 an_info; u8 ext_info; u8 pacing; - u8 req_speeds; /* Refer to #define from module_type[ICE_MODULE_TYPE_TOTAL_BYTE] of * ice_aqc_get_phy_caps structure */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 45f10f8f01dc..e71065f9d391 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -348,7 +348,7 @@ static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid) struct ice_vsi_ctx ctxt = { 0 }; enum ice_status status; - ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_TAGGED | + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED | ICE_AQ_VSI_PVLAN_INSERT_PVID | ICE_AQ_VSI_VLAN_EMOD_STR; ctxt.info.pvid = cpu_to_le16(vid); @@ -2171,7 +2171,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) if (!ice_vsi_add_vlan(vsi, vid)) { vf->num_vlan++; - set_bit(vid, vsi->active_vlans); /* Enable VLAN pruning when VLAN 0 is added */ if (unlikely(!vid)) @@ -2190,7 +2189,6 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) */ if (!ice_vsi_kill_vlan(vsi, vid)) { vf->num_vlan--; - clear_bit(vid, vsi->active_vlans); /* Disable VLAN pruning when removing VLAN 0 */ if (unlikely(!vid)) diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 29ced6b74d36..2b95dc9c7a6a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -53,13 +53,15 @@ * 2^40 * 10^-9 / 60 = 18.3 minutes. * * SYSTIM is converted to real time using a timecounter. As - * timecounter_cyc2time() allows old timestamps, the timecounter - * needs to be updated at least once per half of the SYSTIM interval. - * Scheduling of delayed work is not very accurate, so we aim for 8 - * minutes to be sure the actual interval is shorter than 9.16 minutes. + * timecounter_cyc2time() allows old timestamps, the timecounter needs + * to be updated at least once per half of the SYSTIM interval. + * Scheduling of delayed work is not very accurate, and also the NIC + * clock can be adjusted to run up to 6% faster and the system clock + * up to 10% slower, so we aim for 6 minutes to be sure the actual + * interval in the NIC time is shorter than 9.16 minutes. */ -#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 8) +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 6) #define IGB_PTP_TX_TIMEOUT (HZ * 15) #define INCPERIOD_82576 BIT(E1000_TIMINCA_16NS_SHIFT) #define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 5bfd349bf41a..3ba672e9e353 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -494,7 +494,7 @@ struct mvneta_port { #if defined(__LITTLE_ENDIAN) struct mvneta_tx_desc { u32 command; /* Options used by HW for packet transmitting.*/ - u16 reserverd1; /* csum_l4 (for future use) */ + u16 reserved1; /* csum_l4 (for future use) */ u16 data_size; /* Data size of transmitted packet in bytes */ u32 buf_phys_addr; /* Physical addr of transmitted buffer */ u32 reserved2; /* hw_cmd - (for future use, PMT) */ @@ -519,7 +519,7 @@ struct mvneta_rx_desc { #else struct mvneta_tx_desc { u16 data_size; /* Data size of transmitted packet in bytes */ - u16 reserverd1; /* csum_l4 (for future use) */ + u16 reserved1; /* csum_l4 (for future use) */ u32 command; /* Options used by HW for packet transmitting.*/ u32 reserved2; /* hw_cmd - (for future use, PMT) */ u32 buf_phys_addr; /* Physical addr of transmitted buffer */ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 1857ee0f0871..6f5153afcab4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -1006,7 +1006,6 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) ring->packets++; } ring->bytes += tx_info->nr_bytes; - netdev_tx_sent_queue(ring->tx_queue, tx_info->nr_bytes); AVG_PERF_COUNTER(priv->pstats.tx_pktsz_avg, skb->len); if (tx_info->inl) @@ -1044,7 +1043,10 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) netif_tx_stop_queue(ring->tx_queue); ring->queue_stopped++; } - send_doorbell = !skb->xmit_more || netif_xmit_stopped(ring->tx_queue); + + send_doorbell = __netdev_tx_sent_queue(ring->tx_queue, + tx_info->nr_bytes, + skb->xmit_more); real_size = (real_size / 16) & 0x3f; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index a2df12b79f8e..9bec940330a4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3568,7 +3568,6 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) burst_size = 7; break; case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME: - is_bytes = true; rate = 4 * 1024; burst_size = 4; break; diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index cc1b373c0ace..46dc93d3b9b5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -147,7 +147,8 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, "Cannot satisfy CQ amount. CQs requested %d, CQs available %d. Aborting function start\n", fcoe_pf_params->num_cqs, p_hwfn->hw_info.feat_num[QED_FCOE_CQ]); - return -EINVAL; + rc = -EINVAL; + goto err; } p_data->mtu = cpu_to_le16(fcoe_pf_params->mtu); @@ -156,14 +157,14 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, rc = qed_cxt_acquire_cid(p_hwfn, PROTOCOLID_FCOE, &dummy_cid); if (rc) - return rc; + goto err; cxt_info.iid = dummy_cid; rc = qed_cxt_get_cid_info(p_hwfn, &cxt_info); if (rc) { DP_NOTICE(p_hwfn, "Cannot find context info for dummy cid=%d\n", dummy_cid); - return rc; + goto err; } p_cxt = cxt_info.p_cxt; SET_FIELD(p_cxt->tstorm_ag_context.flags3, @@ -240,6 +241,10 @@ qed_sp_fcoe_func_start(struct qed_hwfn *p_hwfn, rc = qed_spq_post(p_hwfn, p_ent, NULL); return rc; + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + return rc; } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c index 1135387bd99d..4f8a685d1a55 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c @@ -200,6 +200,7 @@ qed_sp_iscsi_func_start(struct qed_hwfn *p_hwfn, "Cannot satisfy CQ amount. Queues requested %d, CQs available %d. Aborting function start\n", p_params->num_queues, p_hwfn->hw_info.feat_num[QED_ISCSI_CQ]); + qed_sp_destroy_request(p_hwfn, p_ent); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 82a1bd1f8a8c..67c02ea93906 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -740,8 +740,7 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, rc = qed_sp_vport_update_rss(p_hwfn, p_ramrod, p_rss_params); if (rc) { - /* Return spq entry which is taken in qed_sp_init_request()*/ - qed_spq_return_entry(p_hwfn, p_ent); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } @@ -1355,6 +1354,7 @@ qed_filter_ucast_common(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "%d is not supported yet\n", p_filter_cmd->opcode); + qed_sp_destroy_request(p_hwfn, *pp_ent); return -EINVAL; } @@ -2056,13 +2056,13 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, } else { rc = qed_fw_vport(p_hwfn, p_params->vport_id, &abs_vport_id); if (rc) - return rc; + goto err; if (p_params->qid != QED_RFS_NTUPLE_QID_RSS) { rc = qed_fw_l2_queue(p_hwfn, p_params->qid, &abs_rx_q_id); if (rc) - return rc; + goto err; p_ramrod->rx_qid_valid = 1; p_ramrod->rx_qid = cpu_to_le16(abs_rx_q_id); @@ -2083,6 +2083,10 @@ qed_configure_rfs_ntuple_filter(struct qed_hwfn *p_hwfn, (u64)p_params->addr, p_params->length); return qed_spq_post(p_hwfn, p_ent, NULL); + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + return rc; } int qed_get_rxq_coalesce(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index f40f654398a0..a96364df4320 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -1944,9 +1944,12 @@ int qed_mcp_trans_speed_mask(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u32 *p_speed_mask) { u32 transceiver_type, transceiver_state; + int ret; - qed_mcp_get_transceiver_data(p_hwfn, p_ptt, &transceiver_state, - &transceiver_type); + ret = qed_mcp_get_transceiver_data(p_hwfn, p_ptt, &transceiver_state, + &transceiver_type); + if (ret) + return ret; if (qed_is_transceiver_ready(transceiver_state, transceiver_type) == false) diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c index c71391b9c757..62113438c880 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c +++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c @@ -1514,6 +1514,7 @@ qed_rdma_register_tid(void *rdma_cxt, default: rc = -EINVAL; DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d\n", rc); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } SET_FIELD(p_ramrod->flags1, diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c index f9167d1354bb..e49fada85410 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_roce.c +++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c @@ -745,6 +745,7 @@ static int qed_roce_sp_destroy_qp_responder(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "qed destroy responder failed: cannot allocate memory (ramrod). rc = %d\n", rc); + qed_sp_destroy_request(p_hwfn, p_ent); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index e95431f6acd4..3157c0d99441 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -167,6 +167,9 @@ struct qed_spq_entry { enum spq_mode comp_mode; struct qed_spq_comp_cb comp_cb; struct qed_spq_comp_done comp_done; /* SPQ_MODE_EBLOCK */ + + /* Posted entry for unlimited list entry in EBLOCK mode */ + struct qed_spq_entry *post_ent; }; struct qed_eq { @@ -396,6 +399,17 @@ struct qed_sp_init_data { struct qed_spq_comp_cb *p_comp_data; }; +/** + * @brief Returns a SPQ entry to the pool / frees the entry if allocated. + * Should be called on in error flows after initializing the SPQ entry + * and before posting it. + * + * @param p_hwfn + * @param p_ent + */ +void qed_sp_destroy_request(struct qed_hwfn *p_hwfn, + struct qed_spq_entry *p_ent); + int qed_sp_init_request(struct qed_hwfn *p_hwfn, struct qed_spq_entry **pp_ent, u8 cmd, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 77b6248ad3b9..888274fa208b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -47,6 +47,19 @@ #include "qed_sp.h" #include "qed_sriov.h" +void qed_sp_destroy_request(struct qed_hwfn *p_hwfn, + struct qed_spq_entry *p_ent) +{ + /* qed_spq_get_entry() can either get an entry from the free_pool, + * or, if no entries are left, allocate a new entry and add it to + * the unlimited_pending list. + */ + if (p_ent->queue == &p_hwfn->p_spq->unlimited_pending) + kfree(p_ent); + else + qed_spq_return_entry(p_hwfn, p_ent); +} + int qed_sp_init_request(struct qed_hwfn *p_hwfn, struct qed_spq_entry **pp_ent, u8 cmd, u8 protocol, struct qed_sp_init_data *p_data) @@ -80,7 +93,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, case QED_SPQ_MODE_BLOCK: if (!p_data->p_comp_data) - return -EINVAL; + goto err; p_ent->comp_cb.cookie = p_data->p_comp_data->cookie; break; @@ -95,7 +108,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, default: DP_NOTICE(p_hwfn, "Unknown SPQE completion mode %d\n", p_ent->comp_mode); - return -EINVAL; + goto err; } DP_VERBOSE(p_hwfn, QED_MSG_SPQ, @@ -109,6 +122,11 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, memset(&p_ent->ramrod, 0, sizeof(p_ent->ramrod)); return 0; + +err: + qed_sp_destroy_request(p_hwfn, p_ent); + + return -EINVAL; } static enum tunnel_clss qed_tunn_clss_to_fw_clss(u8 type) diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index c4a6274dd625..0a9c5bb0fa48 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -142,6 +142,7 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, DP_INFO(p_hwfn, "Ramrod is stuck, requesting MCP drain\n"); rc = qed_mcp_drain(p_hwfn, p_ptt); + qed_ptt_release(p_hwfn, p_ptt); if (rc) { DP_NOTICE(p_hwfn, "MCP drain failed\n"); goto err; @@ -150,18 +151,15 @@ static int qed_spq_block(struct qed_hwfn *p_hwfn, /* Retry after drain */ rc = __qed_spq_block(p_hwfn, p_ent, p_fw_ret, true); if (!rc) - goto out; + return 0; comp_done = (struct qed_spq_comp_done *)p_ent->comp_cb.cookie; - if (comp_done->done == 1) + if (comp_done->done == 1) { if (p_fw_ret) *p_fw_ret = comp_done->fw_return_code; -out: - qed_ptt_release(p_hwfn, p_ptt); - return 0; - + return 0; + } err: - qed_ptt_release(p_hwfn, p_ptt); DP_NOTICE(p_hwfn, "Ramrod is stuck [CID %08x cmd %02x protocol %02x echo %04x]\n", le32_to_cpu(p_ent->elem.hdr.cid), @@ -685,6 +683,8 @@ static int qed_spq_add_entry(struct qed_hwfn *p_hwfn, /* EBLOCK responsible to free the allocated p_ent */ if (p_ent->comp_mode != QED_SPQ_MODE_EBLOCK) kfree(p_ent); + else + p_ent->post_ent = p_en2; p_ent = p_en2; } @@ -767,6 +767,25 @@ static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) SPQ_HIGH_PRI_RESERVE_DEFAULT); } +/* Avoid overriding of SPQ entries when getting out-of-order completions, by + * marking the completions in a bitmap and increasing the chain consumer only + * for the first successive completed entries. + */ +static void qed_spq_comp_bmap_update(struct qed_hwfn *p_hwfn, __le16 echo) +{ + u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; + struct qed_spq *p_spq = p_hwfn->p_spq; + + __set_bit(pos, p_spq->p_comp_bitmap); + while (test_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap)) { + __clear_bit(p_spq->comp_bitmap_idx, + p_spq->p_comp_bitmap); + p_spq->comp_bitmap_idx++; + qed_chain_return_produced(&p_spq->chain); + } +} + int qed_spq_post(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent, u8 *fw_return_code) { @@ -824,11 +843,12 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, p_ent->queue == &p_spq->unlimited_pending); if (p_ent->queue == &p_spq->unlimited_pending) { - /* This is an allocated p_ent which does not need to - * return to pool. - */ + struct qed_spq_entry *p_post_ent = p_ent->post_ent; + kfree(p_ent); - return rc; + + /* Return the entry which was actually posted */ + p_ent = p_post_ent; } if (rc) @@ -842,7 +862,7 @@ int qed_spq_post(struct qed_hwfn *p_hwfn, spq_post_fail2: spin_lock_bh(&p_spq->lock); list_del(&p_ent->list); - qed_chain_return_produced(&p_spq->chain); + qed_spq_comp_bmap_update(p_hwfn, p_ent->elem.hdr.echo); spq_post_fail: /* return to the free pool */ @@ -874,25 +894,8 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, spin_lock_bh(&p_spq->lock); list_for_each_entry_safe(p_ent, tmp, &p_spq->completion_pending, list) { if (p_ent->elem.hdr.echo == echo) { - u16 pos = le16_to_cpu(echo) % SPQ_RING_SIZE; - list_del(&p_ent->list); - - /* Avoid overriding of SPQ entries when getting - * out-of-order completions, by marking the completions - * in a bitmap and increasing the chain consumer only - * for the first successive completed entries. - */ - __set_bit(pos, p_spq->p_comp_bitmap); - - while (test_bit(p_spq->comp_bitmap_idx, - p_spq->p_comp_bitmap)) { - __clear_bit(p_spq->comp_bitmap_idx, - p_spq->p_comp_bitmap); - p_spq->comp_bitmap_idx++; - qed_chain_return_produced(&p_spq->chain); - } - + qed_spq_comp_bmap_update(p_hwfn, echo); p_spq->comp_count++; found = p_ent; break; @@ -931,11 +934,9 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, QED_MSG_SPQ, "Got a completion without a callback function\n"); - if ((found->comp_mode != QED_SPQ_MODE_EBLOCK) || - (found->queue == &p_spq->unlimited_pending)) + if (found->comp_mode != QED_SPQ_MODE_EBLOCK) /* EBLOCK is responsible for returning its own entry into the - * free list, unless it originally added the entry into the - * unlimited pending list. + * free list. */ qed_spq_return_entry(p_hwfn, found); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 9b08a9d9e151..ca6290fa0f30 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -101,6 +101,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf) default: DP_NOTICE(p_hwfn, "Unknown VF personality %d\n", p_hwfn->hw_info.personality); + qed_sp_destroy_request(p_hwfn, p_ent); return -EINVAL; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 9647578cbe6a..14f26bf3b388 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -459,7 +459,7 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter, struct cmd_desc_type0 *first_desc, struct sk_buff *skb, struct qlcnic_host_tx_ring *tx_ring) { - u8 l4proto, opcode = 0, hdr_len = 0; + u8 l4proto, opcode = 0, hdr_len = 0, tag_vlan = 0; u16 flags = 0, vlan_tci = 0; int copied, offset, copy_len, size; struct cmd_desc_type0 *hwdesc; @@ -472,14 +472,16 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter, flags = QLCNIC_FLAGS_VLAN_TAGGED; vlan_tci = ntohs(vh->h_vlan_TCI); protocol = ntohs(vh->h_vlan_encapsulated_proto); + tag_vlan = 1; } else if (skb_vlan_tag_present(skb)) { flags = QLCNIC_FLAGS_VLAN_OOB; vlan_tci = skb_vlan_tag_get(skb); + tag_vlan = 1; } if (unlikely(adapter->tx_pvid)) { - if (vlan_tci && !(adapter->flags & QLCNIC_TAGGING_ENABLED)) + if (tag_vlan && !(adapter->flags & QLCNIC_TAGGING_ENABLED)) return -EIO; - if (vlan_tci && (adapter->flags & QLCNIC_TAGGING_ENABLED)) + if (tag_vlan && (adapter->flags & QLCNIC_TAGGING_ENABLED)) goto set_flags; flags = QLCNIC_FLAGS_VLAN_OOB; diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c index 0afc3d335d56..d11c16aeb19a 100644 --- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c +++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c @@ -234,7 +234,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, struct net_device *real_dev, struct rmnet_endpoint *ep) { - struct rmnet_priv *priv; + struct rmnet_priv *priv = netdev_priv(rmnet_dev); int rc; if (ep->egress_dev) @@ -247,6 +247,8 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, rmnet_dev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; rmnet_dev->hw_features |= NETIF_F_SG; + priv->real_dev = real_dev; + rc = register_netdevice(rmnet_dev); if (!rc) { ep->egress_dev = rmnet_dev; @@ -255,9 +257,7 @@ int rmnet_vnd_newlink(u8 id, struct net_device *rmnet_dev, rmnet_dev->rtnl_link_ops = &rmnet_link_ops; - priv = netdev_priv(rmnet_dev); priv->mux_id = id; - priv->real_dev = real_dev; netdev_dbg(rmnet_dev, "rmnet dev created\n"); } diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index b1b305f8f414..272b9ca66314 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -365,7 +365,8 @@ struct dma_features { /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ #define BUF_SIZE_16KiB 16384 -#define BUF_SIZE_8KiB 8192 +/* RX Buffer size must be < 8191 and multiple of 4/8/16 bytes */ +#define BUF_SIZE_8KiB 8188 #define BUF_SIZE_4KiB 4096 #define BUF_SIZE_2KiB 2048 diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h index ca9d7e48034c..40d6356a7e73 100644 --- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h +++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h @@ -31,7 +31,7 @@ /* Enhanced descriptors */ static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end) { - p->des1 |= cpu_to_le32(((BUF_SIZE_8KiB - 1) + p->des1 |= cpu_to_le32((BUF_SIZE_8KiB << ERDES1_BUFFER2_SIZE_SHIFT) & ERDES1_BUFFER2_SIZE_MASK); diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 77914c89d749..5ef91a790f9d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -262,7 +262,7 @@ static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode, int end) { p->des0 |= cpu_to_le32(RDES0_OWN); - p->des1 |= cpu_to_le32((BUF_SIZE_8KiB - 1) & ERDES1_BUFFER1_SIZE_MASK); + p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK); if (mode == STMMAC_CHAIN_MODE) ehn_desc_rx_set_on_chain(p); diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index abc3f85270cd..d8c5bc412219 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -140,7 +140,7 @@ static void clean_desc3(void *priv_ptr, struct dma_desc *p) static int set_16kib_bfsize(int mtu) { int ret = 0; - if (unlikely(mtu >= BUF_SIZE_8KiB)) + if (unlikely(mtu > BUF_SIZE_8KiB)) ret = BUF_SIZE_16KiB; return ret; } diff --git a/drivers/net/fddi/defza.c b/drivers/net/fddi/defza.c index 3b7f10a5f06a..c5cae8e74dc4 100644 --- a/drivers/net/fddi/defza.c +++ b/drivers/net/fddi/defza.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0+ /* FDDI network adapter driver for DEC FDDIcontroller 700/700-C devices. * * Copyright (c) 2018 Maciej W. Rozycki @@ -56,7 +56,7 @@ #define DRV_VERSION "v.1.1.4" #define DRV_RELDATE "Oct 6 2018" -static char version[] = +static const char version[] = DRV_NAME ": " DRV_VERSION " " DRV_RELDATE " Maciej W. Rozycki\n"; MODULE_AUTHOR("Maciej W. Rozycki <[email protected]>"); @@ -784,7 +784,7 @@ err_rx: static void fza_tx_smt(struct net_device *dev) { struct fza_private *fp = netdev_priv(dev); - struct fza_buffer_tx __iomem *smt_tx_ptr, *skb_data_ptr; + struct fza_buffer_tx __iomem *smt_tx_ptr; int i, len; u32 own; @@ -799,6 +799,7 @@ static void fza_tx_smt(struct net_device *dev) if (!netif_queue_stopped(dev)) { if (dev_nit_active(dev)) { + struct fza_buffer_tx *skb_data_ptr; struct sk_buff *skb; /* Length must be a multiple of 4 as only word diff --git a/drivers/net/fddi/defza.h b/drivers/net/fddi/defza.h index b06acf32738e..93bda61be8e3 100644 --- a/drivers/net/fddi/defza.h +++ b/drivers/net/fddi/defza.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: GPL-2.0+ */ /* FDDI network adapter driver for DEC FDDIcontroller 700/700-C devices. * * Copyright (c) 2018 Maciej W. Rozycki @@ -235,6 +235,7 @@ struct fza_ring_cmd { #define FZA_RING_CMD 0x200400 /* command ring address */ #define FZA_RING_CMD_SIZE 0x40 /* command descriptor ring * size + */ /* Command constants. */ #define FZA_RING_CMD_MASK 0x7fffffff #define FZA_RING_CMD_NOP 0x00000000 /* nop */ diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index e86ea105c802..704537010453 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -92,7 +92,7 @@ static int bcm54612e_config_init(struct phy_device *phydev) return 0; } -static int bcm5481x_config(struct phy_device *phydev) +static int bcm54xx_config_clock_delay(struct phy_device *phydev) { int rc, val; @@ -429,7 +429,7 @@ static int bcm5481_config_aneg(struct phy_device *phydev) ret = genphy_config_aneg(phydev); /* Then we can set up the delay. */ - bcm5481x_config(phydev); + bcm54xx_config_clock_delay(phydev); if (of_property_read_bool(np, "enet-phy-lane-swap")) { /* Lane Swap - Undocumented register...magic! */ @@ -442,6 +442,19 @@ static int bcm5481_config_aneg(struct phy_device *phydev) return ret; } +static int bcm54616s_config_aneg(struct phy_device *phydev) +{ + int ret; + + /* Aneg firsly. */ + ret = genphy_config_aneg(phydev); + + /* Then we can set up the delay. */ + bcm54xx_config_clock_delay(phydev); + + return ret; +} + static int brcm_phy_setbits(struct phy_device *phydev, int reg, int set) { int val; @@ -636,6 +649,7 @@ static struct phy_driver broadcom_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = bcm54xx_config_init, + .config_aneg = bcm54616s_config_aneg, .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, }, { diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 7fc8508b5231..271e8adc39f1 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -220,7 +220,7 @@ static struct phy_driver realtek_drvs[] = { .flags = PHY_HAS_INTERRUPT, }, { .phy_id = 0x001cc816, - .name = "RTL8201F 10/100Mbps Ethernet", + .name = "RTL8201F Fast Ethernet", .phy_id_mask = 0x001fffff, .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 262e7a3c23cb..f2d01cb6f958 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1321,6 +1321,8 @@ static int smsc95xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->net->ethtool_ops = &smsc95xx_ethtool_ops; dev->net->flags |= IFF_MULTICAST; dev->net->hard_header_len += SMSC95XX_TX_OVERHEAD_CSUM; + dev->net->min_mtu = ETH_MIN_MTU; + dev->net->max_mtu = ETH_DATA_LEN; dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; pdata->dev = dev; @@ -1598,6 +1600,8 @@ static int smsc95xx_suspend(struct usb_interface *intf, pm_message_t message) return ret; } + cancel_delayed_work_sync(&pdata->carrier_check); + if (pdata->suspend_flags) { netdev_warn(dev->net, "error during last resume\n"); pdata->suspend_flags = 0; @@ -1840,6 +1844,11 @@ done: */ if (ret && PMSG_IS_AUTO(message)) usbnet_resume(intf); + + if (ret) + schedule_delayed_work(&pdata->carrier_check, + CARRIER_CHECK_DELAY); + return ret; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2e65be8b1387..559d567693b8 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1519,8 +1519,10 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id) if (ns->ndev) nvme_nvm_update_nvm_info(ns); #ifdef CONFIG_NVME_MULTIPATH - if (ns->head->disk) + if (ns->head->disk) { nvme_update_disk_info(ns->head->disk, ns, id); + blk_queue_stack_limits(ns->head->disk->queue, ns->queue); + } #endif } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 5e3cc8c59a39..9901afd804ce 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -285,6 +285,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* set to a default value for 512 until disk is validated */ blk_queue_logical_block_size(q, 512); + blk_set_stacking_limits(&q->limits); /* we need to propagate up the VMC settings */ if (ctrl->vwc & NVME_CTRL_VWC_PRESENT) diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index f4efe289dc7b..a5f9bbce863f 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -420,7 +420,7 @@ static void nvmet_p2pmem_ns_add_p2p(struct nvmet_ctrl *ctrl, struct pci_dev *p2p_dev; int ret; - if (!ctrl->p2p_client) + if (!ctrl->p2p_client || !ns->use_p2pmem) return; if (ns->p2p_dev) { diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index ddce100be57a..3f7971d3706d 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -122,7 +122,6 @@ struct nvmet_rdma_device { int inline_page_count; }; -static struct workqueue_struct *nvmet_rdma_delete_wq; static bool nvmet_rdma_use_srq; module_param_named(use_srq, nvmet_rdma_use_srq, bool, 0444); MODULE_PARM_DESC(use_srq, "Use shared receive queue."); @@ -1274,12 +1273,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id, if (queue->host_qid == 0) { /* Let inflight controller teardown complete */ - flush_workqueue(nvmet_rdma_delete_wq); + flush_scheduled_work(); } ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); if (ret) { - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); /* Destroying rdma_cm id is not needed here */ return 0; } @@ -1344,7 +1343,7 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) if (disconnect) { rdma_disconnect(queue->cm_id); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } } @@ -1374,7 +1373,7 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, mutex_unlock(&nvmet_rdma_queue_mutex); pr_err("failed to connect queue %d\n", queue->idx); - queue_work(nvmet_rdma_delete_wq, &queue->release_work); + schedule_work(&queue->release_work); } /** @@ -1656,17 +1655,8 @@ static int __init nvmet_rdma_init(void) if (ret) goto err_ib_client; - nvmet_rdma_delete_wq = alloc_workqueue("nvmet-rdma-delete-wq", - WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); - if (!nvmet_rdma_delete_wq) { - ret = -ENOMEM; - goto err_unreg_transport; - } - return 0; -err_unreg_transport: - nvmet_unregister_transport(&nvmet_rdma_ops); err_ib_client: ib_unregister_client(&nvmet_rdma_ib_client); return ret; @@ -1674,7 +1664,6 @@ err_ib_client: static void __exit nvmet_rdma_exit(void) { - destroy_workqueue(nvmet_rdma_delete_wq); nvmet_unregister_transport(&nvmet_rdma_ops); ib_unregister_client(&nvmet_rdma_ib_client); WARN_ON_ONCE(!list_empty(&nvmet_rdma_queue_list)); diff --git a/drivers/of/device.c b/drivers/of/device.c index 0f27fad9fe94..5592437bb3d1 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -149,9 +149,11 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma) * set by the driver. */ mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1); - dev->bus_dma_mask = mask; dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; + /* ...but only set bus mask if we found valid dma-ranges earlier */ + if (!ret) + dev->bus_dma_mask = mask; coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", diff --git a/drivers/of/of_numa.c b/drivers/of/of_numa.c index 35c64a4295e0..fe6b13608e51 100644 --- a/drivers/of/of_numa.c +++ b/drivers/of/of_numa.c @@ -104,9 +104,14 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map) distance = of_read_number(matrix, 1); matrix++; + if ((nodea == nodeb && distance != LOCAL_DISTANCE) || + (nodea != nodeb && distance <= LOCAL_DISTANCE)) { + pr_err("Invalid distance[node%d -> node%d] = %d\n", + nodea, nodeb, distance); + return -EINVAL; + } + numa_set_distance(nodea, nodeb, distance); - pr_debug("distance[node%d -> node%d] = %d\n", - nodea, nodeb, distance); /* Set default distance of node B->A same as A->B */ if (nodeb > nodea) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 6843bc7ee9f2..04e294d1d16d 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -87,6 +87,18 @@ struct qeth_dbf_info { #define SENSE_RESETTING_EVENT_BYTE 1 #define SENSE_RESETTING_EVENT_FLAG 0x80 +static inline u32 qeth_get_device_id(struct ccw_device *cdev) +{ + struct ccw_dev_id dev_id; + u32 id; + + ccw_device_get_id(cdev, &dev_id); + id = dev_id.devno; + id |= (u32) (dev_id.ssid << 16); + + return id; +} + /* * Common IO related definitions */ @@ -97,7 +109,8 @@ struct qeth_dbf_info { #define CARD_RDEV_ID(card) dev_name(&card->read.ccwdev->dev) #define CARD_WDEV_ID(card) dev_name(&card->write.ccwdev->dev) #define CARD_DDEV_ID(card) dev_name(&card->data.ccwdev->dev) -#define CHANNEL_ID(channel) dev_name(&channel->ccwdev->dev) +#define CCW_DEVID(cdev) (qeth_get_device_id(cdev)) +#define CARD_DEVID(card) (CCW_DEVID(CARD_RDEV(card))) /** * card stuff @@ -830,6 +843,11 @@ struct qeth_trap_id { /*some helper functions*/ #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "") +static inline bool qeth_netdev_is_registered(struct net_device *dev) +{ + return dev->netdev_ops != NULL; +} + static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf, unsigned int elements) { @@ -973,7 +991,7 @@ int qeth_wait_for_threads(struct qeth_card *, unsigned long); int qeth_do_run_thread(struct qeth_card *, unsigned long); void qeth_clear_thread_start_bit(struct qeth_card *, unsigned long); void qeth_clear_thread_running_bit(struct qeth_card *, unsigned long); -int qeth_core_hardsetup_card(struct qeth_card *); +int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok); void qeth_print_status_message(struct qeth_card *); int qeth_init_qdio_queues(struct qeth_card *); int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *, @@ -1028,11 +1046,6 @@ int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); void qeth_trace_features(struct qeth_card *); void qeth_close_dev(struct qeth_card *); -int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16, - long, - int (*reply_cb)(struct qeth_card *, - struct qeth_reply *, unsigned long), - void *); int qeth_setassparms_cb(struct qeth_card *, struct qeth_reply *, unsigned long); struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *, enum qeth_ipa_funcs, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 3274f13aad57..4bce5ae65a55 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -167,6 +167,8 @@ const char *qeth_get_cardname_short(struct qeth_card *card) return "OSD_1000"; case QETH_LINK_TYPE_10GBIT_ETH: return "OSD_10GIG"; + case QETH_LINK_TYPE_25GBIT_ETH: + return "OSD_25GIG"; case QETH_LINK_TYPE_LANE_ETH100: return "OSD_FE_LANE"; case QETH_LINK_TYPE_LANE_TR: @@ -554,8 +556,8 @@ static int __qeth_issue_next_read(struct qeth_card *card) if (!iob) { dev_warn(&card->gdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s issue_next_read failed: no iob " - "available\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "issue_next_read on device %x failed: no iob available\n", + CARD_DEVID(card)); return -ENOMEM; } qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data); @@ -563,8 +565,8 @@ static int __qeth_issue_next_read(struct qeth_card *card) rc = ccw_device_start(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0); if (rc) { - QETH_DBF_MESSAGE(2, "%s error in starting next read ccw! " - "rc=%i\n", dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "error %i on device %x when starting next read ccw!\n", + rc, CARD_DEVID(card)); atomic_set(&channel->irq_pending, 0); card->read_or_write_problem = 1; qeth_schedule_recovery(card); @@ -613,16 +615,14 @@ static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, const char *ipa_name; int com = cmd->hdr.command; ipa_name = qeth_get_ipa_cmd_name(com); + if (rc) - QETH_DBF_MESSAGE(2, "IPA: %s(x%X) for %s/%s returned " - "x%X \"%s\"\n", - ipa_name, com, dev_name(&card->gdev->dev), - QETH_CARD_IFNAME(card), rc, - qeth_get_ipa_msg(rc)); + QETH_DBF_MESSAGE(2, "IPA: %s(%#x) for device %x returned %#x \"%s\"\n", + ipa_name, com, CARD_DEVID(card), rc, + qeth_get_ipa_msg(rc)); else - QETH_DBF_MESSAGE(5, "IPA: %s(x%X) for %s/%s succeeded\n", - ipa_name, com, dev_name(&card->gdev->dev), - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(5, "IPA: %s(%#x) for device %x succeeded\n", + ipa_name, com, CARD_DEVID(card)); } static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card, @@ -711,7 +711,7 @@ static int qeth_check_idx_response(struct qeth_card *card, QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN); if ((buffer[2] & 0xc0) == 0xc0) { - QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#02x\n", + QETH_DBF_MESSAGE(2, "received an IDX TERMINATE with cause code %#04x\n", buffer[4]); QETH_CARD_TEXT(card, 2, "ckidxres"); QETH_CARD_TEXT(card, 2, " idxterm"); @@ -972,8 +972,8 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev, QETH_CARD_TEXT(card, 2, "CGENCHK"); dev_warn(&cdev->dev, "The qeth device driver " "failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s check on device dstat=x%x, cstat=x%x\n", - dev_name(&cdev->dev), dstat, cstat); + QETH_DBF_MESSAGE(2, "check on channel %x with dstat=%#x, cstat=%#x\n", + CCW_DEVID(cdev), dstat, cstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 64, 1); return 1; @@ -1013,8 +1013,8 @@ static long qeth_check_irb_error(struct qeth_card *card, switch (PTR_ERR(irb)) { case -EIO: - QETH_DBF_MESSAGE(2, "%s i/o-error on device\n", - dev_name(&cdev->dev)); + QETH_DBF_MESSAGE(2, "i/o-error on channel %x\n", + CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT_(card, 2, " rc%d", -EIO); break; @@ -1031,8 +1031,8 @@ static long qeth_check_irb_error(struct qeth_card *card, } break; default: - QETH_DBF_MESSAGE(2, "%s unknown error %ld on device\n", - dev_name(&cdev->dev), PTR_ERR(irb)); + QETH_DBF_MESSAGE(2, "unknown error %ld on channel %x\n", + PTR_ERR(irb), CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT(card, 2, " rc???"); } @@ -1114,9 +1114,9 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, dev_warn(&channel->ccwdev->dev, "The qeth device driver failed to recover " "an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s sense data available. cstat " - "0x%X dstat 0x%X\n", - dev_name(&channel->ccwdev->dev), cstat, dstat); + QETH_DBF_MESSAGE(2, "sense data available on channel %x: cstat %#X dstat %#X\n", + CCW_DEVID(channel->ccwdev), cstat, + dstat); print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET, 16, 1, irb, 32, 1); print_hex_dump(KERN_WARNING, "qeth: sense data ", @@ -1890,8 +1890,8 @@ static int qeth_idx_activate_channel(struct qeth_card *card, if (channel->state != CH_STATE_ACTIVATING) { dev_warn(&channel->ccwdev->dev, "The qeth device driver" " failed to recover an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX activate timed out on channel %x\n", + CCW_DEVID(channel->ccwdev)); QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME); return -ETIME; } @@ -1926,17 +1926,15 @@ static void qeth_idx_write_cb(struct qeth_card *card, "The adapter is used exclusively by another " "host\n"); else - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel:" - " negative reply\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", + CCW_DEVID(channel->ccwdev)); goto out; } memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); if ((temp & ~0x0100) != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel: " - "function level mismatch (sent: 0x%x, received: " - "0x%x)\n", dev_name(&channel->ccwdev->dev), - card->info.func_level, temp); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, temp); goto out; } channel->state = CH_STATE_UP; @@ -1973,9 +1971,8 @@ static void qeth_idx_read_cb(struct qeth_card *card, "insufficient authorization\n"); break; default: - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel:" - " negative reply\n", - dev_name(&channel->ccwdev->dev)); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: negative reply\n", + CCW_DEVID(channel->ccwdev)); } QETH_CARD_TEXT_(card, 2, "idxread%c", QETH_IDX_ACT_CAUSE_CODE(iob->data)); @@ -1984,10 +1981,9 @@ static void qeth_idx_read_cb(struct qeth_card *card, memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); if (temp != qeth_peer_func_level(card->info.func_level)) { - QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel: function " - "level mismatch (sent: 0x%x, received: 0x%x)\n", - dev_name(&channel->ccwdev->dev), - card->info.func_level, temp); + QETH_DBF_MESSAGE(2, "IDX_ACTIVATE on channel %x: function level mismatch (sent: %#x, received: %#x)\n", + CCW_DEVID(channel->ccwdev), + card->info.func_level, temp); goto out; } memcpy(&card->token.issuer_rm_r, @@ -2096,9 +2092,8 @@ int qeth_send_control_data(struct qeth_card *card, int len, (addr_t) iob, 0, 0, event_timeout); spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { - QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: " - "ccw_device_start rc = %i\n", - dev_name(&channel->ccwdev->dev), rc); + QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n", + CARD_DEVID(card), rc); QETH_CARD_TEXT_(card, 2, " err%d", rc); spin_lock_irq(&card->lock); list_del_init(&reply->list); @@ -2853,8 +2848,8 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, } else { dev_warn(&card->gdev->dev, "The qeth driver ran out of channel command buffers\n"); - QETH_DBF_MESSAGE(1, "%s The qeth driver ran out of channel command buffers", - dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(1, "device %x ran out of channel command buffers", + CARD_DEVID(card)); } return iob; @@ -2989,10 +2984,9 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, return 0; default: if (cmd->hdr.return_code) { - QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Unhandled " - "rc=%d\n", - dev_name(&card->gdev->dev), - cmd->hdr.return_code); + QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Unhandled rc=%#x\n", + CARD_DEVID(card), + cmd->hdr.return_code); return 0; } } @@ -3004,8 +2998,8 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, card->options.ipa6.supported_funcs = cmd->hdr.ipa_supported; card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled; } else - QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Flawed LIC detected" - "\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Flawed LIC detected\n", + CARD_DEVID(card)); return 0; } @@ -4297,10 +4291,9 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, cmd->data.setadapterparms.hdr.return_code); if (cmd->data.setadapterparms.hdr.return_code != SET_ACCESS_CTRL_RC_SUCCESS) - QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%s,%d)==%d\n", - card->gdev->dev.kobj.name, - access_ctrl_req->subcmd_code, - cmd->data.setadapterparms.hdr.return_code); + QETH_DBF_MESSAGE(3, "ERR:SET_ACCESS_CTRL(%#x) on device %x: %#x\n", + access_ctrl_req->subcmd_code, CARD_DEVID(card), + cmd->data.setadapterparms.hdr.return_code); switch (cmd->data.setadapterparms.hdr.return_code) { case SET_ACCESS_CTRL_RC_SUCCESS: if (card->options.isolation == ISOLATION_MODE_NONE) { @@ -4312,14 +4305,14 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, } break; case SET_ACCESS_CTRL_RC_ALREADY_NOT_ISOLATED: - QETH_DBF_MESSAGE(2, "%s QDIO data connection isolation already " - "deactivated\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "QDIO data connection isolation on device %x already deactivated\n", + CARD_DEVID(card)); if (fallback) card->options.isolation = card->options.prev_isolation; break; case SET_ACCESS_CTRL_RC_ALREADY_ISOLATED: - QETH_DBF_MESSAGE(2, "%s QDIO data connection isolation already" - " activated\n", dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "QDIO data connection isolation on device %x already activated\n", + CARD_DEVID(card)); if (fallback) card->options.isolation = card->options.prev_isolation; break; @@ -4405,10 +4398,8 @@ int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback) rc = qeth_setadpparms_set_access_ctrl(card, card->options.isolation, fallback); if (rc) { - QETH_DBF_MESSAGE(3, - "IPA(SET_ACCESS_CTRL,%s,%d) sent failed\n", - card->gdev->dev.kobj.name, - rc); + QETH_DBF_MESSAGE(3, "IPA(SET_ACCESS_CTRL(%d) on device %x: sent failed\n", + rc, CARD_DEVID(card)); rc = -EOPNOTSUPP; } } else if (card->options.isolation != ISOLATION_MODE_NONE) { @@ -4443,7 +4434,8 @@ static int qeth_mdio_read(struct net_device *dev, int phy_id, int regnum) rc = BMCR_FULLDPLX; if ((card->info.link_type != QETH_LINK_TYPE_GBIT_ETH) && (card->info.link_type != QETH_LINK_TYPE_OSN) && - (card->info.link_type != QETH_LINK_TYPE_10GBIT_ETH)) + (card->info.link_type != QETH_LINK_TYPE_10GBIT_ETH) && + (card->info.link_type != QETH_LINK_TYPE_25GBIT_ETH)) rc |= BMCR_SPEED100; break; case MII_BMSR: /* Basic mode status register */ @@ -4634,8 +4626,8 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata) rc = qeth_send_ipa_snmp_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len, qeth_snmp_command_cb, (void *)&qinfo); if (rc) - QETH_DBF_MESSAGE(2, "SNMP command failed on %s: (0x%x)\n", - QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "SNMP command failed on device %x: (%#x)\n", + CARD_DEVID(card), rc); else { if (copy_to_user(udata, qinfo.udata, qinfo.udata_len)) rc = -EFAULT; @@ -4869,8 +4861,8 @@ static void qeth_determine_capabilities(struct qeth_card *card) rc = qeth_read_conf_data(card, (void **) &prcd, &length); if (rc) { - QETH_DBF_MESSAGE(2, "%s qeth_read_conf_data returned %i\n", - dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "qeth_read_conf_data on device %x returned %i\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "5err%d", rc); goto out_offline; } @@ -5086,7 +5078,7 @@ static struct ccw_driver qeth_ccw_driver = { .remove = ccwgroup_remove_ccwdev, }; -int qeth_core_hardsetup_card(struct qeth_card *card) +int qeth_core_hardsetup_card(struct qeth_card *card, bool *carrier_ok) { int retries = 3; int rc; @@ -5096,8 +5088,8 @@ int qeth_core_hardsetup_card(struct qeth_card *card) qeth_update_from_chp_desc(card); retry: if (retries < 3) - QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n", - dev_name(&card->gdev->dev)); + QETH_DBF_MESSAGE(2, "Retrying to do IDX activates on device %x.\n", + CARD_DEVID(card)); rc = qeth_qdio_clear_card(card, card->info.type != QETH_CARD_TYPE_IQD); ccw_device_set_offline(CARD_DDEV(card)); ccw_device_set_offline(CARD_WDEV(card)); @@ -5161,13 +5153,20 @@ retriable: if (rc == IPA_RC_LAN_OFFLINE) { dev_warn(&card->gdev->dev, "The LAN is offline\n"); - netif_carrier_off(card->dev); + *carrier_ok = false; } else { rc = -ENODEV; goto out; } } else { - netif_carrier_on(card->dev); + *carrier_ok = true; + } + + if (qeth_netdev_is_registered(card->dev)) { + if (*carrier_ok) + netif_carrier_on(card->dev); + else + netif_carrier_off(card->dev); } card->options.ipa4.supported_funcs = 0; @@ -5201,8 +5200,8 @@ retriable: out: dev_warn(&card->gdev->dev, "The qeth device driver failed to recover " "an error on the device\n"); - QETH_DBF_MESSAGE(2, "%s Initialization in hardsetup failed! rc=%d\n", - dev_name(&card->gdev->dev), rc); + QETH_DBF_MESSAGE(2, "Initialization for device %x failed in hardsetup! rc=%d\n", + CARD_DEVID(card), rc); return rc; } EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card); @@ -5481,11 +5480,12 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, } EXPORT_SYMBOL_GPL(qeth_get_setassparms_cmd); -int qeth_send_setassparms(struct qeth_card *card, - struct qeth_cmd_buffer *iob, __u16 len, long data, - int (*reply_cb)(struct qeth_card *, - struct qeth_reply *, unsigned long), - void *reply_param) +static int qeth_send_setassparms(struct qeth_card *card, + struct qeth_cmd_buffer *iob, u16 len, + long data, int (*reply_cb)(struct qeth_card *, + struct qeth_reply *, + unsigned long), + void *reply_param) { int rc; struct qeth_ipa_cmd *cmd; @@ -5501,7 +5501,6 @@ int qeth_send_setassparms(struct qeth_card *card, rc = qeth_send_ipa_cmd(card, iob, reply_cb, reply_param); return rc; } -EXPORT_SYMBOL_GPL(qeth_send_setassparms); int qeth_send_simple_setassparms_prot(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, @@ -6170,8 +6169,14 @@ static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, WARN_ON_ONCE(1); } - /* fallthrough from high to low, to select all legal speeds: */ + /* partially does fall through, to also select lower speeds */ switch (maxspeed) { + case SPEED_25000: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 25000baseSR_Full); + break; case SPEED_10000: ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); @@ -6254,6 +6259,10 @@ int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, cmd->base.speed = SPEED_10000; cmd->base.port = PORT_FIBRE; break; + case QETH_LINK_TYPE_25GBIT_ETH: + cmd->base.speed = SPEED_25000; + cmd->base.port = PORT_FIBRE; + break; default: cmd->base.speed = SPEED_10; cmd->base.port = PORT_TP; @@ -6320,6 +6329,9 @@ int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, case CARD_INFO_PORTS_10G: cmd->base.speed = SPEED_10000; break; + case CARD_INFO_PORTS_25G: + cmd->base.speed = SPEED_25000; + break; } return 0; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index e85090467afe..3e54be201b27 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -90,6 +90,7 @@ enum qeth_link_types { QETH_LINK_TYPE_GBIT_ETH = 0x03, QETH_LINK_TYPE_OSN = 0x04, QETH_LINK_TYPE_10GBIT_ETH = 0x10, + QETH_LINK_TYPE_25GBIT_ETH = 0x12, QETH_LINK_TYPE_LANE_ETH100 = 0x81, QETH_LINK_TYPE_LANE_TR = 0x82, QETH_LINK_TYPE_LANE_ETH1000 = 0x83, @@ -347,6 +348,7 @@ enum qeth_card_info_port_speed { CARD_INFO_PORTS_100M = 0x00000006, CARD_INFO_PORTS_1G = 0x00000007, CARD_INFO_PORTS_10G = 0x00000008, + CARD_INFO_PORTS_25G = 0x0000000A, }; /* (SET)DELIP(M) IPA stuff ***************************************************/ @@ -436,7 +438,7 @@ struct qeth_ipacmd_setassparms { __u32 flags_32bit; struct qeth_ipa_caps caps; struct qeth_checksum_cmd chksum; - struct qeth_arp_cache_entry add_arp_entry; + struct qeth_arp_cache_entry arp_entry; struct qeth_arp_query_data query_arp; struct qeth_tso_start_data tso; __u8 ip[16]; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 23aaf373f631..2914a1a69f83 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -146,11 +146,11 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac) QETH_CARD_TEXT(card, 2, "L2Wmac"); rc = qeth_l2_send_setdelmac(card, mac, cmd); if (rc == -EEXIST) - QETH_DBF_MESSAGE(2, "MAC %pM already registered on %s\n", - mac, QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "MAC already registered on device %x\n", + CARD_DEVID(card)); else if (rc) - QETH_DBF_MESSAGE(2, "Failed to register MAC %pM on %s: %d\n", - mac, QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "Failed to register MAC on device %x: %d\n", + CARD_DEVID(card), rc); return rc; } @@ -163,8 +163,8 @@ static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac) QETH_CARD_TEXT(card, 2, "L2Rmac"); rc = qeth_l2_send_setdelmac(card, mac, cmd); if (rc) - QETH_DBF_MESSAGE(2, "Failed to delete MAC %pM on %s: %d\n", - mac, QETH_CARD_IFNAME(card), rc); + QETH_DBF_MESSAGE(2, "Failed to delete MAC on device %u: %d\n", + CARD_DEVID(card), rc); return rc; } @@ -260,9 +260,9 @@ static int qeth_l2_send_setdelvlan_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "L2sdvcb"); if (cmd->hdr.return_code) { - QETH_DBF_MESSAGE(2, "Error in processing VLAN %i on %s: 0x%x.\n", + QETH_DBF_MESSAGE(2, "Error in processing VLAN %u on device %x: %#x.\n", cmd->data.setdelvlan.vlan_id, - QETH_CARD_IFNAME(card), cmd->hdr.return_code); + CARD_DEVID(card), cmd->hdr.return_code); QETH_CARD_TEXT_(card, 2, "L2VL%4x", cmd->hdr.command); QETH_CARD_TEXT_(card, 2, "err%d", cmd->hdr.return_code); } @@ -455,8 +455,8 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) rc = qeth_vm_request_mac(card); if (!rc) goto out; - QETH_DBF_MESSAGE(2, "z/VM MAC Service failed on device %s: x%x\n", - CARD_BUS_ID(card), rc); + QETH_DBF_MESSAGE(2, "z/VM MAC Service failed on device %x: %#x\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "err%04x", rc); /* fall back to alternative mechanism: */ } @@ -468,8 +468,8 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) rc = qeth_setadpparms_change_macaddr(card); if (!rc) goto out; - QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %s: x%x\n", - CARD_BUS_ID(card), rc); + QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %x: %#x\n", + CARD_DEVID(card), rc); QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc); /* fall back once more: */ } @@ -826,7 +826,8 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l2_set_offline(cgdev); - unregister_netdev(card->dev); + if (qeth_netdev_is_registered(card->dev)) + unregister_netdev(card->dev); } static const struct ethtool_ops qeth_l2_ethtool_ops = { @@ -862,11 +863,11 @@ static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_set_features = qeth_set_features }; -static int qeth_l2_setup_netdev(struct qeth_card *card) +static int qeth_l2_setup_netdev(struct qeth_card *card, bool carrier_ok) { int rc; - if (card->dev->netdev_ops) + if (qeth_netdev_is_registered(card->dev)) return 0; card->dev->priv_flags |= IFF_UNICAST_FLT; @@ -919,6 +920,9 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) qeth_l2_request_initial_mac(card); netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); rc = register_netdev(card->dev); + if (!rc && carrier_ok) + netif_carrier_on(card->dev); + if (rc) card->dev->netdev_ops = NULL; return rc; @@ -949,6 +953,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc = 0; enum qeth_card_states recover_flag; + bool carrier_ok; mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); @@ -956,7 +961,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); recover_flag = card->state; - rc = qeth_core_hardsetup_card(card); + rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); rc = -ENODEV; @@ -967,7 +972,7 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) dev_info(&card->gdev->dev, "The device represents a Bridge Capable Port\n"); - rc = qeth_l2_setup_netdev(card); + rc = qeth_l2_setup_netdev(card, carrier_ok); if (rc) goto out_remove; diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 0b161cc1fd2e..f08b745c2007 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -278,9 +278,6 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover) QETH_CARD_TEXT(card, 4, "clearip"); - if (recover && card->options.sniffer) - return; - spin_lock_bh(&card->ip_lock); hash_for_each_safe(card->ip_htable, i, tmp, addr, hnode) { @@ -494,9 +491,8 @@ int qeth_l3_setrouting_v4(struct qeth_card *card) QETH_PROT_IPV4); if (rc) { card->options.route4.type = NO_ROUTER; - QETH_DBF_MESSAGE(2, "Error (0x%04x) while setting routing type" - " on %s. Type set to 'no router'.\n", rc, - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Error (%#06x) while setting routing type on device %x. Type set to 'no router'.\n", + rc, CARD_DEVID(card)); } return rc; } @@ -518,9 +514,8 @@ int qeth_l3_setrouting_v6(struct qeth_card *card) QETH_PROT_IPV6); if (rc) { card->options.route6.type = NO_ROUTER; - QETH_DBF_MESSAGE(2, "Error (0x%04x) while setting routing type" - " on %s. Type set to 'no router'.\n", rc, - QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Error (%#06x) while setting routing type on device %x. Type set to 'no router'.\n", + rc, CARD_DEVID(card)); } return rc; } @@ -663,6 +658,8 @@ static int qeth_l3_register_addr_entry(struct qeth_card *card, int rc = 0; int cnt = 3; + if (card->options.sniffer) + return 0; if (addr->proto == QETH_PROT_IPV4) { QETH_CARD_TEXT(card, 2, "setaddr4"); @@ -697,6 +694,9 @@ static int qeth_l3_deregister_addr_entry(struct qeth_card *card, { int rc = 0; + if (card->options.sniffer) + return 0; + if (addr->proto == QETH_PROT_IPV4) { QETH_CARD_TEXT(card, 2, "deladdr4"); QETH_CARD_HEX(card, 3, &addr->u.a4.addr, sizeof(int)); @@ -1070,8 +1070,8 @@ qeth_diags_trace_cb(struct qeth_card *card, struct qeth_reply *reply, } break; default: - QETH_DBF_MESSAGE(2, "Unknown sniffer action (0x%04x) on %s\n", - cmd->data.diagass.action, QETH_CARD_IFNAME(card)); + QETH_DBF_MESSAGE(2, "Unknown sniffer action (%#06x) on device %x\n", + cmd->data.diagass.action, CARD_DEVID(card)); } return 0; @@ -1517,32 +1517,25 @@ static void qeth_l3_set_rx_mode(struct net_device *dev) qeth_l3_handle_promisc_mode(card); } -static const char *qeth_l3_arp_get_error_cause(int *rc) +static int qeth_l3_arp_makerc(int rc) { - switch (*rc) { - case QETH_IPA_ARP_RC_FAILED: - *rc = -EIO; - return "operation failed"; + switch (rc) { + case IPA_RC_SUCCESS: + return 0; case QETH_IPA_ARP_RC_NOTSUPP: - *rc = -EOPNOTSUPP; - return "operation not supported"; - case QETH_IPA_ARP_RC_OUT_OF_RANGE: - *rc = -EINVAL; - return "argument out of range"; case QETH_IPA_ARP_RC_Q_NOTSUPP: - *rc = -EOPNOTSUPP; - return "query operation not supported"; + return -EOPNOTSUPP; + case QETH_IPA_ARP_RC_OUT_OF_RANGE: + return -EINVAL; case QETH_IPA_ARP_RC_Q_NO_DATA: - *rc = -ENOENT; - return "no query data available"; + return -ENOENT; default: - return "unknown error"; + return -EIO; } } static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) { - int tmp; int rc; QETH_CARD_TEXT(card, 3, "arpstnoe"); @@ -1560,13 +1553,10 @@ static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_SET_NO_ENTRIES, no_entries); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, "Could not set number of ARP entries on " - "%s: %s (0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not set number of ARP entries on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static __u32 get_arp_entry_size(struct qeth_card *card, @@ -1716,7 +1706,6 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, { struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - int tmp; int rc; QETH_CARD_TEXT_(card, 3, "qarpipv%i", prot); @@ -1735,15 +1724,10 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, rc = qeth_l3_send_ipa_arp_cmd(card, iob, QETH_SETASS_BASE_LEN+QETH_ARP_CMD_LEN, qeth_l3_arp_query_cb, (void *)qinfo); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, - "Error while querying ARP cache on %s: %s " - "(0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Error while querying ARP cache on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_arp_query(struct qeth_card *card, char __user *udata) @@ -1793,15 +1777,18 @@ out: return rc; } -static int qeth_l3_arp_add_entry(struct qeth_card *card, - struct qeth_arp_cache_entry *entry) +static int qeth_l3_arp_modify_entry(struct qeth_card *card, + struct qeth_arp_cache_entry *entry, + enum qeth_arp_process_subcmds arp_cmd) { + struct qeth_arp_cache_entry *cmd_entry; struct qeth_cmd_buffer *iob; - char buf[16]; - int tmp; int rc; - QETH_CARD_TEXT(card, 3, "arpadent"); + if (arp_cmd == IPA_CMD_ASS_ARP_ADD_ENTRY) + QETH_CARD_TEXT(card, 3, "arpadd"); + else + QETH_CARD_TEXT(card, 3, "arpdel"); /* * currently GuestLAN only supports the ARP assist function @@ -1814,71 +1801,25 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card, return -EOPNOTSUPP; } - iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_ADD_ENTRY, - sizeof(struct qeth_arp_cache_entry), - QETH_PROT_IPV4); + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, arp_cmd, + sizeof(*cmd_entry), QETH_PROT_IPV4); if (!iob) return -ENOMEM; - rc = qeth_send_setassparms(card, iob, - sizeof(struct qeth_arp_cache_entry), - (unsigned long) entry, - qeth_setassparms_cb, NULL); - if (rc) { - tmp = rc; - qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf); - QETH_DBF_MESSAGE(2, "Could not add ARP entry for address %s " - "on %s: %s (0x%x/%d)\n", buf, QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; -} - -static int qeth_l3_arp_remove_entry(struct qeth_card *card, - struct qeth_arp_cache_entry *entry) -{ - struct qeth_cmd_buffer *iob; - char buf[16] = {0, }; - int tmp; - int rc; - QETH_CARD_TEXT(card, 3, "arprment"); + cmd_entry = &__ipa_cmd(iob)->data.setassparms.data.arp_entry; + ether_addr_copy(cmd_entry->macaddr, entry->macaddr); + memcpy(cmd_entry->ipaddr, entry->ipaddr, 4); + rc = qeth_send_ipa_cmd(card, iob, qeth_setassparms_cb, NULL); + if (rc) + QETH_DBF_MESSAGE(2, "Could not modify (cmd: %#x) ARP entry on device %x: %#x\n", + arp_cmd, CARD_DEVID(card), rc); - /* - * currently GuestLAN only supports the ARP assist function - * IPA_CMD_ASS_ARP_QUERY_INFO, but not IPA_CMD_ASS_ARP_REMOVE_ENTRY; - * thus we say EOPNOTSUPP for this ARP function - */ - if (card->info.guestlan) - return -EOPNOTSUPP; - if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { - return -EOPNOTSUPP; - } - memcpy(buf, entry, 12); - iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_REMOVE_ENTRY, - 12, - QETH_PROT_IPV4); - if (!iob) - return -ENOMEM; - rc = qeth_send_setassparms(card, iob, - 12, (unsigned long)buf, - qeth_setassparms_cb, NULL); - if (rc) { - tmp = rc; - memset(buf, 0, 16); - qeth_l3_ipaddr4_to_string((u8 *)entry->ipaddr, buf); - QETH_DBF_MESSAGE(2, "Could not delete ARP entry for address %s" - " on %s: %s (0x%x/%d)\n", buf, QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + return qeth_l3_arp_makerc(rc); } static int qeth_l3_arp_flush_cache(struct qeth_card *card) { int rc; - int tmp; QETH_CARD_TEXT(card, 3, "arpflush"); @@ -1894,19 +1835,17 @@ static int qeth_l3_arp_flush_cache(struct qeth_card *card) } rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_FLUSH_CACHE, 0); - if (rc) { - tmp = rc; - QETH_DBF_MESSAGE(2, "Could not flush ARP cache on %s: %s " - "(0x%x/%d)\n", QETH_CARD_IFNAME(card), - qeth_l3_arp_get_error_cause(&rc), tmp, tmp); - } - return rc; + if (rc) + QETH_DBF_MESSAGE(2, "Could not flush ARP cache on device %x: %#x\n", + CARD_DEVID(card), rc); + return qeth_l3_arp_makerc(rc); } static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { struct qeth_card *card = dev->ml_priv; struct qeth_arp_cache_entry arp_entry; + enum qeth_arp_process_subcmds arp_cmd; int rc = 0; switch (cmd) { @@ -1925,27 +1864,16 @@ static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) rc = qeth_l3_arp_query(card, rq->ifr_ifru.ifru_data); break; case SIOC_QETH_ARP_ADD_ENTRY: - if (!capable(CAP_NET_ADMIN)) { - rc = -EPERM; - break; - } - if (copy_from_user(&arp_entry, rq->ifr_ifru.ifru_data, - sizeof(struct qeth_arp_cache_entry))) - rc = -EFAULT; - else - rc = qeth_l3_arp_add_entry(card, &arp_entry); - break; case SIOC_QETH_ARP_REMOVE_ENTRY: - if (!capable(CAP_NET_ADMIN)) { - rc = -EPERM; - break; - } - if (copy_from_user(&arp_entry, rq->ifr_ifru.ifru_data, - sizeof(struct qeth_arp_cache_entry))) - rc = -EFAULT; - else - rc = qeth_l3_arp_remove_entry(card, &arp_entry); - break; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (copy_from_user(&arp_entry, rq->ifr_data, sizeof(arp_entry))) + return -EFAULT; + + arp_cmd = (cmd == SIOC_QETH_ARP_ADD_ENTRY) ? + IPA_CMD_ASS_ARP_ADD_ENTRY : + IPA_CMD_ASS_ARP_REMOVE_ENTRY; + return qeth_l3_arp_modify_entry(card, &arp_entry, arp_cmd); case SIOC_QETH_ARP_FLUSH_CACHE: if (!capable(CAP_NET_ADMIN)) { rc = -EPERM; @@ -2383,12 +2311,12 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_neigh_setup = qeth_l3_neigh_setup, }; -static int qeth_l3_setup_netdev(struct qeth_card *card) +static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok) { unsigned int headroom; int rc; - if (card->dev->netdev_ops) + if (qeth_netdev_is_registered(card->dev)) return 0; if (card->info.type == QETH_CARD_TYPE_OSD || @@ -2457,6 +2385,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); rc = register_netdev(card->dev); + if (!rc && carrier_ok) + netif_carrier_on(card->dev); + out: if (rc) card->dev->netdev_ops = NULL; @@ -2497,7 +2428,8 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l3_set_offline(cgdev); - unregister_netdev(card->dev); + if (qeth_netdev_is_registered(card->dev)) + unregister_netdev(card->dev); qeth_l3_clear_ip_htable(card, 0); qeth_l3_clear_ipato_list(card); } @@ -2507,6 +2439,7 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) struct qeth_card *card = dev_get_drvdata(&gdev->dev); int rc = 0; enum qeth_card_states recover_flag; + bool carrier_ok; mutex_lock(&card->discipline_mutex); mutex_lock(&card->conf_mutex); @@ -2514,14 +2447,14 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode) QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); recover_flag = card->state; - rc = qeth_core_hardsetup_card(card); + rc = qeth_core_hardsetup_card(card, &carrier_ok); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "2err%04x", rc); rc = -ENODEV; goto out_remove; } - rc = qeth_l3_setup_netdev(card); + rc = qeth_l3_setup_netdev(card, carrier_ok); if (rc) goto out_remove; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index ff6ba6d86cd8..cc56cb3b3eca 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1614,10 +1614,10 @@ static void sci_request_dma(struct uart_port *port) hrtimer_init(&s->rx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); s->rx_timer.function = rx_timer_fn; + s->chan_rx_saved = s->chan_rx = chan; + if (port->type == PORT_SCIFA || port->type == PORT_SCIFB) sci_submit_rx(s); - - s->chan_rx_saved = s->chan_rx = chan; } } @@ -3102,6 +3102,7 @@ static struct uart_driver sci_uart_driver = { static int sci_remove(struct platform_device *dev) { struct sci_port *port = platform_get_drvdata(dev); + unsigned int type = port->port.type; /* uart_remove_... clears it */ sci_ports_in_use &= ~BIT(port->port.line); uart_remove_one_port(&sci_uart_driver, &port->port); @@ -3112,8 +3113,7 @@ static int sci_remove(struct platform_device *dev) sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_trigger.attr); } - if (port->port.type == PORT_SCIFA || port->port.type == PORT_SCIFB || - port->port.type == PORT_HSCIF) { + if (type == PORT_SCIFA || type == PORT_SCIFB || type == PORT_HSCIF) { sysfs_remove_file(&dev->dev.kobj, &dev_attr_rx_fifo_timeout.attr); } diff --git a/drivers/tty/tty_baudrate.c b/drivers/tty/tty_baudrate.c index 7576ceace571..f438eaa68246 100644 --- a/drivers/tty/tty_baudrate.c +++ b/drivers/tty/tty_baudrate.c @@ -77,7 +77,7 @@ speed_t tty_termios_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; } EXPORT_SYMBOL(tty_termios_baud_rate); @@ -113,7 +113,7 @@ speed_t tty_termios_input_baud_rate(struct ktermios *termios) else cbaud += 15; } - return baud_table[cbaud]; + return cbaud >= n_baud_table ? 0 : baud_table[cbaud]; #else /* IBSHIFT */ return tty_termios_baud_rate(termios); #endif /* IBSHIFT */ diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index 55370e651db3..41ec8e5010f3 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -1548,7 +1548,7 @@ static void csi_K(struct vc_data *vc, int vpar) scr_memsetw(start + offset, vc->vc_video_erase_char, 2 * count); vc->vc_need_wrap = 0; if (con_should_update(vc)) - do_update_region(vc, (unsigned long) start, count); + do_update_region(vc, (unsigned long)(start + offset), count); } static void csi_X(struct vc_data *vc, int vpar) /* erase the following vpar positions */ diff --git a/drivers/usb/typec/ucsi/Kconfig b/drivers/usb/typec/ucsi/Kconfig index e36d6c73c4a4..78118883f96c 100644 --- a/drivers/usb/typec/ucsi/Kconfig +++ b/drivers/usb/typec/ucsi/Kconfig @@ -23,6 +23,16 @@ config TYPEC_UCSI if TYPEC_UCSI +config UCSI_CCG + tristate "UCSI Interface Driver for Cypress CCGx" + depends on I2C + help + This driver enables UCSI support on platforms that expose a + Cypress CCGx Type-C controller over I2C interface. + + To compile the driver as a module, choose M here: the module will be + called ucsi_ccg. + config UCSI_ACPI tristate "UCSI ACPI Interface Driver" depends on ACPI diff --git a/drivers/usb/typec/ucsi/Makefile b/drivers/usb/typec/ucsi/Makefile index 7afbea512207..2f4900b26210 100644 --- a/drivers/usb/typec/ucsi/Makefile +++ b/drivers/usb/typec/ucsi/Makefile @@ -8,3 +8,5 @@ typec_ucsi-y := ucsi.o typec_ucsi-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_UCSI_ACPI) += ucsi_acpi.o + +obj-$(CONFIG_UCSI_CCG) += ucsi_ccg.o diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c new file mode 100644 index 000000000000..de8a43bdff68 --- /dev/null +++ b/drivers/usb/typec/ucsi/ucsi_ccg.c @@ -0,0 +1,307 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * UCSI driver for Cypress CCGx Type-C controller + * + * Copyright (C) 2017-2018 NVIDIA Corporation. All rights reserved. + * Author: Ajay Gupta <[email protected]> + * + * Some code borrowed from drivers/usb/typec/ucsi/ucsi_acpi.c + */ +#include <linux/acpi.h> +#include <linux/delay.h> +#include <linux/i2c.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include <asm/unaligned.h> +#include "ucsi.h" + +struct ucsi_ccg { + struct device *dev; + struct ucsi *ucsi; + struct ucsi_ppm ppm; + struct i2c_client *client; +}; + +#define CCGX_RAB_INTR_REG 0x06 +#define CCGX_RAB_UCSI_CONTROL 0x39 +#define CCGX_RAB_UCSI_CONTROL_START BIT(0) +#define CCGX_RAB_UCSI_CONTROL_STOP BIT(1) +#define CCGX_RAB_UCSI_DATA_BLOCK(offset) (0xf000 | ((offset) & 0xff)) + +static int ccg_read(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + const struct i2c_adapter_quirks *quirks = client->adapter->quirks; + unsigned char buf[2]; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + .len = sizeof(buf), + .buf = buf, + }, + { + .addr = client->addr, + .flags = I2C_M_RD, + .buf = data, + }, + }; + u32 rlen, rem_len = len, max_read_len = len; + int status; + + /* check any max_read_len limitation on i2c adapter */ + if (quirks && quirks->max_read_len) + max_read_len = quirks->max_read_len; + + while (rem_len > 0) { + msgs[1].buf = &data[len - rem_len]; + rlen = min_t(u16, rem_len, max_read_len); + msgs[1].len = rlen; + put_unaligned_le16(rab, buf); + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + return status; + } + rab += rlen; + rem_len -= rlen; + } + + return 0; +} + +static int ccg_write(struct ucsi_ccg *uc, u16 rab, u8 *data, u32 len) +{ + struct i2c_client *client = uc->client; + unsigned char *buf; + struct i2c_msg msgs[] = { + { + .addr = client->addr, + .flags = 0x0, + } + }; + int status; + + buf = kzalloc(len + sizeof(rab), GFP_KERNEL); + if (!buf) + return -ENOMEM; + + put_unaligned_le16(rab, buf); + memcpy(buf + sizeof(rab), data, len); + + msgs[0].len = len + sizeof(rab); + msgs[0].buf = buf; + + status = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs)); + if (status < 0) { + dev_err(uc->dev, "i2c_transfer failed %d\n", status); + kfree(buf); + return status; + } + + kfree(buf); + return 0; +} + +static int ucsi_ccg_init(struct ucsi_ccg *uc) +{ + unsigned int count = 10; + u8 data; + int status; + + data = CCGX_RAB_UCSI_CONTROL_STOP; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + data = CCGX_RAB_UCSI_CONTROL_START; + status = ccg_write(uc, CCGX_RAB_UCSI_CONTROL, &data, sizeof(data)); + if (status < 0) + return status; + + /* + * Flush CCGx RESPONSE queue by acking interrupts. Above ucsi control + * register write will push response which must be cleared. + */ + do { + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + if (!data) + return 0; + + status = ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + usleep_range(10000, 11000); + } while (--count); + + return -ETIMEDOUT; +} + +static int ucsi_ccg_send_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_out)); + status = ccg_write(uc, rab, ppm + + offsetof(struct ucsi_data, message_out), + sizeof(uc->ppm.data->message_out)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, ctrl)); + return ccg_write(uc, rab, ppm + offsetof(struct ucsi_data, ctrl), + sizeof(uc->ppm.data->ctrl)); +} + +static int ucsi_ccg_recv_data(struct ucsi_ccg *uc) +{ + u8 *ppm = (u8 *)uc->ppm.data; + int status; + u16 rab; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, cci)); + status = ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, cci), + sizeof(uc->ppm.data->cci)); + if (status < 0) + return status; + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, message_in)); + return ccg_read(uc, rab, ppm + offsetof(struct ucsi_data, message_in), + sizeof(uc->ppm.data->message_in)); +} + +static int ucsi_ccg_ack_interrupt(struct ucsi_ccg *uc) +{ + int status; + unsigned char data; + + status = ccg_read(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); + if (status < 0) + return status; + + return ccg_write(uc, CCGX_RAB_INTR_REG, &data, sizeof(data)); +} + +static int ucsi_ccg_sync(struct ucsi_ppm *ppm) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + int status; + + status = ucsi_ccg_recv_data(uc); + if (status < 0) + return status; + + /* ack interrupt to allow next command to run */ + return ucsi_ccg_ack_interrupt(uc); +} + +static int ucsi_ccg_cmd(struct ucsi_ppm *ppm, struct ucsi_control *ctrl) +{ + struct ucsi_ccg *uc = container_of(ppm, struct ucsi_ccg, ppm); + + ppm->data->ctrl.raw_cmd = ctrl->raw_cmd; + return ucsi_ccg_send_data(uc); +} + +static irqreturn_t ccg_irq_handler(int irq, void *data) +{ + struct ucsi_ccg *uc = data; + + ucsi_notify(uc->ucsi); + + return IRQ_HANDLED; +} + +static int ucsi_ccg_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct device *dev = &client->dev; + struct ucsi_ccg *uc; + int status; + u16 rab; + + uc = devm_kzalloc(dev, sizeof(*uc), GFP_KERNEL); + if (!uc) + return -ENOMEM; + + uc->ppm.data = devm_kzalloc(dev, sizeof(struct ucsi_data), GFP_KERNEL); + if (!uc->ppm.data) + return -ENOMEM; + + uc->ppm.cmd = ucsi_ccg_cmd; + uc->ppm.sync = ucsi_ccg_sync; + uc->dev = dev; + uc->client = client; + + /* reset ccg device and initialize ucsi */ + status = ucsi_ccg_init(uc); + if (status < 0) { + dev_err(uc->dev, "ucsi_ccg_init failed - %d\n", status); + return status; + } + + status = devm_request_threaded_irq(dev, client->irq, NULL, + ccg_irq_handler, + IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + dev_name(dev), uc); + if (status < 0) { + dev_err(uc->dev, "request_threaded_irq failed - %d\n", status); + return status; + } + + uc->ucsi = ucsi_register_ppm(dev, &uc->ppm); + if (IS_ERR(uc->ucsi)) { + dev_err(uc->dev, "ucsi_register_ppm failed\n"); + return PTR_ERR(uc->ucsi); + } + + rab = CCGX_RAB_UCSI_DATA_BLOCK(offsetof(struct ucsi_data, version)); + status = ccg_read(uc, rab, (u8 *)(uc->ppm.data) + + offsetof(struct ucsi_data, version), + sizeof(uc->ppm.data->version)); + if (status < 0) { + ucsi_unregister_ppm(uc->ucsi); + return status; + } + + i2c_set_clientdata(client, uc); + return 0; +} + +static int ucsi_ccg_remove(struct i2c_client *client) +{ + struct ucsi_ccg *uc = i2c_get_clientdata(client); + + ucsi_unregister_ppm(uc->ucsi); + + return 0; +} + +static const struct i2c_device_id ucsi_ccg_device_id[] = { + {"ccgx-ucsi", 0}, + {} +}; +MODULE_DEVICE_TABLE(i2c, ucsi_ccg_device_id); + +static struct i2c_driver ucsi_ccg_driver = { + .driver = { + .name = "ucsi_ccg", + }, + .probe = ucsi_ccg_probe, + .remove = ucsi_ccg_remove, + .id_table = ucsi_ccg_device_id, +}; + +module_i2c_driver(ucsi_ccg_driver); + +MODULE_AUTHOR("Ajay Gupta <[email protected]>"); +MODULE_DESCRIPTION("UCSI driver for Cypress CCGx Type-C controller"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index f15f89df1f36..7ea6fb6a2e5d 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -914,7 +914,7 @@ int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args) ret = xenmem_reservation_increase(args->nr_pages, args->frames); if (ret != args->nr_pages) { - pr_debug("Failed to decrease reservation for DMA buffer\n"); + pr_debug("Failed to increase reservation for DMA buffer\n"); ret = -EFAULT; } else { ret = 0; diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c index df1ed37c3269..de01a6d0059d 100644 --- a/drivers/xen/privcmd-buf.c +++ b/drivers/xen/privcmd-buf.c @@ -21,15 +21,9 @@ MODULE_LICENSE("GPL"); -static unsigned int limit = 64; -module_param(limit, uint, 0644); -MODULE_PARM_DESC(limit, "Maximum number of pages that may be allocated by " - "the privcmd-buf device per open file"); - struct privcmd_buf_private { struct mutex lock; struct list_head list; - unsigned int allocated; }; struct privcmd_buf_vma_private { @@ -60,13 +54,10 @@ static void privcmd_buf_vmapriv_free(struct privcmd_buf_vma_private *vma_priv) { unsigned int i; - vma_priv->file_priv->allocated -= vma_priv->n_pages; - list_del(&vma_priv->list); for (i = 0; i < vma_priv->n_pages; i++) - if (vma_priv->pages[i]) - __free_page(vma_priv->pages[i]); + __free_page(vma_priv->pages[i]); kfree(vma_priv); } @@ -146,8 +137,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) unsigned int i; int ret = 0; - if (!(vma->vm_flags & VM_SHARED) || count > limit || - file_priv->allocated + count > limit) + if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *), @@ -155,19 +145,15 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma) if (!vma_priv) return -ENOMEM; - vma_priv->n_pages = count; - count = 0; - for (i = 0; i < vma_priv->n_pages; i++) { + for (i = 0; i < count; i++) { vma_priv->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!vma_priv->pages[i]) break; - count++; + vma_priv->n_pages++; } mutex_lock(&file_priv->lock); - file_priv->allocated += count; - vma_priv->file_priv = file_priv; vma_priv->users = 1; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 80953528572d..68f322f600a0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3163,6 +3163,9 @@ void btrfs_destroy_inode(struct inode *inode); int btrfs_drop_inode(struct inode *inode); int __init btrfs_init_cachep(void); void __cold btrfs_destroy_cachep(void); +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path); struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, struct btrfs_root *root, int *was_new); struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b0ab41da91d1..3f0b6d1936e8 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1664,9 +1664,8 @@ static int cleaner_kthread(void *arg) struct btrfs_root *root = arg; struct btrfs_fs_info *fs_info = root->fs_info; int again; - struct btrfs_trans_handle *trans; - do { + while (1) { again = 0; /* Make the cleaner go to sleep early. */ @@ -1715,42 +1714,16 @@ static int cleaner_kthread(void *arg) */ btrfs_delete_unused_bgs(fs_info); sleep: + if (kthread_should_park()) + kthread_parkme(); + if (kthread_should_stop()) + return 0; if (!again) { set_current_state(TASK_INTERRUPTIBLE); - if (!kthread_should_stop()) - schedule(); + schedule(); __set_current_state(TASK_RUNNING); } - } while (!kthread_should_stop()); - - /* - * Transaction kthread is stopped before us and wakes us up. - * However we might have started a new transaction and COWed some - * tree blocks when deleting unused block groups for example. So - * make sure we commit the transaction we started to have a clean - * shutdown when evicting the btree inode - if it has dirty pages - * when we do the final iput() on it, eviction will trigger a - * writeback for it which will fail with null pointer dereferences - * since work queues and other resources were already released and - * destroyed by the time the iput/eviction/writeback is made. - */ - trans = btrfs_attach_transaction(root); - if (IS_ERR(trans)) { - if (PTR_ERR(trans) != -ENOENT) - btrfs_err(fs_info, - "cleaner transaction attach returned %ld", - PTR_ERR(trans)); - } else { - int ret; - - ret = btrfs_commit_transaction(trans); - if (ret) - btrfs_err(fs_info, - "cleaner open transaction commit returned %d", - ret); } - - return 0; } static int transaction_kthread(void *arg) @@ -3931,6 +3904,13 @@ void close_ctree(struct btrfs_fs_info *fs_info) int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); + /* + * We don't want the cleaner to start new transactions, add more delayed + * iputs, etc. while we're closing. We can't use kthread_stop() yet + * because that frees the task_struct, and the transaction kthread might + * still try to wake up the cleaner. + */ + kthread_park(fs_info->cleaner_kthread); /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); @@ -3958,9 +3938,8 @@ void close_ctree(struct btrfs_fs_info *fs_info) if (!sb_rdonly(fs_info->sb)) { /* - * If the cleaner thread is stopped and there are - * block groups queued for removal, the deletion will be - * skipped when we quit the cleaner thread. + * The cleaner kthread is stopped, so do one final pass over + * unused block groups. */ btrfs_delete_unused_bgs(fs_info); @@ -4359,13 +4338,23 @@ static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info, unpin = pinned_extents; again: while (1) { + /* + * The btrfs_finish_extent_commit() may get the same range as + * ours between find_first_extent_bit and clear_extent_dirty. + * Hence, hold the unused_bg_unpin_mutex to avoid double unpin + * the same extent range. + */ + mutex_lock(&fs_info->unused_bg_unpin_mutex); ret = find_first_extent_bit(unpin, 0, &start, &end, EXTENT_DIRTY, NULL); - if (ret) + if (ret) { + mutex_unlock(&fs_info->unused_bg_unpin_mutex); break; + } clear_extent_dirty(unpin, start, end); btrfs_error_unpin_extent_range(fs_info, start, end); + mutex_unlock(&fs_info->unused_bg_unpin_mutex); cond_resched(); } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 4ba0aedc878b..74aa552f4793 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -75,7 +75,8 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root, * sure NOFS is set to keep us from deadlocking. */ nofs_flag = memalloc_nofs_save(); - inode = btrfs_iget(fs_info->sb, &location, root, NULL); + inode = btrfs_iget_path(fs_info->sb, &location, root, NULL, path); + btrfs_release_path(path); memalloc_nofs_restore(nofs_flag); if (IS_ERR(inode)) return inode; @@ -838,6 +839,25 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info, path->search_commit_root = 1; path->skip_locking = 1; + /* + * We must pass a path with search_commit_root set to btrfs_iget in + * order to avoid a deadlock when allocating extents for the tree root. + * + * When we are COWing an extent buffer from the tree root, when looking + * for a free extent, at extent-tree.c:find_free_extent(), we can find + * block group without its free space cache loaded. When we find one + * we must load its space cache which requires reading its free space + * cache's inode item from the root tree. If this inode item is located + * in the same leaf that we started COWing before, then we end up in + * deadlock on the extent buffer (trying to read lock it when we + * previously write locked it). + * + * It's safe to read the inode item using the commit root because + * block groups, once loaded, stay in memory forever (until they are + * removed) as well as their space caches once loaded. New block groups + * once created get their ->cached field set to BTRFS_CACHE_FINISHED so + * we will never try to read their inode item while the fs is mounted. + */ inode = lookup_free_space_inode(fs_info, block_group, path); if (IS_ERR(inode)) { btrfs_free_path(path); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d3df5b52278c..9ea4c6f0352f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1531,12 +1531,11 @@ out_check: } btrfs_release_path(path); - if (cur_offset <= end && cow_start == (u64)-1) { + if (cur_offset <= end && cow_start == (u64)-1) cow_start = cur_offset; - cur_offset = end; - } if (cow_start != (u64)-1) { + cur_offset = end; ret = cow_file_range(inode, locked_page, cow_start, end, end, page_started, nr_written, 1, NULL); if (ret) @@ -3570,10 +3569,11 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, /* * read an inode from the btree into the in-memory inode */ -static int btrfs_read_locked_inode(struct inode *inode) +static int btrfs_read_locked_inode(struct inode *inode, + struct btrfs_path *in_path) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - struct btrfs_path *path; + struct btrfs_path *path = in_path; struct extent_buffer *leaf; struct btrfs_inode_item *inode_item; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -3589,15 +3589,18 @@ static int btrfs_read_locked_inode(struct inode *inode) if (!ret) filled = true; - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + } memcpy(&location, &BTRFS_I(inode)->location, sizeof(location)); ret = btrfs_lookup_inode(NULL, root, path, &location, 0); if (ret) { - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); return ret; } @@ -3722,7 +3725,8 @@ cache_acl: btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret); } - btrfs_free_path(path); + if (path != in_path) + btrfs_free_path(path); if (!maybe_acls) cache_no_acl(inode); @@ -5644,8 +5648,9 @@ static struct inode *btrfs_iget_locked(struct super_block *s, /* Get an inode object given its location and corresponding root. * Returns in *is_new if the inode was read from disk */ -struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, - struct btrfs_root *root, int *new) +struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new, + struct btrfs_path *path) { struct inode *inode; @@ -5656,7 +5661,7 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, if (inode->i_state & I_NEW) { int ret; - ret = btrfs_read_locked_inode(inode); + ret = btrfs_read_locked_inode(inode, path); if (!ret) { inode_tree_add(inode); unlock_new_inode(inode); @@ -5678,6 +5683,12 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, return inode; } +struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, + struct btrfs_root *root, int *new) +{ + return btrfs_iget_path(s, location, root, new, NULL); +} + static struct inode *new_simple_dir(struct super_block *s, struct btrfs_key *key, struct btrfs_root *root) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 3ca6943827ef..802a628e9f7d 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3488,6 +3488,8 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize; len = round_down(i_size_read(src), sz) - loff; + if (len == 0) + return 0; olen = len; } } @@ -4257,9 +4259,17 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, goto out_unlock; if (len == 0) olen = len = src->i_size - off; - /* if we extend to eof, continue to block boundary */ - if (off + len == src->i_size) + /* + * If we extend to eof, continue to block boundary if and only if the + * destination end offset matches the destination file's size, otherwise + * we would be corrupting data by placing the eof block into the middle + * of a file. + */ + if (off + len == src->i_size) { + if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size) + goto out_unlock; len = ALIGN(src->i_size, bs) - off; + } if (len == 0) { ret = 0; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b362b45dd757..cbc9d0d2c12d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1916,7 +1916,7 @@ restore: } /* Used to sort the devices by max_avail(descending sort) */ -static int btrfs_cmp_device_free_bytes(const void *dev_info1, +static inline int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2) { if (((struct btrfs_device_info *)dev_info1)->max_avail > @@ -1945,8 +1945,8 @@ static inline void btrfs_descending_sort_devices( * The helper to calc the free space on the devices that can be used to store * file data. */ -static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, - u64 *free_bytes) +static inline int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info, + u64 *free_bytes) { struct btrfs_device_info *devices_info; struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index cab0b1f1f741..efcf89a8ba44 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -440,7 +440,7 @@ static int check_block_group_item(struct btrfs_fs_info *fs_info, type != (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)) { block_group_err(fs_info, leaf, slot, -"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx", +"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llx or 0x%llx", type, hweight64(type), BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA, BTRFS_BLOCK_GROUP_SYSTEM, diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index e07f3376b7df..a5ce99a6c936 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -4396,6 +4396,23 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans, logged_end = end; list_for_each_entry_safe(em, n, &tree->modified_extents, list) { + /* + * Skip extents outside our logging range. It's important to do + * it for correctness because if we don't ignore them, we may + * log them before their ordered extent completes, and therefore + * we could log them without logging their respective checksums + * (the checksum items are added to the csum tree at the very + * end of btrfs_finish_ordered_io()). Also leave such extents + * outside of our range in the list, since we may have another + * ranged fsync in the near future that needs them. If an extent + * outside our range corresponds to a hole, log it to avoid + * leaving gaps between extents (fsck will complain when we are + * not using the NO_HOLES feature). + */ + if ((em->start > end || em->start + em->len <= start) && + em->block_start != EXTENT_MAP_HOLE) + continue; + list_del_init(&em->list); /* * Just an arbitrary number, this can be really CPU intensive diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 27cad84dab23..189df668b6a0 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -1931,10 +1931,17 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off, if (!prealloc_cf) return -ENOMEM; - /* Start by sync'ing the source file */ + /* Start by sync'ing the source and destination files */ ret = file_write_and_wait_range(src_file, src_off, (src_off + len)); - if (ret < 0) + if (ret < 0) { + dout("failed to write src file (%zd)\n", ret); + goto out; + } + ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len)); + if (ret < 0) { + dout("failed to write dst file (%zd)\n", ret); goto out; + } /* * We need FILE_WR caps for dst_ci and FILE_RD for src_ci as other diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 67a9aeb2f4ec..bd13a3267ae0 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -80,12 +80,8 @@ static int parse_reply_info_in(void **p, void *end, info->symlink = *p; *p += info->symlink_len; - if (features & CEPH_FEATURE_DIRLAYOUTHASH) - ceph_decode_copy_safe(p, end, &info->dir_layout, - sizeof(info->dir_layout), bad); - else - memset(&info->dir_layout, 0, sizeof(info->dir_layout)); - + ceph_decode_copy_safe(p, end, &info->dir_layout, + sizeof(info->dir_layout), bad); ceph_decode_32_safe(p, end, info->xattr_len, bad); ceph_decode_need(p, end, info->xattr_len, bad); info->xattr_data = *p; @@ -3182,10 +3178,8 @@ static void send_mds_reconnect(struct ceph_mds_client *mdsc, recon_state.pagelist = pagelist; if (session->s_con.peer_features & CEPH_FEATURE_MDSENC) recon_state.msg_version = 3; - else if (session->s_con.peer_features & CEPH_FEATURE_FLOCK) - recon_state.msg_version = 2; else - recon_state.msg_version = 1; + recon_state.msg_version = 2; err = iterate_session_caps(session, encode_caps_cb, &recon_state); if (err < 0) goto fail; diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index 32d4f13784ba..03f4d24db8fe 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -237,7 +237,8 @@ static bool check_quota_exceeded(struct inode *inode, enum quota_check_op op, ceph_put_snap_realm(mdsc, realm); realm = next; } - ceph_put_snap_realm(mdsc, realm); + if (realm) + ceph_put_snap_realm(mdsc, realm); up_read(&mdsc->snap_rwsem); return exceeded; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 05f01fbd9c7f..22a9d8159720 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5835,9 +5835,10 @@ int ext4_mark_iloc_dirty(handle_t *handle, { int err = 0; - if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) + if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) { + put_bh(iloc->bh); return -EIO; - + } if (IS_I_VERSION(inode)) inode_inc_iversion(inode); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 17adcb16a9c8..437f71fe83ae 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -126,6 +126,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, if (!is_dx_block && type == INDEX) { ext4_error_inode(inode, func, line, block, "directory leaf block found instead of index block"); + brelse(bh); return ERR_PTR(-EFSCORRUPTED); } if (!ext4_has_metadata_csum(inode->i_sb) || @@ -2811,7 +2812,9 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode) list_del_init(&EXT4_I(inode)->i_orphan); mutex_unlock(&sbi->s_orphan_lock); } - } + } else + brelse(iloc.bh); + jbd_debug(4, "superblock will point to %lu\n", inode->i_ino); jbd_debug(4, "orphan inode %lu will point to %d\n", inode->i_ino, NEXT_ORPHAN(inode)); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ebbc663d0798..a5efee34415f 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -459,16 +459,18 @@ static int set_flexbg_block_bitmap(struct super_block *sb, handle_t *handle, BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, bh); - if (err) + if (err) { + brelse(bh); return err; + } ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", first_cluster, first_cluster - start, count2); ext4_set_bits(bh->b_data, first_cluster - start, count2); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (unlikely(err)) return err; - brelse(bh); } return 0; @@ -605,7 +607,6 @@ handle_bb: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } overhead = ext4_group_overhead_blocks(sb, group); @@ -618,9 +619,9 @@ handle_bb: ext4_mark_bitmap_end(EXT4_B2C(sbi, group_data[i].blocks_count), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); handle_ib: if (bg_flags[i] & EXT4_BG_INODE_UNINIT) @@ -635,18 +636,16 @@ handle_ib: bh = bclean(handle, sb, block); if (IS_ERR(bh)) { err = PTR_ERR(bh); - bh = NULL; goto out; } ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8, bh->b_data); err = ext4_handle_dirty_metadata(handle, NULL, bh); + brelse(bh); if (err) goto out; - brelse(bh); } - bh = NULL; /* Mark group tables in block bitmap */ for (j = 0; j < GROUP_TABLE_COUNT; j++) { @@ -685,7 +684,6 @@ handle_ib: } out: - brelse(bh); err2 = ext4_journal_stop(handle); if (err2 && !err) err = err2; @@ -873,6 +871,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode, err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh); if (unlikely(err)) { ext4_std_error(sb, err); + iloc.bh = NULL; goto exit_inode; } brelse(dind); @@ -924,6 +923,7 @@ static int add_new_gdb_meta_bg(struct super_block *sb, sizeof(struct buffer_head *), GFP_NOFS); if (!n_group_desc) { + brelse(gdb_bh); err = -ENOMEM; ext4_warning(sb, "not enough memory for %lu groups", gdb_num + 1); @@ -939,8 +939,6 @@ static int add_new_gdb_meta_bg(struct super_block *sb, kvfree(o_group_desc); BUFFER_TRACE(gdb_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, gdb_bh); - if (unlikely(err)) - brelse(gdb_bh); return err; } @@ -1124,8 +1122,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, backup_block, backup_block - ext4_group_first_block_no(sb, group)); BUFFER_TRACE(bh, "get_write_access"); - if ((err = ext4_journal_get_write_access(handle, bh))) + if ((err = ext4_journal_get_write_access(handle, bh))) { + brelse(bh); break; + } lock_buffer(bh); memcpy(bh->b_data, data, size); if (rest) @@ -2023,7 +2023,7 @@ retry: err = ext4_alloc_flex_bg_array(sb, n_group + 1); if (err) - return err; + goto out; err = ext4_mb_alloc_groupinfo(sb, n_group + 1); if (err) @@ -2059,6 +2059,10 @@ retry: n_blocks_count_retry = 0; free_flex_gd(flex_gd); flex_gd = NULL; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } goto retry; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index a221f1cdf704..53ff6c2a26ed 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4075,6 +4075,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_groups_count = blocks_count; sbi->s_blockfile_groups = min_t(ext4_group_t, sbi->s_groups_count, (EXT4_MAX_BLOCK_FILE_PHYS / EXT4_BLOCKS_PER_GROUP(sb))); + if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != + le32_to_cpu(es->s_inodes_count)) { + ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", + le32_to_cpu(es->s_inodes_count), + ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); + ret = -EINVAL; + goto failed_mount; + } db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) / EXT4_DESC_PER_BLOCK(sb); if (ext4_has_feature_meta_bg(sb)) { @@ -4094,14 +4102,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto failed_mount; } - if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) != - le32_to_cpu(es->s_inodes_count)) { - ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu", - le32_to_cpu(es->s_inodes_count), - ((u64)sbi->s_groups_count * sbi->s_inodes_per_group)); - ret = -EINVAL; - goto failed_mount; - } bgl_lock_init(sbi->s_blockgroup_lock); @@ -4510,6 +4510,7 @@ failed_mount6: percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_free_rwsem(&sbi->s_journal_flag_rwsem); failed_mount5: ext4_ext_release(sb); ext4_release_system_zone(sb); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index f36fc5d5b257..7643d52c776c 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1031,10 +1031,8 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, inode_lock(ea_inode); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); - if (ret) { - iloc.bh = NULL; + if (ret) goto out; - } ref_count = ext4_xattr_inode_get_ref(ea_inode); ref_count += ref_change; @@ -1080,12 +1078,10 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); - iloc.bh = NULL; if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: - brelse(iloc.bh); inode_unlock(ea_inode); return ret; } @@ -1388,6 +1384,12 @@ retry: bh = ext4_getblk(handle, ea_inode, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); + if (!bh) { + WARN_ON_ONCE(1); + EXT4_ERROR_INODE(ea_inode, + "ext4_getblk() return bh = NULL"); + return -EFSCORRUPTED; + } ret = ext4_journal_get_write_access(handle, bh); if (ret) goto out; @@ -2276,8 +2278,10 @@ static struct buffer_head *ext4_xattr_get_block(struct inode *inode) if (!bh) return ERR_PTR(-EIO); error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); return ERR_PTR(error); + } return bh; } @@ -2397,6 +2401,8 @@ retry_inode: error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { + brelse(bs.bh); + bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; @@ -2617,6 +2623,8 @@ out: kfree(buffer); if (is) brelse(is->iloc.bh); + if (bs) + brelse(bs->bh); kfree(is); kfree(bs); @@ -2696,7 +2704,6 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; - struct buffer_head *bh; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; size_t min_offs; @@ -2737,13 +2744,17 @@ retry: * EA block can hold new_extra_isize bytes. */ if (EXT4_I(inode)->i_file_acl) { + struct buffer_head *bh; + bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl); error = -EIO; if (!bh) goto cleanup; error = ext4_xattr_check_block(inode, bh); - if (error) + if (error) { + brelse(bh); goto cleanup; + } base = BHDR(bh); end = bh->b_data + bh->b_size; min_offs = end - base; diff --git a/fs/namespace.c b/fs/namespace.c index 98d27da43304..74f64294a410 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1540,8 +1540,13 @@ static int do_umount(struct mount *mnt, int flags) namespace_lock(); lock_mount_hash(); - event++; + /* Recheck MNT_LOCKED with the locks held */ + retval = -EINVAL; + if (mnt->mnt.mnt_flags & MNT_LOCKED) + goto out; + + event++; if (flags & MNT_DETACH) { if (!list_empty(&mnt->mnt_list)) umount_tree(mnt, UMOUNT_PROPAGATE); @@ -1555,6 +1560,7 @@ static int do_umount(struct mount *mnt, int flags) retval = 0; } } +out: unlock_mount_hash(); namespace_unlock(); return retval; @@ -1645,7 +1651,7 @@ int ksys_umount(char __user *name, int flags) goto dput_and_out; if (!check_mnt(mnt)) goto dput_and_out; - if (mnt->mnt.mnt_flags & MNT_LOCKED) + if (mnt->mnt.mnt_flags & MNT_LOCKED) /* Check optimistically */ goto dput_and_out; retval = -EPERM; if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN)) @@ -1728,8 +1734,14 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry, for (s = r; s; s = next_mnt(s, r)) { if (!(flag & CL_COPY_UNBINDABLE) && IS_MNT_UNBINDABLE(s)) { - s = skip_mnt_tree(s); - continue; + if (s->mnt.mnt_flags & MNT_LOCKED) { + /* Both unbindable and locked. */ + q = ERR_PTR(-EPERM); + goto out; + } else { + s = skip_mnt_tree(s); + continue; + } } if (!(flag & CL_COPY_MNT_NS_FILE) && is_mnt_ns_file(s->mnt.mnt_root)) { @@ -1782,7 +1794,7 @@ void drop_collected_mounts(struct vfsmount *mnt) { namespace_lock(); lock_mount_hash(); - umount_tree(real_mount(mnt), UMOUNT_SYNC); + umount_tree(real_mount(mnt), 0); unlock_mount_hash(); namespace_unlock(); } diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 6fc5425b1474..2652d00842d6 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -243,7 +243,7 @@ xfs_attr3_leaf_verify( struct xfs_mount *mp = bp->b_target->bt_mount; struct xfs_attr_leafblock *leaf = bp->b_addr; struct xfs_attr_leaf_entry *entries; - uint16_t end; + uint32_t end; /* must be 32bit - see below */ int i; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf); @@ -293,6 +293,11 @@ xfs_attr3_leaf_verify( /* * Quickly check the freemap information. Attribute data has to be * aligned to 4-byte boundaries, and likewise for the free space. + * + * Note that for 64k block size filesystems, the freemap entries cannot + * overflow as they are only be16 fields. However, when checking end + * pointer of the freemap, we have to be careful to detect overflows and + * so use uint32_t for those checks. */ for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr.freemap[i].base > mp->m_attr_geo->blksize) @@ -303,7 +308,9 @@ xfs_attr3_leaf_verify( return __this_address; if (ichdr.freemap[i].size & 0x3) return __this_address; - end = ichdr.freemap[i].base + ichdr.freemap[i].size; + + /* be care of 16 bit overflows here */ + end = (uint32_t)ichdr.freemap[i].base + ichdr.freemap[i].size; if (end < ichdr.freemap[i].base) return __this_address; if (end > mp->m_attr_geo->blksize) diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 6e2c08f30f60..6ecdbb3af7de 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1608,7 +1608,7 @@ xfs_ioc_getbmap( error = 0; out_free_buf: kmem_free(buf); - return 0; + return error; } struct getfsmap_info { diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c index 576c375ce12a..6b736ea58d35 100644 --- a/fs/xfs/xfs_message.c +++ b/fs/xfs/xfs_message.c @@ -107,5 +107,5 @@ assfail(char *expr, char *file, int line) void xfs_hex_dump(void *p, int length) { - print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1); + print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_OFFSET, 16, 1, p, length, 1); } diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h index 89f3b03b1445..e3667c9a33a5 100644 --- a/include/asm-generic/4level-fixup.h +++ b/include/asm-generic/4level-fixup.h @@ -3,7 +3,7 @@ #define _4LEVEL_FIXUP_H #define __ARCH_HAS_4LEVEL_HACK -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 #define PUD_SHIFT PGDIR_SHIFT #define PUD_SIZE PGDIR_SIZE diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h index 9c2e0708eb82..73474bb52344 100644 --- a/include/asm-generic/5level-fixup.h +++ b/include/asm-generic/5level-fixup.h @@ -3,7 +3,7 @@ #define _5LEVEL_FIXUP_H #define __ARCH_HAS_5LEVEL_HACK -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 #define P4D_SHIFT PGDIR_SHIFT #define P4D_SIZE PGDIR_SIZE diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h index 0c34215263b8..1d6dd38c0e5e 100644 --- a/include/asm-generic/pgtable-nop4d-hack.h +++ b/include/asm-generic/pgtable-nop4d-hack.h @@ -5,7 +5,7 @@ #ifndef __ASSEMBLY__ #include <asm-generic/5level-fixup.h> -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a pgd gets the size right, and allows diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h index 1a29b2a0282b..04cb913797bc 100644 --- a/include/asm-generic/pgtable-nop4d.h +++ b/include/asm-generic/pgtable-nop4d.h @@ -4,7 +4,7 @@ #ifndef __ASSEMBLY__ -#define __PAGETABLE_P4D_FOLDED +#define __PAGETABLE_P4D_FOLDED 1 typedef struct { pgd_t pgd; } p4d_t; diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index f35f6e8149e4..b85b8271a73d 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -8,7 +8,7 @@ struct mm_struct; -#define __PAGETABLE_PMD_FOLDED +#define __PAGETABLE_PMD_FOLDED 1 /* * Having the pmd type consist of a pud gets the size right, and allows diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h index e950b9c50f34..9bef475db6fe 100644 --- a/include/asm-generic/pgtable-nopud.h +++ b/include/asm-generic/pgtable-nopud.h @@ -9,7 +9,7 @@ #else #include <asm-generic/pgtable-nop4d.h> -#define __PAGETABLE_PUD_FOLDED +#define __PAGETABLE_PUD_FOLDED 1 /* * Having the pud type consist of a p4d gets the size right, and allows diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 5657a20e0c59..359fb935ded6 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -1127,4 +1127,20 @@ static inline bool arch_has_pfn_modify_check(void) #endif #endif +/* + * On some architectures it depends on the mm if the p4d/pud or pmd + * layer of the page table hierarchy is folded or not. + */ +#ifndef mm_p4d_folded +#define mm_p4d_folded(mm) __is_defined(__PAGETABLE_P4D_FOLDED) +#endif + +#ifndef mm_pud_folded +#define mm_pud_folded(mm) __is_defined(__PAGETABLE_PUD_FOLDED) +#endif + +#ifndef mm_pmd_folded +#define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) +#endif + #endif /* _ASM_GENERIC_PGTABLE_H */ diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h index 6b92b3395fa9..65a38c4a02a1 100644 --- a/include/linux/ceph/ceph_features.h +++ b/include/linux/ceph/ceph_features.h @@ -213,12 +213,6 @@ DEFINE_CEPH_FEATURE_DEPRECATED(63, 1, RESERVED_BROKEN, LUMINOUS) // client-facin CEPH_FEATURE_NEW_OSDOPREPLY_ENCODING | \ CEPH_FEATURE_CEPHX_V2) -#define CEPH_FEATURES_REQUIRED_DEFAULT \ - (CEPH_FEATURE_NOSRCADDR | \ - CEPH_FEATURE_SUBSCRIBE2 | \ - CEPH_FEATURE_RECONNECT_SEQ | \ - CEPH_FEATURE_PGID64 | \ - CEPH_FEATURE_PGPOOL3 | \ - CEPH_FEATURE_OSDENC) +#define CEPH_FEATURES_REQUIRED_DEFAULT 0 #endif diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index c0f5db3a9621..2010493e1040 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -143,18 +143,6 @@ #define KASAN_ABI_VERSION 3 #endif -/* - * Because __no_sanitize_address conflicts with inlining: - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 - * we do one or the other. - */ -#ifdef CONFIG_KASAN -#define __no_sanitize_address_or_inline \ - __no_sanitize_address __maybe_unused notrace -#else -#define __no_sanitize_address_or_inline inline -#endif - #if GCC_VERSION >= 50100 #define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1 #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 18c80cfa4fc4..06396c1cf127 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -189,7 +189,7 @@ void __read_once_size(const volatile void *p, void *res, int size) * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ -# define __no_kasan_or_inline __no_sanitize_address __maybe_unused +# define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused #else # define __no_kasan_or_inline __always_inline #endif diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 6b28c1b7310c..f8c400ba1929 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -4,22 +4,26 @@ /* * The attributes in this file are unconditionally defined and they directly - * map to compiler attribute(s) -- except those that are optional. + * map to compiler attribute(s), unless one of the compilers does not support + * the attribute. In that case, __has_attribute is used to check for support + * and the reason is stated in its comment ("Optional: ..."). * * Any other "attributes" (i.e. those that depend on a configuration option, * on a compiler, on an architecture, on plugins, on other attributes...) * should be defined elsewhere (e.g. compiler_types.h or compiler-*.h). + * The intention is to keep this file as simple as possible, as well as + * compiler- and version-agnostic (e.g. avoiding GCC_VERSION checks). * * This file is meant to be sorted (by actual attribute name, * not by #define identifier). Use the __attribute__((__name__)) syntax * (i.e. with underscores) to avoid future collisions with other macros. - * If an attribute is optional, state the reason in the comment. + * Provide links to the documentation of each supported compiler, if it exists. */ /* - * To check for optional attributes, we use __has_attribute, which is supported - * on gcc >= 5, clang >= 2.9 and icc >= 17. In the meantime, to support - * 4.6 <= gcc < 5, we implement __has_attribute by hand. + * __has_attribute is supported on gcc >= 5, clang >= 2.9 and icc >= 17. + * In the meantime, to support 4.6 <= gcc < 5, we implement __has_attribute + * by hand. * * sparse does not support __has_attribute (yet) and defines __GNUC_MINOR__ * depending on the compiler used to build it; however, these attributes have diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 3439d7d0249a..4a3f9c09c92d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -130,6 +130,10 @@ struct ftrace_likely_data { # define randomized_struct_fields_end #endif +#ifndef asm_volatile_goto +#define asm_volatile_goto(x...) asm goto(x) +#endif + /* Are two types/vars the same type (ignoring qualifiers)? */ #define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b)) diff --git a/include/linux/hid.h b/include/linux/hid.h index 2827b87590d8..387c70df6f29 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -722,8 +722,8 @@ struct hid_usage_id { * input will not be passed to raw_event unless hid_device_io_start is * called. * - * raw_event and event should return 0 on no action performed, 1 when no - * further processing should be done and negative on error + * raw_event and event should return negative on error, any other value will + * pass the event on to .event() typically return 0 for success. * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this diff --git a/include/linux/i8253.h b/include/linux/i8253.h index e6bb36a97519..8336b2f6f834 100644 --- a/include/linux/i8253.h +++ b/include/linux/i8253.h @@ -21,6 +21,7 @@ #define PIT_LATCH ((PIT_TICK_RATE + HZ/2) / HZ) extern raw_spinlock_t i8253_lock; +extern bool i8253_clear_counter_on_shutdown; extern struct clock_event_device i8253_clockevent; extern void clockevent_i8253_init(bool oneshot); diff --git a/include/linux/mm.h b/include/linux/mm.h index fcf9cc9d535f..5411de93a363 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1744,11 +1744,15 @@ int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address); static inline void mm_inc_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_add(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_puds(struct mm_struct *mm) { + if (mm_pud_folded(mm)) + return; atomic_long_sub(PTRS_PER_PUD * sizeof(pud_t), &mm->pgtables_bytes); } #endif @@ -1768,11 +1772,15 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); static inline void mm_inc_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_add(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } static inline void mm_dec_nr_pmds(struct mm_struct *mm) { + if (mm_pmd_folded(mm)) + return; atomic_long_sub(PTRS_PER_PMD * sizeof(pmd_t), &mm->pgtables_bytes); } #endif diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index abe975c87b90..7f53ece2c039 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -324,9 +324,8 @@ static inline unsigned int nanddev_ntargets(const struct nand_device *nand) */ static inline unsigned int nanddev_neraseblocks(const struct nand_device *nand) { - return (u64)nand->memorg.luns_per_target * - nand->memorg.eraseblocks_per_lun * - nand->memorg.pages_per_eraseblock; + return nand->memorg.ntargets * nand->memorg.luns_per_target * + nand->memorg.eraseblocks_per_lun; } /** @@ -569,7 +568,7 @@ static inline void nanddev_pos_next_eraseblock(struct nand_device *nand, } /** - * nanddev_pos_next_eraseblock() - Move a position to the next page + * nanddev_pos_next_page() - Move a position to the next page * @nand: NAND device * @pos: the position to update * diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dc1d9ed33b31..857f8abf7b91 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3190,6 +3190,26 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, #endif } +/* Variant of netdev_tx_sent_queue() for drivers that are aware + * that they should not test BQL status themselves. + * We do want to change __QUEUE_STATE_STACK_XOFF only for the last + * skb of a batch. + * Returns true if the doorbell must be used to kick the NIC. + */ +static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, + unsigned int bytes, + bool xmit_more) +{ + if (xmit_more) { +#ifdef CONFIG_BQL + dql_queued(&dev_queue->dql, bytes); +#endif + return netif_tx_queue_stopped(dev_queue); + } + netdev_tx_sent_queue(dev_queue, bytes); + return true; +} + /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index 34fc80f3eb90..1d100efe74ec 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -314,7 +314,7 @@ enum { extern ip_set_id_t ip_set_get_byname(struct net *net, const char *name, struct ip_set **set); extern void ip_set_put_byindex(struct net *net, ip_set_id_t index); -extern const char *ip_set_name_byindex(struct net *net, ip_set_id_t index); +extern void ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name); extern ip_set_id_t ip_set_nfnl_get_byindex(struct net *net, ip_set_id_t index); extern void ip_set_nfnl_put(struct net *net, ip_set_id_t index); diff --git a/include/linux/netfilter/ipset/ip_set_comment.h b/include/linux/netfilter/ipset/ip_set_comment.h index 8e2bab1e8e90..70877f8de7e9 100644 --- a/include/linux/netfilter/ipset/ip_set_comment.h +++ b/include/linux/netfilter/ipset/ip_set_comment.h @@ -43,11 +43,11 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment, rcu_assign_pointer(comment->c, c); } -/* Used only when dumping a set, protected by rcu_read_lock_bh() */ +/* Used only when dumping a set, protected by rcu_read_lock() */ static inline int ip_set_put_comment(struct sk_buff *skb, const struct ip_set_comment *comment) { - struct ip_set_comment_rcu *c = rcu_dereference_bh(comment->c); + struct ip_set_comment_rcu *c = rcu_dereference(comment->c); if (!c) return 0; diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 08f9247e9827..9003e29cde46 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -119,6 +119,8 @@ static inline int hardlockup_detector_perf_init(void) { return 0; } void watchdog_nmi_stop(void); void watchdog_nmi_start(void); int watchdog_nmi_probe(void); +int watchdog_nmi_enable(unsigned int cpu); +void watchdog_nmi_disable(unsigned int cpu); /** * touch_nmi_watchdog - restart NMI watchdog timeout. diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 14b789a123e7..1656c5978498 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -317,6 +317,8 @@ bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr); bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev, const struct in6_addr *addr); +int ipv6_anycast_init(void); +void ipv6_anycast_cleanup(void); /* Device notifier */ int register_inet6addr_notifier(struct notifier_block *nb); diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index d7578cf49c3a..c9c78c15bce0 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -146,10 +146,12 @@ struct ifacaddr6 { struct in6_addr aca_addr; struct fib6_info *aca_rt; struct ifacaddr6 *aca_next; + struct hlist_node aca_addr_lst; int aca_users; refcount_t aca_refcnt; unsigned long aca_cstamp; unsigned long aca_tstamp; + struct rcu_head rcu; }; #define IFA_HOST IPV6_ADDR_LOOPBACK diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index eed04af9b75e..ae7b86f587f2 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -153,4 +153,43 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, const char *fmt, ...) { } #endif /* CONFIG_SYSCTL */ +static inline struct nf_generic_net *nf_generic_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.generic; +} + +static inline struct nf_tcp_net *nf_tcp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.tcp; +} + +static inline struct nf_udp_net *nf_udp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.udp; +} + +static inline struct nf_icmp_net *nf_icmp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmp; +} + +static inline struct nf_icmp_net *nf_icmpv6_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.icmpv6; +} + +#ifdef CONFIG_NF_CT_PROTO_DCCP +static inline struct nf_dccp_net *nf_dccp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.dccp; +} +#endif + +#ifdef CONFIG_NF_CT_PROTO_SCTP +static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net) +{ + return &net->ct.nf_ct_proto.sctp; +} +#endif + #endif /*_NF_CONNTRACK_PROTOCOL_H*/ diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index f5ff8a76e208..b01eb502d49c 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -83,11 +83,11 @@ struct kfd_ioctl_set_cu_mask_args { }; struct kfd_ioctl_get_queue_wave_state_args { - uint64_t ctl_stack_address; /* to KFD */ - uint32_t ctl_stack_used_size; /* from KFD */ - uint32_t save_area_used_size; /* from KFD */ - uint32_t queue_id; /* to KFD */ - uint32_t pad; + __u64 ctl_stack_address; /* to KFD */ + __u32 ctl_stack_used_size; /* from KFD */ + __u32 save_area_used_size; /* from KFD */ + __u32 queue_id; /* to KFD */ + __u32 pad; }; /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */ @@ -255,10 +255,10 @@ struct kfd_hsa_memory_exception_data { /* hw exception data */ struct kfd_hsa_hw_exception_data { - uint32_t reset_type; - uint32_t reset_cause; - uint32_t memory_lost; - uint32_t gpu_id; + __u32 reset_type; + __u32 reset_cause; + __u32 memory_lost; + __u32 gpu_id; }; /* Event data */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 579974b0bf0d..7de4f1bdaf06 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1635,8 +1635,8 @@ enum nft_ng_attributes { NFTA_NG_MODULUS, NFTA_NG_TYPE, NFTA_NG_OFFSET, - NFTA_NG_SET_NAME, - NFTA_NG_SET_ID, + NFTA_NG_SET_NAME, /* deprecated */ + NFTA_NG_SET_ID, /* deprecated */ __NFTA_NG_MAX }; #define NFTA_NG_MAX (__NFTA_NG_MAX - 1) diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h index 156ccd089df1..1610fdbab98d 100644 --- a/include/uapi/linux/netfilter_bridge.h +++ b/include/uapi/linux/netfilter_bridge.h @@ -11,6 +11,10 @@ #include <linux/if_vlan.h> #include <linux/if_pppox.h> +#ifndef __KERNEL__ +#include <limits.h> /* for INT_MIN, INT_MAX */ +#endif + /* Bridge Hooks */ /* After promisc drops, checksum checks. */ #define NF_BR_PRE_ROUTING 0 diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 34dd3d497f2c..c81feb373d3e 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -568,6 +568,8 @@ struct sctp_assoc_reset_event { #define SCTP_ASSOC_CHANGE_DENIED 0x0004 #define SCTP_ASSOC_CHANGE_FAILED 0x0008 +#define SCTP_STREAM_CHANGE_DENIED SCTP_ASSOC_CHANGE_DENIED +#define SCTP_STREAM_CHANGE_FAILED SCTP_ASSOC_CHANGE_FAILED struct sctp_stream_change_event { __u16 strchange_type; __u16 strchange_flags; @@ -1151,6 +1153,7 @@ struct sctp_add_streams { /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, + SCTP_SS_DEFAULT = SCTP_SS_FCFS, SCTP_SS_PRIO, SCTP_SS_RR, SCTP_SS_MAX = SCTP_SS_RR diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 18803ff76e27..4969817124a8 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -42,16 +42,12 @@ int xen_setup_shutdown_event(void); extern unsigned long *xen_contiguous_bitmap; -#ifdef CONFIG_XEN_PV +#if defined(CONFIG_XEN_PV) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, unsigned int address_bits, dma_addr_t *dma_handle); void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); - -int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, - xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages); #else static inline int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, @@ -63,7 +59,13 @@ static inline int xen_create_contiguous_region(phys_addr_t pstart, static inline void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { } +#endif +#if defined(CONFIG_XEN_PV) +int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, + xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, + unsigned int domid, bool no_translate, struct page **pages); +#else static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, unsigned int domid, diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 6377225b2082..1a796e0799ec 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -553,7 +553,6 @@ bool is_bpf_text_address(unsigned long addr) int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { - unsigned long symbol_start, symbol_end; struct bpf_prog_aux *aux; unsigned int it = 0; int ret = -ERANGE; @@ -566,10 +565,9 @@ int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, if (it++ != symnum) continue; - bpf_get_prog_addr_region(aux->prog, &symbol_start, &symbol_end); bpf_get_prog_name(aux->prog, sym); - *value = symbol_start; + *value = (unsigned long)aux->prog->bpf_func; *type = BPF_SYM_ELF_TYPE; ret = 0; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ccb93277aae2..cf5040fd5434 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2078,6 +2078,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; + info.nr_jited_func_lens = 0; goto done; } @@ -2158,11 +2159,11 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_ksyms; - info.nr_jited_ksyms = prog->aux->func_cnt; + info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (info.nr_jited_ksyms && ulen) { if (bpf_dump_raw_ok()) { + unsigned long ksym_addr; u64 __user *user_ksyms; - ulong ksym_addr; u32 i; /* copy the address of the kernel symbol @@ -2170,10 +2171,17 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); - for (i = 0; i < ulen; i++) { - ksym_addr = (ulong) prog->aux->func[i]->bpf_func; - ksym_addr &= PAGE_MASK; - if (put_user((u64) ksym_addr, &user_ksyms[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + ksym_addr = (unsigned long) + prog->aux->func[i]->bpf_func; + if (put_user((u64) ksym_addr, + &user_ksyms[i])) + return -EFAULT; + } + } else { + ksym_addr = (unsigned long) prog->bpf_func; + if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { @@ -2182,7 +2190,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, } ulen = info.nr_jited_func_lens; - info.nr_jited_func_lens = prog->aux->func_cnt; + info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (info.nr_jited_func_lens && ulen) { if (bpf_dump_raw_ok()) { u32 __user *user_lens; @@ -2191,9 +2199,16 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); - for (i = 0; i < ulen; i++) { - func_len = prog->aux->func[i]->jited_len; - if (put_user(func_len, &user_lens[i])) + if (prog->aux->func_cnt) { + for (i = 0; i < ulen; i++) { + func_len = + prog->aux->func[i]->jited_len; + if (put_user(func_len, &user_lens[i])) + return -EFAULT; + } + } else { + func_len = prog->jited_len; + if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { diff --git a/kernel/resource.c b/kernel/resource.c index b3a3a1fc499e..b0fbf685c77a 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -319,16 +319,23 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); /** - * Finds the lowest iomem resource that covers part of [start..end]. The - * caller must specify start, end, flags, and desc (which may be + * Finds the lowest iomem resource that covers part of [@start..@end]. The + * caller must specify @start, @end, @flags, and @desc (which may be * IORES_DESC_NONE). * - * If a resource is found, returns 0 and *res is overwritten with the part - * of the resource that's within [start..end]; if none is found, returns - * -1. + * If a resource is found, returns 0 and @*res is overwritten with the part + * of the resource that's within [@start..@end]; if none is found, returns + * -1 or -EINVAL for other invalid parameters. * * This function walks the whole tree and not just first level children * unless @first_lvl is true. + * + * @start: start address of the resource searched for + * @end: end address of same resource + * @flags: flags which the resource must have + * @desc: descriptor the resource must have + * @first_lvl: walk only the first level children, if set + * @res: return ptr, if resource found */ static int find_next_iomem_res(resource_size_t start, resource_size_t end, unsigned long flags, unsigned long desc, @@ -399,6 +406,8 @@ static int __walk_iomem_res_desc(resource_size_t start, resource_size_t end, * @flags: I/O resource flags * @start: start addr * @end: end addr + * @arg: function argument for the callback @func + * @func: callback function that is called for each qualifying resource area * * NOTE: For a new descriptor search, define a new IORES_DESC in * <linux/ioport.h> and set it in 'desc' of a target resource entry. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f12225f26b70..091e089063be 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5851,11 +5851,14 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot - * happen. + * happen. The hotplug lock is nevertheless taken to satisfy lockdep, + * but there won't be any contention on it. */ + cpus_read_lock(); mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); mutex_unlock(&sched_domains_mutex); + cpus_read_unlock(); /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ee271bb661cc..3648d0300fdf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2400,8 +2400,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) local = 1; /* - * Retry task to preferred node migration periodically, in case it - * case it previously failed, or the scheduler moved us. + * Retry to migrate task to preferred node periodically, in case it + * previously failed, or the scheduler moved us. */ if (time_after(jiffies, p->numa_migrate_retry)) { task_numa_placement(p); diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index ce32cf741b25..8f0644af40be 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -917,9 +917,6 @@ static void check_process_timers(struct task_struct *tsk, struct task_cputime cputime; unsigned long soft; - if (dl_task(tsk)) - check_dl_overrun(tsk); - /* * If cputimer is not running, then there are no active * process wide timers (POSIX 1.b, itimers, RLIMIT_CPU). diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 3ef15a6683c0..bd30e9398d2a 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -535,7 +535,7 @@ int traceprobe_update_arg(struct probe_arg *arg) if (code[1].op != FETCH_OP_IMM) return -EINVAL; - tmp = strpbrk("+-", code->data); + tmp = strpbrk(code->data, "+-"); if (tmp) c = *tmp; ret = traceprobe_split_symbol_offset(code->data, diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index e5222b5fb4fe..923414a246e9 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -974,10 +974,6 @@ static ssize_t map_write(struct file *file, const char __user *buf, if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) goto out; - ret = sort_idmaps(&new_map); - if (ret < 0) - goto out; - ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. @@ -1004,6 +1000,14 @@ static ssize_t map_write(struct file *file, const char __user *buf, e->lower_first = lower_first; } + /* + * If we want to use binary search for lookup, this clones the extent + * array and sorts both copies. + */ + ret = sort_idmaps(&new_map); + if (ret < 0) + goto out; + /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile index 5d73f5cb4d8a..79777645cac9 100644 --- a/lib/raid6/test/Makefile +++ b/lib/raid6/test/Makefile @@ -27,7 +27,7 @@ ifeq ($(ARCH),arm) CFLAGS += -I../../../arch/arm/include -mfpu=neon HAS_NEON = yes endif -ifeq ($(ARCH),arm64) +ifeq ($(ARCH),aarch64) CFLAGS += -I../../../arch/arm64/include HAS_NEON = yes endif @@ -41,7 +41,7 @@ ifeq ($(IS_X86),yes) gcc -c -x assembler - >&/dev/null && \ rm ./-.o && echo -DCONFIG_AS_AVX512=1) else ifeq ($(HAS_NEON),yes) - OBJS += neon.o neon1.o neon2.o neon4.o neon8.o + OBJS += neon.o neon1.o neon2.o neon4.o neon8.o recov_neon.o recov_neon_inner.o CFLAGS += -DCONFIG_KERNEL_MODE_NEON=1 else HAS_ALTIVEC := $(shell printf '\#include <altivec.h>\nvector int a;\n' |\ diff --git a/net/core/dev.c b/net/core/dev.c index 77d43ae2a7bb..0ffcbdd55fa9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3272,7 +3272,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de } skb = next; - if (netif_xmit_stopped(txq) && skb) { + if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 676f3ad629f9..588f475019d4 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1166,8 +1166,8 @@ ip_proto_again: break; } - if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS)) { + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) && + !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 5da9552b186b..2b9fdbc43205 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -717,7 +717,8 @@ int netpoll_setup(struct netpoll *np) read_lock_bh(&idev->lock); list_for_each_entry(ifp, &idev->addr_list, if_list) { - if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) + if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) != + !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL)) continue; np->local_ip.in6 = ifp->addr; err = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e01274bd5e3e..33d9227a8b80 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3367,7 +3367,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = 0; } ret = dumpit(skb, cb); - if (ret < 0) + if (ret) break; } cb->family = idx; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 946de0e24c87..b4ee5c8b928f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4944,6 +4944,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb) * * This is a helper to do that correctly considering GSO_BY_FRAGS. * + * @skb: GSO skb + * * @seg_len: The segmented length (from skb_gso_*_seglen). In the * GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS]. * diff --git a/net/core/sock.c b/net/core/sock.c index 6fcc4bc07d19..080a880a1761 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3279,6 +3279,7 @@ int sock_load_diag_module(int family, int protocol) #ifdef CONFIG_INET if (family == AF_INET && + protocol != IPPROTO_RAW && !rcu_access_pointer(inet_protos[protocol])) return -ENOENT; #endif diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index bcb11f3a27c0..760a9e52e02b 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - void *arg) + void *arg, + struct inet_frag_queue **prev) { struct inet_frags *f = nf->f; struct inet_frag_queue *q; - int err; q = inet_frag_alloc(nf, f, arg); - if (!q) + if (!q) { + *prev = ERR_PTR(-ENOMEM); return NULL; - + } mod_timer(&q->timer, jiffies + nf->timeout); - err = rhashtable_insert_fast(&nf->rhashtable, &q->node, - f->rhash_params); - if (err < 0) { + *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key, + &q->node, f->rhash_params); + if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); @@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { - struct inet_frag_queue *fq; + struct inet_frag_queue *fq = NULL, *prev; if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) return NULL; rcu_read_lock(); - fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); - if (fq) { + prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (!prev) + fq = inet_frag_create(nf, key, &prev); + if (prev && !IS_ERR(prev)) { + fq = prev; if (!refcount_inc_not_zero(&fq->refcnt)) fq = NULL; - rcu_read_unlock(); - return fq; } rcu_read_unlock(); - - return inet_frag_create(nf, key); + return fq; } EXPORT_SYMBOL(inet_frag_find); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 9b0158fa431f..d6ee343fdb86 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -722,10 +722,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) if (ip_is_fragment(&iph)) { skb = skb_share_check(skb, GFP_ATOMIC); if (skb) { - if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) - return skb; - if (pskb_trim_rcsum(skb, netoff + len)) - return skb; + if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) { + kfree_skb(skb); + return NULL; + } + if (pskb_trim_rcsum(skb, netoff + len)) { + kfree_skb(skb); + return NULL; + } memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); if (ip_defrag(net, skb, user)) return NULL; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 26c36cccabdc..fffcc130900e 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1246,7 +1246,7 @@ int ip_setsockopt(struct sock *sk, int level, return -ENOPROTOOPT; err = do_ip_setsockopt(sk, level, optname, optval, optlen); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_SET_REPLACE && optname < BPFILTER_IPT_SET_MAX) err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen); @@ -1559,7 +1559,7 @@ int ip_getsockopt(struct sock *sk, int level, int err; err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); @@ -1596,7 +1596,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, err = do_ip_getsockopt(sk, level, optname, optval, optlen, MSG_CMSG_COMPAT); -#ifdef CONFIG_BPFILTER +#if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && optname < BPFILTER_IPT_GET_MAX) err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3f4d61017a69..f0cd291034f0 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1001,6 +1001,9 @@ static int __init inet6_init(void) err = ip6_flowlabel_init(); if (err) goto ip6_flowlabel_fail; + err = ipv6_anycast_init(); + if (err) + goto ipv6_anycast_fail; err = addrconf_init(); if (err) goto addrconf_fail; @@ -1091,6 +1094,8 @@ ipv6_frag_fail: ipv6_exthdrs_fail: addrconf_cleanup(); addrconf_fail: + ipv6_anycast_cleanup(); +ipv6_anycast_fail: ip6_flowlabel_cleanup(); ip6_flowlabel_fail: ndisc_late_cleanup(); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 4e0ff7031edd..94999058e110 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -44,8 +44,22 @@ #include <net/checksum.h> +#define IN6_ADDR_HSIZE_SHIFT 8 +#define IN6_ADDR_HSIZE BIT(IN6_ADDR_HSIZE_SHIFT) +/* anycast address hash table + */ +static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE]; +static DEFINE_SPINLOCK(acaddr_hash_lock); + static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr); +static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr) +{ + u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net); + + return hash_32(val, IN6_ADDR_HSIZE_SHIFT); +} + /* * socket join an anycast group */ @@ -204,16 +218,39 @@ void ipv6_sock_ac_close(struct sock *sk) rtnl_unlock(); } +static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca) +{ + unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr); + + spin_lock(&acaddr_hash_lock); + hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]); + spin_unlock(&acaddr_hash_lock); +} + +static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca) +{ + spin_lock(&acaddr_hash_lock); + hlist_del_init_rcu(&aca->aca_addr_lst); + spin_unlock(&acaddr_hash_lock); +} + static void aca_get(struct ifacaddr6 *aca) { refcount_inc(&aca->aca_refcnt); } +static void aca_free_rcu(struct rcu_head *h) +{ + struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu); + + fib6_info_release(aca->aca_rt); + kfree(aca); +} + static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) { - fib6_info_release(ac->aca_rt); - kfree(ac); + call_rcu(&ac->rcu, aca_free_rcu); } } @@ -229,6 +266,7 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, aca->aca_addr = *addr; fib6_info_hold(f6i); aca->aca_rt = f6i; + INIT_HLIST_NODE(&aca->aca_addr_lst); aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; @@ -285,6 +323,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca_get(aca); write_unlock_bh(&idev->lock); + ipv6_add_acaddr_hash(net, aca); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -325,6 +365,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) else idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -352,6 +393,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) idev->ac_list = aca->aca_next; write_unlock_bh(&idev->lock); + ipv6_del_acaddr_hash(aca); + addrconf_leave_solict(idev, &aca->aca_addr); ip6_del_rt(dev_net(idev->dev), aca->aca_rt); @@ -390,17 +433,25 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr) { + unsigned int hash = inet6_acaddr_hash(net, addr); + struct net_device *nh_dev; + struct ifacaddr6 *aca; bool found = false; rcu_read_lock(); if (dev) found = ipv6_chk_acast_dev(dev, addr); else - for_each_netdev_rcu(net, dev) - if (ipv6_chk_acast_dev(dev, addr)) { + hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash], + aca_addr_lst) { + nh_dev = fib6_info_nh_dev(aca->aca_rt); + if (!nh_dev || !net_eq(dev_net(nh_dev), net)) + continue; + if (ipv6_addr_equal(&aca->aca_addr, addr)) { found = true; break; } + } rcu_read_unlock(); return found; } @@ -540,3 +591,24 @@ void ac6_proc_exit(struct net *net) remove_proc_entry("anycast6", net->proc_net); } #endif + +/* Init / cleanup code + */ +int __init ipv6_anycast_init(void) +{ + int i; + + for (i = 0; i < IN6_ADDR_HSIZE; i++) + INIT_HLIST_HEAD(&inet6_acaddr_lst[i]); + return 0; +} + +void ipv6_anycast_cleanup(void) +{ + int i; + + spin_lock(&acaddr_hash_lock); + for (i = 0; i < IN6_ADDR_HSIZE; i++) + WARN_ON(!hlist_empty(&inet6_acaddr_lst[i])); + spin_unlock(&acaddr_hash_lock); +} diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1b8bc008b53b..ae3786132c23 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -591,7 +591,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) /* fib entries are never clones */ if (arg.filter.flags & RTM_F_CLONED) - return skb->len; + goto out; w = (void *)cb->args[2]; if (!w) { @@ -621,7 +621,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { if (arg.filter.dump_all_families) - return skb->len; + goto out; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); return -ENOENT; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index b8ac369f98ad..d219979c3e52 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -587,11 +587,16 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) */ ret = -EINPROGRESS; if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len && - nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; - else + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + if (nf_ct_frag6_reasm(fq, skb, dev)) + ret = 0; + skb->_skb_refdst = orefdst; + } else { skb_dst_drop(skb); + } out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index bc4bd247bb7d..1577f2f76060 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -55,11 +55,15 @@ MODULE_AUTHOR("Jozsef Kadlecsik <[email protected]>"); MODULE_DESCRIPTION("core IP set support"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET); -/* When the nfnl mutex is held: */ +/* When the nfnl mutex or ip_set_ref_lock is held: */ #define ip_set_dereference(p) \ - rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&ip_set_ref_lock)) #define ip_set(inst, id) \ ip_set_dereference((inst)->ip_set_list)[id] +#define ip_set_ref_netlink(inst,id) \ + rcu_dereference_raw((inst)->ip_set_list)[id] /* The set types are implemented in modules and registered set types * can be found in ip_set_type_list. Adding/deleting types is @@ -693,21 +697,20 @@ ip_set_put_byindex(struct net *net, ip_set_id_t index) EXPORT_SYMBOL_GPL(ip_set_put_byindex); /* Get the name of a set behind a set index. - * We assume the set is referenced, so it does exist and - * can't be destroyed. The set cannot be renamed due to - * the referencing either. - * + * Set itself is protected by RCU, but its name isn't: to protect against + * renaming, grab ip_set_ref_lock as reader (see ip_set_rename()) and copy the + * name. */ -const char * -ip_set_name_byindex(struct net *net, ip_set_id_t index) +void +ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name) { - const struct ip_set *set = ip_set_rcu_get(net, index); + struct ip_set *set = ip_set_rcu_get(net, index); BUG_ON(!set); - BUG_ON(set->ref == 0); - /* Referenced, so it's safe */ - return set->name; + read_lock_bh(&ip_set_ref_lock); + strncpy(name, set->name, IPSET_MAXNAMELEN); + read_unlock_bh(&ip_set_ref_lock); } EXPORT_SYMBOL_GPL(ip_set_name_byindex); @@ -961,7 +964,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Wraparound */ goto cleanup; - list = kcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(i, sizeof(struct ip_set *), GFP_KERNEL); if (!list) goto cleanup; /* nfnl mutex is held, both lists are valid */ @@ -973,7 +976,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Use new list */ index = inst->ip_set_max; inst->ip_set_max = i; - kfree(tmp); + kvfree(tmp); ret = 0; } else if (ret) { goto cleanup; @@ -1153,7 +1156,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, if (!set) return -ENOENT; - read_lock_bh(&ip_set_ref_lock); + write_lock_bh(&ip_set_ref_lock); if (set->ref != 0) { ret = -IPSET_ERR_REFERENCED; goto out; @@ -1170,7 +1173,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl, strncpy(set->name, name2, IPSET_MAXNAMELEN); out: - read_unlock_bh(&ip_set_ref_lock); + write_unlock_bh(&ip_set_ref_lock); return ret; } @@ -1252,7 +1255,7 @@ ip_set_dump_done(struct netlink_callback *cb) struct ip_set_net *inst = (struct ip_set_net *)cb->args[IPSET_CB_NET]; ip_set_id_t index = (ip_set_id_t)cb->args[IPSET_CB_INDEX]; - struct ip_set *set = ip_set(inst, index); + struct ip_set *set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); @@ -1441,7 +1444,7 @@ next_set: release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[IPSET_CB_ARG0]) { - set = ip_set(inst, index); + set = ip_set_ref_netlink(inst, index); if (set->variant->uref) set->variant->uref(set, cb, false); pr_debug("release set %s\n", set->name); @@ -2059,7 +2062,7 @@ ip_set_net_init(struct net *net) if (inst->ip_set_max >= IPSET_INVALID_ID) inst->ip_set_max = IPSET_INVALID_ID - 1; - list = kcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); + list = kvcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL); if (!list) return -ENOMEM; inst->is_deleted = false; @@ -2087,7 +2090,7 @@ ip_set_net_exit(struct net *net) } } nfnl_unlock(NFNL_SUBSYS_IPSET); - kfree(rcu_dereference_protected(inst->ip_set_list, 1)); + kvfree(rcu_dereference_protected(inst->ip_set_list, 1)); } static struct pernet_operations ip_set_net_ops = { diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index d391485a6acd..613e18e720a4 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -213,13 +213,13 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } @@ -493,13 +493,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_CIDR]) { e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!e.cidr[0] || e.cidr[0] > HOST_MASK) + if (e.cidr[0] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } if (tb[IPSET_ATTR_CIDR2]) { e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - if (!e.cidr[1] || e.cidr[1] > HOST_MASK) + if (e.cidr[1] > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 072a658fde04..4eef55da0878 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -148,9 +148,7 @@ __list_set_del_rcu(struct rcu_head * rcu) { struct set_elem *e = container_of(rcu, struct set_elem, rcu); struct ip_set *set = e->set; - struct list_set *map = set->data; - ip_set_put_byindex(map->net, e->id); ip_set_ext_destroy(set, e); kfree(e); } @@ -158,15 +156,21 @@ __list_set_del_rcu(struct rcu_head * rcu) static inline void list_set_del(struct ip_set *set, struct set_elem *e) { + struct list_set *map = set->data; + set->elements--; list_del_rcu(&e->list); + ip_set_put_byindex(map->net, e->id); call_rcu(&e->rcu, __list_set_del_rcu); } static inline void -list_set_replace(struct set_elem *e, struct set_elem *old) +list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old) { + struct list_set *map = set->data; + list_replace_rcu(&old->list, &e->list); + ip_set_put_byindex(map->net, old->id); call_rcu(&old->rcu, __list_set_del_rcu); } @@ -298,7 +302,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext, INIT_LIST_HEAD(&e->list); list_set_init_extensions(set, ext, e); if (n) - list_set_replace(e, n); + list_set_replace(set, e, n); else if (next) list_add_tail_rcu(&e->list, &next->list); else if (prev) @@ -486,6 +490,7 @@ list_set_list(const struct ip_set *set, const struct list_set *map = set->data; struct nlattr *atd, *nested; u32 i = 0, first = cb->args[IPSET_CB_ARG0]; + char name[IPSET_MAXNAMELEN]; struct set_elem *e; int ret = 0; @@ -504,8 +509,8 @@ list_set_list(const struct ip_set *set, nested = ipset_nest_start(skb, IPSET_ATTR_DATA); if (!nested) goto nla_put_failure; - if (nla_put_string(skb, IPSET_ATTR_NAME, - ip_set_name_byindex(map->net, e->id))) + ip_set_name_byindex(map->net, e->id, name); + if (nla_put_string(skb, IPSET_ATTR_NAME, name)) goto nla_put_failure; if (ip_set_put_extensions(skb, set, e, true)) goto nla_put_failure; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index ca1168d67fac..e92e749aff53 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1073,19 +1073,22 @@ static unsigned int early_drop_list(struct net *net, return drops; } -static noinline int early_drop(struct net *net, unsigned int _hash) +static noinline int early_drop(struct net *net, unsigned int hash) { - unsigned int i; + unsigned int i, bucket; for (i = 0; i < NF_CT_EVICTION_RANGE; i++) { struct hlist_nulls_head *ct_hash; - unsigned int hash, hsize, drops; + unsigned int hsize, drops; rcu_read_lock(); nf_conntrack_get_ht(&ct_hash, &hsize); - hash = reciprocal_scale(_hash++, hsize); + if (!i) + bucket = reciprocal_scale(hash, hsize); + else + bucket = (bucket + 1) % hsize; - drops = early_drop_list(net, &ct_hash[hash]); + drops = early_drop_list(net, &ct_hash[bucket]); rcu_read_unlock(); if (drops) { diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 171e9e122e5f..023c1445bc39 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -384,11 +384,6 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = }, }; -static inline struct nf_dccp_net *dccp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.dccp; -} - static noinline bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, const struct dccp_hdr *dh) @@ -401,7 +396,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb, state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE]; switch (state) { default: - dn = dccp_pernet(net); + dn = nf_dccp_pernet(net); if (dn->dccp_loose == 0) { msg = "not picking up existing connection "; goto out_invalid; @@ -568,7 +563,7 @@ static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout; + timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); return NF_ACCEPT; @@ -681,7 +676,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); unsigned int *timeouts = data; int i; @@ -814,7 +809,7 @@ static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn, static int dccp_init_net(struct net *net) { - struct nf_dccp_net *dn = dccp_pernet(net); + struct nf_dccp_net *dn = nf_dccp_pernet(net); struct nf_proto_net *pn = &dn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index e10e867e0b55..5da19d5fbc76 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -27,11 +27,6 @@ static bool nf_generic_should_process(u8 proto) } } -static inline struct nf_generic_net *generic_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.generic; -} - static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) @@ -58,7 +53,7 @@ static int generic_packet(struct nf_conn *ct, } if (!timeout) - timeout = &generic_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -72,7 +67,7 @@ static int generic_packet(struct nf_conn *ct, static int generic_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); unsigned int *timeout = data; if (!timeout) @@ -138,7 +133,7 @@ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, static int generic_init_net(struct net *net) { - struct nf_generic_net *gn = generic_pernet(net); + struct nf_generic_net *gn = nf_generic_pernet(net); struct nf_proto_net *pn = &gn->pn; gn->timeout = nf_ct_generic_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 3598520bd19b..de64d8a5fdfd 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -25,11 +25,6 @@ static const unsigned int nf_ct_icmp_timeout = 30*HZ; -static inline struct nf_icmp_net *icmp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp; -} - static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, struct nf_conntrack_tuple *tuple) { @@ -103,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct, } if (!timeout) - timeout = &icmp_pernet(nf_ct_net(ct))->timeout; + timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout; nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); return NF_ACCEPT; @@ -275,7 +270,7 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) { if (!timeout) @@ -337,7 +332,7 @@ static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmp_init_net(struct net *net) { - struct nf_icmp_net *in = icmp_pernet(net); + struct nf_icmp_net *in = nf_icmp_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmp_timeout; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index 378618feed5d..a15eefb8e317 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -30,11 +30,6 @@ static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; -static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6; -} - static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, struct net *net, @@ -87,7 +82,7 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, static unsigned int *icmpv6_get_timeouts(struct net *net) { - return &icmpv6_pernet(net)->timeout; + return &nf_icmpv6_pernet(net)->timeout; } /* Returns verdict for packet, or -1 for invalid. */ @@ -286,7 +281,7 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeout = data; - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); if (!timeout) timeout = icmpv6_get_timeouts(net); @@ -348,7 +343,7 @@ static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, static int icmpv6_init_net(struct net *net) { - struct nf_icmp_net *in = icmpv6_pernet(net); + struct nf_icmp_net *in = nf_icmpv6_pernet(net); struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmpv6_timeout; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 3d719d3eb9a3..d53e3e78f605 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -146,11 +146,6 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { } }; -static inline struct nf_sctp_net *sctp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.sctp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -480,7 +475,7 @@ static int sctp_packet(struct nf_conn *ct, timeouts = nf_ct_timeout_lookup(ct); if (!timeouts) - timeouts = sctp_pernet(nf_ct_net(ct))->timeouts; + timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts; nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); @@ -599,7 +594,7 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; /* set default SCTP timeouts. */ @@ -736,7 +731,7 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int sctp_init_net(struct net *net) { - struct nf_sctp_net *sn = sctp_pernet(net); + struct nf_sctp_net *sn = nf_sctp_pernet(net); struct nf_proto_net *pn = &sn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1bcf9984d45e..4dcbd51a8e97 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -272,11 +272,6 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { } }; -static inline struct nf_tcp_net *tcp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.tcp; -} - #ifdef CONFIG_NF_CONNTRACK_PROCFS /* Print out the private part of the conntrack. */ static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct) @@ -475,7 +470,7 @@ static bool tcp_in_window(const struct nf_conn *ct, const struct tcphdr *tcph) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct ip_ct_tcp_state *sender = &state->seen[dir]; struct ip_ct_tcp_state *receiver = &state->seen[!dir]; const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple; @@ -767,7 +762,7 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, { enum tcp_conntrack new_state; struct net *net = nf_ct_net(ct); - const struct nf_tcp_net *tn = tcp_pernet(net); + const struct nf_tcp_net *tn = nf_tcp_pernet(net); const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0]; const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1]; @@ -841,7 +836,7 @@ static int tcp_packet(struct nf_conn *ct, const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_conntrack_tuple *tuple; enum tcp_conntrack new_state, old_state; unsigned int index, *timeouts; @@ -1283,7 +1278,7 @@ static unsigned int tcp_nlattr_tuple_size(void) static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); unsigned int *timeouts = data; int i; @@ -1508,7 +1503,7 @@ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int tcp_init_net(struct net *net) { - struct nf_tcp_net *tn = tcp_pernet(net); + struct nf_tcp_net *tn = nf_tcp_pernet(net); struct nf_proto_net *pn = &tn->pn; if (!pn->users) { diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index a7aa70370913..c879d8d78cfd 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -32,14 +32,9 @@ static const unsigned int udp_timeouts[UDP_CT_MAX] = { [UDP_CT_REPLIED] = 180*HZ, }; -static inline struct nf_udp_net *udp_pernet(struct net *net) -{ - return &net->ct.nf_ct_proto.udp; -} - static unsigned int *udp_get_timeouts(struct net *net) { - return udp_pernet(net)->timeouts; + return nf_udp_pernet(net)->timeouts; } static void udp_error_log(const struct sk_buff *skb, @@ -212,7 +207,7 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); if (!timeouts) timeouts = un->timeouts; @@ -292,7 +287,7 @@ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, static int udp_init_net(struct net *net) { - struct nf_udp_net *un = udp_pernet(net); + struct nf_udp_net *un = nf_udp_pernet(net); struct nf_proto_net *pn = &un->pn; if (!pn->users) { diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index e7a50af1b3d6..a518eb162344 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -382,7 +382,8 @@ err: static int cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, u16 l3num, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_l4proto *l4proto, + const unsigned int *timeouts) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; @@ -408,7 +409,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid, if (!nest_parms) goto nla_put_failure; - ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL); + ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts); if (ret < 0) goto nla_put_failure; @@ -430,6 +431,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, struct netlink_ext_ack *extack) { const struct nf_conntrack_l4proto *l4proto; + unsigned int *timeouts = NULL; struct sk_buff *skb2; int ret, err; __u16 l3num; @@ -442,12 +444,44 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); l4proto = nf_ct_l4proto_find_get(l4num); - /* This protocol is not supported, skip. */ - if (l4proto->l4proto != l4num) { - err = -EOPNOTSUPP; + err = -EOPNOTSUPP; + if (l4proto->l4proto != l4num) goto err; + + switch (l4proto->l4proto) { + case IPPROTO_ICMP: + timeouts = &nf_icmp_pernet(net)->timeout; + break; + case IPPROTO_TCP: + timeouts = nf_tcp_pernet(net)->timeouts; + break; + case IPPROTO_UDP: + timeouts = nf_udp_pernet(net)->timeouts; + break; + case IPPROTO_DCCP: +#ifdef CONFIG_NF_CT_PROTO_DCCP + timeouts = nf_dccp_pernet(net)->dccp_timeout; +#endif + break; + case IPPROTO_ICMPV6: + timeouts = &nf_icmpv6_pernet(net)->timeout; + break; + case IPPROTO_SCTP: +#ifdef CONFIG_NF_CT_PROTO_SCTP + timeouts = nf_sctp_pernet(net)->timeouts; +#endif + break; + case 255: + timeouts = &nf_generic_pernet(net)->timeout; + break; + default: + WARN_ON_ONCE(1); + break; } + if (!timeouts) + goto err; + skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (skb2 == NULL) { err = -ENOMEM; @@ -458,8 +492,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_DEFAULT_SET, - l3num, - l4proto); + l3num, l4proto, timeouts); if (ret <= 0) { kfree_skb(skb2); err = -ENOMEM; diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 768292eac2a4..9d0ede474224 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -54,9 +54,11 @@ static bool nft_xt_put(struct nft_xt *xt) return false; } -static int nft_compat_chain_validate_dependency(const char *tablename, - const struct nft_chain *chain) +static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, + const char *tablename) { + enum nft_chain_types type = NFT_CHAIN_T_DEFAULT; + const struct nft_chain *chain = ctx->chain; const struct nft_base_chain *basechain; if (!tablename || @@ -64,9 +66,12 @@ static int nft_compat_chain_validate_dependency(const char *tablename, return 0; basechain = nft_base_chain(chain); - if (strcmp(tablename, "nat") == 0 && - basechain->type->type != NFT_CHAIN_T_NAT) - return -EINVAL; + if (strcmp(tablename, "nat") == 0) { + if (ctx->family != NFPROTO_BRIDGE) + type = NFT_CHAIN_T_NAT; + if (basechain->type->type != type) + return -EINVAL; + } return 0; } @@ -342,8 +347,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(target->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, target->table); if (ret < 0) return ret; } @@ -590,8 +594,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; - ret = nft_compat_chain_validate_dependency(match->table, - ctx->chain); + ret = nft_compat_chain_validate_dependency(ctx, match->table); if (ret < 0) return ret; } diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 649d1700ec5b..3cc1b3dc3c3c 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -24,7 +24,6 @@ struct nft_ng_inc { u32 modulus; atomic_t counter; u32 offset; - struct nft_set *map; }; static u32 nft_ng_inc_gen(struct nft_ng_inc *priv) @@ -48,34 +47,11 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_inc_gen(priv); } -static void nft_ng_inc_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_inc_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_DREG] = { .type = NLA_U32 }, [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, [NFTA_NG_OFFSET] = { .type = NLA_U32 }, - [NFTA_NG_SET_NAME] = { .type = NLA_STRING, - .len = NFT_SET_MAXNAMELEN - 1 }, - [NFTA_NG_SET_ID] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -101,22 +77,6 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_inc_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_inc *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_inc_init(ctx, expr, tb); - - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, u32 modulus, enum nft_ng_types type, u32 offset) { @@ -143,27 +103,10 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_inc_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_inc *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_INCREMENTAL, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; u32 offset; - struct nft_set *map; }; static u32 nft_ng_random_gen(struct nft_ng_random *priv) @@ -183,25 +126,6 @@ static void nft_ng_random_eval(const struct nft_expr *expr, regs->data[priv->dreg] = nft_ng_random_gen(priv); } -static void nft_ng_random_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = nft_ng_random_gen(priv); - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static int nft_ng_random_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -226,21 +150,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_ng_random_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_ng_random *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_ng_random_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_NG_SET_NAME], - tb[NFTA_NG_SET_ID], genmask); - - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_ng_random *priv = nft_expr_priv(expr); @@ -249,22 +158,6 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } -static int nft_ng_random_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_ng_random *priv = nft_expr_priv(expr); - - if (nft_ng_dump(skb, priv->dreg, priv->modulus, - NFT_NG_RANDOM, priv->offset) || - nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) - goto nla_put_failure; - - return 0; - -nla_put_failure: - return -1; -} - static struct nft_expr_type nft_ng_type; static const struct nft_expr_ops nft_ng_inc_ops = { .type = &nft_ng_type, @@ -274,14 +167,6 @@ static const struct nft_expr_ops nft_ng_inc_ops = { .dump = nft_ng_inc_dump, }; -static const struct nft_expr_ops nft_ng_inc_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), - .eval = nft_ng_inc_map_eval, - .init = nft_ng_inc_map_init, - .dump = nft_ng_inc_map_dump, -}; - static const struct nft_expr_ops nft_ng_random_ops = { .type = &nft_ng_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), @@ -290,14 +175,6 @@ static const struct nft_expr_ops nft_ng_random_ops = { .dump = nft_ng_random_dump, }; -static const struct nft_expr_ops nft_ng_random_map_ops = { - .type = &nft_ng_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), - .eval = nft_ng_random_map_eval, - .init = nft_ng_random_map_init, - .dump = nft_ng_random_map_dump, -}; - static const struct nft_expr_ops * nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { @@ -312,12 +189,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) switch (type) { case NFT_NG_INCREMENTAL: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_inc_map_ops; return &nft_ng_inc_ops; case NFT_NG_RANDOM: - if (tb[NFTA_NG_SET_NAME]) - return &nft_ng_random_map_ops; return &nft_ng_random_ops; } diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index ca5e5d8c5ef8..b13618c764ec 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -50,7 +50,7 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; - if (nla_get_u8(tb[NFTA_OSF_TTL])) { + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) return -EINVAL; diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index c6acfc2d9c84..eb4cbd244c3d 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -114,6 +114,22 @@ static void idletimer_tg_expired(struct timer_list *t) schedule_work(&timer->work); } +static int idletimer_check_sysfs_name(const char *name, unsigned int size) +{ + int ret; + + ret = xt_check_proc_name(name, size); + if (ret < 0) + return ret; + + if (!strcmp(name, "power") || + !strcmp(name, "subsystem") || + !strcmp(name, "uevent")) + return -EINVAL; + + return 0; +} + static int idletimer_tg_create(struct idletimer_tg_info *info) { int ret; @@ -124,6 +140,10 @@ static int idletimer_tg_create(struct idletimer_tg_info *info) goto out; } + ret = idletimer_check_sysfs_name(info->label, sizeof(info->label)); + if (ret < 0) + goto out_free_timer; + sysfs_attr_init(&info->timer->attr.attr); info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL); if (!info->timer->attr.attr.name) { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 6bec37ab4472..a4660c48ff01 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1203,7 +1203,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, &info->labels.mask); if (err) return err; - } else if (labels_nonzero(&info->labels.mask)) { + } else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && + labels_nonzero(&info->labels.mask)) { err = ovs_ct_set_labels(ct, key, &info->labels.value, &info->labels.mask); if (err) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 382196e57a26..bc628acf4f4f 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -611,6 +611,7 @@ struct rxrpc_call { * not hard-ACK'd packet follows this. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ + u16 tx_backoff; /* Delay to insert due to Tx failure */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 8e7434e92097..468efc3660c0 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, else ack_at = expiry; + ack_at += READ_ONCE(call->tx_backoff); ack_at += now; if (time_before(ack_at, call->ack_at)) { WRITE_ONCE(call->ack_at, ack_at); @@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_struct *work) container_of(work, struct rxrpc_call, processor); rxrpc_serial_t *send_ack; unsigned long now, next, t; + unsigned int iterations = 0; rxrpc_see_call(call); @@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_struct *work) call->debug_id, rxrpc_call_states[call->state], call->events); recheck_state: + /* Limit the number of times we do this before returning to the manager */ + iterations++; + if (iterations > 5) + goto requeue; + if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { rxrpc_send_abort_packet(call); goto recheck_state; @@ -447,13 +454,16 @@ recheck_state: rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); /* other events may have been raised since we started checking */ - if (call->events && call->state < RXRPC_CALL_COMPLETE) { - __rxrpc_queue_call(call); - goto out; - } + if (call->events && call->state < RXRPC_CALL_COMPLETE) + goto requeue; out_put: rxrpc_put_call(call, rxrpc_call_put); out: _leave(""); + return; + +requeue: + __rxrpc_queue_call(call); + goto out; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 189418888839..736aa9281100 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -35,6 +35,21 @@ struct rxrpc_abort_buffer { static const char rxrpc_keepalive_string[] = ""; /* + * Increase Tx backoff on transmission failure and clear it on success. + */ +static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret) +{ + if (ret < 0) { + u16 tx_backoff = READ_ONCE(call->tx_backoff); + + if (tx_backoff < HZ) + WRITE_ONCE(call->tx_backoff, tx_backoff + 1); + } else { + WRITE_ONCE(call->tx_backoff, 0); + } +} + +/* * Arrange for a keepalive ping a certain time after we last transmitted. This * lets the far side know we're still interested in this call and helps keep * the route through any intervening firewall open. @@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, else trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, rxrpc_tx_point_call_ack); + rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { @@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_propose_ACK(call, pkt->ack.reason, ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), - true, true, + false, true, rxrpc_propose_ack_retry_tx); } else { spin_lock_bh(&call->lock); @@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) else trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, rxrpc_tx_point_call_abort); - + rxrpc_tx_backoff(call, ret); rxrpc_put_connection(conn); return ret; @@ -413,6 +429,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_nofrag); + rxrpc_tx_backoff(call, ret); if (ret == -EMSGSIZE) goto send_fragmentable; @@ -445,9 +462,18 @@ done: rxrpc_reduce_call_timer(call, expect_rx_by, nowj, rxrpc_timer_set_for_normal); } - } - rxrpc_set_keepalive(call); + rxrpc_set_keepalive(call); + } else { + /* Cancel the call if the initial transmission fails, + * particularly if that's due to network routing issues that + * aren't going away anytime soon. The layer above can arrange + * the retransmission. + */ + if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_USER_ABORT, ret); + } _leave(" = %d [%u]", ret, call->peer->maxdata); return ret; @@ -506,6 +532,7 @@ send_fragmentable: else trace_rxrpc_tx_packet(call->debug_id, &whdr, rxrpc_tx_point_call_data_frag); + rxrpc_tx_backoff(call, ret); up_write(&conn->params.local->defrag_sem); goto done; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 1dae5f2b358f..c8cf4d10c435 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, if (is_redirect) { skb2->tc_redirected = 1; skb2->tc_from_ingress = skb2->tc_at_ingress; - + if (skb2->tc_from_ingress) + skb2->tstamp = 0; /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 9aada2d0ef06..c6c327874abc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key, struct netlink_ext_ack *extack) { const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL; - int option_len, key_depth, msk_depth = 0; + int err, option_len, key_depth, msk_depth = 0; + + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]); if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) { + err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK], + TCA_FLOWER_KEY_ENC_OPTS_MAX, + enc_opts_policy, extack); + if (err) + return err; + nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 57b3ad9394ad..2c38e3d07924 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -648,15 +648,6 @@ deliver: */ skb->dev = qdisc_dev(sch); -#ifdef CONFIG_NET_CLS_ACT - /* - * If it's at ingress let's pretend the delay is - * from the network (tstamp will be updated). - */ - if (skb->tc_redirected && skb->tc_from_ingress) - skb->tstamp = 0; -#endif - if (q->slot.slot_next) { q->slot.packets_left--; q->slot.bytes_left -= qdisc_pkt_len(skb); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 9cb854b05342..c37e1c2dec9d 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_FCFS); + sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); } /* Free the outqueue structure and any related pending chunks. diff --git a/net/tipc/link.c b/net/tipc/link.c index 201c3b5bc96b..836727e363c4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI)) l->priority = peers_prio; - /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ - if (msg_peer_stopping(hdr)) + /* If peer is going down we want full re-establish cycle */ + if (msg_peer_stopping(hdr)) { rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); - else if ((mtyp == RESET_MSG) || !link_is_up(l)) + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ + if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); /* ACTIVATE_MSG takes up link if it was already locally reset */ - if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING)) + if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING) rc = TIPC_LINK_UP_EVT; l->peer_session = msg_session(hdr); diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh index da66e7742282..0ef906499646 100755 --- a/scripts/kconfig/merge_config.sh +++ b/scripts/kconfig/merge_config.sh @@ -102,7 +102,8 @@ if [ ! -r "$INITFILE" ]; then fi MERGE_LIST=$* -SED_CONFIG_EXP="s/^\(# \)\{0,1\}\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)[= ].*/\2/p" +SED_CONFIG_EXP1="s/^\(${CONFIG_PREFIX}[a-zA-Z0-9_]*\)=.*/\1/p" +SED_CONFIG_EXP2="s/^# \(${CONFIG_PREFIX}[a-zA-Z0-9_]*\) is not set$/\1/p" TMP_FILE=$(mktemp ./.tmp.config.XXXXXXXXXX) @@ -116,7 +117,7 @@ for MERGE_FILE in $MERGE_LIST ; do echo "The merge file '$MERGE_FILE' does not exist. Exit." >&2 exit 1 fi - CFG_LIST=$(sed -n "$SED_CONFIG_EXP" $MERGE_FILE) + CFG_LIST=$(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $MERGE_FILE) for CFG in $CFG_LIST ; do grep -q -w $CFG $TMP_FILE || continue @@ -159,7 +160,7 @@ make KCONFIG_ALLCONFIG=$TMP_FILE $OUTPUT_ARG $ALLTARGET # Check all specified config values took (might have missed-dependency issues) -for CFG in $(sed -n "$SED_CONFIG_EXP" $TMP_FILE); do +for CFG in $(sed -n -e "$SED_CONFIG_EXP1" -e "$SED_CONFIG_EXP2" $TMP_FILE); do REQUESTED_VAL=$(grep -w -e "$CFG" $TMP_FILE) ACTUAL_VAL=$(grep -w -e "$CFG" "$KCONFIG_CONFIG") diff --git a/scripts/package/builddeb b/scripts/package/builddeb index 90c9a8ac7adb..f43a274f4f1d 100755 --- a/scripts/package/builddeb +++ b/scripts/package/builddeb @@ -81,11 +81,11 @@ else cp System.map "$tmpdir/boot/System.map-$version" cp $KCONFIG_CONFIG "$tmpdir/boot/config-$version" fi -cp "$($MAKE -s image_name)" "$tmpdir/$installed_image_path" +cp "$($MAKE -s -f $srctree/Makefile image_name)" "$tmpdir/$installed_image_path" -if grep -q "^CONFIG_OF=y" $KCONFIG_CONFIG ; then +if grep -q "^CONFIG_OF_EARLY_FLATTREE=y" $KCONFIG_CONFIG ; then # Only some architectures with OF support have this target - if grep -q dtbs_install "${srctree}/arch/$SRCARCH/Makefile"; then + if [ -d "${srctree}/arch/$SRCARCH/boot/dts" ]; then $MAKE KBUILD_SRC= INSTALL_DTBS_PATH="$tmpdir/usr/lib/$packagename" dtbs_install fi fi diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian index 663a7f343b42..edcad61fe3cd 100755 --- a/scripts/package/mkdebian +++ b/scripts/package/mkdebian @@ -88,6 +88,7 @@ set_debarch() { version=$KERNELRELEASE if [ -n "$KDEB_PKGVERSION" ]; then packageversion=$KDEB_PKGVERSION + revision=${packageversion##*-} else revision=$(cat .version 2>/dev/null||echo 1) packageversion=$version-$revision @@ -205,10 +206,12 @@ cat <<EOF > debian/rules #!$(command -v $MAKE) -f build: - \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC= + \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \ + KBUILD_BUILD_VERSION=${revision} KBUILD_SRC= binary-arch: - \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} KBUILD_SRC= intdeb-pkg + \$(MAKE) KERNELRELEASE=${version} ARCH=${ARCH} \ + KBUILD_BUILD_VERSION=${revision} KBUILD_SRC= intdeb-pkg clean: rm -rf debian/*tmp debian/files diff --git a/scripts/package/mkspec b/scripts/package/mkspec index e05646dc24dc..009147d4718e 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -12,6 +12,7 @@ # how we were called determines which rpms we build and how we build them if [ "$1" = prebuilt ]; then S=DEL + MAKE="$MAKE -f $srctree/Makefile" else S= fi @@ -78,19 +79,19 @@ $S %prep $S %setup -q $S $S %build -$S make %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release} +$S $MAKE %{?_smp_mflags} KBUILD_BUILD_VERSION=%{release} $S %install mkdir -p %{buildroot}/boot %ifarch ia64 mkdir -p %{buildroot}/boot/efi - cp \$(make image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE + cp \$($MAKE image_name) %{buildroot}/boot/efi/vmlinuz-$KERNELRELEASE ln -s efi/vmlinuz-$KERNELRELEASE %{buildroot}/boot/ %else - cp \$(make image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE + cp \$($MAKE image_name) %{buildroot}/boot/vmlinuz-$KERNELRELEASE %endif -$M make %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} KBUILD_SRC= modules_install - make %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr KBUILD_SRC= headers_install +$M $MAKE %{?_smp_mflags} INSTALL_MOD_PATH=%{buildroot} modules_install + $MAKE %{?_smp_mflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install cp System.map %{buildroot}/boot/System.map-$KERNELRELEASE cp .config %{buildroot}/boot/config-$KERNELRELEASE bzip2 -9 --keep vmlinux diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 79f7dd57d571..71f39410691b 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -74,7 +74,7 @@ scm_version() fi # Check for uncommitted changes - if git status -uno --porcelain | grep -qv '^.. scripts/package'; then + if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then printf '%s' -dirty fi diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c index 97f49b751e6e..568575b72f2f 100644 --- a/sound/pci/hda/thinkpad_helper.c +++ b/sound/pci/hda/thinkpad_helper.c @@ -58,8 +58,8 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec, removefunc = false; } if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0 && - snd_hda_gen_add_micmute_led(codec, - update_tpacpi_micmute) > 0) + !snd_hda_gen_add_micmute_led(codec, + update_tpacpi_micmute)) removefunc = false; } diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h index 12835ea0e417..378c051fa177 100644 --- a/tools/arch/arm64/include/asm/barrier.h +++ b/tools/arch/arm64/include/asm/barrier.h @@ -14,74 +14,75 @@ #define wmb() asm volatile("dmb ishst" ::: "memory") #define rmb() asm volatile("dmb ishld" ::: "memory") -#define smp_store_release(p, v) \ -do { \ - union { typeof(*p) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(*p)) (v) }; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("stlrb %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u8 *)__u.__c) \ - : "memory"); \ - break; \ - case 2: \ - asm volatile ("stlrh %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u16 *)__u.__c) \ - : "memory"); \ - break; \ - case 4: \ - asm volatile ("stlr %w1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u32 *)__u.__c) \ - : "memory"); \ - break; \ - case 8: \ - asm volatile ("stlr %1, %0" \ - : "=Q" (*p) \ - : "r" (*(__u64 *)__u.__c) \ - : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ +#define smp_store_release(p, v) \ +do { \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__val = (v) }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("stlrb %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u8_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 2: \ + asm volatile ("stlrh %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u16_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 4: \ + asm volatile ("stlr %w1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u32_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + case 8: \ + asm volatile ("stlr %1, %0" \ + : "=Q" (*p) \ + : "r" (*(__u64_alias_t *)__u.__c) \ + : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ } while (0) -#define smp_load_acquire(p) \ -({ \ - union { typeof(*p) __val; char __c[1]; } __u; \ - \ - switch (sizeof(*p)) { \ - case 1: \ - asm volatile ("ldarb %w0, %1" \ - : "=r" (*(__u8 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 2: \ - asm volatile ("ldarh %w0, %1" \ - : "=r" (*(__u16 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 4: \ - asm volatile ("ldar %w0, %1" \ - : "=r" (*(__u32 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - case 8: \ - asm volatile ("ldar %0, %1" \ - : "=r" (*(__u64 *)__u.__c) \ - : "Q" (*p) : "memory"); \ - break; \ - default: \ - /* Only to shut up gcc ... */ \ - mb(); \ - break; \ - } \ - __u.__val; \ +#define smp_load_acquire(p) \ +({ \ + union { typeof(*p) __val; char __c[1]; } __u = \ + { .__c = { 0 } }; \ + \ + switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("ldarb %w0, %1" \ + : "=r" (*(__u8_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 2: \ + asm volatile ("ldarh %w0, %1" \ + : "=r" (*(__u16_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 4: \ + asm volatile ("ldar %w0, %1" \ + : "=r" (*(__u32_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + case 8: \ + asm volatile ("ldar %0, %1" \ + : "=r" (*(__u64_alias_t *)__u.__c) \ + : "Q" (*p) : "memory"); \ + break; \ + default: \ + /* Only to shut up gcc ... */ \ + mb(); \ + break; \ + } \ + __u.__val; \ }) #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */ diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt index 236b9b97dfdb..667c14e56031 100644 --- a/tools/perf/Documentation/perf-list.txt +++ b/tools/perf/Documentation/perf-list.txt @@ -55,7 +55,6 @@ counted. The following modifiers exist: S - read sample value (PERF_SAMPLE_READ) D - pin the event to the PMU W - group is weak and will fallback to non-group if not schedulable, - only supported in 'perf stat' for now. The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times: diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 3ccb4f0bf088..d95655489f7e 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -387,7 +387,7 @@ SHELL = $(SHELL_PATH) linux_uapi_dir := $(srctree)/tools/include/uapi/linux asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic -arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/ +arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/ beauty_outdir := $(OUTPUT)trace/beauty/generated beauty_ioctl_outdir := $(beauty_outdir)/ioctl diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 10cf889c6d75..488779bc4c8d 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -391,7 +391,12 @@ try_again: ui__warning("%s\n", msg); goto try_again; } - + if ((errno == EINVAL || errno == EBADF) && + pos->leader != pos && + pos->weak_group) { + pos = perf_evlist__reset_weak_group(evlist, pos); + goto try_again; + } rc = -errno; perf_evsel__open_strerror(pos, &opts->target, errno, msg, sizeof(msg)); diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index d1028d7755bb..a635abfa77b6 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -383,32 +383,6 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter) return STAT_RECORD || counter->attr.read_format & PERF_FORMAT_ID; } -static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel) -{ - struct perf_evsel *c2, *leader; - bool is_open = true; - - leader = evsel->leader; - pr_debug("Weak group for %s/%d failed\n", - leader->name, leader->nr_members); - - /* - * for_each_group_member doesn't work here because it doesn't - * include the first entry. - */ - evlist__for_each_entry(evsel_list, c2) { - if (c2 == evsel) - is_open = false; - if (c2->leader == leader) { - if (is_open) - perf_evsel__close(c2); - c2->leader = c2; - c2->nr_members = 0; - } - } - return leader; -} - static bool is_target_alive(struct target *_target, struct thread_map *threads) { @@ -477,7 +451,7 @@ try_again: if ((errno == EINVAL || errno == EBADF) && counter->leader != counter && counter->weak_group) { - counter = perf_evsel__reset_weak_group(counter); + counter = perf_evlist__reset_weak_group(evsel_list, counter); goto try_again; } diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index b2838de13de0..aa0c73e57924 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1429,6 +1429,9 @@ int cmd_top(int argc, const char **argv) } } + if (opts->branch_stack && callchain_param.enabled) + symbol_conf.show_branchflag_count = true; + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ perf_hpp_list.need_collapse = 1; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index dc8a6c4986ce..835619476370 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -108,6 +108,7 @@ struct trace { } stats; unsigned int max_stack; unsigned int min_stack; + bool raw_augmented_syscalls; bool not_ev_qualifier; bool live; bool full_time; @@ -1724,13 +1725,28 @@ static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel, return printed; } -static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size) +static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, bool raw_augmented) { void *augmented_args = NULL; + /* + * For now with BPF raw_augmented we hook into raw_syscalls:sys_enter + * and there we get all 6 syscall args plus the tracepoint common + * fields (sizeof(long)) and the syscall_nr (another long). So we check + * if that is the case and if so don't look after the sc->args_size, + * but always after the full raw_syscalls:sys_enter payload, which is + * fixed. + * + * We'll revisit this later to pass s->args_size to the BPF augmenter + * (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it + * copies only what we need for each syscall, like what happens when we + * use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace + * traffic to just what is needed for each syscall. + */ + int args_size = raw_augmented ? (8 * (int)sizeof(long)) : sc->args_size; - *augmented_args_size = sample->raw_size - sc->args_size; + *augmented_args_size = sample->raw_size - args_size; if (*augmented_args_size > 0) - augmented_args = sample->raw_data + sc->args_size; + augmented_args = sample->raw_data + args_size; return augmented_args; } @@ -1780,7 +1796,7 @@ static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel, * here and avoid using augmented syscalls when the evsel is the raw_syscalls one. */ if (evsel != trace->syscalls.events.sys_enter) - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); ttrace->entry_time = sample->time; msg = ttrace->entry_str; printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name); @@ -1833,7 +1849,7 @@ static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evse goto out_put; args = perf_evsel__sc_tp_ptr(evsel, args, sample); - augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size); + augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls); syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread); fprintf(trace->output, "%s", msg); err = 0; @@ -3501,7 +3517,15 @@ int cmd_trace(int argc, const char **argv) evsel->handler = trace__sys_enter; evlist__for_each_entry(trace.evlist, evsel) { + bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0; + + if (raw_syscalls_sys_exit) { + trace.raw_augmented_syscalls = true; + goto init_augmented_syscall_tp; + } + if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) { +init_augmented_syscall_tp: perf_evsel__init_augmented_syscall_tp(evsel); perf_evsel__init_augmented_syscall_tp_ret(evsel); evsel->handler = trace__sys_exit; diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c new file mode 100644 index 000000000000..90a19336310b --- /dev/null +++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Augment the raw_syscalls tracepoints with the contents of the pointer arguments. + * + * Test it with: + * + * perf trace -e tools/perf/examples/bpf/augmented_raw_syscalls.c cat /etc/passwd > /dev/null + * + * This exactly matches what is marshalled into the raw_syscall:sys_enter + * payload expected by the 'perf trace' beautifiers. + * + * For now it just uses the existing tracepoint augmentation code in 'perf + * trace', in the next csets we'll hook up these with the sys_enter/sys_exit + * code that will combine entry/exit in a strace like way. + */ + +#include <stdio.h> +#include <linux/socket.h> + +/* bpf-output associated map */ +struct bpf_map SEC("maps") __augmented_syscalls__ = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(u32), + .max_entries = __NR_CPUS__, +}; + +struct syscall_enter_args { + unsigned long long common_tp_fields; + long syscall_nr; + unsigned long args[6]; +}; + +struct syscall_exit_args { + unsigned long long common_tp_fields; + long syscall_nr; + long ret; +}; + +struct augmented_filename { + unsigned int size; + int reserved; + char value[256]; +}; + +#define SYS_OPEN 2 +#define SYS_OPENAT 257 + +SEC("raw_syscalls:sys_enter") +int sys_enter(struct syscall_enter_args *args) +{ + struct { + struct syscall_enter_args args; + struct augmented_filename filename; + } augmented_args; + unsigned int len = sizeof(augmented_args); + const void *filename_arg = NULL; + + probe_read(&augmented_args.args, sizeof(augmented_args.args), args); + /* + * Yonghong and Edward Cree sayz: + * + * https://www.spinics.net/lists/netdev/msg531645.html + * + * >> R0=inv(id=0) R1=inv2 R6=ctx(id=0,off=0,imm=0) R7=inv64 R10=fp0,call_-1 + * >> 10: (bf) r1 = r6 + * >> 11: (07) r1 += 16 + * >> 12: (05) goto pc+2 + * >> 15: (79) r3 = *(u64 *)(r1 +0) + * >> dereference of modified ctx ptr R1 off=16 disallowed + * > Aha, we at least got a different error message this time. + * > And indeed llvm has done that optimisation, rather than the more obvious + * > 11: r3 = *(u64 *)(r1 +16) + * > because it wants to have lots of reads share a single insn. You may be able + * > to defeat that optimisation by adding compiler barriers, idk. Maybe someone + * > with llvm knowledge can figure out how to stop it (ideally, llvm would know + * > when it's generating for bpf backend and not do that). -O0? ¯\_(ツ)_/¯ + * + * The optimization mostly likes below: + * + * br1: + * ... + * r1 += 16 + * goto merge + * br2: + * ... + * r1 += 20 + * goto merge + * merge: + * *(u64 *)(r1 + 0) + * + * The compiler tries to merge common loads. There is no easy way to + * stop this compiler optimization without turning off a lot of other + * optimizations. The easiest way is to add barriers: + * + * __asm__ __volatile__("": : :"memory") + * + * after the ctx memory access to prevent their down stream merging. + */ + switch (augmented_args.args.syscall_nr) { + case SYS_OPEN: filename_arg = (const void *)args->args[0]; + __asm__ __volatile__("": : :"memory"); + break; + case SYS_OPENAT: filename_arg = (const void *)args->args[1]; + break; + } + + if (filename_arg != NULL) { + augmented_args.filename.reserved = 0; + augmented_args.filename.size = probe_read_str(&augmented_args.filename.value, + sizeof(augmented_args.filename.value), + filename_arg); + if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) { + len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size; + len &= sizeof(augmented_args.filename.value) - 1; + } + } else { + len = sizeof(augmented_args.args); + } + + perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len); + return 0; +} + +SEC("raw_syscalls:sys_exit") +int sys_exit(struct syscall_exit_args *args) +{ + return 1; /* 0 as soon as we start copying data returned by the kernel, e.g. 'read' */ +} + +license(GPL); diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c index ac1bcdc17dae..f7eb63cbbc65 100644 --- a/tools/perf/jvmti/jvmti_agent.c +++ b/tools/perf/jvmti/jvmti_agent.c @@ -125,7 +125,7 @@ perf_get_timestamp(void) } static int -debug_cache_init(void) +create_jit_cache_dir(void) { char str[32]; char *base, *p; @@ -144,8 +144,13 @@ debug_cache_init(void) strftime(str, sizeof(str), JIT_LANG"-jit-%Y%m%d", &tm); - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/", base); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because %s/.debug/" + " is too long, please check the cwd, JITDUMPDIR, and" + " HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { @@ -154,20 +159,32 @@ debug_cache_init(void) } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit", base); + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit", base); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", base); + return -1; + } ret = mkdir(jit_path, 0755); if (ret == -1) { if (errno != EEXIST) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } } - snprintf(jit_path, PATH_MAX - 1, "%s/.debug/jit/%s.XXXXXXXX", base, str); - + ret = snprintf(jit_path, PATH_MAX, "%s/.debug/jit/%s.XXXXXXXX", base, str); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jit cache dir because" + " %s/.debug/jit/%s.XXXXXXXX is too long, please check" + " the cwd, JITDUMPDIR, and HOME variables", + base, str); + return -1; + } p = mkdtemp(jit_path); if (p != jit_path) { - warn("cannot create jit cache dir %s", jit_path); + warn("jvmti: cannot create jit cache dir %s", jit_path); return -1; } @@ -228,7 +245,7 @@ void *jvmti_open(void) { char dump_path[PATH_MAX]; struct jitheader header; - int fd; + int fd, ret; FILE *fp; init_arch_timestamp(); @@ -245,12 +262,22 @@ void *jvmti_open(void) memset(&header, 0, sizeof(header)); - debug_cache_init(); + /* + * jitdump file dir + */ + if (create_jit_cache_dir() < 0) + return NULL; /* * jitdump file name */ - scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + ret = snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid()); + if (ret >= PATH_MAX) { + warnx("jvmti: cannot generate jitdump file full path because" + " %s/jit-%i.dump is too long, please check the cwd," + " JITDUMPDIR, and HOME variables", jit_path, getpid()); + return NULL; + } fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666); if (fd == -1) diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py index 24cb0bd56afa..f278ce5ebab7 100755 --- a/tools/perf/scripts/python/exported-sql-viewer.py +++ b/tools/perf/scripts/python/exported-sql-viewer.py @@ -119,6 +119,14 @@ def dsoname(name): return "[kernel]" return name +def findnth(s, sub, n, offs=0): + pos = s.find(sub) + if pos < 0: + return pos + if n <= 1: + return offs + pos + return findnth(s[pos + 1:], sub, n - 1, offs + pos + 1) + # Percent to one decimal place def PercentToOneDP(n, d): @@ -1464,6 +1472,317 @@ class BranchWindow(QMdiSubWindow): else: self.find_bar.NotFound() +# Dialog data item converted and validated using a SQL table + +class SQLTableDialogDataItem(): + + def __init__(self, glb, label, placeholder_text, table_name, match_column, column_name1, column_name2, parent): + self.glb = glb + self.label = label + self.placeholder_text = placeholder_text + self.table_name = table_name + self.match_column = match_column + self.column_name1 = column_name1 + self.column_name2 = column_name2 + self.parent = parent + + self.value = "" + + self.widget = QLineEdit() + self.widget.editingFinished.connect(self.Validate) + self.widget.textChanged.connect(self.Invalidate) + self.red = False + self.error = "" + self.validated = True + + self.last_id = 0 + self.first_time = 0 + self.last_time = 2 ** 64 + if self.table_name == "<timeranges>": + query = QSqlQuery(self.glb.db) + QueryExec(query, "SELECT id, time FROM samples ORDER BY id DESC LIMIT 1") + if query.next(): + self.last_id = int(query.value(0)) + self.last_time = int(query.value(1)) + QueryExec(query, "SELECT time FROM samples WHERE time != 0 ORDER BY id LIMIT 1") + if query.next(): + self.first_time = int(query.value(0)) + if placeholder_text: + placeholder_text += ", between " + str(self.first_time) + " and " + str(self.last_time) + + if placeholder_text: + self.widget.setPlaceholderText(placeholder_text) + + def ValueToIds(self, value): + ids = [] + query = QSqlQuery(self.glb.db) + stmt = "SELECT id FROM " + self.table_name + " WHERE " + self.match_column + " = '" + value + "'" + ret = query.exec_(stmt) + if ret: + while query.next(): + ids.append(str(query.value(0))) + return ids + + def IdBetween(self, query, lower_id, higher_id, order): + QueryExec(query, "SELECT id FROM samples WHERE id > " + str(lower_id) + " AND id < " + str(higher_id) + " ORDER BY id " + order + " LIMIT 1") + if query.next(): + return True, int(query.value(0)) + else: + return False, 0 + + def BinarySearchTime(self, lower_id, higher_id, target_time, get_floor): + query = QSqlQuery(self.glb.db) + while True: + next_id = int((lower_id + higher_id) / 2) + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + if not query.next(): + ok, dbid = self.IdBetween(query, lower_id, next_id, "DESC") + if not ok: + ok, dbid = self.IdBetween(query, next_id, higher_id, "") + if not ok: + return str(higher_id) + next_id = dbid + QueryExec(query, "SELECT time FROM samples WHERE id = " + str(next_id)) + next_time = int(query.value(0)) + if get_floor: + if target_time > next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(higher_id) + else: + if target_time >= next_time: + lower_id = next_id + else: + higher_id = next_id + if higher_id <= lower_id + 1: + return str(lower_id) + + def ConvertRelativeTime(self, val): + print "val ", val + mult = 1 + suffix = val[-2:] + if suffix == "ms": + mult = 1000000 + elif suffix == "us": + mult = 1000 + elif suffix == "ns": + mult = 1 + else: + return val + val = val[:-2].strip() + if not self.IsNumber(val): + return val + val = int(val) * mult + if val >= 0: + val += self.first_time + else: + val += self.last_time + return str(val) + + def ConvertTimeRange(self, vrange): + print "vrange ", vrange + if vrange[0] == "": + vrange[0] = str(self.first_time) + if vrange[1] == "": + vrange[1] = str(self.last_time) + vrange[0] = self.ConvertRelativeTime(vrange[0]) + vrange[1] = self.ConvertRelativeTime(vrange[1]) + print "vrange2 ", vrange + if not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return False + print "ok1" + beg_range = max(int(vrange[0]), self.first_time) + end_range = min(int(vrange[1]), self.last_time) + if beg_range > self.last_time or end_range < self.first_time: + return False + print "ok2" + vrange[0] = self.BinarySearchTime(0, self.last_id, beg_range, True) + vrange[1] = self.BinarySearchTime(1, self.last_id + 1, end_range, False) + print "vrange3 ", vrange + return True + + def AddTimeRange(self, value, ranges): + print "value ", value + n = value.count("-") + if n == 1: + pass + elif n == 2: + if value.split("-")[1].strip() == "": + n = 1 + elif n == 3: + n = 2 + else: + return False + pos = findnth(value, "-", n) + vrange = [value[:pos].strip() ,value[pos+1:].strip()] + if self.ConvertTimeRange(vrange): + ranges.append(vrange) + return True + return False + + def InvalidValue(self, value): + self.value = "" + palette = QPalette() + palette.setColor(QPalette.Text,Qt.red) + self.widget.setPalette(palette) + self.red = True + self.error = self.label + " invalid value '" + value + "'" + self.parent.ShowMessage(self.error) + + def IsNumber(self, value): + try: + x = int(value) + except: + x = 0 + return str(x) == value + + def Invalidate(self): + self.validated = False + + def Validate(self): + input_string = self.widget.text() + self.validated = True + if self.red: + palette = QPalette() + self.widget.setPalette(palette) + self.red = False + if not len(input_string.strip()): + self.error = "" + self.value = "" + return + if self.table_name == "<timeranges>": + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if not self.AddTimeRange(value, ranges): + return self.InvalidValue(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + self.value = " OR ".join(ranges) + elif self.table_name == "<ranges>": + singles = [] + ranges = [] + for value in [x.strip() for x in input_string.split(",")]: + if "-" in value: + vrange = value.split("-") + if len(vrange) != 2 or not self.IsNumber(vrange[0]) or not self.IsNumber(vrange[1]): + return self.InvalidValue(value) + ranges.append(vrange) + else: + if not self.IsNumber(value): + return self.InvalidValue(value) + singles.append(value) + ranges = [("(" + self.column_name1 + " >= " + r[0] + " AND " + self.column_name1 + " <= " + r[1] + ")") for r in ranges] + if len(singles): + ranges.append(self.column_name1 + " IN (" + ",".join(singles) + ")") + self.value = " OR ".join(ranges) + elif self.table_name: + all_ids = [] + for value in [x.strip() for x in input_string.split(",")]: + ids = self.ValueToIds(value) + if len(ids): + all_ids.extend(ids) + else: + return self.InvalidValue(value) + self.value = self.column_name1 + " IN (" + ",".join(all_ids) + ")" + if self.column_name2: + self.value = "( " + self.value + " OR " + self.column_name2 + " IN (" + ",".join(all_ids) + ") )" + else: + self.value = input_string.strip() + self.error = "" + self.parent.ClearMessage() + + def IsValid(self): + if not self.validated: + self.Validate() + if len(self.error): + self.parent.ShowMessage(self.error) + return False + return True + +# Selected branch report creation dialog + +class SelectedBranchDialog(QDialog): + + def __init__(self, glb, parent=None): + super(SelectedBranchDialog, self).__init__(parent) + + self.glb = glb + + self.name = "" + self.where_clause = "" + + self.setWindowTitle("Selected Branches") + self.setMinimumWidth(600) + + items = ( + ("Report name:", "Enter a name to appear in the window title bar", "", "", "", ""), + ("Time ranges:", "Enter time ranges", "<timeranges>", "", "samples.id", ""), + ("CPUs:", "Enter CPUs or ranges e.g. 0,5-6", "<ranges>", "", "cpu", ""), + ("Commands:", "Only branches with these commands will be included", "comms", "comm", "comm_id", ""), + ("PIDs:", "Only branches with these process IDs will be included", "threads", "pid", "thread_id", ""), + ("TIDs:", "Only branches with these thread IDs will be included", "threads", "tid", "thread_id", ""), + ("DSOs:", "Only branches with these DSOs will be included", "dsos", "short_name", "samples.dso_id", "to_dso_id"), + ("Symbols:", "Only branches with these symbols will be included", "symbols", "name", "symbol_id", "to_symbol_id"), + ("Raw SQL clause: ", "Enter a raw SQL WHERE clause", "", "", "", ""), + ) + self.data_items = [SQLTableDialogDataItem(glb, *x, parent=self) for x in items] + + self.grid = QGridLayout() + + for row in xrange(len(self.data_items)): + self.grid.addWidget(QLabel(self.data_items[row].label), row, 0) + self.grid.addWidget(self.data_items[row].widget, row, 1) + + self.status = QLabel() + + self.ok_button = QPushButton("Ok", self) + self.ok_button.setDefault(True) + self.ok_button.released.connect(self.Ok) + self.ok_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.cancel_button = QPushButton("Cancel", self) + self.cancel_button.released.connect(self.reject) + self.cancel_button.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Fixed) + + self.hbox = QHBoxLayout() + #self.hbox.addStretch() + self.hbox.addWidget(self.status) + self.hbox.addWidget(self.ok_button) + self.hbox.addWidget(self.cancel_button) + + self.vbox = QVBoxLayout() + self.vbox.addLayout(self.grid) + self.vbox.addLayout(self.hbox) + + self.setLayout(self.vbox); + + def Ok(self): + self.name = self.data_items[0].value + if not self.name: + self.ShowMessage("Report name is required") + return + for d in self.data_items: + if not d.IsValid(): + return + for d in self.data_items[1:]: + if len(d.value): + if len(self.where_clause): + self.where_clause += " AND " + self.where_clause += d.value + if len(self.where_clause): + self.where_clause = " AND ( " + self.where_clause + " ) " + else: + self.ShowMessage("No selection") + return + self.accept() + + def ShowMessage(self, msg): + self.status.setText("<font color=#FF0000>" + msg) + + def ClearMessage(self): + self.status.setText("") + # Event list def GetEventList(db): @@ -1656,7 +1975,7 @@ class TableWindow(QMdiSubWindow, ResizeColumnsToContentsBase): def FindDone(self, row): self.find_bar.Idle() if row >= 0: - self.view.setCurrentIndex(self.model.index(row, 0, QModelIndex())) + self.view.setCurrentIndex(self.model.mapFromSource(self.data_model.index(row, 0, QModelIndex()))) else: self.find_bar.NotFound() @@ -1765,6 +2084,149 @@ class WindowMenu(): def setActiveSubWindow(self, nr): self.mdi_area.setActiveSubWindow(self.mdi_area.subWindowList()[nr - 1]) +# Help text + +glb_help_text = """ +<h1>Contents</h1> +<style> +p.c1 { + text-indent: 40px; +} +p.c2 { + text-indent: 80px; +} +} +</style> +<p class=c1><a href=#reports>1. Reports</a></p> +<p class=c2><a href=#callgraph>1.1 Context-Sensitive Call Graph</a></p> +<p class=c2><a href=#allbranches>1.2 All branches</a></p> +<p class=c2><a href=#selectedbranches>1.3 Selected branches</a></p> +<p class=c1><a href=#tables>2. Tables</a></p> +<h1 id=reports>1. Reports</h1> +<h2 id=callgraph>1.1 Context-Sensitive Call Graph</h2> +The result is a GUI window with a tree representing a context-sensitive +call-graph. Expanding a couple of levels of the tree and adjusting column +widths to suit will display something like: +<pre> + Call Graph: pt_example +Call Path Object Count Time(ns) Time(%) Branch Count Branch Count(%) +v- ls + v- 2638:2638 + v- _start ld-2.19.so 1 10074071 100.0 211135 100.0 + |- unknown unknown 1 13198 0.1 1 0.0 + >- _dl_start ld-2.19.so 1 1400980 13.9 19637 9.3 + >- _d_linit_internal ld-2.19.so 1 448152 4.4 11094 5.3 + v-__libc_start_main@plt ls 1 8211741 81.5 180397 85.4 + >- _dl_fixup ld-2.19.so 1 7607 0.1 108 0.1 + >- __cxa_atexit libc-2.19.so 1 11737 0.1 10 0.0 + >- __libc_csu_init ls 1 10354 0.1 10 0.0 + |- _setjmp libc-2.19.so 1 0 0.0 4 0.0 + v- main ls 1 8182043 99.6 180254 99.9 +</pre> +<h3>Points to note:</h3> +<ul> +<li>The top level is a command name (comm)</li> +<li>The next level is a thread (pid:tid)</li> +<li>Subsequent levels are functions</li> +<li>'Count' is the number of calls</li> +<li>'Time' is the elapsed time until the function returns</li> +<li>Percentages are relative to the level above</li> +<li>'Branch Count' is the total number of branches for that function and all functions that it calls +</ul> +<h3>Find</h3> +Ctrl-F displays a Find bar which finds function names by either an exact match or a pattern match. +The pattern matching symbols are ? for any character and * for zero or more characters. +<h2 id=allbranches>1.2 All branches</h2> +The All branches report displays all branches in chronological order. +Not all data is fetched immediately. More records can be fetched using the Fetch bar provided. +<h3>Disassembly</h3> +Open a branch to display disassembly. This only works if: +<ol> +<li>The disassembler is available. Currently, only Intel XED is supported - see <a href=#xed>Intel XED Setup</a></li> +<li>The object code is available. Currently, only the perf build ID cache is searched for object code. +The default directory ~/.debug can be overridden by setting environment variable PERF_BUILDID_DIR. +One exception is kcore where the DSO long name is used (refer dsos_view on the Tables menu), +or alternatively, set environment variable PERF_KCORE to the kcore file name.</li> +</ol> +<h4 id=xed>Intel XED Setup</h4> +To use Intel XED, libxed.so must be present. To build and install libxed.so: +<pre> +git clone https://github.com/intelxed/mbuild.git mbuild +git clone https://github.com/intelxed/xed +cd xed +./mfile.py --share +sudo ./mfile.py --prefix=/usr/local install +sudo ldconfig +</pre> +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<h2 id=selectedbranches>1.3 Selected branches</h2> +This is the same as the <a href=#allbranches>All branches</a> report but with the data reduced +by various selection criteria. A dialog box displays available criteria which are AND'ed together. +<h3>1.3.1 Time ranges</h3> +The time ranges hint text shows the total time range. Relative time ranges can also be entered in +ms, us or ns. Also, negative values are relative to the end of trace. Examples: +<pre> + 81073085947329-81073085958238 From 81073085947329 to 81073085958238 + 100us-200us From 100us to 200us + 10ms- From 10ms to the end + -100ns The first 100ns + -10ms- The last 10ms +</pre> +N.B. Due to the granularity of timestamps, there could be no branches in any given time range. +<h1 id=tables>2. Tables</h1> +The Tables menu shows all tables and views in the database. Most tables have an associated view +which displays the information in a more friendly way. Not all data for large tables is fetched +immediately. More records can be fetched using the Fetch bar provided. Columns can be sorted, +but that can be slow for large tables. +<p>There are also tables of database meta-information. +For SQLite3 databases, the sqlite_master table is included. +For PostgreSQL databases, information_schema.tables/views/columns are included. +<h3>Find</h3> +Ctrl-F displays a Find bar which finds substrings by either an exact match or a regular expression match. +Refer to Python documentation for the regular expression syntax. +All columns are searched, but only currently fetched rows are searched. +<p>N.B. Results are found in id order, so if the table is re-ordered, find-next and find-previous +will go to the next/previous result in id order, instead of display order. +""" + +# Help window + +class HelpWindow(QMdiSubWindow): + + def __init__(self, glb, parent=None): + super(HelpWindow, self).__init__(parent) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setWidget(self.text) + + AddSubWindow(glb.mainwindow.mdi_area, self, "Exported SQL Viewer Help") + +# Main window that only displays the help text + +class HelpOnlyWindow(QMainWindow): + + def __init__(self, parent=None): + super(HelpOnlyWindow, self).__init__(parent) + + self.setMinimumSize(200, 100) + self.resize(800, 600) + self.setWindowTitle("Exported SQL Viewer Help") + self.setWindowIcon(self.style().standardIcon(QStyle.SP_MessageBoxInformation)) + + self.text = QTextBrowser() + self.text.setHtml(glb_help_text) + self.text.setReadOnly(True) + self.text.setOpenExternalLinks(True) + + self.setCentralWidget(self.text) + # Font resize def ResizeFont(widget, diff): @@ -1851,6 +2313,9 @@ class MainWindow(QMainWindow): self.window_menu = WindowMenu(self.mdi_area, menu) + help_menu = menu.addMenu("&Help") + help_menu.addAction(CreateAction("&Exported SQL Viewer Help", "Helpful information", self.Help, self, QKeySequence.HelpContents)) + def Find(self): win = self.mdi_area.activeSubWindow() if win: @@ -1888,6 +2353,8 @@ class MainWindow(QMainWindow): if event == "branches": label = "All branches" if branches_events == 1 else "All branches " + "(id=" + dbid + ")" reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewBranchView(x), self)) + label = "Selected branches" if branches_events == 1 else "Selected branches " + "(id=" + dbid + ")" + reports_menu.addAction(CreateAction(label, "Create a new window displaying branch events", lambda x=dbid: self.NewSelectedBranchView(x), self)) def TableMenu(self, tables, menu): table_menu = menu.addMenu("&Tables") @@ -1900,9 +2367,18 @@ class MainWindow(QMainWindow): def NewBranchView(self, event_id): BranchWindow(self.glb, event_id, "", "", self) + def NewSelectedBranchView(self, event_id): + dialog = SelectedBranchDialog(self.glb, self) + ret = dialog.exec_() + if ret: + BranchWindow(self.glb, event_id, dialog.name, dialog.where_clause, self) + def NewTableView(self, table_name): TableWindow(self.glb, table_name, self) + def Help(self): + HelpWindow(self.glb, self) + # XED Disassembler class xed_state_t(Structure): @@ -1929,7 +2405,12 @@ class XEDInstruction(): class LibXED(): def __init__(self): - self.libxed = CDLL("libxed.so") + try: + self.libxed = CDLL("libxed.so") + except: + self.libxed = None + if not self.libxed: + self.libxed = CDLL("/usr/local/lib/libxed.so") self.xed_tables_init = self.libxed.xed_tables_init self.xed_tables_init.restype = None @@ -2097,10 +2578,16 @@ class DBRef(): def Main(): if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: exported-sql-viewer.py <database name>" + print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}" raise Exception("Too few arguments") dbname = sys.argv[1] + if dbname == "--help-only": + app = QApplication(sys.argv) + mainwindow = HelpOnlyWindow() + mainwindow.show() + err = app.exec_() + sys.exit(err) is_sqlite3 = False try: diff --git a/tools/perf/tests/attr/test-record-group-sampling b/tools/perf/tests/attr/test-record-group-sampling index 8a33ca4f9e1f..f0729c454f16 100644 --- a/tools/perf/tests/attr/test-record-group-sampling +++ b/tools/perf/tests/attr/test-record-group-sampling @@ -37,4 +37,3 @@ sample_freq=0 sample_period=0 freq=0 write_backward=0 -sample_id_all=0 diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index e88e6f9b1463..668d2a9ef0f4 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1810,3 +1810,30 @@ void perf_evlist__force_leader(struct perf_evlist *evlist) leader->forced_leader = true; } } + +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evsel_list, + struct perf_evsel *evsel) +{ + struct perf_evsel *c2, *leader; + bool is_open = true; + + leader = evsel->leader; + pr_debug("Weak group for %s/%d failed\n", + leader->name, leader->nr_members); + + /* + * for_each_group_member doesn't work here because it doesn't + * include the first entry. + */ + evlist__for_each_entry(evsel_list, c2) { + if (c2 == evsel) + is_open = false; + if (c2->leader == leader) { + if (is_open) + perf_evsel__close(c2); + c2->leader = c2; + c2->nr_members = 0; + } + } + return leader; +} diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index dc66436add98..9919eed6d15b 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -312,4 +312,7 @@ bool perf_evlist__exclude_kernel(struct perf_evlist *evlist); void perf_evlist__force_leader(struct perf_evlist *evlist); +struct perf_evsel *perf_evlist__reset_weak_group(struct perf_evlist *evlist, + struct perf_evsel *evsel); + #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 6d187059a373..d37bb1566cd9 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -956,7 +956,6 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts, attr->sample_freq = 0; attr->sample_period = 0; attr->write_backward = 0; - attr->sample_id_all = 0; } if (opts->no_samples) diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 58f6a9ceb590..4503f3ca45ab 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -1474,6 +1474,8 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder) decoder->have_calc_cyc_to_tsc = false; intel_pt_calc_cyc_to_tsc(decoder, true); } + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder) @@ -1514,6 +1516,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder) decoder->timestamp = timestamp; decoder->timestamp_insn_cnt = 0; + + intel_pt_log_to("Setting timestamp", decoder->timestamp); } /* Walk PSB+ packets when already in sync. */ diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.c b/tools/perf/util/intel-pt-decoder/intel-pt-log.c index e02bc7b166a0..5e64da270f97 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.c @@ -31,6 +31,11 @@ static FILE *f; static char log_name[MAX_LOG_NAME]; bool intel_pt_enable_logging; +void *intel_pt_log_fp(void) +{ + return f; +} + void intel_pt_log_enable(void) { intel_pt_enable_logging = true; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-log.h b/tools/perf/util/intel-pt-decoder/intel-pt-log.h index 45b64f93f358..cc084937f701 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-log.h +++ b/tools/perf/util/intel-pt-decoder/intel-pt-log.h @@ -22,6 +22,7 @@ struct intel_pt_pkt; +void *intel_pt_log_fp(void); void intel_pt_log_enable(void); void intel_pt_log_disable(void); void intel_pt_log_set_name(const char *name); diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index 86cc9a64e982..149ff361ca78 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -206,6 +206,16 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf, intel_pt_dump(pt, buf, len); } +static void intel_pt_log_event(union perf_event *event) +{ + FILE *f = intel_pt_log_fp(); + + if (!intel_pt_enable_logging || !f) + return; + + perf_event__fprintf(event, f); +} + static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a, struct auxtrace_buffer *b) { @@ -2010,9 +2020,9 @@ static int intel_pt_process_event(struct perf_session *session, event->header.type == PERF_RECORD_SWITCH_CPU_WIDE) err = intel_pt_context_switch(pt, event, sample); - intel_pt_log("event %s (%u): cpu %d time %"PRIu64" tsc %#"PRIx64"\n", - perf_event__name(event->header.type), event->header.type, - sample->cpu, sample->time, timestamp); + intel_pt_log("event %u: cpu %d time %"PRIu64" tsc %#"PRIx64" ", + event->header.type, sample->cpu, sample->time, timestamp); + intel_pt_log_event(event); return err; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 7799788f662f..7e49baad304d 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -773,7 +773,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu) if (!is_arm_pmu_core(name)) { pname = pe->pmu ? pe->pmu : "cpu"; - if (strncmp(pname, name, strlen(pname))) + if (strcmp(pname, name)) continue; } diff --git a/tools/testing/selftests/powerpc/include/utils.h b/tools/testing/selftests/powerpc/include/utils.h index 49621822d7c3..ae43a614835d 100644 --- a/tools/testing/selftests/powerpc/include/utils.h +++ b/tools/testing/selftests/powerpc/include/utils.h @@ -82,6 +82,16 @@ do { \ } \ } while (0) +#define SKIP_IF_MSG(x, msg) \ +do { \ + if ((x)) { \ + fprintf(stderr, \ + "[SKIP] Test skipped on line %d: %s\n", \ + __LINE__, msg); \ + return MAGIC_SKIP_RETURN_VALUE; \ + } \ +} while (0) + #define _str(s) #s #define str(s) _str(s) diff --git a/tools/testing/selftests/powerpc/ptrace/core-pkey.c b/tools/testing/selftests/powerpc/ptrace/core-pkey.c index e23e2e199eb4..d5c64fee032d 100644 --- a/tools/testing/selftests/powerpc/ptrace/core-pkey.c +++ b/tools/testing/selftests/powerpc/ptrace/core-pkey.c @@ -352,10 +352,7 @@ static int write_core_pattern(const char *core_pattern) FILE *f; f = fopen(core_pattern_file, "w"); - if (!f) { - perror("Error writing to core_pattern file"); - return TEST_FAIL; - } + SKIP_IF_MSG(!f, "Try with root privileges"); ret = fwrite(core_pattern, 1, len, f); fclose(f); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c index 0b4ebcc2f485..ca29fafeed5d 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-gpr.c @@ -31,7 +31,7 @@ void gpr(void) ASM_LOAD_GPR_IMMED(gpr_1) ASM_LOAD_FPR_SINGLE_PRECISION(flt_1) : - : [gpr_1]"i"(GPR_1), [flt_1] "r" (&a) + : [gpr_1]"i"(GPR_1), [flt_1] "b" (&a) : "memory", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15", "r16", "r17", "r18", "r19", "r20", "r21", "r22", "r23", "r24", diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c index 59206b96e98a..a08a91594dbe 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-gpr.c @@ -59,8 +59,8 @@ trans: "3: ;" : [res] "=r" (result), [texasr] "=r" (texasr) : [gpr_1]"i"(GPR_1), [gpr_2]"i"(GPR_2), - [sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "r" (&a), - [flt_2] "r" (&b), [cptr1] "r" (&cptr[1]) + [sprn_texasr] "i" (SPRN_TEXASR), [flt_1] "b" (&a), + [flt_2] "b" (&b), [cptr1] "b" (&cptr[1]) : "memory", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15", "r16", "r17", "r18", "r19", "r20", "r21", "r22", diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c index b3c061dc9512..f47174746231 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-tar.c @@ -72,7 +72,7 @@ trans: "3: ;" : [res] "=r" (result), [texasr] "=r" (texasr) - : [val] "r" (cptr[1]), [sprn_dscr]"i"(SPRN_DSCR), + : [sprn_dscr]"i"(SPRN_DSCR), [sprn_tar]"i"(SPRN_TAR), [sprn_ppr]"i"(SPRN_PPR), [sprn_texasr]"i"(SPRN_TEXASR), [tar_1]"i"(TAR_1), [dscr_1]"i"(DSCR_1), [tar_2]"i"(TAR_2), [dscr_2]"i"(DSCR_2), diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c index 277dade1b382..18a685bf6a09 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spd-vsx.c @@ -77,8 +77,7 @@ trans: "3: ;" : [res] "=r" (result), [texasr] "=r" (texasr) - : [fp_load] "r" (fp_load), [fp_load_ckpt] "r" (fp_load_ckpt), - [sprn_texasr] "i" (SPRN_TEXASR) + : [sprn_texasr] "i" (SPRN_TEXASR) : "memory", "r0", "r1", "r3", "r4", "r7", "r8", "r9", "r10", "r11" ); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c index 51427a2465f6..ba04999254e3 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-spr.c @@ -74,7 +74,7 @@ trans: "3: ;" : [tfhar] "=r" (tfhar), [res] "=r" (result), - [texasr] "=r" (texasr), [cptr1] "=r" (cptr1) + [texasr] "=r" (texasr), [cptr1] "=b" (cptr1) : [sprn_texasr] "i" (SPRN_TEXASR) : "memory", "r0", "r8", "r31" ); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c index 48b462f75023..f70023b25e6e 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-tar.c @@ -65,7 +65,7 @@ trans: : [sprn_dscr]"i"(SPRN_DSCR), [sprn_tar]"i"(SPRN_TAR), [sprn_ppr]"i"(SPRN_PPR), [sprn_texasr]"i"(SPRN_TEXASR), [tar_1]"i"(TAR_1), [dscr_1]"i"(DSCR_1), [tar_2]"i"(TAR_2), - [dscr_2]"i"(DSCR_2), [cptr1] "r" (&cptr[1]) + [dscr_2]"i"(DSCR_2), [cptr1] "b" (&cptr[1]) : "memory", "r0", "r1", "r3", "r4", "r5", "r6" ); diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c index 17c23cabac3e..dfba80058977 100644 --- a/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c +++ b/tools/testing/selftests/powerpc/ptrace/ptrace-tm-vsx.c @@ -65,8 +65,7 @@ trans: "3: ;" : [res] "=r" (result), [texasr] "=r" (texasr) - : [fp_load] "r" (fp_load), [fp_load_ckpt] "r" (fp_load_ckpt), - [sprn_texasr] "i" (SPRN_TEXASR), [cptr1] "r" (&cptr[1]) + : [sprn_texasr] "i" (SPRN_TEXASR), [cptr1] "b" (&cptr[1]) : "memory", "r0", "r1", "r3", "r4", "r7", "r8", "r9", "r10", "r11" ); |