diff options
620 files changed, 4384 insertions, 2948 deletions
diff --git a/Documentation/devicetree/bindings/net/dwmac-sun8i.txt b/Documentation/devicetree/bindings/net/dwmac-sun8i.txt deleted file mode 100644 index 725f3b187886..000000000000 --- a/Documentation/devicetree/bindings/net/dwmac-sun8i.txt +++ /dev/null @@ -1,84 +0,0 @@ -* Allwinner sun8i GMAC ethernet controller - -This device is a platform glue layer for stmmac. -Please see stmmac.txt for the other unchanged properties. - -Required properties: -- compatible: should be one of the following string: - "allwinner,sun8i-a83t-emac" - "allwinner,sun8i-h3-emac" - "allwinner,sun8i-v3s-emac" - "allwinner,sun50i-a64-emac" -- reg: address and length of the register for the device. -- interrupts: interrupt for the device -- interrupt-names: should be "macirq" -- clocks: A phandle to the reference clock for this device -- clock-names: should be "stmmaceth" -- resets: A phandle to the reset control for this device -- reset-names: should be "stmmaceth" -- phy-mode: See ethernet.txt -- phy-handle: See ethernet.txt -- #address-cells: shall be 1 -- #size-cells: shall be 0 -- syscon: A phandle to the syscon of the SoC with one of the following - compatible string: - - allwinner,sun8i-h3-system-controller - - allwinner,sun8i-v3s-system-controller - - allwinner,sun50i-a64-system-controller - - allwinner,sun8i-a83t-system-controller - -Optional properties: -- allwinner,tx-delay-ps: TX clock delay chain value in ps. Range value is 0-700. Default is 0) -- allwinner,rx-delay-ps: RX clock delay chain value in ps. Range value is 0-3100. Default is 0) -Both delay properties need to be a multiple of 100. They control the delay for -external PHY. - -Optional properties for the following compatibles: - - "allwinner,sun8i-h3-emac", - - "allwinner,sun8i-v3s-emac": -- allwinner,leds-active-low: EPHY LEDs are active low - -Required child node of emac: -- mdio bus node: should be named mdio - -Required properties of the mdio node: -- #address-cells: shall be 1 -- #size-cells: shall be 0 - -The device node referenced by "phy" or "phy-handle" should be a child node -of the mdio node. See phy.txt for the generic PHY bindings. - -Required properties of the phy node with the following compatibles: - - "allwinner,sun8i-h3-emac", - - "allwinner,sun8i-v3s-emac": -- clocks: a phandle to the reference clock for the EPHY -- resets: a phandle to the reset control for the EPHY - -Example: - -emac: ethernet@1c0b000 { - compatible = "allwinner,sun8i-h3-emac"; - syscon = <&syscon>; - reg = <0x01c0b000 0x104>; - interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "macirq"; - resets = <&ccu RST_BUS_EMAC>; - reset-names = "stmmaceth"; - clocks = <&ccu CLK_BUS_EMAC>; - clock-names = "stmmaceth"; - #address-cells = <1>; - #size-cells = <0>; - - phy-handle = <&int_mii_phy>; - phy-mode = "mii"; - allwinner,leds-active-low; - mdio: mdio { - #address-cells = <1>; - #size-cells = <0>; - int_mii_phy: ethernet-phy@1 { - reg = <1>; - clocks = <&ccu CLK_BUS_EPHY>; - resets = <&ccu RST_BUS_EPHY>; - }; - }; -}; diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 3e7b946dea27..5e40e1f68873 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -228,7 +228,7 @@ Learning on the device port should be enabled, as well as learning_sync: bridge link set dev DEV learning on self bridge link set dev DEV learning_sync on self -Learning_sync attribute enables syncing of the learned/forgotton FDB entry to +Learning_sync attribute enables syncing of the learned/forgotten FDB entry to the bridge's FDB. It's possible, but not optimal, to enable learning on the device port and on the bridge port, and disable learning_sync. @@ -245,7 +245,7 @@ the responsibility of the port driver/device to age out these entries. If the port device supports ageing, when the FDB entry expires, it will notify the driver which in turn will notify the bridge with SWITCHDEV_FDB_DEL. If the device does not support ageing, the driver can simulate ageing using a -garbage collection timer to monitor FBD entries. Expired entries will be +garbage collection timer to monitor FDB entries. Expired entries will be notified to the bridge using SWITCHDEV_FDB_DEL. See rocker driver for example of driver running ageing timer. diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt index 65ea5915178b..074670b98bac 100644 --- a/Documentation/printk-formats.txt +++ b/Documentation/printk-formats.txt @@ -58,20 +58,23 @@ Symbols/Function Pointers %ps versatile_init %pB prev_fn_of_versatile_init+0x88/0x88 -For printing symbols and function pointers. The ``S`` and ``s`` specifiers -result in the symbol name with (``S``) or without (``s``) offsets. Where -this is used on a kernel without KALLSYMS - the symbol address is -printed instead. +The ``F`` and ``f`` specifiers are for printing function pointers, +for example, f->func, &gettimeofday. They have the same result as +``S`` and ``s`` specifiers. But they do an extra conversion on +ia64, ppc64 and parisc64 architectures where the function pointers +are actually function descriptors. + +The ``S`` and ``s`` specifiers can be used for printing symbols +from direct addresses, for example, __builtin_return_address(0), +(void *)regs->ip. They result in the symbol name with (``S``) or +without (``s``) offsets. If KALLSYMS are disabled then the symbol +address is printed instead. The ``B`` specifier results in the symbol name with offsets and should be used when printing stack backtraces. The specifier takes into consideration the effect of compiler optimisations which may occur when tail-call``s are used and marked with the noreturn GCC attribute. -On ia64, ppc64 and parisc64 architectures function pointers are -actually function descriptors which must first be resolved. The ``F`` and -``f`` specifiers perform this resolution and then provide the same -functionality as the ``S`` and ``s`` specifiers. Kernel Pointers =============== diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 14db18c970b1..28596e03220b 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -35,9 +35,34 @@ Table : Subdirectories in /proc/sys/net bpf_jit_enable -------------- -This enables Berkeley Packet Filter Just in Time compiler. -Currently supported on x86_64 architecture, bpf_jit provides a framework -to speed packet filtering, the one used by tcpdump/libpcap for example. +This enables the BPF Just in Time (JIT) compiler. BPF is a flexible +and efficient infrastructure allowing to execute bytecode at various +hook points. It is used in a number of Linux kernel subsystems such +as networking (e.g. XDP, tc), tracing (e.g. kprobes, uprobes, tracepoints) +and security (e.g. seccomp). LLVM has a BPF back end that can compile +restricted C into a sequence of BPF instructions. After program load +through bpf(2) and passing a verifier in the kernel, a JIT will then +translate these BPF proglets into native CPU instructions. There are +two flavors of JITs, the newer eBPF JIT currently supported on: + - x86_64 + - arm64 + - ppc64 + - sparc64 + - mips64 + - s390x + +And the older cBPF JIT supported on the following archs: + - arm + - mips + - ppc + - sparc + +eBPF JITs are a superset of cBPF JITs, meaning the kernel will +migrate cBPF instructions into eBPF instructions and then JIT +compile them transparently. Older cBPF JITs can only translate +tcpdump filters, seccomp rules, etc, but not mentioned eBPF +programs loaded through bpf(2). + Values : 0 - disable the JIT (default value) 1 - enable the JIT @@ -46,9 +71,9 @@ Values : bpf_jit_harden -------------- -This enables hardening for the Berkeley Packet Filter Just in Time compiler. -Supported are eBPF JIT backends. Enabling hardening trades off performance, -but can mitigate JIT spraying. +This enables hardening for the BPF JIT compiler. Supported are eBPF +JIT backends. Enabling hardening trades off performance, but can +mitigate JIT spraying. Values : 0 - disable JIT hardening (default value) 1 - enable JIT hardening for unprivileged users only @@ -57,11 +82,11 @@ Values : bpf_jit_kallsyms ---------------- -When Berkeley Packet Filter Just in Time compiler is enabled, then compiled -images are unknown addresses to the kernel, meaning they neither show up in -traces nor in /proc/kallsyms. This enables export of these addresses, which -can be used for debugging/tracing. If bpf_jit_harden is enabled, this feature -is disabled. +When BPF JIT compiler is enabled, then compiled images are unknown +addresses to the kernel, meaning they neither show up in traces nor +in /proc/kallsyms. This enables export of these addresses, which can +be used for debugging/tracing. If bpf_jit_harden is enabled, this +feature is disabled. Values : 0 - disable JIT kallsyms export (default value) 1 - enable JIT kallsyms export for privileged users only diff --git a/MAINTAINERS b/MAINTAINERS index b1387edcca2f..a2add4a4f7f3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7131,7 +7131,6 @@ M: Marc Zyngier <marc.zyngier@arm.com> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core -T: git git://git.infradead.org/users/jcooper/linux.git irqchip/core F: Documentation/devicetree/bindings/interrupt-controller/ F: drivers/irqchip/ @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = NAME = Fearless Coyote # *DOCUMENTATION* @@ -396,7 +396,7 @@ LINUXINCLUDE := \ KBUILD_CPPFLAGS := -D__KERNEL__ KBUILD_CFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ - -fno-strict-aliasing -fno-common \ + -fno-strict-aliasing -fno-common -fshort-wchar \ -Werror-implicit-function-declaration \ -Wno-format-security \ -std=gnu89 $(call cc-option,-fno-PIE) @@ -442,7 +442,7 @@ export RCS_TAR_IGNORE := --exclude SCCS --exclude BitKeeper --exclude .svn \ # =========================================================================== # Rules shared between *config targets and build targets -# Basic helpers built in scripts/ +# Basic helpers built in scripts/basic/ PHONY += scripts_basic scripts_basic: $(Q)$(MAKE) $(build)=scripts/basic @@ -505,7 +505,7 @@ ifeq ($(KBUILD_EXTMOD),) endif endif endif -# install and module_install need also be processed one by one +# install and modules_install need also be processed one by one ifneq ($(filter install,$(MAKECMDGOALS)),) ifneq ($(filter modules_install,$(MAKECMDGOALS)),) mixed-targets := 1 @@ -964,7 +964,7 @@ export KBUILD_VMLINUX_MAIN := $(core-y) $(libs-y2) $(drivers-y) $(net-y) $(virt- export KBUILD_VMLINUX_LIBS := $(libs-y1) export KBUILD_LDS := arch/$(SRCARCH)/kernel/vmlinux.lds export LDFLAGS_vmlinux -# used by scripts/pacmage/Makefile +# used by scripts/package/Makefile export KBUILD_ALLDIRS := $(sort $(filter-out arch/%,$(vmlinux-alldirs)) arch Documentation include samples scripts tools) vmlinux-deps := $(KBUILD_LDS) $(KBUILD_VMLINUX_INIT) $(KBUILD_VMLINUX_MAIN) $(KBUILD_VMLINUX_LIBS) @@ -992,8 +992,8 @@ include/generated/autoksyms.h: FORCE ARCH_POSTLINK := $(wildcard $(srctree)/arch/$(SRCARCH)/Makefile.postlink) # Final link of vmlinux with optional arch pass after final link - cmd_link-vmlinux = \ - $(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux) ; \ +cmd_link-vmlinux = \ + $(CONFIG_SHELL) $< $(LD) $(LDFLAGS) $(LDFLAGS_vmlinux) ; \ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) vmlinux: scripts/link-vmlinux.sh vmlinux_prereq $(vmlinux-deps) FORCE @@ -1184,6 +1184,7 @@ PHONY += kselftest kselftest: $(Q)$(MAKE) -C tools/testing/selftests run_tests +PHONY += kselftest-clean kselftest-clean: $(Q)$(MAKE) -C tools/testing/selftests clean diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h index ff4049155c84..4d61d2a50c52 100644 --- a/arch/alpha/include/asm/io.h +++ b/arch/alpha/include/asm/io.h @@ -299,6 +299,7 @@ static inline void __iomem * ioremap_nocache(unsigned long offset, return ioremap(offset, size); } +#define ioremap_wc ioremap_nocache #define ioremap_uc ioremap_nocache static inline void iounmap(volatile void __iomem *addr) diff --git a/arch/alpha/include/asm/types.h b/arch/alpha/include/asm/types.h index 4cb4b6d3452c..0bc66e1d3a7e 100644 --- a/arch/alpha/include/asm/types.h +++ b/arch/alpha/include/asm/types.h @@ -1,6 +1,6 @@ #ifndef _ALPHA_TYPES_H #define _ALPHA_TYPES_H -#include <asm-generic/int-ll64.h> +#include <uapi/asm/types.h> #endif /* _ALPHA_TYPES_H */ diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h index b37153ecf2ac..db7fc0f511e2 100644 --- a/arch/alpha/include/asm/unistd.h +++ b/arch/alpha/include/asm/unistd.h @@ -3,7 +3,7 @@ #include <uapi/asm/unistd.h> -#define NR_SYSCALLS 514 +#define NR_SYSCALLS 523 #define __ARCH_WANT_OLD_READDIR #define __ARCH_WANT_STAT64 diff --git a/arch/alpha/include/uapi/asm/types.h b/arch/alpha/include/uapi/asm/types.h index 9fd3cd459777..8d1024d7be05 100644 --- a/arch/alpha/include/uapi/asm/types.h +++ b/arch/alpha/include/uapi/asm/types.h @@ -9,8 +9,18 @@ * need to be careful to avoid a name clashes. */ -#ifndef __KERNEL__ +/* + * This is here because we used to use l64 for alpha + * and we don't want to impact user mode with our change to ll64 + * in the kernel. + * + * However, some user programs are fine with this. They can + * flag __SANE_USERSPACE_TYPES__ to get int-ll64.h here. + */ +#if !defined(__SANE_USERSPACE_TYPES__) && !defined(__KERNEL__) #include <asm-generic/int-l64.h> +#else +#include <asm-generic/int-ll64.h> #endif #endif /* _UAPI_ALPHA_TYPES_H */ diff --git a/arch/alpha/include/uapi/asm/unistd.h b/arch/alpha/include/uapi/asm/unistd.h index aa33bf5aacb6..a2945fea6c86 100644 --- a/arch/alpha/include/uapi/asm/unistd.h +++ b/arch/alpha/include/uapi/asm/unistd.h @@ -475,5 +475,19 @@ #define __NR_getrandom 511 #define __NR_memfd_create 512 #define __NR_execveat 513 +#define __NR_seccomp 514 +#define __NR_bpf 515 +#define __NR_userfaultfd 516 +#define __NR_membarrier 517 +#define __NR_mlock2 518 +#define __NR_copy_file_range 519 +#define __NR_preadv2 520 +#define __NR_pwritev2 521 +#define __NR_statx 522 + +/* Alpha doesn't have protection keys. */ +#define __IGNORE_pkey_mprotect +#define __IGNORE_pkey_alloc +#define __IGNORE_pkey_free #endif /* _UAPI_ALPHA_UNISTD_H */ diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index d5f0580746a5..03ff832b1cb4 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -351,7 +351,7 @@ marvel_init_io7(struct io7 *io7) } } -void +void __init marvel_io7_present(gct6_node *node) { int pe; @@ -369,6 +369,7 @@ marvel_io7_present(gct6_node *node) static void __init marvel_find_console_vga_hose(void) { +#ifdef CONFIG_VGA_HOSE u64 *pu64 = (u64 *)((u64)hwrpb + hwrpb->ctbt_offset); if (pu64[7] == 3) { /* TERM_TYPE == graphics */ @@ -402,9 +403,10 @@ marvel_find_console_vga_hose(void) pci_vga_hose = hose; } } +#endif } -gct6_search_struct gct_wanted_node_list[] = { +gct6_search_struct gct_wanted_node_list[] __initdata = { { GCT_TYPE_HOSE, GCT_SUBTYPE_IO_PORT_MODULE, marvel_io7_present }, { 0, 0, NULL } }; diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 219bf271c0ba..b532d925443d 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -461,6 +461,7 @@ titan_ioremap(unsigned long addr, unsigned long size) unsigned long *ptes; unsigned long pfn; +#ifdef CONFIG_VGA_HOSE /* * Adjust the address and hose, if necessary. */ @@ -468,6 +469,7 @@ titan_ioremap(unsigned long addr, unsigned long size) h = pci_vga_hose->index; addr += pci_vga_hose->mem_space->start; } +#endif /* * Find the hose. diff --git a/arch/alpha/kernel/module.c b/arch/alpha/kernel/module.c index 936bc8f89a67..47632fa8c24e 100644 --- a/arch/alpha/kernel/module.c +++ b/arch/alpha/kernel/module.c @@ -181,6 +181,9 @@ apply_relocate_add(Elf64_Shdr *sechdrs, const char *strtab, switch (r_type) { case R_ALPHA_NONE: break; + case R_ALPHA_REFLONG: + *(u32 *)location = value; + break; case R_ALPHA_REFQUAD: /* BUG() can produce misaligned relocations. */ ((u32 *)location)[0] = value; diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index 9fc560459ebd..f6726a746427 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -115,7 +115,7 @@ wait_boot_cpu_to_stop(int cpuid) /* * Where secondaries begin a life of C. */ -void +void __init smp_callin(void) { int cpuid = hard_smp_processor_id(); diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index 9b62e3fd4f03..5b4514abb234 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -532,6 +532,15 @@ sys_call_table: .quad sys_getrandom .quad sys_memfd_create .quad sys_execveat + .quad sys_seccomp + .quad sys_bpf /* 515 */ + .quad sys_userfaultfd + .quad sys_membarrier + .quad sys_mlock2 + .quad sys_copy_file_range + .quad sys_preadv2 /* 520 */ + .quad sys_pwritev2 + .quad sys_statx .size sys_call_table, . - sys_call_table .type sys_call_table, @object diff --git a/arch/alpha/lib/Makefile b/arch/alpha/lib/Makefile index 7083434dd241..a80815960364 100644 --- a/arch/alpha/lib/Makefile +++ b/arch/alpha/lib/Makefile @@ -20,12 +20,8 @@ lib-y = __divqu.o __remqu.o __divlu.o __remlu.o \ checksum.o \ csum_partial_copy.o \ $(ev67-y)strlen.o \ - $(ev67-y)strcat.o \ - strcpy.o \ - $(ev67-y)strncat.o \ - strncpy.o \ - $(ev6-y)stxcpy.o \ - $(ev6-y)stxncpy.o \ + stycpy.o \ + styncpy.o \ $(ev67-y)strchr.o \ $(ev67-y)strrchr.o \ $(ev6-y)memchr.o \ @@ -49,3 +45,17 @@ AFLAGS___remlu.o = -DREM -DINTSIZE $(addprefix $(obj)/,__divqu.o __remqu.o __divlu.o __remlu.o): \ $(src)/$(ev6-y)divide.S FORCE $(call if_changed_rule,as_o_S) + +# There are direct branches between {str*cpy,str*cat} and stx*cpy. +# Ensure the branches are within range by merging these objects. + +LDFLAGS_stycpy.o := -r +LDFLAGS_styncpy.o := -r + +$(obj)/stycpy.o: $(obj)/strcpy.o $(obj)/$(ev67-y)strcat.o \ + $(obj)/$(ev6-y)stxcpy.o FORCE + $(call if_changed,ld) + +$(obj)/styncpy.o: $(obj)/strncpy.o $(obj)/$(ev67-y)strncat.o \ + $(obj)/$(ev6-y)stxncpy.o FORCE + $(call if_changed,ld) diff --git a/arch/alpha/lib/copy_user.S b/arch/alpha/lib/copy_user.S index 159f1b7e6e49..c277a1a4383e 100644 --- a/arch/alpha/lib/copy_user.S +++ b/arch/alpha/lib/copy_user.S @@ -34,7 +34,7 @@ .ent __copy_user __copy_user: .prologue 0 - and $18,$18,$0 + mov $18,$0 and $16,7,$3 beq $0,$35 beq $3,$36 diff --git a/arch/alpha/lib/ev6-copy_user.S b/arch/alpha/lib/ev6-copy_user.S index 35e6710d0700..954ca03ebebe 100644 --- a/arch/alpha/lib/ev6-copy_user.S +++ b/arch/alpha/lib/ev6-copy_user.S @@ -45,9 +45,10 @@ # Pipeline info: Slotting & Comments __copy_user: .prologue 0 - andq $18, $18, $0 - subq $18, 32, $1 # .. E .. .. : Is this going to be a small copy? - beq $0, $zerolength # U .. .. .. : U L U L + mov $18, $0 # .. .. .. E + subq $18, 32, $1 # .. .. E. .. : Is this going to be a small copy? + nop # .. E .. .. + beq $18, $zerolength # U .. .. .. : U L U L and $16,7,$3 # .. .. .. E : is leading dest misalignment ble $1, $onebyteloop # .. .. U .. : 1st branch : small amount of data diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index a5459698f0ee..7db85ab00c52 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -96,7 +96,6 @@ menu "ARC Architecture Configuration" menu "ARC Platform/SoC/Board" -source "arch/arc/plat-sim/Kconfig" source "arch/arc/plat-tb10x/Kconfig" source "arch/arc/plat-axs10x/Kconfig" #New platform adds here diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 44ef35d33956..3a61cfcc38c0 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -107,7 +107,7 @@ core-y += arch/arc/ # w/o this dtb won't embed into kernel binary core-y += arch/arc/boot/dts/ -core-$(CONFIG_ARC_PLAT_SIM) += arch/arc/plat-sim/ +core-y += arch/arc/plat-sim/ core-$(CONFIG_ARC_PLAT_TB10X) += arch/arc/plat-tb10x/ core-$(CONFIG_ARC_PLAT_AXS10X) += arch/arc/plat-axs10x/ core-$(CONFIG_ARC_PLAT_EZNPS) += arch/arc/plat-eznps/ diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 53ce226f77a5..a380ffa1a458 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -15,15 +15,15 @@ / { compatible = "snps,arc"; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; cpu_card { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; - ranges = <0x00000000 0xf0000000 0x10000000>; + ranges = <0x00000000 0x0 0xf0000000 0x10000000>; core_clk: core_clk { #clock-cells = <0>; @@ -91,23 +91,21 @@ mb_intc: dw-apb-ictl@0xe0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; - reg = < 0xe0012000 0x200 >; + reg = < 0x0 0xe0012000 0x0 0x200 >; interrupt-controller; interrupt-parent = <&core_intc>; interrupts = < 7 >; }; memory { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x00000000 0x80000000 0x20000000>; device_type = "memory"; - reg = <0x80000000 0x1b000000>; /* (512 - 32) MiB */ + /* CONFIG_KERNEL_RAM_BASE_ADDRESS needs to match low mem start */ + reg = <0x0 0x80000000 0x0 0x1b000000>; /* (512 - 32) MiB */ }; reserved-memory { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; ranges; /* * We just move frame buffer area to the very end of @@ -118,7 +116,7 @@ */ frame_buffer: frame_buffer@9e000000 { compatible = "shared-dma-pool"; - reg = <0x9e000000 0x2000000>; + reg = <0x0 0x9e000000 0x0 0x2000000>; no-map; }; }; diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index 14df46f141bf..cc9239ef8d08 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -14,15 +14,15 @@ / { compatible = "snps,arc"; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; cpu_card { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; - ranges = <0x00000000 0xf0000000 0x10000000>; + ranges = <0x00000000 0x0 0xf0000000 0x10000000>; core_clk: core_clk { #clock-cells = <0>; @@ -94,30 +94,29 @@ mb_intc: dw-apb-ictl@0xe0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; - reg = < 0xe0012000 0x200 >; + reg = < 0x0 0xe0012000 0x0 0x200 >; interrupt-controller; interrupt-parent = <&core_intc>; interrupts = < 24 >; }; memory { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x00000000 0x80000000 0x40000000>; device_type = "memory"; - reg = <0x80000000 0x20000000>; /* 512MiB */ + /* CONFIG_KERNEL_RAM_BASE_ADDRESS needs to match low mem start */ + reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MiB low mem */ + 0x1 0xc0000000 0x0 0x40000000>; /* 1 GiB highmem */ }; reserved-memory { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; ranges; /* * Move frame buffer out of IOC aperture (0x8z-0xAz). */ frame_buffer: frame_buffer@be000000 { compatible = "shared-dma-pool"; - reg = <0xbe000000 0x2000000>; + reg = <0x0 0xbe000000 0x0 0x2000000>; no-map; }; }; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 695f9fa1996b..4ebb2170abec 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -14,15 +14,15 @@ / { compatible = "snps,arc"; - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; cpu_card { compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; - ranges = <0x00000000 0xf0000000 0x10000000>; + ranges = <0x00000000 0x0 0xf0000000 0x10000000>; core_clk: core_clk { #clock-cells = <0>; @@ -100,30 +100,29 @@ mb_intc: dw-apb-ictl@0xe0012000 { #interrupt-cells = <1>; compatible = "snps,dw-apb-ictl"; - reg = < 0xe0012000 0x200 >; + reg = < 0x0 0xe0012000 0x0 0x200 >; interrupt-controller; interrupt-parent = <&idu_intc>; interrupts = <0>; }; memory { - #address-cells = <1>; - #size-cells = <1>; - ranges = <0x00000000 0x80000000 0x40000000>; device_type = "memory"; - reg = <0x80000000 0x20000000>; /* 512MiB */ + /* CONFIG_KERNEL_RAM_BASE_ADDRESS needs to match low mem start */ + reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MiB low mem */ + 0x1 0xc0000000 0x0 0x40000000>; /* 1 GiB highmem */ }; reserved-memory { - #address-cells = <1>; - #size-cells = <1>; + #address-cells = <2>; + #size-cells = <2>; ranges; /* * Move frame buffer out of IOC aperture (0x8z-0xAz). */ frame_buffer: frame_buffer@be000000 { compatible = "shared-dma-pool"; - reg = <0xbe000000 0x2000000>; + reg = <0x0 0xbe000000 0x0 0x2000000>; no-map; }; }; diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 41cfb29b62c1..0ff7e07edcd4 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -13,7 +13,7 @@ compatible = "simple-bus"; #address-cells = <1>; #size-cells = <1>; - ranges = <0x00000000 0xe0000000 0x10000000>; + ranges = <0x00000000 0x0 0xe0000000 0x10000000>; interrupt-parent = <&mb_intc>; i2sclk: i2sclk@100a0 { diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 57b3e599322f..db04ea4dd2d9 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -21,7 +21,6 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ISA_ARCV2=y CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs" CONFIG_PREEMPT=y diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index f85985adebb2..821a2e562f3f 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -23,7 +23,6 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y CONFIG_ARC_BUILTIN_DTB_NAME="haps_hs_idu" diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index ede625c76216..7c9c706ae7f6 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -39,7 +39,6 @@ CONFIG_IP_PNP=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index b0066a749d4c..6dff83a238b8 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -23,7 +23,6 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index ebe9ebb92933..31ee51b987e7 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -26,7 +26,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ISA_ARCV2=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs" CONFIG_PREEMPT=y diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 4bde43278be6..8d3b1f67cae4 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -24,7 +24,6 @@ CONFIG_MODULE_FORCE_UNLOAD=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu" diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index f6fb3d26557e..6168ce2ac2ef 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -23,7 +23,6 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci" # CONFIG_COMPACTION is not set CONFIG_NET=y diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index b9f0fe00044b..a70bdeb2b3fd 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -23,7 +23,6 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ISA_ARCV2=y CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs" # CONFIG_COMPACTION is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 155add7761ed..ef96406c446e 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -18,7 +18,6 @@ CONFIG_MODULES=y # CONFIG_BLK_DEV_BSG is not set # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set -CONFIG_ARC_PLAT_SIM=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y # CONFIG_ARC_TIMERS_64BIT is not set diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 4c5118384eb5..f30182549395 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -38,7 +38,6 @@ CONFIG_IP_MULTICAST=y # CONFIG_INET_XFRM_MODE_TRANSPORT is not set # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set -# CONFIG_INET_LRO is not set # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h index 19ebddffb279..02fd1cece6ef 100644 --- a/arch/arc/include/asm/cache.h +++ b/arch/arc/include/asm/cache.h @@ -96,7 +96,9 @@ extern unsigned long perip_base, perip_end; #define ARC_REG_SLC_FLUSH 0x904 #define ARC_REG_SLC_INVALIDATE 0x905 #define ARC_REG_SLC_RGN_START 0x914 +#define ARC_REG_SLC_RGN_START1 0x915 #define ARC_REG_SLC_RGN_END 0x916 +#define ARC_REG_SLC_RGN_END1 0x917 /* Bit val in SLC_CONTROL */ #define SLC_CTRL_DIS 0x001 diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h index db7319e9b506..efb79fafff1d 100644 --- a/arch/arc/include/asm/mmu.h +++ b/arch/arc/include/asm/mmu.h @@ -94,6 +94,8 @@ static inline int is_pae40_enabled(void) return IS_ENABLED(CONFIG_ARC_HAS_PAE40); } +extern int pae40_exist_but_not_enab(void); + #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c index f928795fd07a..067ea362fb3e 100644 --- a/arch/arc/kernel/intc-arcv2.c +++ b/arch/arc/kernel/intc-arcv2.c @@ -75,10 +75,20 @@ void arc_init_IRQ(void) * Set a default priority for all available interrupts to prevent * switching of register banks if Fast IRQ and multiple register banks * are supported by CPU. + * Also disable private-per-core IRQ lines so faulty external HW won't + * trigger interrupt that kernel is not ready to handle. */ for (i = NR_EXCEPTIONS; i < irq_bcr.irqs + NR_EXCEPTIONS; i++) { write_aux_reg(AUX_IRQ_SELECT, i); write_aux_reg(AUX_IRQ_PRIORITY, ARCV2_IRQ_DEF_PRIO); + + /* + * Only mask cpu private IRQs here. + * "common" interrupts are masked at IDU, otherwise it would + * need to be unmasked at each cpu, with IPIs + */ + if (i < FIRST_EXT_IRQ) + write_aux_reg(AUX_IRQ_ENABLE, 0); } /* setup status32, don't enable intr yet as kernel doesn't want */ diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index 7e608c6b0a01..47b421fa0147 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -27,7 +27,7 @@ */ void arc_init_IRQ(void) { - int level_mask = 0; + unsigned int level_mask = 0, i; /* Is timer high priority Interrupt (Level2 in ARCompact jargon) */ level_mask |= IS_ENABLED(CONFIG_ARC_COMPACT_IRQ_LEVELS) << TIMER0_IRQ; @@ -40,6 +40,18 @@ void arc_init_IRQ(void) if (level_mask) pr_info("Level-2 interrupts bitset %x\n", level_mask); + + /* + * Disable all IRQ lines so faulty external hardware won't + * trigger interrupt that kernel is not ready to handle. + */ + for (i = TIMER0_IRQ; i < NR_CPU_IRQS; i++) { + unsigned int ienb; + + ienb = read_aux_reg(AUX_IENABLE); + ienb &= ~(1 << i); + write_aux_reg(AUX_IENABLE, ienb); + } } /* diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index a867575a758b..7db283b46ebd 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -665,6 +665,7 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op) static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned int ctrl; + phys_addr_t end; spin_lock_irqsave(&lock, flags); @@ -694,8 +695,19 @@ noinline void slc_op(phys_addr_t paddr, unsigned long sz, const int op) * END needs to be setup before START (latter triggers the operation) * END can't be same as START, so add (l2_line_sz - 1) to sz */ - write_aux_reg(ARC_REG_SLC_RGN_END, (paddr + sz + l2_line_sz - 1)); - write_aux_reg(ARC_REG_SLC_RGN_START, paddr); + end = paddr + sz + l2_line_sz - 1; + if (is_pae40_enabled()) + write_aux_reg(ARC_REG_SLC_RGN_END1, upper_32_bits(end)); + + write_aux_reg(ARC_REG_SLC_RGN_END, lower_32_bits(end)); + + if (is_pae40_enabled()) + write_aux_reg(ARC_REG_SLC_RGN_START1, upper_32_bits(paddr)); + + write_aux_reg(ARC_REG_SLC_RGN_START, lower_32_bits(paddr)); + + /* Make sure "busy" bit reports correct stataus, see STAR 9001165532 */ + read_aux_reg(ARC_REG_SLC_CTRL); while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY); @@ -1111,6 +1123,13 @@ noinline void __init arc_ioc_setup(void) __dc_enable(); } +/* + * Cache related boot time checks/setups only needed on master CPU: + * - Geometry checks (kernel build and hardware agree: e.g. L1_CACHE_BYTES) + * Assume SMP only, so all cores will have same cache config. A check on + * one core suffices for all + * - IOC setup / dma callbacks only need to be done once + */ void __init arc_cache_init_master(void) { unsigned int __maybe_unused cpu = smp_processor_id(); @@ -1190,12 +1209,27 @@ void __ref arc_cache_init(void) printk(arc_cache_mumbojumbo(0, str, sizeof(str))); - /* - * Only master CPU needs to execute rest of function: - * - Assume SMP so all cores will have same cache config so - * any geomtry checks will be same for all - * - IOC setup / dma callbacks only need to be setup once - */ if (!cpu) arc_cache_init_master(); + + /* + * In PAE regime, TLB and cache maintenance ops take wider addresses + * And even if PAE is not enabled in kernel, the upper 32-bits still need + * to be zeroed to keep the ops sane. + * As an optimization for more common !PAE enabled case, zero them out + * once at init, rather than checking/setting to 0 for every runtime op + */ + if (is_isa_arcv2() && pae40_exist_but_not_enab()) { + + if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) + write_aux_reg(ARC_REG_IC_PTAG_HI, 0); + + if (IS_ENABLED(CONFIG_ARC_HAS_DCACHE)) + write_aux_reg(ARC_REG_DC_PTAG_HI, 0); + + if (l2_line_sz) { + write_aux_reg(ARC_REG_SLC_RGN_END1, 0); + write_aux_reg(ARC_REG_SLC_RGN_START1, 0); + } + } } diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index 71d3efff99d3..e9d93604ad0f 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -153,6 +153,19 @@ static void _dma_cache_sync(phys_addr_t paddr, size_t size, } } +/* + * arc_dma_map_page - map a portion of a page for streaming DMA + * + * Ensure that any data held in the cache is appropriately discarded + * or written back. + * + * The device owns this memory once this call has completed. The CPU + * can regain ownership by calling dma_unmap_page(). + * + * Note: while it takes struct page as arg, caller can "abuse" it to pass + * a region larger than PAGE_SIZE, provided it is physically contiguous + * and this still works correctly + */ static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction dir, unsigned long attrs) @@ -165,6 +178,24 @@ static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page, return plat_phys_to_dma(dev, paddr); } +/* + * arc_dma_unmap_page - unmap a buffer previously mapped through dma_map_page() + * + * After this call, reads by the CPU to the buffer are guaranteed to see + * whatever the device wrote there. + * + * Note: historically this routine was not implemented for ARC + */ +static void arc_dma_unmap_page(struct device *dev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + phys_addr_t paddr = plat_dma_to_phys(dev, handle); + + if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC)) + _dma_cache_sync(paddr, size, dir); +} + static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction dir, unsigned long attrs) { @@ -178,6 +209,18 @@ static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg, return nents; } +static void arc_dma_unmap_sg(struct device *dev, struct scatterlist *sg, + int nents, enum dma_data_direction dir, + unsigned long attrs) +{ + struct scatterlist *s; + int i; + + for_each_sg(sg, s, nents, i) + arc_dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, + attrs); +} + static void arc_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction dir) { @@ -223,7 +266,9 @@ const struct dma_map_ops arc_dma_ops = { .free = arc_dma_free, .mmap = arc_dma_mmap, .map_page = arc_dma_map_page, + .unmap_page = arc_dma_unmap_page, .map_sg = arc_dma_map_sg, + .unmap_sg = arc_dma_unmap_sg, .sync_single_for_device = arc_dma_sync_single_for_device, .sync_single_for_cpu = arc_dma_sync_single_for_cpu, .sync_sg_for_cpu = arc_dma_sync_sg_for_cpu, diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index d0126fdfe2d8..b181f3ee38aa 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -104,6 +104,8 @@ /* A copy of the ASID from the PID reg is kept in asid_cache */ DEFINE_PER_CPU(unsigned int, asid_cache) = MM_CTXT_FIRST_CYCLE; +static int __read_mostly pae_exists; + /* * Utility Routine to erase a J-TLB entry * Caller needs to setup Index Reg (manually or via getIndex) @@ -784,7 +786,7 @@ void read_decode_mmu_bcr(void) mmu->u_dtlb = mmu4->u_dtlb * 4; mmu->u_itlb = mmu4->u_itlb * 4; mmu->sasid = mmu4->sasid; - mmu->pae = mmu4->pae; + pae_exists = mmu->pae = mmu4->pae; } } @@ -809,6 +811,11 @@ char *arc_mmu_mumbojumbo(int cpu_id, char *buf, int len) return buf; } +int pae40_exist_but_not_enab(void) +{ + return pae_exists && !is_pae40_enabled(); +} + void arc_mmu_init(void) { char str[256]; @@ -859,6 +866,9 @@ void arc_mmu_init(void) /* swapper_pg_dir is the pgd for the kernel, used by vmalloc */ write_aux_reg(ARC_REG_SCRATCH_DATA0, swapper_pg_dir); #endif + + if (pae40_exist_but_not_enab()) + write_aux_reg(ARC_REG_TLBPD1HI, 0); } /* diff --git a/arch/arc/plat-sim/Kconfig b/arch/arc/plat-sim/Kconfig deleted file mode 100644 index ac6af96a82f3..000000000000 --- a/arch/arc/plat-sim/Kconfig +++ /dev/null @@ -1,13 +0,0 @@ -# -# Copyright (C) 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License version 2 as -# published by the Free Software Foundation. -# - -menuconfig ARC_PLAT_SIM - bool "ARC nSIM based simulation virtual platforms" - help - Support for nSIM based ARC simulation platforms - This includes the standalone nSIM (uart only) vs. System C OSCI VP diff --git a/arch/arc/plat-sim/platform.c b/arch/arc/plat-sim/platform.c index aea87389e44b..5cda56b1a2ea 100644 --- a/arch/arc/plat-sim/platform.c +++ b/arch/arc/plat-sim/platform.c @@ -20,11 +20,14 @@ */ static const char *simulation_compat[] __initconst = { +#ifdef CONFIG_ISA_ARCOMPACT "snps,nsim", - "snps,nsim_hs", "snps,nsimosci", +#else + "snps,nsim_hs", "snps,nsimosci_hs", "snps,zebu_hs", +#endif NULL, }; diff --git a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi index f92f95741207..a183b56283f8 100644 --- a/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi +++ b/arch/arm/boot/dts/exynos5422-odroidxu3-common.dtsi @@ -266,6 +266,7 @@ &hdmicec { status = "okay"; + needs-hpd; }; &hsi2c_4 { diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index dfcc8e00cf1c..0ade3619f3c3 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -297,6 +297,7 @@ #address-cells = <1>; #size-cells = <1>; status = "disabled"; + ranges; adc: adc@50030800 { compatible = "fsl,imx25-gcq"; diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi index aeaa5a6e4fcf..a24e4f1911ab 100644 --- a/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi +++ b/arch/arm/boot/dts/imx6qdl-nitrogen6_som2.dtsi @@ -507,7 +507,7 @@ pinctrl_pcie: pciegrp { fsl,pins = < /* PCIe reset */ - MX6QDL_PAD_EIM_BCLK__GPIO6_IO31 0x030b0 + MX6QDL_PAD_EIM_DA0__GPIO3_IO00 0x030b0 MX6QDL_PAD_EIM_DA4__GPIO3_IO04 0x030b0 >; }; @@ -668,7 +668,7 @@ &pcie { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pcie>; - reset-gpio = <&gpio6 31 GPIO_ACTIVE_LOW>; + reset-gpio = <&gpio3 0 GPIO_ACTIVE_LOW>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts index 54c45402286b..0a24d1bf3c39 100644 --- a/arch/arm/boot/dts/imx7d-sdb.dts +++ b/arch/arm/boot/dts/imx7d-sdb.dts @@ -557,6 +557,14 @@ >; }; + pinctrl_spi4: spi4grp { + fsl,pins = < + MX7D_PAD_GPIO1_IO09__GPIO1_IO9 0x59 + MX7D_PAD_GPIO1_IO12__GPIO1_IO12 0x59 + MX7D_PAD_GPIO1_IO13__GPIO1_IO13 0x59 + >; + }; + pinctrl_tsc2046_pendown: tsc2046_pendown { fsl,pins = < MX7D_PAD_EPDC_BDR1__GPIO2_IO29 0x59 @@ -697,13 +705,5 @@ fsl,pins = < MX7D_PAD_LPSR_GPIO1_IO01__PWM1_OUT 0x110b0 >; - - pinctrl_spi4: spi4grp { - fsl,pins = < - MX7D_PAD_GPIO1_IO09__GPIO1_IO9 0x59 - MX7D_PAD_GPIO1_IO12__GPIO1_IO12 0x59 - MX7D_PAD_GPIO1_IO13__GPIO1_IO13 0x59 - >; - }; }; }; diff --git a/arch/arm/boot/dts/sama5d2.dtsi b/arch/arm/boot/dts/sama5d2.dtsi index cc06da394366..60e69aeacbdb 100644 --- a/arch/arm/boot/dts/sama5d2.dtsi +++ b/arch/arm/boot/dts/sama5d2.dtsi @@ -303,7 +303,7 @@ #size-cells = <1>; atmel,smc = <&hsmc>; reg = <0x10000000 0x10000000 - 0x40000000 0x30000000>; + 0x60000000 0x30000000>; ranges = <0x0 0x0 0x10000000 0x10000000 0x1 0x0 0x60000000 0x10000000 0x2 0x0 0x70000000 0x10000000 @@ -1048,18 +1048,18 @@ }; hsmc: hsmc@f8014000 { - compatible = "atmel,sama5d3-smc", "syscon", "simple-mfd"; + compatible = "atmel,sama5d2-smc", "syscon", "simple-mfd"; reg = <0xf8014000 0x1000>; - interrupts = <5 IRQ_TYPE_LEVEL_HIGH 6>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH 6>; clocks = <&hsmc_clk>; #address-cells = <1>; #size-cells = <1>; ranges; - pmecc: ecc-engine@ffffc070 { + pmecc: ecc-engine@f8014070 { compatible = "atmel,sama5d2-pmecc"; - reg = <0xffffc070 0x490>, - <0xffffc500 0x100>; + reg = <0xf8014070 0x490>, + <0xf8014500 0x100>; }; }; diff --git a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts index 6713d0f2b3f4..b1502df7b509 100644 --- a/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts +++ b/arch/arm/boot/dts/sun8i-h2-plus-orangepi-zero.dts @@ -56,8 +56,6 @@ aliases { serial0 = &uart0; - /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */ - ethernet0 = &emac; ethernet1 = &xr819; }; @@ -104,13 +102,6 @@ status = "okay"; }; -&emac { - phy-handle = <&int_mii_phy>; - phy-mode = "mii"; - allwinner,leds-active-low; - status = "okay"; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>; diff --git a/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts index d756ff825116..a337af1de322 100644 --- a/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-bananapi-m2-plus.dts @@ -52,7 +52,6 @@ compatible = "sinovoip,bpi-m2-plus", "allwinner,sun8i-h3"; aliases { - ethernet0 = &emac; serial0 = &uart0; serial1 = &uart1; }; @@ -115,30 +114,12 @@ status = "okay"; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&emac_rgmii_pins>; - phy-supply = <®_gmac_3v3>; - phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; - - allwinner,leds-active-low; - status = "okay"; -}; - &ir { pinctrl-names = "default"; pinctrl-0 = <&ir_pins_a>; status = "okay"; }; -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <0>; - }; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; diff --git a/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts b/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts index 78f6c24952dd..8d2cc6e9a03f 100644 --- a/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts +++ b/arch/arm/boot/dts/sun8i-h3-nanopi-neo.dts @@ -46,10 +46,3 @@ model = "FriendlyARM NanoPi NEO"; compatible = "friendlyarm,nanopi-neo", "allwinner,sun8i-h3"; }; - -&emac { - phy-handle = <&int_mii_phy>; - phy-mode = "mii"; - allwinner,leds-active-low; - status = "okay"; -}; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts index 17cdeae19c6f..8ff71b1bb45b 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-2.dts @@ -54,7 +54,6 @@ aliases { serial0 = &uart0; /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */ - ethernet0 = &emac; ethernet1 = &rtl8189; }; @@ -118,13 +117,6 @@ status = "okay"; }; -&emac { - phy-handle = <&int_mii_phy>; - phy-mode = "mii"; - allwinner,leds-active-low; - status = "okay"; -}; - &ir { pinctrl-names = "default"; pinctrl-0 = <&ir_pins_a>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts index 6880268e8b87..5fea430e0eb1 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-one.dts @@ -52,7 +52,6 @@ compatible = "xunlong,orangepi-one", "allwinner,sun8i-h3"; aliases { - ethernet0 = &emac; serial0 = &uart0; }; @@ -98,13 +97,6 @@ status = "okay"; }; -&emac { - phy-handle = <&int_mii_phy>; - phy-mode = "mii"; - allwinner,leds-active-low; - status = "okay"; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts index a10281b455f5..8b93f5c781a7 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc-plus.dts @@ -53,11 +53,6 @@ }; }; -&emac { - /* LEDs changed to active high on the plus */ - /delete-property/ allwinner,leds-active-low; -}; - &mmc1 { pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins_a>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts index 998b60f8d295..1a044b17d6c6 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dts @@ -52,7 +52,6 @@ compatible = "xunlong,orangepi-pc", "allwinner,sun8i-h3"; aliases { - ethernet0 = &emac; serial0 = &uart0; }; @@ -114,13 +113,6 @@ status = "okay"; }; -&emac { - phy-handle = <&int_mii_phy>; - phy-mode = "mii"; - allwinner,leds-active-low; - status = "okay"; -}; - &ir { pinctrl-names = "default"; pinctrl-0 = <&ir_pins_a>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts index 331ed683ac62..828ae7a526d9 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus.dts @@ -47,10 +47,6 @@ model = "Xunlong Orange Pi Plus / Plus 2"; compatible = "xunlong,orangepi-plus", "allwinner,sun8i-h3"; - aliases { - ethernet0 = &emac; - }; - reg_gmac_3v3: gmac-3v3 { compatible = "regulator-fixed"; regulator-name = "gmac-3v3"; @@ -78,24 +74,6 @@ status = "okay"; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&emac_rgmii_pins>; - phy-supply = <®_gmac_3v3>; - phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; - - allwinner,leds-active-low; - status = "okay"; -}; - -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <0>; - }; -}; - &mmc2 { pinctrl-names = "default"; pinctrl-0 = <&mmc2_8bit_pins>; diff --git a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts index 80026f3caafc..97920b12a944 100644 --- a/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts +++ b/arch/arm/boot/dts/sun8i-h3-orangepi-plus2e.dts @@ -61,19 +61,3 @@ gpio = <&pio 3 6 GPIO_ACTIVE_HIGH>; /* PD6 */ }; }; - -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&emac_rgmii_pins>; - phy-supply = <®_gmac_3v3>; - phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; - status = "okay"; -}; - -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; -}; diff --git a/arch/arm/boot/dts/sunxi-h3-h5.dtsi b/arch/arm/boot/dts/sunxi-h3-h5.dtsi index d38282b9e5d4..11240a8313c2 100644 --- a/arch/arm/boot/dts/sunxi-h3-h5.dtsi +++ b/arch/arm/boot/dts/sunxi-h3-h5.dtsi @@ -391,32 +391,6 @@ clocks = <&osc24M>; }; - emac: ethernet@1c30000 { - compatible = "allwinner,sun8i-h3-emac"; - syscon = <&syscon>; - reg = <0x01c30000 0x10000>; - interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "macirq"; - resets = <&ccu RST_BUS_EMAC>; - reset-names = "stmmaceth"; - clocks = <&ccu CLK_BUS_EMAC>; - clock-names = "stmmaceth"; - #address-cells = <1>; - #size-cells = <0>; - status = "disabled"; - - mdio: mdio { - #address-cells = <1>; - #size-cells = <0>; - int_mii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - clocks = <&ccu CLK_BUS_EPHY>; - resets = <&ccu RST_BUS_EPHY>; - }; - }; - }; - spi0: spi@01c68000 { compatible = "allwinner,sun8i-h3-spi"; reg = <0x01c68000 0x1000>; diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 127e2dd2e21c..4a879f6ff13b 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -225,12 +225,6 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -/* We do not have shadow page tables, hence the empty hooks */ -static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ -} - struct kvm_vcpu *kvm_arm_get_running_vcpu(void); struct kvm_vcpu __percpu **kvm_get_running_vcpus(void); void kvm_arm_halt_guest(struct kvm *kvm); diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index d735e5fc4772..195da38cb9a2 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -1,7 +1,7 @@ menuconfig ARCH_AT91 bool "Atmel SoCs" depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V7 || ARM_SINGLE_ARMV7M - select ARM_CPU_SUSPEND if PM + select ARM_CPU_SUSPEND if PM && ARCH_MULTI_V7 select COMMON_CLK_AT91 select GPIOLIB select PINCTRL diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c index 667fddac3856..5036f996e694 100644 --- a/arch/arm/mach-at91/pm.c +++ b/arch/arm/mach-at91/pm.c @@ -608,6 +608,9 @@ static void __init at91_pm_init(void (*pm_idle)(void)) void __init at91rm9200_pm_init(void) { + if (!IS_ENABLED(CONFIG_SOC_AT91RM9200)) + return; + at91_dt_ramc(); /* @@ -620,18 +623,27 @@ void __init at91rm9200_pm_init(void) void __init at91sam9_pm_init(void) { + if (!IS_ENABLED(CONFIG_SOC_AT91SAM9)) + return; + at91_dt_ramc(); at91_pm_init(at91sam9_idle); } void __init sama5_pm_init(void) { + if (!IS_ENABLED(CONFIG_SOC_SAMA5)) + return; + at91_dt_ramc(); at91_pm_init(NULL); } void __init sama5d2_pm_init(void) { + if (!IS_ENABLED(CONFIG_SOC_SAMA5D2)) + return; + at91_pm_backup_init(); sama5_pm_init(); } diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts index 0d1f026d831a..6872135d7f84 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-bananapi-m64.dts @@ -67,14 +67,6 @@ }; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; - phy-handle = <&ext_rgmii_phy>; - status = "okay"; -}; - &i2c1 { pinctrl-names = "default"; pinctrl-0 = <&i2c1_pins>; @@ -85,13 +77,6 @@ bias-pull-up; }; -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts index 24f1aac366d6..f82ccf332c0f 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts @@ -48,18 +48,3 @@ /* TODO: Camera, touchscreen, etc. */ }; - -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; - phy-handle = <&ext_rgmii_phy>; - status = "okay"; -}; - -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; -}; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts index 08cda24ea194..7c533b6d4ba9 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64.dts @@ -78,15 +78,6 @@ status = "okay"; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&rmii_pins>; - phy-mode = "rmii"; - phy-handle = <&ext_rmii_phy1>; - status = "okay"; - -}; - &i2c1 { pinctrl-names = "default"; pinctrl-0 = <&i2c1_pins>; @@ -97,13 +88,6 @@ bias-pull-up; }; -&mdio { - ext_rmii_phy1: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts index 17eb1cc5bf6b..d891a1a27f6c 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts @@ -76,21 +76,6 @@ status = "okay"; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&rgmii_pins>; - phy-mode = "rgmii"; - phy-handle = <&ext_rgmii_phy>; - status = "okay"; -}; - -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; -}; - &mmc2 { pinctrl-names = "default"; pinctrl-0 = <&mmc2_pins>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index bd0f33b77f57..68aadc9b96dc 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -449,26 +449,6 @@ #size-cells = <0>; }; - emac: ethernet@1c30000 { - compatible = "allwinner,sun50i-a64-emac"; - syscon = <&syscon>; - reg = <0x01c30000 0x10000>; - interrupts = <GIC_SPI 82 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "macirq"; - resets = <&ccu RST_BUS_EMAC>; - reset-names = "stmmaceth"; - clocks = <&ccu CLK_BUS_EMAC>; - clock-names = "stmmaceth"; - status = "disabled"; - #address-cells = <1>; - #size-cells = <0>; - - mdio: mdio { - #address-cells = <1>; - #size-cells = <0>; - }; - }; - gic: interrupt-controller@1c81000 { compatible = "arm,gic-400"; reg = <0x01c81000 0x1000>, diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts index 968908761194..1c2387bd5df6 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts @@ -50,7 +50,6 @@ compatible = "friendlyarm,nanopi-neo2", "allwinner,sun50i-h5"; aliases { - ethernet0 = &emac; serial0 = &uart0; }; @@ -109,22 +108,6 @@ status = "okay"; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&emac_rgmii_pins>; - phy-supply = <®_gmac_3v3>; - phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; - status = "okay"; -}; - -&mdio { - ext_rgmii_phy: ethernet-phy@7 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <7>; - }; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts index a8296feee884..4f77c8470f6c 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-pc2.dts @@ -59,7 +59,6 @@ }; aliases { - ethernet0 = &emac; serial0 = &uart0; }; @@ -137,28 +136,12 @@ status = "okay"; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&emac_rgmii_pins>; - phy-supply = <®_gmac_3v3>; - phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; - status = "okay"; -}; - &ir { pinctrl-names = "default"; pinctrl-0 = <&ir_pins_a>; status = "okay"; }; -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts index d906b302cbcd..6be06873e5af 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-orangepi-prime.dts @@ -54,7 +54,6 @@ compatible = "xunlong,orangepi-prime", "allwinner,sun50i-h5"; aliases { - ethernet0 = &emac; serial0 = &uart0; }; @@ -144,28 +143,12 @@ status = "okay"; }; -&emac { - pinctrl-names = "default"; - pinctrl-0 = <&emac_rgmii_pins>; - phy-supply = <®_gmac_3v3>; - phy-handle = <&ext_rgmii_phy>; - phy-mode = "rgmii"; - status = "okay"; -}; - &ir { pinctrl-names = "default"; pinctrl-0 = <&ir_pins_a>; status = "okay"; }; -&mdio { - ext_rgmii_phy: ethernet-phy@1 { - compatible = "ethernet-phy-ieee802.3-c22"; - reg = <1>; - }; -}; - &mmc0 { pinctrl-names = "default"; pinctrl-0 = <&mmc0_pins_a>, <&mmc0_cd_pin>; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi index 732e2e06f503..d9a720bff05d 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h5.dtsi @@ -120,5 +120,8 @@ }; &pio { + interrupts = <GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>; compatible = "allwinner,sun50i-h5-pinctrl"; }; diff --git a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi index 1eb1f1e9aac4..4d360713ed12 100644 --- a/arch/arm64/boot/dts/marvell/armada-ap806.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-ap806.dtsi @@ -268,10 +268,10 @@ ap_gpio: gpio { compatible = "marvell,armada-8k-gpio"; offset = <0x1040>; - ngpios = <19>; + ngpios = <20>; gpio-controller; #gpio-cells = <2>; - gpio-ranges = <&ap_pinctrl 0 0 19>; + gpio-ranges = <&ap_pinctrl 0 0 20>; }; }; }; diff --git a/arch/arm64/boot/dts/renesas/salvator-common.dtsi b/arch/arm64/boot/dts/renesas/salvator-common.dtsi index a451996f590a..f903957da504 100644 --- a/arch/arm64/boot/dts/renesas/salvator-common.dtsi +++ b/arch/arm64/boot/dts/renesas/salvator-common.dtsi @@ -45,7 +45,7 @@ stdout-path = "serial0:115200n8"; }; - audio_clkout: audio_clkout { + audio_clkout: audio-clkout { /* * This is same as <&rcar_sound 0> * but needed to avoid cs2000/rcar_sound probe dead-lock diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index 74d08e44a651..a652ce0a5cb2 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -65,13 +65,13 @@ DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *, u64 _val; \ if (needs_unstable_timer_counter_workaround()) { \ const struct arch_timer_erratum_workaround *wa; \ - preempt_disable(); \ + preempt_disable_notrace(); \ wa = __this_cpu_read(timer_unstable_counter_workaround); \ if (wa && wa->read_##reg) \ _val = wa->read_##reg(); \ else \ _val = read_sysreg(reg); \ - preempt_enable(); \ + preempt_enable_notrace(); \ } else { \ _val = read_sysreg(reg); \ } \ diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index acae781f7359..3288c2b36731 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -114,10 +114,10 @@ /* * This is the base location for PIE (ET_DYN with INTERP) loads. On - * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * 64-bit, this is above 4GB to leave the entire 32-bit address * space open for things that want to use the area for 32-bit pointers. */ -#define ELF_ET_DYN_BASE 0x100000000UL +#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3) #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d68630007b14..e923b58606e2 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -326,12 +326,6 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -/* We do not have shadow page tables, hence the empty hooks */ -static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ -} - struct kvm_vcpu *kvm_arm_get_running_vcpu(void); struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void); void kvm_arm_halt_guest(struct kvm *kvm); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 06da8ea16bbe..c7b4995868e1 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -161,9 +161,11 @@ void fpsimd_flush_thread(void) { if (!system_supports_fpsimd()) return; + preempt_disable(); memset(¤t->thread.fpsimd_state, 0, sizeof(struct fpsimd_state)); fpsimd_flush_task_state(current); set_thread_flag(TIF_FOREIGN_FPSTATE); + preempt_enable(); } /* diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 973df7de7bf8..adb0910b88f5 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -354,7 +354,6 @@ __primary_switched: tst x23, ~(MIN_KIMG_ALIGN - 1) // already running randomized? b.ne 0f mov x0, x21 // pass FDT address in x0 - mov x1, x23 // pass modulo offset in x1 bl kaslr_early_init // parse FDT for KASLR options cbz x0, 0f // KASLR disabled? just proceed orr x23, x23, x0 // record KASLR offset diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index a9710efb8c01..47080c49cc7e 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -75,7 +75,7 @@ extern void *__init __fixmap_remap_fdt(phys_addr_t dt_phys, int *size, * containing function pointers) to be reinitialized, and zero-initialized * .bss variables will be reset to 0. */ -u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset) +u64 __init kaslr_early_init(u64 dt_phys) { void *fdt; u64 seed, offset, mask, module_range; @@ -131,15 +131,17 @@ u64 __init kaslr_early_init(u64 dt_phys, u64 modulo_offset) /* * The kernel Image should not extend across a 1GB/32MB/512MB alignment * boundary (for 4KB/16KB/64KB granule kernels, respectively). If this - * happens, increase the KASLR offset by the size of the kernel image - * rounded up by SWAPPER_BLOCK_SIZE. + * happens, round down the KASLR offset by (1 << SWAPPER_TABLE_SHIFT). + * + * NOTE: The references to _text and _end below will already take the + * modulo offset (the physical displacement modulo 2 MB) into + * account, given that the physical placement is controlled by + * the loader, and will not change as a result of the virtual + * mapping we choose. */ - if ((((u64)_text + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT) != - (((u64)_end + offset + modulo_offset) >> SWAPPER_TABLE_SHIFT)) { - u64 kimg_sz = _end - _text; - offset = (offset + round_up(kimg_sz, SWAPPER_BLOCK_SIZE)) - & mask; - } + if ((((u64)_text + offset) >> SWAPPER_TABLE_SHIFT) != + (((u64)_end + offset) >> SWAPPER_TABLE_SHIFT)) + offset = round_down(offset, 1 << SWAPPER_TABLE_SHIFT); if (IS_ENABLED(CONFIG_KASAN)) /* diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 2509e4fe6992..1f22a41565a3 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -435,8 +435,11 @@ retry: * the mmap_sem because it would already be released * in __lock_page_or_retry in mm/filemap.c. */ - if (fatal_signal_pending(current)) + if (fatal_signal_pending(current)) { + if (!user_mode(regs)) + goto no_context; return 0; + } /* * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of diff --git a/arch/c6x/configs/dsk6455_defconfig b/arch/c6x/configs/dsk6455_defconfig index 4663487c67a1..d764ea4cce7f 100644 --- a/arch/c6x/configs/dsk6455_defconfig +++ b/arch/c6x/configs/dsk6455_defconfig @@ -1,5 +1,4 @@ CONFIG_SOC_TMS320C6455=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_SPARSE_IRQ=y @@ -25,7 +24,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_BLK_DEV_RAM_SIZE=17000 -CONFIG_MISC_DEVICES=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/c6x/configs/evmc6457_defconfig b/arch/c6x/configs/evmc6457_defconfig index bba40e195ec4..05d0b4a25ab1 100644 --- a/arch/c6x/configs/evmc6457_defconfig +++ b/arch/c6x/configs/evmc6457_defconfig @@ -1,5 +1,4 @@ CONFIG_SOC_TMS320C6457=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_SPARSE_IRQ=y @@ -26,7 +25,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_BLK_DEV_RAM_SIZE=17000 -CONFIG_MISC_DEVICES=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/c6x/configs/evmc6472_defconfig b/arch/c6x/configs/evmc6472_defconfig index 8c46155f6d31..8d81fcf86b0e 100644 --- a/arch/c6x/configs/evmc6472_defconfig +++ b/arch/c6x/configs/evmc6472_defconfig @@ -1,5 +1,4 @@ CONFIG_SOC_TMS320C6472=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_SPARSE_IRQ=y @@ -27,7 +26,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_BLK_DEV_RAM_SIZE=17000 -CONFIG_MISC_DEVICES=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/c6x/configs/evmc6474_defconfig b/arch/c6x/configs/evmc6474_defconfig index 15533f632313..8156a98f3958 100644 --- a/arch/c6x/configs/evmc6474_defconfig +++ b/arch/c6x/configs/evmc6474_defconfig @@ -1,5 +1,4 @@ CONFIG_SOC_TMS320C6474=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_SPARSE_IRQ=y @@ -27,7 +26,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_BLK_DEV_RAM_SIZE=17000 -CONFIG_MISC_DEVICES=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/c6x/configs/evmc6678_defconfig b/arch/c6x/configs/evmc6678_defconfig index 5f126d4905b1..c4f433c25b69 100644 --- a/arch/c6x/configs/evmc6678_defconfig +++ b/arch/c6x/configs/evmc6678_defconfig @@ -1,5 +1,4 @@ CONFIG_SOC_TMS320C6678=y -CONFIG_EXPERIMENTAL=y # CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_SPARSE_IRQ=y @@ -27,7 +26,6 @@ CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y CONFIG_BLK_DEV_RAM_COUNT=2 CONFIG_BLK_DEV_RAM_SIZE=17000 -CONFIG_MISC_DEVICES=y # CONFIG_INPUT is not set # CONFIG_SERIO is not set # CONFIG_VT is not set diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c index 43afc03e4125..9519fa5f97d0 100644 --- a/arch/c6x/platforms/megamod-pic.c +++ b/arch/c6x/platforms/megamod-pic.c @@ -208,14 +208,14 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np) pic = kzalloc(sizeof(struct megamod_pic), GFP_KERNEL); if (!pic) { - pr_err("%s: Could not alloc PIC structure.\n", np->full_name); + pr_err("%pOF: Could not alloc PIC structure.\n", np); return NULL; } pic->irqhost = irq_domain_add_linear(np, NR_COMBINERS * 32, &megamod_domain_ops, pic); if (!pic->irqhost) { - pr_err("%s: Could not alloc host.\n", np->full_name); + pr_err("%pOF: Could not alloc host.\n", np); goto error_free; } @@ -225,7 +225,7 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np) pic->regs = of_iomap(np, 0); if (!pic->regs) { - pr_err("%s: Could not map registers.\n", np->full_name); + pr_err("%pOF: Could not map registers.\n", np); goto error_free; } @@ -253,8 +253,8 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np) irq_data = irq_get_irq_data(irq); if (!irq_data) { - pr_err("%s: combiner-%d no irq_data for virq %d!\n", - np->full_name, i, irq); + pr_err("%pOF: combiner-%d no irq_data for virq %d!\n", + np, i, irq); continue; } @@ -265,16 +265,16 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np) * of the core priority interrupts (4 - 15). */ if (hwirq < 4 || hwirq >= NR_PRIORITY_IRQS) { - pr_err("%s: combiner-%d core irq %ld out of range!\n", - np->full_name, i, hwirq); + pr_err("%pOF: combiner-%d core irq %ld out of range!\n", + np, i, hwirq); continue; } /* record the mapping */ mapping[hwirq - 4] = i; - pr_debug("%s: combiner-%d cascading to hwirq %ld\n", - np->full_name, i, hwirq); + pr_debug("%pOF: combiner-%d cascading to hwirq %ld\n", + np, i, hwirq); cascade_data[i].pic = pic; cascade_data[i].index = i; @@ -290,8 +290,8 @@ static struct megamod_pic * __init init_megamod_pic(struct device_node *np) /* Finally, set up the MUX registers */ for (i = 0; i < NR_MUX_OUTPUTS; i++) { if (mapping[i] != IRQ_UNMAPPED) { - pr_debug("%s: setting mux %d to priority %d\n", - np->full_name, mapping[i], i + 4); + pr_debug("%pOF: setting mux %d to priority %d\n", + np, mapping[i], i + 4); set_megamod_mux(pic, mapping[i], i); } } diff --git a/arch/c6x/platforms/plldata.c b/arch/c6x/platforms/plldata.c index 755359eb6286..e8b6cc6a7b5a 100644 --- a/arch/c6x/platforms/plldata.c +++ b/arch/c6x/platforms/plldata.c @@ -436,8 +436,8 @@ void __init c64x_setup_clocks(void) err = of_property_read_u32(node, "clock-frequency", &val); if (err || val == 0) { - pr_err("%s: no clock-frequency found! Using %dMHz\n", - node->full_name, (int)val / 1000000); + pr_err("%pOF: no clock-frequency found! Using %dMHz\n", + node, (int)val / 1000000); val = 25000000; } clkin1.rate = val; diff --git a/arch/c6x/platforms/timer64.c b/arch/c6x/platforms/timer64.c index 0bd0452ded80..241a9a607193 100644 --- a/arch/c6x/platforms/timer64.c +++ b/arch/c6x/platforms/timer64.c @@ -204,14 +204,14 @@ void __init timer64_init(void) timer = of_iomap(np, 0); if (!timer) { - pr_debug("%s: Cannot map timer registers.\n", np->full_name); + pr_debug("%pOF: Cannot map timer registers.\n", np); goto out; } - pr_debug("%s: Timer registers=%p.\n", np->full_name, timer); + pr_debug("%pOF: Timer registers=%p.\n", np, timer); cd->irq = irq_of_parse_and_map(np, 0); if (cd->irq == NO_IRQ) { - pr_debug("%s: Cannot find interrupt.\n", np->full_name); + pr_debug("%pOF: Cannot find interrupt.\n", np); iounmap(timer); goto out; } @@ -229,7 +229,7 @@ void __init timer64_init(void) dscr_set_devstate(timer64_devstate_id, DSCR_DEVSTATE_ENABLED); } - pr_debug("%s: Timer irq=%d.\n", np->full_name, cd->irq); + pr_debug("%pOF: Timer irq=%d.\n", np, cd->irq); clockevents_calc_mult_shift(cd, c6x_core_freq / TIMER_DIVISOR, 5); diff --git a/arch/m32r/include/asm/flat.h b/arch/m32r/include/asm/flat.h index 455ce7ddbf14..dfcb0e4eb256 100644 --- a/arch/m32r/include/asm/flat.h +++ b/arch/m32r/include/asm/flat.h @@ -95,7 +95,7 @@ static inline unsigned long m32r_flat_get_addr_from_rp (u32 *rp, return ~0; /* bogus value */ } -static inline void flat_put_addr_at_rp(u32 *rp, u32 addr, u32 relval) +static inline int flat_put_addr_at_rp(u32 *rp, u32 addr, u32 relval) { unsigned int reloc = flat_m32r_get_reloc_type (relval); if (reloc & 0xf0) { @@ -133,6 +133,7 @@ static inline void flat_put_addr_at_rp(u32 *rp, u32 addr, u32 relval) break; } } + return 0; } // kludge - text_len is a local variable in the only user. diff --git a/arch/microblaze/include/asm/flat.h b/arch/microblaze/include/asm/flat.h index f23c3d266bae..3d2747d4c967 100644 --- a/arch/microblaze/include/asm/flat.h +++ b/arch/microblaze/include/asm/flat.h @@ -60,7 +60,7 @@ static inline int flat_get_addr_from_rp(u32 __user *rp, u32 relval, u32 flags, * unaligned. */ -static inline void +static inline int flat_put_addr_at_rp(u32 __user *rp, u32 addr, u32 relval) { u32 *p = (__force u32 *)rp; diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 2998479fd4e8..a9af1d2dcd69 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -938,11 +938,6 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ -} - /* Emulation */ int kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu, u32 *out); enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause); diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index 6dd13641a418..1395654cfc8d 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -872,15 +872,13 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall) if (unlikely(test_thread_flag(TIF_SECCOMP))) { int ret, i; struct seccomp_data sd; + unsigned long args[6]; sd.nr = syscall; sd.arch = syscall_get_arch(); - for (i = 0; i < 6; i++) { - unsigned long v, r; - - r = mips_get_syscall_arg(&v, current, regs, i); - sd.args[i] = r ? 0 : v; - } + syscall_get_arguments(current, regs, 0, 6, args); + for (i = 0; i < 6; i++) + sd.args[i] = args[i]; sd.instruction_pointer = KSTK_EIP(current); ret = __secure_computing(&sd); diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S index 27c2f90eeb21..a9a7d78803cd 100644 --- a/arch/mips/kernel/scall32-o32.S +++ b/arch/mips/kernel/scall32-o32.S @@ -190,12 +190,6 @@ illegal_syscall: sll t1, t0, 2 beqz v0, einval lw t2, sys_call_table(t1) # syscall routine - sw a0, PT_R2(sp) # call routine directly on restart - - /* Some syscalls like execve get their arguments from struct pt_regs - and claim zero arguments in the syscall table. Thus we have to - assume the worst case and shuffle around all potential arguments. - If you want performance, don't use indirect syscalls. */ move a0, a1 # shift argument registers move a1, a2 @@ -207,11 +201,6 @@ illegal_syscall: sw t4, 16(sp) sw t5, 20(sp) sw t6, 24(sp) - sw a0, PT_R4(sp) # .. and push back a0 - a3, some - sw a1, PT_R5(sp) # syscalls expect them there - sw a2, PT_R6(sp) - sw a3, PT_R7(sp) - sw a3, PT_R26(sp) # update a3 for syscall restarting jr t2 /* Unreached */ diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S index c30bc520885f..9ebe3e2403b1 100644 --- a/arch/mips/kernel/scall64-o32.S +++ b/arch/mips/kernel/scall64-o32.S @@ -198,7 +198,6 @@ LEAF(sys32_syscall) dsll t1, t0, 3 beqz v0, einval ld t2, sys32_call_table(t1) # syscall routine - sd a0, PT_R2(sp) # call routine directly on restart move a0, a1 # shift argument registers move a1, a2 @@ -207,11 +206,6 @@ LEAF(sys32_syscall) move a4, a5 move a5, a6 move a6, a7 - sd a0, PT_R4(sp) # ... and push back a0 - a3, some - sd a1, PT_R5(sp) # syscalls expect them there - sd a2, PT_R6(sp) - sd a3, PT_R7(sp) - sd a3, PT_R26(sp) # update a3 for syscall restarting jr t2 /* Unreached */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 36f858c37ca7..81b0031f909f 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -199,7 +199,7 @@ config PPC select HAVE_OPTPROBES if PPC64 select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI if PPC64 - select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE if SMP diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 8b3f1238d07f..e372ed871c51 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -67,11 +67,6 @@ extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); -static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ -} - #define HPTEG_CACHE_NUM (1 << 15) #define HPTEG_HASH_BITS_PTE 13 #define HPTEG_HASH_BITS_PTE_LONG 12 diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h index 0c76675394c5..35bec1c5bd5a 100644 --- a/arch/powerpc/include/asm/mmu_context.h +++ b/arch/powerpc/include/asm/mmu_context.h @@ -90,6 +90,24 @@ static inline void switch_mm_irqs_off(struct mm_struct *prev, /* Mark this context has been used on the new CPU */ if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(next))) { cpumask_set_cpu(smp_processor_id(), mm_cpumask(next)); + + /* + * This full barrier orders the store to the cpumask above vs + * a subsequent operation which allows this CPU to begin loading + * translations for next. + * + * When using the radix MMU that operation is the load of the + * MMU context id, which is then moved to SPRN_PID. + * + * For the hash MMU it is either the first load from slb_cache + * in switch_slb(), and/or the store of paca->mm_ctx_id in + * copy_mm_to_paca(). + * + * On the read side the barrier is in pte_xchg(), which orders + * the store to the PTE vs the load of mm_cpumask. + */ + smp_mb(); + new_on_cpu = true; } diff --git a/arch/powerpc/include/asm/pgtable-be-types.h b/arch/powerpc/include/asm/pgtable-be-types.h index 9c0f5db5cf46..67e7e3d990f4 100644 --- a/arch/powerpc/include/asm/pgtable-be-types.h +++ b/arch/powerpc/include/asm/pgtable-be-types.h @@ -87,6 +87,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) unsigned long *p = (unsigned long *)ptep; __be64 prev; + /* See comment in switch_mm_irqs_off() */ prev = (__force __be64)__cmpxchg_u64(p, (__force unsigned long)pte_raw(old), (__force unsigned long)pte_raw(new)); diff --git a/arch/powerpc/include/asm/pgtable-types.h b/arch/powerpc/include/asm/pgtable-types.h index 8bd3b13fe2fb..369a164b545c 100644 --- a/arch/powerpc/include/asm/pgtable-types.h +++ b/arch/powerpc/include/asm/pgtable-types.h @@ -62,6 +62,7 @@ static inline bool pte_xchg(pte_t *ptep, pte_t old, pte_t new) { unsigned long *p = (unsigned long *)ptep; + /* See comment in switch_mm_irqs_off() */ return pte_val(old) == __cmpxchg_u64(p, pte_val(old), pte_val(new)); } #endif diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index ec480966f9bf..1f0fd361e09b 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -362,7 +362,8 @@ void enable_kernel_vsx(void) cpumsr = msr_check_and_set(MSR_FP|MSR_VEC|MSR_VSX); - if (current->thread.regs && (current->thread.regs->msr & MSR_VSX)) { + if (current->thread.regs && + (current->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP))) { check_if_tm_restore_required(current); /* * If a thread has already been reclaimed then the @@ -386,7 +387,7 @@ void flush_vsx_to_thread(struct task_struct *tsk) { if (tsk->thread.regs) { preempt_disable(); - if (tsk->thread.regs->msr & MSR_VSX) { + if (tsk->thread.regs->msr & (MSR_VSX|MSR_VEC|MSR_FP)) { BUG_ON(tsk != current); giveup_vsx(tsk); } diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index a160c14304eb..53766e2bc029 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -294,32 +294,26 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, struct kvm_create_spapr_tce_64 *args) { struct kvmppc_spapr_tce_table *stt = NULL; + struct kvmppc_spapr_tce_table *siter; unsigned long npages, size; int ret = -ENOMEM; int i; + int fd = -1; if (!args->size) return -EINVAL; - /* Check this LIOBN hasn't been previously allocated */ - list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) { - if (stt->liobn == args->liobn) - return -EBUSY; - } - size = _ALIGN_UP(args->size, PAGE_SIZE >> 3); npages = kvmppc_tce_pages(size); ret = kvmppc_account_memlimit(kvmppc_stt_pages(npages), true); - if (ret) { - stt = NULL; - goto fail; - } + if (ret) + return ret; ret = -ENOMEM; stt = kzalloc(sizeof(*stt) + npages * sizeof(struct page *), GFP_KERNEL); if (!stt) - goto fail; + goto fail_acct; stt->liobn = args->liobn; stt->page_shift = args->page_shift; @@ -334,24 +328,42 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, goto fail; } - kvm_get_kvm(kvm); + ret = fd = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, + stt, O_RDWR | O_CLOEXEC); + if (ret < 0) + goto fail; mutex_lock(&kvm->lock); - list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); + + /* Check this LIOBN hasn't been previously allocated */ + ret = 0; + list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) { + if (siter->liobn == args->liobn) { + ret = -EBUSY; + break; + } + } + + if (!ret) { + list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables); + kvm_get_kvm(kvm); + } mutex_unlock(&kvm->lock); - return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, - stt, O_RDWR | O_CLOEXEC); + if (!ret) + return fd; -fail: - if (stt) { - for (i = 0; i < npages; i++) - if (stt->pages[i]) - __free_page(stt->pages[i]); + put_unused_fd(fd); - kfree(stt); - } + fail: + for (i = 0; i < npages; i++) + if (stt->pages[i]) + __free_page(stt->pages[i]); + + kfree(stt); + fail_acct: + kvmppc_account_memlimit(kvmppc_stt_pages(npages), false); return ret; } diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index c52184a8efdf..9c9c983b864f 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1291,6 +1291,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR) /* Hypervisor doorbell - exit only if host IPI flag set */ cmpwi r12, BOOK3S_INTERRUPT_H_DOORBELL bne 3f +BEGIN_FTR_SECTION + PPC_MSGSYNC +END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) lbz r0, HSTATE_HOST_IPI(r13) cmpwi r0, 0 beq 4f diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c index 4636ca6e7d38..d1ed2c41b5d2 100644 --- a/arch/powerpc/kvm/book3s_xive_template.c +++ b/arch/powerpc/kvm/book3s_xive_template.c @@ -16,7 +16,22 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc) u8 cppr; u16 ack; - /* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */ + /* + * Ensure any previous store to CPPR is ordered vs. + * the subsequent loads from PIPR or ACK. + */ + eieio(); + + /* + * DD1 bug workaround: If PIPR is less favored than CPPR + * ignore the interrupt or we might incorrectly lose an IPB + * bit. + */ + if (cpu_has_feature(CPU_FTR_POWER9_DD1)) { + u8 pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR); + if (pipr >= xc->hw_cppr) + return; + } /* Perform the acknowledge OS to register cycle. */ ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG)); @@ -235,6 +250,11 @@ skip_ipi: /* * If we found an interrupt, adjust what the guest CPPR should * be as if we had just fetched that interrupt from HW. + * + * Note: This can only make xc->cppr smaller as the previous + * loop will only exit with hirq != 0 if prio is lower than + * the current xc->cppr. Thus we don't need to re-check xc->mfrr + * for pending IPIs. */ if (hirq) xc->cppr = prio; @@ -381,6 +401,12 @@ X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr) xc->cppr = cppr; /* + * Order the above update of xc->cppr with the subsequent + * read of xc->mfrr inside push_pending_to_hw() + */ + smp_mb(); + + /* * We are masking less, we need to look for pending things * to deliver and set VP pending bits accordingly to trigger * a new interrupt otherwise we might miss MFRR changes for @@ -420,21 +446,37 @@ X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr) * used to signal MFRR changes is EOId when fetched from * the queue. */ - if (irq == XICS_IPI || irq == 0) + if (irq == XICS_IPI || irq == 0) { + /* + * This barrier orders the setting of xc->cppr vs. + * subsquent test of xc->mfrr done inside + * scan_interrupts and push_pending_to_hw + */ + smp_mb(); goto bail; + } /* Find interrupt source */ sb = kvmppc_xive_find_source(xive, irq, &src); if (!sb) { pr_devel(" source not found !\n"); rc = H_PARAMETER; + /* Same as above */ + smp_mb(); goto bail; } state = &sb->irq_state[src]; kvmppc_xive_select_irq(state, &hw_num, &xd); state->in_eoi = true; - mb(); + + /* + * This barrier orders both setting of in_eoi above vs, + * subsequent test of guest_priority, and the setting + * of xc->cppr vs. subsquent test of xc->mfrr done inside + * scan_interrupts and push_pending_to_hw + */ + smp_mb(); again: if (state->guest_priority == MASKED) { @@ -461,6 +503,14 @@ again: } + /* + * This barrier orders the above guest_priority check + * and spin_lock/unlock with clearing in_eoi below. + * + * It also has to be a full mb() as it must ensure + * the MMIOs done in source_eoi() are completed before + * state->in_eoi is visible. + */ mb(); state->in_eoi = false; bail: @@ -495,6 +545,18 @@ X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server, /* Locklessly write over MFRR */ xc->mfrr = mfrr; + /* + * The load of xc->cppr below and the subsequent MMIO store + * to the IPI must happen after the above mfrr update is + * globally visible so that: + * + * - Synchronize with another CPU doing an H_EOI or a H_CPPR + * updating xc->cppr then reading xc->mfrr. + * + * - The target of the IPI sees the xc->mfrr update + */ + mb(); + /* Shoot the IPI if most favored than target cppr */ if (mfrr < xc->cppr) __x_writeq(0, __x_trig_page(&xc->vp_ipi_data)); diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c index b5d960d6db3d..4c7b8591f737 100644 --- a/arch/powerpc/platforms/powernv/npu-dma.c +++ b/arch/powerpc/platforms/powernv/npu-dma.c @@ -614,15 +614,6 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn, mmio_invalidate(npu_context, 1, address, true); } -static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - struct npu_context *npu_context = mn_to_npu_context(mn); - - mmio_invalidate(npu_context, 1, address, true); -} - static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) @@ -640,7 +631,6 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn, static const struct mmu_notifier_ops nv_nmmu_notifier_ops = { .release = pnv_npu2_mn_release, .change_pte = pnv_npu2_mn_change_pte, - .invalidate_page = pnv_npu2_mn_invalidate_page, .invalidate_range = pnv_npu2_mn_invalidate_range, }; diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h index b9300f8aee10..07a82bc933a7 100644 --- a/arch/s390/include/asm/compat.h +++ b/arch/s390/include/asm/compat.h @@ -8,11 +8,12 @@ #include <linux/sched/task_stack.h> #include <linux/thread_info.h> -#define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p(typeof(0?(t)0:0ULL), u64)) +#define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p( \ + typeof(0?(__force t)0:0ULL), u64)) #define __SC_DELOUSE(t,v) ({ \ BUILD_BUG_ON(sizeof(t) > 4 && !__TYPE_IS_PTR(t)); \ - (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v)); \ + (__force t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v)); \ }) #define PSW32_MASK_PER 0x40000000UL diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 4541ac44b35f..24bc41622a98 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -44,6 +44,11 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | _ASCE_TYPE_REGION3; break; + case -PAGE_SIZE: + /* forked 5-level task, set new asce with new_mm->pgd */ + mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | + _ASCE_USER_BITS | _ASCE_TYPE_REGION1; + break; case 1UL << 53: /* forked 4-level task, set new asce with new mm->pgd */ mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH | diff --git a/arch/s390/kvm/sthyi.c b/arch/s390/kvm/sthyi.c index 926b5244263e..a2e5c24f47a7 100644 --- a/arch/s390/kvm/sthyi.c +++ b/arch/s390/kvm/sthyi.c @@ -394,7 +394,7 @@ static int sthyi(u64 vaddr) "srl %[cc],28\n" : [cc] "=d" (cc) : [code] "d" (code), [addr] "a" (addr) - : "memory", "cc"); + : "3", "memory", "cc"); return cc; } @@ -425,7 +425,7 @@ int handle_sthyi(struct kvm_vcpu *vcpu) VCPU_EVENT(vcpu, 3, "STHYI: fc: %llu addr: 0x%016llx", code, addr); trace_kvm_s390_handle_sthyi(vcpu, code, addr); - if (reg1 == reg2 || reg1 & 1 || reg2 & 1 || addr & ~PAGE_MASK) + if (reg1 == reg2 || reg1 & 1 || reg2 & 1) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); if (code & 0xffff) { @@ -433,6 +433,9 @@ int handle_sthyi(struct kvm_vcpu *vcpu) goto out; } + if (addr & ~PAGE_MASK) + return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); + /* * If the page has not yet been faulted in, we want to do that * now and not after all the expensive calculations. diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 2e10d2b8ad35..5bea139517a2 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -119,7 +119,8 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, return addr; check_asce_limit: - if (addr + len > current->mm->context.asce_limit) { + if (addr + len > current->mm->context.asce_limit && + addr + len <= TASK_SIZE) { rc = crst_table_upgrade(mm, addr + len); if (rc) return (unsigned long) rc; @@ -183,7 +184,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, } check_asce_limit: - if (addr + len > current->mm->context.asce_limit) { + if (addr + len > current->mm->context.asce_limit && + addr + len <= TASK_SIZE) { rc = crst_table_upgrade(mm, addr + len); if (rc) return (unsigned long) rc; diff --git a/arch/sparc/include/asm/page_32.h b/arch/sparc/include/asm/page_32.h index 0efd0583a8c9..6249214148c2 100644 --- a/arch/sparc/include/asm/page_32.h +++ b/arch/sparc/include/asm/page_32.h @@ -68,6 +68,7 @@ typedef struct { unsigned long iopgprot; } iopgprot_t; #define iopgprot_val(x) ((x).iopgprot) #define __pte(x) ((pte_t) { (x) } ) +#define __pmd(x) ((pmd_t) { { (x) }, }) #define __iopte(x) ((iopte_t) { (x) } ) #define __pgd(x) ((pgd_t) { (x) } ) #define __ctxd(x) ((ctxd_t) { (x) } ) @@ -95,6 +96,7 @@ typedef unsigned long iopgprot_t; #define iopgprot_val(x) (x) #define __pte(x) (x) +#define __pmd(x) ((pmd_t) { { (x) }, }) #define __iopte(x) (x) #define __pgd(x) (x) #define __ctxd(x) (x) diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index f10e2f712394..9ebebf1fd93d 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -1266,8 +1266,6 @@ static int pci_sun4v_probe(struct platform_device *op) * ATU group, but ATU hcalls won't be available. */ hv_atu = false; - pr_err(PFX "Could not register hvapi ATU err=%d\n", - err); } else { pr_info(PFX "Registered hvapi ATU major[%lu] minor[%lu]\n", vatu_major, vatu_minor); diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index a38787b84322..732af9a9f6dd 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -602,7 +602,7 @@ void pcibios_fixup_bus(struct pci_bus *bus) { struct pci_dev *dev; int i, has_io, has_mem; - unsigned int cmd; + unsigned int cmd = 0; struct linux_pcic *pcic; /* struct linux_pbm_info* pbm = &pcic->pbm; */ int node; diff --git a/arch/sparc/lib/multi3.S b/arch/sparc/lib/multi3.S index d6b6c97fe3c7..703127aaf4a5 100644 --- a/arch/sparc/lib/multi3.S +++ b/arch/sparc/lib/multi3.S @@ -5,26 +5,26 @@ .align 4 ENTRY(__multi3) /* %o0 = u, %o1 = v */ mov %o1, %g1 - srl %o3, 0, %g4 - mulx %g4, %g1, %o1 + srl %o3, 0, %o4 + mulx %o4, %g1, %o1 srlx %g1, 0x20, %g3 - mulx %g3, %g4, %g5 - sllx %g5, 0x20, %o5 - srl %g1, 0, %g4 + mulx %g3, %o4, %g7 + sllx %g7, 0x20, %o5 + srl %g1, 0, %o4 sub %o1, %o5, %o5 srlx %o5, 0x20, %o5 - addcc %g5, %o5, %g5 + addcc %g7, %o5, %g7 srlx %o3, 0x20, %o5 - mulx %g4, %o5, %g4 + mulx %o4, %o5, %o4 mulx %g3, %o5, %o5 sethi %hi(0x80000000), %g3 - addcc %g5, %g4, %g5 - srlx %g5, 0x20, %g5 + addcc %g7, %o4, %g7 + srlx %g7, 0x20, %g7 add %g3, %g3, %g3 movcc %xcc, %g0, %g3 - addcc %o5, %g5, %o5 - sllx %g4, 0x20, %g4 - add %o1, %g4, %o1 + addcc %o5, %g7, %o5 + sllx %o4, 0x20, %o4 + add %o1, %o4, %o1 add %o5, %g3, %g2 mulx %g1, %o2, %g1 add %g1, %g2, %g1 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 781521b7cf9e..323cb065be5e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -100,6 +100,7 @@ config X86 select GENERIC_STRNCPY_FROM_USER select GENERIC_STRNLEN_USER select GENERIC_TIME_VSYSCALL + select HARDLOCKUP_CHECK_TIMESTAMP if X86_64 select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI select HAVE_ALIGNED_STRUCT_PAGE if SLUB @@ -163,7 +164,7 @@ config X86 select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI - select HAVE_HARDLOCKUP_DETECTOR_PERF if HAVE_PERF_EVENTS_NMI + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index a0838ab929f2..c14217cd0155 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -116,8 +116,7 @@ void __putstr(const char *s) } } - if (boot_params->screen_info.orig_video_mode == 0 && - lines == 0 && cols == 0) + if (lines == 0 || cols == 0) return; x = boot_params->screen_info.orig_x; diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 2ed8f0c25def..1bb08ecffd24 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -520,8 +520,14 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # the description in lib/decompressor_xxx.c for specific information. # # extra_bytes = (uncompressed_size >> 12) + 65536 + 128 +# +# LZ4 is even worse: data that cannot be further compressed grows by 0.4%, +# or one byte per 256 bytes. OTOH, we can safely get rid of the +128 as +# the size-dependent part now grows so fast. +# +# extra_bytes = (uncompressed_size >> 8) + 65536 -#define ZO_z_extra_bytes ((ZO_z_output_len >> 12) + 65536 + 128) +#define ZO_z_extra_bytes ((ZO_z_output_len >> 8) + 65536) #if ZO_z_output_len > ZO_z_input_len # define ZO_z_extract_offset (ZO_z_output_len + ZO_z_extra_bytes - \ ZO_z_input_len) diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S index 1cd792db15ef..1eab79c9ac48 100644 --- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S +++ b/arch/x86/crypto/sha1_avx2_x86_64_asm.S @@ -117,11 +117,10 @@ .set T1, REG_T1 .endm -#define K_BASE %r8 #define HASH_PTR %r9 +#define BLOCKS_CTR %r8 #define BUFFER_PTR %r10 #define BUFFER_PTR2 %r13 -#define BUFFER_END %r11 #define PRECALC_BUF %r14 #define WK_BUF %r15 @@ -205,14 +204,14 @@ * blended AVX2 and ALU instruction scheduling * 1 vector iteration per 8 rounds */ - vmovdqu ((i * 2) + PRECALC_OFFSET)(BUFFER_PTR), W_TMP + vmovdqu (i * 2)(BUFFER_PTR), W_TMP .elseif ((i & 7) == 1) - vinsertf128 $1, (((i-1) * 2)+PRECALC_OFFSET)(BUFFER_PTR2),\ + vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\ WY_TMP, WY_TMP .elseif ((i & 7) == 2) vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY .elseif ((i & 7) == 4) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP .elseif ((i & 7) == 7) vmovdqu WY_TMP, PRECALC_WK(i&~7) @@ -255,7 +254,7 @@ vpxor WY, WY_TMP, WY_TMP .elseif ((i & 7) == 7) vpxor WY_TMP2, WY_TMP, WY - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -291,7 +290,7 @@ vpsrld $30, WY, WY vpor WY, WY_TMP, WY .elseif ((i & 7) == 7) - vpaddd K_XMM(K_BASE), WY, WY_TMP + vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP vmovdqu WY_TMP, PRECALC_WK(i&~7) PRECALC_ROTATE_WY @@ -446,6 +445,16 @@ .endm +/* Add constant only if (%2 > %3) condition met (uses RTA as temp) + * %1 + %2 >= %3 ? %4 : 0 + */ +.macro ADD_IF_GE a, b, c, d + mov \a, RTA + add $\d, RTA + cmp $\c, \b + cmovge RTA, \a +.endm + /* * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining */ @@ -463,13 +472,16 @@ lea (2*4*80+32)(%rsp), WK_BUF # Precalc WK for first 2 blocks - PRECALC_OFFSET = 0 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64 .set i, 0 .rept 160 PRECALC i .set i, i + 1 .endr - PRECALC_OFFSET = 128 + + /* Go to next block if needed */ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128 + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 xchg WK_BUF, PRECALC_BUF .align 32 @@ -479,8 +491,8 @@ _loop: * we use K_BASE value as a signal of a last block, * it is set below by: cmovae BUFFER_PTR, K_BASE */ - cmp K_BASE, BUFFER_PTR - jne _begin + test BLOCKS_CTR, BLOCKS_CTR + jnz _begin .align 32 jmp _end .align 32 @@ -512,10 +524,10 @@ _loop0: .set j, j+2 .endr - add $(2*64), BUFFER_PTR /* move to next odd-64-byte block */ - cmp BUFFER_END, BUFFER_PTR /* is current block the last one? */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ - + /* Update Counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128 /* * rounds * 60,62,64,66,68 @@ -532,8 +544,8 @@ _loop0: UPDATE_HASH 12(HASH_PTR), D UPDATE_HASH 16(HASH_PTR), E - cmp K_BASE, BUFFER_PTR /* is current block the last one? */ - je _loop + test BLOCKS_CTR, BLOCKS_CTR + jz _loop mov TB, B @@ -575,10 +587,10 @@ _loop2: .set j, j+2 .endr - add $(2*64), BUFFER_PTR2 /* move to next even-64-byte block */ - - cmp BUFFER_END, BUFFER_PTR2 /* is current block the last one */ - cmovae K_BASE, BUFFER_PTR /* signal the last iteration smartly */ + /* update counter */ + sub $1, BLOCKS_CTR + /* Move to the next block only if needed*/ + ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128 jmp _loop3 _loop3: @@ -641,19 +653,12 @@ _loop3: avx2_zeroupper - lea K_XMM_AR(%rip), K_BASE - + /* Setup initial values */ mov CTX, HASH_PTR mov BUF, BUFFER_PTR - lea 64(BUF), BUFFER_PTR2 - - shl $6, CNT /* mul by 64 */ - add BUF, CNT - add $64, CNT - mov CNT, BUFFER_END - cmp BUFFER_END, BUFFER_PTR2 - cmovae K_BASE, BUFFER_PTR2 + mov BUF, BUFFER_PTR2 + mov CNT, BLOCKS_CTR xmm_mov BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index f960a043cdeb..fc61739150e7 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -201,7 +201,7 @@ asmlinkage void sha1_transform_avx2(u32 *digest, const char *data, static bool avx2_usable(void) { - if (false && avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) + if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_BMI1) && boot_cpu_has(X86_FEATURE_BMI2)) return true; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index d271fb79248f..6d078b89a5e8 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1211,6 +1211,8 @@ ENTRY(nmi) * other IST entries. */ + ASM_CLAC + /* Use %rdx as our temp variable throughout */ pushq %rdx diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 8e3db8f642a7..939050169d12 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2114,7 +2114,7 @@ static void refresh_pce(void *ignored) load_mm_cr4(this_cpu_read(cpu_tlbstate.loaded_mm)); } -static void x86_pmu_event_mapped(struct perf_event *event) +static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm) { if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; @@ -2129,22 +2129,20 @@ static void x86_pmu_event_mapped(struct perf_event *event) * For now, this can't happen because all callers hold mmap_sem * for write. If this changes, we'll need a different solution. */ - lockdep_assert_held_exclusive(¤t->mm->mmap_sem); + lockdep_assert_held_exclusive(&mm->mmap_sem); - if (atomic_inc_return(¤t->mm->context.perf_rdpmc_allowed) == 1) - on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); + if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1) + on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } -static void x86_pmu_event_unmapped(struct perf_event *event) +static void x86_pmu_event_unmapped(struct perf_event *event, struct mm_struct *mm) { - if (!current->mm) - return; if (!(event->hw.flags & PERF_X86_EVENT_RDPMC_ALLOWED)) return; - if (atomic_dec_and_test(¤t->mm->context.perf_rdpmc_allowed)) - on_each_cpu_mask(mm_cpumask(current->mm), refresh_pce, NULL, 1); + if (atomic_dec_and_test(&mm->context.perf_rdpmc_allowed)) + on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1); } static int x86_pmu_event_idx(struct perf_event *event) @@ -2337,12 +2335,9 @@ static unsigned long get_segment_base(unsigned int segment) #ifdef CONFIG_MODIFY_LDT_SYSCALL struct ldt_struct *ldt; - if (idx > LDT_ENTRIES) - return 0; - /* IRQs are off, so this synchronizes with smp_store_release */ ldt = lockless_dereference(current->active_mm->context.ldt); - if (!ldt || idx > ldt->nr_entries) + if (!ldt || idx >= ldt->nr_entries) return 0; desc = &ldt->entries[idx]; @@ -2350,7 +2345,7 @@ static unsigned long get_segment_base(unsigned int segment) return 0; #endif } else { - if (idx > GDT_ENTRIES) + if (idx >= GDT_ENTRIES) return 0; desc = raw_cpu_ptr(gdt_page.gdt) + idx; diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 8ae8c5ce3a1f..ddd8d3516bfc 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -69,7 +69,7 @@ struct bts_buffer { struct bts_phys buf[0]; }; -struct pmu bts_pmu; +static struct pmu bts_pmu; static size_t buf_size(struct page *page) { diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index eb0533558c2b..d32c0eed38ca 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -587,7 +587,7 @@ static __initconst const u64 p4_hw_cache_event_ids * P4_CONFIG_ALIASABLE or bits for P4_PEBS_METRIC, they are * either up to date automatically or not applicable at all. */ -struct p4_event_alias { +static struct p4_event_alias { u64 original; u64 alternative; } p4_event_aliases[] = { diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c index a45e2114a846..8e2457cb6b4a 100644 --- a/arch/x86/events/intel/rapl.c +++ b/arch/x86/events/intel/rapl.c @@ -559,7 +559,7 @@ static struct attribute_group rapl_pmu_format_group = { .attrs = rapl_formats_attr, }; -const struct attribute_group *rapl_attr_groups[] = { +static const struct attribute_group *rapl_attr_groups[] = { &rapl_pmu_attr_group, &rapl_pmu_format_group, &rapl_pmu_events_group, diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 44ec523287f6..1c5390f1cf09 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -721,7 +721,7 @@ static struct attribute *uncore_pmu_attrs[] = { NULL, }; -static struct attribute_group uncore_pmu_attr_group = { +static const struct attribute_group uncore_pmu_attr_group = { .attrs = uncore_pmu_attrs, }; diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index cda569332005..6a5cbe90f859 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -272,7 +272,7 @@ static struct attribute *nhmex_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_ubox_format_group = { +static const struct attribute_group nhmex_uncore_ubox_format_group = { .name = "format", .attrs = nhmex_uncore_ubox_formats_attr, }; @@ -299,7 +299,7 @@ static struct attribute *nhmex_uncore_cbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_cbox_format_group = { +static const struct attribute_group nhmex_uncore_cbox_format_group = { .name = "format", .attrs = nhmex_uncore_cbox_formats_attr, }; @@ -407,7 +407,7 @@ static struct attribute *nhmex_uncore_bbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_bbox_format_group = { +static const struct attribute_group nhmex_uncore_bbox_format_group = { .name = "format", .attrs = nhmex_uncore_bbox_formats_attr, }; @@ -484,7 +484,7 @@ static struct attribute *nhmex_uncore_sbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_sbox_format_group = { +static const struct attribute_group nhmex_uncore_sbox_format_group = { .name = "format", .attrs = nhmex_uncore_sbox_formats_attr, }; @@ -898,7 +898,7 @@ static struct attribute *nhmex_uncore_mbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_mbox_format_group = { +static const struct attribute_group nhmex_uncore_mbox_format_group = { .name = "format", .attrs = nhmex_uncore_mbox_formats_attr, }; @@ -1163,7 +1163,7 @@ static struct attribute *nhmex_uncore_rbox_formats_attr[] = { NULL, }; -static struct attribute_group nhmex_uncore_rbox_format_group = { +static const struct attribute_group nhmex_uncore_rbox_format_group = { .name = "format", .attrs = nhmex_uncore_rbox_formats_attr, }; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index a3dcc12bef4a..db1127ce685e 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -130,7 +130,7 @@ static struct attribute *snb_uncore_formats_attr[] = { NULL, }; -static struct attribute_group snb_uncore_format_group = { +static const struct attribute_group snb_uncore_format_group = { .name = "format", .attrs = snb_uncore_formats_attr, }; @@ -289,7 +289,7 @@ static struct attribute *snb_uncore_imc_formats_attr[] = { NULL, }; -static struct attribute_group snb_uncore_imc_format_group = { +static const struct attribute_group snb_uncore_imc_format_group = { .name = "format", .attrs = snb_uncore_imc_formats_attr, }; @@ -769,7 +769,7 @@ static struct attribute *nhm_uncore_formats_attr[] = { NULL, }; -static struct attribute_group nhm_uncore_format_group = { +static const struct attribute_group nhm_uncore_format_group = { .name = "format", .attrs = nhm_uncore_formats_attr, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 4f9127644b80..db1fe377e6dd 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -602,27 +602,27 @@ static struct uncore_event_desc snbep_uncore_qpi_events[] = { { /* end: all zeroes */ }, }; -static struct attribute_group snbep_uncore_format_group = { +static const struct attribute_group snbep_uncore_format_group = { .name = "format", .attrs = snbep_uncore_formats_attr, }; -static struct attribute_group snbep_uncore_ubox_format_group = { +static const struct attribute_group snbep_uncore_ubox_format_group = { .name = "format", .attrs = snbep_uncore_ubox_formats_attr, }; -static struct attribute_group snbep_uncore_cbox_format_group = { +static const struct attribute_group snbep_uncore_cbox_format_group = { .name = "format", .attrs = snbep_uncore_cbox_formats_attr, }; -static struct attribute_group snbep_uncore_pcu_format_group = { +static const struct attribute_group snbep_uncore_pcu_format_group = { .name = "format", .attrs = snbep_uncore_pcu_formats_attr, }; -static struct attribute_group snbep_uncore_qpi_format_group = { +static const struct attribute_group snbep_uncore_qpi_format_group = { .name = "format", .attrs = snbep_uncore_qpi_formats_attr, }; @@ -1431,27 +1431,27 @@ static struct attribute *ivbep_uncore_qpi_formats_attr[] = { NULL, }; -static struct attribute_group ivbep_uncore_format_group = { +static const struct attribute_group ivbep_uncore_format_group = { .name = "format", .attrs = ivbep_uncore_formats_attr, }; -static struct attribute_group ivbep_uncore_ubox_format_group = { +static const struct attribute_group ivbep_uncore_ubox_format_group = { .name = "format", .attrs = ivbep_uncore_ubox_formats_attr, }; -static struct attribute_group ivbep_uncore_cbox_format_group = { +static const struct attribute_group ivbep_uncore_cbox_format_group = { .name = "format", .attrs = ivbep_uncore_cbox_formats_attr, }; -static struct attribute_group ivbep_uncore_pcu_format_group = { +static const struct attribute_group ivbep_uncore_pcu_format_group = { .name = "format", .attrs = ivbep_uncore_pcu_formats_attr, }; -static struct attribute_group ivbep_uncore_qpi_format_group = { +static const struct attribute_group ivbep_uncore_qpi_format_group = { .name = "format", .attrs = ivbep_uncore_qpi_formats_attr, }; @@ -1887,7 +1887,7 @@ static struct attribute *knl_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_ubox_format_group = { +static const struct attribute_group knl_uncore_ubox_format_group = { .name = "format", .attrs = knl_uncore_ubox_formats_attr, }; @@ -1927,7 +1927,7 @@ static struct attribute *knl_uncore_cha_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_cha_format_group = { +static const struct attribute_group knl_uncore_cha_format_group = { .name = "format", .attrs = knl_uncore_cha_formats_attr, }; @@ -2037,7 +2037,7 @@ static struct attribute *knl_uncore_pcu_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_pcu_format_group = { +static const struct attribute_group knl_uncore_pcu_format_group = { .name = "format", .attrs = knl_uncore_pcu_formats_attr, }; @@ -2187,7 +2187,7 @@ static struct attribute *knl_uncore_irp_formats_attr[] = { NULL, }; -static struct attribute_group knl_uncore_irp_format_group = { +static const struct attribute_group knl_uncore_irp_format_group = { .name = "format", .attrs = knl_uncore_irp_formats_attr, }; @@ -2385,7 +2385,7 @@ static struct attribute *hswep_uncore_ubox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_ubox_format_group = { +static const struct attribute_group hswep_uncore_ubox_format_group = { .name = "format", .attrs = hswep_uncore_ubox_formats_attr, }; @@ -2439,7 +2439,7 @@ static struct attribute *hswep_uncore_cbox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_cbox_format_group = { +static const struct attribute_group hswep_uncore_cbox_format_group = { .name = "format", .attrs = hswep_uncore_cbox_formats_attr, }; @@ -2621,7 +2621,7 @@ static struct attribute *hswep_uncore_sbox_formats_attr[] = { NULL, }; -static struct attribute_group hswep_uncore_sbox_format_group = { +static const struct attribute_group hswep_uncore_sbox_format_group = { .name = "format", .attrs = hswep_uncore_sbox_formats_attr, }; @@ -3314,7 +3314,7 @@ static struct attribute *skx_uncore_cha_formats_attr[] = { NULL, }; -static struct attribute_group skx_uncore_chabox_format_group = { +static const struct attribute_group skx_uncore_chabox_format_group = { .name = "format", .attrs = skx_uncore_cha_formats_attr, }; @@ -3427,7 +3427,7 @@ static struct attribute *skx_uncore_iio_formats_attr[] = { NULL, }; -static struct attribute_group skx_uncore_iio_format_group = { +static const struct attribute_group skx_uncore_iio_format_group = { .name = "format", .attrs = skx_uncore_iio_formats_attr, }; @@ -3484,7 +3484,7 @@ static struct attribute *skx_uncore_formats_attr[] = { NULL, }; -static struct attribute_group skx_uncore_format_group = { +static const struct attribute_group skx_uncore_format_group = { .name = "format", .attrs = skx_uncore_formats_attr, }; @@ -3605,7 +3605,7 @@ static struct attribute *skx_upi_uncore_formats_attr[] = { NULL, }; -static struct attribute_group skx_upi_uncore_format_group = { +static const struct attribute_group skx_upi_uncore_format_group = { .name = "format", .attrs = skx_upi_uncore_formats_attr, }; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index ca3c48c0872f..5a28e8e55e36 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -286,7 +286,7 @@ #define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ #define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ #define X86_FEATURE_AVIC (15*32+13) /* Virtual Interrupt Controller */ -#define X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE (15*32+15) /* Virtual VMLOAD VMSAVE */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* Virtual VMSAVE VMLOAD */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (ecx), word 16 */ #define X86_FEATURE_AVX512VBMI (16*32+ 1) /* AVX512 Vector Bit Manipulation instructions*/ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1c18d83d3f09..9aeb91935ce0 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -247,11 +247,11 @@ extern int force_personality32; /* * This is the base location for PIE (ET_DYN with INTERP) loads. On - * 64-bit, this is raised to 4GB to leave the entire 32-bit address + * 64-bit, this is above 4GB to leave the entire 32-bit address * space open for things that want to use the area for 32-bit pointers. */ #define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ - 0x100000000UL) + (TASK_SIZE / 3 * 2)) /* This yields a mask that user programs can use to figure out what instruction set this CPU supports. This could be done in user space, diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 255645f60ca2..554cdb205d17 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -450,10 +450,10 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu) return 0; } -static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate) +static inline void __copy_kernel_to_fpregs(union fpregs_state *fpstate, u64 mask) { if (use_xsave()) { - copy_kernel_to_xregs(&fpstate->xsave, -1); + copy_kernel_to_xregs(&fpstate->xsave, mask); } else { if (use_fxsr()) copy_kernel_to_fxregs(&fpstate->fxsave); @@ -477,7 +477,7 @@ static inline void copy_kernel_to_fpregs(union fpregs_state *fpstate) : : [addr] "m" (fpstate)); } - __copy_kernel_to_fpregs(fpstate); + __copy_kernel_to_fpregs(fpstate, -1); } extern int copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 87ac4fba6d8e..92c9032502d8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -492,6 +492,7 @@ struct kvm_vcpu_arch { unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr8; + u32 pkru; u32 hflags; u64 efer; u64 apic_base; @@ -1374,8 +1375,6 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); int kvm_cpu_get_interrupt(struct kvm_vcpu *v); void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); -void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address); void kvm_define_shared_msr(unsigned index, u32 msr); int kvm_set_shared_msr(unsigned index, u64 val, u64 mask); diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 265c907d7d4c..7a234be7e298 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -140,9 +140,7 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.execute_only_pkey = -1; } #endif - init_new_context_ldt(tsk, mm); - - return 0; + return init_new_context_ldt(tsk, mm); } static inline void destroy_context(struct mm_struct *mm) { diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 7cf7c70b6ef2..0ee83321a313 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -40,13 +40,16 @@ static void aperfmperf_snapshot_khz(void *dummy) struct aperfmperf_sample *s = this_cpu_ptr(&samples); ktime_t now = ktime_get(); s64 time_delta = ktime_ms_delta(now, s->time); + unsigned long flags; /* Don't bother re-computing within the cache threshold time. */ if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) return; + local_irq_save(flags); rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); + local_irq_restore(flags); aperf_delta = aperf - s->aperf; mperf_delta = mperf - s->mperf; diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index d7cc190ae457..f7370abd33c6 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -122,7 +122,7 @@ static struct attribute *thermal_throttle_attrs[] = { NULL }; -static struct attribute_group thermal_attr_group = { +static const struct attribute_group thermal_attr_group = { .attrs = thermal_throttle_attrs, .name = "thermal_throttle" }; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 9cb98ee103db..86e8f0b2537b 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -561,7 +561,7 @@ static struct attribute *mc_default_attrs[] = { NULL }; -static struct attribute_group mc_attr_group = { +static const struct attribute_group mc_attr_group = { .attrs = mc_default_attrs, .name = "microcode", }; @@ -707,7 +707,7 @@ static struct attribute *cpu_root_microcode_attrs[] = { NULL }; -static struct attribute_group cpu_root_microcode_group = { +static const struct attribute_group cpu_root_microcode_group = { .name = "microcode", .attrs = cpu_root_microcode_attrs, }; diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index c5bb63be4ba1..40d5a8a75212 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -237,6 +237,18 @@ set_mtrr(unsigned int reg, unsigned long base, unsigned long size, mtrr_type typ stop_machine(mtrr_rendezvous_handler, &data, cpu_online_mask); } +static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, + unsigned long size, mtrr_type type) +{ + struct set_mtrr_data data = { .smp_reg = reg, + .smp_base = base, + .smp_size = size, + .smp_type = type + }; + + stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask); +} + static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type) { @@ -370,7 +382,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, /* Search for an empty MTRR */ i = mtrr_if->get_free_region(base, size, replace); if (i >= 0) { - set_mtrr(i, base, size, type); + set_mtrr_cpuslocked(i, base, size, type); if (likely(replace < 0)) { mtrr_usage_table[i] = 1; } else { @@ -378,7 +390,7 @@ int mtrr_add_page(unsigned long base, unsigned long size, if (increment) mtrr_usage_table[i]++; if (unlikely(replace != i)) { - set_mtrr(replace, 0, 0, 0); + set_mtrr_cpuslocked(replace, 0, 0, 0); mtrr_usage_table[replace] = 0; } } @@ -506,7 +518,7 @@ int mtrr_del_page(int reg, unsigned long base, unsigned long size) goto out; } if (--mtrr_usage_table[reg] < 1) - set_mtrr(reg, 0, 0, 0); + set_mtrr_cpuslocked(reg, 0, 0, 0); error = reg; out: mutex_unlock(&mtrr_mutex); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 46c3c73e7f43..9ba79543d9ee 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -53,6 +53,7 @@ void __head __startup_64(unsigned long physaddr) pudval_t *pud; pmdval_t *pmd, pmd_entry; int i; + unsigned int *next_pgt_ptr; /* Is the address too large? */ if (physaddr >> MAX_PHYSMEM_BITS) @@ -91,9 +92,9 @@ void __head __startup_64(unsigned long physaddr) * creates a bunch of nonsense entries but that is fine -- * it avoids problems around wraparound. */ - - pud = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); + pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index 4afc67f5facc..06e1ff5562c0 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -55,7 +55,7 @@ static struct bin_attribute *boot_params_data_attrs[] = { NULL, }; -static struct attribute_group boot_params_attr_group = { +static const struct attribute_group boot_params_attr_group = { .attrs = boot_params_version_attrs, .bin_attrs = boot_params_data_attrs, }; @@ -202,7 +202,7 @@ static struct bin_attribute *setup_data_data_attrs[] = { NULL, }; -static struct attribute_group setup_data_attr_group = { +static const struct attribute_group setup_data_attr_group = { .attrs = setup_data_type_attrs, .bin_attrs = setup_data_data_attrs, }; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b474c8de7fba..54b9e89d4d6b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -971,7 +971,8 @@ void common_cpu_up(unsigned int cpu, struct task_struct *idle) * Returns zero if CPU booted OK, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) +static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, + int *cpu0_nmi_registered) { volatile u32 *trampoline_status = (volatile u32 *) __va(real_mode_header->trampoline_status); @@ -979,7 +980,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) unsigned long start_ip = real_mode_header->trampoline_start; unsigned long boot_error = 0; - int cpu0_nmi_registered = 0; unsigned long timeout; idle->thread.sp = (unsigned long)task_pt_regs(idle); @@ -1035,7 +1035,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) boot_error = apic->wakeup_secondary_cpu(apicid, start_ip); else boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, - &cpu0_nmi_registered); + cpu0_nmi_registered); if (!boot_error) { /* @@ -1080,12 +1080,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) */ smpboot_restore_warm_reset_vector(); } - /* - * Clean up the nmi handler. Do this after the callin and callout sync - * to avoid impact of possible long unregister time. - */ - if (cpu0_nmi_registered) - unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); return boot_error; } @@ -1093,8 +1087,9 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) int native_cpu_up(unsigned int cpu, struct task_struct *tidle) { int apicid = apic->cpu_present_to_apicid(cpu); + int cpu0_nmi_registered = 0; unsigned long flags; - int err; + int err, ret = 0; WARN_ON(irqs_disabled()); @@ -1131,10 +1126,11 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) common_cpu_up(cpu, tidle); - err = do_boot_cpu(apicid, cpu, tidle); + err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered); if (err) { pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); - return -EIO; + ret = -EIO; + goto unreg_nmi; } /* @@ -1150,7 +1146,15 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) touch_nmi_watchdog(); } - return 0; +unreg_nmi: + /* + * Clean up the nmi handler. Do this after the callin and callout sync + * to avoid impact of possible long unregister time. + */ + if (cpu0_nmi_registered) + unregister_nmi_handler(NMI_LOCAL, "wake_cpu0"); + + return ret; } /** diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 59ca2eea522c..19adbb418443 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -469,7 +469,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_cpuid_7_0_ecx_x86_features; cpuid_mask(&entry->ecx, CPUID_7_ECX); /* PKU is not yet implemented for shadow paging. */ - if (!tdp_enabled) + if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) entry->ecx &= ~F(PKU); entry->edx &= kvm_cpuid_7_0_edx_x86_features; entry->edx &= get_scattered_cpuid_leaf(7, 0, CPUID_EDX); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 762cdf2595f9..e1e89ee4af75 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -84,11 +84,6 @@ static inline u64 kvm_read_edx_eax(struct kvm_vcpu *vcpu) | ((u64)(kvm_register_read(vcpu, VCPU_REGS_RDX) & -1u) << 32); } -static inline u32 kvm_read_pkru(struct kvm_vcpu *vcpu) -{ - return kvm_x86_ops->get_pkru(vcpu); -} - static inline void enter_guest_mode(struct kvm_vcpu *vcpu) { vcpu->arch.hflags |= HF_GUEST_MASK; diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index d7d248a000dd..4b9a3ae6b725 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -185,7 +185,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, * index of the protection domain, so pte_pkey * 2 is * is the index of the first bit for the domain. */ - pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3; + pkru_bits = (vcpu->arch.pkru >> (pte_pkey * 2)) & 3; /* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */ offset = (pfec & ~1) + diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 1107626938cc..af256b786a70 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1100,7 +1100,7 @@ static __init int svm_hardware_setup(void) if (vls) { if (!npt_enabled || - !boot_cpu_has(X86_FEATURE_VIRTUAL_VMLOAD_VMSAVE) || + !boot_cpu_has(X86_FEATURE_V_VMSAVE_VMLOAD) || !IS_ENABLED(CONFIG_X86_64)) { vls = false; } else { @@ -1777,11 +1777,6 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_svm(vcpu)->vmcb->save.rflags = rflags; } -static u32 svm_get_pkru(struct kvm_vcpu *vcpu) -{ - return 0; -} - static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) { switch (reg) { @@ -5413,8 +5408,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, - .get_pkru = svm_get_pkru, - .tlb_flush = svm_flush_tlb, .run = svm_vcpu_run, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 9b21b1223035..c6ef2940119b 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -636,8 +636,6 @@ struct vcpu_vmx { u64 current_tsc_ratio; - bool guest_pkru_valid; - u32 guest_pkru; u32 host_pkru; /* @@ -2383,11 +2381,6 @@ static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) to_vmx(vcpu)->emulation_required = emulation_required(vcpu); } -static u32 vmx_get_pkru(struct kvm_vcpu *vcpu) -{ - return to_vmx(vcpu)->guest_pkru; -} - static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu) { u32 interruptibility = vmcs_read32(GUEST_INTERRUPTIBILITY_INFO); @@ -9020,8 +9013,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) vmx_set_interrupt_shadow(vcpu, 0); - if (vmx->guest_pkru_valid) - __write_pkru(vmx->guest_pkru); + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && + vcpu->arch.pkru != vmx->host_pkru) + __write_pkru(vcpu->arch.pkru); atomic_switch_perf_msrs(vmx); debugctlmsr = get_debugctlmsr(); @@ -9169,13 +9164,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) * back on host, so it is safe to read guest PKRU from current * XSAVE. */ - if (boot_cpu_has(X86_FEATURE_OSPKE)) { - vmx->guest_pkru = __read_pkru(); - if (vmx->guest_pkru != vmx->host_pkru) { - vmx->guest_pkru_valid = true; + if (static_cpu_has(X86_FEATURE_PKU) && + kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { + vcpu->arch.pkru = __read_pkru(); + if (vcpu->arch.pkru != vmx->host_pkru) __write_pkru(vmx->host_pkru); - } else - vmx->guest_pkru_valid = false; } /* @@ -11682,8 +11675,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .get_rflags = vmx_get_rflags, .set_rflags = vmx_set_rflags, - .get_pkru = vmx_get_pkru, - .tlb_flush = vmx_flush_tlb, .run = vmx_vcpu_run, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d734aa8c5b4f..272320eb328c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3245,7 +3245,12 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest + offset, src, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(dest + offset, &vcpu->arch.pkru, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest + offset, src, size); + } valid -= feature; @@ -3283,7 +3288,11 @@ static void load_xsave(struct kvm_vcpu *vcpu, u8 *src) u32 size, offset, ecx, edx; cpuid_count(XSTATE_CPUID, index, &size, &offset, &ecx, &edx); - memcpy(dest, src + offset, size); + if (feature == XFEATURE_MASK_PKRU) + memcpy(&vcpu->arch.pkru, src + offset, + sizeof(vcpu->arch.pkru)); + else + memcpy(dest, src + offset, size); } valid -= feature; @@ -6725,17 +6734,6 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page); -void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm, - unsigned long address) -{ - /* - * The physical address of apic access page is stored in the VMCS. - * Update it when it becomes invalid. - */ - if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT)) - kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); -} - /* * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the @@ -7633,7 +7631,9 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) */ vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); - __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); + /* PKRU is separately restored in kvm_x86_ops->run. */ + __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state, + ~XFEATURE_MASK_PKRU); trace_kvm_fpu(1); } diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 229d04a83f85..a88cfbfbd078 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -50,8 +50,7 @@ unsigned long tasksize_64bit(void) static unsigned long stack_maxrandom_size(unsigned long task_size) { unsigned long max = 0; - if ((current->flags & PF_RANDOMIZE) && - !(current->personality & ADDR_NO_RANDOMIZE)) { + if (current->flags & PF_RANDOMIZE) { max = (-1UL) & __STACK_RND_MASK(task_size == tasksize_32bit()); max <<= PAGE_SHIFT; } @@ -79,13 +78,13 @@ static int mmap_is_legacy(void) static unsigned long arch_rnd(unsigned int rndbits) { + if (!(current->flags & PF_RANDOMIZE)) + return 0; return (get_random_long() & ((1UL << rndbits) - 1)) << PAGE_SHIFT; } unsigned long arch_mmap_rnd(void) { - if (!(current->flags & PF_RANDOMIZE)) - return 0; return arch_rnd(mmap_is_ia32() ? mmap32_rnd_bits : mmap64_rnd_bits); } diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c index 3e4bdb442fbc..f44c0bc95aa2 100644 --- a/arch/x86/platform/uv/tlb_uv.c +++ b/arch/x86/platform/uv/tlb_uv.c @@ -26,7 +26,7 @@ static struct bau_operations ops __ro_after_init; /* timeouts in nanoseconds (indexed by UVH_AGING_PRESCALE_SEL urgency7 30:28) */ -static int timeout_base_ns[] = { +static const int timeout_base_ns[] = { 20, 160, 1280, @@ -1216,7 +1216,7 @@ static struct bau_pq_entry *find_another_by_swack(struct bau_pq_entry *msg, * set a bit in the UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE register. * Such a message must be ignored. */ -void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) +static void process_uv2_message(struct msg_desc *mdp, struct bau_control *bcp) { unsigned long mmr_image; unsigned char swack_vec; diff --git a/arch/x86/um/user-offsets.c b/arch/x86/um/user-offsets.c index ae4cd58c0c7a..02250b2633b8 100644 --- a/arch/x86/um/user-offsets.c +++ b/arch/x86/um/user-offsets.c @@ -50,7 +50,7 @@ void foo(void) DEFINE(HOST_GS, GS); DEFINE(HOST_ORIG_AX, ORIG_EAX); #else -#if defined(PTRACE_GETREGSET) && defined(PTRACE_SETREGSET) +#ifdef FP_XSTATE_MAGIC1 DEFINE(HOST_FP_SIZE, sizeof(struct _xstate) / sizeof(unsigned long)); #else DEFINE(HOST_FP_SIZE, sizeof(struct _fpstate) / sizeof(unsigned long)); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 9ebc2945f991..4f927a58dff8 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -75,6 +75,8 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(STATS), QUEUE_FLAG_NAME(POLL_STATS), QUEUE_FLAG_NAME(REGISTERED), + QUEUE_FLAG_NAME(SCSI_PASSTHROUGH), + QUEUE_FLAG_NAME(QUIESCED), }; #undef QUEUE_FLAG_NAME @@ -265,6 +267,7 @@ static const char *const cmd_flag_name[] = { CMD_FLAG_NAME(RAHEAD), CMD_FLAG_NAME(BACKGROUND), CMD_FLAG_NAME(NOUNMAP), + CMD_FLAG_NAME(NOWAIT), }; #undef CMD_FLAG_NAME diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c index 0c3354cf3552..76944e3271bf 100644 --- a/block/blk-mq-pci.c +++ b/block/blk-mq-pci.c @@ -36,12 +36,18 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev) for (queue = 0; queue < set->nr_hw_queues; queue++) { mask = pci_irq_get_affinity(pdev, queue); if (!mask) - return -EINVAL; + goto fallback; for_each_cpu(cpu, mask) set->mq_map[cpu] = queue; } return 0; + +fallback: + WARN_ON_ONCE(set->nr_hw_queues > 1); + for_each_possible_cpu(cpu) + set->mq_map[cpu] = 0; + return 0; } EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues); diff --git a/block/blk-mq.c b/block/blk-mq.c index 535cbdf32aab..4603b115e234 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -360,12 +360,12 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, return ERR_PTR(ret); rq = blk_mq_get_request(q, NULL, op, &alloc_data); + blk_queue_exit(q); if (!rq) return ERR_PTR(-EWOULDBLOCK); blk_mq_put_ctx(alloc_data.ctx); - blk_queue_exit(q); rq->__data_len = 0; rq->__sector = (sector_t) -1; @@ -411,12 +411,11 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, alloc_data.ctx = __blk_mq_get_ctx(q, cpu); rq = blk_mq_get_request(q, NULL, op, &alloc_data); + blk_queue_exit(q); if (!rq) return ERR_PTR(-EWOULDBLOCK); - blk_queue_exit(q); - return rq; } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a7285bf2831c..80f5481fe9f6 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -382,6 +382,14 @@ static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw) } \ } while (0) +static inline unsigned int throtl_bio_data_size(struct bio *bio) +{ + /* assume it's one sector */ + if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) + return 512; + return bio->bi_iter.bi_size; +} + static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg) { INIT_LIST_HEAD(&qn->node); @@ -934,6 +942,7 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, bool rw = bio_data_dir(bio); u64 bytes_allowed, extra_bytes, tmp; unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd; + unsigned int bio_size = throtl_bio_data_size(bio); jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw]; @@ -947,14 +956,14 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, do_div(tmp, HZ); bytes_allowed = tmp; - if (tg->bytes_disp[rw] + bio->bi_iter.bi_size <= bytes_allowed) { + if (tg->bytes_disp[rw] + bio_size <= bytes_allowed) { if (wait) *wait = 0; return true; } /* Calc approx time to dispatch */ - extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed; + extra_bytes = tg->bytes_disp[rw] + bio_size - bytes_allowed; jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw)); if (!jiffy_wait) @@ -1034,11 +1043,12 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) { bool rw = bio_data_dir(bio); + unsigned int bio_size = throtl_bio_data_size(bio); /* Charge the bio to the group */ - tg->bytes_disp[rw] += bio->bi_iter.bi_size; + tg->bytes_disp[rw] += bio_size; tg->io_disp[rw]++; - tg->last_bytes_disp[rw] += bio->bi_iter.bi_size; + tg->last_bytes_disp[rw] += bio_size; tg->last_io_disp[rw]++; /* diff --git a/block/bsg-lib.c b/block/bsg-lib.c index c4513b23f57a..dd56d7460cb9 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -29,26 +29,25 @@ #include <scsi/scsi_cmnd.h> /** - * bsg_destroy_job - routine to teardown/delete a bsg job + * bsg_teardown_job - routine to teardown a bsg job * @job: bsg_job that is to be torn down */ -static void bsg_destroy_job(struct kref *kref) +static void bsg_teardown_job(struct kref *kref) { struct bsg_job *job = container_of(kref, struct bsg_job, kref); struct request *rq = job->req; - blk_end_request_all(rq, BLK_STS_OK); - put_device(job->dev); /* release reference for the request */ kfree(job->request_payload.sg_list); kfree(job->reply_payload.sg_list); - kfree(job); + + blk_end_request_all(rq, BLK_STS_OK); } void bsg_job_put(struct bsg_job *job) { - kref_put(&job->kref, bsg_destroy_job); + kref_put(&job->kref, bsg_teardown_job); } EXPORT_SYMBOL_GPL(bsg_job_put); @@ -100,7 +99,7 @@ EXPORT_SYMBOL_GPL(bsg_job_done); */ static void bsg_softirq_done(struct request *rq) { - struct bsg_job *job = rq->special; + struct bsg_job *job = blk_mq_rq_to_pdu(rq); bsg_job_put(job); } @@ -122,33 +121,20 @@ static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req) } /** - * bsg_create_job - create the bsg_job structure for the bsg request + * bsg_prepare_job - create the bsg_job structure for the bsg request * @dev: device that is being sent the bsg request * @req: BSG request that needs a job structure */ -static int bsg_create_job(struct device *dev, struct request *req) +static int bsg_prepare_job(struct device *dev, struct request *req) { struct request *rsp = req->next_rq; - struct request_queue *q = req->q; struct scsi_request *rq = scsi_req(req); - struct bsg_job *job; + struct bsg_job *job = blk_mq_rq_to_pdu(req); int ret; - BUG_ON(req->special); - - job = kzalloc(sizeof(struct bsg_job) + q->bsg_job_size, GFP_KERNEL); - if (!job) - return -ENOMEM; - - req->special = job; - job->req = req; - if (q->bsg_job_size) - job->dd_data = (void *)&job[1]; job->request = rq->cmd; job->request_len = rq->cmd_len; - job->reply = rq->sense; - job->reply_len = SCSI_SENSE_BUFFERSIZE; /* Size of sense buffer - * allocated */ + if (req->bio) { ret = bsg_map_buffer(&job->request_payload, req); if (ret) @@ -187,7 +173,6 @@ static void bsg_request_fn(struct request_queue *q) { struct device *dev = q->queuedata; struct request *req; - struct bsg_job *job; int ret; if (!get_device(dev)) @@ -199,7 +184,7 @@ static void bsg_request_fn(struct request_queue *q) break; spin_unlock_irq(q->queue_lock); - ret = bsg_create_job(dev, req); + ret = bsg_prepare_job(dev, req); if (ret) { scsi_req(req)->result = ret; blk_end_request_all(req, BLK_STS_OK); @@ -207,8 +192,7 @@ static void bsg_request_fn(struct request_queue *q) continue; } - job = req->special; - ret = q->bsg_job_fn(job); + ret = q->bsg_job_fn(blk_mq_rq_to_pdu(req)); spin_lock_irq(q->queue_lock); if (ret) break; @@ -219,6 +203,35 @@ static void bsg_request_fn(struct request_queue *q) spin_lock_irq(q->queue_lock); } +static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp) +{ + struct bsg_job *job = blk_mq_rq_to_pdu(req); + struct scsi_request *sreq = &job->sreq; + + memset(job, 0, sizeof(*job)); + + scsi_req_init(sreq); + sreq->sense_len = SCSI_SENSE_BUFFERSIZE; + sreq->sense = kzalloc(sreq->sense_len, gfp); + if (!sreq->sense) + return -ENOMEM; + + job->req = req; + job->reply = sreq->sense; + job->reply_len = sreq->sense_len; + job->dd_data = job + 1; + + return 0; +} + +static void bsg_exit_rq(struct request_queue *q, struct request *req) +{ + struct bsg_job *job = blk_mq_rq_to_pdu(req); + struct scsi_request *sreq = &job->sreq; + + kfree(sreq->sense); +} + /** * bsg_setup_queue - Create and add the bsg hooks so we can receive requests * @dev: device to attach bsg device to @@ -235,7 +248,9 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name, q = blk_alloc_queue(GFP_KERNEL); if (!q) return ERR_PTR(-ENOMEM); - q->cmd_size = sizeof(struct scsi_request); + q->cmd_size = sizeof(struct bsg_job) + dd_job_size; + q->init_rq_fn = bsg_init_rq; + q->exit_rq_fn = bsg_exit_rq; q->request_fn = bsg_request_fn; ret = blk_init_allocated_queue(q); @@ -243,7 +258,6 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name, goto out_cleanup_queue; q->queuedata = dev; - q->bsg_job_size = dd_job_size; q->bsg_job_fn = job_fn; queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q); queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q); diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c index 38554c2ea38a..abaf9d78a206 100644 --- a/block/compat_ioctl.c +++ b/block/compat_ioctl.c @@ -79,7 +79,7 @@ static int compat_hdio_getgeo(struct gendisk *disk, struct block_device *bdev, static int compat_hdio_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - unsigned long *__user p; + unsigned long __user *p; int error; p = compat_alloc_user_space(sizeof(unsigned long)); diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index 43839b00fe6c..903605dbc1a5 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -87,8 +87,13 @@ static void skcipher_free_async_sgls(struct skcipher_async_req *sreq) } sgl = sreq->tsg; n = sg_nents(sgl); - for_each_sg(sgl, sg, n, i) - put_page(sg_page(sg)); + for_each_sg(sgl, sg, n, i) { + struct page *page = sg_page(sg); + + /* some SGs may not have a page mapped */ + if (page && page_ref_count(page)) + put_page(page); + } kfree(sreq->tsg); } diff --git a/crypto/chacha20_generic.c b/crypto/chacha20_generic.c index 8b3c04d625c3..4a45fa4890c0 100644 --- a/crypto/chacha20_generic.c +++ b/crypto/chacha20_generic.c @@ -91,9 +91,14 @@ int crypto_chacha20_crypt(struct skcipher_request *req) crypto_chacha20_init(state, ctx, walk.iv); while (walk.nbytes > 0) { + unsigned int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes = round_down(nbytes, walk.stride); + chacha20_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr, - walk.nbytes); - err = skcipher_walk_done(&walk, 0); + nbytes); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); } return err; diff --git a/crypto/testmgr.h b/crypto/testmgr.h index 6ceb0e2758bb..d54971d2d1c8 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -32675,6 +32675,10 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = { "\x5b\x86\x2f\x37\x30\xe3\x7c\xfd" "\xc4\xfd\x80\x6c\x22\xf2\x21", .rlen = 375, + .also_non_np = 1, + .np = 3, + .tap = { 375 - 20, 4, 16 }, + }, { /* RFC7539 A.2. Test Vector #3 */ .key = "\x1c\x92\x40\xa5\xeb\x55\xd3\x8a" "\xf3\x33\x88\x86\x04\xf6\xb5\xf0" @@ -33049,6 +33053,9 @@ static const struct cipher_testvec chacha20_enc_tv_template[] = { "\xa1\xed\xad\xd5\x76\xfa\x24\x8f" "\x98", .rlen = 1281, + .also_non_np = 1, + .np = 3, + .tap = { 1200, 1, 80 }, }, }; diff --git a/drivers/acpi/acpica/nsxfeval.c b/drivers/acpi/acpica/nsxfeval.c index 538c61677c10..783f4c838aee 100644 --- a/drivers/acpi/acpica/nsxfeval.c +++ b/drivers/acpi/acpica/nsxfeval.c @@ -100,9 +100,13 @@ acpi_evaluate_object_typed(acpi_handle handle, free_buffer_on_error = TRUE; } - status = acpi_get_handle(handle, pathname, &target_handle); - if (ACPI_FAILURE(status)) { - return_ACPI_STATUS(status); + if (pathname) { + status = acpi_get_handle(handle, pathname, &target_handle); + if (ACPI_FAILURE(status)) { + return_ACPI_STATUS(status); + } + } else { + target_handle = handle; } full_pathname = acpi_ns_get_external_pathname(target_handle); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 62068a5e814f..ae3d6d152633 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1741,7 +1741,7 @@ error: * functioning ECDT EC first in order to handle the events. * https://bugzilla.kernel.org/show_bug.cgi?id=115021 */ -int __init acpi_ec_ecdt_start(void) +static int __init acpi_ec_ecdt_start(void) { acpi_handle handle; @@ -2003,20 +2003,17 @@ static inline void acpi_ec_query_exit(void) int __init acpi_ec_init(void) { int result; + int ecdt_fail, dsdt_fail; /* register workqueue for _Qxx evaluations */ result = acpi_ec_query_init(); if (result) - goto err_exit; - /* Now register the driver for the EC */ - result = acpi_bus_register_driver(&acpi_ec_driver); - if (result) - goto err_exit; + return result; -err_exit: - if (result) - acpi_ec_query_exit(); - return result; + /* Drivers must be started after acpi_ec_query_init() */ + ecdt_fail = acpi_ec_ecdt_start(); + dsdt_fail = acpi_bus_register_driver(&acpi_ec_driver); + return ecdt_fail && dsdt_fail ? -ENODEV : 0; } /* EC driver currently not unloadable */ diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 58dd7ab3c653..3f5af4d7a739 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -185,7 +185,6 @@ typedef int (*acpi_ec_query_func) (void *data); int acpi_ec_init(void); int acpi_ec_ecdt_probe(void); int acpi_ec_dsdt_probe(void); -int acpi_ec_ecdt_start(void); void acpi_ec_block_transactions(void); void acpi_ec_unblock_transactions(void); int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c index 917c789f953d..476a52c60cf3 100644 --- a/drivers/acpi/property.c +++ b/drivers/acpi/property.c @@ -1047,7 +1047,7 @@ static struct fwnode_handle *acpi_graph_get_child_prop_value( fwnode_for_each_child_node(fwnode, child) { u32 nr; - if (!fwnode_property_read_u32(fwnode, prop_name, &nr)) + if (fwnode_property_read_u32(child, prop_name, &nr)) continue; if (val == nr) diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 33897298f03e..70fd5502c284 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2084,7 +2084,6 @@ int __init acpi_scan_init(void) acpi_gpe_apply_masked_gpes(); acpi_update_all_gpes(); - acpi_ec_ecdt_start(); acpi_scan_initialized = true; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index f7665c31feca..831cdd7d197d 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3362,7 +3362,7 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) const char *failure_string; struct binder_buffer *buffer; - if (proc->tsk != current) + if (proc->tsk != current->group_leader) return -EINVAL; if ((vma->vm_end - vma->vm_start) > SZ_4M) diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c index 1a50cd3b4233..9b34dff64536 100644 --- a/drivers/ata/ahci_da850.c +++ b/drivers/ata/ahci_da850.c @@ -216,12 +216,16 @@ static int ahci_da850_probe(struct platform_device *pdev) return rc; res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!res) + if (!res) { + rc = -ENODEV; goto disable_resources; + } pwrdn_reg = devm_ioremap(dev, res->start, resource_size(res)); - if (!pwrdn_reg) + if (!pwrdn_reg) { + rc = -ENOMEM; goto disable_resources; + } da850_sata_init(dev, pwrdn_reg, hpriv->mmio, mpy); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index fa7dd4394c02..1945a8ea2099 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2411,6 +2411,9 @@ static void ata_dev_config_trusted(struct ata_device *dev) u64 trusted_cap; unsigned int err; + if (!ata_id_has_trusted(dev->id)) + return; + if (!ata_identify_page_supported(dev, ATA_LOG_SECURITY)) { ata_dev_warn(dev, "Security Log not supported\n"); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ef8334949b42..f321b96405f5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -221,8 +221,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) } static int -figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit, - loff_t logical_blocksize) +figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { loff_t size = get_size(offset, sizelimit, lo->lo_backing_file); sector_t x = (sector_t)size; @@ -234,12 +233,6 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit, lo->lo_offset = offset; if (lo->lo_sizelimit != sizelimit) lo->lo_sizelimit = sizelimit; - if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) { - lo->lo_logical_blocksize = logical_blocksize; - blk_queue_physical_block_size(lo->lo_queue, lo->lo_blocksize); - blk_queue_logical_block_size(lo->lo_queue, - lo->lo_logical_blocksize); - } set_capacity(lo->lo_disk, x); bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9); /* let user-space know about the new size */ @@ -820,7 +813,6 @@ static void loop_config_discard(struct loop_device *lo) struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; - int lo_bits = 9; /* * We use punch hole to reclaim the free space used by the @@ -840,11 +832,9 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_granularity = inode->i_sb->s_blocksize; q->limits.discard_alignment = 0; - if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) - lo_bits = blksize_bits(lo->lo_logical_blocksize); - blk_queue_max_discard_sectors(q, UINT_MAX >> lo_bits); - blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> lo_bits); + blk_queue_max_discard_sectors(q, UINT_MAX >> 9); + blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); } @@ -938,7 +928,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->use_dio = false; lo->lo_blocksize = lo_blocksize; - lo->lo_logical_blocksize = 512; lo->lo_device = bdev; lo->lo_flags = lo_flags; lo->lo_backing_file = file; @@ -1104,7 +1093,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); - int lo_flags = lo->lo_flags; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && @@ -1137,26 +1125,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (err) goto exit; - if (info->lo_flags & LO_FLAGS_BLOCKSIZE) { - if (!(lo->lo_flags & LO_FLAGS_BLOCKSIZE)) - lo->lo_logical_blocksize = 512; - lo->lo_flags |= LO_FLAGS_BLOCKSIZE; - if (LO_INFO_BLOCKSIZE(info) != 512 && - LO_INFO_BLOCKSIZE(info) != 1024 && - LO_INFO_BLOCKSIZE(info) != 2048 && - LO_INFO_BLOCKSIZE(info) != 4096) - return -EINVAL; - if (LO_INFO_BLOCKSIZE(info) > lo->lo_blocksize) - return -EINVAL; - } - if (lo->lo_offset != info->lo_offset || - lo->lo_sizelimit != info->lo_sizelimit || - lo->lo_flags != lo_flags || - ((lo->lo_flags & LO_FLAGS_BLOCKSIZE) && - lo->lo_logical_blocksize != LO_INFO_BLOCKSIZE(info))) { - if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit, - LO_INFO_BLOCKSIZE(info))) { + lo->lo_sizelimit != info->lo_sizelimit) { + if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { err = -EFBIG; goto exit; } @@ -1348,8 +1319,7 @@ static int loop_set_capacity(struct loop_device *lo) if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; - return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit, - lo->lo_logical_blocksize); + return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); } static int loop_set_dio(struct loop_device *lo, unsigned long arg) diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 2c096b9a17b8..fecd3f97ef8c 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -49,7 +49,6 @@ struct loop_device { struct file * lo_backing_file; struct block_device *lo_device; unsigned lo_blocksize; - unsigned lo_logical_blocksize; void *key_data; gfp_t old_gfp_mask; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 1498b899a593..d3d5523862c2 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -381,6 +381,7 @@ static void virtblk_config_changed_work(struct work_struct *work) struct request_queue *q = vblk->disk->queue; char cap_str_2[10], cap_str_10[10]; char *envp[] = { "RESIZE=1", NULL }; + unsigned long long nblocks; u64 capacity; /* Host must always specify the capacity. */ @@ -393,16 +394,19 @@ static void virtblk_config_changed_work(struct work_struct *work) capacity = (sector_t)-1; } - string_get_size(capacity, queue_logical_block_size(q), + nblocks = DIV_ROUND_UP_ULL(capacity, queue_logical_block_size(q) >> 9); + + string_get_size(nblocks, queue_logical_block_size(q), STRING_UNITS_2, cap_str_2, sizeof(cap_str_2)); - string_get_size(capacity, queue_logical_block_size(q), + string_get_size(nblocks, queue_logical_block_size(q), STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); dev_notice(&vdev->dev, - "new size: %llu %d-byte logical blocks (%s/%s)\n", - (unsigned long long)capacity, - queue_logical_block_size(q), - cap_str_10, cap_str_2); + "new size: %llu %d-byte logical blocks (%s/%s)\n", + nblocks, + queue_logical_block_size(q), + cap_str_10, + cap_str_2); set_capacity(vblk->disk, capacity); revalidate_disk(vblk->disk); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 792da683e70d..2adb8599be93 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -244,6 +244,7 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) { struct pending_req *req, *n; unsigned int j, r; + bool busy = false; for (r = 0; r < blkif->nr_rings; r++) { struct xen_blkif_ring *ring = &blkif->rings[r]; @@ -261,8 +262,10 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) * don't have any discard_io or other_io requests. So, checking * for inflight IO is enough. */ - if (atomic_read(&ring->inflight) > 0) - return -EBUSY; + if (atomic_read(&ring->inflight) > 0) { + busy = true; + continue; + } if (ring->irq) { unbind_from_irqhandler(ring->irq, ring); @@ -300,6 +303,9 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); ring->active = false; } + if (busy) + return -EBUSY; + blkif->nr_ring_pages = 0; /* * blkif->rings was allocated in connect_ring, so we should free it in diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 98e34e4c62b8..2468c28d4771 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2075,9 +2075,9 @@ static int blkfront_resume(struct xenbus_device *dev) /* * Get the bios in the request so we can re-queue them. */ - if (req_op(shadow[i].request) == REQ_OP_FLUSH || - req_op(shadow[i].request) == REQ_OP_DISCARD || - req_op(shadow[i].request) == REQ_OP_SECURE_ERASE || + if (req_op(shadow[j].request) == REQ_OP_FLUSH || + req_op(shadow[j].request) == REQ_OP_DISCARD || + req_op(shadow[j].request) == REQ_OP_SECURE_ERASE || shadow[j].request->cmd_flags & REQ_FUA) { /* * Flush operations don't contain bios, so diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig index fcae5ca6ac92..54a67f8a28eb 100644 --- a/drivers/clocksource/Kconfig +++ b/drivers/clocksource/Kconfig @@ -262,7 +262,7 @@ config CLKSRC_LPC32XX config CLKSRC_PISTACHIO bool "Clocksource for Pistachio SoC" if COMPILE_TEST - depends on HAS_IOMEM + depends on GENERIC_CLOCKEVENTS && HAS_IOMEM select TIMER_OF help Enables the clocksource for the Pistachio SoC. diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index aae87c4c546e..72bbfccef113 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -1440,7 +1440,7 @@ static int __init arch_timer_mem_acpi_init(int platform_timer_count) * While unlikely, it's theoretically possible that none of the frames * in a timer expose the combination of feature we want. */ - for (i = i; i < timer_count; i++) { + for (i = 0; i < timer_count; i++) { timer = &timers[i]; frame = arch_timer_mem_find_best_frame(timer); diff --git a/drivers/clocksource/em_sti.c b/drivers/clocksource/em_sti.c index bc48cbf6a795..269db74a0658 100644 --- a/drivers/clocksource/em_sti.c +++ b/drivers/clocksource/em_sti.c @@ -305,7 +305,7 @@ static int em_sti_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { dev_err(&pdev->dev, "failed to get irq\n"); - return -EINVAL; + return irq; } /* map memory, let base point to the STI instance */ @@ -314,11 +314,12 @@ static int em_sti_probe(struct platform_device *pdev) if (IS_ERR(p->base)) return PTR_ERR(p->base); - if (devm_request_irq(&pdev->dev, irq, em_sti_interrupt, - IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING, - dev_name(&pdev->dev), p)) { + ret = devm_request_irq(&pdev->dev, irq, em_sti_interrupt, + IRQF_TIMER | IRQF_IRQPOLL | IRQF_NOBALANCING, + dev_name(&pdev->dev), p); + if (ret) { dev_err(&pdev->dev, "failed to request low IRQ\n"); - return -ENOENT; + return ret; } /* get hold of clock */ diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index d509b500a7b5..4d7aef9d9c15 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -128,9 +128,9 @@ static __init int timer_base_init(struct device_node *np, const char *name = of_base->name ? of_base->name : np->full_name; of_base->base = of_io_request_and_map(np, of_base->index, name); - if (!of_base->base) { + if (IS_ERR(of_base->base)) { pr_err("Failed to iomap (%s)\n", name); - return -ENXIO; + return PTR_ERR(of_base->base); } return 0; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 0566455f233e..65ee4fcace1f 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1613,8 +1613,7 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time) static inline int32_t get_avg_frequency(struct cpudata *cpu) { - return mul_ext_fp(cpu->sample.core_avg_perf, - cpu->pstate.max_pstate_physical * cpu->pstate.scaling); + return mul_ext_fp(cpu->sample.core_avg_perf, cpu_khz); } static inline int32_t get_avg_pstate(struct cpudata *cpu) diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 427cbe012729..dadc4a808df5 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -1073,7 +1073,7 @@ static int aead_perform(struct aead_request *req, int encrypt, req_ctx->hmac_virt = dma_pool_alloc(buffer_pool, flags, &crypt->icv_rev_aes); if (unlikely(!req_ctx->hmac_virt)) - goto free_buf_src; + goto free_buf_dst; if (!encrypt) { scatterwalk_map_and_copy(req_ctx->hmac_virt, req->src, cryptlen, authsize, 0); @@ -1088,10 +1088,10 @@ static int aead_perform(struct aead_request *req, int encrypt, BUG_ON(qmgr_stat_overflow(SEND_QID)); return -EINPROGRESS; -free_buf_src: - free_buf_chain(dev, req_ctx->src, crypt->src_buf); free_buf_dst: free_buf_chain(dev, req_ctx->dst, crypt->dst_buf); +free_buf_src: + free_buf_chain(dev, req_ctx->src, crypt->src_buf); crypt->ctl_flags = CTL_FLAG_UNUSED; return -ENOMEM; } diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index b10cbaa82ff5..b26256f23d67 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -717,8 +717,8 @@ static int tegra_adma_probe(struct platform_device *pdev) tdc->chan_addr = tdma->base_addr + ADMA_CH_REG_OFFSET(i); tdc->irq = of_irq_get(pdev->dev.of_node, i); - if (tdc->irq < 0) { - ret = tdc->irq; + if (tdc->irq <= 0) { + ret = tdc->irq ?: -ENXIO; goto irq_dispose; } diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c index e338c3743562..45c65f805fd6 100644 --- a/drivers/gpio/gpio-mvebu.c +++ b/drivers/gpio/gpio-mvebu.c @@ -557,7 +557,7 @@ static void mvebu_gpio_irq_handler(struct irq_desc *desc) edge_cause = mvebu_gpio_read_edge_cause(mvchip); edge_mask = mvebu_gpio_read_edge_mask(mvchip); - cause = (data_in ^ level_mask) | (edge_cause & edge_mask); + cause = (data_in & level_mask) | (edge_cause & edge_mask); for (i = 0; i < mvchip->chip.ngpio; i++) { int irq; diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index 16fe9742597b..fc80add5fedb 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -2,6 +2,7 @@ #include <linux/mutex.h> #include <linux/device.h> #include <linux/sysfs.h> +#include <linux/gpio.h> #include <linux/gpio/consumer.h> #include <linux/gpio/driver.h> #include <linux/interrupt.h> @@ -432,6 +433,11 @@ static struct attribute *gpiochip_attrs[] = { }; ATTRIBUTE_GROUPS(gpiochip); +static struct gpio_desc *gpio_to_valid_desc(int gpio) +{ + return gpio_is_valid(gpio) ? gpio_to_desc(gpio) : NULL; +} + /* * /sys/class/gpio/export ... write-only * integer N ... number of GPIO to export (full access) @@ -450,7 +456,7 @@ static ssize_t export_store(struct class *class, if (status < 0) goto done; - desc = gpio_to_desc(gpio); + desc = gpio_to_valid_desc(gpio); /* reject invalid GPIOs */ if (!desc) { pr_warn("%s: invalid GPIO %ld\n", __func__, gpio); @@ -493,7 +499,7 @@ static ssize_t unexport_store(struct class *class, if (status < 0) goto done; - desc = gpio_to_desc(gpio); + desc = gpio_to_valid_desc(gpio); /* reject bogus commands (gpio_unexport ignores them) */ if (!desc) { pr_warn("%s: invalid GPIO %ld\n", __func__, gpio); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index 6558a3ed57a7..e1cde6b80027 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -147,36 +147,6 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node, } /** - * amdgpu_mn_invalidate_page - callback to notify about mm change - * - * @mn: our notifier - * @mn: the mm this callback is about - * @address: address of invalidate page - * - * Invalidation of a single page. Blocks for all BOs mapping it - * and unmap them by move them into system domain again. - */ -static void amdgpu_mn_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn); - struct interval_tree_node *it; - - mutex_lock(&rmn->lock); - - it = interval_tree_iter_first(&rmn->objects, address, address); - if (it) { - struct amdgpu_mn_node *node; - - node = container_of(it, struct amdgpu_mn_node, it); - amdgpu_mn_invalidate_node(node, address, address); - } - - mutex_unlock(&rmn->lock); -} - -/** * amdgpu_mn_invalidate_range_start - callback to notify about mm change * * @mn: our notifier @@ -215,7 +185,6 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn, static const struct mmu_notifier_ops amdgpu_mn_ops = { .release = amdgpu_mn_release, - .invalidate_page = amdgpu_mn_invalidate_page, .invalidate_range_start = amdgpu_mn_invalidate_range_start, }; diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c index 2d51a2269fc6..5131bfb94f06 100644 --- a/drivers/gpu/drm/bridge/sil-sii8620.c +++ b/drivers/gpu/drm/bridge/sil-sii8620.c @@ -597,9 +597,9 @@ static void sii8620_mt_read_devcap(struct sii8620 *ctx, bool xdevcap) static void sii8620_mt_read_devcap_reg_recv(struct sii8620 *ctx, struct sii8620_mt_msg *msg) { - u8 reg = msg->reg[0] & 0x7f; + u8 reg = msg->reg[1] & 0x7f; - if (msg->reg[0] & 0x80) + if (msg->reg[1] & 0x80) ctx->xdevcap[reg] = msg->ret; else ctx->devcap[reg] = msg->ret; diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 1b755439f591..2fd383d7253a 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -1631,6 +1631,9 @@ int drm_atomic_check_only(struct drm_atomic_state *state) if (config->funcs->atomic_check) ret = config->funcs->atomic_check(state->dev, state); + if (ret) + return ret; + if (!state->allow_modeset) { for_each_new_crtc_in_state(state, crtc, crtc_state, i) { if (drm_atomic_crtc_needs_modeset(crtc_state)) { @@ -1641,7 +1644,7 @@ int drm_atomic_check_only(struct drm_atomic_state *state) } } - return ret; + return 0; } EXPORT_SYMBOL(drm_atomic_check_only); @@ -2203,10 +2206,10 @@ int drm_mode_atomic_ioctl(struct drm_device *dev, struct drm_atomic_state *state; struct drm_modeset_acquire_ctx ctx; struct drm_plane *plane; - struct drm_out_fence_state *fence_state = NULL; + struct drm_out_fence_state *fence_state; unsigned plane_mask; int ret = 0; - unsigned int i, j, num_fences = 0; + unsigned int i, j, num_fences; /* disallow for drivers not supporting atomic: */ if (!drm_core_check_feature(dev, DRIVER_ATOMIC)) @@ -2247,6 +2250,8 @@ retry: plane_mask = 0; copied_objs = 0; copied_props = 0; + fence_state = NULL; + num_fences = 0; for (i = 0; i < arg->count_objs; i++) { uint32_t obj_id, count_props; diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index ad4e9cfe48a2..88c6d78ee2d5 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -255,13 +255,13 @@ drm_gem_object_release_handle(int id, void *ptr, void *data) struct drm_gem_object *obj = ptr; struct drm_device *dev = obj->dev; + if (dev->driver->gem_close_object) + dev->driver->gem_close_object(obj, file_priv); + if (drm_core_check_feature(dev, DRIVER_PRIME)) drm_gem_remove_prime_handles(obj, file_priv); drm_vma_node_revoke(&obj->vma_node, file_priv); - if (dev->driver->gem_close_object) - dev->driver->gem_close_object(obj, file_priv); - drm_gem_object_handle_put_unlocked(obj); return 0; diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c index 85ab1eec73e5..7a00351d5b5d 100644 --- a/drivers/gpu/drm/drm_plane.c +++ b/drivers/gpu/drm/drm_plane.c @@ -719,6 +719,7 @@ int drm_mode_setplane(struct drm_device *dev, void *data, crtc = drm_crtc_find(dev, plane_req->crtc_id); if (!crtc) { + drm_framebuffer_put(fb); DRM_DEBUG_KMS("Unknown crtc ID %d\n", plane_req->crtc_id); return -ENOENT; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 72b97ce525e8..21c36e256884 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -2714,7 +2714,7 @@ static int shadow_indirect_ctx(struct intel_shadow_wa_ctx *wa_ctx) unmap_src: i915_gem_object_unpin_map(obj); put_obj: - i915_gem_object_put(wa_ctx->indirect_ctx.obj); + i915_gem_object_put(obj); return ret; } diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index b0738d2b2a7f..6f972e6ec663 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -1221,6 +1221,14 @@ static int intel_init_workaround_bb(struct intel_engine_cs *engine) return ret; } +static u8 gtiir[] = { + [RCS] = 0, + [BCS] = 0, + [VCS] = 1, + [VCS2] = 1, + [VECS] = 3, +}; + static int gen8_init_common_ring(struct intel_engine_cs *engine) { struct drm_i915_private *dev_priv = engine->i915; @@ -1245,9 +1253,22 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine) DRM_DEBUG_DRIVER("Execlists enabled for %s\n", engine->name); - /* After a GPU reset, we may have requests to replay */ + GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir)); + + /* + * Clear any pending interrupt state. + * + * We do it twice out of paranoia that some of the IIR are double + * buffered, and if we only reset it once there may still be + * an interrupt pending. + */ + I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]), + GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift); + I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]), + GT_CONTEXT_SWITCH_INTERRUPT << engine->irq_shift); clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted); + /* After a GPU reset, we may have requests to replay */ submit = false; for (n = 0; n < ARRAY_SIZE(engine->execlist_port); n++) { if (!port_isset(&port[n])) diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index 227309b01206..cf98596c7ce1 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -569,15 +569,13 @@ static void ipu_plane_atomic_update(struct drm_plane *plane, return; } + ics = ipu_drm_fourcc_to_colorspace(fb->format->format); switch (ipu_plane->dp_flow) { case IPU_DP_FLOW_SYNC_BG: - ipu_dp_setup_channel(ipu_plane->dp, - IPUV3_COLORSPACE_RGB, - IPUV3_COLORSPACE_RGB); + ipu_dp_setup_channel(ipu_plane->dp, ics, IPUV3_COLORSPACE_RGB); ipu_dp_set_global_alpha(ipu_plane->dp, true, 0, true); break; case IPU_DP_FLOW_SYNC_FG: - ics = ipu_drm_fourcc_to_colorspace(fb->format->format); ipu_dp_setup_channel(ipu_plane->dp, ics, IPUV3_COLORSPACE_UNKNOWN); /* Enable local alpha on partial plane */ diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index c41f48ae7913..ff3d0f5efbb1 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -270,11 +270,15 @@ static void rockchip_drm_fb_resume(struct drm_device *drm) static int rockchip_drm_sys_suspend(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct rockchip_drm_private *priv = drm->dev_private; + struct rockchip_drm_private *priv; + + if (!drm) + return 0; drm_kms_helper_poll_disable(drm); rockchip_drm_fb_suspend(drm); + priv = drm->dev_private; priv->state = drm_atomic_helper_suspend(drm); if (IS_ERR(priv->state)) { rockchip_drm_fb_resume(drm); @@ -288,8 +292,12 @@ static int rockchip_drm_sys_suspend(struct device *dev) static int rockchip_drm_sys_resume(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct rockchip_drm_private *priv = drm->dev_private; + struct rockchip_drm_private *priv; + + if (!drm) + return 0; + priv = drm->dev_private; drm_atomic_helper_resume(drm, priv->state); rockchip_drm_fb_resume(drm); drm_kms_helper_poll_enable(drm); diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c index d599206a1e86..ace59651892f 100644 --- a/drivers/gpu/drm/sun4i/sun4i_drv.c +++ b/drivers/gpu/drm/sun4i/sun4i_drv.c @@ -25,12 +25,20 @@ #include "sun4i_framebuffer.h" #include "sun4i_tcon.h" +static void sun4i_drv_lastclose(struct drm_device *dev) +{ + struct sun4i_drv *drv = dev->dev_private; + + drm_fbdev_cma_restore_mode(drv->fbdev); +} + DEFINE_DRM_GEM_CMA_FOPS(sun4i_drv_fops); static struct drm_driver sun4i_drv_driver = { .driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC, /* Generic Operations */ + .lastclose = sun4i_drv_lastclose, .fops = &sun4i_drv_fops, .name = "sun4i-drm", .desc = "Allwinner sun4i Display Engine", diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 5d50e45ae274..b850562fbdd6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1566,10 +1566,34 @@ vmw_kms_atomic_check_modeset(struct drm_device *dev, } +/** + * vmw_kms_atomic_commit - Perform an atomic state commit + * + * @dev: DRM device + * @state: the driver state object + * @nonblock: Whether nonblocking behaviour is requested + * + * This is a simple wrapper around drm_atomic_helper_commit() for + * us to clear the nonblocking value. + * + * Nonblocking commits currently cause synchronization issues + * for vmwgfx. + * + * RETURNS + * Zero for success or negative error code on failure. + */ +int vmw_kms_atomic_commit(struct drm_device *dev, + struct drm_atomic_state *state, + bool nonblock) +{ + return drm_atomic_helper_commit(dev, state, false); +} + + static const struct drm_mode_config_funcs vmw_kms_funcs = { .fb_create = vmw_kms_fb_create, .atomic_check = vmw_kms_atomic_check_modeset, - .atomic_commit = drm_atomic_helper_commit, + .atomic_commit = vmw_kms_atomic_commit, }; static int vmw_kms_generic_present(struct vmw_private *dev_priv, diff --git a/drivers/gpu/ipu-v3/Kconfig b/drivers/gpu/ipu-v3/Kconfig index 08766c6e7856..87a20b3dcf7a 100644 --- a/drivers/gpu/ipu-v3/Kconfig +++ b/drivers/gpu/ipu-v3/Kconfig @@ -1,6 +1,7 @@ config IMX_IPUV3_CORE tristate "IPUv3 core support" depends on SOC_IMX5 || SOC_IMX6Q || ARCH_MULTIPLATFORM + depends on DRM || !DRM # if DRM=m, this can't be 'y' select GENERIC_IRQ_CHIP help Choose this if you have a i.MX5/6 system and want to use the Image diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c index f19348328a71..6fdf9231c23c 100644 --- a/drivers/i2c/busses/i2c-aspeed.c +++ b/drivers/i2c/busses/i2c-aspeed.c @@ -410,10 +410,11 @@ static bool aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus) } /* We are in an invalid state; reset bus to a known state. */ - if (!bus->msgs && bus->master_state != ASPEED_I2C_MASTER_STOP) { + if (!bus->msgs) { dev_err(bus->dev, "bus in unknown state"); bus->cmd_err = -EIO; - aspeed_i2c_do_stop(bus); + if (bus->master_state != ASPEED_I2C_MASTER_STOP) + aspeed_i2c_do_stop(bus); goto out_no_complete; } msg = &bus->msgs[bus->msgs_index]; diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 143a8fd582b4..2b98a173136f 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -198,8 +198,7 @@ static void i2c_dw_configure_slave(struct dw_i2c_dev *dev) dev->functionality = I2C_FUNC_SLAVE | DW_IC_DEFAULT_FUNCTIONALITY; dev->slave_cfg = DW_IC_CON_RX_FIFO_FULL_HLD_CTRL | - DW_IC_CON_RESTART_EN | DW_IC_CON_STOP_DET_IFADDRESSED | - DW_IC_CON_SPEED_FAST; + DW_IC_CON_RESTART_EN | DW_IC_CON_STOP_DET_IFADDRESSED; dev->mode = DW_IC_SLAVE; @@ -257,7 +256,8 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) struct dw_i2c_dev *dev; u32 acpi_speed, ht = 0; struct resource *mem; - int irq, ret; + int i, irq, ret; + const int supported_speeds[] = { 0, 100000, 400000, 1000000, 3400000 }; irq = platform_get_irq(pdev, 0); if (irq < 0) @@ -298,9 +298,16 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) } acpi_speed = i2c_acpi_find_bus_speed(&pdev->dev); - /* Some broken DSTDs use 1MiHz instead of 1MHz */ - if (acpi_speed == 1048576) - acpi_speed = 1000000; + /* + * Some DSTDs use a non standard speed, round down to the lowest + * standard speed. + */ + for (i = 1; i < ARRAY_SIZE(supported_speeds); i++) { + if (acpi_speed < supported_speeds[i]) + break; + } + acpi_speed = supported_speeds[i - 1]; + /* * Find bus speed from the "clock-frequency" device property, ACPI * or by using fast mode if neither is set. @@ -430,7 +437,7 @@ static void dw_i2c_plat_complete(struct device *dev) #endif #ifdef CONFIG_PM -static int dw_i2c_plat_suspend(struct device *dev) +static int dw_i2c_plat_runtime_suspend(struct device *dev) { struct platform_device *pdev = to_platform_device(dev); struct dw_i2c_dev *i_dev = platform_get_drvdata(pdev); @@ -452,11 +459,21 @@ static int dw_i2c_plat_resume(struct device *dev) return 0; } +#ifdef CONFIG_PM_SLEEP +static int dw_i2c_plat_suspend(struct device *dev) +{ + pm_runtime_resume(dev); + return dw_i2c_plat_runtime_suspend(dev); +} +#endif + static const struct dev_pm_ops dw_i2c_dev_pm_ops = { .prepare = dw_i2c_plat_prepare, .complete = dw_i2c_plat_complete, SET_SYSTEM_SLEEP_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume) - SET_RUNTIME_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume, NULL) + SET_RUNTIME_PM_OPS(dw_i2c_plat_runtime_suspend, + dw_i2c_plat_resume, + NULL) }; #define DW_I2C_DEV_PMOPS (&dw_i2c_dev_pm_ops) diff --git a/drivers/i2c/busses/i2c-designware-slave.c b/drivers/i2c/busses/i2c-designware-slave.c index 0548c7ea578c..78d8fb73927d 100644 --- a/drivers/i2c/busses/i2c-designware-slave.c +++ b/drivers/i2c/busses/i2c-designware-slave.c @@ -177,6 +177,8 @@ static int i2c_dw_reg_slave(struct i2c_client *slave) return -EBUSY; if (slave->flags & I2C_CLIENT_TEN) return -EAFNOSUPPORT; + pm_runtime_get_sync(dev->dev); + /* * Set slave address in the IC_SAR register, * the address to which the DW_apb_i2c responds. @@ -205,6 +207,7 @@ static int i2c_dw_unreg_slave(struct i2c_client *slave) dev->disable_int(dev); dev->disable(dev); dev->slave = NULL; + pm_runtime_put(dev->dev); return 0; } @@ -272,7 +275,7 @@ static int i2c_dw_irq_handler_slave(struct dw_i2c_dev *dev) slave_activity = ((dw_readl(dev, DW_IC_STATUS) & DW_IC_STATUS_SLAVE_ACTIVITY) >> 6); - if (!enabled || !(raw_stat & ~DW_IC_INTR_ACTIVITY)) + if (!enabled || !(raw_stat & ~DW_IC_INTR_ACTIVITY) || !dev->slave) return 0; dev_dbg(dev->dev, @@ -382,7 +385,6 @@ int i2c_dw_probe_slave(struct dw_i2c_dev *dev) ret = i2c_add_numbered_adapter(adap); if (ret) dev_err(dev->dev, "failure adding adapter: %d\n", ret); - pm_runtime_put_noidle(dev->dev); return ret; } diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index e98e44e584a4..22ffcb73c185 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -341,8 +341,10 @@ static int ismt_process_desc(const struct ismt_desc *desc, break; case I2C_SMBUS_BLOCK_DATA: case I2C_SMBUS_I2C_BLOCK_DATA: - memcpy(&data->block[1], dma_buffer, desc->rxbytes); - data->block[0] = desc->rxbytes; + if (desc->rxbytes != dma_buffer[0] + 1) + return -EMSGSIZE; + + memcpy(data->block, dma_buffer, desc->rxbytes); break; } return 0; diff --git a/drivers/i2c/busses/i2c-simtec.c b/drivers/i2c/busses/i2c-simtec.c index b4685bb9b5d7..adca51a99487 100644 --- a/drivers/i2c/busses/i2c-simtec.c +++ b/drivers/i2c/busses/i2c-simtec.c @@ -127,8 +127,7 @@ static int simtec_i2c_probe(struct platform_device *dev) iounmap(pd->reg); err_res: - release_resource(pd->ioarea); - kfree(pd->ioarea); + release_mem_region(pd->ioarea->start, size); err: kfree(pd); @@ -142,8 +141,7 @@ static int simtec_i2c_remove(struct platform_device *dev) i2c_del_adapter(&pd->adap); iounmap(pd->reg); - release_resource(pd->ioarea); - kfree(pd->ioarea); + release_mem_region(pd->ioarea->start, resource_size(pd->ioarea)); kfree(pd); return 0; diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 12822a4b8f8f..56e46581b84b 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -353,8 +353,8 @@ static int i2c_device_probe(struct device *dev) } /* - * An I2C ID table is not mandatory, if and only if, a suitable Device - * Tree match table entry is supplied for the probing device. + * An I2C ID table is not mandatory, if and only if, a suitable OF + * or ACPI ID table is supplied for the probing device. */ if (!driver->id_table && !i2c_acpi_match_device(dev->driver->acpi_match_table, client) && diff --git a/drivers/iio/adc/ina2xx-adc.c b/drivers/iio/adc/ina2xx-adc.c index 232c0b80d658..c3f86138cb55 100644 --- a/drivers/iio/adc/ina2xx-adc.c +++ b/drivers/iio/adc/ina2xx-adc.c @@ -644,7 +644,7 @@ static int ina2xx_capture_thread(void *data) { struct iio_dev *indio_dev = data; struct ina2xx_chip_info *chip = iio_priv(indio_dev); - unsigned int sampling_us = SAMPLING_PERIOD(chip); + int sampling_us = SAMPLING_PERIOD(chip); int buffer_us; /* diff --git a/drivers/iio/adc/stm32-adc-core.c b/drivers/iio/adc/stm32-adc-core.c index e09233b03c05..609676384f5e 100644 --- a/drivers/iio/adc/stm32-adc-core.c +++ b/drivers/iio/adc/stm32-adc-core.c @@ -64,7 +64,7 @@ #define STM32H7_CKMODE_MASK GENMASK(17, 16) /* STM32 H7 maximum analog clock rate (from datasheet) */ -#define STM32H7_ADC_MAX_CLK_RATE 72000000 +#define STM32H7_ADC_MAX_CLK_RATE 36000000 /** * stm32_adc_common_regs - stm32 common registers, compatible dependent data @@ -148,14 +148,14 @@ static int stm32f4_adc_clk_sel(struct platform_device *pdev, return -EINVAL; } - priv->common.rate = rate; + priv->common.rate = rate / stm32f4_pclk_div[i]; val = readl_relaxed(priv->common.base + STM32F4_ADC_CCR); val &= ~STM32F4_ADC_ADCPRE_MASK; val |= i << STM32F4_ADC_ADCPRE_SHIFT; writel_relaxed(val, priv->common.base + STM32F4_ADC_CCR); dev_dbg(&pdev->dev, "Using analog clock source at %ld kHz\n", - rate / (stm32f4_pclk_div[i] * 1000)); + priv->common.rate / 1000); return 0; } @@ -250,7 +250,7 @@ static int stm32h7_adc_clk_sel(struct platform_device *pdev, out: /* rate used later by each ADC instance to control BOOST mode */ - priv->common.rate = rate; + priv->common.rate = rate / div; /* Set common clock mode and prescaler */ val = readl_relaxed(priv->common.base + STM32H7_ADC_CCR); @@ -260,7 +260,7 @@ out: writel_relaxed(val, priv->common.base + STM32H7_ADC_CCR); dev_dbg(&pdev->dev, "Using %s clock/%d source at %ld kHz\n", - ckmode ? "bus" : "adc", div, rate / (div * 1000)); + ckmode ? "bus" : "adc", div, priv->common.rate / 1000); return 0; } diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c index 16ade0a0327b..0e4b379ada45 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c @@ -111,8 +111,6 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state) s32 poll_value = 0; if (state) { - if (!atomic_read(&st->user_requested_state)) - return 0; if (sensor_hub_device_open(st->hsdev)) return -EIO; @@ -161,6 +159,9 @@ static int _hid_sensor_power_state(struct hid_sensor_common *st, bool state) &report_val); } + pr_debug("HID_SENSOR %s set power_state %d report_state %d\n", + st->pdev->name, state_val, report_val); + sensor_hub_get_feature(st->hsdev, st->power_state.report_id, st->power_state.index, sizeof(state_val), &state_val); @@ -182,6 +183,7 @@ int hid_sensor_power_state(struct hid_sensor_common *st, bool state) ret = pm_runtime_get_sync(&st->pdev->dev); else { pm_runtime_mark_last_busy(&st->pdev->dev); + pm_runtime_use_autosuspend(&st->pdev->dev); ret = pm_runtime_put_autosuspend(&st->pdev->dev); } if (ret < 0) { @@ -285,8 +287,6 @@ int hid_sensor_setup_trigger(struct iio_dev *indio_dev, const char *name, /* Default to 3 seconds, but can be changed from sysfs */ pm_runtime_set_autosuspend_delay(&attrb->pdev->dev, 3000); - pm_runtime_use_autosuspend(&attrb->pdev->dev); - return ret; error_unreg_trigger: iio_trigger_unregister(trig); diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index 8cf84d3488b2..12898424d838 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -696,7 +696,7 @@ static const struct adis16480_chip_info adis16480_chip_info[] = { .gyro_max_val = IIO_RAD_TO_DEGREE(22500), .gyro_max_scale = 450, .accel_max_val = IIO_M_S_2_TO_G(12500), - .accel_max_scale = 5, + .accel_max_scale = 10, }, [ADIS16485] = { .channels = adis16485_channels, diff --git a/drivers/iio/magnetometer/st_magn_core.c b/drivers/iio/magnetometer/st_magn_core.c index 8e1b0861fbe4..c38563699984 100644 --- a/drivers/iio/magnetometer/st_magn_core.c +++ b/drivers/iio/magnetometer/st_magn_core.c @@ -356,9 +356,7 @@ static const struct st_sensor_settings st_magn_sensors_settings[] = { .drdy_irq = { .addr = 0x62, .mask_int1 = 0x01, - .addr_ihl = 0x63, - .mask_ihl = 0x04, - .addr_stat_drdy = ST_SENSORS_DEFAULT_STAT_ADDR, + .addr_stat_drdy = 0x67, }, .multi_read_bit = false, .bootime = 2, diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index d82b788374b6..0d2ea3ee371b 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -282,6 +282,11 @@ static int bmp280_read_temp(struct bmp280_data *data, } adc_temp = be32_to_cpu(tmp) >> 12; + if (adc_temp == BMP280_TEMP_SKIPPED) { + /* reading was skipped */ + dev_err(data->dev, "reading temperature skipped\n"); + return -EIO; + } comp_temp = bmp280_compensate_temp(data, adc_temp); /* @@ -317,6 +322,11 @@ static int bmp280_read_press(struct bmp280_data *data, } adc_press = be32_to_cpu(tmp) >> 12; + if (adc_press == BMP280_PRESS_SKIPPED) { + /* reading was skipped */ + dev_err(data->dev, "reading pressure skipped\n"); + return -EIO; + } comp_press = bmp280_compensate_press(data, adc_press); *val = comp_press; @@ -345,6 +355,11 @@ static int bmp280_read_humid(struct bmp280_data *data, int *val, int *val2) } adc_humidity = be16_to_cpu(tmp); + if (adc_humidity == BMP280_HUMIDITY_SKIPPED) { + /* reading was skipped */ + dev_err(data->dev, "reading humidity skipped\n"); + return -EIO; + } comp_humidity = bmp280_compensate_humidity(data, adc_humidity); *val = comp_humidity; @@ -597,14 +612,20 @@ static const struct bmp280_chip_info bmp280_chip_info = { static int bme280_chip_config(struct bmp280_data *data) { - int ret = bmp280_chip_config(data); + int ret; u8 osrs = BMP280_OSRS_HUMIDITIY_X(data->oversampling_humid + 1); + /* + * Oversampling of humidity must be set before oversampling of + * temperature/pressure is set to become effective. + */ + ret = regmap_update_bits(data->regmap, BMP280_REG_CTRL_HUMIDITY, + BMP280_OSRS_HUMIDITY_MASK, osrs); + if (ret < 0) return ret; - return regmap_update_bits(data->regmap, BMP280_REG_CTRL_HUMIDITY, - BMP280_OSRS_HUMIDITY_MASK, osrs); + return bmp280_chip_config(data); } static const struct bmp280_chip_info bme280_chip_info = { diff --git a/drivers/iio/pressure/bmp280.h b/drivers/iio/pressure/bmp280.h index 2c770e13be0e..61347438b779 100644 --- a/drivers/iio/pressure/bmp280.h +++ b/drivers/iio/pressure/bmp280.h @@ -96,6 +96,11 @@ #define BME280_CHIP_ID 0x60 #define BMP280_SOFT_RESET_VAL 0xB6 +/* BMP280 register skipped special values */ +#define BMP280_TEMP_SKIPPED 0x80000 +#define BMP280_PRESS_SKIPPED 0x80000 +#define BMP280_HUMIDITY_SKIPPED 0x8000 + /* Regmap configurations */ extern const struct regmap_config bmp180_regmap_config; extern const struct regmap_config bmp280_regmap_config; diff --git a/drivers/iio/trigger/stm32-timer-trigger.c b/drivers/iio/trigger/stm32-timer-trigger.c index d22bc56dd9fc..25ad6abfee22 100644 --- a/drivers/iio/trigger/stm32-timer-trigger.c +++ b/drivers/iio/trigger/stm32-timer-trigger.c @@ -366,34 +366,32 @@ static int stm32_counter_read_raw(struct iio_dev *indio_dev, int *val, int *val2, long mask) { struct stm32_timer_trigger *priv = iio_priv(indio_dev); + u32 dat; switch (mask) { case IIO_CHAN_INFO_RAW: - { - u32 cnt; - - regmap_read(priv->regmap, TIM_CNT, &cnt); - *val = cnt; + regmap_read(priv->regmap, TIM_CNT, &dat); + *val = dat; + return IIO_VAL_INT; + case IIO_CHAN_INFO_ENABLE: + regmap_read(priv->regmap, TIM_CR1, &dat); + *val = (dat & TIM_CR1_CEN) ? 1 : 0; return IIO_VAL_INT; - } - case IIO_CHAN_INFO_SCALE: - { - u32 smcr; - regmap_read(priv->regmap, TIM_SMCR, &smcr); - smcr &= TIM_SMCR_SMS; + case IIO_CHAN_INFO_SCALE: + regmap_read(priv->regmap, TIM_SMCR, &dat); + dat &= TIM_SMCR_SMS; *val = 1; *val2 = 0; /* in quadrature case scale = 0.25 */ - if (smcr == 3) + if (dat == 3) *val2 = 2; return IIO_VAL_FRACTIONAL_LOG2; } - } return -EINVAL; } @@ -403,15 +401,31 @@ static int stm32_counter_write_raw(struct iio_dev *indio_dev, int val, int val2, long mask) { struct stm32_timer_trigger *priv = iio_priv(indio_dev); + u32 dat; switch (mask) { case IIO_CHAN_INFO_RAW: - regmap_write(priv->regmap, TIM_CNT, val); + return regmap_write(priv->regmap, TIM_CNT, val); - return IIO_VAL_INT; case IIO_CHAN_INFO_SCALE: /* fixed scale */ return -EINVAL; + + case IIO_CHAN_INFO_ENABLE: + if (val) { + regmap_read(priv->regmap, TIM_CR1, &dat); + if (!(dat & TIM_CR1_CEN)) + clk_enable(priv->clk); + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, + TIM_CR1_CEN); + } else { + regmap_read(priv->regmap, TIM_CR1, &dat); + regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_CEN, + 0); + if (dat & TIM_CR1_CEN) + clk_disable(priv->clk); + } + return 0; } return -EINVAL; @@ -471,7 +485,7 @@ static int stm32_get_trigger_mode(struct iio_dev *indio_dev, regmap_read(priv->regmap, TIM_SMCR, &smcr); - return smcr == TIM_SMCR_SMS ? 0 : -EINVAL; + return (smcr & TIM_SMCR_SMS) == TIM_SMCR_SMS ? 0 : -EINVAL; } static const struct iio_enum stm32_trigger_mode_enum = { @@ -507,9 +521,19 @@ static int stm32_set_enable_mode(struct iio_dev *indio_dev, { struct stm32_timer_trigger *priv = iio_priv(indio_dev); int sms = stm32_enable_mode2sms(mode); + u32 val; if (sms < 0) return sms; + /* + * Triggered mode sets CEN bit automatically by hardware. So, first + * enable counter clock, so it can use it. Keeps it in sync with CEN. + */ + if (sms == 6) { + regmap_read(priv->regmap, TIM_CR1, &val); + if (!(val & TIM_CR1_CEN)) + clk_enable(priv->clk); + } regmap_update_bits(priv->regmap, TIM_SMCR, TIM_SMCR_SMS, sms); @@ -571,11 +595,14 @@ static int stm32_get_quadrature_mode(struct iio_dev *indio_dev, { struct stm32_timer_trigger *priv = iio_priv(indio_dev); u32 smcr; + int mode; regmap_read(priv->regmap, TIM_SMCR, &smcr); - smcr &= TIM_SMCR_SMS; + mode = (smcr & TIM_SMCR_SMS) - 1; + if ((mode < 0) || (mode > ARRAY_SIZE(stm32_quadrature_modes))) + return -EINVAL; - return smcr - 1; + return mode; } static const struct iio_enum stm32_quadrature_mode_enum = { @@ -592,13 +619,20 @@ static const char *const stm32_count_direction_states[] = { static int stm32_set_count_direction(struct iio_dev *indio_dev, const struct iio_chan_spec *chan, - unsigned int mode) + unsigned int dir) { struct stm32_timer_trigger *priv = iio_priv(indio_dev); + u32 val; + int mode; - regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_DIR, mode); + /* In encoder mode, direction is RO (given by TI1/TI2 signals) */ + regmap_read(priv->regmap, TIM_SMCR, &val); + mode = (val & TIM_SMCR_SMS) - 1; + if ((mode >= 0) || (mode < ARRAY_SIZE(stm32_quadrature_modes))) + return -EBUSY; - return 0; + return regmap_update_bits(priv->regmap, TIM_CR1, TIM_CR1_DIR, + dir ? TIM_CR1_DIR : 0); } static int stm32_get_count_direction(struct iio_dev *indio_dev, @@ -609,7 +643,7 @@ static int stm32_get_count_direction(struct iio_dev *indio_dev, regmap_read(priv->regmap, TIM_CR1, &cr1); - return (cr1 & TIM_CR1_DIR); + return ((cr1 & TIM_CR1_DIR) ? 1 : 0); } static const struct iio_enum stm32_count_direction_enum = { @@ -672,7 +706,9 @@ static const struct iio_chan_spec_ext_info stm32_trigger_count_info[] = { static const struct iio_chan_spec stm32_trigger_channel = { .type = IIO_COUNT, .channel = 0, - .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | BIT(IIO_CHAN_INFO_SCALE), + .info_mask_separate = BIT(IIO_CHAN_INFO_RAW) | + BIT(IIO_CHAN_INFO_ENABLE) | + BIT(IIO_CHAN_INFO_SCALE), .ext_info = stm32_trigger_count_info, .indexed = 1 }; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index a5dfab6adf49..221468f77128 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -537,10 +537,11 @@ void ib_unregister_device(struct ib_device *device) } up_read(&lists_rwsem); - mutex_unlock(&device_mutex); - ib_device_unregister_rdmacg(device); ib_device_unregister_sysfs(device); + + mutex_unlock(&device_mutex); + ib_cache_cleanup_one(device); ib_security_destroy_port_pkey_list(device); diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index 8c4ec564e495..55e8f5ed8b3c 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -166,24 +166,6 @@ static int invalidate_page_trampoline(struct ib_umem *item, u64 start, return 0; } -static void ib_umem_notifier_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn); - - if (!context->invalidate_range) - return; - - ib_ucontext_notifier_start_account(context); - down_read(&context->umem_rwsem); - rbt_ib_umem_for_each_in_range(&context->umem_tree, address, - address + PAGE_SIZE, - invalidate_page_trampoline, NULL); - up_read(&context->umem_rwsem); - ib_ucontext_notifier_end_account(context); -} - static int invalidate_range_start_trampoline(struct ib_umem *item, u64 start, u64 end, void *cookie) { @@ -237,7 +219,6 @@ static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn, static const struct mmu_notifier_ops ib_umem_notifiers = { .release = ib_umem_notifier_release, - .invalidate_page = ib_umem_notifier_invalidate_page, .invalidate_range_start = ib_umem_notifier_invalidate_range_start, .invalidate_range_end = ib_umem_notifier_invalidate_range_end, }; diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index c551d2b275fd..739bd69ef1d4 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1015,7 +1015,7 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file, cq->uobject = &obj->uobject; cq->comp_handler = ib_uverbs_comp_handler; cq->event_handler = ib_uverbs_cq_event_handler; - cq->cq_context = &ev_file->ev_queue; + cq->cq_context = ev_file ? &ev_file->ev_queue : NULL; atomic_set(&cq->usecnt, 0); obj->uobject.object = cq; @@ -1522,6 +1522,7 @@ static int create_qp(struct ib_uverbs_file *file, qp->qp_type = attr.qp_type; atomic_set(&qp->usecnt, 0); atomic_inc(&pd->usecnt); + qp->port = 0; if (attr.send_cq) atomic_inc(&attr.send_cq->usecnt); if (attr.recv_cq) @@ -1962,8 +1963,9 @@ static int modify_qp(struct ib_uverbs_file *file, attr->alt_timeout = cmd->base.alt_timeout; attr->rate_limit = cmd->rate_limit; - attr->ah_attr.type = rdma_ah_find_type(qp->device, - cmd->base.dest.port_num); + if (cmd->base.attr_mask & IB_QP_AV) + attr->ah_attr.type = rdma_ah_find_type(qp->device, + cmd->base.dest.port_num); if (cmd->base.dest.is_global) { rdma_ah_set_grh(&attr->ah_attr, NULL, cmd->base.dest.flow_label, @@ -1981,8 +1983,9 @@ static int modify_qp(struct ib_uverbs_file *file, rdma_ah_set_port_num(&attr->ah_attr, cmd->base.dest.port_num); - attr->alt_ah_attr.type = rdma_ah_find_type(qp->device, - cmd->base.dest.port_num); + if (cmd->base.attr_mask & IB_QP_ALT_PATH) + attr->alt_ah_attr.type = + rdma_ah_find_type(qp->device, cmd->base.dest.port_num); if (cmd->base.alt_dest.is_global) { rdma_ah_set_grh(&attr->alt_ah_attr, NULL, cmd->base.alt_dest.flow_label, diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index c023e2c81b8f..5e530d2bee44 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -1153,7 +1153,6 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, kref_get(&file->ref); mutex_unlock(&uverbs_dev->lists_mutex); - ib_uverbs_event_handler(&file->event_handler, &event); mutex_lock(&file->cleanup_mutex); ucontext = file->ucontext; @@ -1170,6 +1169,7 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, * for example due to freeing the resources * (e.g mmput). */ + ib_uverbs_event_handler(&file->event_handler, &event); ib_dev->disassociate_ucontext(ucontext); mutex_lock(&file->cleanup_mutex); ib_uverbs_cleanup_ucontext(file, ucontext, true); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 7f8fe443df46..b456e3ca1876 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -838,6 +838,7 @@ struct ib_qp *ib_create_qp(struct ib_pd *pd, spin_lock_init(&qp->mr_lock); INIT_LIST_HEAD(&qp->rdma_mrs); INIT_LIST_HEAD(&qp->sig_mrs); + qp->port = 0; if (qp_init_attr->qp_type == IB_QPT_XRC_TGT) return ib_create_xrc_qp(qp, qp_init_attr); @@ -1297,7 +1298,11 @@ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, if (ret) return ret; } - return ib_security_modify_qp(qp, attr, attr_mask, udata); + ret = ib_security_modify_qp(qp, attr, attr_mask, udata); + if (!ret && (attr_mask & IB_QP_PORT)) + qp->port = attr->port_num; + + return ret; } EXPORT_SYMBOL(ib_modify_qp_with_udata); diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 5332f06b99ba..c2fba76becd4 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -661,7 +661,7 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd, rhp = php->rhp; if (mr_type != IB_MR_TYPE_MEM_REG || - max_num_sg > t4_max_fr_depth(&rhp->rdev.lldi.ulptx_memwrite_dsgl && + max_num_sg > t4_max_fr_depth(rhp->rdev.lldi.ulptx_memwrite_dsgl && use_dsgl)) return ERR_PTR(-EINVAL); diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index ccbf52c8ff6f..e4b56a0dd6d0 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -67,8 +67,6 @@ struct mmu_rb_handler { static unsigned long mmu_node_start(struct mmu_rb_node *); static unsigned long mmu_node_last(struct mmu_rb_node *); -static inline void mmu_notifier_page(struct mmu_notifier *, struct mm_struct *, - unsigned long); static inline void mmu_notifier_range_start(struct mmu_notifier *, struct mm_struct *, unsigned long, unsigned long); @@ -82,7 +80,6 @@ static void do_remove(struct mmu_rb_handler *handler, static void handle_remove(struct work_struct *work); static const struct mmu_notifier_ops mn_opts = { - .invalidate_page = mmu_notifier_page, .invalidate_range_start = mmu_notifier_range_start, }; @@ -285,12 +282,6 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler, handler->ops->remove(handler->ops_arg, node); } -static inline void mmu_notifier_page(struct mmu_notifier *mn, - struct mm_struct *mm, unsigned long addr) -{ - mmu_notifier_mem_invalidate(mn, mm, addr, addr + PAGE_SIZE); -} - static inline void mmu_notifier_range_start(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c index f78a733a63ec..d545302b8ef8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_ah.c +++ b/drivers/infiniband/hw/hns/hns_roce_ah.c @@ -64,8 +64,10 @@ struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd, } else { u8 *dmac = rdma_ah_retrieve_dmac(ah_attr); - if (!dmac) + if (!dmac) { + kfree(ah); return ERR_PTR(-EINVAL); + } memcpy(ah->av.mac, dmac, ETH_ALEN); } diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c index 9ec1ae9a82c9..a49ff2eb6fb3 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c +++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c @@ -130,20 +130,32 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_commit_buf( u64 base = 0; u32 i, j; u32 k = 0; - u32 low; /* copy base values in obj_info */ - for (i = I40IW_HMC_IW_QP, j = 0; - i <= I40IW_HMC_IW_PBLE; i++, j += 8) { + for (i = I40IW_HMC_IW_QP, j = 0; i <= I40IW_HMC_IW_PBLE; i++, j += 8) { + if ((i == I40IW_HMC_IW_SRQ) || + (i == I40IW_HMC_IW_FSIMC) || + (i == I40IW_HMC_IW_FSIAV)) { + info[i].base = 0; + info[i].cnt = 0; + continue; + } get_64bit_val(buf, j, &temp); info[i].base = RS_64_1(temp, 32) * 512; if (info[i].base > base) { base = info[i].base; k = i; } - low = (u32)(temp); - if (low) - info[i].cnt = low; + if (i == I40IW_HMC_IW_APBVT_ENTRY) { + info[i].cnt = 1; + continue; + } + if (i == I40IW_HMC_IW_QP) + info[i].cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS); + else if (i == I40IW_HMC_IW_CQ) + info[i].cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS); + else + info[i].cnt = (u32)(temp); } size = info[k].cnt * info[k].size + info[k].base; if (size & 0x1FFFFF) @@ -155,6 +167,31 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_commit_buf( } /** + * i40iw_sc_decode_fpm_query() - Decode a 64 bit value into max count and size + * @buf: ptr to fpm query buffer + * @buf_idx: index into buf + * @info: ptr to i40iw_hmc_obj_info struct + * @rsrc_idx: resource index into info + * + * Decode a 64 bit value from fpm query buffer into max count and size + */ +static u64 i40iw_sc_decode_fpm_query(u64 *buf, + u32 buf_idx, + struct i40iw_hmc_obj_info *obj_info, + u32 rsrc_idx) +{ + u64 temp; + u32 size; + + get_64bit_val(buf, buf_idx, &temp); + obj_info[rsrc_idx].max_cnt = (u32)temp; + size = (u32)RS_64_1(temp, 32); + obj_info[rsrc_idx].size = LS_64_1(1, size); + + return temp; +} + +/** * i40iw_sc_parse_fpm_query_buf() - parses fpm query buffer * @buf: ptr to fpm query buffer * @info: ptr to i40iw_hmc_obj_info struct @@ -168,9 +205,9 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_query_buf( struct i40iw_hmc_info *hmc_info, struct i40iw_hmc_fpm_misc *hmc_fpm_misc) { - u64 temp; struct i40iw_hmc_obj_info *obj_info; - u32 i, j, size; + u64 temp; + u32 size; u16 max_pe_sds; obj_info = hmc_info->hmc_obj; @@ -185,41 +222,52 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_query_buf( hmc_fpm_misc->max_sds = max_pe_sds; hmc_info->sd_table.sd_cnt = max_pe_sds + hmc_info->first_sd_index; - for (i = I40IW_HMC_IW_QP, j = 8; - i <= I40IW_HMC_IW_ARP; i++, j += 8) { - get_64bit_val(buf, j, &temp); - if (i == I40IW_HMC_IW_QP) - obj_info[i].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS); - else if (i == I40IW_HMC_IW_CQ) - obj_info[i].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS); - else - obj_info[i].max_cnt = (u32)temp; + get_64bit_val(buf, 8, &temp); + obj_info[I40IW_HMC_IW_QP].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS); + size = (u32)RS_64_1(temp, 32); + obj_info[I40IW_HMC_IW_QP].size = LS_64_1(1, size); - size = (u32)RS_64_1(temp, 32); - obj_info[i].size = ((u64)1 << size); - } - for (i = I40IW_HMC_IW_MR, j = 48; - i <= I40IW_HMC_IW_PBLE; i++, j += 8) { - get_64bit_val(buf, j, &temp); - obj_info[i].max_cnt = (u32)temp; - size = (u32)RS_64_1(temp, 32); - obj_info[i].size = LS_64_1(1, size); - } + get_64bit_val(buf, 16, &temp); + obj_info[I40IW_HMC_IW_CQ].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS); + size = (u32)RS_64_1(temp, 32); + obj_info[I40IW_HMC_IW_CQ].size = LS_64_1(1, size); + + i40iw_sc_decode_fpm_query(buf, 32, obj_info, I40IW_HMC_IW_HTE); + i40iw_sc_decode_fpm_query(buf, 40, obj_info, I40IW_HMC_IW_ARP); + + obj_info[I40IW_HMC_IW_APBVT_ENTRY].size = 8192; + obj_info[I40IW_HMC_IW_APBVT_ENTRY].max_cnt = 1; + + i40iw_sc_decode_fpm_query(buf, 48, obj_info, I40IW_HMC_IW_MR); + i40iw_sc_decode_fpm_query(buf, 56, obj_info, I40IW_HMC_IW_XF); - get_64bit_val(buf, 120, &temp); - hmc_fpm_misc->max_ceqs = (u8)RS_64(temp, I40IW_QUERY_FPM_MAX_CEQS); - get_64bit_val(buf, 120, &temp); - hmc_fpm_misc->ht_multiplier = RS_64(temp, I40IW_QUERY_FPM_HTMULTIPLIER); - get_64bit_val(buf, 120, &temp); - hmc_fpm_misc->timer_bucket = RS_64(temp, I40IW_QUERY_FPM_TIMERBUCKET); get_64bit_val(buf, 64, &temp); + obj_info[I40IW_HMC_IW_XFFL].max_cnt = (u32)temp; + obj_info[I40IW_HMC_IW_XFFL].size = 4; hmc_fpm_misc->xf_block_size = RS_64(temp, I40IW_QUERY_FPM_XFBLOCKSIZE); if (!hmc_fpm_misc->xf_block_size) return I40IW_ERR_INVALID_SIZE; + + i40iw_sc_decode_fpm_query(buf, 72, obj_info, I40IW_HMC_IW_Q1); + get_64bit_val(buf, 80, &temp); + obj_info[I40IW_HMC_IW_Q1FL].max_cnt = (u32)temp; + obj_info[I40IW_HMC_IW_Q1FL].size = 4; hmc_fpm_misc->q1_block_size = RS_64(temp, I40IW_QUERY_FPM_Q1BLOCKSIZE); if (!hmc_fpm_misc->q1_block_size) return I40IW_ERR_INVALID_SIZE; + + i40iw_sc_decode_fpm_query(buf, 88, obj_info, I40IW_HMC_IW_TIMER); + + get_64bit_val(buf, 112, &temp); + obj_info[I40IW_HMC_IW_PBLE].max_cnt = (u32)temp; + obj_info[I40IW_HMC_IW_PBLE].size = 8; + + get_64bit_val(buf, 120, &temp); + hmc_fpm_misc->max_ceqs = (u8)RS_64(temp, I40IW_QUERY_FPM_MAX_CEQS); + hmc_fpm_misc->ht_multiplier = RS_64(temp, I40IW_QUERY_FPM_HTMULTIPLIER); + hmc_fpm_misc->timer_bucket = RS_64(temp, I40IW_QUERY_FPM_TIMERBUCKET); + return 0; } @@ -3392,13 +3440,6 @@ enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev, u8 hmc_fn_ hmc_info->sd_table.sd_entry = virt_mem.va; } - /* fill size of objects which are fixed */ - hmc_info->hmc_obj[I40IW_HMC_IW_XFFL].size = 4; - hmc_info->hmc_obj[I40IW_HMC_IW_Q1FL].size = 4; - hmc_info->hmc_obj[I40IW_HMC_IW_PBLE].size = 8; - hmc_info->hmc_obj[I40IW_HMC_IW_APBVT_ENTRY].size = 8192; - hmc_info->hmc_obj[I40IW_HMC_IW_APBVT_ENTRY].max_cnt = 1; - return ret_code; } @@ -4840,7 +4881,7 @@ void i40iw_vsi_stats_free(struct i40iw_sc_vsi *vsi) { u8 fcn_id = vsi->fcn_id; - if ((vsi->stats_fcn_id_alloc) && (fcn_id != I40IW_INVALID_FCN_ID)) + if (vsi->stats_fcn_id_alloc && fcn_id < I40IW_MAX_STATS_COUNT) vsi->dev->fcn_id_array[fcn_id] = false; i40iw_hw_stats_stop_timer(vsi); } diff --git a/drivers/infiniband/hw/i40iw/i40iw_d.h b/drivers/infiniband/hw/i40iw/i40iw_d.h index a39ac12b6a7e..2ebaadbed379 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_d.h +++ b/drivers/infiniband/hw/i40iw/i40iw_d.h @@ -1507,8 +1507,8 @@ enum { I40IW_CQ0_ALIGNMENT_MASK = (256 - 1), I40IW_HOST_CTX_ALIGNMENT_MASK = (4 - 1), I40IW_SHADOWAREA_MASK = (128 - 1), - I40IW_FPM_QUERY_BUF_ALIGNMENT_MASK = 0, - I40IW_FPM_COMMIT_BUF_ALIGNMENT_MASK = 0 + I40IW_FPM_QUERY_BUF_ALIGNMENT_MASK = (4 - 1), + I40IW_FPM_COMMIT_BUF_ALIGNMENT_MASK = (4 - 1) }; enum i40iw_alignment { diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c index 71050c5d29a0..7f5583d83622 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_puda.c +++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c @@ -685,7 +685,7 @@ static enum i40iw_status_code i40iw_puda_cq_create(struct i40iw_puda_rsrc *rsrc) cqsize = rsrc->cq_size * (sizeof(struct i40iw_cqe)); tsize = cqsize + sizeof(struct i40iw_cq_shadow_area); ret = i40iw_allocate_dma_mem(dev->hw, &rsrc->cqmem, tsize, - I40IW_CQ0_ALIGNMENT_MASK); + I40IW_CQ0_ALIGNMENT); if (ret) return ret; diff --git a/drivers/infiniband/hw/i40iw/i40iw_status.h b/drivers/infiniband/hw/i40iw/i40iw_status.h index 91c421762f06..f7013f11d808 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_status.h +++ b/drivers/infiniband/hw/i40iw/i40iw_status.h @@ -62,7 +62,7 @@ enum i40iw_status_code { I40IW_ERR_INVALID_ALIGNMENT = -23, I40IW_ERR_FLUSHED_QUEUE = -24, I40IW_ERR_INVALID_PUSH_PAGE_INDEX = -25, - I40IW_ERR_INVALID_IMM_DATA_SIZE = -26, + I40IW_ERR_INVALID_INLINE_DATA_SIZE = -26, I40IW_ERR_TIMEOUT = -27, I40IW_ERR_OPCODE_MISMATCH = -28, I40IW_ERR_CQP_COMPL_ERROR = -29, diff --git a/drivers/infiniband/hw/i40iw/i40iw_uk.c b/drivers/infiniband/hw/i40iw/i40iw_uk.c index b0d3a0e8a9b5..1060725d18bc 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_uk.c +++ b/drivers/infiniband/hw/i40iw/i40iw_uk.c @@ -435,7 +435,7 @@ static enum i40iw_status_code i40iw_inline_rdma_write(struct i40iw_qp_uk *qp, op_info = &info->op.inline_rdma_write; if (op_info->len > I40IW_MAX_INLINE_DATA_SIZE) - return I40IW_ERR_INVALID_IMM_DATA_SIZE; + return I40IW_ERR_INVALID_INLINE_DATA_SIZE; ret_code = i40iw_inline_data_size_to_wqesize(op_info->len, &wqe_size); if (ret_code) @@ -511,7 +511,7 @@ static enum i40iw_status_code i40iw_inline_send(struct i40iw_qp_uk *qp, op_info = &info->op.inline_send; if (op_info->len > I40IW_MAX_INLINE_DATA_SIZE) - return I40IW_ERR_INVALID_IMM_DATA_SIZE; + return I40IW_ERR_INVALID_INLINE_DATA_SIZE; ret_code = i40iw_inline_data_size_to_wqesize(op_info->len, &wqe_size); if (ret_code) @@ -784,7 +784,7 @@ static enum i40iw_status_code i40iw_cq_poll_completion(struct i40iw_cq_uk *cq, get_64bit_val(cqe, 0, &qword0); get_64bit_val(cqe, 16, &qword2); - info->tcp_seq_num = (u8)RS_64(qword0, I40IWCQ_TCPSEQNUM); + info->tcp_seq_num = (u32)RS_64(qword0, I40IWCQ_TCPSEQNUM); info->qp_id = (u32)RS_64(qword2, I40IWCQ_QPID); @@ -1187,7 +1187,7 @@ enum i40iw_status_code i40iw_inline_data_size_to_wqesize(u32 data_size, u8 *wqe_size) { if (data_size > I40IW_MAX_INLINE_DATA_SIZE) - return I40IW_ERR_INVALID_IMM_DATA_SIZE; + return I40IW_ERR_INVALID_INLINE_DATA_SIZE; if (data_size <= 16) *wqe_size = I40IW_QP_WQE_MIN_SIZE; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index a7f2e60085c4..f7fcde1ff0aa 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1085,6 +1085,12 @@ static int mlx5_ib_modify_port(struct ib_device *ibdev, u8 port, int mask, bool is_ib = (mlx5_ib_port_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND); + /* CM layer calls ib_modify_port() regardless of the link layer. For + * Ethernet ports, qkey violation and Port capabilities are meaningless. + */ + if (!is_ib) + return 0; + if (MLX5_CAP_GEN(dev->mdev, ib_virt) && is_ib) { change_mask = props->clr_port_cap_mask | props->set_port_cap_mask; value = ~props->clr_port_cap_mask | props->set_port_cap_mask; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 0889ff367c86..f58f8f5f3ebe 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1238,6 +1238,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, goto err_destroy_tis; sq->base.container_mibqp = qp; + sq->base.mqp.event = mlx5_ib_qp_event; } if (qp->rq.wqe_cnt) { diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c index 69bda611d313..90aa326fd7c0 100644 --- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c +++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c @@ -65,13 +65,28 @@ int pvrdma_req_notify_cq(struct ib_cq *ibcq, struct pvrdma_dev *dev = to_vdev(ibcq->device); struct pvrdma_cq *cq = to_vcq(ibcq); u32 val = cq->cq_handle; + unsigned long flags; + int has_data = 0; val |= (notify_flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ? PVRDMA_UAR_CQ_ARM_SOL : PVRDMA_UAR_CQ_ARM; + spin_lock_irqsave(&cq->cq_lock, flags); + pvrdma_write_uar_cq(dev, val); - return 0; + if (notify_flags & IB_CQ_REPORT_MISSED_EVENTS) { + unsigned int head; + + has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx, + cq->ibcq.cqe, &head); + if (unlikely(has_data == PVRDMA_INVALID_IDX)) + dev_err(&dev->pdev->dev, "CQ ring state invalid\n"); + } + + spin_unlock_irqrestore(&cq->cq_lock, flags); + + return has_data; } /** diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 298a6ba51411..ca0e19ae7a90 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -476,10 +476,21 @@ static const u8 xboxone_hori_init[] = { }; /* - * A rumble packet is required for some PowerA pads to start + * A specific rumble packet is required for some PowerA pads to start * sending input reports. One of those pads is (0x24c6:0x543a). */ -static const u8 xboxone_zerorumble_init[] = { +static const u8 xboxone_rumblebegin_init[] = { + 0x09, 0x00, 0x00, 0x09, 0x00, 0x0F, 0x00, 0x00, + 0x1D, 0x1D, 0xFF, 0x00, 0x00 +}; + +/* + * A rumble packet with zero FF intensity will immediately + * terminate the rumbling required to init PowerA pads. + * This should happen fast enough that the motors don't + * spin up to enough speed to actually vibrate the gamepad. + */ +static const u8 xboxone_rumbleend_init[] = { 0x09, 0x00, 0x00, 0x09, 0x00, 0x0F, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; @@ -494,9 +505,12 @@ static const struct xboxone_init_packet xboxone_init_packets[] = { XBOXONE_INIT_PKT(0x0e6f, 0x0165, xboxone_hori_init), XBOXONE_INIT_PKT(0x0f0d, 0x0067, xboxone_hori_init), XBOXONE_INIT_PKT(0x0000, 0x0000, xboxone_fw2015_init), - XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_zerorumble_init), - XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_zerorumble_init), - XBOXONE_INIT_PKT(0x24c6, 0x543a, xboxone_zerorumble_init), + XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init), + XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init), + XBOXONE_INIT_PKT(0x24c6, 0x543a, xboxone_rumblebegin_init), + XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumbleend_init), + XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumbleend_init), + XBOXONE_INIT_PKT(0x24c6, 0x543a, xboxone_rumbleend_init), }; struct xpad_output_packet { diff --git a/drivers/input/misc/soc_button_array.c b/drivers/input/misc/soc_button_array.c index f600f3a7a3c6..23520df7650f 100644 --- a/drivers/input/misc/soc_button_array.c +++ b/drivers/input/misc/soc_button_array.c @@ -331,7 +331,7 @@ static int soc_button_probe(struct platform_device *pdev) error = gpiod_count(dev, NULL); if (error < 0) { dev_dbg(dev, "no GPIO attached, ignoring...\n"); - return error; + return -ENODEV; } priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c index 262d1057c1da..850b00e3ad8e 100644 --- a/drivers/input/mouse/alps.c +++ b/drivers/input/mouse/alps.c @@ -1215,14 +1215,24 @@ static int alps_decode_ss4_v2(struct alps_fields *f, case SS4_PACKET_ID_TWO: if (priv->flags & ALPS_BUTTONPAD) { - f->mt[0].x = SS4_BTL_MF_X_V2(p, 0); + if (IS_SS4PLUS_DEV(priv->dev_id)) { + f->mt[0].x = SS4_PLUS_BTL_MF_X_V2(p, 0); + f->mt[1].x = SS4_PLUS_BTL_MF_X_V2(p, 1); + } else { + f->mt[0].x = SS4_BTL_MF_X_V2(p, 0); + f->mt[1].x = SS4_BTL_MF_X_V2(p, 1); + } f->mt[0].y = SS4_BTL_MF_Y_V2(p, 0); - f->mt[1].x = SS4_BTL_MF_X_V2(p, 1); f->mt[1].y = SS4_BTL_MF_Y_V2(p, 1); } else { - f->mt[0].x = SS4_STD_MF_X_V2(p, 0); + if (IS_SS4PLUS_DEV(priv->dev_id)) { + f->mt[0].x = SS4_PLUS_STD_MF_X_V2(p, 0); + f->mt[1].x = SS4_PLUS_STD_MF_X_V2(p, 1); + } else { + f->mt[0].x = SS4_STD_MF_X_V2(p, 0); + f->mt[1].x = SS4_STD_MF_X_V2(p, 1); + } f->mt[0].y = SS4_STD_MF_Y_V2(p, 0); - f->mt[1].x = SS4_STD_MF_X_V2(p, 1); f->mt[1].y = SS4_STD_MF_Y_V2(p, 1); } f->pressure = SS4_MF_Z_V2(p, 0) ? 0x30 : 0; @@ -1239,16 +1249,27 @@ static int alps_decode_ss4_v2(struct alps_fields *f, case SS4_PACKET_ID_MULTI: if (priv->flags & ALPS_BUTTONPAD) { - f->mt[2].x = SS4_BTL_MF_X_V2(p, 0); + if (IS_SS4PLUS_DEV(priv->dev_id)) { + f->mt[0].x = SS4_PLUS_BTL_MF_X_V2(p, 0); + f->mt[1].x = SS4_PLUS_BTL_MF_X_V2(p, 1); + } else { + f->mt[2].x = SS4_BTL_MF_X_V2(p, 0); + f->mt[3].x = SS4_BTL_MF_X_V2(p, 1); + } + f->mt[2].y = SS4_BTL_MF_Y_V2(p, 0); - f->mt[3].x = SS4_BTL_MF_X_V2(p, 1); f->mt[3].y = SS4_BTL_MF_Y_V2(p, 1); no_data_x = SS4_MFPACKET_NO_AX_BL; no_data_y = SS4_MFPACKET_NO_AY_BL; } else { - f->mt[2].x = SS4_STD_MF_X_V2(p, 0); + if (IS_SS4PLUS_DEV(priv->dev_id)) { + f->mt[0].x = SS4_PLUS_STD_MF_X_V2(p, 0); + f->mt[1].x = SS4_PLUS_STD_MF_X_V2(p, 1); + } else { + f->mt[0].x = SS4_STD_MF_X_V2(p, 0); + f->mt[1].x = SS4_STD_MF_X_V2(p, 1); + } f->mt[2].y = SS4_STD_MF_Y_V2(p, 0); - f->mt[3].x = SS4_STD_MF_X_V2(p, 1); f->mt[3].y = SS4_STD_MF_Y_V2(p, 1); no_data_x = SS4_MFPACKET_NO_AX; no_data_y = SS4_MFPACKET_NO_AY; @@ -2541,8 +2562,8 @@ static int alps_set_defaults_ss4_v2(struct psmouse *psmouse, memset(otp, 0, sizeof(otp)); - if (alps_get_otp_values_ss4_v2(psmouse, 0, &otp[0][0]) || - alps_get_otp_values_ss4_v2(psmouse, 1, &otp[1][0])) + if (alps_get_otp_values_ss4_v2(psmouse, 1, &otp[1][0]) || + alps_get_otp_values_ss4_v2(psmouse, 0, &otp[0][0])) return -1; alps_update_device_area_ss4_v2(otp, priv); diff --git a/drivers/input/mouse/alps.h b/drivers/input/mouse/alps.h index ed2d6879fa52..c80a7c76cb76 100644 --- a/drivers/input/mouse/alps.h +++ b/drivers/input/mouse/alps.h @@ -100,6 +100,10 @@ enum SS4_PACKET_ID { ((_b[1 + _i * 3] << 5) & 0x1F00) \ ) +#define SS4_PLUS_STD_MF_X_V2(_b, _i) (((_b[0 + (_i) * 3] << 4) & 0x0070) | \ + ((_b[1 + (_i) * 3] << 4) & 0x0F80) \ + ) + #define SS4_STD_MF_Y_V2(_b, _i) (((_b[1 + (_i) * 3] << 3) & 0x0010) | \ ((_b[2 + (_i) * 3] << 5) & 0x01E0) | \ ((_b[2 + (_i) * 3] << 4) & 0x0E00) \ @@ -109,6 +113,10 @@ enum SS4_PACKET_ID { ((_b[0 + (_i) * 3] >> 3) & 0x0010) \ ) +#define SS4_PLUS_BTL_MF_X_V2(_b, _i) (SS4_PLUS_STD_MF_X_V2(_b, _i) | \ + ((_b[0 + (_i) * 3] >> 4) & 0x0008) \ + ) + #define SS4_BTL_MF_Y_V2(_b, _i) (SS4_STD_MF_Y_V2(_b, _i) | \ ((_b[0 + (_i) * 3] >> 3) & 0x0008) \ ) diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 3b616cb7c67f..cfbc8ba4c96c 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -1247,7 +1247,12 @@ static const struct acpi_device_id elan_acpi_id[] = { { "ELAN0000", 0 }, { "ELAN0100", 0 }, { "ELAN0600", 0 }, + { "ELAN0602", 0 }, { "ELAN0605", 0 }, + { "ELAN0608", 0 }, + { "ELAN0605", 0 }, + { "ELAN0609", 0 }, + { "ELAN060B", 0 }, { "ELAN1000", 0 }, { } }; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 16c30460ef04..5af0b7d200bc 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -535,16 +535,17 @@ static void synaptics_apply_quirks(struct psmouse *psmouse, } } +static bool synaptics_has_agm(struct synaptics_data *priv) +{ + return (SYN_CAP_ADV_GESTURE(priv->info.ext_cap_0c) || + SYN_CAP_IMAGE_SENSOR(priv->info.ext_cap_0c)); +} + static int synaptics_set_advanced_gesture_mode(struct psmouse *psmouse) { static u8 param = 0xc8; - struct synaptics_data *priv = psmouse->private; int error; - if (!(SYN_CAP_ADV_GESTURE(priv->info.ext_cap_0c) || - SYN_CAP_IMAGE_SENSOR(priv->info.ext_cap_0c))) - return 0; - error = psmouse_sliced_command(psmouse, SYN_QUE_MODEL); if (error) return error; @@ -553,9 +554,6 @@ static int synaptics_set_advanced_gesture_mode(struct psmouse *psmouse) if (error) return error; - /* Advanced gesture mode also sends multi finger data */ - priv->info.capabilities |= BIT(1); - return 0; } @@ -578,7 +576,7 @@ static int synaptics_set_mode(struct psmouse *psmouse) if (error) return error; - if (priv->absolute_mode) { + if (priv->absolute_mode && synaptics_has_agm(priv)) { error = synaptics_set_advanced_gesture_mode(psmouse); if (error) { psmouse_err(psmouse, @@ -766,9 +764,7 @@ static int synaptics_parse_hw_state(const u8 buf[], ((buf[0] & 0x04) >> 1) | ((buf[3] & 0x04) >> 2)); - if ((SYN_CAP_ADV_GESTURE(priv->info.ext_cap_0c) || - SYN_CAP_IMAGE_SENSOR(priv->info.ext_cap_0c)) && - hw->w == 2) { + if (synaptics_has_agm(priv) && hw->w == 2) { synaptics_parse_agm(buf, priv, hw); return 1; } @@ -1033,6 +1029,15 @@ static void synaptics_image_sensor_process(struct psmouse *psmouse, synaptics_report_mt_data(psmouse, sgm, num_fingers); } +static bool synaptics_has_multifinger(struct synaptics_data *priv) +{ + if (SYN_CAP_MULTIFINGER(priv->info.capabilities)) + return true; + + /* Advanced gesture mode also sends multi finger data */ + return synaptics_has_agm(priv); +} + /* * called for each full received packet from the touchpad */ @@ -1079,7 +1084,7 @@ static void synaptics_process_packet(struct psmouse *psmouse) if (SYN_CAP_EXTENDED(info->capabilities)) { switch (hw.w) { case 0 ... 1: - if (SYN_CAP_MULTIFINGER(info->capabilities)) + if (synaptics_has_multifinger(priv)) num_fingers = hw.w + 2; break; case 2: @@ -1123,7 +1128,7 @@ static void synaptics_process_packet(struct psmouse *psmouse) input_report_abs(dev, ABS_TOOL_WIDTH, finger_width); input_report_key(dev, BTN_TOOL_FINGER, num_fingers == 1); - if (SYN_CAP_MULTIFINGER(info->capabilities)) { + if (synaptics_has_multifinger(priv)) { input_report_key(dev, BTN_TOOL_DOUBLETAP, num_fingers == 2); input_report_key(dev, BTN_TOOL_TRIPLETAP, num_fingers == 3); } @@ -1283,7 +1288,7 @@ static void set_input_params(struct psmouse *psmouse, __set_bit(BTN_TOUCH, dev->keybit); __set_bit(BTN_TOOL_FINGER, dev->keybit); - if (SYN_CAP_MULTIFINGER(info->capabilities)) { + if (synaptics_has_multifinger(priv)) { __set_bit(BTN_TOOL_DOUBLETAP, dev->keybit); __set_bit(BTN_TOOL_TRIPLETAP, dev->keybit); } diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c index 922ea02edcc3..0871010f18d5 100644 --- a/drivers/input/mouse/trackpoint.c +++ b/drivers/input/mouse/trackpoint.c @@ -265,7 +265,8 @@ static int trackpoint_start_protocol(struct psmouse *psmouse, unsigned char *fir if (ps2_command(&psmouse->ps2dev, param, MAKE_PS2_CMD(0, 2, TP_READ_ID))) return -1; - if (param[0] != TP_MAGIC_IDENT) + /* add new TP ID. */ + if (!(param[0] & TP_MAGIC_IDENT)) return -1; if (firmware_id) @@ -380,8 +381,8 @@ int trackpoint_detect(struct psmouse *psmouse, bool set_properties) return 0; if (trackpoint_read(ps2dev, TP_EXT_BTN, &button_info)) { - psmouse_warn(psmouse, "failed to get extended button data\n"); - button_info = 0; + psmouse_warn(psmouse, "failed to get extended button data, assuming 3 buttons\n"); + button_info = 0x33; } psmouse->private = kzalloc(sizeof(struct trackpoint_data), GFP_KERNEL); diff --git a/drivers/input/mouse/trackpoint.h b/drivers/input/mouse/trackpoint.h index 5617ed3a7d7a..88055755f82e 100644 --- a/drivers/input/mouse/trackpoint.h +++ b/drivers/input/mouse/trackpoint.h @@ -21,8 +21,9 @@ #define TP_COMMAND 0xE2 /* Commands start with this */ #define TP_READ_ID 0xE1 /* Sent for device identification */ -#define TP_MAGIC_IDENT 0x01 /* Sent after a TP_READ_ID followed */ +#define TP_MAGIC_IDENT 0x03 /* Sent after a TP_READ_ID followed */ /* by the firmware ID */ + /* Firmware ID includes 0x1, 0x2, 0x3 */ /* diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index 294a409e283b..d6b873b57054 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -574,7 +574,9 @@ struct amd_iommu { static inline struct amd_iommu *dev_to_amd_iommu(struct device *dev) { - return container_of(dev, struct amd_iommu, iommu.dev); + struct iommu_device *iommu = dev_to_iommu_device(dev); + + return container_of(iommu, struct amd_iommu, iommu); } #define ACPIHID_UID_LEN 256 diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 6629c472eafd..dccf5b76eff2 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -391,13 +391,6 @@ static int mn_clear_flush_young(struct mmu_notifier *mn, return 0; } -static void mn_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - __mn_flush_page(mn, address); -} - static void mn_invalidate_range(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) @@ -436,7 +429,6 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm) static const struct mmu_notifier_ops iommu_mn = { .release = mn_release, .clear_flush_young = mn_clear_flush_young, - .invalidate_page = mn_invalidate_page, .invalidate_range = mn_invalidate_range, }; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 687f18f65cea..3e8636f1220e 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4736,7 +4736,9 @@ static void intel_disable_iommus(void) static inline struct intel_iommu *dev_to_intel_iommu(struct device *dev) { - return container_of(dev, struct intel_iommu, iommu.dev); + struct iommu_device *iommu_dev = dev_to_iommu_device(dev); + + return container_of(iommu_dev, struct intel_iommu, iommu); } static ssize_t intel_iommu_show_version(struct device *dev, diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index f167c0d84ebf..f620dccec8ee 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -223,14 +223,6 @@ static void intel_change_pte(struct mmu_notifier *mn, struct mm_struct *mm, intel_flush_svm_range(svm, address, 1, 1, 0); } -static void intel_invalidate_page(struct mmu_notifier *mn, struct mm_struct *mm, - unsigned long address) -{ - struct intel_svm *svm = container_of(mn, struct intel_svm, notifier); - - intel_flush_svm_range(svm, address, 1, 1, 0); -} - /* Pages have been freed at this point */ static void intel_invalidate_range(struct mmu_notifier *mn, struct mm_struct *mm, @@ -285,7 +277,6 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) static const struct mmu_notifier_ops intel_mmuops = { .release = intel_mm_release, .change_pte = intel_change_pte, - .invalidate_page = intel_invalidate_page, .invalidate_range = intel_invalidate_range, }; diff --git a/drivers/iommu/iommu-sysfs.c b/drivers/iommu/iommu-sysfs.c index c58351ed61c1..36d1a7ce7fc4 100644 --- a/drivers/iommu/iommu-sysfs.c +++ b/drivers/iommu/iommu-sysfs.c @@ -62,32 +62,40 @@ int iommu_device_sysfs_add(struct iommu_device *iommu, va_list vargs; int ret; - device_initialize(&iommu->dev); + iommu->dev = kzalloc(sizeof(*iommu->dev), GFP_KERNEL); + if (!iommu->dev) + return -ENOMEM; - iommu->dev.class = &iommu_class; - iommu->dev.parent = parent; - iommu->dev.groups = groups; + device_initialize(iommu->dev); + + iommu->dev->class = &iommu_class; + iommu->dev->parent = parent; + iommu->dev->groups = groups; va_start(vargs, fmt); - ret = kobject_set_name_vargs(&iommu->dev.kobj, fmt, vargs); + ret = kobject_set_name_vargs(&iommu->dev->kobj, fmt, vargs); va_end(vargs); if (ret) goto error; - ret = device_add(&iommu->dev); + ret = device_add(iommu->dev); if (ret) goto error; + dev_set_drvdata(iommu->dev, iommu); + return 0; error: - put_device(&iommu->dev); + put_device(iommu->dev); return ret; } void iommu_device_sysfs_remove(struct iommu_device *iommu) { - device_unregister(&iommu->dev); + dev_set_drvdata(iommu->dev, NULL); + device_unregister(iommu->dev); + iommu->dev = NULL; } /* * IOMMU drivers can indicate a device is managed by a given IOMMU using @@ -102,14 +110,14 @@ int iommu_device_link(struct iommu_device *iommu, struct device *link) if (!iommu || IS_ERR(iommu)) return -ENODEV; - ret = sysfs_add_link_to_group(&iommu->dev.kobj, "devices", + ret = sysfs_add_link_to_group(&iommu->dev->kobj, "devices", &link->kobj, dev_name(link)); if (ret) return ret; - ret = sysfs_create_link_nowarn(&link->kobj, &iommu->dev.kobj, "iommu"); + ret = sysfs_create_link_nowarn(&link->kobj, &iommu->dev->kobj, "iommu"); if (ret) - sysfs_remove_link_from_group(&iommu->dev.kobj, "devices", + sysfs_remove_link_from_group(&iommu->dev->kobj, "devices", dev_name(link)); return ret; @@ -121,5 +129,5 @@ void iommu_device_unlink(struct iommu_device *iommu, struct device *link) return; sysfs_remove_link(&link->kobj, "iommu"); - sysfs_remove_link_from_group(&iommu->dev.kobj, "devices", dev_name(link)); + sysfs_remove_link_from_group(&iommu->dev->kobj, "devices", dev_name(link)); } diff --git a/drivers/irqchip/irq-atmel-aic-common.c b/drivers/irqchip/irq-atmel-aic-common.c index 28b26c80f4cf..072bd227b6c6 100644 --- a/drivers/irqchip/irq-atmel-aic-common.c +++ b/drivers/irqchip/irq-atmel-aic-common.c @@ -137,14 +137,14 @@ static void __init aic_common_ext_irq_of_init(struct irq_domain *domain) #define AT91_RTC_IMR 0x28 #define AT91_RTC_IRQ_MASK 0x1f -void __init aic_common_rtc_irq_fixup(struct device_node *root) +void __init aic_common_rtc_irq_fixup(void) { struct device_node *np; void __iomem *regs; - np = of_find_compatible_node(root, NULL, "atmel,at91rm9200-rtc"); + np = of_find_compatible_node(NULL, NULL, "atmel,at91rm9200-rtc"); if (!np) - np = of_find_compatible_node(root, NULL, + np = of_find_compatible_node(NULL, NULL, "atmel,at91sam9x5-rtc"); if (!np) @@ -165,7 +165,7 @@ void __init aic_common_rtc_irq_fixup(struct device_node *root) #define AT91_RTT_ALMIEN (1 << 16) /* Alarm Interrupt Enable */ #define AT91_RTT_RTTINCIEN (1 << 17) /* Real Time Timer Increment Interrupt Enable */ -void __init aic_common_rtt_irq_fixup(struct device_node *root) +void __init aic_common_rtt_irq_fixup(void) { struct device_node *np; void __iomem *regs; @@ -196,11 +196,10 @@ static void __init aic_common_irq_fixup(const struct of_device_id *matches) return; match = of_match_node(matches, root); - of_node_put(root); if (match) { - void (*fixup)(struct device_node *) = match->data; - fixup(root); + void (*fixup)(void) = match->data; + fixup(); } of_node_put(root); diff --git a/drivers/irqchip/irq-atmel-aic-common.h b/drivers/irqchip/irq-atmel-aic-common.h index af60376d50de..242e62c1851e 100644 --- a/drivers/irqchip/irq-atmel-aic-common.h +++ b/drivers/irqchip/irq-atmel-aic-common.h @@ -33,8 +33,8 @@ struct irq_domain *__init aic_common_of_init(struct device_node *node, const char *name, int nirqs, const struct of_device_id *matches); -void __init aic_common_rtc_irq_fixup(struct device_node *root); +void __init aic_common_rtc_irq_fixup(void); -void __init aic_common_rtt_irq_fixup(struct device_node *root); +void __init aic_common_rtt_irq_fixup(void); #endif /* __IRQ_ATMEL_AIC_COMMON_H */ diff --git a/drivers/irqchip/irq-atmel-aic.c b/drivers/irqchip/irq-atmel-aic.c index 37f952dd9fc9..bb1ad451392f 100644 --- a/drivers/irqchip/irq-atmel-aic.c +++ b/drivers/irqchip/irq-atmel-aic.c @@ -209,20 +209,20 @@ static const struct irq_domain_ops aic_irq_ops = { .xlate = aic_irq_domain_xlate, }; -static void __init at91rm9200_aic_irq_fixup(struct device_node *root) +static void __init at91rm9200_aic_irq_fixup(void) { - aic_common_rtc_irq_fixup(root); + aic_common_rtc_irq_fixup(); } -static void __init at91sam9260_aic_irq_fixup(struct device_node *root) +static void __init at91sam9260_aic_irq_fixup(void) { - aic_common_rtt_irq_fixup(root); + aic_common_rtt_irq_fixup(); } -static void __init at91sam9g45_aic_irq_fixup(struct device_node *root) +static void __init at91sam9g45_aic_irq_fixup(void) { - aic_common_rtc_irq_fixup(root); - aic_common_rtt_irq_fixup(root); + aic_common_rtc_irq_fixup(); + aic_common_rtt_irq_fixup(); } static const struct of_device_id aic_irq_fixups[] __initconst = { diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c index c04ee9a23d09..6acad2ea0fb3 100644 --- a/drivers/irqchip/irq-atmel-aic5.c +++ b/drivers/irqchip/irq-atmel-aic5.c @@ -305,9 +305,9 @@ static const struct irq_domain_ops aic5_irq_ops = { .xlate = aic5_irq_domain_xlate, }; -static void __init sama5d3_aic_irq_fixup(struct device_node *root) +static void __init sama5d3_aic_irq_fixup(void) { - aic_common_rtc_irq_fixup(root); + aic_common_rtc_irq_fixup(); } static const struct of_device_id aic5_irq_fixups[] __initconst = { diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c index bddf169c4b37..b009b916a292 100644 --- a/drivers/irqchip/irq-brcmstb-l2.c +++ b/drivers/irqchip/irq-brcmstb-l2.c @@ -189,6 +189,7 @@ static int __init brcmstb_l2_intc_of_init(struct device_node *np, ct->chip.irq_suspend = brcmstb_l2_intc_suspend; ct->chip.irq_resume = brcmstb_l2_intc_resume; + ct->chip.irq_pm_shutdown = brcmstb_l2_intc_suspend; if (data->can_wake) { /* This IRQ chip can wake the system, set all child interrupts diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c index 249240d9a425..833a90fe33ae 100644 --- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c +++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c @@ -43,6 +43,7 @@ static int of_pmsi_get_dev_id(struct irq_domain *domain, struct device *dev, *dev_id = args.args[0]; break; } + index++; } while (!ret); return ret; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 68932873eebc..284738add89b 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1835,7 +1835,7 @@ static int __init its_of_probe(struct device_node *node) #define ACPI_GICV3_ITS_MEM_SIZE (SZ_128K) -#if defined(CONFIG_ACPI_NUMA) && (ACPI_CA_VERSION >= 0x20170531) +#ifdef CONFIG_ACPI_NUMA struct its_srat_map { /* numa node id */ u32 numa_node; @@ -1843,7 +1843,7 @@ struct its_srat_map { u32 its_id; }; -static struct its_srat_map its_srat_maps[MAX_NUMNODES] __initdata; +static struct its_srat_map *its_srat_maps __initdata; static int its_in_srat __initdata; static int __init acpi_get_its_numa_node(u32 its_id) @@ -1857,6 +1857,12 @@ static int __init acpi_get_its_numa_node(u32 its_id) return NUMA_NO_NODE; } +static int __init gic_acpi_match_srat_its(struct acpi_subtable_header *header, + const unsigned long end) +{ + return 0; +} + static int __init gic_acpi_parse_srat_its(struct acpi_subtable_header *header, const unsigned long end) { @@ -1873,12 +1879,6 @@ static int __init gic_acpi_parse_srat_its(struct acpi_subtable_header *header, return -EINVAL; } - if (its_in_srat >= MAX_NUMNODES) { - pr_err("SRAT: ITS affinity exceeding max count[%d]\n", - MAX_NUMNODES); - return -EINVAL; - } - node = acpi_map_pxm_to_node(its_affinity->proximity_domain); if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) { @@ -1897,14 +1897,37 @@ static int __init gic_acpi_parse_srat_its(struct acpi_subtable_header *header, static void __init acpi_table_parse_srat_its(void) { + int count; + + count = acpi_table_parse_entries(ACPI_SIG_SRAT, + sizeof(struct acpi_table_srat), + ACPI_SRAT_TYPE_GIC_ITS_AFFINITY, + gic_acpi_match_srat_its, 0); + if (count <= 0) + return; + + its_srat_maps = kmalloc(count * sizeof(struct its_srat_map), + GFP_KERNEL); + if (!its_srat_maps) { + pr_warn("SRAT: Failed to allocate memory for its_srat_maps!\n"); + return; + } + acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), ACPI_SRAT_TYPE_GIC_ITS_AFFINITY, gic_acpi_parse_srat_its, 0); } + +/* free the its_srat_maps after ITS probing */ +static void __init acpi_its_srat_maps_free(void) +{ + kfree(its_srat_maps); +} #else static void __init acpi_table_parse_srat_its(void) { } static int __init acpi_get_its_numa_node(u32 its_id) { return NUMA_NO_NODE; } +static void __init acpi_its_srat_maps_free(void) { } #endif static int __init gic_acpi_parse_madt_its(struct acpi_subtable_header *header, @@ -1951,6 +1974,7 @@ static void __init its_acpi_probe(void) acpi_table_parse_srat_its(); acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_TRANSLATOR, gic_acpi_parse_madt_its, 0); + acpi_its_srat_maps_free(); } #else static void __init its_acpi_probe(void) { } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index dbffb7ab6203..984c3ecfd22c 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -353,6 +353,8 @@ static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs if (static_key_true(&supports_deactivate)) gic_write_eoir(irqnr); + else + isb(); err = handle_domain_irq(gic_data.domain, irqnr, regs); if (err) { @@ -640,11 +642,16 @@ static void gic_smp_init(void) static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { - unsigned int cpu = cpumask_any_and(mask_val, cpu_online_mask); + unsigned int cpu; void __iomem *reg; int enabled; u64 val; + if (force) + cpu = cpumask_first(mask_val); + else + cpu = cpumask_any_and(mask_val, cpu_online_mask); + if (cpu >= nr_cpu_ids) return -EINVAL; @@ -831,8 +838,11 @@ static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, if (ret) return ret; - for (i = 0; i < nr_irqs; i++) - gic_irq_domain_map(domain, virq + i, hwirq + i); + for (i = 0; i < nr_irqs; i++) { + ret = gic_irq_domain_map(domain, virq + i, hwirq + i); + if (ret) + return ret; + } return 0; } diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 1b1df4f770bd..d3e7c43718b8 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -361,6 +361,7 @@ static void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) if (likely(irqnr > 15 && irqnr < 1020)) { if (static_key_true(&supports_deactivate)) writel_relaxed(irqstat, cpu_base + GIC_CPU_EOI); + isb(); handle_domain_irq(gic->domain, irqnr, regs); continue; } @@ -401,10 +402,12 @@ static void gic_handle_cascade_irq(struct irq_desc *desc) goto out; cascade_irq = irq_find_mapping(chip_data->domain, gic_irq); - if (unlikely(gic_irq < 32 || gic_irq > 1020)) + if (unlikely(gic_irq < 32 || gic_irq > 1020)) { handle_bad_irq(desc); - else + } else { + isb(); generic_handle_irq(cascade_irq); + } out: chained_irq_exit(chip, desc); @@ -1027,8 +1030,11 @@ static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, if (ret) return ret; - for (i = 0; i < nr_irqs; i++) - gic_irq_domain_map(domain, virq + i, hwirq + i); + for (i = 0; i < nr_irqs; i++) { + ret = gic_irq_domain_map(domain, virq + i, hwirq + i); + if (ret) + return ret; + } return 0; } diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index 6ab1d3afec02..48ee1bad473f 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -1020,8 +1020,11 @@ static int __init gic_of_init(struct device_node *node, gic_len = resource_size(&res); } - if (mips_cm_present()) + if (mips_cm_present()) { write_gcr_gic_base(gic_base | CM_GCR_GIC_BASE_GICEN_MSK); + /* Ensure GIC region is enabled before trying to access it */ + __sync(); + } gic_present = true; __gic_init(gic_base, gic_len, cpu_vec, 0, node); diff --git a/drivers/isdn/mISDN/fsm.c b/drivers/isdn/mISDN/fsm.c index 78fc5d5e9051..92e6570b1143 100644 --- a/drivers/isdn/mISDN/fsm.c +++ b/drivers/isdn/mISDN/fsm.c @@ -26,7 +26,7 @@ #define FSM_TIMER_DEBUG 0 -void +int mISDN_FsmNew(struct Fsm *fsm, struct FsmNode *fnlist, int fncount) { @@ -34,6 +34,8 @@ mISDN_FsmNew(struct Fsm *fsm, fsm->jumpmatrix = kzalloc(sizeof(FSMFNPTR) * fsm->state_count * fsm->event_count, GFP_KERNEL); + if (fsm->jumpmatrix == NULL) + return -ENOMEM; for (i = 0; i < fncount; i++) if ((fnlist[i].state >= fsm->state_count) || @@ -45,6 +47,7 @@ mISDN_FsmNew(struct Fsm *fsm, } else fsm->jumpmatrix[fsm->state_count * fnlist[i].event + fnlist[i].state] = (FSMFNPTR) fnlist[i].routine; + return 0; } EXPORT_SYMBOL(mISDN_FsmNew); diff --git a/drivers/isdn/mISDN/fsm.h b/drivers/isdn/mISDN/fsm.h index 928f5be192c1..e1def8490221 100644 --- a/drivers/isdn/mISDN/fsm.h +++ b/drivers/isdn/mISDN/fsm.h @@ -55,7 +55,7 @@ struct FsmTimer { void *arg; }; -extern void mISDN_FsmNew(struct Fsm *, struct FsmNode *, int); +extern int mISDN_FsmNew(struct Fsm *, struct FsmNode *, int); extern void mISDN_FsmFree(struct Fsm *); extern int mISDN_FsmEvent(struct FsmInst *, int , void *); extern void mISDN_FsmChangeState(struct FsmInst *, int); diff --git a/drivers/isdn/mISDN/layer1.c b/drivers/isdn/mISDN/layer1.c index bebc57b72138..3192b0eb3944 100644 --- a/drivers/isdn/mISDN/layer1.c +++ b/drivers/isdn/mISDN/layer1.c @@ -414,8 +414,7 @@ l1_init(u_int *deb) l1fsm_s.event_count = L1_EVENT_COUNT; l1fsm_s.strEvent = strL1Event; l1fsm_s.strState = strL1SState; - mISDN_FsmNew(&l1fsm_s, L1SFnList, ARRAY_SIZE(L1SFnList)); - return 0; + return mISDN_FsmNew(&l1fsm_s, L1SFnList, ARRAY_SIZE(L1SFnList)); } void diff --git a/drivers/isdn/mISDN/layer2.c b/drivers/isdn/mISDN/layer2.c index 7243a6746f8b..9ff0903a0e89 100644 --- a/drivers/isdn/mISDN/layer2.c +++ b/drivers/isdn/mISDN/layer2.c @@ -2247,15 +2247,26 @@ static struct Bprotocol X75SLP = { int Isdnl2_Init(u_int *deb) { + int res; debug = deb; mISDN_register_Bprotocol(&X75SLP); l2fsm.state_count = L2_STATE_COUNT; l2fsm.event_count = L2_EVENT_COUNT; l2fsm.strEvent = strL2Event; l2fsm.strState = strL2State; - mISDN_FsmNew(&l2fsm, L2FnList, ARRAY_SIZE(L2FnList)); - TEIInit(deb); + res = mISDN_FsmNew(&l2fsm, L2FnList, ARRAY_SIZE(L2FnList)); + if (res) + goto error; + res = TEIInit(deb); + if (res) + goto error_fsm; return 0; + +error_fsm: + mISDN_FsmFree(&l2fsm); +error: + mISDN_unregister_Bprotocol(&X75SLP); + return res; } void diff --git a/drivers/isdn/mISDN/tei.c b/drivers/isdn/mISDN/tei.c index 908127efccf8..12d9e5f4beb1 100644 --- a/drivers/isdn/mISDN/tei.c +++ b/drivers/isdn/mISDN/tei.c @@ -1387,23 +1387,37 @@ create_teimanager(struct mISDNdevice *dev) int TEIInit(u_int *deb) { + int res; debug = deb; teifsmu.state_count = TEI_STATE_COUNT; teifsmu.event_count = TEI_EVENT_COUNT; teifsmu.strEvent = strTeiEvent; teifsmu.strState = strTeiState; - mISDN_FsmNew(&teifsmu, TeiFnListUser, ARRAY_SIZE(TeiFnListUser)); + res = mISDN_FsmNew(&teifsmu, TeiFnListUser, ARRAY_SIZE(TeiFnListUser)); + if (res) + goto error; teifsmn.state_count = TEI_STATE_COUNT; teifsmn.event_count = TEI_EVENT_COUNT; teifsmn.strEvent = strTeiEvent; teifsmn.strState = strTeiState; - mISDN_FsmNew(&teifsmn, TeiFnListNet, ARRAY_SIZE(TeiFnListNet)); + res = mISDN_FsmNew(&teifsmn, TeiFnListNet, ARRAY_SIZE(TeiFnListNet)); + if (res) + goto error_smn; deactfsm.state_count = DEACT_STATE_COUNT; deactfsm.event_count = DEACT_EVENT_COUNT; deactfsm.strEvent = strDeactEvent; deactfsm.strState = strDeactState; - mISDN_FsmNew(&deactfsm, DeactFnList, ARRAY_SIZE(DeactFnList)); + res = mISDN_FsmNew(&deactfsm, DeactFnList, ARRAY_SIZE(DeactFnList)); + if (res) + goto error_deact; return 0; + +error_deact: + mISDN_FsmFree(&teifsmn); +error_smn: + mISDN_FsmFree(&teifsmu); +error: + return res; } void TEIFree(void) diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 0e8ab5bb3575..d24e4b05f5da 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -504,7 +504,6 @@ static int multipath_clone_and_map(struct dm_target *ti, struct request *rq, if (queue_dying) { atomic_inc(&m->pg_init_in_progress); activate_or_offline_path(pgpath); - return DM_MAPIO_REQUEUE; } return DM_MAPIO_DELAY_REQUEUE; } @@ -1458,7 +1457,6 @@ static int noretry_error(blk_status_t error) case BLK_STS_TARGET: case BLK_STS_NEXUS: case BLK_STS_MEDIUM: - case BLK_STS_RESOURCE: return 1; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 2edbcc2d7d3f..d669fddd9290 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -27,16 +27,6 @@ #define DM_MSG_PREFIX "core" -#ifdef CONFIG_PRINTK -/* - * ratelimit state to be used in DMXXX_LIMIT(). - */ -DEFINE_RATELIMIT_STATE(dm_ratelimit_state, - DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); -EXPORT_SYMBOL(dm_ratelimit_state); -#endif - /* * Cookies are numeric values sent with CHANGE and REMOVE * uevents while resuming, removing or renaming the device. @@ -1523,7 +1513,7 @@ static void __split_and_process_bio(struct mapped_device *md, } /* drop the extra reference count */ - dec_pending(ci.io, error); + dec_pending(ci.io, errno_to_blk_status(error)); } /*----------------------------------------------------------------- * CRUD END diff --git a/drivers/md/md.c b/drivers/md/md.c index c99634612fc4..b01e458d31e9 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7996,7 +7996,7 @@ bool md_write_start(struct mddev *mddev, struct bio *bi) if (mddev->safemode == 1) mddev->safemode = 0; /* sync_checkers is always 0 when writes_pending is in per-cpu mode */ - if (mddev->in_sync || !mddev->sync_checkers) { + if (mddev->in_sync || mddev->sync_checkers) { spin_lock(&mddev->lock); if (mddev->in_sync) { mddev->in_sync = 0; @@ -8656,6 +8656,9 @@ void md_check_recovery(struct mddev *mddev) if (mddev_trylock(mddev)) { int spares = 0; + if (!mddev->external && mddev->safemode == 1) + mddev->safemode = 0; + if (mddev->ro) { struct md_rdev *rdev; if (!mddev->external && mddev->in_sync) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index bfa1e907c472..2dcbafa8e66c 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -236,9 +236,10 @@ struct r5l_io_unit { bool need_split_bio; struct bio *split_bio; - unsigned int has_flush:1; /* include flush request */ - unsigned int has_fua:1; /* include fua request */ - unsigned int has_null_flush:1; /* include empty flush request */ + unsigned int has_flush:1; /* include flush request */ + unsigned int has_fua:1; /* include fua request */ + unsigned int has_null_flush:1; /* include null flush request */ + unsigned int has_flush_payload:1; /* include flush payload */ /* * io isn't sent yet, flush/fua request can only be submitted till it's * the first IO in running_ios list @@ -571,6 +572,8 @@ static void r5l_log_endio(struct bio *bio) struct r5l_io_unit *io_deferred; struct r5l_log *log = io->log; unsigned long flags; + bool has_null_flush; + bool has_flush_payload; if (bio->bi_status) md_error(log->rdev->mddev, log->rdev); @@ -580,6 +583,16 @@ static void r5l_log_endio(struct bio *bio) spin_lock_irqsave(&log->io_list_lock, flags); __r5l_set_io_unit_state(io, IO_UNIT_IO_END); + + /* + * if the io doesn't not have null_flush or flush payload, + * it is not safe to access it after releasing io_list_lock. + * Therefore, it is necessary to check the condition with + * the lock held. + */ + has_null_flush = io->has_null_flush; + has_flush_payload = io->has_flush_payload; + if (log->need_cache_flush && !list_empty(&io->stripe_list)) r5l_move_to_end_ios(log); else @@ -600,19 +613,23 @@ static void r5l_log_endio(struct bio *bio) if (log->need_cache_flush) md_wakeup_thread(log->rdev->mddev->thread); - if (io->has_null_flush) { + /* finish flush only io_unit and PAYLOAD_FLUSH only io_unit */ + if (has_null_flush) { struct bio *bi; WARN_ON(bio_list_empty(&io->flush_barriers)); while ((bi = bio_list_pop(&io->flush_barriers)) != NULL) { bio_endio(bi); - atomic_dec(&io->pending_stripe); + if (atomic_dec_and_test(&io->pending_stripe)) { + __r5l_stripe_write_finished(io); + return; + } } } - - /* finish flush only io_unit and PAYLOAD_FLUSH only io_unit */ - if (atomic_read(&io->pending_stripe) == 0) - __r5l_stripe_write_finished(io); + /* decrease pending_stripe for flush payload */ + if (has_flush_payload) + if (atomic_dec_and_test(&io->pending_stripe)) + __r5l_stripe_write_finished(io); } static void r5l_do_submit_io(struct r5l_log *log, struct r5l_io_unit *io) @@ -881,6 +898,11 @@ static void r5l_append_flush_payload(struct r5l_log *log, sector_t sect) payload->size = cpu_to_le32(sizeof(__le64)); payload->flush_stripes[0] = cpu_to_le64(sect); io->meta_offset += meta_size; + /* multiple flush payloads count as one pending_stripe */ + if (!io->has_flush_payload) { + io->has_flush_payload = 1; + atomic_inc(&io->pending_stripe); + } mutex_unlock(&log->io_mutex); } @@ -2540,23 +2562,32 @@ static ssize_t r5c_journal_mode_show(struct mddev *mddev, char *page) */ int r5c_journal_mode_set(struct mddev *mddev, int mode) { - struct r5conf *conf = mddev->private; - struct r5l_log *log = conf->log; - - if (!log) - return -ENODEV; + struct r5conf *conf; + int err; if (mode < R5C_JOURNAL_MODE_WRITE_THROUGH || mode > R5C_JOURNAL_MODE_WRITE_BACK) return -EINVAL; + err = mddev_lock(mddev); + if (err) + return err; + conf = mddev->private; + if (!conf || !conf->log) { + mddev_unlock(mddev); + return -ENODEV; + } + if (raid5_calc_degraded(conf) > 0 && - mode == R5C_JOURNAL_MODE_WRITE_BACK) + mode == R5C_JOURNAL_MODE_WRITE_BACK) { + mddev_unlock(mddev); return -EINVAL; + } mddev_suspend(mddev); conf->log->r5c_journal_mode = mode; mddev_resume(mddev); + mddev_unlock(mddev); pr_debug("md/raid:%s: setting r5c cache mode to %d: %s\n", mdname(mddev), mode, r5c_journal_mode_str[mode]); diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c index 99e644cda4d1..ebf69ff48ae2 100644 --- a/drivers/memory/atmel-ebi.c +++ b/drivers/memory/atmel-ebi.c @@ -72,7 +72,7 @@ struct atmel_smc_timing_xlate { { .name = nm, .converter = atmel_smc_cs_conf_set_pulse, .shift = pos} #define ATMEL_SMC_CYCLE_XLATE(nm, pos) \ - { .name = nm, .converter = atmel_smc_cs_conf_set_setup, .shift = pos} + { .name = nm, .converter = atmel_smc_cs_conf_set_cycle, .shift = pos} static void at91sam9_ebi_get_config(struct atmel_ebi_dev *ebid, struct atmel_ebi_dev_config *conf) @@ -120,12 +120,14 @@ static int atmel_ebi_xslate_smc_timings(struct atmel_ebi_dev *ebid, if (!ret) { required = true; ncycles = DIV_ROUND_UP(val, clk_period_ns); - if (ncycles > ATMEL_SMC_MODE_TDF_MAX || - ncycles < ATMEL_SMC_MODE_TDF_MIN) { + if (ncycles > ATMEL_SMC_MODE_TDF_MAX) { ret = -EINVAL; goto out; } + if (ncycles < ATMEL_SMC_MODE_TDF_MIN) + ncycles = ATMEL_SMC_MODE_TDF_MIN; + smcconf->mode |= ATMEL_SMC_MODE_TDF(ncycles); } @@ -263,7 +265,7 @@ static int atmel_ebi_xslate_smc_config(struct atmel_ebi_dev *ebid, } ret = atmel_ebi_xslate_smc_timings(ebid, np, &conf->smcconf); - if (ret) + if (ret < 0) return -EINVAL; if ((ret > 0 && !required) || (!ret && required)) { diff --git a/drivers/mfd/atmel-smc.c b/drivers/mfd/atmel-smc.c index 954cf0f66a31..20cc0ea470fa 100644 --- a/drivers/mfd/atmel-smc.c +++ b/drivers/mfd/atmel-smc.c @@ -206,7 +206,7 @@ EXPORT_SYMBOL_GPL(atmel_smc_cs_conf_set_pulse); * parameter * * This function encodes the @ncycles value as described in the datasheet - * (section "SMC Pulse Register"), and then stores the result in the + * (section "SMC Cycle Register"), and then stores the result in the * @conf->setup field at @shift position. * * Returns -EINVAL if @shift is invalid, -ERANGE if @ncycles does not fit in diff --git a/drivers/mfd/da9062-core.c b/drivers/mfd/da9062-core.c index fbe0f245ce8e..fe1811523e4a 100644 --- a/drivers/mfd/da9062-core.c +++ b/drivers/mfd/da9062-core.c @@ -645,6 +645,9 @@ static const struct regmap_range da9062_aa_readable_ranges[] = { .range_min = DA9062AA_VLDO1_B, .range_max = DA9062AA_VLDO4_B, }, { + .range_min = DA9062AA_BBAT_CONT, + .range_max = DA9062AA_BBAT_CONT, + }, { .range_min = DA9062AA_INTERFACE, .range_max = DA9062AA_CONFIG_E, }, { @@ -721,6 +724,9 @@ static const struct regmap_range da9062_aa_writeable_ranges[] = { .range_min = DA9062AA_VLDO1_B, .range_max = DA9062AA_VLDO4_B, }, { + .range_min = DA9062AA_BBAT_CONT, + .range_max = DA9062AA_BBAT_CONT, + }, { .range_min = DA9062AA_GP_ID_0, .range_max = DA9062AA_GP_ID_19, }, diff --git a/drivers/misc/mic/scif/scif_dma.c b/drivers/misc/mic/scif/scif_dma.c index 64d5760d069a..63d6246d6dff 100644 --- a/drivers/misc/mic/scif/scif_dma.c +++ b/drivers/misc/mic/scif/scif_dma.c @@ -200,16 +200,6 @@ static void scif_mmu_notifier_release(struct mmu_notifier *mn, schedule_work(&scif_info.misc_work); } -static void scif_mmu_notifier_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - struct scif_mmu_notif *mmn; - - mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier); - scif_rma_destroy_tcw(mmn, address, PAGE_SIZE); -} - static void scif_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, @@ -235,7 +225,6 @@ static void scif_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, static const struct mmu_notifier_ops scif_mmu_notifier_ops = { .release = scif_mmu_notifier_release, .clear_flush_young = NULL, - .invalidate_page = scif_mmu_notifier_invalidate_page, .invalidate_range_start = scif_mmu_notifier_invalidate_range_start, .invalidate_range_end = scif_mmu_notifier_invalidate_range_end}; diff --git a/drivers/misc/sgi-gru/grutlbpurge.c b/drivers/misc/sgi-gru/grutlbpurge.c index e936d43895d2..9918eda0e05f 100644 --- a/drivers/misc/sgi-gru/grutlbpurge.c +++ b/drivers/misc/sgi-gru/grutlbpurge.c @@ -247,17 +247,6 @@ static void gru_invalidate_range_end(struct mmu_notifier *mn, gru_dbg(grudev, "gms %p, start 0x%lx, end 0x%lx\n", gms, start, end); } -static void gru_invalidate_page(struct mmu_notifier *mn, struct mm_struct *mm, - unsigned long address) -{ - struct gru_mm_struct *gms = container_of(mn, struct gru_mm_struct, - ms_notifier); - - STAT(mmu_invalidate_page); - gru_flush_tlb_range(gms, address, PAGE_SIZE); - gru_dbg(grudev, "gms %p, address 0x%lx\n", gms, address); -} - static void gru_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct gru_mm_struct *gms = container_of(mn, struct gru_mm_struct, @@ -269,7 +258,6 @@ static void gru_release(struct mmu_notifier *mn, struct mm_struct *mm) static const struct mmu_notifier_ops gru_mmuops = { - .invalidate_page = gru_invalidate_page, .invalidate_range_start = gru_invalidate_range_start, .invalidate_range_end = gru_invalidate_range_end, .release = gru_release, diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index f1bbfd389367..8bd7aba811e9 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1213,7 +1213,7 @@ static void mmc_blk_issue_drv_op(struct mmc_queue *mq, struct request *req) break; } mq_rq->drv_op_result = ret; - blk_end_request_all(req, ret); + blk_end_request_all(req, ret ? BLK_STS_IOERR : BLK_STS_OK); } static void mmc_blk_issue_discard_rq(struct mmc_queue *mq, struct request *req) @@ -1371,12 +1371,46 @@ static inline void mmc_apply_rel_rw(struct mmc_blk_request *brq, R1_CC_ERROR | /* Card controller error */ \ R1_ERROR) /* General/unknown error */ -static bool mmc_blk_has_cmd_err(struct mmc_command *cmd) +static void mmc_blk_eval_resp_error(struct mmc_blk_request *brq) { - if (!cmd->error && cmd->resp[0] & CMD_ERRORS) - cmd->error = -EIO; + u32 val; + + /* + * Per the SD specification(physical layer version 4.10)[1], + * section 4.3.3, it explicitly states that "When the last + * block of user area is read using CMD18, the host should + * ignore OUT_OF_RANGE error that may occur even the sequence + * is correct". And JESD84-B51 for eMMC also has a similar + * statement on section 6.8.3. + * + * Multiple block read/write could be done by either predefined + * method, namely CMD23, or open-ending mode. For open-ending mode, + * we should ignore the OUT_OF_RANGE error as it's normal behaviour. + * + * However the spec[1] doesn't tell us whether we should also + * ignore that for predefined method. But per the spec[1], section + * 4.15 Set Block Count Command, it says"If illegal block count + * is set, out of range error will be indicated during read/write + * operation (For example, data transfer is stopped at user area + * boundary)." In another word, we could expect a out of range error + * in the response for the following CMD18/25. And if argument of + * CMD23 + the argument of CMD18/25 exceed the max number of blocks, + * we could also expect to get a -ETIMEDOUT or any error number from + * the host drivers due to missing data response(for write)/data(for + * read), as the cards will stop the data transfer by itself per the + * spec. So we only need to check R1_OUT_OF_RANGE for open-ending mode. + */ - return cmd->error; + if (!brq->stop.error) { + bool oor_with_open_end; + /* If there is no error yet, check R1 response */ + + val = brq->stop.resp[0] & CMD_ERRORS; + oor_with_open_end = val & R1_OUT_OF_RANGE && !brq->mrq.sbc; + + if (val && !oor_with_open_end) + brq->stop.error = -EIO; + } } static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card, @@ -1400,8 +1434,11 @@ static enum mmc_blk_status mmc_blk_err_check(struct mmc_card *card, * stop.error indicates a problem with the stop command. Data * may have been transferred, or may still be transferring. */ - if (brq->sbc.error || brq->cmd.error || mmc_blk_has_cmd_err(&brq->stop) || - brq->data.error) { + + mmc_blk_eval_resp_error(brq); + + if (brq->sbc.error || brq->cmd.error || + brq->stop.error || brq->data.error) { switch (mmc_blk_cmd_recovery(card, req, brq, &ecc_err, &gen_err)) { case ERR_RETRY: return MMC_BLK_RETRY; @@ -1681,9 +1718,9 @@ static bool mmc_blk_rw_cmd_err(struct mmc_blk_data *md, struct mmc_card *card, if (err) req_pending = old_req_pending; else - req_pending = blk_end_request(req, 0, blocks << 9); + req_pending = blk_end_request(req, BLK_STS_OK, blocks << 9); } else { - req_pending = blk_end_request(req, 0, brq->data.bytes_xfered); + req_pending = blk_end_request(req, BLK_STS_OK, brq->data.bytes_xfered); } return req_pending; } diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c index bc1781bb070b..c580af05b033 100644 --- a/drivers/mmc/host/sdhci-xenon.c +++ b/drivers/mmc/host/sdhci-xenon.c @@ -210,8 +210,27 @@ static void xenon_set_uhs_signaling(struct sdhci_host *host, sdhci_writew(host, ctrl_2, SDHCI_HOST_CONTROL2); } +static void xenon_set_power(struct sdhci_host *host, unsigned char mode, + unsigned short vdd) +{ + struct mmc_host *mmc = host->mmc; + u8 pwr = host->pwr; + + sdhci_set_power_noreg(host, mode, vdd); + + if (host->pwr == pwr) + return; + + if (host->pwr == 0) + vdd = 0; + + if (!IS_ERR(mmc->supply.vmmc)) + mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, vdd); +} + static const struct sdhci_ops sdhci_xenon_ops = { .set_clock = sdhci_set_clock, + .set_power = xenon_set_power, .set_bus_width = sdhci_set_bus_width, .reset = xenon_reset, .set_uhs_signaling = xenon_set_uhs_signaling, diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c index 2c8baa0c2c4e..ceec21bd30c4 100644 --- a/drivers/mtd/nand/atmel/nand-controller.c +++ b/drivers/mtd/nand/atmel/nand-controller.c @@ -1364,7 +1364,18 @@ static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand, ret = atmel_smc_cs_conf_set_timing(smcconf, ATMEL_HSMC_TIMINGS_TADL_SHIFT, ncycles); - if (ret) + /* + * Version 4 of the ONFI spec mandates that tADL be at least 400 + * nanoseconds, but, depending on the master clock rate, 400 ns may not + * fit in the tADL field of the SMC reg. We need to relax the check and + * accept the -ERANGE return code. + * + * Note that previous versions of the ONFI spec had a lower tADL_min + * (100 or 200 ns). It's not clear why this timing constraint got + * increased but it seems most NANDs are fine with values lower than + * 400ns, so we should be safe. + */ + if (ret && ret != -ERANGE) return ret; ncycles = DIV_ROUND_UP(conf->timings.sdr.tAR_min, mckperiodps); diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c index 03a0d057bf2f..e4211c3cc49b 100644 --- a/drivers/mtd/nand/nandsim.c +++ b/drivers/mtd/nand/nandsim.c @@ -2373,6 +2373,7 @@ static int __init ns_init_module(void) return 0; err_exit: + nandsim_debugfs_remove(nand); free_nandsim(nand); nand_release(nsmtd); for (i = 0;i < ARRAY_SIZE(nand->partitions); ++i) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 9bee6c1c70cc..fc63992ab0e0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1569,7 +1569,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) new_slave->delay = 0; new_slave->link_failure_count = 0; - if (bond_update_speed_duplex(new_slave)) + if (bond_update_speed_duplex(new_slave) && + bond_needs_speed_duplex(bond)) new_slave->link = BOND_LINK_DOWN; new_slave->last_rx = jiffies - @@ -2140,11 +2141,13 @@ static void bond_miimon_commit(struct bonding *bond) continue; case BOND_LINK_UP: - if (bond_update_speed_duplex(slave)) { + if (bond_update_speed_duplex(slave) && + bond_needs_speed_duplex(bond)) { slave->link = BOND_LINK_DOWN; - netdev_warn(bond->dev, - "failed to get link speed/duplex for %s\n", - slave->dev->name); + if (net_ratelimit()) + netdev_warn(bond->dev, + "failed to get link speed/duplex for %s\n", + slave->dev->name); continue; } bond_set_slave_link_state(slave, BOND_LINK_UP, diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 648f91b58d1e..9b6ce7c3f6c3 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1048,6 +1048,7 @@ struct bcm_sf2_of_data { u32 type; const u16 *reg_offsets; unsigned int core_reg_align; + unsigned int num_cfp_rules; }; /* Register offsets for the SWITCH_REG_* block */ @@ -1071,6 +1072,7 @@ static const struct bcm_sf2_of_data bcm_sf2_7445_data = { .type = BCM7445_DEVICE_ID, .core_reg_align = 0, .reg_offsets = bcm_sf2_7445_reg_offsets, + .num_cfp_rules = 256, }; static const u16 bcm_sf2_7278_reg_offsets[] = { @@ -1093,6 +1095,7 @@ static const struct bcm_sf2_of_data bcm_sf2_7278_data = { .type = BCM7278_DEVICE_ID, .core_reg_align = 1, .reg_offsets = bcm_sf2_7278_reg_offsets, + .num_cfp_rules = 128, }; static const struct of_device_id bcm_sf2_of_match[] = { @@ -1149,6 +1152,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) priv->type = data->type; priv->reg_offsets = data->reg_offsets; priv->core_reg_align = data->core_reg_align; + priv->num_cfp_rules = data->num_cfp_rules; /* Auto-detection using standard registers will not work, so * provide an indication of what kind of device we are for diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index 7d3030e04f11..7f9125eef3df 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -72,6 +72,7 @@ struct bcm_sf2_priv { u32 type; const u16 *reg_offsets; unsigned int core_reg_align; + unsigned int num_cfp_rules; /* spinlock protecting access to the indirect registers */ spinlock_t indir_lock; diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index 2fb32d67065f..8a1da7e67707 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -98,7 +98,7 @@ static inline void bcm_sf2_cfp_rule_addr_set(struct bcm_sf2_priv *priv, { u32 reg; - WARN_ON(addr >= CFP_NUM_RULES); + WARN_ON(addr >= priv->num_cfp_rules); reg = core_readl(priv, CORE_CFP_ACC); reg &= ~(XCESS_ADDR_MASK << XCESS_ADDR_SHIFT); @@ -109,7 +109,7 @@ static inline void bcm_sf2_cfp_rule_addr_set(struct bcm_sf2_priv *priv, static inline unsigned int bcm_sf2_cfp_rule_size(struct bcm_sf2_priv *priv) { /* Entry #0 is reserved */ - return CFP_NUM_RULES - 1; + return priv->num_cfp_rules - 1; } static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port, @@ -523,7 +523,7 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv, if (!(reg & OP_STR_DONE)) break; - } while (index < CFP_NUM_RULES); + } while (index < priv->num_cfp_rules); /* Put the TCAM size here */ nfc->data = bcm_sf2_cfp_rule_size(priv); @@ -544,7 +544,7 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port, case ETHTOOL_GRXCLSRLCNT: /* Subtract the default, unusable rule */ nfc->rule_cnt = bitmap_weight(priv->cfp.used, - CFP_NUM_RULES) - 1; + priv->num_cfp_rules) - 1; /* We support specifying rule locations */ nfc->data |= RX_CLS_LOC_SPECIAL; break; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 1d307f2def2d..6e253d913fe2 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1661,21 +1661,21 @@ static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata) return 0; } -static int xgene_enet_check_phy_handle(struct xgene_enet_pdata *pdata) +static void xgene_enet_check_phy_handle(struct xgene_enet_pdata *pdata) { int ret; if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) - return 0; + return; if (!IS_ENABLED(CONFIG_MDIO_XGENE)) - return 0; + return; ret = xgene_enet_phy_connect(pdata->ndev); if (!ret) pdata->mdio_driver = true; - return 0; + return; } static void xgene_enet_gpiod_get(struct xgene_enet_pdata *pdata) @@ -1779,10 +1779,6 @@ static int xgene_enet_get_resources(struct xgene_enet_pdata *pdata) if (ret) return ret; - ret = xgene_enet_check_phy_handle(pdata); - if (ret) - return ret; - xgene_enet_gpiod_get(pdata); pdata->clk = devm_clk_get(&pdev->dev, NULL); @@ -2097,9 +2093,11 @@ static int xgene_enet_probe(struct platform_device *pdev) goto err; } + xgene_enet_check_phy_handle(pdata); + ret = xgene_enet_init_hw(pdata); if (ret) - goto err; + goto err2; link_state = pdata->mac_ops->link_state; if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) { @@ -2117,29 +2115,30 @@ static int xgene_enet_probe(struct platform_device *pdev) spin_lock_init(&pdata->stats_lock); ret = xgene_extd_stats_init(pdata); if (ret) - goto err2; + goto err1; xgene_enet_napi_add(pdata); ret = register_netdev(ndev); if (ret) { netdev_err(ndev, "Failed to register netdev\n"); - goto err2; + goto err1; } return 0; -err2: +err1: /* * If necessary, free_netdev() will call netif_napi_del() and undo * the effects of xgene_enet_napi_add()'s calls to netif_napi_add(). */ + xgene_enet_delete_desc_rings(pdata); + +err2: if (pdata->mdio_driver) xgene_enet_phy_disconnect(pdata); else if (phy_interface_mode_is_rgmii(pdata->phy_mode)) xgene_enet_mdio_remove(pdata); -err1: - xgene_enet_delete_desc_rings(pdata); err: free_netdev(ndev); return ret; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index fce0fd3f23ff..bf9b3f020e10 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -105,8 +105,7 @@ struct aq_hw_ops { int (*hw_set_mac_address)(struct aq_hw_s *self, u8 *mac_addr); - int (*hw_get_link_status)(struct aq_hw_s *self, - struct aq_hw_link_status_s *link_status); + int (*hw_get_link_status)(struct aq_hw_s *self); int (*hw_set_link_speed)(struct aq_hw_s *self, u32 speed); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 9ee1c5016784..6ac9e2602d6d 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -103,6 +103,8 @@ int aq_nic_cfg_start(struct aq_nic_s *self) else cfg->vecs = 1U; + cfg->num_rss_queues = min(cfg->vecs, AQ_CFG_NUM_RSS_QUEUES_DEF); + cfg->irq_type = aq_pci_func_get_irq_type(self->aq_pci_func); if ((cfg->irq_type == AQ_HW_IRQ_LEGACY) || @@ -123,33 +125,30 @@ static void aq_nic_service_timer_cb(unsigned long param) struct net_device *ndev = aq_nic_get_ndev(self); int err = 0; unsigned int i = 0U; - struct aq_hw_link_status_s link_status; struct aq_ring_stats_rx_s stats_rx; struct aq_ring_stats_tx_s stats_tx; if (aq_utils_obj_test(&self->header.flags, AQ_NIC_FLAGS_IS_NOT_READY)) goto err_exit; - err = self->aq_hw_ops.hw_get_link_status(self->aq_hw, &link_status); + err = self->aq_hw_ops.hw_get_link_status(self->aq_hw); if (err < 0) goto err_exit; - self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw, - self->aq_nic_cfg.is_interrupt_moderation); - - if (memcmp(&link_status, &self->link_status, sizeof(link_status))) { - if (link_status.mbps) { - aq_utils_obj_set(&self->header.flags, - AQ_NIC_FLAG_STARTED); - aq_utils_obj_clear(&self->header.flags, - AQ_NIC_LINK_DOWN); - netif_carrier_on(self->ndev); - } else { - netif_carrier_off(self->ndev); - aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN); - } + self->link_status = self->aq_hw->aq_link_status; - self->link_status = link_status; + self->aq_hw_ops.hw_interrupt_moderation_set(self->aq_hw, + self->aq_nic_cfg.is_interrupt_moderation); + + if (self->link_status.mbps) { + aq_utils_obj_set(&self->header.flags, + AQ_NIC_FLAG_STARTED); + aq_utils_obj_clear(&self->header.flags, + AQ_NIC_LINK_DOWN); + netif_carrier_on(self->ndev); + } else { + netif_carrier_off(self->ndev); + aq_utils_obj_set(&self->header.flags, AQ_NIC_LINK_DOWN); } memset(&stats_rx, 0U, sizeof(struct aq_ring_stats_rx_s)); @@ -597,14 +596,11 @@ exit: } int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) -__releases(&ring->lock) -__acquires(&ring->lock) { struct aq_ring_s *ring = NULL; unsigned int frags = 0U; unsigned int vec = skb->queue_mapping % self->aq_nic_cfg.vecs; unsigned int tc = 0U; - unsigned int trys = AQ_CFG_LOCK_TRYS; int err = NETDEV_TX_OK; bool is_nic_in_bad_state; @@ -628,36 +624,21 @@ __acquires(&ring->lock) goto err_exit; } - do { - if (spin_trylock(&ring->header.lock)) { - frags = aq_nic_map_skb(self, skb, ring); - - if (likely(frags)) { - err = self->aq_hw_ops.hw_ring_tx_xmit( - self->aq_hw, - ring, frags); - if (err >= 0) { - if (aq_ring_avail_dx(ring) < - AQ_CFG_SKB_FRAGS_MAX + 1) - aq_nic_ndev_queue_stop( - self, - ring->idx); - - ++ring->stats.tx.packets; - ring->stats.tx.bytes += skb->len; - } - } else { - err = NETDEV_TX_BUSY; - } + frags = aq_nic_map_skb(self, skb, ring); - spin_unlock(&ring->header.lock); - break; - } - } while (--trys); + if (likely(frags)) { + err = self->aq_hw_ops.hw_ring_tx_xmit(self->aq_hw, + ring, + frags); + if (err >= 0) { + if (aq_ring_avail_dx(ring) < AQ_CFG_SKB_FRAGS_MAX + 1) + aq_nic_ndev_queue_stop(self, ring->idx); - if (!trys) { + ++ring->stats.tx.packets; + ring->stats.tx.bytes += skb->len; + } + } else { err = NETDEV_TX_BUSY; - goto err_exit; } err_exit: @@ -688,11 +669,26 @@ int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev) netdev_for_each_mc_addr(ha, ndev) { ether_addr_copy(self->mc_list.ar[i++], ha->addr); ++self->mc_list.count; + + if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) + break; } - return self->aq_hw_ops.hw_multicast_list_set(self->aq_hw, + if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) { + /* Number of filters is too big: atlantic does not support this. + * Force all multi filter to support this. + * With this we disable all UC filters and setup "all pass" + * multicast mask + */ + self->packet_filter |= IFF_ALLMULTI; + self->aq_hw->aq_nic_cfg->mc_list_count = 0; + return self->aq_hw_ops.hw_packet_filter_set(self->aq_hw, + self->packet_filter); + } else { + return self->aq_hw_ops.hw_multicast_list_set(self->aq_hw, self->mc_list.ar, self->mc_list.count); + } } int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 9a0817938eca..ec5579fb8268 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -101,7 +101,6 @@ int aq_ring_init(struct aq_ring_s *self) self->hw_head = 0; self->sw_head = 0; self->sw_tail = 0; - spin_lock_init(&self->header.lock); return 0; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_utils.h b/drivers/net/ethernet/aquantia/atlantic/aq_utils.h index f6012b34abe6..e12bcdfb874a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_utils.h @@ -17,7 +17,6 @@ #define AQ_DIMOF(_ARY_) ARRAY_SIZE(_ARY_) struct aq_obj_s { - spinlock_t lock; /* spinlock for nic/rings processing */ atomic_t flags; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c index ad5b4d4dac7f..fee446af748f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_vec.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_vec.c @@ -34,8 +34,6 @@ struct aq_vec_s { #define AQ_VEC_RX_ID 1 static int aq_vec_poll(struct napi_struct *napi, int budget) -__releases(&self->lock) -__acquires(&self->lock) { struct aq_vec_s *self = container_of(napi, struct aq_vec_s, napi); struct aq_ring_s *ring = NULL; @@ -47,7 +45,7 @@ __acquires(&self->lock) if (!self) { err = -EINVAL; - } else if (spin_trylock(&self->header.lock)) { + } else { for (i = 0U, ring = self->ring[0]; self->tx_rings > i; ++i, ring = self->ring[i]) { if (self->aq_hw_ops->hw_ring_tx_head_update) { @@ -105,11 +103,8 @@ __acquires(&self->lock) self->aq_hw_ops->hw_irq_enable(self->aq_hw, 1U << self->aq_ring_param.vec_idx); } - -err_exit: - spin_unlock(&self->header.lock); } - +err_exit: return work_done; } @@ -185,8 +180,6 @@ int aq_vec_init(struct aq_vec_s *self, struct aq_hw_ops *aq_hw_ops, self->aq_hw_ops = aq_hw_ops; self->aq_hw = aq_hw; - spin_lock_init(&self->header.lock); - for (i = 0U, ring = self->ring[0]; self->tx_rings > i; ++i, ring = self->ring[i]) { err = aq_ring_init(&ring[AQ_VEC_TX_ID]); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index faeb4935ef3e..c5a02df7a48b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -629,6 +629,12 @@ static int hw_atl_a0_hw_ring_rx_receive(struct aq_hw_s *self, buff->is_udp_cso = (is_err & 0x10U) ? 0 : 1; else if (0x0U == (pkt_type & 0x1CU)) buff->is_tcp_cso = (is_err & 0x10U) ? 0 : 1; + + /* Checksum offload workaround for small packets */ + if (rxd_wb->pkt_len <= 60) { + buff->is_ip_cso = 0U; + buff->is_cso_err = 0U; + } } is_err &= ~0x18U; 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 1bceb7358e5c..21784cc39dab 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 @@ -645,6 +645,12 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, buff->is_udp_cso = buff->is_cso_err ? 0U : 1U; 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; + } } is_err &= ~0x18U; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index 8d6d8f5804da..4f5ec9a0fbfb 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -141,6 +141,12 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self, err = hw_atl_utils_ver_match(aq_hw_caps->fw_ver_expected, aq_hw_read_reg(self, 0x18U)); + + if (err < 0) + pr_err("%s: Bad FW version detected: expected=%x, actual=%x\n", + AQ_CFG_DRV_NAME, + aq_hw_caps->fw_ver_expected, + aq_hw_read_reg(self, 0x18U)); return err; } @@ -313,11 +319,11 @@ void hw_atl_utils_mpi_set(struct aq_hw_s *self, err_exit:; } -int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self, - struct aq_hw_link_status_s *link_status) +int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self) { u32 cp0x036C = aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR); u32 link_speed_mask = cp0x036C >> HW_ATL_MPI_SPEED_SHIFT; + struct aq_hw_link_status_s *link_status = &self->aq_link_status; if (!link_speed_mask) { link_status->mbps = 0U; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h index a66aee51ab5b..e0360a6b2202 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h @@ -180,8 +180,7 @@ void hw_atl_utils_mpi_set(struct aq_hw_s *self, int hw_atl_utils_mpi_set_speed(struct aq_hw_s *self, u32 speed, enum hal_atl_utils_fw_state_e state); -int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self, - struct aq_hw_link_status_s *link_status); +int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self); int hw_atl_utils_get_mac_permanent(struct aq_hw_s *self, struct aq_hw_caps_s *aq_hw_caps, diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index dc3052751bc1..c28fa5a8734c 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -597,7 +597,7 @@ static int bcm_sysport_set_coalesce(struct net_device *dev, static void bcm_sysport_free_cb(struct bcm_sysport_cb *cb) { - dev_kfree_skb_any(cb->skb); + dev_consume_skb_any(cb->skb); cb->skb = NULL; dma_unmap_addr_set(cb, dma_addr, 0); } @@ -1346,6 +1346,8 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv, ring->cbs = kcalloc(size, sizeof(struct bcm_sysport_cb), GFP_KERNEL); if (!ring->cbs) { + dma_free_coherent(kdev, sizeof(struct dma_desc), + ring->desc_cpu, ring->desc_dma); netif_err(priv, hw, priv->netdev, "CB allocation failed\n"); return -ENOMEM; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index e7c8539cbddf..f20b3d2a4c23 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4647,7 +4647,6 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp) pf->port_id = le16_to_cpu(resp->port_id); bp->dev->dev_port = pf->port_id; memcpy(pf->mac_addr, resp->mac_address, ETH_ALEN); - memcpy(bp->dev->dev_addr, pf->mac_addr, ETH_ALEN); pf->max_rsscos_ctxs = le16_to_cpu(resp->max_rsscos_ctx); pf->max_cp_rings = le16_to_cpu(resp->max_cmpl_rings); pf->max_tx_rings = le16_to_cpu(resp->max_tx_rings); @@ -4687,16 +4686,6 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp) vf->max_stat_ctxs = le16_to_cpu(resp->max_stat_ctx); memcpy(vf->mac_addr, resp->mac_address, ETH_ALEN); - mutex_unlock(&bp->hwrm_cmd_lock); - - if (is_valid_ether_addr(vf->mac_addr)) { - /* overwrite netdev dev_adr with admin VF MAC */ - memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN); - } else { - eth_hw_addr_random(bp->dev); - rc = bnxt_approve_mac(bp, bp->dev->dev_addr); - } - return rc; #endif } @@ -7152,6 +7141,7 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc) bp->tx_nr_rings = bp->tx_nr_rings_per_tc; netdev_reset_tc(dev); } + bp->tx_nr_rings += bp->tx_nr_rings_xdp; bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) : bp->tx_nr_rings + bp->rx_nr_rings; bp->num_stat_ctxs = bp->cp_nr_rings; @@ -7661,6 +7651,28 @@ void bnxt_restore_pf_fw_resources(struct bnxt *bp) bnxt_subtract_ulp_resources(bp, BNXT_ROCE_ULP); } +static int bnxt_init_mac_addr(struct bnxt *bp) +{ + int rc = 0; + + if (BNXT_PF(bp)) { + memcpy(bp->dev->dev_addr, bp->pf.mac_addr, ETH_ALEN); + } else { +#ifdef CONFIG_BNXT_SRIOV + struct bnxt_vf_info *vf = &bp->vf; + + if (is_valid_ether_addr(vf->mac_addr)) { + /* overwrite netdev dev_adr with admin VF MAC */ + memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN); + } else { + eth_hw_addr_random(bp->dev); + rc = bnxt_approve_mac(bp, bp->dev->dev_addr); + } +#endif + } + return rc; +} + static void bnxt_parse_log_pcie_link(struct bnxt *bp) { enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN; @@ -7789,7 +7801,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rc = -1; goto init_err_pci_clean; } - + rc = bnxt_init_mac_addr(bp); + if (rc) { + dev_err(&pdev->dev, "Unable to initialize mac address.\n"); + rc = -EADDRNOTAVAIL; + goto init_err_pci_clean; + } rc = bnxt_hwrm_queue_qportcfg(bp); if (rc) { netdev_err(bp->dev, "hwrm query qportcfg failure rc: %x\n", diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index 77da75a55c02..997e10e8b863 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -84,6 +84,8 @@ static int bnxt_unregister_dev(struct bnxt_en_dev *edev, int ulp_id) max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp); bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs + 1); + if (ulp->msix_requested) + edev->en_ops->bnxt_free_msix(edev, ulp_id); } if (ulp->max_async_event_id) bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0); diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index a981c4ee9d72..fea3f9a5fb2d 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1360,7 +1360,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev, if (skb) { pkts_compl++; bytes_compl += GENET_CB(skb)->bytes_sent; - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); } txbds_processed++; @@ -1875,7 +1875,7 @@ static int bcmgenet_alloc_rx_buffers(struct bcmgenet_priv *priv, cb = ring->cbs + i; skb = bcmgenet_rx_refill(priv, cb); if (skb) - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); if (!cb->skb) return -ENOMEM; } @@ -1894,7 +1894,7 @@ static void bcmgenet_free_rx_buffers(struct bcmgenet_priv *priv) skb = bcmgenet_free_rx_cb(&priv->pdev->dev, cb); if (skb) - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); } } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index ef4be781fd05..09ea62ee96d3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -529,6 +529,7 @@ enum { /* adapter flags */ USING_SOFT_PARAMS = (1 << 6), MASTER_PF = (1 << 7), FW_OFLD_CONN = (1 << 9), + ROOT_NO_RELAXED_ORDERING = (1 << 10), }; enum { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index e403fa18f1b1..33bb8678833a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -4654,11 +4654,6 @@ static void print_port_info(const struct net_device *dev) dev->name, adap->params.vpd.id, adap->name, buf); } -static void enable_pcie_relaxed_ordering(struct pci_dev *dev) -{ - pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN); -} - /* * Free the following resources: * - memory used for tables @@ -4908,7 +4903,6 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_enable_pcie_error_reporting(pdev); - enable_pcie_relaxed_ordering(pdev); pci_set_master(pdev); pci_save_state(pdev); @@ -4947,6 +4941,23 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->msg_enable = DFLT_MSG_ENABLE; memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map)); + /* If possible, we use PCIe Relaxed Ordering Attribute to deliver + * Ingress Packet Data to Free List Buffers in order to allow for + * chipset performance optimizations between the Root Complex and + * Memory Controllers. (Messages to the associated Ingress Queue + * notifying new Packet Placement in the Free Lists Buffers will be + * send without the Relaxed Ordering Attribute thus guaranteeing that + * all preceding PCIe Transaction Layer Packets will be processed + * first.) But some Root Complexes have various issues with Upstream + * Transaction Layer Packets with the Relaxed Ordering Attribute set. + * The PCIe devices which under the Root Complexes will be cleared the + * Relaxed Ordering bit in the configuration space, So we check our + * PCIe configuration space to see if it's flagged with advice against + * using Relaxed Ordering. + */ + if (!pcie_relaxed_ordering_enabled(pdev)) + adapter->flags |= ROOT_NO_RELAXED_ORDERING; + spin_lock_init(&adapter->stats_lock); spin_lock_init(&adapter->tid_release_lock); spin_lock_init(&adapter->win0_lock); diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index ede12209f20b..4ef68f69b58c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2719,6 +2719,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, struct fw_iq_cmd c; struct sge *s = &adap->sge; struct port_info *pi = netdev_priv(dev); + int relaxed = !(adap->flags & ROOT_NO_RELAXED_ORDERING); /* Size needs to be multiple of 16, including status entry. */ iq->size = roundup(iq->size, 16); @@ -2772,8 +2773,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, flsz = fl->size / 8 + s->stat_len / sizeof(struct tx_desc); c.iqns_to_fl0congen |= htonl(FW_IQ_CMD_FL0PACKEN_F | - FW_IQ_CMD_FL0FETCHRO_F | - FW_IQ_CMD_FL0DATARO_F | + FW_IQ_CMD_FL0FETCHRO_V(relaxed) | + FW_IQ_CMD_FL0DATARO_V(relaxed) | FW_IQ_CMD_FL0PADEN_F); if (cong >= 0) c.iqns_to_fl0congen |= diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 82bf7aac6cdb..0293b41171a5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -369,12 +369,12 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, list_del(&entry.list); spin_unlock(&adap->mbox_lock); ret = (v == MBOX_OWNER_FW) ? -EBUSY : -ETIMEDOUT; - t4_record_mbox(adap, cmd, MBOX_LEN, access, ret); + t4_record_mbox(adap, cmd, size, access, ret); return ret; } /* Copy in the new mailbox command and send it on its way ... */ - t4_record_mbox(adap, cmd, MBOX_LEN, access, 0); + t4_record_mbox(adap, cmd, size, access, 0); for (i = 0; i < size; i += 8) t4_write_reg64(adap, data_reg + i, be64_to_cpu(*p++)); @@ -426,7 +426,7 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, } ret = (pcie_fw & PCIE_FW_ERR_F) ? -ENXIO : -ETIMEDOUT; - t4_record_mbox(adap, cmd, MBOX_LEN, access, ret); + t4_record_mbox(adap, cmd, size, access, ret); dev_err(adap->pdev_dev, "command %#x in mailbox %d timed out\n", *(const u8 *)cmd, mbox); t4_report_fw_error(adap); diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h index 109bc630408b..08c6ddb84a04 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h @@ -408,6 +408,7 @@ enum { /* adapter flags */ USING_MSI = (1UL << 1), USING_MSIX = (1UL << 2), QUEUES_BOUND = (1UL << 3), + ROOT_NO_RELAXED_ORDERING = (1UL << 4), }; /* diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index ac7a150c54e9..2b85b874fd0d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2888,6 +2888,24 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, */ adapter->name = pci_name(pdev); adapter->msg_enable = DFLT_MSG_ENABLE; + + /* If possible, we use PCIe Relaxed Ordering Attribute to deliver + * Ingress Packet Data to Free List Buffers in order to allow for + * chipset performance optimizations between the Root Complex and + * Memory Controllers. (Messages to the associated Ingress Queue + * notifying new Packet Placement in the Free Lists Buffers will be + * send without the Relaxed Ordering Attribute thus guaranteeing that + * all preceding PCIe Transaction Layer Packets will be processed + * first.) But some Root Complexes have various issues with Upstream + * Transaction Layer Packets with the Relaxed Ordering Attribute set. + * The PCIe devices which under the Root Complexes will be cleared the + * Relaxed Ordering bit in the configuration space, So we check our + * PCIe configuration space to see if it's flagged with advice against + * using Relaxed Ordering. + */ + if (!pcie_relaxed_ordering_enabled(pdev)) + adapter->flags |= ROOT_NO_RELAXED_ORDERING; + err = adap_init0(adapter); if (err) goto err_unmap_bar; diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index e37dde2ba97f..05498e7f2840 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -2205,6 +2205,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, struct port_info *pi = netdev_priv(dev); struct fw_iq_cmd cmd, rpl; int ret, iqandst, flsz = 0; + int relaxed = !(adapter->flags & ROOT_NO_RELAXED_ORDERING); /* * If we're using MSI interrupts and we're not initializing the @@ -2300,6 +2301,8 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, cpu_to_be32( FW_IQ_CMD_FL0HOSTFCMODE_V(SGE_HOSTFCMODE_NONE) | FW_IQ_CMD_FL0PACKEN_F | + FW_IQ_CMD_FL0FETCHRO_V(relaxed) | + FW_IQ_CMD_FL0DATARO_V(relaxed) | FW_IQ_CMD_FL0PADEN_F); /* In T6, for egress queue type FL there is internal overhead diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 34dae51effd4..59da7ac3c108 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1863,7 +1863,6 @@ err_setup_mdio: err_ioremap: release_resource(priv->res); err_req_mem: - netif_napi_del(&priv->napi); free_netdev(netdev); err_alloc_etherdev: return err; diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c index 6e67d22fd0d5..1c7da16ad0ff 100644 --- a/drivers/net/ethernet/freescale/fman/mac.c +++ b/drivers/net/ethernet/freescale/fman/mac.c @@ -623,6 +623,8 @@ static struct platform_device *dpaa_eth_add_device(int fman_id, goto no_mem; } + pdev->dev.of_node = node; + pdev->dev.parent = priv->dev; set_dma_ops(&pdev->dev, get_dma_ops(priv->dev)); ret = platform_device_add_data(pdev, &data, sizeof(data)); diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index 48d21c1e09f2..4d598ca8503a 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -6504,7 +6504,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, struct resource *res; const char *dt_mac_addr; const char *mac_from; - char hw_mac_addr[ETH_ALEN]; + char hw_mac_addr[ETH_ALEN] = {0}; u32 id; int features; int phy_mode; diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 09b9bc17bce9..5fe5cdc51357 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -432,7 +432,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) /* Virtual PCI function needs to determine UAR page size from * firmware. Only master PCI function can set the uar page size */ - if (enable_4k_uar) + if (enable_4k_uar || !dev->persist->num_vfs) dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT; else dev->uar_page_shift = PAGE_SHIFT; @@ -2277,7 +2277,7 @@ static int mlx4_init_hca(struct mlx4_dev *dev) dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; - if (enable_4k_uar) { + if (enable_4k_uar || !dev->persist->num_vfs) { init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT; init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0039b4725405..2f26fb34d741 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -263,6 +263,7 @@ struct mlx5e_dcbx { /* The only setting that cannot be read from FW */ u8 tc_tsa[IEEE_8021QAZ_MAX_TCS]; + u8 cap; }; #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 2eb54d36e16e..c1d384fca4dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -288,13 +288,8 @@ static int mlx5e_dcbnl_ieee_setpfc(struct net_device *dev, static u8 mlx5e_dcbnl_getdcbx(struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_dcbx *dcbx = &priv->dcbx; - u8 mode = DCB_CAP_DCBX_VER_IEEE | DCB_CAP_DCBX_VER_CEE; - - if (dcbx->mode == MLX5E_DCBX_PARAM_VER_OPER_HOST) - mode |= DCB_CAP_DCBX_HOST; - return mode; + return priv->dcbx.cap; } static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) @@ -312,6 +307,7 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) /* set dcbx to fw controlled */ if (!mlx5e_dcbnl_set_dcbx_mode(priv, MLX5E_DCBX_PARAM_VER_OPER_AUTO)) { dcbx->mode = MLX5E_DCBX_PARAM_VER_OPER_AUTO; + dcbx->cap &= ~DCB_CAP_DCBX_HOST; return 0; } @@ -324,6 +320,8 @@ static u8 mlx5e_dcbnl_setdcbx(struct net_device *dev, u8 mode) if (mlx5e_dcbnl_switch_to_host_mode(netdev_priv(dev))) return 1; + dcbx->cap = mode; + return 0; } @@ -628,9 +626,9 @@ static u8 mlx5e_dcbnl_getcap(struct net_device *netdev, *cap = false; break; case DCB_CAP_ATTR_DCBX: - *cap = (DCB_CAP_DCBX_LLD_MANAGED | - DCB_CAP_DCBX_VER_CEE | - DCB_CAP_DCBX_STATIC); + *cap = priv->dcbx.cap | + DCB_CAP_DCBX_VER_CEE | + DCB_CAP_DCBX_VER_IEEE; break; default: *cap = 0; @@ -754,8 +752,16 @@ void mlx5e_dcbnl_initialize(struct mlx5e_priv *priv) { struct mlx5e_dcbx *dcbx = &priv->dcbx; + if (!MLX5_CAP_GEN(priv->mdev, qos)) + return; + if (MLX5_CAP_GEN(priv->mdev, dcbx)) mlx5e_dcbnl_query_dcbx_mode(priv, &dcbx->mode); + priv->dcbx.cap = DCB_CAP_DCBX_VER_CEE | + DCB_CAP_DCBX_VER_IEEE; + if (priv->dcbx.mode == MLX5E_DCBX_PARAM_VER_OPER_HOST) + priv->dcbx.cap |= DCB_CAP_DCBX_HOST; + mlx5e_ets_init(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 917fade5f5d5..f5594014715b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -641,8 +641,10 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, new_channels.params = priv->channels.params; new_channels.params.num_channels = count; - mlx5e_build_default_indir_rqt(priv->mdev, new_channels.params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); + if (!netif_is_rxfh_configured(priv->netdev)) + mlx5e_build_default_indir_rqt(priv->mdev, + new_channels.params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 57f31fa478ce..6ad7f07e7861 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1969,6 +1969,7 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, } mlx5e_build_common_cq_param(priv, param); + param->cq_period_mode = params->rx_cq_period_mode; } static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 325b2c8c1c6d..7344433259fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -222,13 +222,13 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, if (unlikely(!page)) return -ENOMEM; - dma_info->page = page; dma_info->addr = dma_map_page(rq->pdev, page, 0, RQ_PAGE_SIZE(rq), rq->buff.map_dir); if (unlikely(dma_mapping_error(rq->pdev, dma_info->addr))) { put_page(page); return -ENOMEM; } + dma_info->page = page; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 3c536f560dd2..7f282e8f4e7f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1443,12 +1443,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int ret; - dst = ip6_route_output(dev_net(mirred_dev), NULL, fl6); - ret = dst->error; - if (ret) { - dst_release(dst); + ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst, + fl6); + if (ret < 0) return ret; - } *out_ttl = ip6_dst_hoplimit(dst); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index aaa0f4ebba9a..31353e5c3c78 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -128,10 +128,10 @@ static inline int mlx5e_skb_l3_header_offset(struct sk_buff *skb) return mlx5e_skb_l2_header_offset(skb); } -static inline unsigned int mlx5e_calc_min_inline(enum mlx5_inline_modes mode, - struct sk_buff *skb) +static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode, + struct sk_buff *skb) { - int hlen; + u16 hlen; switch (mode) { case MLX5_INLINE_MODE_NONE: @@ -140,19 +140,22 @@ static inline unsigned int mlx5e_calc_min_inline(enum mlx5_inline_modes mode, hlen = eth_get_headlen(skb->data, skb_headlen(skb)); if (hlen == ETH_HLEN && !skb_vlan_tag_present(skb)) hlen += VLAN_HLEN; - return hlen; + break; case MLX5_INLINE_MODE_IP: /* When transport header is set to zero, it means no transport * header. When transport header is set to 0xff's, it means * transport header wasn't set. */ - if (skb_transport_offset(skb)) - return mlx5e_skb_l3_header_offset(skb); + if (skb_transport_offset(skb)) { + hlen = mlx5e_skb_l3_header_offset(skb); + break; + } /* fall through */ case MLX5_INLINE_MODE_L2: default: - return mlx5e_skb_l2_header_offset(skb); + hlen = mlx5e_skb_l2_header_offset(skb); } + return min_t(u16, hlen, skb->len); } static inline void mlx5e_tx_skb_pull_inline(unsigned char **skb_data, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 95b64025ce36..5bc0593bd76e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -815,7 +815,7 @@ void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports) struct mlx5_eswitch_rep *rep; int vport; - for (vport = 0; vport < nvports; vport++) { + for (vport = nvports - 1; vport >= 0; vport--) { rep = &esw->offloads.vport_reps[vport]; if (!rep->valid) continue; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index c065132b956d..16885827367b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1186,7 +1186,6 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, } } - clear_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); set_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); out: mutex_unlock(&dev->intf_state_mutex); @@ -1261,7 +1260,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_drain_health_recovery(dev); mutex_lock(&dev->intf_state_mutex); - if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { + if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is down, NOP\n", __func__); if (cleanup) @@ -1270,7 +1269,6 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, } clear_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state); - set_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state); if (mlx5_device_registered(dev)) mlx5_detach_device(dev); @@ -1565,8 +1563,6 @@ static void shutdown(struct pci_dev *pdev) int err; dev_info(&pdev->dev, "Shutdown was called\n"); - /* Notify mlx5 clients that the kernel is being shut down */ - set_bit(MLX5_INTERFACE_STATE_SHUTDOWN, &dev->intf_state); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, priv, false); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c index f774de6f5fcb..520f6382dfde 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c @@ -201,13 +201,13 @@ static int destroy_srq_cmd(struct mlx5_core_dev *dev, static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq, u16 lwm, int is_srq) { - /* arm_srq structs missing using identical xrc ones */ - u32 srq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)] = {0}; - u32 srq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0}; + u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0}; + u32 srq_out[MLX5_ST_SZ_DW(arm_rq_out)] = {0}; - MLX5_SET(arm_xrc_srq_in, srq_in, opcode, MLX5_CMD_OP_ARM_XRC_SRQ); - MLX5_SET(arm_xrc_srq_in, srq_in, xrc_srqn, srq->srqn); - MLX5_SET(arm_xrc_srq_in, srq_in, lwm, lwm); + MLX5_SET(arm_rq_in, srq_in, opcode, MLX5_CMD_OP_ARM_RQ); + MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ); + MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn); + MLX5_SET(arm_rq_in, srq_in, lwm, lwm); return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in), srq_out, sizeof(srq_out)); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 60bf8f27cc00..c6a3e61b53bd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -4139,6 +4139,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, return -EINVAL; if (!info->linking) break; + if (netdev_has_any_upper_dev(upper_dev)) + return -EINVAL; if (netif_is_lag_master(upper_dev) && !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev, info->upper_info)) @@ -4258,6 +4260,10 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev, upper_dev = info->upper_dev; if (!netif_is_bridge_master(upper_dev)) return -EINVAL; + if (!info->linking) + break; + if (netdev_has_any_upper_dev(upper_dev)) + return -EINVAL; break; case NETDEV_CHANGEUPPER: upper_dev = info->upper_dev; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 5eb1606765c5..d39ffbfcc436 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -705,6 +705,7 @@ static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port, bool is_port_mc_router) { struct mlxsw_sp_bridge_port *bridge_port; + int err; if (switchdev_trans_ph_prepare(trans)) return 0; @@ -715,11 +716,17 @@ static int mlxsw_sp_port_attr_mc_router_set(struct mlxsw_sp_port *mlxsw_sp_port, return 0; if (!bridge_port->bridge_device->multicast_enabled) - return 0; + goto out; - return mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port, - MLXSW_SP_FLOOD_TYPE_MC, - is_port_mc_router); + err = mlxsw_sp_bridge_port_flood_table_set(mlxsw_sp_port, bridge_port, + MLXSW_SP_FLOOD_TYPE_MC, + is_port_mc_router); + if (err) + return err; + +out: + bridge_port->mrouter = is_port_mc_router; + return 0; } static int mlxsw_sp_port_mc_disabled_set(struct mlxsw_sp_port *mlxsw_sp_port, diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index dd7fa9cf225f..b0837b58c3a1 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -115,14 +115,10 @@ nfp_flower_cmsg_portmod_rx(struct nfp_app *app, struct sk_buff *skb) return; } - if (link) { + if (link) netif_carrier_on(netdev); - rtnl_lock(); - dev_set_mtu(netdev, be16_to_cpu(msg->mtu)); - rtnl_unlock(); - } else { + else netif_carrier_off(netdev); - } rcu_read_unlock(); } diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index 0e08404480ef..d25b5038c3a2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -42,33 +42,29 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_two *frame, struct tc_cls_flower_offload *flow, u8 key_type, bool mask_version) { + struct fl_flow_key *target = mask_version ? flow->mask : flow->key; struct flow_dissector_key_vlan *flow_vlan; u16 tmp_tci; + memset(frame, 0, sizeof(struct nfp_flower_meta_two)); /* Populate the metadata frame. */ frame->nfp_flow_key_layer = key_type; frame->mask_id = ~0; - if (mask_version) { - frame->tci = cpu_to_be16(~0); - return; - } - - flow_vlan = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_VLAN, - flow->key); - - /* Populate the tci field. */ - if (!flow_vlan->vlan_id) { - tmp_tci = 0; - } else { - tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, - flow_vlan->vlan_priority) | - FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, - flow_vlan->vlan_id) | - NFP_FLOWER_MASK_VLAN_CFI; + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + flow_vlan = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_VLAN, + target); + /* Populate the tci field. */ + if (flow_vlan->vlan_id) { + tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, + flow_vlan->vlan_priority) | + FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, + flow_vlan->vlan_id) | + NFP_FLOWER_MASK_VLAN_CFI; + frame->tci = cpu_to_be16(tmp_tci); + } } - frame->tci = cpu_to_be16(tmp_tci); } static void @@ -99,17 +95,18 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame, bool mask_version) { struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_eth_addrs *flow_mac; - - flow_mac = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - target); + struct flow_dissector_key_eth_addrs *addr; memset(frame, 0, sizeof(struct nfp_flower_mac_mpls)); - /* Populate mac frame. */ - ether_addr_copy(frame->mac_dst, &flow_mac->dst[0]); - ether_addr_copy(frame->mac_src, &flow_mac->src[0]); + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + addr = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + target); + /* Populate mac frame. */ + ether_addr_copy(frame->mac_dst, &addr->dst[0]); + ether_addr_copy(frame->mac_src, &addr->src[0]); + } if (mask_version) frame->mpls_lse = cpu_to_be32(~0); @@ -121,14 +118,17 @@ nfp_flower_compile_tport(struct nfp_flower_tp_ports *frame, bool mask_version) { struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ports *flow_tp; + struct flow_dissector_key_ports *tp; - flow_tp = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_PORTS, - target); + memset(frame, 0, sizeof(struct nfp_flower_tp_ports)); - frame->port_src = flow_tp->src; - frame->port_dst = flow_tp->dst; + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_PORTS)) { + tp = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_PORTS, + target); + frame->port_src = tp->src; + frame->port_dst = tp->dst; + } } static void @@ -137,25 +137,27 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame, bool mask_version) { struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv4_addrs *flow_ipv4; - struct flow_dissector_key_basic *flow_basic; - - flow_ipv4 = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - target); - - flow_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - target); + struct flow_dissector_key_ipv4_addrs *addr; + struct flow_dissector_key_basic *basic; - /* Populate IPv4 frame. */ - frame->reserved = 0; - frame->ipv4_src = flow_ipv4->src; - frame->ipv4_dst = flow_ipv4->dst; - frame->proto = flow_basic->ip_proto; /* Wildcard TOS/TTL for now. */ - frame->tos = 0; - frame->ttl = 0; + memset(frame, 0, sizeof(struct nfp_flower_ipv4)); + + if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + addr = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + target); + frame->ipv4_src = addr->src; + frame->ipv4_dst = addr->dst; + } + + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + target); + frame->proto = basic->ip_proto; + } } static void @@ -164,26 +166,27 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame, bool mask_version) { struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv6_addrs *flow_ipv6; - struct flow_dissector_key_basic *flow_basic; - - flow_ipv6 = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - target); + struct flow_dissector_key_ipv6_addrs *addr; + struct flow_dissector_key_basic *basic; - flow_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - target); - - /* Populate IPv6 frame. */ - frame->reserved = 0; - frame->ipv6_src = flow_ipv6->src; - frame->ipv6_dst = flow_ipv6->dst; - frame->proto = flow_basic->ip_proto; /* Wildcard LABEL/TOS/TTL for now. */ - frame->ipv6_flow_label_exthdr = 0; - frame->tos = 0; - frame->ttl = 0; + memset(frame, 0, sizeof(struct nfp_flower_ipv6)); + + if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + addr = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + target); + frame->ipv6_src = addr->src; + frame->ipv6_dst = addr->dst; + } + + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + target); + frame->proto = basic->ip_proto; + } } int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 4ad10bd5e139..74a96d6bb05c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -105,43 +105,62 @@ static int nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, struct tc_cls_flower_offload *flow) { - struct flow_dissector_key_control *mask_enc_ctl; - struct flow_dissector_key_basic *mask_basic; - struct flow_dissector_key_basic *key_basic; + struct flow_dissector_key_basic *mask_basic = NULL; + struct flow_dissector_key_basic *key_basic = NULL; + struct flow_dissector_key_ip *mask_ip = NULL; u32 key_layer_two; u8 key_layer; int key_size; - mask_enc_ctl = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - flow->mask); + if (dissector_uses_key(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_dissector_key_control *mask_enc_ctl = + skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_ENC_CONTROL, + flow->mask); + /* We are expecting a tunnel. For now we ignore offloading. */ + if (mask_enc_ctl->addr_type) + return -EOPNOTSUPP; + } - mask_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->mask); + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + mask_basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + flow->mask); + + key_basic = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_BASIC, + flow->key); + } + + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) + mask_ip = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_IP, + flow->mask); - key_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->key); key_layer_two = 0; key_layer = NFP_FLOWER_LAYER_PORT | NFP_FLOWER_LAYER_MAC; key_size = sizeof(struct nfp_flower_meta_one) + sizeof(struct nfp_flower_in_port) + sizeof(struct nfp_flower_mac_mpls); - /* We are expecting a tunnel. For now we ignore offloading. */ - if (mask_enc_ctl->addr_type) - return -EOPNOTSUPP; - - if (mask_basic->n_proto) { + if (mask_basic && mask_basic->n_proto) { /* Ethernet type is present in the key. */ switch (key_basic->n_proto) { case cpu_to_be16(ETH_P_IP): + if (mask_ip && mask_ip->tos) + return -EOPNOTSUPP; + if (mask_ip && mask_ip->ttl) + return -EOPNOTSUPP; key_layer |= NFP_FLOWER_LAYER_IPV4; key_size += sizeof(struct nfp_flower_ipv4); break; case cpu_to_be16(ETH_P_IPV6): + if (mask_ip && mask_ip->tos) + return -EOPNOTSUPP; + if (mask_ip && mask_ip->ttl) + return -EOPNOTSUPP; key_layer |= NFP_FLOWER_LAYER_IPV6; key_size += sizeof(struct nfp_flower_ipv6); break; @@ -152,6 +171,11 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, case cpu_to_be16(ETH_P_ARP): return -EOPNOTSUPP; + /* Currently we do not offload MPLS. */ + case cpu_to_be16(ETH_P_MPLS_UC): + case cpu_to_be16(ETH_P_MPLS_MC): + return -EOPNOTSUPP; + /* Will be included in layer 2. */ case cpu_to_be16(ETH_P_8021Q): break; @@ -166,7 +190,7 @@ nfp_flower_calculate_key_layers(struct nfp_fl_key_ls *ret_key_ls, } } - if (mask_basic->ip_proto) { + if (mask_basic && mask_basic->ip_proto) { /* Ethernet type is present in the key. */ switch (key_basic->ip_proto) { case IPPROTO_TCP: diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index d67969d3e484..3f199db2002e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -98,21 +98,20 @@ static int nfp_pcie_sriov_enable(struct pci_dev *pdev, int num_vfs) struct nfp_pf *pf = pci_get_drvdata(pdev); int err; - mutex_lock(&pf->lock); - if (num_vfs > pf->limit_vfs) { nfp_info(pf->cpp, "Firmware limits number of VFs to %u\n", pf->limit_vfs); - err = -EINVAL; - goto err_unlock; + return -EINVAL; } err = pci_enable_sriov(pdev, num_vfs); if (err) { dev_warn(&pdev->dev, "Failed to enable PCI SR-IOV: %d\n", err); - goto err_unlock; + return err; } + mutex_lock(&pf->lock); + err = nfp_app_sriov_enable(pf->app, num_vfs); if (err) { dev_warn(&pdev->dev, @@ -129,9 +128,8 @@ static int nfp_pcie_sriov_enable(struct pci_dev *pdev, int num_vfs) return num_vfs; err_sriov_disable: - pci_disable_sriov(pdev); -err_unlock: mutex_unlock(&pf->lock); + pci_disable_sriov(pdev); return err; #endif return 0; @@ -158,10 +156,10 @@ static int nfp_pcie_sriov_disable(struct pci_dev *pdev) pf->num_vfs = 0; + mutex_unlock(&pf->lock); + pci_disable_sriov(pdev); dev_dbg(&pdev->dev, "Removed VFs.\n"); - - mutex_unlock(&pf->lock); #endif return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 4631ca8b8eb2..66a09e490cf5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -895,6 +895,8 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) netdev_tx_sent_queue(nd_q, txbuf->real_len); + skb_tx_timestamp(skb); + tx_ring->wr_p += nr_frags + 1; if (nfp_net_tx_ring_should_stop(tx_ring)) nfp_net_tx_ring_stop(nd_q, tx_ring); @@ -903,13 +905,10 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) if (!skb->xmit_more || netif_xmit_stopped(nd_q)) nfp_net_tx_xmit_more_flush(tx_ring); - skb_tx_timestamp(skb); - return NETDEV_TX_OK; err_unmap: - --f; - while (f >= 0) { + while (--f >= 0) { frag = &skb_shinfo(skb)->frags[f]; dma_unmap_page(dp->dev, tx_ring->txbufs[wr_idx].dma_addr, skb_frag_size(frag), DMA_TO_DEVICE); @@ -1752,6 +1751,10 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) continue; } + nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr); + + nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr); + if (likely(!meta.portid)) { netdev = dp->netdev; } else { @@ -1760,16 +1763,12 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) nn = netdev_priv(dp->netdev); netdev = nfp_app_repr_get(nn->app, meta.portid); if (unlikely(!netdev)) { - nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, skb); + nfp_net_rx_drop(dp, r_vec, rx_ring, NULL, skb); continue; } nfp_repr_inc_rx_stats(netdev, pkt_len); } - nfp_net_dma_unmap_rx(dp, rxbuf->dma_addr); - - nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr); - skb_reserve(skb, pkt_off); skb_put(skb, pkt_len); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 5797dbf2b507..34b985384d26 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -456,13 +456,9 @@ static int nfp_net_pf_app_start(struct nfp_pf *pf) { int err; - err = nfp_net_pf_app_start_ctrl(pf); - if (err) - return err; - err = nfp_app_start(pf->app, pf->ctrl_vnic); if (err) - goto err_ctrl_stop; + return err; if (pf->num_vfs) { err = nfp_app_sriov_enable(pf->app, pf->num_vfs); @@ -474,8 +470,6 @@ static int nfp_net_pf_app_start(struct nfp_pf *pf) err_app_stop: nfp_app_stop(pf->app); -err_ctrl_stop: - nfp_net_pf_app_stop_ctrl(pf); return err; } @@ -484,7 +478,6 @@ static void nfp_net_pf_app_stop(struct nfp_pf *pf) if (pf->num_vfs) nfp_app_sriov_disable(pf->app); nfp_app_stop(pf->app); - nfp_net_pf_app_stop_ctrl(pf); } static void nfp_net_pci_unmap_mem(struct nfp_pf *pf) @@ -559,7 +552,7 @@ err_unmap_ctrl: static void nfp_net_pci_remove_finish(struct nfp_pf *pf) { - nfp_net_pf_app_stop(pf); + nfp_net_pf_app_stop_ctrl(pf); /* stop app first, to avoid double free of ctrl vNIC's ddir */ nfp_net_debugfs_dir_clean(&pf->ddir); @@ -690,6 +683,7 @@ int nfp_net_pci_probe(struct nfp_pf *pf) { struct nfp_net_fw_version fw_ver; u8 __iomem *ctrl_bar, *qc_bar; + struct nfp_net *nn; int stride; int err; @@ -766,7 +760,7 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (err) goto err_free_vnics; - err = nfp_net_pf_app_start(pf); + err = nfp_net_pf_app_start_ctrl(pf); if (err) goto err_free_irqs; @@ -774,12 +768,20 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (err) goto err_stop_app; + err = nfp_net_pf_app_start(pf); + if (err) + goto err_clean_vnics; + mutex_unlock(&pf->lock); return 0; +err_clean_vnics: + list_for_each_entry(nn, &pf->vnics, vnic_list) + if (nfp_net_is_data_vnic(nn)) + nfp_net_pf_clean_vnic(pf, nn); err_stop_app: - nfp_net_pf_app_stop(pf); + nfp_net_pf_app_stop_ctrl(pf); err_free_irqs: nfp_net_pf_free_irqs(pf); err_free_vnics: @@ -803,6 +805,8 @@ void nfp_net_pci_remove(struct nfp_pf *pf) if (list_empty(&pf->vnics)) goto out; + nfp_net_pf_app_stop(pf); + list_for_each_entry(nn, &pf->vnics, vnic_list) if (nfp_net_is_data_vnic(nn)) nfp_net_pf_clean_vnic(pf, nn); diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c index 66ff15d08bad..0a66389c06c2 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c @@ -2311,7 +2311,7 @@ netxen_md_rdqueue(struct netxen_adapter *adapter, loop_cnt++) { NX_WR_DUMP_REG(select_addr, adapter->ahw.pci_base0, queue_id); read_addr = queueEntry->read_addr; - for (k = 0; k < read_cnt; k--) { + for (k = 0; k < read_cnt; k++) { NX_RD_DUMP_REG(read_addr, adapter->ahw.pci_base0, &read_value); *data_buff++ = read_value; diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c index 28ea0af89aef..e3223f2fe2ff 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c @@ -724,7 +724,7 @@ static void ql_build_coredump_seg_header( seg_hdr->cookie = MPI_COREDUMP_COOKIE; seg_hdr->segNum = seg_number; seg_hdr->segSize = seg_size; - memcpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1); + strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1); } /* diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index bd07a15d3b7c..e03fcf914690 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -6863,8 +6863,7 @@ static void rtl8169_tx_clear_range(struct rtl8169_private *tp, u32 start, rtl8169_unmap_tx_skb(&tp->pci_dev->dev, tx_skb, tp->TxDescArray + entry); if (skb) { - tp->dev->stats.tx_dropped++; - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); tx_skb->skb = NULL; } } @@ -7319,7 +7318,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp) tp->tx_stats.packets++; tp->tx_stats.bytes += tx_skb->skb->len; u64_stats_update_end(&tp->tx_stats.syncp); - dev_kfree_skb_any(tx_skb->skb); + dev_consume_skb_any(tx_skb->skb); tx_skb->skb = NULL; } dirty_tx++; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c index 73427e29df2a..fbd00cb0cb7d 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c @@ -47,6 +47,8 @@ static int sxgbe_probe_config_dt(struct platform_device *pdev, plat->mdio_bus_data = devm_kzalloc(&pdev->dev, sizeof(*plat->mdio_bus_data), GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg), GFP_KERNEL); if (!dma_cfg) diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c index c905971c5f3a..990a63d7fcb7 100644 --- a/drivers/net/ethernet/sfc/mcdi_port.c +++ b/drivers/net/ethernet/sfc/mcdi_port.c @@ -938,7 +938,6 @@ enum efx_stats_action { static int efx_mcdi_mac_stats(struct efx_nic *efx, enum efx_stats_action action, int clear) { - struct efx_ef10_nic_data *nic_data = efx->nic_data; MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN); int rc; int change = action == EFX_STATS_PULL ? 0 : 1; @@ -960,7 +959,12 @@ static int efx_mcdi_mac_stats(struct efx_nic *efx, MAC_STATS_IN_PERIODIC_NOEVENT, 1, MAC_STATS_IN_PERIOD_MS, period); MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len); - MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, nic_data->vport_id); + + if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) { + struct efx_ef10_nic_data *nic_data = efx->nic_data; + + MCDI_SET_DWORD(inbuf, MAC_STATS_IN_PORT_ID, nic_data->vport_id); + } rc = efx_mcdi_rpc_quiet(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf), NULL, 0, NULL); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 17d4bbaeb65c..6e359572b9f0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -269,7 +269,10 @@ static int socfpga_dwmac_set_phy_mode(struct socfpga_dwmac *dwmac) ctrl &= ~(SYSMGR_EMACGRP_CTRL_PHYSEL_MASK << reg_shift); ctrl |= val << reg_shift; - if (dwmac->f2h_ptp_ref_clk) { + if (dwmac->f2h_ptp_ref_clk || + phymode == PHY_INTERFACE_MODE_MII || + phymode == PHY_INTERFACE_MODE_GMII || + phymode == PHY_INTERFACE_MODE_SGMII) { ctrl |= SYSMGR_EMACGRP_CTRL_PTP_REF_CLK_MASK << (reg_shift / 2); regmap_read(sys_mgr_base_addr, SYSMGR_FPGAGRP_MODULE_REG, &module); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index fffd6d5fc907..39c2122a4f26 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -979,14 +979,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) } static const struct of_device_id sun8i_dwmac_match[] = { - { .compatible = "allwinner,sun8i-h3-emac", - .data = &emac_variant_h3 }, - { .compatible = "allwinner,sun8i-v3s-emac", - .data = &emac_variant_v3s }, - { .compatible = "allwinner,sun8i-a83t-emac", - .data = &emac_variant_a83t }, - { .compatible = "allwinner,sun50i-a64-emac", - .data = &emac_variant_a64 }, { } }; MODULE_DEVICE_TABLE(of, sun8i_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index db157a47000c..72ec711fcba2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -204,6 +204,7 @@ int stmmac_mdio_register(struct net_device *ndev) struct stmmac_priv *priv = netdev_priv(ndev); struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data; struct device_node *mdio_node = priv->plat->mdio_node; + struct device *dev = ndev->dev.parent; int addr, found; if (!mdio_bus_data) @@ -237,7 +238,7 @@ int stmmac_mdio_register(struct net_device *ndev) else err = mdiobus_register(new_bus); if (err != 0) { - netdev_err(ndev, "Cannot register the MDIO bus\n"); + dev_err(dev, "Cannot register the MDIO bus\n"); goto bus_register_fail; } @@ -285,14 +286,12 @@ int stmmac_mdio_register(struct net_device *ndev) irq_str = irq_num; break; } - netdev_info(ndev, "PHY ID %08x at %d IRQ %s (%s)%s\n", - phydev->phy_id, addr, irq_str, phydev_name(phydev), - act ? " active" : ""); + phy_attached_info(phydev); found = 1; } if (!found && !mdio_node) { - netdev_warn(ndev, "No PHY found\n"); + dev_warn(dev, "No PHY found\n"); mdiobus_unregister(new_bus); mdiobus_free(new_bus); return -ENODEV; diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c index 56ba411421f0..38d1cc557c11 100644 --- a/drivers/net/ethernet/ti/cpsw-common.c +++ b/drivers/net/ethernet/ti/cpsw-common.c @@ -96,7 +96,7 @@ int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr) if (of_machine_is_compatible("ti,dra7")) return davinci_emac_3517_get_macid(dev, 0x514, slave, mac_addr); - dev_err(dev, "incompatible machine/device type for reading mac address\n"); + dev_info(dev, "incompatible machine/device type for reading mac address\n"); return -ENOENT; } EXPORT_SYMBOL_GPL(ti_cm_get_macid); diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 0d78727f1a14..d91cbc6c3ca4 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1269,7 +1269,12 @@ static void netvsc_link_change(struct work_struct *w) bool notify = false, reschedule = false; unsigned long flags, next_reconfig, delay; - rtnl_lock(); + /* if changes are happening, comeback later */ + if (!rtnl_trylock()) { + schedule_delayed_work(&ndev_ctx->dwork, LINKCHANGE_INT); + return; + } + net_device = rtnl_dereference(ndev_ctx->nvdev); if (!net_device) goto out_unlock; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 5e1ab1160856..98e4deaa3a6a 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3521,6 +3521,7 @@ module_init(macsec_init); module_exit(macsec_exit); MODULE_ALIAS_RTNL_LINK("macsec"); +MODULE_ALIAS_GENL_FAMILY("macsec"); MODULE_DESCRIPTION("MACsec IEEE 802.1AE"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 5068c582d502..d0626bf5c540 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -749,9 +749,6 @@ void phy_stop_machine(struct phy_device *phydev) if (phydev->state > PHY_UP && phydev->state != PHY_HALTED) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); - - /* Now we can run the state machine synchronously */ - phy_state_machine(&phydev->state_queue.work); } /** diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1790f7fec125..2f742ae5b92e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -864,15 +864,17 @@ EXPORT_SYMBOL(phy_attached_info); #define ATTACHED_FMT "attached PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)" void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) { + const char *drv_name = phydev->drv ? phydev->drv->name : "unbound"; + if (!fmt) { dev_info(&phydev->mdio.dev, ATTACHED_FMT "\n", - phydev->drv->name, phydev_name(phydev), + drv_name, phydev_name(phydev), phydev->irq); } else { va_list ap; dev_info(&phydev->mdio.dev, ATTACHED_FMT, - phydev->drv->name, phydev_name(phydev), + drv_name, phydev_name(phydev), phydev->irq); va_start(ap, fmt); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 32ad87345f57..0a2c0a42283f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1879,6 +1879,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) err_detach: tun_detach_all(dev); + /* register_netdevice() already called tun_free_netdev() */ + goto err_free_dev; + err_free_flow: tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index 8f572b9f3625..9c80e80c5493 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1758,6 +1758,13 @@ static const struct usb_device_id cdc_devs[] = { .driver_info = (unsigned long)&wwan_noarp_info, }, + /* u-blox TOBY-L4 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x1546, 0x1010, + USB_CLASS_COMM, + USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, + }, + /* Generic CDC-NCM devices */ { USB_INTERFACE_INFO(USB_CLASS_COMM, USB_CDC_SUBCLASS_NCM, USB_CDC_PROTO_NONE), diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 98f17b05c68b..b06169ea60dc 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1058,7 +1058,7 @@ static void free_old_xmit_skbs(struct send_queue *sq) bytes += skb->len; packets++; - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); } /* Avoid overhead when no packets have been processed diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c index d21258d277ce..f1b60740e020 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c @@ -159,8 +159,10 @@ void brcmf_feat_attach(struct brcmf_pub *drvr) brcmf_feat_firmware_capabilities(ifp); memset(&gscan_cfg, 0, sizeof(gscan_cfg)); - brcmf_feat_iovar_data_set(ifp, BRCMF_FEAT_GSCAN, "pfn_gscan_cfg", - &gscan_cfg, sizeof(gscan_cfg)); + if (drvr->bus_if->chip != BRCM_CC_43430_CHIP_ID) + brcmf_feat_iovar_data_set(ifp, BRCMF_FEAT_GSCAN, + "pfn_gscan_cfg", + &gscan_cfg, sizeof(gscan_cfg)); brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_PNO, "pfn"); if (drvr->bus_if->wowl_supported) brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_WOWL, "wowl"); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index b4ecd1fe1374..97208ce19f92 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -154,7 +154,7 @@ static const struct iwl_tt_params iwl9000_tt_params = { const struct iwl_cfg iwl9160_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9160", .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_next_step = IWL9260B_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, IWL_DEVICE_9000, .ht_params = &iwl9000_ht_params, .nvm_ver = IWL9000_NVM_VERSION, @@ -165,7 +165,7 @@ const struct iwl_cfg iwl9160_2ac_cfg = { const struct iwl_cfg iwl9260_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9260", .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_next_step = IWL9260B_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, IWL_DEVICE_9000, .ht_params = &iwl9000_ht_params, .nvm_ver = IWL9000_NVM_VERSION, @@ -176,7 +176,7 @@ const struct iwl_cfg iwl9260_2ac_cfg = { const struct iwl_cfg iwl9270_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9270", .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_next_step = IWL9260B_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, IWL_DEVICE_9000, .ht_params = &iwl9000_ht_params, .nvm_ver = IWL9000_NVM_VERSION, @@ -186,8 +186,8 @@ const struct iwl_cfg iwl9270_2ac_cfg = { const struct iwl_cfg iwl9460_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9460", - .fw_name_pre = IWL9000_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9260A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, IWL_DEVICE_9000, .ht_params = &iwl9000_ht_params, .nvm_ver = IWL9000_NVM_VERSION, @@ -198,8 +198,8 @@ const struct iwl_cfg iwl9460_2ac_cfg = { const struct iwl_cfg iwl9560_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9560", - .fw_name_pre = IWL9000_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9260A_FW_PRE, + .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, IWL_DEVICE_9000, .ht_params = &iwl9000_ht_params, .nvm_ver = IWL9000_NVM_VERSION, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index 0fa8c473f1e2..c73a6438ce8f 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -328,6 +328,7 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * @IWL_UCODE_TLV_CAPA_TX_POWER_ACK: reduced TX power API has larger * command size (command version 4) that supports toggling ACK TX * power reduction. + * @IWL_UCODE_TLV_CAPA_MLME_OFFLOAD: supports MLME offload * * @NUM_IWL_UCODE_TLV_CAPA: number of bits used */ @@ -373,6 +374,7 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG = (__force iwl_ucode_tlv_capa_t)80, IWL_UCODE_TLV_CAPA_LQM_SUPPORT = (__force iwl_ucode_tlv_capa_t)81, IWL_UCODE_TLV_CAPA_TX_POWER_ACK = (__force iwl_ucode_tlv_capa_t)84, + IWL_UCODE_TLV_CAPA_MLME_OFFLOAD = (__force iwl_ucode_tlv_capa_t)96, NUM_IWL_UCODE_TLV_CAPA #ifdef __CHECKER__ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index c52623cb7c2a..d19c74827fbb 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -276,10 +276,10 @@ struct iwl_pwr_tx_backoff { * @fw_name_pre: Firmware filename prefix. The api version and extension * (.ucode) will be added to filename before loading from disk. The * filename is constructed as fw_name_pre<api>.ucode. - * @fw_name_pre_next_step: same as @fw_name_pre, only for next step + * @fw_name_pre_b_or_c_step: same as @fw_name_pre, only for b or c steps * (if supported) - * @fw_name_pre_rf_next_step: same as @fw_name_pre_next_step, only for rf next - * step. Supported only in integrated solutions. + * @fw_name_pre_rf_next_step: same as @fw_name_pre_b_or_c_step, only for rf + * next step. Supported only in integrated solutions. * @ucode_api_max: Highest version of uCode API supported by driver. * @ucode_api_min: Lowest version of uCode API supported by driver. * @max_inst_size: The maximal length of the fw inst section @@ -330,7 +330,7 @@ struct iwl_cfg { /* params specific to an individual device within a device family */ const char *name; const char *fw_name_pre; - const char *fw_name_pre_next_step; + const char *fw_name_pre_b_or_c_step; const char *fw_name_pre_rf_next_step; /* params not likely to change within a device family */ const struct iwl_base_params *base_params; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 6fdb5921e17f..4e0f86fe0a6f 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -216,8 +216,9 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) const char *fw_pre_name; if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_9000 && - CSR_HW_REV_STEP(drv->trans->hw_rev) == SILICON_B_STEP) - fw_pre_name = cfg->fw_name_pre_next_step; + (CSR_HW_REV_STEP(drv->trans->hw_rev) == SILICON_B_STEP || + CSR_HW_REV_STEP(drv->trans->hw_rev) == SILICON_C_STEP)) + fw_pre_name = cfg->fw_name_pre_b_or_c_step; else if (drv->trans->cfg->integrated && CSR_HW_RFID_STEP(drv->trans->hw_rf_id) == SILICON_B_STEP && cfg->fw_name_pre_rf_next_step) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 5c08f4d40f6a..3ee6767392b6 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -785,7 +785,8 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, int num_of_ch, __le32 *channels, u16 fw_mcc) { int ch_idx; - u16 ch_flags, prev_ch_flags = 0; + u16 ch_flags; + u32 reg_rule_flags, prev_reg_rule_flags = 0; const u8 *nvm_chan = cfg->ext_nvm ? iwl_ext_nvm_channels : iwl_nvm_channels; struct ieee80211_regdomain *regd; @@ -834,8 +835,11 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, continue; } + reg_rule_flags = iwl_nvm_get_regdom_bw_flags(nvm_chan, ch_idx, + ch_flags, cfg); + /* we can't continue the same rule */ - if (ch_idx == 0 || prev_ch_flags != ch_flags || + if (ch_idx == 0 || prev_reg_rule_flags != reg_rule_flags || center_freq - prev_center_freq > 20) { valid_rules++; new_rule = true; @@ -854,18 +858,17 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, rule->power_rule.max_eirp = DBM_TO_MBM(IWL_DEFAULT_MAX_TX_POWER); - rule->flags = iwl_nvm_get_regdom_bw_flags(nvm_chan, ch_idx, - ch_flags, cfg); + rule->flags = reg_rule_flags; /* rely on auto-calculation to merge BW of contiguous chans */ rule->flags |= NL80211_RRF_AUTO_BW; rule->freq_range.max_bandwidth_khz = 0; - prev_ch_flags = ch_flags; prev_center_freq = center_freq; + prev_reg_rule_flags = reg_rule_flags; IWL_DEBUG_DEV(dev, IWL_DL_LAR, - "Ch. %d [%sGHz] %s%s%s%s%s%s%s%s%s(0x%02x): Ad-Hoc %ssupported\n", + "Ch. %d [%sGHz] %s%s%s%s%s%s%s%s%s(0x%02x) reg_flags 0x%x: %s\n", center_freq, band == NL80211_BAND_5GHZ ? "5.2" : "2.4", CHECK_AND_PRINT_I(VALID), @@ -877,10 +880,10 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, CHECK_AND_PRINT_I(160MHZ), CHECK_AND_PRINT_I(INDOOR_ONLY), CHECK_AND_PRINT_I(GO_CONCURRENT), - ch_flags, + ch_flags, reg_rule_flags, ((ch_flags & NVM_CHANNEL_ACTIVE) && !(ch_flags & NVM_CHANNEL_RADAR)) - ? "" : "not "); + ? "Ad-Hoc" : ""); } regd->n_reg_rules = valid_rules; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 79e7a7a285dc..82863e9273eb 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -1275,8 +1275,10 @@ static int iwl_mvm_sar_get_wgds_table(struct iwl_mvm *mvm) entry = &wifi_pkg->package.elements[idx++]; if ((entry->type != ACPI_TYPE_INTEGER) || - (entry->integer.value > U8_MAX)) - return -EINVAL; + (entry->integer.value > U8_MAX)) { + ret = -EINVAL; + goto out_free; + } mvm->geo_profiles[i].values[j] = entry->integer.value; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index c7b1e58e3384..ce901be5fba8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -2597,8 +2597,18 @@ static void iwl_mvm_purge_deferred_tx_frames(struct iwl_mvm *mvm, spin_lock_bh(&mvm_sta->lock); for (i = 0; i <= IWL_MAX_TID_COUNT; i++) { tid_data = &mvm_sta->tid_data[i]; - while ((skb = __skb_dequeue(&tid_data->deferred_tx_frames))) + + while ((skb = __skb_dequeue(&tid_data->deferred_tx_frames))) { + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + + /* + * The first deferred frame should've stopped the MAC + * queues, so we should never get a second deferred + * frame for the RA/TID. + */ + iwl_mvm_start_mac_queues(mvm, info->hw_queue); ieee80211_free_txskb(mvm->hw, skb); + } } spin_unlock_bh(&mvm_sta->lock); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 65beca3a457a..8999a1199d60 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1291,7 +1291,7 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, * first index into rate scale table. */ if (info->flags & IEEE80211_TX_STAT_AMPDU) { - rs_collect_tpc_data(mvm, lq_sta, curr_tbl, lq_rate.index, + rs_collect_tpc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, info->status.ampdu_len, info->status.ampdu_ack_len, reduced_txp); @@ -1312,7 +1312,7 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, if (info->status.ampdu_ack_len == 0) info->status.ampdu_len = 1; - rs_collect_tlc_data(mvm, lq_sta, curr_tbl, lq_rate.index, + rs_collect_tlc_data(mvm, lq_sta, curr_tbl, tx_resp_rate.index, info->status.ampdu_len, info->status.ampdu_ack_len); @@ -1348,11 +1348,11 @@ void iwl_mvm_rs_tx_status(struct iwl_mvm *mvm, struct ieee80211_sta *sta, continue; rs_collect_tpc_data(mvm, lq_sta, tmp_tbl, - lq_rate.index, 1, + tx_resp_rate.index, 1, i < retries ? 0 : legacy_success, reduced_txp); rs_collect_tlc_data(mvm, lq_sta, tmp_tbl, - lq_rate.index, 1, + tx_resp_rate.index, 1, i < retries ? 0 : legacy_success); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index f3e608196369..71c8b800ffa9 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -636,9 +636,9 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, baid_data = rcu_dereference(mvm->baid_map[baid]); if (!baid_data) { - WARN(!(reorder & IWL_RX_MPDU_REORDER_BA_OLD_SN), - "Received baid %d, but no data exists for this BAID\n", - baid); + IWL_DEBUG_RX(mvm, + "Got valid BAID but no baid allocated, bypass the re-ordering buffer. Baid %d reorder 0x%x\n", + baid, reorder); return false; } @@ -759,7 +759,9 @@ static void iwl_mvm_agg_rx_received(struct iwl_mvm *mvm, data = rcu_dereference(mvm->baid_map[baid]); if (!data) { - WARN_ON(!(reorder_data & IWL_RX_MPDU_REORDER_BA_OLD_SN)); + IWL_DEBUG_RX(mvm, + "Got valid BAID but no baid allocated, bypass the re-ordering buffer. Baid %d reorder 0x%x\n", + baid, reorder_data); goto out; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index ab66b4394dfc..027ee5e72172 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -121,7 +121,8 @@ int iwl_mvm_sta_send_to_fw(struct iwl_mvm *mvm, struct ieee80211_sta *sta, .mac_id_n_color = cpu_to_le32(mvm_sta->mac_id_n_color), .add_modify = update ? 1 : 0, .station_flags_msk = cpu_to_le32(STA_FLG_FAT_EN_MSK | - STA_FLG_MIMO_EN_MSK), + STA_FLG_MIMO_EN_MSK | + STA_FLG_RTS_MIMO_PROT), .tid_disable_tx = cpu_to_le16(mvm_sta->tid_disable_agg), }; int ret; @@ -290,8 +291,8 @@ static void iwl_mvm_rx_agg_session_expired(unsigned long data) goto unlock; mvm_sta = iwl_mvm_sta_from_mac80211(sta); - ieee80211_stop_rx_ba_session_offl(mvm_sta->vif, - sta->addr, ba_data->tid); + ieee80211_rx_ba_timer_expired(mvm_sta->vif, + sta->addr, ba_data->tid); unlock: rcu_read_unlock(); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 60360ed73f26..5fcc9dd6be56 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -185,8 +185,14 @@ static u16 iwl_mvm_tx_csum(struct iwl_mvm *mvm, struct sk_buff *skb, else udp_hdr(skb)->check = 0; - /* mac header len should include IV, size is in words */ - if (info->control.hw_key) + /* + * mac header len should include IV, size is in words unless + * the IV is added by the firmware like in WEP. + * In new Tx API, the IV is always added by the firmware. + */ + if (!iwl_mvm_has_new_tx_api(mvm) && info->control.hw_key && + info->control.hw_key->cipher != WLAN_CIPHER_SUITE_WEP40 && + info->control.hw_key->cipher != WLAN_CIPHER_SUITE_WEP104) mh_len += info->control.hw_key->iv_len; mh_len /= 2; offload_assist |= mh_len << TX_CMD_OFFLD_MH_SIZE; @@ -1815,6 +1821,8 @@ void iwl_mvm_rx_ba_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) struct iwl_mvm_tid_data *tid_data; struct iwl_mvm_sta *mvmsta; + ba_info.flags = IEEE80211_TX_STAT_AMPDU; + if (iwl_mvm_has_new_tx_api(mvm)) { struct iwl_mvm_compressed_ba_notif *ba_res = (void *)pkt->data; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index f16c1bb9bf94..84f4ba01e14f 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -510,9 +510,17 @@ static const struct pci_device_id iwl_hw_card_ids[] = { /* 9000 Series */ {IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)}, + {IWL_PCI_DEVICE(0x271B, 0x0210, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0000, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0010, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0014, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x4010, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0210, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0214, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x1410, iwl9270_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x1610, iwl9270_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x0A10, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x0010, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x0210, iwl9460_2ac_cfg)}, @@ -527,10 +535,22 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x9DF0, 0x2A10, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0060, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0260, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0064, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x00A4, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x02A4, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x00A0, iwl9460_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x02A0, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x0060, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0xA370, 0x0060, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x31DC, 0x0060, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0030, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x4030, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0230, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0234, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0238, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x023C, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0x9DF0, 0x0030, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0xA370, 0x0030, iwl9560_2ac_cfg)}, {IWL_PCI_DEVICE(0x31DC, 0x0030, iwl9560_2ac_cfg)}, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index fa315d84e98e..a1ea9ef97ed9 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -787,6 +787,8 @@ int iwl_pci_fw_enter_d0i3(struct iwl_trans *trans); void iwl_pcie_enable_rx_wake(struct iwl_trans *trans, bool enable); +void iwl_pcie_rx_allocator_work(struct work_struct *data); + /* common functions that are used by gen2 transport */ void iwl_pcie_apm_config(struct iwl_trans *trans); int iwl_pcie_prepare_card_hw(struct iwl_trans *trans); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 351c4423125a..942736d3fa75 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -597,7 +597,7 @@ static void iwl_pcie_rx_allocator_get(struct iwl_trans *trans, rxq->free_count += RX_CLAIM_REQ_ALLOC; } -static void iwl_pcie_rx_allocator_work(struct work_struct *data) +void iwl_pcie_rx_allocator_work(struct work_struct *data) { struct iwl_rb_allocator *rba_p = container_of(data, struct iwl_rb_allocator, rx_alloc); @@ -900,10 +900,6 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans) return err; } def_rxq = trans_pcie->rxq; - if (!rba->alloc_wq) - rba->alloc_wq = alloc_workqueue("rb_allocator", - WQ_HIGHPRI | WQ_UNBOUND, 1); - INIT_WORK(&rba->rx_alloc, iwl_pcie_rx_allocator_work); spin_lock(&rba->lock); atomic_set(&rba->req_pending, 0); @@ -1017,10 +1013,6 @@ void iwl_pcie_rx_free(struct iwl_trans *trans) } cancel_work_sync(&rba->rx_alloc); - if (rba->alloc_wq) { - destroy_workqueue(rba->alloc_wq); - rba->alloc_wq = NULL; - } iwl_pcie_free_rbs_pool(trans); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index f95eec52508e..3927bbf04f72 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1786,6 +1786,11 @@ void iwl_trans_pcie_free(struct iwl_trans *trans) iwl_pcie_tx_free(trans); iwl_pcie_rx_free(trans); + if (trans_pcie->rba.alloc_wq) { + destroy_workqueue(trans_pcie->rba.alloc_wq); + trans_pcie->rba.alloc_wq = NULL; + } + if (trans_pcie->msix_enabled) { for (i = 0; i < trans_pcie->alloc_vecs; i++) { irq_set_affinity_hint( @@ -3169,6 +3174,10 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, trans_pcie->inta_mask = CSR_INI_SET_MASK; } + trans_pcie->rba.alloc_wq = alloc_workqueue("rb_allocator", + WQ_HIGHPRI | WQ_UNBOUND, 1); + INIT_WORK(&trans_pcie->rba.rx_alloc, iwl_pcie_rx_allocator_work); + #ifdef CONFIG_IWLWIFI_PCIE_RTPM trans->runtime_pm_mode = IWL_PLAT_PM_MODE_D0I3; #else diff --git a/drivers/net/wireless/ti/wl1251/main.c b/drivers/net/wireless/ti/wl1251/main.c index 08f0477f78d9..9915d83a4a30 100644 --- a/drivers/net/wireless/ti/wl1251/main.c +++ b/drivers/net/wireless/ti/wl1251/main.c @@ -1571,6 +1571,7 @@ struct ieee80211_hw *wl1251_alloc_hw(void) wl->state = WL1251_STATE_OFF; mutex_init(&wl->mutex); + spin_lock_init(&wl->wl_lock); wl->tx_mgmt_frm_rate = DEFAULT_HW_GEN_TX_RATE; wl->tx_mgmt_frm_mod = DEFAULT_HW_GEN_MODULATION_TYPE; diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c index 9a03c5871efe..f58d8e305323 100644 --- a/drivers/ntb/ntb_transport.c +++ b/drivers/ntb/ntb_transport.c @@ -924,10 +924,8 @@ out1: ntb_free_mw(nt, i); /* if there's an actual failure, we should just bail */ - if (rc < 0) { - ntb_link_disable(ndev); + if (rc < 0) return; - } out: if (ntb_link_is_up(ndev, NULL, NULL) == 1) @@ -1059,7 +1057,7 @@ static int ntb_transport_probe(struct ntb_client *self, struct ntb_dev *ndev) int node; int rc, i; - mw_count = ntb_mw_count(ndev, PIDX); + mw_count = ntb_peer_mw_count(ndev); if (!ndev->ops->mw_set_trans) { dev_err(&ndev->dev, "Inbound MW based NTB API is required\n"); diff --git a/drivers/ntb/test/ntb_tool.c b/drivers/ntb/test/ntb_tool.c index f002bf48a08d..a69815c45ce6 100644 --- a/drivers/ntb/test/ntb_tool.c +++ b/drivers/ntb/test/ntb_tool.c @@ -959,7 +959,7 @@ static int tool_probe(struct ntb_client *self, struct ntb_dev *ntb) tc->ntb = ntb; init_waitqueue_head(&tc->link_wq); - tc->mw_count = min(ntb_mw_count(tc->ntb, PIDX), MAX_MWS); + tc->mw_count = min(ntb_peer_mw_count(tc->ntb), MAX_MWS); for (i = 0; i < tc->mw_count; i++) { rc = tool_init_mw(tc, i); if (rc) diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 2e582a240943..5f5cd306f76d 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -794,7 +794,8 @@ static int nvmf_check_allowed_opts(struct nvmf_ctrl_options *opts, int i; for (i = 0; i < ARRAY_SIZE(opt_tokens); i++) { - if (opt_tokens[i].token & ~allowed_opts) { + if ((opt_tokens[i].token & opts->mask) && + (opt_tokens[i].token & ~allowed_opts)) { pr_warn("invalid parameter '%s'\n", opt_tokens[i].pattern); } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 74a124a06264..ea892e732268 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -109,6 +109,7 @@ struct nvme_dev { /* host memory buffer support: */ u64 host_mem_size; u32 nr_host_mem_descs; + dma_addr_t host_mem_descs_dma; struct nvme_host_mem_buf_desc *host_mem_descs; void **host_mem_desc_bufs; }; @@ -801,6 +802,7 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, return; } + nvmeq->cqe_seen = 1; req = blk_mq_tag_to_rq(*nvmeq->tags, cqe->command_id); nvme_end_request(req, cqe->status, cqe->result); } @@ -830,10 +832,8 @@ static void nvme_process_cq(struct nvme_queue *nvmeq) consumed++; } - if (consumed) { + if (consumed) nvme_ring_cq_doorbell(nvmeq); - nvmeq->cqe_seen = 1; - } } static irqreturn_t nvme_irq(int irq, void *data) @@ -1566,16 +1566,10 @@ static inline void nvme_release_cmb(struct nvme_dev *dev) static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits) { - size_t len = dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs); + u64 dma_addr = dev->host_mem_descs_dma; struct nvme_command c; - u64 dma_addr; int ret; - dma_addr = dma_map_single(dev->dev, dev->host_mem_descs, len, - DMA_TO_DEVICE); - if (dma_mapping_error(dev->dev, dma_addr)) - return -ENOMEM; - memset(&c, 0, sizeof(c)); c.features.opcode = nvme_admin_set_features; c.features.fid = cpu_to_le32(NVME_FEAT_HOST_MEM_BUF); @@ -1592,7 +1586,6 @@ static int nvme_set_host_mem(struct nvme_dev *dev, u32 bits) "failed to set host mem (err %d, flags %#x).\n", ret, bits); } - dma_unmap_single(dev->dev, dma_addr, len, DMA_TO_DEVICE); return ret; } @@ -1610,7 +1603,9 @@ static void nvme_free_host_mem(struct nvme_dev *dev) kfree(dev->host_mem_desc_bufs); dev->host_mem_desc_bufs = NULL; - kfree(dev->host_mem_descs); + dma_free_coherent(dev->dev, + dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs), + dev->host_mem_descs, dev->host_mem_descs_dma); dev->host_mem_descs = NULL; } @@ -1618,6 +1613,7 @@ static int nvme_alloc_host_mem(struct nvme_dev *dev, u64 min, u64 preferred) { struct nvme_host_mem_buf_desc *descs; u32 chunk_size, max_entries, len; + dma_addr_t descs_dma; int i = 0; void **bufs; u64 size = 0, tmp; @@ -1628,7 +1624,8 @@ retry: tmp = (preferred + chunk_size - 1); do_div(tmp, chunk_size); max_entries = tmp; - descs = kcalloc(max_entries, sizeof(*descs), GFP_KERNEL); + descs = dma_zalloc_coherent(dev->dev, max_entries * sizeof(*descs), + &descs_dma, GFP_KERNEL); if (!descs) goto out; @@ -1662,6 +1659,7 @@ retry: dev->nr_host_mem_descs = i; dev->host_mem_size = size; dev->host_mem_descs = descs; + dev->host_mem_descs_dma = descs_dma; dev->host_mem_desc_bufs = bufs; return 0; @@ -1675,7 +1673,8 @@ out_free_bufs: kfree(bufs); out_free_descs: - kfree(descs); + dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs, + descs_dma); out: /* try a smaller chunk size if we failed early */ if (chunk_size >= PAGE_SIZE * 2 && (i == 0 || size < min)) { diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index da04df1af231..a03299d77922 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -920,7 +920,11 @@ static int nvme_rdma_map_sg_fr(struct nvme_rdma_queue *queue, struct nvme_keyed_sgl_desc *sg = &c->common.dptr.ksgl; int nr; - nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, PAGE_SIZE); + /* + * Align the MR to a 4K page size to match the ctrl page size and + * the block virtual boundary. + */ + nr = ib_map_mr_sg(req->mr, req->sg_table.sgl, count, NULL, SZ_4K); if (nr < count) { if (nr < 0) return nr; @@ -1583,7 +1587,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl) goto out_cleanup_queue; ctrl->ctrl.max_hw_sectors = - (ctrl->max_fr_pages - 1) << (PAGE_SHIFT - 9); + (ctrl->max_fr_pages - 1) << (ilog2(SZ_4K) - 9); error = nvme_init_identify(&ctrl->ctrl); if (error) diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 2d7a98ab53fb..a53bb6635b83 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -199,12 +199,6 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) copy_and_pad(id->mn, sizeof(id->mn), model, sizeof(model) - 1); copy_and_pad(id->fr, sizeof(id->fr), UTS_RELEASE, strlen(UTS_RELEASE)); - memset(id->mn, ' ', sizeof(id->mn)); - strncpy((char *)id->mn, "Linux", sizeof(id->mn)); - - memset(id->fr, ' ', sizeof(id->fr)); - strncpy((char *)id->fr, UTS_RELEASE, sizeof(id->fr)); - id->rab = 6; /* diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 1b7f2520a20d..309c84aa7595 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -394,7 +394,7 @@ nvmet_fc_free_ls_iodlist(struct nvmet_fc_tgtport *tgtport) static struct nvmet_fc_ls_iod * nvmet_fc_alloc_ls_iod(struct nvmet_fc_tgtport *tgtport) { - static struct nvmet_fc_ls_iod *iod; + struct nvmet_fc_ls_iod *iod; unsigned long flags; spin_lock_irqsave(&tgtport->lock, flags); @@ -471,7 +471,7 @@ nvmet_fc_destroy_fcp_iodlist(struct nvmet_fc_tgtport *tgtport, static struct nvmet_fc_fcp_iod * nvmet_fc_alloc_fcp_iod(struct nvmet_fc_tgt_queue *queue) { - static struct nvmet_fc_fcp_iod *fod; + struct nvmet_fc_fcp_iod *fod; lockdep_assert_held(&queue->qlock); @@ -704,7 +704,7 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue) { struct nvmet_fc_tgtport *tgtport = queue->assoc->tgtport; struct nvmet_fc_fcp_iod *fod = queue->fod; - struct nvmet_fc_defer_fcp_req *deferfcp; + struct nvmet_fc_defer_fcp_req *deferfcp, *tempptr; unsigned long flags; int i, writedataactive; bool disconnect; @@ -735,7 +735,8 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue) } /* Cleanup defer'ed IOs in queue */ - list_for_each_entry(deferfcp, &queue->avail_defer_list, req_list) { + list_for_each_entry_safe(deferfcp, tempptr, &queue->avail_defer_list, + req_list) { list_del(&deferfcp->req_list); kfree(deferfcp); } diff --git a/drivers/of/device.c b/drivers/of/device.c index 28c38c756f92..e0a28ea341fe 100644 --- a/drivers/of/device.c +++ b/drivers/of/device.c @@ -89,6 +89,7 @@ int of_dma_configure(struct device *dev, struct device_node *np) bool coherent; unsigned long offset; const struct iommu_ops *iommu; + u64 mask; /* * Set default coherent_dma_mask to 32 bit. Drivers are expected to @@ -134,10 +135,9 @@ int of_dma_configure(struct device *dev, struct device_node *np) * Limit coherent and dma mask based on size and default mask * set by the driver. */ - dev->coherent_dma_mask = min(dev->coherent_dma_mask, - DMA_BIT_MASK(ilog2(dma_addr + size))); - *dev->dma_mask = min((*dev->dma_mask), - DMA_BIT_MASK(ilog2(dma_addr + size))); + mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1); + dev->coherent_dma_mask &= mask; + *dev->dma_mask &= mask; coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c index 5c63b920b471..ed92c1254cff 100644 --- a/drivers/parisc/dino.c +++ b/drivers/parisc/dino.c @@ -956,7 +956,7 @@ static int __init dino_probe(struct parisc_device *dev) dino_dev->hba.dev = dev; dino_dev->hba.base_addr = ioremap_nocache(hpa, 4096); - dino_dev->hba.lmmio_space_offset = 0; /* CPU addrs == bus addrs */ + dino_dev->hba.lmmio_space_offset = PCI_F_EXTEND; spin_lock_init(&dino_dev->dinosaur_pen); dino_dev->hba.iommu = ccio_get_iommu(dev); diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 253d92409bb3..2225afc1cbbb 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -538,12 +538,9 @@ msi_setup_entry(struct pci_dev *dev, int nvec, const struct irq_affinity *affd) struct msi_desc *entry; u16 control; - if (affd) { + if (affd) masks = irq_create_affinity_masks(nvec, affd); - if (!masks) - dev_err(&dev->dev, "can't allocate MSI affinity masks for %d vectors\n", - nvec); - } + /* MSI Entry Initialization */ entry = alloc_msi_entry(&dev->dev, nvec, masks); @@ -679,12 +676,8 @@ static int msix_setup_entries(struct pci_dev *dev, void __iomem *base, struct msi_desc *entry; int ret, i; - if (affd) { + if (affd) masks = irq_create_affinity_masks(nvec, affd); - if (!masks) - dev_err(&dev->dev, "can't allocate MSI-X affinity masks for %d vectors\n", - nvec); - } for (i = 0, curmsk = masks; i < nvec; i++) { entry = alloc_msi_entry(&dev->dev, 1, curmsk); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index b4b7eab29400..fdf65a6c13f6 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -514,7 +514,7 @@ EXPORT_SYMBOL(pci_find_resource); */ struct pci_dev *pci_find_pcie_root_port(struct pci_dev *dev) { - struct pci_dev *bridge, *highest_pcie_bridge = NULL; + struct pci_dev *bridge, *highest_pcie_bridge = dev; bridge = pci_upstream_bridge(dev); while (bridge && pci_is_pcie(bridge)) { diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index c31310db0404..e6a917b4acd3 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1762,6 +1762,48 @@ static void pci_configure_extended_tags(struct pci_dev *dev) PCI_EXP_DEVCTL_EXT_TAG); } +/** + * pcie_relaxed_ordering_enabled - Probe for PCIe relaxed ordering enable + * @dev: PCI device to query + * + * Returns true if the device has enabled relaxed ordering attribute. + */ +bool pcie_relaxed_ordering_enabled(struct pci_dev *dev) +{ + u16 v; + + pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &v); + + return !!(v & PCI_EXP_DEVCTL_RELAX_EN); +} +EXPORT_SYMBOL(pcie_relaxed_ordering_enabled); + +static void pci_configure_relaxed_ordering(struct pci_dev *dev) +{ + struct pci_dev *root; + + /* PCI_EXP_DEVICE_RELAX_EN is RsvdP in VFs */ + if (dev->is_virtfn) + return; + + if (!pcie_relaxed_ordering_enabled(dev)) + return; + + /* + * For now, we only deal with Relaxed Ordering issues with Root + * Ports. Peer-to-Peer DMA is another can of worms. + */ + root = pci_find_pcie_root_port(dev); + if (!root) + return; + + if (root->dev_flags & PCI_DEV_FLAGS_NO_RELAXED_ORDERING) { + pcie_capability_clear_word(dev, PCI_EXP_DEVCTL, + PCI_EXP_DEVCTL_RELAX_EN); + dev_info(&dev->dev, "Disable Relaxed Ordering because the Root Port didn't support it\n"); + } +} + static void pci_configure_device(struct pci_dev *dev) { struct hotplug_params hpp; @@ -1769,6 +1811,7 @@ static void pci_configure_device(struct pci_dev *dev) pci_configure_mps(dev); pci_configure_extended_tags(dev); + pci_configure_relaxed_ordering(dev); memset(&hpp, 0, sizeof(hpp)); ret = pci_get_hp_params(dev, &hpp); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 6967c6b4cf6b..140760403f36 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4016,6 +4016,95 @@ DECLARE_PCI_FIXUP_CLASS_EARLY(0x1797, 0x6869, PCI_CLASS_NOT_DEFINED, 8, quirk_tw686x_class); /* + * Some devices have problems with Transaction Layer Packets with the Relaxed + * Ordering Attribute set. Such devices should mark themselves and other + * Device Drivers should check before sending TLPs with RO set. + */ +static void quirk_relaxedordering_disable(struct pci_dev *dev) +{ + dev->dev_flags |= PCI_DEV_FLAGS_NO_RELAXED_ORDERING; + dev_info(&dev->dev, "Disable Relaxed Ordering Attributes to avoid PCIe Completion erratum\n"); +} + +/* + * Intel Xeon processors based on Broadwell/Haswell microarchitecture Root + * Complex has a Flow Control Credit issue which can cause performance + * problems with Upstream Transaction Layer Packets with Relaxed Ordering set. + */ +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f01, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f02, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f03, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f04, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f05, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f06, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f07, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f08, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f09, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0a, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0b, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0c, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0d, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x6f0e, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f01, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f02, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f03, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f04, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f05, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f06, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f07, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f08, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f09, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0a, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0b, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0c, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0d, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, 0x2f0e, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); + +/* + * The AMD ARM A1100 (AKA "SEATTLE") SoC has a bug in its PCIe Root Complex + * where Upstream Transaction Layer Packets with the Relaxed Ordering + * Attribute clear are allowed to bypass earlier TLPs with Relaxed Ordering + * set. This is a violation of the PCIe 3.0 Transaction Ordering Rules + * outlined in Section 2.4.1 (PCI Express(r) Base Specification Revision 3.0 + * November 10, 2010). As a result, on this platform we can't use Relaxed + * Ordering for Upstream TLPs. + */ +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_AMD, 0x1a00, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_AMD, 0x1a01, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); +DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_AMD, 0x1a02, PCI_CLASS_NOT_DEFINED, 8, + quirk_relaxedordering_disable); + +/* * Per PCIe r3.0, sec 2.2.9, "Completion headers must supply the same * values for the Attribute as were supplied in the header of the * corresponding Request, except as explicitly allowed when IDO is used." diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c index 4fac49e55d47..4b43aa62fbc7 100644 --- a/drivers/rtc/rtc-ds1307.c +++ b/drivers/rtc/rtc-ds1307.c @@ -1301,7 +1301,6 @@ static void ds1307_clks_register(struct ds1307 *ds1307) static const struct regmap_config regmap_config = { .reg_bits = 8, .val_bits = 8, - .max_register = 0x12, }; static int ds1307_probe(struct i2c_client *client, diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c index ba6ac83a6c25..5ccfdc80d0ec 100644 --- a/drivers/s390/cio/vfio_ccw_cp.c +++ b/drivers/s390/cio/vfio_ccw_cp.c @@ -481,7 +481,7 @@ static int ccwchain_fetch_tic(struct ccwchain *chain, ccw_tail = ccw_head + (iter->ch_len - 1) * sizeof(struct ccw1); if ((ccw_head <= ccw->cda) && (ccw->cda <= ccw_tail)) { - ccw->cda = (__u32) (addr_t) (iter->ch_ccw + + ccw->cda = (__u32) (addr_t) (((char *)iter->ch_ccw) + (ccw->cda - ccw_head)); return 0; } diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index f4538d7a3016..d145e0d90227 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -47,6 +47,17 @@ config SCSI_NETLINK default n depends on NET +config SCSI_MQ_DEFAULT + bool "SCSI: use blk-mq I/O path by default" + depends on SCSI + ---help--- + This option enables the new blk-mq based I/O path for SCSI + devices by default. With the option the scsi_mod.use_blk_mq + module/boot option defaults to Y, without it to N, but it can + still be overridden either way. + + If unsure say N. + config SCSI_PROC_FS bool "legacy /proc/scsi/ support" depends on SCSI && PROC_FS diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c index 4591113c49de..a1a2c71e1626 100644 --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@ -549,7 +549,9 @@ static void get_container_name_callback(void *context, struct fib * fibptr) if ((le32_to_cpu(get_name_reply->status) == CT_OK) && (get_name_reply->data[0] != '\0')) { char *sp = get_name_reply->data; - sp[sizeof(((struct aac_get_name_resp *)NULL)->data)] = '\0'; + int data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + + sp[data_size - 1] = '\0'; while (*sp == ' ') ++sp; if (*sp) { @@ -579,12 +581,15 @@ static void get_container_name_callback(void *context, struct fib * fibptr) static int aac_get_container_name(struct scsi_cmnd * scsicmd) { int status; + int data_size; struct aac_get_name *dinfo; struct fib * cmd_fibcontext; struct aac_dev * dev; dev = (struct aac_dev *)scsicmd->device->host->hostdata; + data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd); aac_fib_init(cmd_fibcontext); @@ -593,7 +598,7 @@ static int aac_get_container_name(struct scsi_cmnd * scsicmd) dinfo->command = cpu_to_le32(VM_ContainerConfig); dinfo->type = cpu_to_le32(CT_READ_NAME); dinfo->cid = cpu_to_le32(scmd_id(scsicmd)); - dinfo->count = cpu_to_le32(sizeof(((struct aac_get_name_resp *)NULL)->data)); + dinfo->count = cpu_to_le32(data_size - 1); status = aac_fib_send(ContainerCommand, cmd_fibcontext, diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index d31a9bc2ba69..ee2667e20e42 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2274,7 +2274,7 @@ struct aac_get_name_resp { __le32 parm3; __le32 parm4; __le32 parm5; - u8 data[16]; + u8 data[17]; }; #define CT_CID_TO_32BITS_UID 165 diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index 2029ad225121..5be0086142ca 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -3845,8 +3845,10 @@ csio_hw_start(struct csio_hw *hw) if (csio_is_hw_ready(hw)) return 0; - else + else if (csio_match_state(hw, csio_hws_uninit)) return -EINVAL; + else + return -ENODEV; } int diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c index ea0c31086cc6..dcd074169aa9 100644 --- a/drivers/scsi/csiostor/csio_init.c +++ b/drivers/scsi/csiostor/csio_init.c @@ -969,10 +969,14 @@ static int csio_probe_one(struct pci_dev *pdev, const struct pci_device_id *id) pci_set_drvdata(pdev, hw); - if (csio_hw_start(hw) != 0) { - dev_err(&pdev->dev, - "Failed to start FW, continuing in debug mode.\n"); - return 0; + rv = csio_hw_start(hw); + if (rv) { + if (rv == -EINVAL) { + dev_err(&pdev->dev, + "Failed to start FW, continuing in debug mode.\n"); + return 0; + } + goto err_lnode_exit; } sprintf(hw->fwrev_str, "%u.%u.%u.%u\n", diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c index a69a9ac836f5..1d02cf9fe06c 100644 --- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c @@ -1635,6 +1635,9 @@ static int init_act_open(struct cxgbi_sock *csk) goto rel_resource; } + if (!(n->nud_state & NUD_VALID)) + neigh_event_send(n, NULL); + csk->atid = cxgb4_alloc_atid(lldi->tids, csk); if (csk->atid < 0) { pr_err("%s, NO atid available.\n", ndev->name); diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index b0c68d24db01..f838bd73befa 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -3351,6 +3351,16 @@ static void ipr_worker_thread(struct work_struct *work) return; } + if (ioa_cfg->scsi_unblock) { + ioa_cfg->scsi_unblock = 0; + ioa_cfg->scsi_blocked = 0; + spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); + scsi_unblock_requests(ioa_cfg->host); + spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags); + if (ioa_cfg->scsi_blocked) + scsi_block_requests(ioa_cfg->host); + } + if (!ioa_cfg->scan_enabled) { spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags); return; @@ -4935,6 +4945,7 @@ static int ipr_slave_configure(struct scsi_device *sdev) } if (ipr_is_vset_device(res)) { sdev->scsi_level = SCSI_SPC_3; + sdev->no_report_opcodes = 1; blk_queue_rq_timeout(sdev->request_queue, IPR_VSET_RW_TIMEOUT); blk_queue_max_hw_sectors(sdev->request_queue, IPR_VSET_MAX_SECTORS); @@ -7211,9 +7222,8 @@ static int ipr_ioa_bringdown_done(struct ipr_cmnd *ipr_cmd) ENTER; if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].removing_ioa) { ipr_trace; - spin_unlock_irq(ioa_cfg->host->host_lock); - scsi_unblock_requests(ioa_cfg->host); - spin_lock_irq(ioa_cfg->host->host_lock); + ioa_cfg->scsi_unblock = 1; + schedule_work(&ioa_cfg->work_q); } ioa_cfg->in_reset_reload = 0; @@ -7287,13 +7297,7 @@ static int ipr_ioa_reset_done(struct ipr_cmnd *ipr_cmd) list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q); wake_up_all(&ioa_cfg->reset_wait_q); - spin_unlock(ioa_cfg->host->host_lock); - scsi_unblock_requests(ioa_cfg->host); - spin_lock(ioa_cfg->host->host_lock); - - if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].allow_cmds) - scsi_block_requests(ioa_cfg->host); - + ioa_cfg->scsi_unblock = 1; schedule_work(&ioa_cfg->work_q); LEAVE; return IPR_RC_JOB_RETURN; @@ -9249,8 +9253,11 @@ static void _ipr_initiate_ioa_reset(struct ipr_ioa_cfg *ioa_cfg, spin_unlock(&ioa_cfg->hrrq[i]._lock); } wmb(); - if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].removing_ioa) + if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].removing_ioa) { + ioa_cfg->scsi_unblock = 0; + ioa_cfg->scsi_blocked = 1; scsi_block_requests(ioa_cfg->host); + } ipr_cmd = ipr_get_free_ipr_cmnd(ioa_cfg); ioa_cfg->reset_cmd = ipr_cmd; @@ -9306,9 +9313,8 @@ static void ipr_initiate_ioa_reset(struct ipr_ioa_cfg *ioa_cfg, wake_up_all(&ioa_cfg->reset_wait_q); if (!ioa_cfg->hrrq[IPR_INIT_HRRQ].removing_ioa) { - spin_unlock_irq(ioa_cfg->host->host_lock); - scsi_unblock_requests(ioa_cfg->host); - spin_lock_irq(ioa_cfg->host->host_lock); + ioa_cfg->scsi_unblock = 1; + schedule_work(&ioa_cfg->work_q); } return; } else { diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h index e98a87a65335..c7f0e9e3cd7d 100644 --- a/drivers/scsi/ipr.h +++ b/drivers/scsi/ipr.h @@ -1488,6 +1488,8 @@ struct ipr_ioa_cfg { u8 cfg_locked:1; u8 clear_isr:1; u8 probe_done:1; + u8 scsi_unblock:1; + u8 scsi_blocked:1; u8 revid; diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 316c3df0c3fd..71c4746341ea 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -6228,8 +6228,8 @@ static int megasas_probe_one(struct pci_dev *pdev, fail_start_aen: fail_io_attach: megasas_mgmt_info.count--; - megasas_mgmt_info.instance[megasas_mgmt_info.max_index] = NULL; megasas_mgmt_info.max_index--; + megasas_mgmt_info.instance[megasas_mgmt_info.max_index] = NULL; instance->instancet->disable_intr(instance); megasas_destroy_irqs(instance); diff --git a/drivers/scsi/qedf/qedf_els.c b/drivers/scsi/qedf/qedf_els.c index eb07f1de8afa..59c18ca4cda9 100644 --- a/drivers/scsi/qedf/qedf_els.c +++ b/drivers/scsi/qedf/qedf_els.c @@ -489,7 +489,7 @@ static void qedf_srr_compl(struct qedf_els_cb_arg *cb_arg) /* If a SRR times out, simply free resources */ if (srr_req->event == QEDF_IOREQ_EV_ELS_TMO) - goto out_free; + goto out_put; /* Normalize response data into struct fc_frame */ mp_req = &(srr_req->mp_req); @@ -501,7 +501,7 @@ static void qedf_srr_compl(struct qedf_els_cb_arg *cb_arg) if (!fp) { QEDF_ERR(&(qedf->dbg_ctx), "fc_frame_alloc failure.\n"); - goto out_free; + goto out_put; } /* Copy frame header from firmware into fp */ @@ -526,9 +526,10 @@ static void qedf_srr_compl(struct qedf_els_cb_arg *cb_arg) } fc_frame_free(fp); -out_free: +out_put: /* Put reference for original command since SRR completed */ kref_put(&orig_io_req->refcount, qedf_release_cmd); +out_free: kfree(cb_arg); } @@ -780,7 +781,7 @@ static void qedf_rec_compl(struct qedf_els_cb_arg *cb_arg) /* If a REC times out, free resources */ if (rec_req->event == QEDF_IOREQ_EV_ELS_TMO) - goto out_free; + goto out_put; /* Normalize response data into struct fc_frame */ mp_req = &(rec_req->mp_req); @@ -792,7 +793,7 @@ static void qedf_rec_compl(struct qedf_els_cb_arg *cb_arg) if (!fp) { QEDF_ERR(&(qedf->dbg_ctx), "fc_frame_alloc failure.\n"); - goto out_free; + goto out_put; } /* Copy frame header from firmware into fp */ @@ -884,9 +885,10 @@ static void qedf_rec_compl(struct qedf_els_cb_arg *cb_arg) out_free_frame: fc_frame_free(fp); -out_free: +out_put: /* Put reference for original command since REC completed */ kref_put(&orig_io_req->refcount, qedf_release_cmd); +out_free: kfree(cb_arg); } diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c index 33142610882f..b18646d6057f 100644 --- a/drivers/scsi/qla2xxx/qla_tmpl.c +++ b/drivers/scsi/qla2xxx/qla_tmpl.c @@ -401,9 +401,6 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha, for (i = 0; i < vha->hw->max_req_queues; i++) { struct req_que *req = vha->hw->req_q_map[i]; - if (!test_bit(i, vha->hw->req_qid_map)) - continue; - if (req || !buf) { length = req ? req->length : REQUEST_ENTRY_CNT_24XX; @@ -418,9 +415,6 @@ qla27xx_fwdt_entry_t263(struct scsi_qla_host *vha, for (i = 0; i < vha->hw->max_rsp_queues; i++) { struct rsp_que *rsp = vha->hw->rsp_q_map[i]; - if (!test_bit(i, vha->hw->rsp_qid_map)) - continue; - if (rsp || !buf) { length = rsp ? rsp->length : RESPONSE_ENTRY_CNT_MQ; @@ -660,9 +654,6 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha, for (i = 0; i < vha->hw->max_req_queues; i++) { struct req_que *req = vha->hw->req_q_map[i]; - if (!test_bit(i, vha->hw->req_qid_map)) - continue; - if (req || !buf) { qla27xx_insert16(i, buf, len); qla27xx_insert16(1, buf, len); @@ -675,9 +666,6 @@ qla27xx_fwdt_entry_t274(struct scsi_qla_host *vha, for (i = 0; i < vha->hw->max_rsp_queues; i++) { struct rsp_que *rsp = vha->hw->rsp_q_map[i]; - if (!test_bit(i, vha->hw->rsp_qid_map)) - continue; - if (rsp || !buf) { qla27xx_insert16(i, buf, len); qla27xx_insert16(1, buf, len); diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 3d38c6d463b8..1bf274e3b2b6 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -800,7 +800,11 @@ MODULE_LICENSE("GPL"); module_param(scsi_logging_level, int, S_IRUGO|S_IWUSR); MODULE_PARM_DESC(scsi_logging_level, "a bit mask of logging levels"); +#ifdef CONFIG_SCSI_MQ_DEFAULT bool scsi_use_blk_mq = true; +#else +bool scsi_use_blk_mq = false; +#endif module_param_named(use_blk_mq, scsi_use_blk_mq, bool, S_IWUSR | S_IRUGO); static int __init init_scsi(void) diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index bea36adeee17..e2647f2d4430 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1277,6 +1277,9 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt) { struct request *rq = SCpnt->request; + if (SCpnt->flags & SCMD_ZONE_WRITE_LOCK) + sd_zbc_write_unlock_zone(SCpnt); + if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) __free_page(rq->special_vec.bv_page); diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 96855df9f49d..8aa54779aac1 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -294,6 +294,9 @@ int sd_zbc_write_lock_zone(struct scsi_cmnd *cmd) test_and_set_bit(zno, sdkp->zones_wlock)) return BLKPREP_DEFER; + WARN_ON_ONCE(cmd->flags & SCMD_ZONE_WRITE_LOCK); + cmd->flags |= SCMD_ZONE_WRITE_LOCK; + return BLKPREP_OK; } @@ -302,9 +305,10 @@ void sd_zbc_write_unlock_zone(struct scsi_cmnd *cmd) struct request *rq = cmd->request; struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); - if (sdkp->zones_wlock) { + if (sdkp->zones_wlock && cmd->flags & SCMD_ZONE_WRITE_LOCK) { unsigned int zno = sd_zbc_zone_no(sdkp, blk_rq_pos(rq)); WARN_ON_ONCE(!test_bit(zno, sdkp->zones_wlock)); + cmd->flags &= ~SCMD_ZONE_WRITE_LOCK; clear_bit_unlock(zno, sdkp->zones_wlock); smp_mb__after_atomic(); } @@ -335,9 +339,6 @@ void sd_zbc_complete(struct scsi_cmnd *cmd, case REQ_OP_WRITE_ZEROES: case REQ_OP_WRITE_SAME: - /* Unlock the zone */ - sd_zbc_write_unlock_zone(cmd); - if (result && sshdr->sense_key == ILLEGAL_REQUEST && sshdr->asc == 0x21) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index f1cdf32d7514..8927f9f54ad9 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -99,7 +99,7 @@ static int ses_recv_diag(struct scsi_device *sdev, int page_code, ret = scsi_execute_req(sdev, cmd, DMA_FROM_DEVICE, buf, bufflen, NULL, SES_TIMEOUT, SES_RETRIES, NULL); - if (unlikely(!ret)) + if (unlikely(ret)) return ret; recv_page_code = ((unsigned char *)buf)[0]; diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index d7ff71e0c85c..84e782d8e7c3 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1021,7 +1021,7 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) read_lock_irqsave(&sfp->rq_list_lock, iflags); val = 0; list_for_each_entry(srp, &sfp->rq_list, entry) { - if (val > SG_MAX_QUEUE) + if (val >= SG_MAX_QUEUE) break; memset(&rinfo[val], 0, SZ_SG_REQ_INFO); rinfo[val].req_state = srp->done + 1; diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 8e5013d9cad4..94e402ed30f6 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -4299,11 +4299,11 @@ static int st_probe(struct device *dev) kref_init(&tpnt->kref); tpnt->disk = disk; disk->private_data = &tpnt->driver; - disk->queue = SDp->request_queue; /* SCSI tape doesn't register this gendisk via add_disk(). Manually * take queue reference that release_disk() expects. */ - if (!blk_get_queue(disk->queue)) + if (!blk_get_queue(SDp->request_queue)) goto out_put_disk; + disk->queue = SDp->request_queue; tpnt->driver = &st_template; tpnt->device = SDp; diff --git a/drivers/soc/imx/gpcv2.c b/drivers/soc/imx/gpcv2.c index 3039072911a5..afc7ecc3c187 100644 --- a/drivers/soc/imx/gpcv2.c +++ b/drivers/soc/imx/gpcv2.c @@ -200,16 +200,11 @@ static int imx7_pgc_domain_probe(struct platform_device *pdev) domain->dev = &pdev->dev; - ret = pm_genpd_init(&domain->genpd, NULL, true); - if (ret) { - dev_err(domain->dev, "Failed to init power domain\n"); - return ret; - } - domain->regulator = devm_regulator_get_optional(domain->dev, "power"); if (IS_ERR(domain->regulator)) { if (PTR_ERR(domain->regulator) != -ENODEV) { - dev_err(domain->dev, "Failed to get domain's regulator\n"); + if (PTR_ERR(domain->regulator) != -EPROBE_DEFER) + dev_err(domain->dev, "Failed to get domain's regulator\n"); return PTR_ERR(domain->regulator); } } else { @@ -217,6 +212,12 @@ static int imx7_pgc_domain_probe(struct platform_device *pdev) domain->voltage, domain->voltage); } + ret = pm_genpd_init(&domain->genpd, NULL, true); + if (ret) { + dev_err(domain->dev, "Failed to init power domain\n"); + return ret; + } + ret = of_genpd_add_provider_simple(domain->dev->of_node, &domain->genpd); if (ret) { diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c index 279e7c5551dd..39225de9d7f1 100644 --- a/drivers/soc/ti/knav_qmss_queue.c +++ b/drivers/soc/ti/knav_qmss_queue.c @@ -745,6 +745,9 @@ void *knav_pool_create(const char *name, bool slot_found; int ret; + if (!kdev) + return ERR_PTR(-EPROBE_DEFER); + if (!kdev->dev) return ERR_PTR(-ENODEV); diff --git a/drivers/soc/ti/ti_sci_pm_domains.c b/drivers/soc/ti/ti_sci_pm_domains.c index b0b283810e72..de31b9389e2e 100644 --- a/drivers/soc/ti/ti_sci_pm_domains.c +++ b/drivers/soc/ti/ti_sci_pm_domains.c @@ -176,6 +176,8 @@ static int ti_sci_pm_domain_probe(struct platform_device *pdev) ti_sci_pd->dev = dev; + ti_sci_pd->pd.name = "ti_sci_pd"; + ti_sci_pd->pd.attach_dev = ti_sci_pd_attach_dev; ti_sci_pd->pd.detach_dev = ti_sci_pd_detach_dev; diff --git a/drivers/staging/fsl-mc/bus/fsl-mc-allocator.c b/drivers/staging/fsl-mc/bus/fsl-mc-allocator.c index b37a6f48225f..8ea3920400a0 100644 --- a/drivers/staging/fsl-mc/bus/fsl-mc-allocator.c +++ b/drivers/staging/fsl-mc/bus/fsl-mc-allocator.c @@ -16,9 +16,9 @@ static bool __must_check fsl_mc_is_allocatable(const char *obj_type) { - return strcmp(obj_type, "dpbp") || - strcmp(obj_type, "dpmcp") || - strcmp(obj_type, "dpcon"); + return strcmp(obj_type, "dpbp") == 0 || + strcmp(obj_type, "dpmcp") == 0 || + strcmp(obj_type, "dpcon") == 0; } /** diff --git a/drivers/staging/rtl8188eu/os_dep/usb_intf.c b/drivers/staging/rtl8188eu/os_dep/usb_intf.c index d283341cfe43..56cd4e5e51b2 100644 --- a/drivers/staging/rtl8188eu/os_dep/usb_intf.c +++ b/drivers/staging/rtl8188eu/os_dep/usb_intf.c @@ -45,6 +45,7 @@ static struct usb_device_id rtw_usb_id_tbl[] = { {USB_DEVICE(0x2001, 0x3311)}, /* DLink GO-USB-N150 REV B1 */ {USB_DEVICE(0x2357, 0x010c)}, /* TP-Link TL-WN722N v2 */ {USB_DEVICE(0x0df6, 0x0076)}, /* Sitecom N150 v2 */ + {USB_DEVICE(USB_VENDER_ID_REALTEK, 0xffef)}, /* Rosewill RNX-N150NUB */ {} /* Terminating entry */ }; diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index 284749fb0f6b..a6d5164c33a9 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -69,13 +69,8 @@ static void pty_close(struct tty_struct *tty, struct file *filp) #ifdef CONFIG_UNIX98_PTYS if (tty->driver == ptm_driver) { mutex_lock(&devpts_mutex); - if (tty->link->driver_data) { - struct path *path = tty->link->driver_data; - - devpts_pty_kill(path->dentry); - path_put(path); - kfree(path); - } + if (tty->link->driver_data) + devpts_pty_kill(tty->link->driver_data); mutex_unlock(&devpts_mutex); } #endif @@ -607,25 +602,24 @@ static inline void legacy_pty_init(void) { } static struct cdev ptmx_cdev; /** - * pty_open_peer - open the peer of a pty - * @tty: the peer of the pty being opened + * ptm_open_peer - open the peer of a pty + * @master: the open struct file of the ptmx device node + * @tty: the master of the pty being opened + * @flags: the flags for open * - * Open the cached dentry in tty->link, providing a safe way for userspace - * to get the slave end of a pty (where they have the master fd and cannot - * access or trust the mount namespace /dev/pts was mounted inside). + * Provide a race free way for userspace to open the slave end of a pty + * (where they have the master fd and cannot access or trust the mount + * namespace /dev/pts was mounted inside). */ -static struct file *pty_open_peer(struct tty_struct *tty, int flags) -{ - if (tty->driver->subtype != PTY_TYPE_MASTER) - return ERR_PTR(-EIO); - return dentry_open(tty->link->driver_data, flags, current_cred()); -} - -static int pty_get_peer(struct tty_struct *tty, int flags) +int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags) { int fd = -1; - struct file *filp = NULL; + struct file *filp; int retval = -EINVAL; + struct path path; + + if (tty->driver != ptm_driver) + return -EIO; fd = get_unused_fd_flags(0); if (fd < 0) { @@ -633,7 +627,16 @@ static int pty_get_peer(struct tty_struct *tty, int flags) goto err; } - filp = pty_open_peer(tty, flags); + /* Compute the slave's path */ + path.mnt = devpts_mntget(master, tty->driver_data); + if (IS_ERR(path.mnt)) { + retval = PTR_ERR(path.mnt); + goto err_put; + } + path.dentry = tty->link->driver_data; + + filp = dentry_open(&path, flags, current_cred()); + mntput(path.mnt); if (IS_ERR(filp)) { retval = PTR_ERR(filp); goto err_put; @@ -662,8 +665,6 @@ static int pty_unix98_ioctl(struct tty_struct *tty, return pty_get_pktmode(tty, (int __user *)arg); case TIOCGPTN: /* Get PT Number */ return put_user(tty->index, (unsigned int __user *)arg); - case TIOCGPTPEER: /* Open the other end */ - return pty_get_peer(tty, (int) arg); case TIOCSIG: /* Send signal to other side of pty */ return pty_signal(tty, (int) arg); } @@ -791,7 +792,6 @@ static int ptmx_open(struct inode *inode, struct file *filp) { struct pts_fs_info *fsi; struct tty_struct *tty; - struct path *pts_path; struct dentry *dentry; int retval; int index; @@ -845,26 +845,16 @@ static int ptmx_open(struct inode *inode, struct file *filp) retval = PTR_ERR(dentry); goto err_release; } - /* We need to cache a fake path for TIOCGPTPEER. */ - pts_path = kmalloc(sizeof(struct path), GFP_KERNEL); - if (!pts_path) - goto err_release; - pts_path->mnt = filp->f_path.mnt; - pts_path->dentry = dentry; - path_get(pts_path); - tty->link->driver_data = pts_path; + tty->link->driver_data = dentry; retval = ptm_driver->ops->open(tty, filp); if (retval) - goto err_path_put; + goto err_release; tty_debug_hangup(tty, "opening (count=%d)\n", tty->count); tty_unlock(tty); return 0; -err_path_put: - path_put(pts_path); - kfree(pts_path); err_release: tty_unlock(tty); // This will also put-ref the fsi diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 974b13d24401..10c4038c0e8d 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -2518,6 +2518,9 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case TIOCSSERIAL: tty_warn_deprecated_flags(p); break; + case TIOCGPTPEER: + /* Special because the struct file is needed */ + return ptm_open_peer(file, tty, (int)arg); default: retval = tty_jobctrl_ioctl(tty, real_tty, file, cmd, arg); if (retval != -ENOIOCTLCMD) diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c index 007a4f366086..1c4797e53f68 100644 --- a/drivers/virtio/virtio_pci_common.c +++ b/drivers/virtio/virtio_pci_common.c @@ -107,6 +107,7 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, { struct virtio_pci_device *vp_dev = to_vp_device(vdev); const char *name = dev_name(&vp_dev->vdev.dev); + unsigned flags = PCI_IRQ_MSIX; unsigned i, v; int err = -ENOMEM; @@ -126,10 +127,13 @@ static int vp_request_msix_vectors(struct virtio_device *vdev, int nvectors, GFP_KERNEL)) goto error; + if (desc) { + flags |= PCI_IRQ_AFFINITY; + desc->pre_vectors++; /* virtio config vector */ + } + err = pci_alloc_irq_vectors_affinity(vp_dev->pci_dev, nvectors, - nvectors, PCI_IRQ_MSIX | - (desc ? PCI_IRQ_AFFINITY : 0), - desc); + nvectors, flags, desc); if (err < 0) goto error; vp_dev->msix_enabled = 1; diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile index 8feab810aed9..7f188b8d0c67 100644 --- a/drivers/xen/Makefile +++ b/drivers/xen/Makefile @@ -7,9 +7,6 @@ obj-y += xenbus/ nostackp := $(call cc-option, -fno-stack-protector) CFLAGS_features.o := $(nostackp) -CFLAGS_efi.o += -fshort-wchar -LDFLAGS += $(call ld-option, --no-wchar-size-warning) - dom0-$(CONFIG_ARM64) += arm-device.o dom0-$(CONFIG_PCI) += pci.o dom0-$(CONFIG_USB_SUPPORT) += dbgp.o diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c index 4da69dbf7dca..1bdd02a6d6ac 100644 --- a/drivers/xen/biomerge.c +++ b/drivers/xen/biomerge.c @@ -10,8 +10,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, unsigned long bfn1 = pfn_to_bfn(page_to_pfn(vec1->bv_page)); unsigned long bfn2 = pfn_to_bfn(page_to_pfn(vec2->bv_page)); - return __BIOVEC_PHYS_MERGEABLE(vec1, vec2) && - ((bfn1 == bfn2) || ((bfn1+1) == bfn2)); + return bfn1 + PFN_DOWN(vec1->bv_offset + vec1->bv_len) == bfn2; #else /* * XXX: Add support for merging bio_vec when using different page diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index f3bf8f4e2d6c..82360594fa8e 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -484,13 +484,6 @@ static void mn_invl_range_start(struct mmu_notifier *mn, mutex_unlock(&priv->lock); } -static void mn_invl_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - mn_invl_range_start(mn, mm, address, address + PAGE_SIZE); -} - static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm) { @@ -522,7 +515,6 @@ static void mn_release(struct mmu_notifier *mn, static const struct mmu_notifier_ops gntdev_mmu_ops = { .release = mn_release, - .invalidate_page = mn_invl_page, .invalidate_range_start = mn_invl_range_start, }; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 879ff9c7ffd0..6466153f2bf0 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -664,8 +664,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; - if ((current->flags & PF_RANDOMIZE) && - !(current->personality & ADDR_NO_RANDOMIZE)) { + if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 080e2ebb8aa0..f45b61fe9a9a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3516,7 +3516,7 @@ static blk_status_t wait_dev_flush(struct btrfs_device *device) struct bio *bio = device->flush_bio; if (!device->flush_bio_sent) - return 0; + return BLK_STS_OK; device->flush_bio_sent = 0; wait_for_completion_io(&device->flush_wait); @@ -3563,7 +3563,7 @@ static int barrier_all_devices(struct btrfs_fs_info *info) continue; write_dev_flush(dev); - dev->last_flush_error = 0; + dev->last_flush_error = BLK_STS_OK; } /* wait for all the barriers */ diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 95c212037095..24bcd5cd9cf2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7924,11 +7924,12 @@ err: return ret; } -static inline int submit_dio_repair_bio(struct inode *inode, struct bio *bio, - int mirror_num) +static inline blk_status_t submit_dio_repair_bio(struct inode *inode, + struct bio *bio, + int mirror_num) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); - int ret; + blk_status_t ret; BUG_ON(bio_op(bio) == REQ_OP_WRITE); @@ -7980,10 +7981,10 @@ static int btrfs_check_dio_repairable(struct inode *inode, return 1; } -static int dio_read_error(struct inode *inode, struct bio *failed_bio, - struct page *page, unsigned int pgoff, - u64 start, u64 end, int failed_mirror, - bio_end_io_t *repair_endio, void *repair_arg) +static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio, + struct page *page, unsigned int pgoff, + u64 start, u64 end, int failed_mirror, + bio_end_io_t *repair_endio, void *repair_arg) { struct io_failure_record *failrec; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; @@ -7993,18 +7994,19 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, int read_mode = 0; int segs; int ret; + blk_status_t status; BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE); ret = btrfs_get_io_failure_record(inode, start, end, &failrec); if (ret) - return ret; + return errno_to_blk_status(ret); ret = btrfs_check_dio_repairable(inode, failed_bio, failrec, failed_mirror); if (!ret) { free_io_failure(failure_tree, io_tree, failrec); - return -EIO; + return BLK_STS_IOERR; } segs = bio_segments(failed_bio); @@ -8022,13 +8024,13 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio, "Repair DIO Read Error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d\n", read_mode, failrec->this_mirror, failrec->in_validation); - ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror); - if (ret) { + status = submit_dio_repair_bio(inode, bio, failrec->this_mirror); + if (status) { free_io_failure(failure_tree, io_tree, failrec); bio_put(bio); } - return ret; + return status; } struct btrfs_retry_complete { @@ -8065,8 +8067,8 @@ end: bio_put(bio); } -static int __btrfs_correct_data_nocsum(struct inode *inode, - struct btrfs_io_bio *io_bio) +static blk_status_t __btrfs_correct_data_nocsum(struct inode *inode, + struct btrfs_io_bio *io_bio) { struct btrfs_fs_info *fs_info; struct bio_vec bvec; @@ -8076,8 +8078,8 @@ static int __btrfs_correct_data_nocsum(struct inode *inode, unsigned int pgoff; u32 sectorsize; int nr_sectors; - int ret; - int err = 0; + blk_status_t ret; + blk_status_t err = BLK_STS_OK; fs_info = BTRFS_I(inode)->root->fs_info; sectorsize = fs_info->sectorsize; @@ -8183,11 +8185,12 @@ static blk_status_t __btrfs_subio_endio_read(struct inode *inode, int csum_pos; bool uptodate = (err == 0); int ret; + blk_status_t status; fs_info = BTRFS_I(inode)->root->fs_info; sectorsize = fs_info->sectorsize; - err = 0; + err = BLK_STS_OK; start = io_bio->logical; done.inode = inode; io_bio->bio.bi_iter = io_bio->iter; @@ -8209,12 +8212,12 @@ try_again: done.start = start; init_completion(&done.done); - ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page, - pgoff, start, start + sectorsize - 1, - io_bio->mirror_num, - btrfs_retry_endio, &done); - if (ret) { - err = errno_to_blk_status(ret); + status = dio_read_error(inode, &io_bio->bio, bvec.bv_page, + pgoff, start, start + sectorsize - 1, + io_bio->mirror_num, btrfs_retry_endio, + &done); + if (status) { + err = status; goto next; } @@ -8250,7 +8253,7 @@ static blk_status_t btrfs_subio_endio_read(struct inode *inode, if (unlikely(err)) return __btrfs_correct_data_nocsum(inode, io_bio); else - return 0; + return BLK_STS_OK; } else { return __btrfs_subio_endio_read(inode, io_bio, err); } @@ -8423,9 +8426,9 @@ static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode, return 0; } -static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, - u64 file_offset, int skip_sum, - int async_submit) +static inline blk_status_t +__btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, u64 file_offset, + int skip_sum, int async_submit) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_dio_private *dip = bio->bi_private; @@ -8488,6 +8491,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip, int clone_offset = 0; int clone_len; int ret; + blk_status_t status; map_length = orig_bio->bi_iter.bi_size; submit_len = map_length; @@ -8537,9 +8541,9 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip, */ atomic_inc(&dip->pending_bios); - ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum, - async_submit); - if (ret) { + status = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum, + async_submit); + if (status) { bio_put(bio); atomic_dec(&dip->pending_bios); goto out_err; @@ -8557,9 +8561,9 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip, } while (submit_len > 0); submit: - ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum, - async_submit); - if (!ret) + status = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum, + async_submit); + if (!status) return 0; bio_put(bio); diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index 208638384cd2..2cf6ba40f7c4 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -905,7 +905,7 @@ static void raid_write_end_io(struct bio *bio) if (!atomic_dec_and_test(&rbio->stripes_pending)) return; - err = 0; + err = BLK_STS_OK; /* OK, we have read all the stripes we need to. */ max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ? @@ -1324,7 +1324,7 @@ write_data: return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } /* @@ -1475,7 +1475,7 @@ static void raid_rmw_end_io(struct bio *bio) cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } static void async_rmw_stripe(struct btrfs_raid_bio *rbio) @@ -1579,7 +1579,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio) return 0; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); return -EIO; finish: @@ -1795,12 +1795,12 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) void **pointers; int faila = -1, failb = -1; struct page *page; - int err; + blk_status_t err; int i; pointers = kcalloc(rbio->real_stripes, sizeof(void *), GFP_NOFS); if (!pointers) { - err = -ENOMEM; + err = BLK_STS_RESOURCE; goto cleanup_io; } @@ -1856,7 +1856,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) * a bad data or Q stripe. * TODO, we should redo the xor here. */ - err = -EIO; + err = BLK_STS_IOERR; goto cleanup; } /* @@ -1882,7 +1882,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio) if (rbio->bbio->raid_map[failb] == RAID6_Q_STRIPE) { if (rbio->bbio->raid_map[faila] == RAID5_P_STRIPE) { - err = -EIO; + err = BLK_STS_IOERR; goto cleanup; } /* @@ -1954,13 +1954,13 @@ pstripe: } } - err = 0; + err = BLK_STS_OK; cleanup: kfree(pointers); cleanup_io: if (rbio->operation == BTRFS_RBIO_READ_REBUILD) { - if (err == 0) + if (err == BLK_STS_OK) cache_rbio_pages(rbio); else clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); @@ -1968,7 +1968,7 @@ cleanup_io: rbio_orig_end_io(rbio, err); } else if (rbio->operation == BTRFS_RBIO_REBUILD_MISSING) { rbio_orig_end_io(rbio, err); - } else if (err == 0) { + } else if (err == BLK_STS_OK) { rbio->faila = -1; rbio->failb = -1; @@ -2005,7 +2005,7 @@ static void raid_recover_end_io(struct bio *bio) return; if (atomic_read(&rbio->error) > rbio->bbio->max_errors) - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); else __raid_recover_end_io(rbio); } @@ -2104,7 +2104,7 @@ out: cleanup: if (rbio->operation == BTRFS_RBIO_READ_REBUILD || rbio->operation == BTRFS_RBIO_REBUILD_MISSING) - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); return -EIO; } @@ -2431,7 +2431,7 @@ submit_write: nr_data = bio_list_size(&bio_list); if (!nr_data) { /* Every parity is right */ - rbio_orig_end_io(rbio, 0); + rbio_orig_end_io(rbio, BLK_STS_OK); return; } @@ -2451,7 +2451,7 @@ submit_write: return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe) @@ -2519,7 +2519,7 @@ static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio) return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); } /* @@ -2633,7 +2633,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio) return; cleanup: - rbio_orig_end_io(rbio, -EIO); + rbio_orig_end_io(rbio, BLK_STS_IOERR); return; finish: diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e8b9a269fdde..bd679bc7a1a9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -6212,8 +6212,8 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical) } } -int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, int async_submit) +blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, int async_submit) { struct btrfs_device *dev; struct bio *first_bio = bio; @@ -6233,7 +6233,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, &map_length, &bbio, mirror_num, 1); if (ret) { btrfs_bio_counter_dec(fs_info); - return ret; + return errno_to_blk_status(ret); } total_devs = bbio->num_stripes; @@ -6256,7 +6256,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, } btrfs_bio_counter_dec(fs_info); - return ret; + return errno_to_blk_status(ret); } if (map_length < length) { @@ -6283,7 +6283,7 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, dev_nr, async_submit); } btrfs_bio_counter_dec(fs_info); - return 0; + return BLK_STS_OK; } struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid, diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 6f45fd60d15a..93277fc60930 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -74,7 +74,7 @@ struct btrfs_device { int missing; int can_discard; int is_tgtdev_for_dev_replace; - int last_flush_error; + blk_status_t last_flush_error; int flush_bio_sent; #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED @@ -416,8 +416,8 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 type); void btrfs_mapping_init(struct btrfs_mapping_tree *tree); void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree); -int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, - int mirror_num, int async_submit); +blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio, + int mirror_num, int async_submit); int btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fmode_t flags, void *holder); int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 50836280a6f8..1bc709fe330a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -189,7 +189,7 @@ static int ceph_releasepage(struct page *page, gfp_t g) /* * read a single page, without unlocking it. */ -static int readpage_nounlock(struct file *filp, struct page *page) +static int ceph_do_readpage(struct file *filp, struct page *page) { struct inode *inode = file_inode(filp); struct ceph_inode_info *ci = ceph_inode(inode); @@ -219,7 +219,7 @@ static int readpage_nounlock(struct file *filp, struct page *page) err = ceph_readpage_from_fscache(inode, page); if (err == 0) - goto out; + return -EINPROGRESS; dout("readpage inode %p file %p page %p index %lu\n", inode, filp, page, page->index); @@ -249,8 +249,11 @@ out: static int ceph_readpage(struct file *filp, struct page *page) { - int r = readpage_nounlock(filp, page); - unlock_page(page); + int r = ceph_do_readpage(filp, page); + if (r != -EINPROGRESS) + unlock_page(page); + else + r = 0; return r; } @@ -1237,7 +1240,7 @@ retry_locked: goto retry_locked; r = writepage_nounlock(page, NULL); if (r < 0) - goto fail_nosnap; + goto fail_unlock; goto retry_locked; } @@ -1265,11 +1268,14 @@ retry_locked: } /* we need to read it. */ - r = readpage_nounlock(file, page); - if (r < 0) - goto fail_nosnap; + r = ceph_do_readpage(file, page); + if (r < 0) { + if (r == -EINPROGRESS) + return -EAGAIN; + goto fail_unlock; + } goto retry_locked; -fail_nosnap: +fail_unlock: unlock_page(page); return r; } diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index fd1172823f86..337f88673ed9 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -297,13 +297,7 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp) } } -static void ceph_vfs_readpage_complete(struct page *page, void *data, int error) -{ - if (!error) - SetPageUptodate(page); -} - -static void ceph_vfs_readpage_complete_unlock(struct page *page, void *data, int error) +static void ceph_readpage_from_fscache_complete(struct page *page, void *data, int error) { if (!error) SetPageUptodate(page); @@ -331,7 +325,7 @@ int ceph_readpage_from_fscache(struct inode *inode, struct page *page) return -ENOBUFS; ret = fscache_read_or_alloc_page(ci->fscache, page, - ceph_vfs_readpage_complete, NULL, + ceph_readpage_from_fscache_complete, NULL, GFP_KERNEL); switch (ret) { @@ -360,7 +354,7 @@ int ceph_readpages_from_fscache(struct inode *inode, return -ENOBUFS; ret = fscache_read_or_alloc_pages(ci->fscache, mapping, pages, nr_pages, - ceph_vfs_readpage_complete_unlock, + ceph_readpage_from_fscache_complete, NULL, mapping_gfp_mask(mapping)); switch (ret) { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 59647eb72c5f..83a8f52cd879 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1223,6 +1223,7 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, char *tmp_end, *value; char delim; bool got_ip = false; + bool got_version = false; unsigned short port = 0; struct sockaddr *dstaddr = (struct sockaddr *)&vol->dstaddr; @@ -1874,24 +1875,35 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, pr_warn("CIFS: server netbiosname longer than 15 truncated.\n"); break; case Opt_ver: + /* version of mount userspace tools, not dialect */ string = match_strdup(args); if (string == NULL) goto out_nomem; + /* If interface changes in mount.cifs bump to new ver */ if (strncasecmp(string, "1", 1) == 0) { + if (strlen(string) > 1) { + pr_warn("Bad mount helper ver=%s. Did " + "you want SMB1 (CIFS) dialect " + "and mean to type vers=1.0 " + "instead?\n", string); + goto cifs_parse_mount_err; + } /* This is the default */ break; } /* For all other value, error */ - pr_warn("CIFS: Invalid version specified\n"); + pr_warn("CIFS: Invalid mount helper version specified\n"); goto cifs_parse_mount_err; case Opt_vers: + /* protocol version (dialect) */ string = match_strdup(args); if (string == NULL) goto out_nomem; if (cifs_parse_smb_version(string, vol) != 0) goto cifs_parse_mount_err; + got_version = true; break; case Opt_sec: string = match_strdup(args); @@ -1973,6 +1985,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname, else if (override_gid == 1) pr_notice("CIFS: ignoring forcegid mount option specified with no gid= option.\n"); + if (got_version == false) + pr_warn("No dialect specified on mount. Default has changed to " + "a more secure dialect, SMB3 (vers=3.0), from CIFS " + "(SMB1). To use the less secure SMB1 dialect to access " + "old servers which do not support SMB3 specify vers=1.0" + " on mount. For somewhat newer servers such as Windows " + "7 try vers=2.1.\n"); + kfree(mountdata_copy); return 0; diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 56366e984076..e702d48bd023 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -194,15 +194,20 @@ cifs_bp_rename_retry: } /* + * Don't allow path components longer than the server max. * Don't allow the separator character in a path component. * The VFS will not allow "/", but "\" is allowed by posix. */ static int -check_name(struct dentry *direntry) +check_name(struct dentry *direntry, struct cifs_tcon *tcon) { struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb); int i; + if (unlikely(direntry->d_name.len > + le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength))) + return -ENAMETOOLONG; + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)) { for (i = 0; i < direntry->d_name.len; i++) { if (direntry->d_name.name[i] == '\\') { @@ -500,10 +505,6 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, return finish_no_open(file, res); } - rc = check_name(direntry); - if (rc) - return rc; - xid = get_xid(); cifs_dbg(FYI, "parent inode = 0x%p name is: %pd and dentry = 0x%p\n", @@ -516,6 +517,11 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry, } tcon = tlink_tcon(tlink); + + rc = check_name(direntry, tcon); + if (rc) + goto out_free_xid; + server = tcon->ses->server; if (server->ops->new_lease_key) @@ -776,7 +782,7 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry, } pTcon = tlink_tcon(tlink); - rc = check_name(direntry); + rc = check_name(direntry, pTcon); if (rc) goto lookup_out; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5fb2fc2d0080..7aa67206f6da 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -514,7 +514,12 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses) * No tcon so can't do * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]); */ - if (rc != 0) + if (rc == -EOPNOTSUPP) { + cifs_dbg(VFS, "Dialect not supported by server. Consider " + "specifying vers=1.0 or vers=2.1 on mount for accessing" + " older servers\n"); + goto neg_exit; + } else if (rc != 0) goto neg_exit; cifs_dbg(FYI, "mode 0x%x\n", rsp->SecurityMode); @@ -3219,8 +3224,8 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf, kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) * le32_to_cpu(pfs_inf->SectorsPerAllocationUnit); kst->f_blocks = le64_to_cpu(pfs_inf->TotalAllocationUnits); - kst->f_bfree = le64_to_cpu(pfs_inf->ActualAvailableAllocationUnits); - kst->f_bavail = le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits); + kst->f_bfree = kst->f_bavail = + le64_to_cpu(pfs_inf->CallerAvailableAllocationUnits); return; } diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 18700fd25a0b..2826882c81d1 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,8 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* BB FIXME - analyze following length BB */ -#define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */ +/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ +#define MAX_SMB2_HDR_SIZE 0x00b0 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) @@ -646,11 +646,10 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, pte_t pte, *ptep = NULL; pmd_t *pmdp = NULL; spinlock_t *ptl; - bool changed; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) { - unsigned long address; + unsigned long address, start, end; cond_resched(); @@ -658,8 +657,13 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, continue; address = pgoff_address(index, vma); - changed = false; - if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl)) + + /* + * Note because we provide start/end to follow_pte_pmd it will + * call mmu_notifier_invalidate_range_start() on our behalf + * before taking any lock. + */ + if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &ptep, &pmdp, &ptl)) continue; if (pmdp) { @@ -676,7 +680,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping, pmd = pmd_wrprotect(pmd); pmd = pmd_mkclean(pmd); set_pmd_at(vma->vm_mm, address, pmdp, pmd); - changed = true; + mmu_notifier_invalidate_range(vma->vm_mm, start, end); unlock_pmd: spin_unlock(ptl); #endif @@ -691,13 +695,12 @@ unlock_pmd: pte = pte_wrprotect(pte); pte = pte_mkclean(pte); set_pte_at(vma->vm_mm, address, ptep, pte); - changed = true; + mmu_notifier_invalidate_range(vma->vm_mm, start, end); unlock_pte: pte_unmap_unlock(ptep, ptl); } - if (changed) - mmu_notifier_invalidate_page(vma->vm_mm, address); + mmu_notifier_invalidate_range_end(vma->vm_mm, start, end); } i_mmap_unlock_read(mapping); } @@ -1383,6 +1386,16 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf, trace_dax_pmd_fault(inode, vmf, max_pgoff, 0); + /* + * Make sure that the faulting address's PMD offset (color) matches + * the PMD offset from the start of the file. This is necessary so + * that a PMD range in the page table overlaps exactly with a PMD + * range in the radix tree. + */ + if ((vmf->pgoff & PG_PMD_COLOUR) != + ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR)) + goto fallback; + /* Fall back to PTEs if we're going to COW */ if (write && !(vma->vm_flags & VM_SHARED)) goto fallback; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 108df2e3602c..7eae33ffa3fc 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -133,6 +133,50 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb) return sb->s_fs_info; } +static int devpts_ptmx_path(struct path *path) +{ + struct super_block *sb; + int err; + + /* Has the devpts filesystem already been found? */ + if (path->mnt->mnt_sb->s_magic == DEVPTS_SUPER_MAGIC) + return 0; + + /* Is a devpts filesystem at "pts" in the same directory? */ + err = path_pts(path); + if (err) + return err; + + /* Is the path the root of a devpts filesystem? */ + sb = path->mnt->mnt_sb; + if ((sb->s_magic != DEVPTS_SUPER_MAGIC) || + (path->mnt->mnt_root != sb->s_root)) + return -ENODEV; + + return 0; +} + +struct vfsmount *devpts_mntget(struct file *filp, struct pts_fs_info *fsi) +{ + struct path path; + int err; + + path = filp->f_path; + path_get(&path); + + err = devpts_ptmx_path(&path); + dput(path.dentry); + if (err) { + mntput(path.mnt); + path.mnt = ERR_PTR(err); + } + if (DEVPTS_SB(path.mnt->mnt_sb) != fsi) { + mntput(path.mnt); + path.mnt = ERR_PTR(-ENODEV); + } + return path.mnt; +} + struct pts_fs_info *devpts_acquire(struct file *filp) { struct pts_fs_info *result; @@ -143,27 +187,16 @@ struct pts_fs_info *devpts_acquire(struct file *filp) path = filp->f_path; path_get(&path); - /* Has the devpts filesystem already been found? */ - sb = path.mnt->mnt_sb; - if (sb->s_magic != DEVPTS_SUPER_MAGIC) { - /* Is a devpts filesystem at "pts" in the same directory? */ - err = path_pts(&path); - if (err) { - result = ERR_PTR(err); - goto out; - } - - /* Is the path the root of a devpts filesystem? */ - result = ERR_PTR(-ENODEV); - sb = path.mnt->mnt_sb; - if ((sb->s_magic != DEVPTS_SUPER_MAGIC) || - (path.mnt->mnt_root != sb->s_root)) - goto out; + err = devpts_ptmx_path(&path); + if (err) { + result = ERR_PTR(err); + goto out; } /* * pty code needs to hold extra references in case of last /dev/tty close */ + sb = path.mnt->mnt_sb; atomic_inc(&sb->s_active); result = DEVPTS_SB(sb); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index e767e4389cb1..adbe328b957c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -600,8 +600,13 @@ static void ep_remove_wait_queue(struct eppoll_entry *pwq) wait_queue_head_t *whead; rcu_read_lock(); - /* If it is cleared by POLLFREE, it should be rcu-safe */ - whead = rcu_dereference(pwq->whead); + /* + * If it is cleared by POLLFREE, it should be rcu-safe. + * If we read NULL we need a barrier paired with + * smp_store_release() in ep_poll_callback(), otherwise + * we rely on whead->lock. + */ + whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); @@ -1134,17 +1139,6 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v struct eventpoll *ep = epi->ep; int ewake = 0; - if ((unsigned long)key & POLLFREE) { - ep_pwq_from_wait(wait)->whead = NULL; - /* - * whead = NULL above can race with ep_remove_wait_queue() - * which can do another remove_wait_queue() after us, so we - * can't use __remove_wait_queue(). whead->lock is held by - * the caller. - */ - list_del_init(&wait->entry); - } - spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); @@ -1228,10 +1222,26 @@ out_unlock: if (pwake) ep_poll_safewake(&ep->poll_wait); - if (epi->event.events & EPOLLEXCLUSIVE) - return ewake; + if (!(epi->event.events & EPOLLEXCLUSIVE)) + ewake = 1; + + if ((unsigned long)key & POLLFREE) { + /* + * If we race with ep_remove_wait_queue() it can miss + * ->whead = NULL and do another remove_wait_queue() after + * us, so we can't use __remove_wait_queue(). + */ + list_del_init(&wait->entry); + /* + * ->whead != NULL protects us from the race with ep_free() + * or ep_remove(), ep_remove_wait_queue() takes whead->lock + * held by the caller. Once we nullify it, nothing protects + * ep/epi or even wait. + */ + smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); + } - return 1; + return ewake; } /* diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 5a1052627a81..701085620cd8 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2300,7 +2300,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) EXT4_MAX_BLOCK_LOG_SIZE); struct sg { struct ext4_group_info info; - ext4_grpblk_t counters[blocksize_bits + 2]; + ext4_grpblk_t counters[EXT4_MAX_BLOCK_LOG_SIZE + 2]; } sg; group--; @@ -2309,6 +2309,9 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); + i = (blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + + sizeof(struct ext4_group_info); + grinfo = ext4_get_group_info(sb, group); /* Load the group info in memory only if not already loaded. */ if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) { @@ -2320,7 +2323,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) buddy_loaded = 1; } - memcpy(&sg, ext4_get_group_info(sb, group), sizeof(sg)); + memcpy(&sg, ext4_get_group_info(sb, group), i); if (buddy_loaded) ext4_mb_unload_buddy(&e4b); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 82a5af9f6668..3dd970168448 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1543,7 +1543,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, /* Clear padding bytes. */ memset(val + i->value_len, 0, new_size - i->value_len); } - return 0; + goto update_hash; } /* Compute min_offs and last. */ @@ -1707,6 +1707,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, here->e_value_size = cpu_to_le32(i->value_len); } +update_hash: if (i->value) { __le32 hash = 0; @@ -1725,7 +1726,8 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i, here->e_name_len, &crc32c_hash, 1); } else if (is_block) { - __le32 *value = s->base + min_offs - new_size; + __le32 *value = s->base + le16_to_cpu( + here->e_value_offs); hash = ext4_xattr_hash_entry(here->e_name, here->e_name_len, value, diff --git a/fs/iomap.c b/fs/iomap.c index 039266128b7f..59cc98ad7577 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -278,7 +278,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data, unsigned long bytes; /* Bytes to write to page */ offset = (pos & (PAGE_SIZE - 1)); - bytes = min_t(unsigned long, PAGE_SIZE - offset, length); + bytes = min_t(loff_t, PAGE_SIZE - offset, length); rpage = __iomap_read_page(inode, pos); if (IS_ERR(rpage)) @@ -373,7 +373,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count, unsigned offset, bytes; offset = pos & (PAGE_SIZE - 1); /* Within page */ - bytes = min_t(unsigned, PAGE_SIZE - offset, count); + bytes = min_t(loff_t, PAGE_SIZE - offset, count); if (IS_DAX(inode)) status = iomap_dax_zero(pos, offset, bytes, iomap); diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 78b41e1d5c67..60726ae7cf26 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -619,16 +619,10 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) if (!sb->s_root) goto out_no_root; - /* logical blocks are represented by 40 bits in pxd_t, etc. */ - sb->s_maxbytes = ((u64) sb->s_blocksize) << 40; -#if BITS_PER_LONG == 32 - /* - * Page cache is indexed by long. - * I would use MAX_LFS_FILESIZE, but it's only half as big + /* logical blocks are represented by 40 bits in pxd_t, etc. + * and page cache is indexed by long */ - sb->s_maxbytes = min(((u64) PAGE_SIZE << 32) - 1, - (u64)sb->s_maxbytes); -#endif + sb->s_maxbytes = min(((loff_t)sb->s_blocksize) << 40, MAX_LFS_FILESIZE); sb->s_time_gran = 1; return 0; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 20fbcab97753..5f940d2a136b 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -144,7 +144,7 @@ static void next_decode_page(struct nfsd4_compoundargs *argp) argp->p = page_address(argp->pagelist[0]); argp->pagelist++; if (argp->pagelen < PAGE_SIZE) { - argp->end = argp->p + (argp->pagelen>>2); + argp->end = argp->p + XDR_QUADLEN(argp->pagelen); argp->pagelen = 0; } else { argp->end = argp->p + (PAGE_SIZE>>2); @@ -1279,9 +1279,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) argp->pagelen -= pages * PAGE_SIZE; len -= pages * PAGE_SIZE; - argp->p = (__be32 *)page_address(argp->pagelist[0]); - argp->pagelist++; - argp->end = argp->p + XDR_QUADLEN(PAGE_SIZE); + next_decode_page(argp); } argp->p += XDR_QUADLEN(len); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 38d0383dc7f9..bc69d40c4e8b 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -969,7 +969,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, int use_wgather; loff_t pos = offset; unsigned int pflags = current->flags; - int flags = 0; + rwf_t flags = 0; if (test_bit(RQ_LOCAL, &rqstp->rq_flags)) /* diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 53a17496c5c5..566e6ef99f07 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1124,6 +1124,10 @@ void dquot_free_reserved_space(struct dquot *dquot, qsize_t number) WARN_ON_ONCE(1); dquot->dq_dqb.dqb_rsvspace = 0; } + if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= + dquot->dq_dqb.dqb_bsoftlimit) + dquot->dq_dqb.dqb_btime = (time64_t) 0; + clear_bit(DQ_BLKS_B, &dquot->dq_flags); } static void dquot_decr_inodes(struct dquot *dquot, qsize_t number) @@ -1145,7 +1149,8 @@ static void dquot_decr_space(struct dquot *dquot, qsize_t number) dquot->dq_dqb.dqb_curspace -= number; else dquot->dq_dqb.dqb_curspace = 0; - if (dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit) + if (dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace <= + dquot->dq_dqb.dqb_bsoftlimit) dquot->dq_dqb.dqb_btime = (time64_t) 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } @@ -1381,14 +1386,18 @@ static int info_idq_free(struct dquot *dquot, qsize_t inodes) static int info_bdq_free(struct dquot *dquot, qsize_t space) { + qsize_t tspace; + + tspace = dquot->dq_dqb.dqb_curspace + dquot->dq_dqb.dqb_rsvspace; + if (test_bit(DQ_FAKE_B, &dquot->dq_flags) || - dquot->dq_dqb.dqb_curspace <= dquot->dq_dqb.dqb_bsoftlimit) + tspace <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_NOWARN; - if (dquot->dq_dqb.dqb_curspace - space <= dquot->dq_dqb.dqb_bsoftlimit) + if (tspace - space <= dquot->dq_dqb.dqb_bsoftlimit) return QUOTA_NL_BSOFTBELOW; - if (dquot->dq_dqb.dqb_curspace >= dquot->dq_dqb.dqb_bhardlimit && - dquot->dq_dqb.dqb_curspace - space < dquot->dq_dqb.dqb_bhardlimit) + if (tspace >= dquot->dq_dqb.dqb_bhardlimit && + tspace - space < dquot->dq_dqb.dqb_bhardlimit) return QUOTA_NL_BHARDBELOW; return QUOTA_NL_NOWARN; } @@ -2681,7 +2690,7 @@ static int do_set_dqblk(struct dquot *dquot, struct qc_dqblk *di) if (check_blim) { if (!dm->dqb_bsoftlimit || - dm->dqb_curspace < dm->dqb_bsoftlimit) { + dm->dqb_curspace + dm->dqb_rsvspace < dm->dqb_bsoftlimit) { dm->dqb_btime = 0; clear_bit(DQ_BLKS_B, &dquot->dq_flags); } else if (!(di->d_fieldmask & QC_SPC_TIMER)) diff --git a/fs/read_write.c b/fs/read_write.c index 0cc7033aa413..61b58c7b6531 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -33,7 +33,7 @@ const struct file_operations generic_ro_fops = { EXPORT_SYMBOL(generic_ro_fops); -static inline int unsigned_offsets(struct file *file) +static inline bool unsigned_offsets(struct file *file) { return file->f_mode & FMODE_UNSIGNED_OFFSET; } @@ -633,7 +633,7 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to) EXPORT_SYMBOL(iov_shorten); static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, int type, int flags) + loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; @@ -655,7 +655,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, - loff_t *ppos, int type, int flags) + loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; @@ -871,7 +871,7 @@ out: #endif static ssize_t do_iter_read(struct file *file, struct iov_iter *iter, - loff_t *pos, int flags) + loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; @@ -899,7 +899,7 @@ out: } ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags) + rwf_t flags) { if (!file->f_op->read_iter) return -EINVAL; @@ -908,7 +908,7 @@ ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, EXPORT_SYMBOL(vfs_iter_read); static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, - loff_t *pos, int flags) + loff_t *pos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; @@ -935,7 +935,7 @@ static ssize_t do_iter_write(struct file *file, struct iov_iter *iter, } ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags) + rwf_t flags) { if (!file->f_op->write_iter) return -EINVAL; @@ -944,7 +944,7 @@ ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, EXPORT_SYMBOL(vfs_iter_write); ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -962,7 +962,7 @@ ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, EXPORT_SYMBOL(vfs_readv); ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -981,7 +981,7 @@ ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, EXPORT_SYMBOL(vfs_writev); static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, int flags) + unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -1001,7 +1001,7 @@ static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, int flags) + unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; @@ -1027,7 +1027,7 @@ static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; @@ -1050,7 +1050,7 @@ static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; @@ -1094,7 +1094,7 @@ SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, - int, flags) + rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); @@ -1114,7 +1114,7 @@ SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, - int, flags) + rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); @@ -1127,7 +1127,7 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, #ifdef CONFIG_COMPAT static size_t compat_readv(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -1147,7 +1147,7 @@ static size_t compat_readv(struct file *file, static size_t do_compat_readv(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, int flags) + compat_ulong_t vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1173,7 +1173,7 @@ COMPAT_SYSCALL_DEFINE3(readv, compat_ulong_t, fd, static long do_compat_preadv64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret; @@ -1211,7 +1211,7 @@ COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos, int, flags) + unsigned long, vlen, loff_t, pos, rwf_t, flags) { return do_compat_preadv64(fd, vec, vlen, pos, flags); } @@ -1220,7 +1220,7 @@ COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, - int, flags) + rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; @@ -1232,7 +1232,7 @@ COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, static size_t compat_writev(struct file *file, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t *pos, int flags) + unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; @@ -1254,7 +1254,7 @@ static size_t compat_writev(struct file *file, static size_t do_compat_writev(compat_ulong_t fd, const struct compat_iovec __user* vec, - compat_ulong_t vlen, int flags) + compat_ulong_t vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret; @@ -1279,7 +1279,7 @@ COMPAT_SYSCALL_DEFINE3(writev, compat_ulong_t, fd, static long do_compat_pwritev64(unsigned long fd, const struct compat_iovec __user *vec, - unsigned long vlen, loff_t pos, int flags) + unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret; @@ -1317,7 +1317,7 @@ COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct compat_iovec __user *,vec, - unsigned long, vlen, loff_t, pos, int, flags) + unsigned long, vlen, loff_t, pos, rwf_t, flags) { return do_compat_pwritev64(fd, vec, vlen, pos, flags); } @@ -1325,7 +1325,7 @@ COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct compat_iovec __user *,vec, - compat_ulong_t, vlen, u32, pos_low, u32, pos_high, int, flags) + compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; diff --git a/fs/select.c b/fs/select.c index 9d5f15ed87fe..c6362e38ae92 100644 --- a/fs/select.c +++ b/fs/select.c @@ -1164,11 +1164,7 @@ int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, if (ufdset) { return compat_get_bitmap(fdset, ufdset, nr); } else { - /* Tricky, must clear full unsigned long in the - * kernel fdset at the end, ALIGN makes sure that - * actually happens. - */ - memset(fdset, 0, ALIGN(nr, BITS_PER_LONG)); + zero_fd_set(nr, fdset); return 0; } } diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index ffd5a15d1bb6..abf5beaae907 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1246,13 +1246,13 @@ xfs_dialloc_ag_inobt( /* free inodes to the left? */ if (useleft && trec.ir_freecount) { - rec = trec; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); cur = tcur; pag->pagl_leftrec = trec.ir_startino; pag->pagl_rightrec = rec.ir_startino; pag->pagl_pagino = pagino; + rec = trec; goto alloc_inode; } diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 0053bcf2b10a..4ebd0bafc914 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -749,9 +749,20 @@ xfs_log_mount_finish( return 0; } + /* + * During the second phase of log recovery, we need iget and + * iput to behave like they do for an active filesystem. + * xfs_fs_drop_inode needs to be able to prevent the deletion + * of inodes before we're done replaying log items on those + * inodes. Turn it off immediately after recovery finishes + * so that we don't leak the quota inodes if subsequent mount + * activities fail. + */ + mp->m_super->s_flags |= MS_ACTIVE; error = xlog_recover_finish(mp->m_log); if (!error) xfs_log_work_queue(mp); + mp->m_super->s_flags &= ~MS_ACTIVE; return error; } diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 40d4e8b4e193..ea7d4b4e50d0 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -945,15 +945,6 @@ xfs_mountfs( } /* - * During the second phase of log recovery, we need iget and - * iput to behave like they do for an active filesystem. - * xfs_fs_drop_inode needs to be able to prevent the deletion - * of inodes before we're done replaying log items on those - * inodes. - */ - mp->m_super->s_flags |= MS_ACTIVE; - - /* * Finish recovering the file system. This part needed to be delayed * until after the root and real-time bitmap inodes were consistently * read in. @@ -1028,12 +1019,13 @@ xfs_mountfs( out_quota: xfs_qm_unmount_quotas(mp); out_rtunmount: - mp->m_super->s_flags &= ~MS_ACTIVE; xfs_rtunmount_inodes(mp); out_rele_rip: IRELE(rip); cancel_delayed_work_sync(&mp->m_reclaim_work); xfs_reclaim_inodes(mp, SYNC_WAIT); + /* Clean out dquots that might be in memory after quotacheck. */ + xfs_qm_unmount(mp); out_log_dealloc: mp->m_flags |= XFS_MOUNT_UNMOUNTING; xfs_log_mount_cancel(mp); diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h index fc824e2828f3..5d2add1a6c96 100644 --- a/include/asm-generic/topology.h +++ b/include/asm-generic/topology.h @@ -48,7 +48,11 @@ #define parent_node(node) ((void)(node),0) #endif #ifndef cpumask_of_node -#define cpumask_of_node(node) ((void)node, cpu_online_mask) + #ifdef CONFIG_NEED_MULTIPLE_NODES + #define cpumask_of_node(node) ((node) == 0 ? cpu_online_mask : cpu_none_mask) + #else + #define cpumask_of_node(node) ((void)node, cpu_online_mask) + #endif #endif #ifndef pcibus_to_node #define pcibus_to_node(bus) ((void)(bus), -1) diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index da0be9a8d1de..9623d78f8494 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -60,6 +60,22 @@ #define ALIGN_FUNCTION() . = ALIGN(8) /* + * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which + * generates .data.identifier sections, which need to be pulled in with + * .data. We don't want to pull in .data..other sections, which Linux + * has defined. Same for text and bss. + */ +#ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION +#define TEXT_MAIN .text .text.[0-9a-zA-Z_]* +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* +#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* +#else +#define TEXT_MAIN .text +#define DATA_MAIN .data +#define BSS_MAIN .bss +#endif + +/* * Align to a 32 byte boundary equal to the * alignment gcc 4.5 uses for a struct */ @@ -198,12 +214,9 @@ /* * .data section - * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections generates - * .data.identifier which needs to be pulled in with .data, but don't want to - * pull in .data..stuff which has its own requirements. Same for bss. */ #define DATA_DATA \ - *(.data .data.[0-9a-zA-Z_]*) \ + *(DATA_MAIN) \ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data) \ @@ -434,16 +447,17 @@ VMLINUX_SYMBOL(__security_initcall_end) = .; \ } -/* .text section. Map to function alignment to avoid address changes +/* + * .text section. Map to function alignment to avoid address changes * during second ld run in second ld pass when generating System.map - * LD_DEAD_CODE_DATA_ELIMINATION option enables -ffunction-sections generates - * .text.identifier which needs to be pulled in with .text , but some - * architectures define .text.foo which is not intended to be pulled in here. - * Those enabling LD_DEAD_CODE_DATA_ELIMINATION must ensure they don't have - * conflicting section names, and must pull in .text.[0-9a-zA-Z_]* */ + * + * TEXT_MAIN here will match .text.fixup and .text.unlikely if dead + * code elimination is enabled, so these sections should be converted + * to use ".." first. + */ #define TEXT_TEXT \ ALIGN_FUNCTION(); \ - *(.text.hot .text .text.fixup .text.unlikely) \ + *(.text.hot TEXT_MAIN .text.fixup .text.unlikely) \ *(.ref.text) \ MEM_KEEP(init.text) \ MEM_KEEP(exit.text) \ @@ -613,7 +627,7 @@ BSS_FIRST_SECTIONS \ *(.bss..page_aligned) \ *(.dynbss) \ - *(.bss .bss.[0-9a-zA-Z_]*) \ + *(BSS_MAIN) \ *(COMMON) \ } diff --git a/include/linux/ata.h b/include/linux/ata.h index e65ae4b2ed48..c7a353825450 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -60,7 +60,8 @@ enum { ATA_ID_FW_REV = 23, ATA_ID_PROD = 27, ATA_ID_MAX_MULTSECT = 47, - ATA_ID_DWORD_IO = 48, + ATA_ID_DWORD_IO = 48, /* before ATA-8 */ + ATA_ID_TRUSTED = 48, /* ATA-8 and later */ ATA_ID_CAPABILITY = 49, ATA_ID_OLD_PIO_MODES = 51, ATA_ID_OLD_DMA_MODES = 52, @@ -889,6 +890,13 @@ static inline bool ata_id_has_dword_io(const u16 *id) return id[ATA_ID_DWORD_IO] & (1 << 0); } +static inline bool ata_id_has_trusted(const u16 *id) +{ + if (ata_id_major_version(id) <= 7) + return false; + return id[ATA_ID_TRUSTED] & (1 << 0); +} + static inline bool ata_id_has_unload(const u16 *id) { if (ata_id_major_version(id) >= 7 && diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 25f6a0cb27d3..2a5d52fa90f5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -568,7 +568,6 @@ struct request_queue { #if defined(CONFIG_BLK_DEV_BSG) bsg_job_fn *bsg_job_fn; - int bsg_job_size; struct bsg_class_device bsg_dev; #endif diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index e34dde2da0ef..637a20cfb237 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -24,6 +24,7 @@ #define _BLK_BSG_ #include <linux/blkdev.h> +#include <scsi/scsi_request.h> struct request; struct device; @@ -37,6 +38,7 @@ struct bsg_buffer { }; struct bsg_job { + struct scsi_request sreq; struct device *dev; struct request *req; diff --git a/include/linux/compat.h b/include/linux/compat.h index 5a6a109b4a50..3fc433303d7a 100644 --- a/include/linux/compat.h +++ b/include/linux/compat.h @@ -27,7 +27,7 @@ #endif #ifndef __SC_DELOUSE -#define __SC_DELOUSE(t,v) ((t)(unsigned long)(v)) +#define __SC_DELOUSE(t,v) ((__force t)(unsigned long)(v)) #endif #define COMPAT_SYSCALL_DEFINE0(name) \ @@ -365,10 +365,10 @@ asmlinkage ssize_t compat_sys_pwritev(compat_ulong_t fd, compat_ulong_t vlen, u32 pos_low, u32 pos_high); asmlinkage ssize_t compat_sys_preadv2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); asmlinkage ssize_t compat_sys_pwritev2(compat_ulong_t fd, const struct compat_iovec __user *vec, - compat_ulong_t vlen, u32 pos_low, u32 pos_high, int flags); + compat_ulong_t vlen, u32 pos_low, u32 pos_high, rwf_t flags); #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 asmlinkage long compat_sys_preadv64(unsigned long fd, @@ -382,6 +382,18 @@ asmlinkage long compat_sys_pwritev64(unsigned long fd, unsigned long vlen, loff_t pos); #endif +#ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 +asmlinkage long compat_sys_readv64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + +#ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 +asmlinkage long compat_sys_pwritev64v2(unsigned long fd, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t pos, rwf_t flags); +#endif + asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int); asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv, diff --git a/include/linux/compiler.h b/include/linux/compiler.h index eca8ad75e28b..043b60de041e 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -517,7 +517,8 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s # define __compiletime_error_fallback(condition) do { } while (0) #endif -#define __compiletime_assert(condition, msg, prefix, suffix) \ +#ifdef __OPTIMIZE__ +# define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ bool __cond = !(condition); \ extern void prefix ## suffix(void) __compiletime_error(msg); \ @@ -525,6 +526,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s prefix ## suffix(); \ __compiletime_error_fallback(__cond); \ } while (0) +#else +# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) +#endif #define _compiletime_assert(condition, msg, prefix, suffix) \ __compiletime_assert(condition, msg, prefix, suffix) diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 1473455d0341..4f2b3b2076c4 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -549,46 +549,29 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size); *---------------------------------------------------------------*/ #define DM_NAME "device-mapper" -#ifdef CONFIG_PRINTK -extern struct ratelimit_state dm_ratelimit_state; - -#define dm_ratelimit() __ratelimit(&dm_ratelimit_state) -#else -#define dm_ratelimit() 0 -#endif +#define DM_RATELIMIT(pr_func, fmt, ...) \ +do { \ + static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, \ + DEFAULT_RATELIMIT_BURST); \ + \ + if (__ratelimit(&rs)) \ + pr_func(DM_FMT(fmt), ##__VA_ARGS__); \ +} while (0) #define DM_FMT(fmt) DM_NAME ": " DM_MSG_PREFIX ": " fmt "\n" #define DMCRIT(fmt, ...) pr_crit(DM_FMT(fmt), ##__VA_ARGS__) #define DMERR(fmt, ...) pr_err(DM_FMT(fmt), ##__VA_ARGS__) -#define DMERR_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMERR(fmt, ##__VA_ARGS__); \ -} while (0) - +#define DMERR_LIMIT(fmt, ...) DM_RATELIMIT(pr_err, fmt, ##__VA_ARGS__) #define DMWARN(fmt, ...) pr_warn(DM_FMT(fmt), ##__VA_ARGS__) -#define DMWARN_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMWARN(fmt, ##__VA_ARGS__); \ -} while (0) - +#define DMWARN_LIMIT(fmt, ...) DM_RATELIMIT(pr_warn, fmt, ##__VA_ARGS__) #define DMINFO(fmt, ...) pr_info(DM_FMT(fmt), ##__VA_ARGS__) -#define DMINFO_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMINFO(fmt, ##__VA_ARGS__); \ -} while (0) +#define DMINFO_LIMIT(fmt, ...) DM_RATELIMIT(pr_info, fmt, ##__VA_ARGS__) #ifdef CONFIG_DM_DEBUG #define DMDEBUG(fmt, ...) printk(KERN_DEBUG DM_FMT(fmt), ##__VA_ARGS__) -#define DMDEBUG_LIMIT(fmt, ...) \ -do { \ - if (dm_ratelimit()) \ - DMDEBUG(fmt, ##__VA_ARGS__); \ -} while (0) +#define DMDEBUG_LIMIT(fmt, ...) DM_RATELIMIT(pr_debug, fmt, ##__VA_ARGS__) #else #define DMDEBUG(fmt, ...) no_printk(fmt, ##__VA_ARGS__) #define DMDEBUG_LIMIT(fmt, ...) no_printk(fmt, ##__VA_ARGS__) diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 277ab9af9ac2..100cb4343763 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -19,6 +19,7 @@ struct pts_fs_info; +struct vfsmount *devpts_mntget(struct file *, struct pts_fs_info *); struct pts_fs_info *devpts_acquire(struct file *); void devpts_release(struct pts_fs_info *); @@ -32,6 +33,15 @@ void *devpts_get_priv(struct dentry *); /* unlink */ void devpts_pty_kill(struct dentry *); +/* in pty.c */ +int ptm_open_peer(struct file *master, struct tty_struct *tty, int flags); + +#else +static inline int +ptm_open_peer(struct file *master, struct tty_struct *tty, int flags) +{ + return -EIO; +} #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index 6e1fd5d21248..2625fc47c7e5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -72,6 +72,8 @@ extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; +typedef __kernel_rwf_t rwf_t; + struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); @@ -907,9 +909,9 @@ static inline struct file *get_file(struct file *f) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 -#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) +#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 @@ -1758,9 +1760,9 @@ extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *) extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, @@ -2874,9 +2876,9 @@ extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags); + rwf_t flags); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, - int flags); + rwf_t flags); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); @@ -3143,7 +3145,7 @@ static inline int iocb_flags(struct file *file) return res; } -static inline int kiocb_set_rw_flags(struct kiocb *ki, int flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) { if (unlikely(flags & ~RWF_SUPPORTED)) return -EOPNOTSUPP; diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h index d68bec297a45..c380daa40c0e 100644 --- a/include/linux/iio/iio.h +++ b/include/linux/iio/iio.h @@ -535,7 +535,7 @@ struct iio_buffer_setup_ops { * @scan_timestamp: [INTERN] set if any buffers have requested timestamp * @scan_index_timestamp:[INTERN] cache of the index to the timestamp * @trig: [INTERN] current device trigger (buffer modes) - * @trig_readonly [INTERN] mark the current trigger immutable + * @trig_readonly: [INTERN] mark the current trigger immutable * @pollfunc: [DRIVER] function run on trigger being received * @pollfunc_event: [DRIVER] function run on events trigger being received * @channels: [DRIVER] channel specification structure table diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h index ea08302f2d7b..7142d8d6e470 100644 --- a/include/linux/iio/trigger.h +++ b/include/linux/iio/trigger.h @@ -144,8 +144,8 @@ void devm_iio_trigger_unregister(struct device *dev, /** * iio_trigger_set_immutable() - set an immutable trigger on destination * - * @indio_dev - IIO device structure containing the device - * @trig - trigger to assign to device + * @indio_dev: IIO device structure containing the device + * @trig: trigger to assign to device * **/ int iio_trigger_set_immutable(struct iio_dev *indio_dev, struct iio_trigger *trig); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 2cb54adc4a33..176f7569d874 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -240,7 +240,7 @@ struct iommu_device { struct list_head list; const struct iommu_ops *ops; struct fwnode_handle *fwnode; - struct device dev; + struct device *dev; }; int iommu_device_register(struct iommu_device *iommu); @@ -265,6 +265,11 @@ static inline void iommu_device_set_fwnode(struct iommu_device *iommu, iommu->fwnode = fwnode; } +static inline struct iommu_device *dev_to_iommu_device(struct device *dev) +{ + return (struct iommu_device *)dev_get_drvdata(dev); +} + #define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ #define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ #define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ @@ -589,6 +594,11 @@ static inline void iommu_device_set_fwnode(struct iommu_device *iommu, { } +static inline struct iommu_device *dev_to_iommu_device(struct device *dev) +{ + return NULL; +} + static inline void iommu_device_unregister(struct iommu_device *iommu) { } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 77d427974f57..bae11c7e7bf3 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -61,6 +61,7 @@ extern int memblock_debug; #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK #define __init_memblock __meminit #define __initdata_memblock __meminitdata +void memblock_discard(void); #else #define __init_memblock #define __initdata_memblock @@ -74,8 +75,6 @@ phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align, int nid, ulong flags); phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align); -phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr); -phys_addr_t get_allocated_memblock_memory_regions_info(phys_addr_t *addr); void memblock_allow_resize(void); int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); int memblock_add(phys_addr_t base, phys_addr_t size); @@ -110,6 +109,9 @@ void __next_mem_range_rev(u64 *idx, int nid, ulong flags, void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start, phys_addr_t *out_end); +void __memblock_free_early(phys_addr_t base, phys_addr_t size); +void __memblock_free_late(phys_addr_t base, phys_addr_t size); + /** * for_each_mem_range - iterate through memblock areas from type_a and not * included in type_b. Or just type_a if type_b is NULL. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 3914e3dd6168..9b15a4bcfa77 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -484,7 +484,8 @@ bool mem_cgroup_oom_synchronize(bool wait); extern int do_swap_account; #endif -void lock_page_memcg(struct page *page); +struct mem_cgroup *lock_page_memcg(struct page *page); +void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, @@ -809,7 +810,12 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) { } -static inline void lock_page_memcg(struct page *page) +static inline struct mem_cgroup *lock_page_memcg(struct page *page) +{ + return NULL; +} + +static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index df6ce59a1f95..205d82d4c468 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -673,9 +673,7 @@ enum mlx5_device_state { }; enum mlx5_interface_state { - MLX5_INTERFACE_STATE_DOWN = BIT(0), - MLX5_INTERFACE_STATE_UP = BIT(1), - MLX5_INTERFACE_STATE_SHUTDOWN = BIT(2), + MLX5_INTERFACE_STATE_UP = BIT(0), }; enum mlx5_pci_status { diff --git a/include/linux/mm.h b/include/linux/mm.h index 46b9ac5e8569..c1f6c95f3496 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1260,6 +1260,7 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + unsigned long *start, unsigned long *end, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index c91b3bcd158f..7b2e31b1745a 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -95,17 +95,6 @@ struct mmu_notifier_ops { pte_t pte); /* - * Before this is invoked any secondary MMU is still ok to - * read/write to the page previously pointed to by the Linux - * pte because the page hasn't been freed yet and it won't be - * freed until this returns. If required set_page_dirty has to - * be called internally to this method. - */ - void (*invalidate_page)(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address); - - /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_sem and/or the * locks protecting the reverse maps are held. If the subsystem @@ -220,8 +209,6 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); -extern void __mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address); extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end); extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, @@ -268,13 +255,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm, __mmu_notifier_change_pte(mm, address, pte); } -static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address) -{ - if (mm_has_notifiers(mm)) - __mmu_notifier_invalidate_page(mm, address); -} - static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { @@ -442,11 +422,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm, { } -static inline void mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address) -{ -} - static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { diff --git a/include/linux/net.h b/include/linux/net.h index dda2cc939a53..ebeb48c92005 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -37,7 +37,7 @@ struct net; /* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. - * Eventually all flags will be in sk->sk_wq_flags. + * Eventually all flags will be in sk->sk_wq->flags. */ #define SOCKWQ_ASYNC_NOSPACE 0 #define SOCKWQ_ASYNC_WAITDATA 1 diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 779b23595596..c99ba7914c0a 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3866,6 +3866,8 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev, bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); +bool netdev_has_any_upper_dev(struct net_device *dev); + void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 8aa01fd859fb..a36abe2da13e 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -168,6 +168,14 @@ extern int sysctl_hardlockup_all_cpu_backtrace; #define sysctl_softlockup_all_cpu_backtrace 0 #define sysctl_hardlockup_all_cpu_backtrace 0 #endif + +#if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \ + defined(CONFIG_HARDLOCKUP_DETECTOR) +void watchdog_update_hrtimer_threshold(u64 period); +#else +static inline void watchdog_update_hrtimer_threshold(u64 period) { } +#endif + extern bool is_hardlockup(void); struct ctl_table; extern int proc_watchdog(struct ctl_table *, int , diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 25d8225dbd04..8efff888bd9b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -254,7 +254,7 @@ enum { NVME_CTRL_VWC_PRESENT = 1 << 0, NVME_CTRL_OACS_SEC_SUPP = 1 << 0, NVME_CTRL_OACS_DIRECTIVES = 1 << 5, - NVME_CTRL_OACS_DBBUF_SUPP = 1 << 7, + NVME_CTRL_OACS_DBBUF_SUPP = 1 << 8, }; struct nvme_lbaf { diff --git a/include/linux/oom.h b/include/linux/oom.h index 8a266e2be5a6..76aac4ce39bc 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -6,6 +6,8 @@ #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> +#include <linux/sched/coredump.h> /* MMF_* */ +#include <linux/mm.h> /* VM_FAULT* */ struct zonelist; struct notifier_block; @@ -63,6 +65,26 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk) return tsk->signal->oom_mm; } +/* + * Checks whether a page fault on the given mm is still reliable. + * This is no longer true if the oom reaper started to reap the + * address space which is reflected by MMF_UNSTABLE flag set in + * the mm. At that moment any !shared mapping would lose the content + * and could cause a memory corruption (zero pages instead of the + * original content). + * + * User should call this before establishing a page table entry for + * a !shared mapping and under the proper page table lock. + * + * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. + */ +static inline int check_stable_address_space(struct mm_struct *mm) +{ + if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) + return VM_FAULT_SIGBUS; + return 0; +} + extern unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, const nodemask_t *nodemask, unsigned long totalpages); diff --git a/include/linux/pci.h b/include/linux/pci.h index a75c13673852..f958d0732af6 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -188,6 +188,8 @@ enum pci_dev_flags { * the direct_complete optimization. */ PCI_DEV_FLAGS_NEEDS_RESUME = (__force pci_dev_flags_t) (1 << 11), + /* Don't use Relaxed Ordering for TLPs directed at this device */ + PCI_DEV_FLAGS_NO_RELAXED_ORDERING = (__force pci_dev_flags_t) (1 << 12), }; enum pci_irq_reroute_variant { @@ -1126,6 +1128,7 @@ bool pci_check_pme_status(struct pci_dev *dev); void pci_pme_wakeup_bus(struct pci_bus *bus); void pci_d3cold_enable(struct pci_dev *dev); void pci_d3cold_disable(struct pci_dev *dev); +bool pcie_relaxed_ordering_enabled(struct pci_dev *dev); /* PCI Virtual Channel */ int pci_save_vc_state(struct pci_dev *dev); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index a3b873fc59e4..c00cd4b02f32 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -310,8 +310,8 @@ struct pmu { * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ - void (*event_mapped) (struct perf_event *event); /*optional*/ - void (*event_unmapped) (struct perf_event *event); /*optional*/ + void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ + void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are @@ -1201,7 +1201,7 @@ extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, - struct task_struct *task); + struct task_struct *task, struct perf_event *event); extern void perf_bp_event(struct perf_event *event, void *data); #ifndef perf_misc_flags diff --git a/include/linux/pid.h b/include/linux/pid.h index 4d179316e431..719582744a2e 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -8,7 +8,9 @@ enum pid_type PIDTYPE_PID, PIDTYPE_PGID, PIDTYPE_SID, - PIDTYPE_MAX + PIDTYPE_MAX, + /* only valid to __task_pid_nr_ns() */ + __PIDTYPE_TGID }; /* diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index d8c97ec8a8e6..37b4bb2545b3 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -436,9 +436,9 @@ static inline int ptr_ring_consume_batched_bh(struct ptr_ring *r, __PTR_RING_PEEK_CALL_v; \ }) -static inline void **__ptr_ring_init_queue_alloc(int size, gfp_t gfp) +static inline void **__ptr_ring_init_queue_alloc(unsigned int size, gfp_t gfp) { - return kzalloc(ALIGN(size * sizeof(void *), SMP_CACHE_BYTES), gfp); + return kcalloc(size, sizeof(void *), gfp); } static inline void __ptr_ring_set_size(struct ptr_ring *r, int size) @@ -582,7 +582,8 @@ static inline int ptr_ring_resize(struct ptr_ring *r, int size, gfp_t gfp, * In particular if you consume ring in interrupt or BH context, you must * disable interrupts/BH when doing so. */ -static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, +static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, + unsigned int nrings, int size, gfp_t gfp, void (*destroy)(void *)) { @@ -590,7 +591,7 @@ static inline int ptr_ring_resize_multiple(struct ptr_ring **rings, int nrings, void ***queues; int i; - queues = kmalloc(nrings * sizeof *queues, gfp); + queues = kmalloc_array(nrings, sizeof(*queues), gfp); if (!queues) goto noqueues; diff --git a/include/linux/sched.h b/include/linux/sched.h index 8337e2db0bb2..c05ac5f5aa03 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1163,13 +1163,6 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk) return tsk->tgid; } -extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns); - -static inline pid_t task_tgid_vnr(struct task_struct *tsk) -{ - return pid_vnr(task_tgid(tsk)); -} - /** * pid_alive - check that a task structure is not stale * @p: Task structure to be checked. @@ -1185,23 +1178,6 @@ static inline int pid_alive(const struct task_struct *p) return p->pids[PIDTYPE_PID].pid != NULL; } -static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) -{ - pid_t pid = 0; - - rcu_read_lock(); - if (pid_alive(tsk)) - pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); - rcu_read_unlock(); - - return pid; -} - -static inline pid_t task_ppid_nr(const struct task_struct *tsk) -{ - return task_ppid_nr_ns(tsk, &init_pid_ns); -} - static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) { return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns); @@ -1223,6 +1199,33 @@ static inline pid_t task_session_vnr(struct task_struct *tsk) return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL); } +static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns); +} + +static inline pid_t task_tgid_vnr(struct task_struct *tsk) +{ + return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL); +} + +static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns) +{ + pid_t pid = 0; + + rcu_read_lock(); + if (pid_alive(tsk)) + pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns); + rcu_read_unlock(); + + return pid; +} + +static inline pid_t task_ppid_nr(const struct task_struct *tsk) +{ + return task_ppid_nr_ns(tsk, &init_pid_ns); +} + /* Obsolete, do not use: */ static inline pid_t task_pgrp_nr(struct task_struct *tsk) { diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h index 35226cd4efb0..8621ffdeecbf 100644 --- a/include/linux/skb_array.h +++ b/include/linux/skb_array.h @@ -193,7 +193,8 @@ static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) } static inline int skb_array_resize_multiple(struct skb_array **rings, - int nrings, int size, gfp_t gfp) + int nrings, unsigned int size, + gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); return ptr_ring_resize_multiple((struct ptr_ring **)rings, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index dbe29b6c9bd6..d67a8182e5eb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -973,7 +973,23 @@ int __must_check skb_to_sgvec_nomark(struct sk_buff *skb, struct scatterlist *sg int __must_check skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len); int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer); -int skb_pad(struct sk_buff *skb, int pad); +int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error); + +/** + * skb_pad - zero pad the tail of an skb + * @skb: buffer to pad + * @pad: space to pad + * + * Ensure that a buffer is followed by a padding area that is zero + * filled. Used by network drivers which may DMA or transfer data + * beyond the buffer end onto the wire. + * + * May return error in out of memory cases. The skb is freed on error. + */ +static inline int skb_pad(struct sk_buff *skb, int pad) +{ + return __skb_pad(skb, pad, true); +} #define dev_kfree_skb(a) consume_skb(a) int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, @@ -2825,25 +2841,42 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length + * @free_on_error: free buffer on error * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it * is untouched. Otherwise it is extended. Returns zero on - * success. The skb is freed on error. + * success. The skb is freed on error if @free_on_error is true. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, + bool free_on_error) { unsigned int size = skb->len; if (unlikely(size < len)) { len -= size; - if (skb_pad(skb, len)) + if (__skb_pad(skb, len, free_on_error)) return -ENOMEM; __skb_put(skb, len); } return 0; } +/** + * skb_put_padto - increase size and pad an skbuff up to a minimal size + * @skb: buffer to pad + * @len: minimal length + * + * Pads up a buffer to ensure the trailing bytes exist and are + * blanked. If the buffer already contains sufficient data it + * is untouched. Otherwise it is extended. Returns zero on + * success. The skb is freed on error. + */ +static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +{ + return __skb_put_padto(skb, len, true); +} + static inline int skb_add_data(struct sk_buff *skb, struct iov_iter *from, int copy) { diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3cb15ea48aee..138c94535864 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -100,11 +100,12 @@ union bpf_attr; #define __MAP(n,...) __MAP##n(__VA_ARGS__) #define __SC_DECL(t, a) t a -#define __TYPE_IS_L(t) (__same_type((t)0, 0L)) -#define __TYPE_IS_UL(t) (__same_type((t)0, 0UL)) -#define __TYPE_IS_LL(t) (__same_type((t)0, 0LL) || __same_type((t)0, 0ULL)) +#define __TYPE_AS(t, v) __same_type((__force t)0, v) +#define __TYPE_IS_L(t) (__TYPE_AS(t, 0L)) +#define __TYPE_IS_UL(t) (__TYPE_AS(t, 0UL)) +#define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a -#define __SC_CAST(t, a) (t) a +#define __SC_CAST(t, a) (__force t) a #define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long)) @@ -578,12 +579,12 @@ asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_preadv2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h); asmlinkage long sys_pwritev2(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, unsigned long pos_l, unsigned long pos_h, - int flags); + rwf_t flags); asmlinkage long sys_getcwd(char __user *buf, unsigned long size); asmlinkage long sys_mkdir(const char __user *pathname, umode_t mode); asmlinkage long sys_chdir(const char __user *filename); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 536c80ff7ad9..5012b524283d 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -508,9 +508,9 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, static inline void perf_trace_buf_submit(void *raw_data, int size, int rctx, u16 type, u64 count, struct pt_regs *regs, void *head, - struct task_struct *task) + struct task_struct *task, struct perf_event *event) { - perf_tp_event(type, count, raw_data, size, regs, head, rctx, task); + perf_tp_event(type, count, raw_data, size, regs, head, rctx, task, event); } #endif diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index acdd6f915a8d..20ef8e6ec2db 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -156,7 +156,7 @@ copy_to_user(void __user *to, const void *from, unsigned long n) } #ifdef CONFIG_COMPAT static __always_inline unsigned long __must_check -copy_in_user(void __user *to, const void *from, unsigned long n) +copy_in_user(void __user *to, const void __user *from, unsigned long n) { might_fault(); if (access_ok(VERIFY_WRITE, to, n) && access_ok(VERIFY_READ, from, n)) diff --git a/include/linux/wait.h b/include/linux/wait.h index 5b74e36c0ca8..dc19880c02f5 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -757,6 +757,43 @@ extern int do_wait_intr_irq(wait_queue_head_t *, wait_queue_entry_t *); __ret; \ }) +#define __wait_event_killable_timeout(wq_head, condition, timeout) \ + ___wait_event(wq_head, ___wait_cond_timeout(condition), \ + TASK_KILLABLE, 0, timeout, \ + __ret = schedule_timeout(__ret)) + +/** + * wait_event_killable_timeout - sleep until a condition gets true or a timeout elapses + * @wq_head: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_KILLABLE) until the + * @condition evaluates to true or a kill signal is received. + * The @condition is checked each time the waitqueue @wq_head is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * Returns: + * 0 if the @condition evaluated to %false after the @timeout elapsed, + * 1 if the @condition evaluated to %true after the @timeout elapsed, + * the remaining jiffies (at least 1) if the @condition evaluated + * to %true before the @timeout elapsed, or -%ERESTARTSYS if it was + * interrupted by a kill signal. + * + * Only kill signals interrupt this process. + */ +#define wait_event_killable_timeout(wq_head, condition, timeout) \ +({ \ + long __ret = timeout; \ + might_sleep(); \ + if (!___wait_cond_timeout(condition)) \ + __ret = __wait_event_killable_timeout(wq_head, \ + condition, timeout); \ + __ret; \ +}) + #define __wait_event_lock_irq(wq_head, condition, lock, cmd) \ (void)___wait_event(wq_head, condition, TASK_UNINTERRUPTIBLE, 0, 0, \ diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 6df79e96a780..f44ff2476758 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -336,6 +336,16 @@ static inline void in6_dev_put(struct inet6_dev *idev) in6_dev_finish_destroy(idev); } +static inline void in6_dev_put_clear(struct inet6_dev **pidev) +{ + struct inet6_dev *idev = *pidev; + + if (idev) { + in6_dev_put(idev); + *pidev = NULL; + } +} + static inline void __in6_dev_put(struct inet6_dev *idev) { refcount_dec(&idev->refcnt); diff --git a/include/net/bonding.h b/include/net/bonding.h index b00508d22e0a..b2e68657a216 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -277,6 +277,11 @@ static inline bool bond_is_lb(const struct bonding *bond) BOND_MODE(bond) == BOND_MODE_ALB; } +static inline bool bond_needs_speed_duplex(const struct bonding *bond) +{ + return BOND_MODE(bond) == BOND_MODE_8023AD || bond_is_lb(bond); +} + static inline bool bond_is_nondyn_tlb(const struct bonding *bond) { return (BOND_MODE(bond) == BOND_MODE_TLB) && diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 8ffd434676b7..71c72a939bf8 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -29,18 +29,18 @@ #include <linux/sched/signal.h> #include <net/ip.h> -#ifdef CONFIG_NET_RX_BUSY_POLL - -struct napi_struct; -extern unsigned int sysctl_net_busy_read __read_mostly; -extern unsigned int sysctl_net_busy_poll __read_mostly; - /* 0 - Reserved to indicate value not set * 1..NR_CPUS - Reserved for sender_cpu * NR_CPUS+1..~0 - Region available for NAPI IDs */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) +#ifdef CONFIG_NET_RX_BUSY_POLL + +struct napi_struct; +extern unsigned int sysctl_net_busy_read __read_mostly; +extern unsigned int sysctl_net_busy_poll __read_mostly; + static inline bool net_busy_loop_on(void) { return sysctl_net_busy_poll; diff --git a/include/net/ip.h b/include/net/ip.h index 821cedcc8e73..0cf7f5a65fe6 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -352,7 +352,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, !forwarding) return dst_mtu(dst); - return min(dst->dev->mtu, IP_MAX_MTU); + return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); } static inline unsigned int ip_skb_dst_mtu(struct sock *sk, @@ -364,7 +364,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk, return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding); } - return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU); + return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); } u32 ip_idents_reserve(u32 hash, int segs); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 1a88008cc6f5..af509f801084 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -70,6 +70,7 @@ struct fib6_node { __u16 fn_flags; int fn_sernum; struct rt6_info *rr_ptr; + struct rcu_head rcu; }; #ifndef CONFIG_IPV6_SUBTREES @@ -104,7 +105,7 @@ struct rt6_info { * the same cache line. */ struct fib6_table *rt6i_table; - struct fib6_node *rt6i_node; + struct fib6_node __rcu *rt6i_node; struct in6_addr rt6i_gateway; @@ -167,13 +168,40 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) rt0->rt6i_flags |= RTF_EXPIRES; } +/* Function to safely get fn->sernum for passed in rt + * and store result in passed in cookie. + * Return true if we can get cookie safely + * Return false if not + */ +static inline bool rt6_get_cookie_safe(const struct rt6_info *rt, + u32 *cookie) +{ + struct fib6_node *fn; + bool status = false; + + rcu_read_lock(); + fn = rcu_dereference(rt->rt6i_node); + + if (fn) { + *cookie = fn->fn_sernum; + status = true; + } + + rcu_read_unlock(); + return status; +} + static inline u32 rt6_get_cookie(const struct rt6_info *rt) { + u32 cookie = 0; + if (rt->rt6i_flags & RTF_PCPU || (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->dst.from)) rt = (struct rt6_info *)(rt->dst.from); - return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; + rt6_get_cookie_safe(rt, &cookie); + + return cookie; } static inline void ip6_rt_put(struct rt6_info *rt) diff --git a/include/net/mac80211.h b/include/net/mac80211.h index b2b5419467cc..f8149ca192b4 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -5499,6 +5499,21 @@ static inline void ieee80211_stop_rx_ba_session_offl(struct ieee80211_vif *vif, ieee80211_manage_rx_ba_offl(vif, addr, tid + IEEE80211_NUM_TIDS); } +/** + * ieee80211_rx_ba_timer_expired - stop a Rx BA session due to timeout + * + * Some device drivers do not offload AddBa/DelBa negotiation, but handle rx + * buffer reording internally, and therefore also handle the session timer. + * + * Trigger the timeout flow, which sends a DelBa. + * + * @vif: &struct ieee80211_vif pointer from the add_interface callback + * @addr: station mac address + * @tid: the rx tid + */ +void ieee80211_rx_ba_timer_expired(struct ieee80211_vif *vif, + const u8 *addr, unsigned int tid); + /* Rate control API */ /** diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 1c123e2b2415..c1109cdbbfa6 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -101,6 +101,13 @@ struct Qdisc { spinlock_t busylock ____cacheline_aligned_in_smp; }; +static inline void qdisc_refcount_inc(struct Qdisc *qdisc) +{ + if (qdisc->flags & TCQ_F_BUILTIN) + return; + refcount_inc(&qdisc->refcnt); +} + static inline bool qdisc_is_running(const struct Qdisc *qdisc) { return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; @@ -806,8 +813,11 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new, old = *pold; *pold = new; if (old != NULL) { - qdisc_tree_reduce_backlog(old, old->q.qlen, old->qstats.backlog); + unsigned int qlen = old->q.qlen; + unsigned int backlog = old->qstats.backlog; + qdisc_reset(old); + qdisc_tree_reduce_backlog(old, qlen, backlog); } sch_tree_unlock(sch); diff --git a/include/net/sock.h b/include/net/sock.h index 7c0632c7e870..aeeec62992ca 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -507,9 +507,7 @@ int sk_set_peek_off(struct sock *sk, int val); static inline int sk_peek_offset(struct sock *sk, int flags) { if (unlikely(flags & MSG_PEEK)) { - s32 off = READ_ONCE(sk->sk_peek_off); - if (off >= 0) - return off; + return READ_ONCE(sk->sk_peek_off); } return 0; diff --git a/include/net/tcp.h b/include/net/tcp.h index ada65e767b28..f642a39f9eee 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1004,9 +1004,7 @@ void tcp_get_default_congestion_control(char *name); void tcp_get_available_congestion_control(char *buf, size_t len); void tcp_get_allowed_congestion_control(char *buf, size_t len); int tcp_set_allowed_congestion_control(char *allowed); -int tcp_set_congestion_control(struct sock *sk, const char *name, bool load); -void tcp_reinit_congestion_control(struct sock *sk, - const struct tcp_congestion_ops *ca); +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit); u32 tcp_slow_start(struct tcp_sock *tp, u32 acked); void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked); diff --git a/include/net/udp.h b/include/net/udp.h index cc8036987dcb..626c2d8a70c5 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -260,7 +260,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, } void udp_v4_early_demux(struct sk_buff *skb); -void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); +bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, const struct sock *)); @@ -366,12 +366,13 @@ static inline bool udp_skb_is_linear(struct sk_buff *skb) static inline int copy_linear_skb(struct sk_buff *skb, int len, int off, struct iov_iter *to) { - int n, copy = len - off; + int n; - n = copy_to_iter(skb->data + off, copy, to); - if (n == copy) + n = copy_to_iter(skb->data + off, len, to); + if (n == len) return 0; + iov_iter_revert(to, n); return -EFAULT; } diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index b5732432bb29..88c32aba32f7 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1683,6 +1683,7 @@ struct ib_qp { enum ib_qp_type qp_type; struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; + u8 port; }; struct ib_mr { diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h index a1266d318c85..6af198d8120b 100644 --- a/include/scsi/scsi_cmnd.h +++ b/include/scsi/scsi_cmnd.h @@ -57,6 +57,7 @@ struct scsi_pointer { /* for scmd->flags */ #define SCMD_TAGGED (1 << 0) #define SCMD_UNCHECKED_ISA_DMA (1 << 1) +#define SCMD_ZONE_WRITE_LOCK (1 << 2) struct scsi_cmnd { struct scsi_request req; diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h index a2d4a8ac94ca..a04adbc70ddf 100644 --- a/include/uapi/linux/aio_abi.h +++ b/include/uapi/linux/aio_abi.h @@ -28,6 +28,7 @@ #define __LINUX__AIO_ABI_H #include <linux/types.h> +#include <linux/fs.h> #include <asm/byteorder.h> typedef __kernel_ulong_t aio_context_t; @@ -62,14 +63,6 @@ struct io_event { __s64 res2; /* secondary result */ }; -#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) -#define PADDED(x,y) x, y -#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) -#define PADDED(x,y) y, x -#else -#error edit for your odd byteorder. -#endif - /* * we always use a 64bit off_t when communicating * with userland. its up to libraries to do the @@ -79,8 +72,16 @@ struct io_event { struct iocb { /* these are internal to the kernel/libc. */ __u64 aio_data; /* data to be returned in event's data */ - __u32 PADDED(aio_key, aio_rw_flags); - /* the kernel sets aio_key to the req # */ + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) + __u32 aio_key; /* the kernel sets aio_key to the req # */ + __kernel_rwf_t aio_rw_flags; /* RWF_* flags */ +#elif defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) + __kernel_rwf_t aio_rw_flags; /* RWF_* flags */ + __u32 aio_key; /* the kernel sets aio_key to the req # */ +#else +#error edit for your odd byteorder. +#endif /* common fields */ __u16 aio_lio_opcode; /* see IOCB_CMD_ above */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index b7495d05e8de..56235dddea7d 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -358,13 +358,25 @@ struct fscrypt_key { #define SYNC_FILE_RANGE_WRITE 2 #define SYNC_FILE_RANGE_WAIT_AFTER 4 -/* flags for preadv2/pwritev2: */ -#define RWF_HIPRI 0x00000001 /* high priority request, poll if possible */ -#define RWF_DSYNC 0x00000002 /* per-IO O_DSYNC */ -#define RWF_SYNC 0x00000004 /* per-IO O_SYNC */ -#define RWF_NOWAIT 0x00000008 /* per-IO, return -EAGAIN if operation would block */ - -#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC |\ - RWF_NOWAIT) +/* + * Flags for preadv2/pwritev2: + */ + +typedef int __bitwise __kernel_rwf_t; + +/* high priority request, poll if possible */ +#define RWF_HIPRI ((__force __kernel_rwf_t)0x00000001) + +/* per-IO O_DSYNC */ +#define RWF_DSYNC ((__force __kernel_rwf_t)0x00000002) + +/* per-IO O_SYNC */ +#define RWF_SYNC ((__force __kernel_rwf_t)0x00000004) + +/* per-IO, return -EAGAIN if operation would block */ +#define RWF_NOWAIT ((__force __kernel_rwf_t)0x00000008) + +/* mask of flags supported by the kernel */ +#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT) #endif /* _UAPI_LINUX_FS_H */ diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index a3960f98679c..c8125ec1f4f2 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -22,7 +22,6 @@ enum { LO_FLAGS_AUTOCLEAR = 4, LO_FLAGS_PARTSCAN = 8, LO_FLAGS_DIRECT_IO = 16, - LO_FLAGS_BLOCKSIZE = 32, }; #include <asm/posix_types.h> /* for __kernel_old_dev_t */ @@ -60,8 +59,6 @@ struct loop_info64 { __u64 lo_init[2]; }; -#define LO_INFO_BLOCKSIZE(l) (l)->lo_init[0] - /* * Loop filter types */ diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 6d3c54264d8e..3f03567631cb 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -145,43 +145,6 @@ struct nd_cmd_clear_error { __u64 cleared; } __packed; -struct nd_cmd_trans_spa { - __u64 spa; - __u32 status; - __u8 flags; - __u8 _reserved[3]; - __u64 trans_length; - __u32 num_nvdimms; - struct nd_nvdimm_device { - __u32 nfit_device_handle; - __u32 _reserved; - __u64 dpa; - } __packed devices[0]; - -} __packed; - -struct nd_cmd_ars_err_inj { - __u64 err_inj_spa_range_base; - __u64 err_inj_spa_range_length; - __u8 err_inj_options; - __u32 status; -} __packed; - -struct nd_cmd_ars_err_inj_clr { - __u64 err_inj_clr_spa_range_base; - __u64 err_inj_clr_spa_range_length; - __u32 status; -} __packed; - -struct nd_cmd_ars_err_inj_stat { - __u32 status; - __u32 inj_err_rec_count; - struct nd_error_stat_query_record { - __u64 err_inj_stat_spa_range_base; - __u64 err_inj_stat_spa_range_length; - } __packed record[0]; -} __packed; - enum { ND_CMD_IMPLEMENTED = 0, diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 62d686d96581..9eb8b3511636 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -66,7 +66,7 @@ static struct fsnotify_group *audit_watch_group; /* fsnotify events we care about. */ #define AUDIT_FS_WATCH (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF |\ - FS_MOVE_SELF | FS_EVENT_ON_CHILD) + FS_MOVE_SELF | FS_EVENT_ON_CHILD | FS_UNMOUNT) static void audit_free_parent(struct audit_parent *parent) { @@ -457,13 +457,15 @@ void audit_remove_watch_rule(struct audit_krule *krule) list_del(&krule->rlist); if (list_empty(&watch->rules)) { + /* + * audit_remove_watch() drops our reference to 'parent' which + * can get freed. Grab our own reference to be safe. + */ + audit_get_parent(parent); audit_remove_watch(watch); - - if (list_empty(&parent->watches)) { - audit_get_parent(parent); + if (list_empty(&parent->watches)) fsnotify_destroy_mark(&parent->mark, audit_watch_group); - audit_put_parent(parent); - } + audit_put_parent(parent); } } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4fb463172aa8..d11c8181f4c5 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -652,12 +652,27 @@ static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, } } +static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) +{ + return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && + BITS_PER_LONG == 64; +} + +static u32 htab_size_value(const struct bpf_htab *htab, bool percpu) +{ + u32 size = htab->map.value_size; + + if (percpu || fd_htab_map_needs_adjust(htab)) + size = round_up(size, 8); + return size; +} + static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, bool percpu, bool onallcpus, struct htab_elem *old_elem) { - u32 size = htab->map.value_size; + u32 size = htab_size_value(htab, percpu); bool prealloc = htab_is_prealloc(htab); struct htab_elem *l_new, **pl_new; void __percpu *pptr; @@ -696,9 +711,6 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, memcpy(l_new->key, key, key_size); if (percpu) { - /* round up value_size to 8 bytes */ - size = round_up(size, 8); - if (prealloc) { pptr = htab_elem_get_ptr(l_new, key_size); } else { @@ -1209,17 +1221,9 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { static struct bpf_map *fd_htab_map_alloc(union bpf_attr *attr) { - struct bpf_map *map; - if (attr->value_size != sizeof(u32)) return ERR_PTR(-EINVAL); - - /* pointer is stored internally */ - attr->value_size = sizeof(void *); - map = htab_map_alloc(attr); - attr->value_size = sizeof(u32); - - return map; + return htab_map_alloc(attr); } static void fd_htab_map_free(struct bpf_map *map) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 8d5151688504..87a1213dd326 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1892,6 +1892,7 @@ static struct cftype files[] = { { .name = "memory_pressure", .read_u64 = cpuset_read_u64, + .private = FILE_MEMORY_PRESSURE, }, { diff --git a/kernel/events/core.c b/kernel/events/core.c index 426c2ffba16d..03ac9c8b02fb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2217,6 +2217,33 @@ static int group_can_go_on(struct perf_event *event, return can_add_hw; } +/* + * Complement to update_event_times(). This computes the tstamp_* values to + * continue 'enabled' state from @now, and effectively discards the time + * between the prior tstamp_stopped and now (as we were in the OFF state, or + * just switched (context) time base). + * + * This further assumes '@event->state == INACTIVE' (we just came from OFF) and + * cannot have been scheduled in yet. And going into INACTIVE state means + * '@event->tstamp_stopped = @now'. + * + * Thus given the rules of update_event_times(): + * + * total_time_enabled = tstamp_stopped - tstamp_enabled + * total_time_running = tstamp_stopped - tstamp_running + * + * We can insert 'tstamp_stopped == now' and reverse them to compute new + * tstamp_* values. + */ +static void __perf_event_enable_time(struct perf_event *event, u64 now) +{ + WARN_ON_ONCE(event->state != PERF_EVENT_STATE_INACTIVE); + + event->tstamp_stopped = now; + event->tstamp_enabled = now - event->total_time_enabled; + event->tstamp_running = now - event->total_time_running; +} + static void add_event_to_ctx(struct perf_event *event, struct perf_event_context *ctx) { @@ -2224,9 +2251,12 @@ static void add_event_to_ctx(struct perf_event *event, list_add_event(event, ctx); perf_group_attach(event); - event->tstamp_enabled = tstamp; - event->tstamp_running = tstamp; - event->tstamp_stopped = tstamp; + /* + * We can be called with event->state == STATE_OFF when we create with + * .disabled = 1. In that case the IOC_ENABLE will call this function. + */ + if (event->state == PERF_EVENT_STATE_INACTIVE) + __perf_event_enable_time(event, tstamp); } static void ctx_sched_out(struct perf_event_context *ctx, @@ -2471,10 +2501,11 @@ static void __perf_event_mark_enabled(struct perf_event *event) u64 tstamp = perf_event_time(event); event->state = PERF_EVENT_STATE_INACTIVE; - event->tstamp_enabled = tstamp - event->total_time_enabled; + __perf_event_enable_time(event, tstamp); list_for_each_entry(sub, &event->sibling_list, group_entry) { + /* XXX should not be > INACTIVE if event isn't */ if (sub->state >= PERF_EVENT_STATE_INACTIVE) - sub->tstamp_enabled = tstamp - sub->total_time_enabled; + __perf_event_enable_time(sub, tstamp); } } @@ -5090,7 +5121,7 @@ static void perf_mmap_open(struct vm_area_struct *vma) atomic_inc(&event->rb->aux_mmap_count); if (event->pmu->event_mapped) - event->pmu->event_mapped(event); + event->pmu->event_mapped(event, vma->vm_mm); } static void perf_pmu_output_stop(struct perf_event *event); @@ -5113,7 +5144,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) unsigned long size = perf_data_size(rb); if (event->pmu->event_unmapped) - event->pmu->event_unmapped(event); + event->pmu->event_unmapped(event, vma->vm_mm); /* * rb->aux_mmap_count will always drop before rb->mmap_count and @@ -5411,7 +5442,7 @@ aux_unlock: vma->vm_ops = &perf_mmap_vmops; if (event->pmu->event_mapped) - event->pmu->event_mapped(event); + event->pmu->event_mapped(event, vma->vm_mm); return ret; } @@ -7875,16 +7906,15 @@ void perf_trace_run_bpf_submit(void *raw_data, int size, int rctx, } } perf_tp_event(call->event.type, count, raw_data, size, regs, head, - rctx, task); + rctx, task, NULL); } EXPORT_SYMBOL_GPL(perf_trace_run_bpf_submit); void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, - struct task_struct *task) + struct task_struct *task, struct perf_event *event) { struct perf_sample_data data; - struct perf_event *event; struct perf_raw_record raw = { .frag = { @@ -7898,9 +7928,15 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, perf_trace_buf_update(record, event_type); - hlist_for_each_entry_rcu(event, head, hlist_entry) { + /* Use the given event instead of the hlist */ + if (event) { if (perf_tp_event_match(event, &data, regs)) perf_swevent_event(event, count, &data, regs); + } else { + hlist_for_each_entry_rcu(event, head, hlist_entry) { + if (perf_tp_event_match(event, &data, regs)) + perf_swevent_event(event, count, &data, regs); + } } /* @@ -9580,6 +9616,8 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, if (ret) return -EFAULT; + attr->size = size; + if (attr->__reserved_1) return -EINVAL; @@ -10001,28 +10039,27 @@ SYSCALL_DEFINE5(perf_event_open, goto err_context; /* - * Do not allow to attach to a group in a different - * task or CPU context: + * Make sure we're both events for the same CPU; + * grouping events for different CPUs is broken; since + * you can never concurrently schedule them anyhow. */ - if (move_group) { - /* - * Make sure we're both on the same task, or both - * per-cpu events. - */ - if (group_leader->ctx->task != ctx->task) - goto err_context; + if (group_leader->cpu != event->cpu) + goto err_context; - /* - * Make sure we're both events for the same CPU; - * grouping events for different CPUs is broken; since - * you can never concurrently schedule them anyhow. - */ - if (group_leader->cpu != event->cpu) - goto err_context; - } else { - if (group_leader->ctx != ctx) - goto err_context; - } + /* + * Make sure we're both on the same task, or both + * per-CPU events. + */ + if (group_leader->ctx->task != ctx->task) + goto err_context; + + /* + * Do not allow to attach to a group in a different task + * or CPU context. If we're moving SW events, we'll fix + * this up later, so allow that. + */ + if (!move_group && group_leader->ctx != ctx) + goto err_context; /* * Only a group leader can be exclusive or pinned diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 0e137f98a50c..267f6ef91d97 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -1262,8 +1262,6 @@ void uprobe_end_dup_mmap(void) void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { - newmm->uprobes_state.xol_area = NULL; - if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { set_bit(MMF_HAS_UPROBES, &newmm->flags); /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ diff --git a/kernel/fork.c b/kernel/fork.c index e075b7780421..b7e9e57b71ea 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -785,6 +785,13 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } +static void mm_init_uprobes_state(struct mm_struct *mm) +{ +#ifdef CONFIG_UPROBES + mm->uprobes_state.xol_area = NULL; +#endif +} + static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { @@ -806,11 +813,13 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); + RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_mm_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS mm->pmd_huge_pte = NULL; #endif + mm_init_uprobes_state(mm); if (current->mm) { mm->flags = current->mm->flags & MMF_INIT_MASK; diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index a3cc37c0c85e..3675c6004f2a 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -1000,7 +1000,7 @@ EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name); void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) { - unsigned long flags; + unsigned long flags, trigger, tmp; struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0); if (!desc) @@ -1014,6 +1014,8 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) irq_settings_clr_and_set(desc, clr, set); + trigger = irqd_get_trigger_type(&desc->irq_data); + irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU | IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT); if (irq_settings_has_no_balance_set(desc)) @@ -1025,7 +1027,11 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) if (irq_settings_is_level(desc)) irqd_set(&desc->irq_data, IRQD_LEVEL); - irqd_set(&desc->irq_data, irq_settings_get_trigger_mask(desc)); + tmp = irq_settings_get_trigger_mask(desc); + if (tmp != IRQ_TYPE_NONE) + trigger = tmp; + + irqd_set(&desc->irq_data, trigger); irq_put_desc_unlock(desc, flags); } diff --git a/kernel/irq/ipi.c b/kernel/irq/ipi.c index 1a9abc1c8ea0..259a22aa9934 100644 --- a/kernel/irq/ipi.c +++ b/kernel/irq/ipi.c @@ -165,7 +165,7 @@ irq_hw_number_t ipi_get_hwirq(unsigned int irq, unsigned int cpu) struct irq_data *data = irq_get_irq_data(irq); struct cpumask *ipimask = data ? irq_data_get_affinity_mask(data) : NULL; - if (!data || !ipimask || cpu > nr_cpu_ids) + if (!data || !ipimask || cpu >= nr_cpu_ids) return INVALID_HWIRQ; if (!cpumask_test_cpu(cpu, ipimask)) @@ -195,7 +195,7 @@ static int ipi_send_verify(struct irq_chip *chip, struct irq_data *data, if (!chip->ipi_send_single && !chip->ipi_send_mask) return -EINVAL; - if (cpu > nr_cpu_ids) + if (cpu >= nr_cpu_ids) return -EINVAL; if (dest) { diff --git a/kernel/kmod.c b/kernel/kmod.c index 6d016c5d97c8..2f37acde640b 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -71,6 +71,18 @@ static atomic_t kmod_concurrent_max = ATOMIC_INIT(MAX_KMOD_CONCURRENT); static DECLARE_WAIT_QUEUE_HEAD(kmod_wq); /* + * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads + * running at the same time without returning. When this happens we + * believe you've somehow ended up with a recursive module dependency + * creating a loop. + * + * We have no option but to fail. + * + * Userspace should proactively try to detect and prevent these. + */ +#define MAX_KMOD_ALL_BUSY_TIMEOUT 5 + +/* modprobe_path is set via /proc/sys. */ char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe"; @@ -167,8 +179,17 @@ int __request_module(bool wait, const char *fmt, ...) pr_warn_ratelimited("request_module: kmod_concurrent_max (%u) close to 0 (max_modprobes: %u), for module %s, throttling...", atomic_read(&kmod_concurrent_max), MAX_KMOD_CONCURRENT, module_name); - wait_event_interruptible(kmod_wq, - atomic_dec_if_positive(&kmod_concurrent_max) >= 0); + ret = wait_event_killable_timeout(kmod_wq, + atomic_dec_if_positive(&kmod_concurrent_max) >= 0, + MAX_KMOD_ALL_BUSY_TIMEOUT * HZ); + if (!ret) { + pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now", + module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT); + return -ETIME; + } else if (ret == -ERESTARTSYS) { + pr_warn_ratelimited("request_module: sigkill sent for modprobe %s, giving up", module_name); + return ret; + } } trace_module_request(module_name, wait, _RET_IP_); diff --git a/kernel/kthread.c b/kernel/kthread.c index 26db528c1d88..1c19edf82427 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -637,6 +637,7 @@ repeat: schedule(); try_to_freeze(); + cond_resched(); goto repeat; } EXPORT_SYMBOL_GPL(kthread_worker_fn); diff --git a/kernel/pid.c b/kernel/pid.c index c69c30d827e5..020dedbdf066 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -527,8 +527,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, if (!ns) ns = task_active_pid_ns(current); if (likely(pid_alive(task))) { - if (type != PIDTYPE_PID) + if (type != PIDTYPE_PID) { + if (type == __PIDTYPE_TGID) + type = PIDTYPE_PID; task = task->group_leader; + } nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns); } rcu_read_unlock(); @@ -537,12 +540,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type, } EXPORT_SYMBOL(__task_pid_nr_ns); -pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns) -{ - return pid_nr_ns(task_tgid(tsk), ns); -} -EXPORT_SYMBOL(task_tgid_nr_ns); - struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) { return ns_of_pid(task_pid(tsk)); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 17f11c6b0a9f..d6afed6d0752 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -70,9 +70,10 @@ static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode, list_for_each_entry_safe(curr, next, &wq_head->head, entry) { unsigned flags = curr->flags; - - if (curr->func(curr, mode, wake_flags, key) && - (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) + int ret = curr->func(curr, mode, wake_flags, key); + if (ret < 0) + break; + if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) break; } } diff --git a/kernel/signal.c b/kernel/signal.c index 7e33f8c583e6..ed804a470dcd 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1194,7 +1194,11 @@ force_sig_info(int sig, struct siginfo *info, struct task_struct *t) recalc_sigpending_and_wake(t); } } - if (action->sa.sa_handler == SIG_DFL) + /* + * Don't clear SIGNAL_UNKILLABLE for traced tasks, users won't expect + * debugging to leave init killable. + */ + if (action->sa.sa_handler == SIG_DFL && !t->ptrace) t->signal->flags &= ~SIGNAL_UNKILLABLE; ret = specific_send_sig_info(sig, info, t); spin_unlock_irqrestore(&t->sighand->siglock, flags); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index cedafa008de5..7e7e61c00d61 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -637,9 +637,7 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) tk->ktime_sec = seconds; /* Update the monotonic raw base */ - seconds = tk->raw_sec; - nsec = (u32)(tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift); - tk->tkr_raw.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); + tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 8f5d1bf18854..f2674a056c26 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -203,6 +203,7 @@ struct timer_base { bool migration_enabled; bool nohz_active; bool is_idle; + bool must_forward_clk; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; @@ -856,13 +857,19 @@ get_target_base(struct timer_base *base, unsigned tflags) static inline void forward_timer_base(struct timer_base *base) { - unsigned long jnow = READ_ONCE(jiffies); + unsigned long jnow; /* - * We only forward the base when it's idle and we have a delta between - * base clock and jiffies. + * We only forward the base when we are idle or have just come out of + * idle (must_forward_clk logic), and have a delta between base clock + * and jiffies. In the common case, run_timers will take care of it. */ - if (!base->is_idle || (long) (jnow - base->clk) < 2) + if (likely(!base->must_forward_clk)) + return; + + jnow = READ_ONCE(jiffies); + base->must_forward_clk = base->is_idle; + if ((long)(jnow - base->clk) < 2) return; /* @@ -938,6 +945,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * same array bucket then just return: */ if (timer_pending(timer)) { + /* + * The downside of this optimization is that it can result in + * larger granularity than you would get from adding a new + * timer with this expiry. + */ if (timer->expires == expires) return 1; @@ -948,6 +960,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); + forward_timer_base(base); clk = base->clk; idx = calc_wheel_index(expires, clk); @@ -964,6 +977,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) } } else { base = lock_timer_base(timer, &flags); + forward_timer_base(base); } ret = detach_if_pending(timer, base, false); @@ -991,12 +1005,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); + forward_timer_base(base); } } - /* Try to forward a stale timer base clock */ - forward_timer_base(base); - timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance @@ -1112,6 +1124,7 @@ void add_timer_on(struct timer_list *timer, int cpu) WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } + forward_timer_base(base); debug_activate(timer, timer->expires); internal_add_timer(base, timer); @@ -1497,10 +1510,16 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) if (!is_max_delta) expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* - * If we expect to sleep more than a tick, mark the base idle: + * If we expect to sleep more than a tick, mark the base idle. + * Also the tick is stopped so any added timer must forward + * the base clk itself to keep granularity small. This idle + * logic is only maintained for the BASE_STD base, deferrable + * timers may still see large granularity skew (by design). */ - if ((expires - basem) > TICK_NSEC) + if ((expires - basem) > TICK_NSEC) { + base->must_forward_clk = true; base->is_idle = true; + } } raw_spin_unlock(&base->lock); @@ -1611,6 +1630,19 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + /* + * must_forward_clk must be cleared before running timers so that any + * timer functions that call mod_timer will not try to forward the + * base. idle trcking / clock forwarding logic is only used with + * BASE_STD timers. + * + * The deferrable base does not do idle tracking at all, so we do + * not forward it. This can result in very large variations in + * granularity for deferrable timers, but they can be deferred for + * long periods due to idle. + */ + base->must_forward_clk = false; + __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 37385193a608..dc498b605d5d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -204,10 +204,36 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, fmt_cnt++; } - return __trace_printk(1/* fake ip will not be printed */, fmt, - mod[0] == 2 ? arg1 : mod[0] == 1 ? (long) arg1 : (u32) arg1, - mod[1] == 2 ? arg2 : mod[1] == 1 ? (long) arg2 : (u32) arg2, - mod[2] == 2 ? arg3 : mod[2] == 1 ? (long) arg3 : (u32) arg3); +/* Horrid workaround for getting va_list handling working with different + * argument type combinations generically for 32 and 64 bit archs. + */ +#define __BPF_TP_EMIT() __BPF_ARG3_TP() +#define __BPF_TP(...) \ + __trace_printk(1 /* Fake ip will not be printed. */, \ + fmt, ##__VA_ARGS__) + +#define __BPF_ARG1_TP(...) \ + ((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_TP(arg1, ##__VA_ARGS__) \ + : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_TP((long)arg1, ##__VA_ARGS__) \ + : __BPF_TP((u32)arg1, ##__VA_ARGS__))) + +#define __BPF_ARG2_TP(...) \ + ((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \ + : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \ + : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__))) + +#define __BPF_ARG3_TP(...) \ + ((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \ + ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \ + : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \ + ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \ + : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__))) + + return __BPF_TP_EMIT(); } static const struct bpf_func_proto bpf_trace_printk_proto = { diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 02004ae91860..96cea88fa00f 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -889,6 +889,10 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace) function_profile_call(trace->func, 0, NULL, NULL); + /* If function graph is shutting down, ret_stack can be NULL */ + if (!current->ret_stack) + return 0; + if (index >= 0 && index < FTRACE_RETFUNC_DEPTH) current->ret_stack[index].subtime = 0; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 529cc50d7243..81279c6602ff 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -4386,15 +4386,19 @@ EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu); * the page that was allocated, with the read page of the buffer. * * Returns: - * The page allocated, or NULL on error. + * The page allocated, or ERR_PTR */ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) { - struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu]; + struct ring_buffer_per_cpu *cpu_buffer; struct buffer_data_page *bpage = NULL; unsigned long flags; struct page *page; + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return ERR_PTR(-ENODEV); + + cpu_buffer = buffer->buffers[cpu]; local_irq_save(flags); arch_spin_lock(&cpu_buffer->lock); @@ -4412,7 +4416,7 @@ void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu) page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); if (!page) - return NULL; + return ERR_PTR(-ENOMEM); bpage = page_address(page); @@ -4467,8 +4471,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_free_read_page); * * for example: * rpage = ring_buffer_alloc_read_page(buffer, cpu); - * if (!rpage) - * return error; + * if (IS_ERR(rpage)) + * return PTR_ERR(rpage); * ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0); * if (ret >= 0) * process_page(rpage, ret); diff --git a/kernel/trace/ring_buffer_benchmark.c b/kernel/trace/ring_buffer_benchmark.c index 9fbcaf567886..68ee79afe31c 100644 --- a/kernel/trace/ring_buffer_benchmark.c +++ b/kernel/trace/ring_buffer_benchmark.c @@ -113,7 +113,7 @@ static enum event_status read_page(int cpu) int i; bpage = ring_buffer_alloc_read_page(buffer, cpu); - if (!bpage) + if (IS_ERR(bpage)) return EVENT_DROPPED; ret = ring_buffer_read_page(buffer, &bpage, PAGE_SIZE, cpu, 1); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 42b9355033d4..44004d8aa3b3 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6598,7 +6598,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; - ssize_t ret; + ssize_t ret = 0; ssize_t size; if (!count) @@ -6612,10 +6612,15 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, if (!info->spare) { info->spare = ring_buffer_alloc_read_page(iter->trace_buffer->buffer, iter->cpu_file); - info->spare_cpu = iter->cpu_file; + if (IS_ERR(info->spare)) { + ret = PTR_ERR(info->spare); + info->spare = NULL; + } else { + info->spare_cpu = iter->cpu_file; + } } if (!info->spare) - return -ENOMEM; + return ret; /* Do we have previous read data to read? */ if (info->read < PAGE_SIZE) @@ -6790,8 +6795,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, ref->ref = 1; ref->buffer = iter->trace_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); - if (!ref->page) { - ret = -ENOMEM; + if (IS_ERR(ref->page)) { + ret = PTR_ERR(ref->page); + ref->page = NULL; kfree(ref); break; } @@ -8293,6 +8299,7 @@ __init static int tracer_alloc_buffers(void) if (ret < 0) goto out_free_cpumask; /* Used for event triggers */ + ret = -ENOMEM; temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE); if (!temp_buffer) goto out_rm_hp_state; @@ -8407,4 +8414,4 @@ __init static int clear_boot_tracer(void) } fs_initcall(tracer_init_tracefs); -late_initcall(clear_boot_tracer); +late_initcall_sync(clear_boot_tracer); diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 562fa69df5d3..13ba2d3f6a91 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -306,6 +306,7 @@ static void perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct pt_regs *pt_regs) { + struct perf_event *event; struct ftrace_entry *entry; struct hlist_head *head; struct pt_regs regs; @@ -329,8 +330,9 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, entry->ip = ip; entry->parent_ip = parent_ip; + event = container_of(ops, struct perf_event, ftrace_ops); perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN, - 1, ®s, head, NULL); + 1, ®s, head, NULL, event); #undef ENTRY_SIZE } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 59a411ff60c7..181e139a8057 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1959,6 +1959,10 @@ static int create_filter(struct trace_event_call *call, if (err && set_str) append_filter_err(ps, filter); } + if (err && !set_str) { + free_event_filter(filter); + filter = NULL; + } create_filter_finish(ps); *filterp = filter; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c9b5aa10fbf9..8a907e12b6b9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -1200,7 +1200,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) memset(&entry[1], 0, dsize); store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, - head, NULL); + head, NULL, NULL); } NOKPROBE_SYMBOL(kprobe_perf_func); @@ -1236,7 +1236,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, entry->ret_ip = (unsigned long)ri->ret_addr; store_trace_args(sizeof(*entry), &tk->tp, regs, (u8 *)&entry[1], dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, - head, NULL); + head, NULL, NULL); } NOKPROBE_SYMBOL(kretprobe_perf_func); #endif /* CONFIG_PERF_EVENTS */ diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 5e10395da88e..74d9a86eccc0 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -596,7 +596,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) (unsigned long *)&rec->args); perf_trace_buf_submit(rec, size, rctx, sys_data->enter_event->event.type, 1, regs, - head, NULL); + head, NULL, NULL); } static int perf_sysenter_enable(struct trace_event_call *call) @@ -667,7 +667,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret) rec->nr = syscall_nr; rec->ret = syscall_get_return_value(current, regs); perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type, - 1, regs, head, NULL); + 1, regs, head, NULL, NULL); } static int perf_sysexit_enable(struct trace_event_call *call) diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index a7581fec9681..4525e0271a53 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -1156,7 +1156,7 @@ static void __uprobe_perf_func(struct trace_uprobe *tu, } perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, - head, NULL); + head, NULL, NULL); out: preempt_enable(); } diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 0a689bbb78ef..305039b122fa 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -221,16 +221,19 @@ void tracing_map_array_free(struct tracing_map_array *a) if (!a) return; - if (!a->pages) { - kfree(a); - return; - } + if (!a->pages) + goto free; for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; free_page((unsigned long)a->pages[i]); } + + kfree(a->pages); + + free: + kfree(a); } struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 06d3389bca0d..f5d52024f6b7 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -240,6 +240,7 @@ static void set_sample_period(void) * hardlockup detector generates a warning */ sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); + watchdog_update_hrtimer_threshold(sample_period); } /* Commands for resetting the watchdog */ diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 295a0d84934c..3a09ea1b1d3d 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -37,6 +37,62 @@ void arch_touch_nmi_watchdog(void) } EXPORT_SYMBOL(arch_touch_nmi_watchdog); +#ifdef CONFIG_HARDLOCKUP_CHECK_TIMESTAMP +static DEFINE_PER_CPU(ktime_t, last_timestamp); +static DEFINE_PER_CPU(unsigned int, nmi_rearmed); +static ktime_t watchdog_hrtimer_sample_threshold __read_mostly; + +void watchdog_update_hrtimer_threshold(u64 period) +{ + /* + * The hrtimer runs with a period of (watchdog_threshold * 2) / 5 + * + * So it runs effectively with 2.5 times the rate of the NMI + * watchdog. That means the hrtimer should fire 2-3 times before + * the NMI watchdog expires. The NMI watchdog on x86 is based on + * unhalted CPU cycles, so if Turbo-Mode is enabled the CPU cycles + * might run way faster than expected and the NMI fires in a + * smaller period than the one deduced from the nominal CPU + * frequency. Depending on the Turbo-Mode factor this might be fast + * enough to get the NMI period smaller than the hrtimer watchdog + * period and trigger false positives. + * + * The sample threshold is used to check in the NMI handler whether + * the minimum time between two NMI samples has elapsed. That + * prevents false positives. + * + * Set this to 4/5 of the actual watchdog threshold period so the + * hrtimer is guaranteed to fire at least once within the real + * watchdog threshold. + */ + watchdog_hrtimer_sample_threshold = period * 2; +} + +static bool watchdog_check_timestamp(void) +{ + ktime_t delta, now = ktime_get_mono_fast_ns(); + + delta = now - __this_cpu_read(last_timestamp); + if (delta < watchdog_hrtimer_sample_threshold) { + /* + * If ktime is jiffies based, a stalled timer would prevent + * jiffies from being incremented and the filter would look + * at a stale timestamp and never trigger. + */ + if (__this_cpu_inc_return(nmi_rearmed) < 10) + return false; + } + __this_cpu_write(nmi_rearmed, 0); + __this_cpu_write(last_timestamp, now); + return true; +} +#else +static inline bool watchdog_check_timestamp(void) +{ + return true; +} +#endif + static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, @@ -61,6 +117,9 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } + if (!watchdog_check_timestamp()) + return; + /* check for a hardlockup * This is done by making sure our timer interrupt * is incrementing. The timer interrupt should have diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 98fe715522e8..c617b9d1d6cb 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -798,6 +798,13 @@ config HARDLOCKUP_DETECTOR_PERF select SOFTLOCKUP_DETECTOR # +# Enables a timestamp based low pass filter to compensate for perf based +# hard lockup detection which runs too fast due to turbo modes. +# +config HARDLOCKUP_CHECK_TIMESTAMP + bool + +# # arch/ can define HAVE_HARDLOCKUP_DETECTOR_ARCH to provide their own hard # lockup detector rather than the perf based detector. # diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c index 5a0f75a3bf01..eead4b339466 100644 --- a/lib/mpi/mpicoder.c +++ b/lib/mpi/mpicoder.c @@ -364,11 +364,11 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) } miter.consumed = lzeros; - sg_miter_stop(&miter); nbytes -= lzeros; nbits = nbytes * 8; if (nbits > MAX_EXTERN_MPI_BITS) { + sg_miter_stop(&miter); pr_info("MPI: mpi too large (%u bits)\n", nbits); return NULL; } @@ -376,6 +376,8 @@ MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int nbytes) if (nbytes > 0) nbits -= count_leading_zeros(*buff) - (BITS_PER_LONG - 8); + sg_miter_stop(&miter); + nlimbs = DIV_ROUND_UP(nbytes, BYTES_PER_MPI_LIMB); val = mpi_alloc(nlimbs); if (!val) diff --git a/mm/cma_debug.c b/mm/cma_debug.c index 595b757bef72..c03ccbc405a0 100644 --- a/mm/cma_debug.c +++ b/mm/cma_debug.c @@ -167,7 +167,7 @@ static void cma_debugfs_add_one(struct cma *cma, int idx) char name[16]; int u32s; - sprintf(name, "cma-%s", cma->name); + scnprintf(name, sizeof(name), "cma-%s", cma->name); tmp = debugfs_create_dir(name, cma_debugfs_root); diff --git a/mm/filemap.c b/mm/filemap.c index a49702445ce0..65b4b6e7f7bd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -885,6 +885,7 @@ void __init pagecache_init(void) page_writeback_init(); } +/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */ struct wait_page_key { struct page *page; int bit_nr; @@ -909,8 +910,10 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, if (wait_page->bit_nr != key->bit_nr) return 0; + + /* Stop walking if it's locked */ if (test_bit(key->bit_nr, &key->page->flags)) - return 0; + return -1; return autoremove_wake_function(wait, mode, sync, key); } @@ -964,6 +967,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, int ret = 0; init_wait(wait); + wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; wait_page.page = page; wait_page.bit_nr = bit_nr; @@ -972,10 +976,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, spin_lock_irq(&q->lock); if (likely(list_empty(&wait->entry))) { - if (lock) - __add_wait_queue_entry_tail_exclusive(q, wait); - else - __add_wait_queue(q, wait); + __add_wait_queue_entry_tail(q, wait); SetPageWaiters(page); } @@ -985,10 +986,6 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, if (likely(test_bit(bit_nr, &page->flags))) { io_schedule(); - if (unlikely(signal_pending_state(state, current))) { - ret = -EINTR; - break; - } } if (lock) { @@ -998,6 +995,11 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, if (!test_bit(bit_nr, &page->flags)) break; } + + if (unlikely(signal_pending_state(state, current))) { + ret = -EINTR; + break; + } } finish_wait(q, wait); @@ -1039,7 +1041,7 @@ void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter) unsigned long flags; spin_lock_irqsave(&q->lock, flags); - __add_wait_queue(q, waiter); + __add_wait_queue_entry_tail(q, waiter); SetPageWaiters(page); spin_unlock_irqrestore(&q->lock, flags); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 216114f6ef0b..90731e3b7e58 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -32,6 +32,7 @@ #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/shmem_fs.h> +#include <linux/oom.h> #include <asm/tlb.h> #include <asm/pgalloc.h> @@ -550,6 +551,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, struct mem_cgroup *memcg; pgtable_t pgtable; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; + int ret = 0; VM_BUG_ON_PAGE(!PageCompound(page), page); @@ -561,9 +563,8 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, pgtable = pte_alloc_one(vma->vm_mm, haddr); if (unlikely(!pgtable)) { - mem_cgroup_cancel_charge(page, memcg, true); - put_page(page); - return VM_FAULT_OOM; + ret = VM_FAULT_OOM; + goto release; } clear_huge_page(page, haddr, HPAGE_PMD_NR); @@ -576,13 +577,14 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { - spin_unlock(vmf->ptl); - mem_cgroup_cancel_charge(page, memcg, true); - put_page(page); - pte_free(vma->vm_mm, pgtable); + goto unlock_release; } else { pmd_t entry; + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto unlock_release; + /* Deliver the page fault to userland */ if (userfaultfd_missing(vma)) { int ret; @@ -610,6 +612,15 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, } return 0; +unlock_release: + spin_unlock(vmf->ptl); +release: + if (pgtable) + pte_free(vma->vm_mm, pgtable); + mem_cgroup_cancel_charge(page, memcg, true); + put_page(page); + return ret; + } /* @@ -688,7 +699,10 @@ int do_huge_pmd_anonymous_page(struct vm_fault *vmf) ret = 0; set = false; if (pmd_none(*vmf->pmd)) { - if (userfaultfd_missing(vma)) { + ret = check_stable_address_space(vma->vm_mm); + if (ret) { + spin_unlock(vmf->ptl); + } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); diff --git a/mm/madvise.c b/mm/madvise.c index 47d8d8a25eae..4d7d1e5ddba9 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -368,8 +368,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, pte_offset_map_lock(mm, pmd, addr, &ptl); goto out; } - put_page(page); unlock_page(page); + put_page(page); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); pte--; addr -= PAGE_SIZE; @@ -613,6 +613,7 @@ static int madvise_inject_error(int behavior, unsigned long start, unsigned long end) { struct page *page; + struct zone *zone; if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -646,6 +647,11 @@ static int madvise_inject_error(int behavior, if (ret) return ret; } + + /* Ensure that all poisoned pages are removed from per-cpu lists */ + for_each_populated_zone(zone) + drain_all_pages(zone); + return 0; } #endif diff --git a/mm/memblock.c b/mm/memblock.c index 2cb25fe4452c..91205780e6b1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -285,31 +285,27 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u } #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK - -phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info( - phys_addr_t *addr) -{ - if (memblock.reserved.regions == memblock_reserved_init_regions) - return 0; - - *addr = __pa(memblock.reserved.regions); - - return PAGE_ALIGN(sizeof(struct memblock_region) * - memblock.reserved.max); -} - -phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info( - phys_addr_t *addr) +/** + * Discard memory and reserved arrays if they were allocated + */ +void __init memblock_discard(void) { - if (memblock.memory.regions == memblock_memory_init_regions) - return 0; + phys_addr_t addr, size; - *addr = __pa(memblock.memory.regions); + if (memblock.reserved.regions != memblock_reserved_init_regions) { + addr = __pa(memblock.reserved.regions); + size = PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.reserved.max); + __memblock_free_late(addr, size); + } - return PAGE_ALIGN(sizeof(struct memblock_region) * - memblock.memory.max); + if (memblock.memory.regions != memblock_memory_init_regions) { + addr = __pa(memblock.memory.regions); + size = PAGE_ALIGN(sizeof(struct memblock_region) * + memblock.memory.max); + __memblock_free_late(addr, size); + } } - #endif /** diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3df3c04d73ab..e09741af816f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1611,9 +1611,13 @@ cleanup: * @page: the page * * This function protects unlocked LRU pages from being moved to - * another cgroup and stabilizes their page->mem_cgroup binding. + * another cgroup. + * + * It ensures lifetime of the returned memcg. Caller is responsible + * for the lifetime of the page; __unlock_page_memcg() is available + * when @page might get freed inside the locked section. */ -void lock_page_memcg(struct page *page) +struct mem_cgroup *lock_page_memcg(struct page *page) { struct mem_cgroup *memcg; unsigned long flags; @@ -1622,18 +1626,24 @@ void lock_page_memcg(struct page *page) * The RCU lock is held throughout the transaction. The fast * path can get away without acquiring the memcg->move_lock * because page moving starts with an RCU grace period. - */ + * + * The RCU lock also protects the memcg from being freed when + * the page state that is going to change is the only thing + * preventing the page itself from being freed. E.g. writeback + * doesn't hold a page reference and relies on PG_writeback to + * keep off truncation, migration and so forth. + */ rcu_read_lock(); if (mem_cgroup_disabled()) - return; + return NULL; again: memcg = page->mem_cgroup; if (unlikely(!memcg)) - return; + return NULL; if (atomic_read(&memcg->moving_account) <= 0) - return; + return memcg; spin_lock_irqsave(&memcg->move_lock, flags); if (memcg != page->mem_cgroup) { @@ -1649,18 +1659,18 @@ again: memcg->move_lock_task = current; memcg->move_lock_flags = flags; - return; + return memcg; } EXPORT_SYMBOL(lock_page_memcg); /** - * unlock_page_memcg - unlock a page->mem_cgroup binding - * @page: the page + * __unlock_page_memcg - unlock and unpin a memcg + * @memcg: the memcg + * + * Unlock and unpin a memcg returned by lock_page_memcg(). */ -void unlock_page_memcg(struct page *page) +void __unlock_page_memcg(struct mem_cgroup *memcg) { - struct mem_cgroup *memcg = page->mem_cgroup; - if (memcg && memcg->move_lock_task == current) { unsigned long flags = memcg->move_lock_flags; @@ -1672,6 +1682,15 @@ void unlock_page_memcg(struct page *page) rcu_read_unlock(); } + +/** + * unlock_page_memcg - unlock a page->mem_cgroup binding + * @page: the page + */ +void unlock_page_memcg(struct page *page) +{ + __unlock_page_memcg(page->mem_cgroup); +} EXPORT_SYMBOL(unlock_page_memcg); /* diff --git a/mm/memory.c b/mm/memory.c index e158f7ac6730..56e48e4593cb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -68,6 +68,7 @@ #include <linux/debugfs.h> #include <linux/userfaultfd_k.h> #include <linux/dax.h> +#include <linux/oom.h> #include <asm/io.h> #include <asm/mmu_context.h> @@ -2893,6 +2894,7 @@ static int do_anonymous_page(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct mem_cgroup *memcg; struct page *page; + int ret = 0; pte_t entry; /* File mapping without ->vm_ops ? */ @@ -2925,6 +2927,9 @@ static int do_anonymous_page(struct vm_fault *vmf) vmf->address, &vmf->ptl); if (!pte_none(*vmf->pte)) goto unlock; + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto unlock; /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -2959,6 +2964,10 @@ static int do_anonymous_page(struct vm_fault *vmf) if (!pte_none(*vmf->pte)) goto release; + ret = check_stable_address_space(vma->vm_mm); + if (ret) + goto release; + /* Deliver the page fault to userland, check inside PT lock */ if (userfaultfd_missing(vma)) { pte_unmap_unlock(vmf->pte, vmf->ptl); @@ -2978,7 +2987,7 @@ setpte: update_mmu_cache(vma, vmf->address, vmf->pte); unlock: pte_unmap_unlock(vmf->pte, vmf->ptl); - return 0; + return ret; release: mem_cgroup_cancel_charge(page, memcg, false); put_page(page); @@ -3252,7 +3261,7 @@ int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, int finish_fault(struct vm_fault *vmf) { struct page *page; - int ret; + int ret = 0; /* Did we COW the page? */ if ((vmf->flags & FAULT_FLAG_WRITE) && @@ -3260,7 +3269,15 @@ int finish_fault(struct vm_fault *vmf) page = vmf->cow_page; else page = vmf->page; - ret = alloc_set_pte(vmf, vmf->memcg, page); + + /* + * check even for read faults because we might have lost our CoWed + * page + */ + if (!(vmf->vma->vm_flags & VM_SHARED)) + ret = check_stable_address_space(vmf->vma->vm_mm); + if (!ret) + ret = alloc_set_pte(vmf, vmf->memcg, page); if (vmf->pte) pte_unmap_unlock(vmf->pte, vmf->ptl); return ret; @@ -3900,19 +3917,6 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address, mem_cgroup_oom_synchronize(false); } - /* - * This mm has been already reaped by the oom reaper and so the - * refault cannot be trusted in general. Anonymous refaults would - * lose data and give a zero page instead e.g. This is especially - * problem for use_mm() because regular tasks will just die and - * the corrupted data will not be visible anywhere while kthread - * will outlive the oom victim and potentially propagate the date - * further. - */ - if (unlikely((current->flags & PF_KTHREAD) && !(ret & VM_FAULT_ERROR) - && test_bit(MMF_UNSTABLE, &vma->vm_mm->flags))) - ret = VM_FAULT_SIGBUS; - return ret; } EXPORT_SYMBOL_GPL(handle_mm_fault); @@ -4004,7 +4008,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) #endif /* __PAGETABLE_PMD_FOLDED */ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, - pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) + unsigned long *start, unsigned long *end, + pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { pgd_t *pgd; p4d_t *p4d; @@ -4031,17 +4036,29 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, if (!pmdpp) goto out; + if (start && end) { + *start = address & PMD_MASK; + *end = *start + PMD_SIZE; + mmu_notifier_invalidate_range_start(mm, *start, *end); + } *ptlp = pmd_lock(mm, pmd); if (pmd_huge(*pmd)) { *pmdpp = pmd; return 0; } spin_unlock(*ptlp); + if (start && end) + mmu_notifier_invalidate_range_end(mm, *start, *end); } if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) goto out; + if (start && end) { + *start = address & PAGE_MASK; + *end = *start + PAGE_SIZE; + mmu_notifier_invalidate_range_start(mm, *start, *end); + } ptep = pte_offset_map_lock(mm, pmd, address, ptlp); if (!pte_present(*ptep)) goto unlock; @@ -4049,6 +4066,8 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address, return 0; unlock: pte_unmap_unlock(ptep, *ptlp); + if (start && end) + mmu_notifier_invalidate_range_end(mm, *start, *end); out: return -EINVAL; } @@ -4060,20 +4079,21 @@ static inline int follow_pte(struct mm_struct *mm, unsigned long address, /* (void) is needed to make gcc happy */ (void) __cond_lock(*ptlp, - !(res = __follow_pte_pmd(mm, address, ptepp, NULL, - ptlp))); + !(res = __follow_pte_pmd(mm, address, NULL, NULL, + ptepp, NULL, ptlp))); return res; } int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + unsigned long *start, unsigned long *end, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp) { int res; /* (void) is needed to make gcc happy */ (void) __cond_lock(*ptlp, - !(res = __follow_pte_pmd(mm, address, ptepp, pmdpp, - ptlp))); + !(res = __follow_pte_pmd(mm, address, start, end, + ptepp, pmdpp, ptlp))); return res; } EXPORT_SYMBOL(follow_pte_pmd); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d911fa5cb2a7..618ab125228b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -861,11 +861,6 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, *policy |= (pol->flags & MPOL_MODE_FLAGS); } - if (vma) { - up_read(¤t->mm->mmap_sem); - vma = NULL; - } - err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { diff --git a/mm/migrate.c b/mm/migrate.c index d68a41da6abb..e84eeb4e4356 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -41,6 +41,7 @@ #include <linux/page_idle.h> #include <linux/page_owner.h> #include <linux/sched/mm.h> +#include <linux/ptrace.h> #include <asm/tlbflush.h> @@ -1652,7 +1653,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, const int __user *, nodes, int __user *, status, int, flags) { - const struct cred *cred = current_cred(), *tcred; struct task_struct *task; struct mm_struct *mm; int err; @@ -1676,14 +1676,9 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, /* * Check if this process has the right to modify the specified - * process. The right exists if the process has administrative - * capabilities, superuser privileges or the same - * userid as the target process. + * process. Use the regular "ptrace_may_access()" checks. */ - tcred = __task_cred(task); - if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) && - !capable(CAP_SYS_NICE)) { + if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out; diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 54ca54562928..314285284e6e 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -174,20 +174,6 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, srcu_read_unlock(&srcu, id); } -void __mmu_notifier_invalidate_page(struct mm_struct *mm, - unsigned long address) -{ - struct mmu_notifier *mn; - int id; - - id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { - if (mn->ops->invalidate_page) - mn->ops->invalidate_page(mn, mm, address); - } - srcu_read_unlock(&srcu, id); -} - void __mmu_notifier_invalidate_range_start(struct mm_struct *mm, unsigned long start, unsigned long end) { diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 36454d0f96ee..3637809a18d0 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -146,22 +146,6 @@ static unsigned long __init free_low_memory_core_early(void) NULL) count += __free_memory_core(start, end); -#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK - { - phys_addr_t size; - - /* Free memblock.reserved array if it was allocated */ - size = get_allocated_memblock_reserved_regions_info(&start); - if (size) - count += __free_memory_core(start, start + size); - - /* Free memblock.memory array if it was allocated */ - size = get_allocated_memblock_memory_regions_info(&start); - if (size) - count += __free_memory_core(start, start + size); - } -#endif - return count; } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 96e93b214d31..bf050ab025b7 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2724,9 +2724,12 @@ EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); + struct mem_cgroup *memcg; + struct lruvec *lruvec; int ret; - lock_page_memcg(page); + memcg = lock_page_memcg(page); + lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); if (mapping && mapping_use_writeback_tags(mapping)) { struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); @@ -2754,12 +2757,18 @@ int test_clear_page_writeback(struct page *page) } else { ret = TestClearPageWriteback(page); } + /* + * NOTE: Page might be free now! Writeback doesn't hold a page + * reference on its own, it relies on truncation to wait for + * the clearing of PG_writeback. The below can only access + * page state that is static across allocation cycles. + */ if (ret) { - dec_lruvec_page_state(page, NR_WRITEBACK); + dec_lruvec_state(lruvec, NR_WRITEBACK); dec_zone_page_state(page, NR_ZONE_WRITE_PENDING); inc_node_page_state(page, NR_WRITTEN); } - unlock_page_memcg(page); + __unlock_page_memcg(memcg); return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6d00f746c2fd..1423da8dd16f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -66,6 +66,7 @@ #include <linux/kthread.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> +#include <linux/nmi.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -1584,6 +1585,10 @@ void __init page_alloc_init_late(void) /* Reinit limits that are based on free pages after the kernel is up */ files_maxfiles_init(); #endif +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK + /* Discard memblock private memory */ + memblock_discard(); +#endif for_each_populated_zone(zone) set_zone_contiguous(zone); @@ -2531,9 +2536,14 @@ void drain_all_pages(struct zone *zone) #ifdef CONFIG_HIBERNATION +/* + * Touch the watchdog for every WD_PAGE_COUNT pages. + */ +#define WD_PAGE_COUNT (128*1024) + void mark_free_pages(struct zone *zone) { - unsigned long pfn, max_zone_pfn; + unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT; unsigned long flags; unsigned int order, t; struct page *page; @@ -2548,6 +2558,11 @@ void mark_free_pages(struct zone *zone) if (pfn_valid(pfn)) { page = pfn_to_page(pfn); + if (!--page_count) { + touch_nmi_watchdog(); + page_count = WD_PAGE_COUNT; + } + if (page_zone(page) != zone) continue; @@ -2561,8 +2576,13 @@ void mark_free_pages(struct zone *zone) unsigned long i; pfn = page_to_pfn(page); - for (i = 0; i < (1UL << order); i++) + for (i = 0; i < (1UL << order); i++) { + if (!--page_count) { + touch_nmi_watchdog(); + page_count = WD_PAGE_COUNT; + } swsusp_set_page_free(pfn_to_page(pfn + i)); + } } } spin_unlock_irqrestore(&zone->lock, flags); @@ -3271,10 +3291,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, /* * Go through the zonelist yet one more time, keep very high watermark * here, this is only to catch a parallel oom killing, we must fail if - * we're still under heavy pressure. + * we're still under heavy pressure. But make sure that this reclaim + * attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY + * allocation which will never fail due to oom_lock already held. */ - page = get_page_from_freelist(gfp_mask | __GFP_HARDWALL, order, - ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac); + page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) & + ~__GFP_DIRECT_RECLAIM, order, + ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac); if (page) goto out; diff --git a/mm/rmap.c b/mm/rmap.c index c1286d47aa1f..c570f82e6827 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -887,11 +887,21 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, .address = address, .flags = PVMW_SYNC, }; + unsigned long start = address, end; int *cleaned = arg; - bool invalidation_needed = false; + + /* + * We have to assume the worse case ie pmd for invalidation. Note that + * the page can not be free from this function. + */ + end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); while (page_vma_mapped_walk(&pvmw)) { + unsigned long cstart, cend; int ret = 0; + + cstart = address = pvmw.address; if (pvmw.pte) { pte_t entry; pte_t *pte = pvmw.pte; @@ -899,11 +909,12 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, if (!pte_dirty(*pte) && !pte_write(*pte)) continue; - flush_cache_page(vma, pvmw.address, pte_pfn(*pte)); - entry = ptep_clear_flush(vma, pvmw.address, pte); + flush_cache_page(vma, address, pte_pfn(*pte)); + entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); - set_pte_at(vma->vm_mm, pvmw.address, pte, entry); + set_pte_at(vma->vm_mm, address, pte, entry); + cend = cstart + PAGE_SIZE; ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE @@ -913,11 +924,13 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, if (!pmd_dirty(*pmd) && !pmd_write(*pmd)) continue; - flush_cache_page(vma, pvmw.address, page_to_pfn(page)); - entry = pmdp_huge_clear_flush(vma, pvmw.address, pmd); + flush_cache_page(vma, address, page_to_pfn(page)); + entry = pmdp_huge_clear_flush(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); - set_pmd_at(vma->vm_mm, pvmw.address, pmd, entry); + set_pmd_at(vma->vm_mm, address, pmd, entry); + cstart &= PMD_MASK; + cend = cstart + PMD_SIZE; ret = 1; #else /* unexpected pmd-mapped page? */ @@ -926,15 +939,12 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma, } if (ret) { + mmu_notifier_invalidate_range(vma->vm_mm, cstart, cend); (*cleaned)++; - invalidation_needed = true; } } - if (invalidation_needed) { - mmu_notifier_invalidate_range(vma->vm_mm, address, - address + (1UL << compound_order(page))); - } + mmu_notifier_invalidate_range_end(vma->vm_mm, start, end); return true; } @@ -1328,7 +1338,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, }; pte_t pteval; struct page *subpage; - bool ret = true, invalidation_needed = false; + bool ret = true; + unsigned long start = address, end; enum ttu_flags flags = (enum ttu_flags)arg; /* munlock has nothing to gain from examining un-locked vmas */ @@ -1340,6 +1351,14 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, flags & TTU_MIGRATION, page); } + /* + * We have to assume the worse case ie pmd for invalidation. Note that + * the page can not be free in this function as call of try_to_unmap() + * must hold a reference on the page. + */ + end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); + while (page_vma_mapped_walk(&pvmw)) { /* * If the page is mlock()d, we cannot swap it out. @@ -1368,9 +1387,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, VM_BUG_ON_PAGE(!pvmw.pte, page); subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); + address = pvmw.address; + if (!(flags & TTU_IGNORE_ACCESS)) { - if (ptep_clear_flush_young_notify(vma, pvmw.address, + if (ptep_clear_flush_young_notify(vma, address, pvmw.pte)) { ret = false; page_vma_mapped_walk_done(&pvmw); @@ -1379,7 +1400,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* Nuke the page table entry. */ - flush_cache_page(vma, pvmw.address, pte_pfn(*pvmw.pte)); + flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially @@ -1389,12 +1410,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ - pteval = ptep_get_and_clear(mm, pvmw.address, - pvmw.pte); + pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pte_dirty(pteval)); } else { - pteval = ptep_clear_flush(vma, pvmw.address, pvmw.pte); + pteval = ptep_clear_flush(vma, address, pvmw.pte); } /* Move the dirty bit to the page. Now the pte is gone. */ @@ -1409,12 +1429,12 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageHuge(page)) { int nr = 1 << compound_order(page); hugetlb_count_sub(nr, mm); - set_huge_swap_pte_at(mm, pvmw.address, + set_huge_swap_pte_at(mm, address, pvmw.pte, pteval, vma_mmu_pagesize(vma)); } else { dec_mm_counter(mm, mm_counter(page)); - set_pte_at(mm, pvmw.address, pvmw.pte, pteval); + set_pte_at(mm, address, pvmw.pte, pteval); } } else if (pte_unused(pteval)) { @@ -1438,7 +1458,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); } else if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(subpage) }; pte_t swp_pte; @@ -1449,6 +1469,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) { WARN_ON_ONCE(1); ret = false; + /* We have to invalidate as we cleared the pte */ page_vma_mapped_walk_done(&pvmw); break; } @@ -1464,7 +1485,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * If the page was redirtied, it cannot be * discarded. Remap the page to page table. */ - set_pte_at(mm, pvmw.address, pvmw.pte, pteval); + set_pte_at(mm, address, pvmw.pte, pteval); SetPageSwapBacked(page); ret = false; page_vma_mapped_walk_done(&pvmw); @@ -1472,7 +1493,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } if (swap_duplicate(entry) < 0) { - set_pte_at(mm, pvmw.address, pvmw.pte, pteval); + set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; @@ -1488,18 +1509,18 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); - set_pte_at(mm, pvmw.address, pvmw.pte, swp_pte); + set_pte_at(mm, address, pvmw.pte, swp_pte); } else dec_mm_counter(mm, mm_counter_file(page)); discard: page_remove_rmap(subpage, PageHuge(page)); put_page(page); - invalidation_needed = true; + mmu_notifier_invalidate_range(mm, address, + address + PAGE_SIZE); } - if (invalidation_needed) - mmu_notifier_invalidate_range(mm, address, - address + (1UL << compound_order(page))); + mmu_notifier_invalidate_range_end(vma->vm_mm, start, end); + return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index 6540e5982444..fbcb3c96a186 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3967,7 +3967,7 @@ int __init shmem_init(void) } #ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE - if (has_transparent_hugepage() && shmem_huge < SHMEM_HUGE_DENY) + if (has_transparent_hugepage() && shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; else shmem_huge = 0; /* just in case it was patched */ @@ -4028,7 +4028,7 @@ static ssize_t shmem_enabled_store(struct kobject *kobj, return -EINVAL; shmem_huge = huge; - if (shmem_huge < SHMEM_HUGE_DENY) + if (shmem_huge > SHMEM_HUGE_DENY) SHMEM_SB(shm_mnt->mnt_sb)->huge = shmem_huge; return count; } diff --git a/mm/slub.c b/mm/slub.c index 1d3f9835f4ea..e8b4e31162ca 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5642,13 +5642,14 @@ static void sysfs_slab_remove_workfn(struct work_struct *work) * A cache is never shut down before deactivation is * complete, so no need to worry about synchronization. */ - return; + goto out; #ifdef CONFIG_MEMCG kset_unregister(s->memcg_kset); #endif kobject_uevent(&s->kobj, KOBJ_REMOVE); kobject_del(&s->kobj); +out: kobject_put(&s->kobj); } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 8698c1c86c4d..a47e3894c775 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1671,7 +1671,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page **pages; unsigned int nr_pages, array_size, i; const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO; - const gfp_t alloc_mask = gfp_mask | __GFP_HIGHMEM | __GFP_NOWARN; + const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN; + const gfp_t highmem_mask = (gfp_mask & (GFP_DMA | GFP_DMA32)) ? + 0 : + __GFP_HIGHMEM; nr_pages = get_vm_area_size(area) >> PAGE_SHIFT; array_size = (nr_pages * sizeof(struct page *)); @@ -1679,7 +1682,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, area->nr_pages = nr_pages; /* Please note that the recursion is strictly bounded. */ if (array_size > PAGE_SIZE) { - pages = __vmalloc_node(array_size, 1, nested_gfp|__GFP_HIGHMEM, + pages = __vmalloc_node(array_size, 1, nested_gfp|highmem_mask, PAGE_KERNEL, node, area->caller); } else { pages = kmalloc_node(array_size, nested_gfp, node); @@ -1700,9 +1703,9 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, } if (node == NUMA_NO_NODE) - page = alloc_page(alloc_mask); + page = alloc_page(alloc_mask|highmem_mask); else - page = alloc_pages_node(node, alloc_mask, 0); + page = alloc_pages_node(node, alloc_mask|highmem_mask, 0); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vunmap() */ @@ -1710,7 +1713,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } area->pages[i] = page; - if (gfpflags_allow_blocking(gfp_mask)) + if (gfpflags_allow_blocking(gfp_mask|highmem_mask)) cond_resched(); } diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 861ae2a165f4..5a7be3bddfa9 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -53,6 +53,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) brstats->tx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); +#ifdef CONFIG_NET_SWITCHDEV + skb->offload_fwd_mark = 0; +#endif BR_INPUT_SKB_CB(skb)->brdev = dev; skb_reset_mac_header(skb); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 181a44d0f1da..f6b1c7de059d 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -115,7 +115,7 @@ br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) { - if (!fdb->added_by_user) + if (!fdb->added_by_user || !fdb->dst) return; switch (type) { diff --git a/net/core/datagram.c b/net/core/datagram.c index ee5647bd91b3..8c2f4489ff8f 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -169,14 +169,20 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, int *peeked, int *off, int *err, struct sk_buff **last) { + bool peek_at_off = false; struct sk_buff *skb; - int _off = *off; + int _off = 0; + + if (unlikely(flags & MSG_PEEK && *off >= 0)) { + peek_at_off = true; + _off = *off; + } *last = queue->prev; skb_queue_walk(queue, skb) { if (flags & MSG_PEEK) { - if (_off >= skb->len && (skb->len || _off || - skb->peeked)) { + if (peek_at_off && _off >= skb->len && + (_off || skb->peeked)) { _off -= skb->len; continue; } @@ -356,7 +362,7 @@ int __sk_queue_drop_skb(struct sock *sk, struct sk_buff_head *sk_queue, if (flags & MSG_PEEK) { err = -ENOENT; spin_lock_bh(&sk_queue->lock); - if (skb == skb_peek(sk_queue)) { + if (skb->next) { __skb_unlink(skb, sk_queue); refcount_dec(&skb->users); if (destructor) diff --git a/net/core/dev.c b/net/core/dev.c index ce15a06d5558..86b4b0a79e7a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5289,6 +5289,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, BUSY_POLL_BUDGET); + trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); netpoll_poll_unlock(have_poll_lock); if (rc == BUSY_POLL_BUDGET) __napi_schedule(napi); @@ -5667,12 +5668,13 @@ EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ -static bool netdev_has_any_upper_dev(struct net_device *dev) +bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.upper); } +EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device diff --git a/net/core/filter.c b/net/core/filter.c index f44fc22fd45a..169974998c76 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2836,15 +2836,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, sk->sk_prot->setsockopt == tcp_setsockopt) { if (optname == TCP_CONGESTION) { char name[TCP_CA_NAME_MAX]; + bool reinit = bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN; strncpy(name, optval, min_t(long, optlen, TCP_CA_NAME_MAX-1)); name[TCP_CA_NAME_MAX-1] = 0; - ret = tcp_set_congestion_control(sk, name, false); - if (!ret && bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN) - /* replacing an existing ca */ - tcp_reinit_congestion_control(sk, - inet_csk(sk)->icsk_ca_ops); + ret = tcp_set_congestion_control(sk, name, false, reinit); } else { struct tcp_sock *tp = tcp_sk(sk); @@ -2872,7 +2869,6 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, ret = -EINVAL; } } - ret = -EINVAL; #endif } else { ret = -EINVAL; @@ -3505,6 +3501,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, bpf_target_off(struct sk_buff, tc_index, 2, target_size)); #else + *target_size = 2; if (type == BPF_WRITE) *insn++ = BPF_MOV64_REG(si->dst_reg, si->dst_reg); else @@ -3520,6 +3517,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_JMP_IMM(BPF_JGE, si->dst_reg, MIN_NAPI_ID, 1); *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #else + *target_size = 4; *insn++ = BPF_MOV64_IMM(si->dst_reg, 0); #endif break; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index f990eb8b30a9..e07556606284 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1363,18 +1363,20 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, EXPORT_SYMBOL(skb_copy_expand); /** - * skb_pad - zero pad the tail of an skb + * __skb_pad - zero pad the tail of an skb * @skb: buffer to pad * @pad: space to pad + * @free_on_error: free buffer on error * * Ensure that a buffer is followed by a padding area that is zero * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * - * May return error in out of memory cases. The skb is freed on error. + * May return error in out of memory cases. The skb is freed on error + * if @free_on_error is true. */ -int skb_pad(struct sk_buff *skb, int pad) +int __skb_pad(struct sk_buff *skb, int pad, bool free_on_error) { int err; int ntail; @@ -1403,10 +1405,11 @@ int skb_pad(struct sk_buff *skb, int pad) return 0; free_skb: - kfree_skb(skb); + if (free_on_error) + kfree_skb(skb); return err; } -EXPORT_SYMBOL(skb_pad); +EXPORT_SYMBOL(__skb_pad); /** * pskb_put - add data to the tail of a potentially fragmented buffer diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 9fe25bf63296..b68168fcc06a 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -24,6 +24,7 @@ #include <net/checksum.h> #include <net/inet_sock.h> +#include <net/inet_common.h> #include <net/sock.h> #include <net/xfrm.h> @@ -170,6 +171,15 @@ const char *dccp_packet_name(const int type) EXPORT_SYMBOL_GPL(dccp_packet_name); +static void dccp_sk_destruct(struct sock *sk) +{ + struct dccp_sock *dp = dccp_sk(sk); + + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_tx_ccid = NULL; + inet_sock_destruct(sk); +} + int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) { struct dccp_sock *dp = dccp_sk(sk); @@ -179,6 +189,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) icsk->icsk_syn_retries = sysctl_dccp_request_retries; sk->sk_state = DCCP_CLOSED; sk->sk_write_space = dccp_write_space; + sk->sk_destruct = dccp_sk_destruct; icsk->icsk_sync_mss = dccp_sync_mss; dp->dccps_mss_cache = 536; dp->dccps_rate_last = jiffies; @@ -201,10 +212,7 @@ void dccp_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - /* - * DCCP doesn't use sk_write_queue, just sk_send_head - * for retransmissions - */ + __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; @@ -222,8 +230,7 @@ void dccp_destroy_sock(struct sock *sk) dp->dccps_hc_rx_ackvec = NULL; } ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); - ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); - dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; + dp->dccps_hc_rx_ccid = NULL; /* clean up feature negotiation state */ dccp_feat_list_purge(&dp->dccps_featneg); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index c442051d5a55..20bc9c56fca0 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -577,7 +577,7 @@ static int dsa_dst_parse(struct dsa_switch_tree *dst) return err; } - if (!dst->cpu_dp->netdev) { + if (!dst->cpu_dp) { pr_warn("Tree has no master device\n"); return -EINVAL; } diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index fab41de8e983..fcd90f79458e 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -42,6 +42,10 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len; if (skb_tailroom(skb) >= padlen + KSZ_INGRESS_TAG_LEN) { + /* Let dsa_slave_xmit() free skb */ + if (__skb_put_padto(skb, skb->len + padlen, false)) + return NULL; + nskb = skb; } else { nskb = alloc_skb(NET_IP_ALIGN + skb->len + @@ -56,12 +60,15 @@ static struct sk_buff *ksz_xmit(struct sk_buff *skb, struct net_device *dev) skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head); skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); - kfree_skb(skb); - } - /* skb is freed when it fails */ - if (skb_put_padto(nskb, nskb->len + padlen)) - return NULL; + /* Let skb_put_padto() free nskb, and let dsa_slave_xmit() free + * skb + */ + if (skb_put_padto(nskb, nskb->len + padlen)) + return NULL; + + consume_skb(skb); + } tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); tag[0] = 0; diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index b09e56214005..9c7b1d74a5c6 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -40,7 +40,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) skb_set_network_header(nskb, skb_network_header(skb) - skb->head); skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head); skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); - kfree_skb(skb); + consume_skb(skb); if (padlen) { skb_put_zero(nskb, padlen); diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 4e7bdb213cd0..172d8309f89e 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -314,7 +314,8 @@ static void send_hsr_supervision_frame(struct hsr_port *master, hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->MacAddressA, master->dev->dev_addr); - skb_put_padto(skb, ETH_ZLEN + HSR_HLEN); + if (skb_put_padto(skb, ETH_ZLEN + HSR_HLEN)) + return; hsr_forward_skb(skb, master); return; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 0cbee0a666ff..df68963dc90a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -258,7 +258,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * esp_output_udp_encap(x, skb, esp); if (!skb_cloned(skb)) { - if (tailen <= skb_availroom(skb)) { + if (tailen <= skb_tailroom(skb)) { nfrags = 1; trailer = skb; tail = skb_tail_pointer(trailer); @@ -292,8 +292,6 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * kunmap_atomic(vaddr); - spin_unlock_bh(&x->lock); - nfrags = skb_shinfo(skb)->nr_frags; __skb_fill_page_desc(skb, nfrags, page, pfrag->offset, @@ -301,6 +299,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * skb_shinfo(skb)->nr_frags = ++nfrags; pfrag->offset = pfrag->offset + allocsize; + + spin_unlock_bh(&x->lock); + nfrags++; skb->len += tailen; @@ -381,7 +382,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * (unsigned char *)esph - skb->data, assoclen + ivlen + esp->clen + alen); if (unlikely(err < 0)) - goto error; + goto error_free; if (!esp->inplace) { int allocsize; @@ -392,7 +393,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * spin_lock_bh(&x->lock); if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) { spin_unlock_bh(&x->lock); - goto error; + goto error_free; } skb_shinfo(skb)->nr_frags = 1; @@ -409,7 +410,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * (unsigned char *)esph - skb->data, assoclen + ivlen + esp->clen + alen); if (unlikely(err < 0)) - goto error; + goto error_free; } if ((x->props.flags & XFRM_STATE_ESN)) @@ -442,8 +443,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * if (sg != dsg) esp_ssg_unref(x, tmp); - kfree(tmp); +error_free: + kfree(tmp); error: return err; } @@ -695,8 +697,10 @@ skip_cow: sg_init_table(sg, nfrags); err = skb_to_sgvec(skb, sg, 0, skb->len); - if (unlikely(err < 0)) + if (unlikely(err < 0)) { + kfree(tmp); goto out; + } skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index e0666016a764..50112324fa5c 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -257,7 +257,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); err = esp_output_tail(x, skb, &esp); - if (err < 0) + if (err) return err; secpath_reset(skb); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b8d18171cca3..ec3a9ce281a6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1083,15 +1083,17 @@ struct fib_info *fib_create_info(struct fib_config *cfg, fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (!fi) goto failure; - fib_info_cnt++; if (cfg->fc_mx) { fi->fib_metrics = kzalloc(sizeof(*fi->fib_metrics), GFP_KERNEL); - if (!fi->fib_metrics) - goto failure; + if (unlikely(!fi->fib_metrics)) { + kfree(fi); + return ERR_PTR(err); + } atomic_set(&fi->fib_metrics->refcnt, 1); - } else + } else { fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; - + } + fib_info_cnt++; fi->fib_net = net; fi->fib_protocol = cfg->fc_protocol; fi->fib_scope = cfg->fc_scope; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 498706b072fb..caf2f1101d02 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1007,10 +1007,18 @@ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + struct net_device *dev = skb->dev; + struct in_device *in_dev; int len = skb->len; bool dropped = true; + if (netif_is_l3_master(dev)) { + dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); + if (!dev) + goto drop; + } + + in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 0bc3c3d73e61..9e9d9afd18f7 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -268,14 +268,14 @@ unsigned int arpt_do_table(struct sk_buff *skb, acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); - /* Target might have changed stuff. */ - arp = arp_hdr(skb); - - if (verdict == XT_CONTINUE) + if (verdict == XT_CONTINUE) { + /* Target might have changed stuff. */ + arp = arp_hdr(skb); e = arpt_next_entry(e); - else + } else { /* Verdict */ break; + } } while (!acpar.hotdrop); xt_write_recseq_end(addend); local_bh_enable(); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2a55a40211cb..622ed2887cd5 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -352,13 +352,14 @@ ipt_do_table(struct sk_buff *skb, acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); - /* Target might have changed stuff. */ - ip = ip_hdr(skb); - if (verdict == XT_CONTINUE) + if (verdict == XT_CONTINUE) { + /* Target might have changed stuff. */ + ip = ip_hdr(skb); e = ipt_next_entry(e); - else + } else { /* Verdict */ break; + } } while (!acpar.hotdrop); xt_write_recseq_end(addend); diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 7d72decb80f9..efaa04dcc80e 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -117,7 +117,8 @@ clusterip_config_entry_put(struct net *net, struct clusterip_config *c) * functions are also incrementing the refcount on their own, * so it's safe to remove the entry even if it's in use. */ #ifdef CONFIG_PROC_FS - proc_remove(c->pde); + if (cn->procdir) + proc_remove(c->pde); #endif return; } @@ -815,6 +816,7 @@ static void clusterip_net_exit(struct net *net) #ifdef CONFIG_PROC_FS struct clusterip_net *cn = net_generic(net, clusterip_net_id); proc_remove(cn->procdir); + cn->procdir = NULL; #endif nf_unregister_net_hook(net, &cip_arp_ops); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0383e66f59bc..2331de20ca50 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1267,7 +1267,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) if (mtu) return mtu; - mtu = dst->dev->mtu; + mtu = READ_ONCE(dst->dev->mtu); if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { if (rt->rt_uses_gateway && mtu > 576) @@ -2750,26 +2750,34 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); + else + skb_dst_set(skb, &rt->dst); } if (err) goto errout_free; - skb_dst_set(skb, &rt->dst); if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = rt->rt_table_id; - if (rtm->rtm_flags & RTM_F_FIB_MATCH) + if (rtm->rtm_flags & RTM_F_FIB_MATCH) { + if (!res.fi) { + err = fib_props[res.type].error; + if (!err) + err = -EHOSTUNREACH; + goto errout_free; + } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, table_id, rt->rt_type, res.prefix, res.prefixlen, fl4.flowi4_tos, res.fi, 0); - else + } else { err = rt_fill_info(net, dst, src, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); + } if (err < 0) goto errout_free; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 71ce33decd97..a3e91b552edc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2481,7 +2481,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, name[val] = 0; lock_sock(sk); - err = tcp_set_congestion_control(sk, name, true); + err = tcp_set_congestion_control(sk, name, true, true); release_sock(sk); return err; } diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index fde983f6376b..421ea1b918da 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -189,8 +189,8 @@ void tcp_init_congestion_control(struct sock *sk) INET_ECN_dontxmit(sk); } -void tcp_reinit_congestion_control(struct sock *sk, - const struct tcp_congestion_ops *ca) +static void tcp_reinit_congestion_control(struct sock *sk, + const struct tcp_congestion_ops *ca) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -338,7 +338,7 @@ out: * tcp_reinit_congestion_control (if the current congestion control was * already initialized. */ -int tcp_set_congestion_control(struct sock *sk, const char *name, bool load) +int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, bool reinit) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; @@ -360,9 +360,18 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load) if (!ca) { err = -ENOENT; } else if (!load) { - icsk->icsk_ca_ops = ca; - if (!try_module_get(ca->owner)) + const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops; + + if (try_module_get(ca->owner)) { + if (reinit) { + tcp_reinit_congestion_control(sk, ca); + } else { + icsk->icsk_ca_ops = ca; + module_put(old_ca->owner); + } + } else { err = -EBUSY; + } } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))) { err = -EPERM; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 53de1424c13c..bab7f0493098 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3009,8 +3009,7 @@ void tcp_rearm_rto(struct sock *sk) /* delta_us may not be positive if the socket is locked * when the retrans timer fires and is rescheduled. */ - if (delta_us > 0) - rto = usecs_to_jiffies(delta_us); + rto = usecs_to_jiffies(max_t(int, delta_us, 1)); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, TCP_RTO_MAX); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a20e7f03d5f7..e9252c7df809 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1722,6 +1722,8 @@ process: */ sock_hold(sk); refcounted = true; + if (tcp_filter(sk, skb)) + goto discard_and_relse; nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); @@ -1729,8 +1731,6 @@ process: } if (nsk == sk) { reqsk_put(req); - } else if (tcp_filter(sk, skb)) { - goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 2417f55374c5..6bb9e14c710a 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -122,14 +122,14 @@ int tcp_set_ulp(struct sock *sk, const char *name) ulp_ops = __tcp_ulp_find_autoload(name); if (!ulp_ops) - err = -ENOENT; - else - err = ulp_ops->init(sk); + return -ENOENT; - if (err) - goto out; + err = ulp_ops->init(sk); + if (err) { + module_put(ulp_ops->owner); + return err; + } icsk->icsk_ulp_ops = ulp_ops; - out: - return err; + return 0; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a7c804f73990..62344804baae 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1176,7 +1176,7 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif - if (likely(!skb->_skb_refdst)) + if (likely(!skb->_skb_refdst && !skb_sec_path(skb))) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } @@ -1574,7 +1574,8 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, return ip_recv_error(sk, msg, len, addr_len); try_again: - peeking = off = sk_peek_offset(sk, flags); + peeking = flags & MSG_PEEK; + off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err); if (!skb) return err; @@ -1928,14 +1929,16 @@ drop: /* For TCP sockets, sk_rx_dst is protected by socket lock * For UDP, we use xchg() to guard against concurrent changes. */ -void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) +bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) { struct dst_entry *old; if (dst_hold_safe(dst)) { old = xchg(&sk->sk_rx_dst, dst); dst_release(old); + return old != dst; } + return false; } EXPORT_SYMBOL(udp_sk_rx_dst_set); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3c46e9513a31..936e9ab4dda5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5556,7 +5556,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) * our DAD process, so we don't need * to do it again */ - if (!(ifp->rt->rt6i_node)) + if (!rcu_access_pointer(ifp->rt->rt6i_node)) ip6_ins_rt(ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 9ed35473dcb5..ab64f367d11c 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -226,7 +226,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info int tailen = esp->tailen; if (!skb_cloned(skb)) { - if (tailen <= skb_availroom(skb)) { + if (tailen <= skb_tailroom(skb)) { nfrags = 1; trailer = skb; tail = skb_tail_pointer(trailer); @@ -260,8 +260,6 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info kunmap_atomic(vaddr); - spin_unlock_bh(&x->lock); - nfrags = skb_shinfo(skb)->nr_frags; __skb_fill_page_desc(skb, nfrags, page, pfrag->offset, @@ -269,6 +267,9 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info skb_shinfo(skb)->nr_frags = ++nfrags; pfrag->offset = pfrag->offset + allocsize; + + spin_unlock_bh(&x->lock); + nfrags++; skb->len += tailen; @@ -345,7 +346,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info (unsigned char *)esph - skb->data, assoclen + ivlen + esp->clen + alen); if (unlikely(err < 0)) - goto error; + goto error_free; if (!esp->inplace) { int allocsize; @@ -356,7 +357,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info spin_lock_bh(&x->lock); if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) { spin_unlock_bh(&x->lock); - goto error; + goto error_free; } skb_shinfo(skb)->nr_frags = 1; @@ -373,7 +374,7 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info (unsigned char *)esph - skb->data, assoclen + ivlen + esp->clen + alen); if (unlikely(err < 0)) - goto error; + goto error_free; } if ((x->props.flags & XFRM_STATE_ESN)) @@ -406,8 +407,9 @@ int esp6_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info if (sg != dsg) esp_ssg_unref(x, tmp); - kfree(tmp); +error_free: + kfree(tmp); error: return err; } diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index f02f131f6435..1cf437f75b0b 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -286,7 +286,7 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32)); err = esp6_output_tail(x, skb, &esp); - if (err < 0) + if (err) return err; secpath_reset(skb); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index ebb299cf72b7..e1c85bb4eac0 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -148,11 +148,23 @@ static struct fib6_node *node_alloc(void) return fn; } -static void node_free(struct fib6_node *fn) +static void node_free_immediate(struct fib6_node *fn) { kmem_cache_free(fib6_node_kmem, fn); } +static void node_free_rcu(struct rcu_head *head) +{ + struct fib6_node *fn = container_of(head, struct fib6_node, rcu); + + kmem_cache_free(fib6_node_kmem, fn); +} + +static void node_free(struct fib6_node *fn) +{ + call_rcu(&fn->rcu, node_free_rcu); +} + static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) { int cpu; @@ -601,9 +613,9 @@ insert_above: if (!in || !ln) { if (in) - node_free(in); + node_free_immediate(in); if (ln) - node_free(ln); + node_free_immediate(ln); return ERR_PTR(-ENOMEM); } @@ -877,7 +889,7 @@ add: rt->dst.rt6_next = iter; *ins = rt; - rt->rt6i_node = fn; + rcu_assign_pointer(rt->rt6i_node, fn); atomic_inc(&rt->rt6i_ref); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); @@ -903,7 +915,7 @@ add: return err; *ins = rt; - rt->rt6i_node = fn; + rcu_assign_pointer(rt->rt6i_node, fn); rt->dst.rt6_next = iter->dst.rt6_next; atomic_inc(&rt->rt6i_ref); if (!info->skip_notify) @@ -914,6 +926,8 @@ add: } nsiblings = iter->rt6i_nsiblings; fib6_purge_rt(iter, fn, info->nl_net); + if (fn->rr_ptr == iter) + fn->rr_ptr = NULL; rt6_release(iter); if (nsiblings) { @@ -926,6 +940,8 @@ add: if (rt6_qualify_for_ecmp(iter)) { *ins = iter->dst.rt6_next; fib6_purge_rt(iter, fn, info->nl_net); + if (fn->rr_ptr == iter) + fn->rr_ptr = NULL; rt6_release(iter); nsiblings--; } else { @@ -1014,7 +1030,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, /* Create subtree root node */ sfn = node_alloc(); if (!sfn) - goto st_failure; + goto failure; sfn->leaf = info->nl_net->ipv6.ip6_null_entry; atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); @@ -1031,12 +1047,12 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (IS_ERR(sn)) { /* If it is failed, discard just allocated - root, and then (in st_failure) stale node + root, and then (in failure) stale node in main tree. */ - node_free(sfn); + node_free_immediate(sfn); err = PTR_ERR(sn); - goto st_failure; + goto failure; } /* Now link new subtree to main tree */ @@ -1051,7 +1067,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (IS_ERR(sn)) { err = PTR_ERR(sn); - goto st_failure; + goto failure; } } @@ -1092,18 +1108,17 @@ out: atomic_inc(&pn->leaf->rt6i_ref); } #endif - /* Always release dst as dst->__refcnt is guaranteed - * to be taken before entering this function - */ - dst_release_immediate(&rt->dst); + goto failure; } return err; -#ifdef CONFIG_IPV6_SUBTREES - /* Subtree creation failed, probably main tree node - is orphan. If it is, shoot it. +failure: + /* fn->leaf could be NULL if fn is an intermediate node and we + * failed to add the new route to it in both subtree creation + * failure and fib6_add_rt2node() failure case. + * In both cases, fib6_repair_tree() should be called to fix + * fn->leaf. */ -st_failure: if (fn && !(fn->fn_flags & (RTN_RTINFO|RTN_ROOT))) fib6_repair_tree(info->nl_net, fn); /* Always release dst as dst->__refcnt is guaranteed @@ -1111,7 +1126,6 @@ st_failure: */ dst_release_immediate(&rt->dst); return err; -#endif } /* @@ -1466,8 +1480,9 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, int fib6_del(struct rt6_info *rt, struct nl_info *info) { + struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, + lockdep_is_held(&rt->rt6i_table->tb6_lock)); struct net *net = info->nl_net; - struct fib6_node *fn = rt->rt6i_node; struct rt6_info **rtp; #if RT6_DEBUG >= 2 @@ -1656,7 +1671,9 @@ static int fib6_clean_node(struct fib6_walker *w) if (res) { #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", - __func__, rt, rt->rt6i_node, res); + __func__, rt, + rcu_access_pointer(rt->rt6i_node), + res); #endif continue; } @@ -1778,8 +1795,10 @@ static int fib6_age(struct rt6_info *rt, void *arg) } gc_args->more++; } else if (rt->rt6i_flags & RTF_CACHE) { + if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) + rt->dst.obsolete = DST_OBSOLETE_KILL; if (atomic_read(&rt->dst.__refcnt) == 1 && - time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { + rt->dst.obsolete == DST_OBSOLETE_KILL) { RT6_TRACE("aging clone %p\n", rt); return -1; } else if (rt->rt6i_flags & RTF_GATEWAY) { diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 02d795fe3d7f..a5e466d4e093 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -242,7 +242,6 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, pktopt = xchg(&np->pktoptions, NULL); kfree_skb(pktopt); - sk->sk_destruct = inet_sock_destruct; /* * ... and add it to the refcnt debug socks count * in the new family. -acme diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index abb2c307fbe8..a338bbc33cf3 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -86,7 +86,6 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) while (offset <= packet_len) { struct ipv6_opt_hdr *exthdr; - unsigned int len; switch (**nexthdr) { @@ -112,10 +111,9 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) + offset); - len = ipv6_optlen(exthdr); - if (len + offset >= IPV6_MAXPLEN) + offset += ipv6_optlen(exthdr); + if (offset > IPV6_MAXPLEN) return -EINVAL; - offset += len; *nexthdr = &exthdr->nexthdr; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index a640fbcba15d..2d0e7798c793 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -417,14 +417,11 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, struct net_device *loopback_dev = dev_net(dev)->loopback_dev; - if (dev != loopback_dev) { - if (idev && idev->dev == dev) { - struct inet6_dev *loopback_idev = - in6_dev_get(loopback_dev); - if (loopback_idev) { - rt->rt6i_idev = loopback_idev; - in6_dev_put(idev); - } + if (idev && idev->dev != loopback_dev) { + struct inet6_dev *loopback_idev = in6_dev_get(loopback_dev); + if (loopback_idev) { + rt->rt6i_idev = loopback_idev; + in6_dev_put(idev); } } } @@ -443,7 +440,8 @@ static bool rt6_check_expired(const struct rt6_info *rt) if (time_after(jiffies, rt->dst.expires)) return true; } else if (rt->dst.from) { - return rt6_check_expired((struct rt6_info *) rt->dst.from); + return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK || + rt6_check_expired((struct rt6_info *)rt->dst.from); } return false; } @@ -1292,7 +1290,9 @@ static void rt6_dst_from_metrics_check(struct rt6_info *rt) static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) { - if (!rt->rt6i_node || (rt->rt6i_node->fn_sernum != cookie)) + u32 rt_cookie = 0; + + if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) @@ -1360,8 +1360,14 @@ static void ip6_link_failure(struct sk_buff *skb) if (rt->rt6i_flags & RTF_CACHE) { if (dst_hold_safe(&rt->dst)) ip6_del_rt(rt); - } else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT)) { - rt->rt6i_node->fn_sernum = -1; + } else { + struct fib6_node *fn; + + rcu_read_lock(); + fn = rcu_dereference(rt->rt6i_node); + if (fn && (rt->rt6i_flags & RTF_DEFAULT)) + fn->fn_sernum = -1; + rcu_read_unlock(); } } } @@ -1378,7 +1384,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { return !(rt->rt6i_flags & RTF_CACHE) && - (rt->rt6i_flags & RTF_PCPU || rt->rt6i_node); + (rt->rt6i_flags & RTF_PCPU || + rcu_access_pointer(rt->rt6i_node)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, @@ -3724,10 +3731,10 @@ static int ip6_route_dev_notify(struct notifier_block *this, /* NETDEV_UNREGISTER could be fired for multiple times by * netdev_wait_allrefs(). Make sure we only call this once. */ - in6_dev_put(net->ipv6.ip6_null_entry->rt6i_idev); + in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES - in6_dev_put(net->ipv6.ip6_prohibit_entry->rt6i_idev); - in6_dev_put(net->ipv6.ip6_blk_hole_entry->rt6i_idev); + in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev); + in6_dev_put_clear(&net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2521690d62d6..206210125fd7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1456,6 +1456,8 @@ process: } sock_hold(sk); refcounted = true; + if (tcp_filter(sk, skb)) + goto discard_and_relse; nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); @@ -1464,8 +1466,6 @@ process: if (nsk == sk) { reqsk_put(req); tcp_v6_restore_cb(skb); - } else if (tcp_filter(sk, skb)) { - goto discard_and_relse; } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); goto discard_and_relse; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 578142b7ca3e..d6886228e1d0 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -362,7 +362,8 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, return ipv6_recv_rxpmtu(sk, msg, len, addr_len); try_again: - peeking = off = sk_peek_offset(sk, flags); + peeking = flags & MSG_PEEK; + off = sk_peek_offset(sk, flags); skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err); if (!skb) return err; @@ -767,6 +768,15 @@ start_lookup: return 0; } +static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) +{ + if (udp_sk_rx_dst_set(sk, dst)) { + const struct rt6_info *rt = (const struct rt6_info *)dst; + + inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); + } +} + int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { @@ -816,7 +826,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int ret; if (unlikely(sk->sk_rx_dst != dst)) - udp_sk_rx_dst_set(sk, dst); + udp6_sk_rx_dst_set(sk, dst); ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 2e6990f8b80b..23fa7c8b09a5 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -2213,7 +2213,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct irda_sock *self = irda_sk(sk); - struct irda_device_list list; + struct irda_device_list list = { 0 }; struct irda_device_info *discoveries; struct irda_ias_set * ias_opt; /* IAS get/query params */ struct ias_object * ias_obj; /* Object in IAS */ diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index da49191f7ad0..4abf6287d7e1 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1383,6 +1383,10 @@ static int kcm_attach(struct socket *sock, struct socket *csock, if (!csk) return -EINVAL; + /* We must prevent loops or risk deadlock ! */ + if (csk->sk_family == PF_KCM) + return -EOPNOTSUPP; + psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL); if (!psock) return -ENOMEM; diff --git a/net/key/af_key.c b/net/key/af_key.c index ca9d3ae665e7..98f4d8211b9a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -228,7 +228,7 @@ static int pfkey_broadcast_one(struct sk_buff *skb, struct sk_buff **skb2, #define BROADCAST_ONE 1 #define BROADCAST_REGISTERED 2 #define BROADCAST_PROMISC_ONLY 4 -static int pfkey_broadcast(struct sk_buff *skb, +static int pfkey_broadcast(struct sk_buff *skb, gfp_t allocation, int broadcast_flags, struct sock *one_sk, struct net *net) { @@ -278,7 +278,7 @@ static int pfkey_broadcast(struct sk_buff *skb, rcu_read_unlock(); if (one_sk != NULL) - err = pfkey_broadcast_one(skb, &skb2, GFP_KERNEL, one_sk); + err = pfkey_broadcast_one(skb, &skb2, allocation, one_sk); kfree_skb(skb2); kfree_skb(skb); @@ -311,7 +311,7 @@ static int pfkey_do_dump(struct pfkey_sock *pfk) hdr = (struct sadb_msg *) pfk->dump.skb->data; hdr->sadb_msg_seq = 0; hdr->sadb_msg_errno = rc; - pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = NULL; } @@ -355,7 +355,7 @@ static int pfkey_error(const struct sadb_msg *orig, int err, struct sock *sk) hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk)); + pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ONE, sk, sock_net(sk)); return 0; } @@ -1389,7 +1389,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_ xfrm_state_put(x); - pfkey_broadcast(resp_skb, BROADCAST_ONE, sk, net); + pfkey_broadcast(resp_skb, GFP_KERNEL, BROADCAST_ONE, sk, net); return 0; } @@ -1476,7 +1476,7 @@ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) hdr->sadb_msg_seq = c->seq; hdr->sadb_msg_pid = c->portid; - pfkey_broadcast(skb, BROADCAST_ALL, NULL, xs_net(x)); + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x)); return 0; } @@ -1589,7 +1589,7 @@ static int pfkey_get(struct sock *sk, struct sk_buff *skb, const struct sadb_msg out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, BROADCAST_ONE, sk, sock_net(sk)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); return 0; } @@ -1694,8 +1694,8 @@ static int pfkey_register(struct sock *sk, struct sk_buff *skb, const struct sad return -ENOBUFS; } - pfkey_broadcast(supp_skb, BROADCAST_REGISTERED, sk, sock_net(sk)); - + pfkey_broadcast(supp_skb, GFP_KERNEL, BROADCAST_REGISTERED, sk, + sock_net(sk)); return 0; } @@ -1712,7 +1712,8 @@ static int unicast_flush_resp(struct sock *sk, const struct sadb_msg *ihdr) hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); - return pfkey_broadcast(skb, BROADCAST_ONE, sk, sock_net(sk)); + return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, + sock_net(sk)); } static int key_notify_sa_flush(const struct km_event *c) @@ -1733,7 +1734,7 @@ static int key_notify_sa_flush(const struct km_event *c) hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; - pfkey_broadcast(skb, BROADCAST_ALL, NULL, c->net); + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } @@ -1790,7 +1791,7 @@ static int dump_sa(struct xfrm_state *x, int count, void *ptr) out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) - pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; @@ -1878,7 +1879,7 @@ static int pfkey_promisc(struct sock *sk, struct sk_buff *skb, const struct sadb new_hdr->sadb_msg_errno = 0; } - pfkey_broadcast(skb, BROADCAST_ALL, NULL, sock_net(sk)); + pfkey_broadcast(skb, GFP_KERNEL, BROADCAST_ALL, NULL, sock_net(sk)); return 0; } @@ -2206,7 +2207,7 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = c->seq; out_hdr->sadb_msg_pid = c->portid; - pfkey_broadcast(out_skb, BROADCAST_ALL, NULL, xp_net(xp)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp)); return 0; } @@ -2426,7 +2427,7 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = hdr->sadb_msg_seq; out_hdr->sadb_msg_pid = hdr->sadb_msg_pid; - pfkey_broadcast(out_skb, BROADCAST_ONE, sk, xp_net(xp)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ONE, sk, xp_net(xp)); err = 0; out: @@ -2682,7 +2683,7 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) - pfkey_broadcast(pfk->dump.skb, BROADCAST_ONE, + pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, &pfk->sk, sock_net(&pfk->sk)); pfk->dump.skb = out_skb; @@ -2739,7 +2740,7 @@ static int key_notify_policy_flush(const struct km_event *c) hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); hdr->sadb_msg_reserved = 0; - pfkey_broadcast(skb_out, BROADCAST_ALL, NULL, c->net); + pfkey_broadcast(skb_out, GFP_ATOMIC, BROADCAST_ALL, NULL, c->net); return 0; } @@ -2803,7 +2804,7 @@ static int pfkey_process(struct sock *sk, struct sk_buff *skb, const struct sadb void *ext_hdrs[SADB_EXT_MAX]; int err; - pfkey_broadcast(skb_clone(skb, GFP_KERNEL), + pfkey_broadcast(skb_clone(skb, GFP_KERNEL), GFP_KERNEL, BROADCAST_PROMISC_ONLY, NULL, sock_net(sk)); memset(ext_hdrs, 0, sizeof(ext_hdrs)); @@ -3024,7 +3025,8 @@ static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c) out_hdr->sadb_msg_seq = 0; out_hdr->sadb_msg_pid = 0; - pfkey_broadcast(out_skb, BROADCAST_REGISTERED, NULL, xs_net(x)); + pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, + xs_net(x)); return 0; } @@ -3212,7 +3214,8 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_ctx->ctx_len); } - return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x)); + return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, + xs_net(x)); } static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt, @@ -3408,7 +3411,8 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, n_port->sadb_x_nat_t_port_port = sport; n_port->sadb_x_nat_t_port_reserved = 0; - return pfkey_broadcast(skb, BROADCAST_REGISTERED, NULL, xs_net(x)); + return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_REGISTERED, NULL, + xs_net(x)); } #ifdef CONFIG_NET_KEY_MIGRATE @@ -3599,7 +3603,7 @@ static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* broadcast migrate message to sockets */ - pfkey_broadcast(skb, BROADCAST_ALL, NULL, &init_net); + pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, &init_net); return 0; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index b0c2d4ae781d..90165a6874bc 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -113,7 +113,6 @@ struct l2tp_net { spinlock_t l2tp_session_hlist_lock; }; -static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel); static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk) { @@ -127,39 +126,6 @@ static inline struct l2tp_net *l2tp_pernet(const struct net *net) return net_generic(net, l2tp_net_id); } -/* Tunnel reference counts. Incremented per session that is added to - * the tunnel. - */ -static inline void l2tp_tunnel_inc_refcount_1(struct l2tp_tunnel *tunnel) -{ - refcount_inc(&tunnel->ref_count); -} - -static inline void l2tp_tunnel_dec_refcount_1(struct l2tp_tunnel *tunnel) -{ - if (refcount_dec_and_test(&tunnel->ref_count)) - l2tp_tunnel_free(tunnel); -} -#ifdef L2TP_REFCNT_DEBUG -#define l2tp_tunnel_inc_refcount(_t) \ -do { \ - pr_debug("l2tp_tunnel_inc_refcount: %s:%d %s: cnt=%d\n", \ - __func__, __LINE__, (_t)->name, \ - refcount_read(&_t->ref_count)); \ - l2tp_tunnel_inc_refcount_1(_t); \ -} while (0) -#define l2tp_tunnel_dec_refcount(_t) \ -do { \ - pr_debug("l2tp_tunnel_dec_refcount: %s:%d %s: cnt=%d\n", \ - __func__, __LINE__, (_t)->name, \ - refcount_read(&_t->ref_count)); \ - l2tp_tunnel_dec_refcount_1(_t); \ -} while (0) -#else -#define l2tp_tunnel_inc_refcount(t) l2tp_tunnel_inc_refcount_1(t) -#define l2tp_tunnel_dec_refcount(t) l2tp_tunnel_dec_refcount_1(t) -#endif - /* Session hash global list for L2TPv3. * The session_id SHOULD be random according to RFC3931, but several * L2TP implementations use incrementing session_ids. So we do a real @@ -229,6 +195,27 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id) return &tunnel->session_hlist[hash_32(session_id, L2TP_HASH_BITS)]; } +/* Lookup a tunnel. A new reference is held on the returned tunnel. */ +struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) +{ + const struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_tunnel *tunnel; + + rcu_read_lock_bh(); + list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { + if (tunnel->tunnel_id == tunnel_id) { + l2tp_tunnel_inc_refcount(tunnel); + rcu_read_unlock_bh(); + + return tunnel; + } + } + rcu_read_unlock_bh(); + + return NULL; +} +EXPORT_SYMBOL_GPL(l2tp_tunnel_get); + /* Lookup a session. A new reference is held on the returned session. * Optionally calls session->ref() too if do_ref is true. */ @@ -1348,17 +1335,6 @@ static void l2tp_udp_encap_destroy(struct sock *sk) } } -/* Really kill the tunnel. - * Come here only when all sessions have been cleared from the tunnel. - */ -static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) -{ - BUG_ON(refcount_read(&tunnel->ref_count) != 0); - BUG_ON(tunnel->sock != NULL); - l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: free...\n", tunnel->name); - kfree_rcu(tunnel, rcu); -} - /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { @@ -1844,6 +1820,8 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn l2tp_session_set_header_len(session, tunnel->version); + refcount_set(&session->ref_count, 1); + err = l2tp_session_add_to_tunnel(tunnel, session); if (err) { kfree(session); @@ -1851,10 +1829,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn return ERR_PTR(err); } - /* Bump the reference count. The session context is deleted - * only when this drops to zero. - */ - refcount_set(&session->ref_count, 1); l2tp_tunnel_inc_refcount(tunnel); /* Ensure tunnel socket isn't deleted */ diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index cdb6e3327f74..9101297f27ad 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -231,6 +231,8 @@ out: return tunnel; } +struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id); + struct l2tp_session *l2tp_session_get(const struct net *net, struct l2tp_tunnel *tunnel, u32 session_id, bool do_ref); @@ -269,6 +271,17 @@ int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); +static inline void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) +{ + refcount_inc(&tunnel->ref_count); +} + +static inline void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) +{ + if (refcount_dec_and_test(&tunnel->ref_count)) + kfree_rcu(tunnel, rcu); +} + /* Session reference counts. Incremented when code obtains a reference * to a session. */ diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 12cfcd0ca807..57427d430f10 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -65,10 +65,12 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info, (info->attrs[L2TP_ATTR_CONN_ID])) { tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]); session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]); - tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel) + tunnel = l2tp_tunnel_get(net, tunnel_id); + if (tunnel) { session = l2tp_session_get(net, tunnel, session_id, do_ref); + l2tp_tunnel_dec_refcount(tunnel); + } } return session; @@ -271,8 +273,8 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info } tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]); - tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel == NULL) { + tunnel = l2tp_tunnel_get(net, tunnel_id); + if (!tunnel) { ret = -ENODEV; goto out; } @@ -282,6 +284,8 @@ static int l2tp_nl_cmd_tunnel_delete(struct sk_buff *skb, struct genl_info *info (void) l2tp_tunnel_delete(tunnel); + l2tp_tunnel_dec_refcount(tunnel); + out: return ret; } @@ -299,8 +303,8 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info } tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]); - tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel == NULL) { + tunnel = l2tp_tunnel_get(net, tunnel_id); + if (!tunnel) { ret = -ENODEV; goto out; } @@ -311,6 +315,8 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info ret = l2tp_tunnel_notify(&l2tp_nl_family, info, tunnel, L2TP_CMD_TUNNEL_MODIFY); + l2tp_tunnel_dec_refcount(tunnel); + out: return ret; } @@ -438,34 +444,37 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info) if (!info->attrs[L2TP_ATTR_CONN_ID]) { ret = -EINVAL; - goto out; + goto err; } tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]); - tunnel = l2tp_tunnel_find(net, tunnel_id); - if (tunnel == NULL) { - ret = -ENODEV; - goto out; - } - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; - goto out; + goto err; + } + + tunnel = l2tp_tunnel_get(net, tunnel_id); + if (!tunnel) { + ret = -ENODEV; + goto err_nlmsg; } ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel, L2TP_CMD_TUNNEL_GET); if (ret < 0) - goto err_out; + goto err_nlmsg_tunnel; + + l2tp_tunnel_dec_refcount(tunnel); return genlmsg_unicast(net, msg, info->snd_portid); -err_out: +err_nlmsg_tunnel: + l2tp_tunnel_dec_refcount(tunnel); +err_nlmsg: nlmsg_free(msg); - -out: +err: return ret; } @@ -509,8 +518,9 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf ret = -EINVAL; goto out; } + tunnel_id = nla_get_u32(info->attrs[L2TP_ATTR_CONN_ID]); - tunnel = l2tp_tunnel_find(net, tunnel_id); + tunnel = l2tp_tunnel_get(net, tunnel_id); if (!tunnel) { ret = -ENODEV; goto out; @@ -518,24 +528,24 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if (!info->attrs[L2TP_ATTR_SESSION_ID]) { ret = -EINVAL; - goto out; + goto out_tunnel; } session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]); if (!info->attrs[L2TP_ATTR_PEER_SESSION_ID]) { ret = -EINVAL; - goto out; + goto out_tunnel; } peer_session_id = nla_get_u32(info->attrs[L2TP_ATTR_PEER_SESSION_ID]); if (!info->attrs[L2TP_ATTR_PW_TYPE]) { ret = -EINVAL; - goto out; + goto out_tunnel; } cfg.pw_type = nla_get_u16(info->attrs[L2TP_ATTR_PW_TYPE]); if (cfg.pw_type >= __L2TP_PWTYPE_MAX) { ret = -EINVAL; - goto out; + goto out_tunnel; } if (tunnel->version > 2) { @@ -557,7 +567,7 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf u16 len = nla_len(info->attrs[L2TP_ATTR_COOKIE]); if (len > 8) { ret = -EINVAL; - goto out; + goto out_tunnel; } cfg.cookie_len = len; memcpy(&cfg.cookie[0], nla_data(info->attrs[L2TP_ATTR_COOKIE]), len); @@ -566,7 +576,7 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf u16 len = nla_len(info->attrs[L2TP_ATTR_PEER_COOKIE]); if (len > 8) { ret = -EINVAL; - goto out; + goto out_tunnel; } cfg.peer_cookie_len = len; memcpy(&cfg.peer_cookie[0], nla_data(info->attrs[L2TP_ATTR_PEER_COOKIE]), len); @@ -609,7 +619,7 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if ((l2tp_nl_cmd_ops[cfg.pw_type] == NULL) || (l2tp_nl_cmd_ops[cfg.pw_type]->session_create == NULL)) { ret = -EPROTONOSUPPORT; - goto out; + goto out_tunnel; } /* Check that pseudowire-specific params are present */ @@ -619,7 +629,7 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf case L2TP_PWTYPE_ETH_VLAN: if (!info->attrs[L2TP_ATTR_VLAN_ID]) { ret = -EINVAL; - goto out; + goto out_tunnel; } break; case L2TP_PWTYPE_ETH: @@ -647,6 +657,8 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf } } +out_tunnel: + l2tp_tunnel_dec_refcount(tunnel); out: return ret; } diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 8708cbe8af5b..2b36eff5d97e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -7,7 +7,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation - * Copyright(c) 2015 Intel Deutschland GmbH + * Copyright(c) 2015-2017 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -466,3 +466,23 @@ void ieee80211_manage_rx_ba_offl(struct ieee80211_vif *vif, rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_manage_rx_ba_offl); + +void ieee80211_rx_ba_timer_expired(struct ieee80211_vif *vif, + const u8 *addr, unsigned int tid) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct ieee80211_local *local = sdata->local; + struct sta_info *sta; + + rcu_read_lock(); + sta = sta_info_get_bss(sdata, addr); + if (!sta) + goto unlock; + + set_bit(tid, sta->ampdu_mlme.tid_rx_timer_expired); + ieee80211_queue_work(&local->hw, &sta->ampdu_mlme.work); + + unlock: + rcu_read_unlock(); +} +EXPORT_SYMBOL(ieee80211_rx_ba_timer_expired); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index eb541786ccb7..b1d3740ae36a 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -441,7 +441,7 @@ nf_nat_setup_info(struct nf_conn *ct, else ct->status |= IPS_DST_NAT; - if (nfct_help(ct)) + if (nfct_help(ct) && !nfct_seqadj(ct)) if (!nfct_seqadj_ext_add(ct)) return NF_DROP; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index f5a7cb68694e..b89f4f65b2a0 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -305,7 +305,7 @@ static int nft_target_validate(const struct nft_ctx *ctx, const struct nf_hook_ops *ops = &basechain->ops[0]; hook_mask = 1 << ops->hooknum; - if (!(hook_mask & target->hooks)) + if (target->hooks && !(hook_mask & target->hooks)) return -EINVAL; ret = nft_compat_chain_validate_dependency(target->table, @@ -484,7 +484,7 @@ static int nft_match_validate(const struct nft_ctx *ctx, const struct nf_hook_ops *ops = &basechain->ops[0]; hook_mask = 1 << ops->hooknum; - if (!(hook_mask & match->hooks)) + if (match->hooks && !(hook_mask & match->hooks)) return -EINVAL; ret = nft_compat_chain_validate_dependency(match->table, diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 18dd57a52651..14538b1d4d11 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -65,19 +65,23 @@ static int nft_limit_init(struct nft_limit *limit, limit->nsecs = unit * NSEC_PER_SEC; if (limit->rate == 0 || limit->nsecs < unit) return -EOVERFLOW; - limit->tokens = limit->tokens_max = limit->nsecs; - - if (tb[NFTA_LIMIT_BURST]) { - u64 rate; + if (tb[NFTA_LIMIT_BURST]) limit->burst = ntohl(nla_get_be32(tb[NFTA_LIMIT_BURST])); + else + limit->burst = 0; + + if (limit->rate + limit->burst < limit->rate) + return -EOVERFLOW; - rate = limit->rate + limit->burst; - if (rate < limit->rate) - return -EOVERFLOW; + /* The token bucket size limits the number of tokens can be + * accumulated. tokens_max specifies the bucket size. + * tokens_max = unit * (rate + burst) / rate. + */ + limit->tokens = div_u64(limit->nsecs * (limit->rate + limit->burst), + limit->rate); + limit->tokens_max = limit->tokens; - limit->rate = rate; - } if (tb[NFTA_LIMIT_FLAGS]) { u32 flags = ntohl(nla_get_be32(tb[NFTA_LIMIT_FLAGS])); @@ -95,9 +99,8 @@ static int nft_limit_dump(struct sk_buff *skb, const struct nft_limit *limit, { u32 flags = limit->invert ? NFT_LIMIT_F_INV : 0; u64 secs = div_u64(limit->nsecs, NSEC_PER_SEC); - u64 rate = limit->rate - limit->burst; - if (nla_put_be64(skb, NFTA_LIMIT_RATE, cpu_to_be64(rate), + if (nla_put_be64(skb, NFTA_LIMIT_RATE, cpu_to_be64(limit->rate), NFTA_LIMIT_PAD) || nla_put_be64(skb, NFTA_LIMIT_UNIT, cpu_to_be64(secs), NFTA_LIMIT_PAD) || diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index e4610676299b..a54a556fcdb5 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1337,6 +1337,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb, goto out; } + OVS_CB(skb)->acts_origlen = acts->orig_len; err = do_execute_actions(dp, skb, key, acts->actions, acts->actions_len); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 45fe8c8a884d..6b44fe405282 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -381,7 +381,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, } static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info, - unsigned int hdrlen) + unsigned int hdrlen, int actions_attrlen) { size_t size = NLMSG_ALIGN(sizeof(struct ovs_header)) + nla_total_size(hdrlen) /* OVS_PACKET_ATTR_PACKET */ @@ -398,7 +398,7 @@ static size_t upcall_msg_size(const struct dp_upcall_info *upcall_info, /* OVS_PACKET_ATTR_ACTIONS */ if (upcall_info->actions_len) - size += nla_total_size(upcall_info->actions_len); + size += nla_total_size(actions_attrlen); /* OVS_PACKET_ATTR_MRU */ if (upcall_info->mru) @@ -465,7 +465,8 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb, else hlen = skb->len; - len = upcall_msg_size(upcall_info, hlen - cutlen); + len = upcall_msg_size(upcall_info, hlen - cutlen, + OVS_CB(skb)->acts_origlen); user_skb = genlmsg_new(len, GFP_ATOMIC); if (!user_skb) { err = -ENOMEM; diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 5d8dcd88815f..480600649d0b 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -99,11 +99,13 @@ struct datapath { * when a packet is received by OVS. * @mru: The maximum received fragement size; 0 if the packet is not * fragmented. + * @acts_origlen: The netlink size of the flow actions applied to this skb. * @cutlen: The number of bytes from the packet end to be removed. */ struct ovs_skb_cb { struct vport *input_vport; u16 mru; + u16 acts_origlen; u32 cutlen; }; #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 008a45ca3112..1c61af9af67d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2191,6 +2191,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct timespec ts; __u32 ts_status; bool is_drop_n_account = false; + bool do_vnet = false; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing @@ -2241,8 +2242,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; - if (po->has_vnet_hdr) + if (po->has_vnet_hdr) { netoff += sizeof(struct virtio_net_hdr); + do_vnet = true; + } macoff = netoff - maclen; } if (po->tp_version <= TPACKET_V2) { @@ -2259,8 +2262,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, skb_set_owner_r(copy_skb, sk); } snaplen = po->rx_ring.frame_size - macoff; - if ((int)snaplen < 0) + if ((int)snaplen < 0) { snaplen = 0; + do_vnet = false; + } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { @@ -2273,6 +2278,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; + do_vnet = false; } } spin_lock(&sk->sk_receive_queue.lock); @@ -2298,7 +2304,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } spin_unlock(&sk->sk_receive_queue.lock); - if (po->has_vnet_hdr) { + if (do_vnet) { if (virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true)) { diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index dd30d74824b0..ec3383f97d4c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -223,6 +223,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->call_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_call *call = b->call_backlog[tail]; + call->socket = rx; if (rx->discard_new_call) { _debug("discard %lx", call->user_call_ID); rx->discard_new_call(call, call->user_call_ID); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index d516ba8178b8..541707802a23 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -41,6 +41,7 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t, { struct xt_tgchk_param par; struct xt_target *target; + struct ipt_entry e = {}; int ret = 0; target = xt_request_find_target(AF_INET, t->u.user.name, @@ -52,6 +53,7 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t, memset(&par, 0, sizeof(par)); par.net = net; par.table = table; + par.entryinfo = &e; par.target = target; par.targinfo = t->data; par.hook_mask = hook; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 39da0c5801c9..6c5ea84d2682 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -205,7 +205,7 @@ static void tcf_chain_flush(struct tcf_chain *chain) { struct tcf_proto *tp; - if (*chain->p_filter_chain) + if (chain->p_filter_chain) RCU_INIT_POINTER(*chain->p_filter_chain, NULL); while ((tp = rtnl_dereference(chain->filter_chain)) != NULL) { RCU_INIT_POINTER(chain->filter_chain, tp->next); @@ -215,9 +215,15 @@ static void tcf_chain_flush(struct tcf_chain *chain) static void tcf_chain_destroy(struct tcf_chain *chain) { - list_del(&chain->list); - tcf_chain_flush(chain); - kfree(chain); + /* May be already removed from the list by the previous call. */ + if (!list_empty(&chain->list)) + list_del_init(&chain->list); + + /* There might still be a reference held when we got here from + * tcf_block_put. Wait for the user to drop reference before free. + */ + if (!chain->refcnt) + kfree(chain); } struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, @@ -288,8 +294,10 @@ void tcf_block_put(struct tcf_block *block) if (!block) return; - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) + list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { + tcf_chain_flush(chain); tcf_chain_destroy(chain); + } kfree(block); } EXPORT_SYMBOL(tcf_block_put); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index bd24a550e0f9..4fb5a3222d0d 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -286,9 +286,6 @@ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { - struct Qdisc *root = qdisc_dev(q)->qdisc; - - WARN_ON_ONCE(root == &noop_qdisc); ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); if (invisible) @@ -839,7 +836,7 @@ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) - refcount_inc(&new->refcnt); + qdisc_refcount_inc(new); if (!ingress) qdisc_destroy(old); @@ -850,7 +847,7 @@ skip: notify_and_destroy(net, skb, n, classid, dev->qdisc, new); if (new && !new->ops->attach) - refcount_inc(&new->refcnt); + qdisc_refcount_inc(new); dev->qdisc = new ? : &noop_qdisc; if (new && new->ops->attach) @@ -1259,7 +1256,7 @@ replay: if (q == p || (p && check_loop(q, p, 0))) return -ELOOP; - refcount_inc(&q->refcnt); + qdisc_refcount_inc(q); goto graft; } else { if (!q) diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 572fe2584e48..c403c87aff7a 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -572,8 +572,10 @@ static void atm_tc_destroy(struct Qdisc *sch) struct atm_flow_data *flow, *tmp; pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) + list_for_each_entry(flow, &p->flows, list) { tcf_block_put(flow->block); + flow->block = NULL; + } list_for_each_entry_safe(flow, tmp, &p->flows, list) { if (flow->ref > 1) diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 481036f6b54e..156c8a33c677 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1139,6 +1139,13 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) struct tc_ratespec *r; int err; + qdisc_watchdog_init(&q->watchdog, sch); + hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + q->delay_timer.function = cbq_undelay; + + if (!opt) + return -EINVAL; + err = nla_parse_nested(tb, TCA_CBQ_MAX, opt, cbq_policy, NULL); if (err < 0) return err; @@ -1177,9 +1184,6 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) q->link.avpkt = q->link.allot/2; q->link.minidle = -0x7FFFFFFF; - qdisc_watchdog_init(&q->watchdog, sch); - hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); - q->delay_timer.function = cbq_undelay; q->toplevel = TC_CBQ_MAXLEVEL; q->now = psched_get_time(); @@ -1431,8 +1435,10 @@ static void cbq_destroy(struct Qdisc *sch) * be bound to classes which have been destroyed already. --TGR '04 */ for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { tcf_block_put(cl->block); + cl->block = NULL; + } } for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 337f2d6d81e4..2c0c05f2cc34 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -491,10 +491,8 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt) if (!q->flows) return -ENOMEM; q->backlogs = kvzalloc(q->flows_cnt * sizeof(u32), GFP_KERNEL); - if (!q->backlogs) { - kvfree(q->flows); + if (!q->backlogs) return -ENOMEM; - } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 57ba406f1437..4ba6da5fb254 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -785,7 +785,7 @@ static void attach_default_qdiscs(struct net_device *dev) dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); dev->qdisc = txq->qdisc_sleeping; - refcount_inc(&dev->qdisc->refcnt); + qdisc_refcount_inc(dev->qdisc); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT); if (qdisc) { diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index b52f74610dc7..11ab8dace901 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1418,6 +1418,8 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) struct tc_hfsc_qopt *qopt; int err; + qdisc_watchdog_init(&q->watchdog, sch); + if (opt == NULL || nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); @@ -1428,6 +1430,10 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) return err; q->eligible = RB_ROOT; + err = tcf_block_get(&q->root.block, &q->root.filter_list); + if (err) + return err; + q->root.cl_common.classid = sch->handle; q->root.refcnt = 1; q->root.sched = q; @@ -1444,8 +1450,6 @@ hfsc_init_qdisc(struct Qdisc *sch, struct nlattr *opt) qdisc_class_hash_insert(&q->clhash, &q->root.cl_common); qdisc_class_hash_grow(sch, &q->clhash); - qdisc_watchdog_init(&q->watchdog, sch); - return 0; } @@ -1522,8 +1526,10 @@ hfsc_destroy_qdisc(struct Qdisc *sch) unsigned int i; for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode) { tcf_block_put(cl->block); + cl->block = NULL; + } } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 51d3ba682af9..73a53c08091b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -477,6 +477,9 @@ static void hhf_destroy(struct Qdisc *sch) kvfree(q->hhf_valid_bits[i]); } + if (!q->hh_flows) + return; + for (i = 0; i < HH_FLOWS_CNT; i++) { struct hh_flow_state *flow, *next; struct list_head *head = &q->hh_flows[i]; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 203286ab4427..5bf5177b2bd3 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1017,6 +1017,9 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) int err; int i; + qdisc_watchdog_init(&q->watchdog, sch); + INIT_WORK(&q->work, htb_work_func); + if (!opt) return -EINVAL; @@ -1041,8 +1044,6 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < TC_HTB_NUMPRIO; i++) INIT_LIST_HEAD(q->drops + i); - qdisc_watchdog_init(&q->watchdog, sch); - INIT_WORK(&q->work, htb_work_func); qdisc_skb_head_init(&q->direct_queue); if (tb[TCA_HTB_DIRECT_QLEN]) @@ -1258,8 +1259,10 @@ static void htb_destroy(struct Qdisc *sch) tcf_block_put(q->block); for (i = 0; i < q->clhash.hashsize; i++) { - hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) + hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { tcf_block_put(cl->block); + cl->block = NULL; + } } for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i], diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index f143b7bbaa0d..9c454f5d6c38 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -257,12 +257,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->max_bands; i++) q->queues[i] = &noop_qdisc; - err = multiq_tune(sch, opt); - - if (err) - kfree(q->queues); - - return err; + return multiq_tune(sch, opt); } static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 1b3dd6190e93..14d1724e0dc4 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -933,11 +933,11 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt) struct netem_sched_data *q = qdisc_priv(sch); int ret; + qdisc_watchdog_init(&q->watchdog, sch); + if (!opt) return -EINVAL; - qdisc_watchdog_init(&q->watchdog, sch); - q->loss_model = CLG_RANDOM; ret = netem_change(sch, opt); if (ret) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index f80ea2cc5f1f..fc69fc5956e9 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -437,6 +437,7 @@ congestion_drop: qdisc_drop(head, sch, to_free); slot_queue_add(slot, skb); + qdisc_tree_reduce_backlog(sch, 0, delta); return NET_XMIT_CN; } @@ -468,8 +469,10 @@ enqueue: /* Return Congestion Notification only if we dropped a packet * from this flow. */ - if (qlen != slot->qlen) + if (qlen != slot->qlen) { + qdisc_tree_reduce_backlog(sch, 0, dropped - qdisc_pkt_len(skb)); return NET_XMIT_CN; + } /* As we dropped a packet, better let upper stack know this */ qdisc_tree_reduce_backlog(sch, 1, dropped); @@ -713,13 +716,13 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) int i; int err; + setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, + (unsigned long)sch); + err = tcf_block_get(&q->block, &q->filter_list); if (err) return err; - setup_deferrable_timer(&q->perturb_timer, sfq_perturbation, - (unsigned long)sch); - for (i = 0; i < SFQ_MAX_DEPTH + 1; i++) { q->dep[i].next = i + SFQ_MAX_FLOWS; q->dep[i].prev = i + SFQ_MAX_FLOWS; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index b2e4b6ad241a..493270f0d5b0 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -425,12 +425,13 @@ static int tbf_init(struct Qdisc *sch, struct nlattr *opt) { struct tbf_sched_data *q = qdisc_priv(sch); + qdisc_watchdog_init(&q->watchdog, sch); + q->qdisc = &noop_qdisc; + if (opt == NULL) return -EINVAL; q->t_c = ktime_get_ns(); - qdisc_watchdog_init(&q->watchdog, sch); - q->qdisc = &noop_qdisc; return tbf_change(sch, opt); } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 2a186b201ad2..a4b6ffb61495 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -512,7 +512,9 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, { addr->sa.sa_family = AF_INET6; addr->v6.sin6_port = port; + addr->v6.sin6_flowinfo = 0; addr->v6.sin6_addr = *saddr; + addr->v6.sin6_scope_id = 0; } /* Compare addresses exactly. diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index 9a647214a91e..e99518e79b52 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -70,7 +70,8 @@ static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb, info = nla_data(attr); list_for_each_entry_rcu(laddr, address_list, list) { - memcpy(info, &laddr->a, addrlen); + memcpy(info, &laddr->a, sizeof(laddr->a)); + memset(info + sizeof(laddr->a), 0, addrlen - sizeof(laddr->a)); info += addrlen; } @@ -93,7 +94,9 @@ static int inet_diag_msg_sctpaddrs_fill(struct sk_buff *skb, info = nla_data(attr); list_for_each_entry(from, &asoc->peer.transport_addr_list, transports) { - memcpy(info, &from->ipaddr, addrlen); + memcpy(info, &from->ipaddr, sizeof(from->ipaddr)); + memset(info + sizeof(from->ipaddr), 0, + addrlen - sizeof(from->ipaddr)); info += addrlen; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 1db478e34520..8d760863bc41 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4538,8 +4538,7 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_ictrlchunks = asoc->stats.ictrlchunks; prim = asoc->peer.primary_path; - memcpy(&info->sctpi_p_address, &prim->ipaddr, - sizeof(struct sockaddr_storage)); + memcpy(&info->sctpi_p_address, &prim->ipaddr, sizeof(prim->ipaddr)); info->sctpi_p_state = prim->state; info->sctpi_p_cwnd = prim->cwnd; info->sctpi_p_srtt = prim->srtt; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 2b720fa35c4f..e18500151236 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -421,6 +421,9 @@ static void svc_data_ready(struct sock *sk) dprintk("svc: socket %p(inet %p), busy=%d\n", svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); + + /* Refer to svc_setup_socket() for details. */ + rmb(); svsk->sk_odata(sk); if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags)) svc_xprt_enqueue(&svsk->sk_xprt); @@ -437,6 +440,9 @@ static void svc_write_space(struct sock *sk) if (svsk) { dprintk("svc: socket %p(inet %p), write_space busy=%d\n", svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); + + /* Refer to svc_setup_socket() for details. */ + rmb(); svsk->sk_owspace(sk); svc_xprt_enqueue(&svsk->sk_xprt); } @@ -760,8 +766,12 @@ static void svc_tcp_listen_data_ready(struct sock *sk) dprintk("svc: socket %p TCP (listen) state change %d\n", sk, sk->sk_state); - if (svsk) + if (svsk) { + /* Refer to svc_setup_socket() for details. */ + rmb(); svsk->sk_odata(sk); + } + /* * This callback may called twice when a new connection * is established as a child socket inherits everything @@ -794,6 +804,8 @@ static void svc_tcp_state_change(struct sock *sk) if (!svsk) printk("svc: socket %p: no user data\n", sk); else { + /* Refer to svc_setup_socket() for details. */ + rmb(); svsk->sk_ostate(sk); if (sk->sk_state != TCP_ESTABLISHED) { set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); @@ -1381,12 +1393,18 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, return ERR_PTR(err); } - inet->sk_user_data = svsk; svsk->sk_sock = sock; svsk->sk_sk = inet; svsk->sk_ostate = inet->sk_state_change; svsk->sk_odata = inet->sk_data_ready; svsk->sk_owspace = inet->sk_write_space; + /* + * This barrier is necessary in order to prevent race condition + * with svc_data_ready(), svc_listen_data_ready() and others + * when calling callbacks above. + */ + wmb(); + inet->sk_user_data = svsk; /* Initialize the socket */ if (sock->type == SOCK_DGRAM) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index d174ee3254ee..89cd061c4468 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -65,6 +65,8 @@ static struct tipc_bearer *bearer_get(struct net *net, int bearer_id) } static void bearer_disable(struct net *net, struct tipc_bearer *b); +static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev); /** * tipc_media_find - locates specified media object by name @@ -428,6 +430,10 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, /* Associate TIPC bearer with L2 bearer */ rcu_assign_pointer(b->media_ptr, dev); + b->pt.dev = dev; + b->pt.type = htons(ETH_P_TIPC); + b->pt.func = tipc_l2_rcv_msg; + dev_add_pack(&b->pt); memset(&b->bcast_addr, 0, sizeof(b->bcast_addr)); memcpy(b->bcast_addr.value, dev->broadcast, b->media->hwaddr_len); b->bcast_addr.media_id = b->media->type_id; @@ -447,6 +453,7 @@ void tipc_disable_l2_media(struct tipc_bearer *b) struct net_device *dev; dev = (struct net_device *)rtnl_dereference(b->media_ptr); + dev_remove_pack(&b->pt); RCU_INIT_POINTER(dev->tipc_ptr, NULL); synchronize_net(); dev_put(dev); @@ -594,11 +601,12 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, struct tipc_bearer *b; rcu_read_lock(); - b = rcu_dereference_rtnl(dev->tipc_ptr); + b = rcu_dereference_rtnl(dev->tipc_ptr) ?: + rcu_dereference_rtnl(orig_dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && - (skb->pkt_type <= PACKET_BROADCAST))) { + (skb->pkt_type <= PACKET_MULTICAST))) { skb->next = NULL; - tipc_rcv(dev_net(dev), skb, b); + tipc_rcv(dev_net(b->pt.dev), skb, b); rcu_read_unlock(); return NET_RX_SUCCESS; } @@ -659,11 +667,6 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt, return NOTIFY_OK; } -static struct packet_type tipc_packet_type __read_mostly = { - .type = htons(ETH_P_TIPC), - .func = tipc_l2_rcv_msg, -}; - static struct notifier_block notifier = { .notifier_call = tipc_l2_device_event, .priority = 0, @@ -671,19 +674,12 @@ static struct notifier_block notifier = { int tipc_bearer_setup(void) { - int err; - - err = register_netdevice_notifier(¬ifier); - if (err) - return err; - dev_add_pack(&tipc_packet_type); - return 0; + return register_netdevice_notifier(¬ifier); } void tipc_bearer_cleanup(void) { unregister_netdevice_notifier(¬ifier); - dev_remove_pack(&tipc_packet_type); } void tipc_bearer_stop(struct net *net) diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 635c9086e19a..e07a55a80c18 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -131,6 +131,7 @@ struct tipc_media { * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer * @bcast_addr: media address used in broadcasting + * @pt: packet type for bearer * @rcu: rcu struct for tipc_bearer * @priority: default link priority for bearer * @window: default window size for bearer @@ -151,6 +152,7 @@ struct tipc_bearer { char name[TIPC_MAX_BEARER_NAME]; struct tipc_media *media; struct tipc_media_addr bcast_addr; + struct packet_type pt; struct rcu_head rcu; u32 priority; u32 window; diff --git a/net/tipc/msg.c b/net/tipc/msg.c index ab3087687a32..6ef379f004ac 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -479,13 +479,14 @@ bool tipc_msg_make_bundle(struct sk_buff **skb, struct tipc_msg *msg, bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) { struct sk_buff *_skb = *skb; - struct tipc_msg *hdr = buf_msg(_skb); + struct tipc_msg *hdr; struct tipc_msg ohdr; - int dlen = min_t(uint, msg_data_sz(hdr), MAX_FORWARD_SIZE); + int dlen; if (skb_linearize(_skb)) goto exit; hdr = buf_msg(_skb); + dlen = min_t(uint, msg_data_sz(hdr), MAX_FORWARD_SIZE); if (msg_dest_droppable(hdr)) goto exit; if (msg_errcode(hdr)) @@ -511,8 +512,11 @@ bool tipc_msg_reverse(u32 own_node, struct sk_buff **skb, int err) pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC)) goto exit; + /* reassign after skb header modifications */ + hdr = buf_msg(_skb); /* Now reverse the concerned fields */ msg_set_errcode(hdr, err); + msg_set_non_seq(hdr, 0); msg_set_origport(hdr, msg_destport(&ohdr)); msg_set_destport(hdr, msg_origport(&ohdr)); msg_set_destnode(hdr, msg_prevnode(&ohdr)); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 9bfe886ab330..750949dfc1d7 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -258,13 +258,15 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, arg = nlmsg_new(0, GFP_KERNEL); if (!arg) { kfree_skb(msg->rep); + msg->rep = NULL; return -ENOMEM; } err = __tipc_nl_compat_dumpit(cmd, msg, arg); - if (err) + if (err) { kfree_skb(msg->rep); - + msg->rep = NULL; + } kfree_skb(arg); return err; diff --git a/net/tipc/node.c b/net/tipc/node.c index 9b4dcb6a16b5..7dd22330a6b4 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1126,8 +1126,8 @@ int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr, strncpy(linkname, tipc_link_name(link), len); err = 0; } -exit: tipc_node_read_unlock(node); +exit: tipc_node_put(node); return err; } @@ -1557,6 +1557,8 @@ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b) /* Check/update node state before receiving */ if (unlikely(skb)) { + if (unlikely(skb_linearize(skb))) + goto discard; tipc_node_write_lock(n); if (tipc_node_check_state(n, skb, bearer_id, &xmitq)) { if (le->link) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 101e3597338f..d50edd6e0019 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2255,8 +2255,8 @@ void tipc_sk_reinit(struct net *net) do { tsk = ERR_PTR(rhashtable_walk_start(&iter)); - if (tsk) - continue; + if (IS_ERR(tsk)) + goto walk_stop; while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) { spin_lock_bh(&tsk->sk.sk_lock.slock); @@ -2265,7 +2265,7 @@ void tipc_sk_reinit(struct net *net) msg_set_orignode(msg, tn->own_addr); spin_unlock_bh(&tsk->sk.sk_lock.slock); } - +walk_stop: rhashtable_walk_stop(&iter); } while (tsk == ERR_PTR(-EAGAIN)); } diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index 0bf91cd3733c..be3d9e3183dc 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -52,7 +52,6 @@ struct tipc_subscriber { struct list_head subscrp_list; }; -static void tipc_subscrp_delete(struct tipc_subscription *sub); static void tipc_subscrb_put(struct tipc_subscriber *subscriber); /** @@ -197,15 +196,19 @@ static void tipc_subscrb_subscrp_delete(struct tipc_subscriber *subscriber, { struct list_head *subscription_list = &subscriber->subscrp_list; struct tipc_subscription *sub, *temp; + u32 timeout; spin_lock_bh(&subscriber->lock); list_for_each_entry_safe(sub, temp, subscription_list, subscrp_list) { if (s && memcmp(s, &sub->evt.s, sizeof(struct tipc_subscr))) continue; - tipc_nametbl_unsubscribe(sub); - list_del(&sub->subscrp_list); - tipc_subscrp_delete(sub); + timeout = htohl(sub->evt.s.timeout, sub->swap); + if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer)) { + tipc_nametbl_unsubscribe(sub); + list_del(&sub->subscrp_list); + tipc_subscrp_put(sub); + } if (s) break; @@ -236,18 +239,12 @@ static void tipc_subscrb_delete(struct tipc_subscriber *subscriber) tipc_subscrb_put(subscriber); } -static void tipc_subscrp_delete(struct tipc_subscription *sub) -{ - u32 timeout = htohl(sub->evt.s.timeout, sub->swap); - - if (timeout == TIPC_WAIT_FOREVER || del_timer(&sub->timer)) - tipc_subscrp_put(sub); -} - static void tipc_subscrp_cancel(struct tipc_subscr *s, struct tipc_subscriber *subscriber) { + tipc_subscrb_get(subscriber); tipc_subscrb_subscrp_delete(subscriber, s); + tipc_subscrb_put(subscriber); } static struct tipc_subscription *tipc_subscrp_create(struct net *net, diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 7b52a380d710..be8982b4f8c0 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2304,10 +2304,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, */ mutex_lock(&u->iolock); - if (flags & MSG_PEEK) - skip = sk_peek_offset(sk, flags); - else - skip = 0; + skip = max(sk_peek_offset(sk, flags), 0); do { int chunk; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index ff61d8557929..69b16ee327d9 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2226,7 +2226,6 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, goto no_transform; } - dst_hold(&xdst->u.dst); route = xdst->route; } } @@ -3308,9 +3307,15 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_state *x_new[XFRM_MAX_DEPTH]; struct xfrm_migrate *mp; + /* Stage 0 - sanity checks */ if ((err = xfrm_migrate_check(m, num_migrate)) < 0) goto out; + if (dir >= XFRM_POLICY_MAX) { + err = -EINVAL; + goto out; + } + /* Stage 1 - find policy */ if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) { err = -ENOENT; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 6c0956d10db6..a792effdb0b5 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1620,6 +1620,7 @@ int xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family, struct net *net) { + int i; int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (!afinfo) @@ -1628,6 +1629,9 @@ xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, spin_lock_bh(&net->xfrm.xfrm_state_lock); /*FIXME*/ if (afinfo->tmpl_sort) err = afinfo->tmpl_sort(dst, src, n); + else + for (i = 0; i < n; i++) + dst[i] = src[i]; spin_unlock_bh(&net->xfrm.xfrm_state_lock); rcu_read_unlock(); return err; @@ -1638,6 +1642,7 @@ int xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family) { + int i; int err = 0; struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); struct net *net = xs_net(*src); @@ -1648,6 +1653,9 @@ xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, spin_lock_bh(&net->xfrm.xfrm_state_lock); if (afinfo->state_sort) err = afinfo->state_sort(dst, src, n); + else + for (i = 0; i < n; i++) + dst[i] = src[i]; spin_unlock_bh(&net->xfrm.xfrm_state_lock); rcu_read_unlock(); return err; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 2be4c6af008a..9391ced05259 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -796,7 +796,7 @@ static int copy_user_offload(struct xfrm_state_offload *xso, struct sk_buff *skb return -EMSGSIZE; xuo = nla_data(attr); - + memset(xuo, 0, sizeof(*xuo)); xuo->ifindex = xso->dev->ifindex; xuo->flags = xso->flags; @@ -1869,6 +1869,7 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct return -EMSGSIZE; id = nlmsg_data(nlh); + memset(&id->sa_id, 0, sizeof(id->sa_id)); memcpy(&id->sa_id.daddr, &x->id.daddr, sizeof(x->id.daddr)); id->sa_id.spi = x->id.spi; id->sa_id.family = x->props.family; @@ -2578,6 +2579,8 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct ue = nlmsg_data(nlh); copy_to_user_state(x, &ue->state); ue->hard = (c->data.hard != 0) ? 1 : 0; + /* clear the padding bytes */ + memset(&ue->hard + 1, 0, sizeof(*ue) - offsetofend(typeof(*ue), hard)); err = xfrm_mark_put(skb, &x->mark); if (err) @@ -2715,6 +2718,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) struct nlattr *attr; id = nlmsg_data(nlh); + memset(id, 0, sizeof(*id)); memcpy(&id->daddr, &x->id.daddr, sizeof(id->daddr)); id->spi = x->id.spi; id->family = x->props.family; diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index dd8e2dde0b34..9ffd3dda3889 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -85,8 +85,8 @@ TMPOUT := $(if $(KBUILD_EXTMOD),$(firstword $(KBUILD_EXTMOD))/) # try-run # Usage: option = $(call try-run, $(CC)...-o "$$TMP",option-ok,otherwise) -# Exit code chooses option. "$$TMP" is can be used as temporary file and -# is automatically cleaned up. +# Exit code chooses option. "$$TMP" serves as a temporary file and is +# automatically cleaned up. try-run = $(shell set -e; \ TMP="$(TMPOUT).$$$$.tmp"; \ TMPO="$(TMPOUT).$$$$.o"; \ @@ -261,7 +261,6 @@ make-cmd = $(call escsq,$(subst \#,\\\#,$(subst $$,$$$$,$(cmd_$(1))))) any-prereq = $(filter-out $(PHONY),$?) $(filter-out $(PHONY) $(wildcard $^),$^) # Execute command if command has changed or prerequisite(s) are updated. -# if_changed = $(if $(strip $(any-prereq) $(arg-check)), \ @set -e; \ $(echo-cmd) $(cmd_$(1)); \ @@ -315,7 +314,7 @@ if_changed_rule = $(if $(strip $(any-prereq) $(arg-check) ), \ $(rule_$(1)), @:) ### -# why - tell why a a target got build +# why - tell why a target got built # enabled by make V=2 # Output (listed in the order they are checked): # (1) - due to target is PHONY diff --git a/scripts/Makefile.asm-generic b/scripts/Makefile.asm-generic index 95f7d8090152..a6c8c1780855 100644 --- a/scripts/Makefile.asm-generic +++ b/scripts/Makefile.asm-generic @@ -1,9 +1,9 @@ # include/asm-generic contains a lot of files that are used # verbatim by several architectures. # -# This Makefile reads the file arch/$(SRCARCH)/include/asm/Kbuild +# This Makefile reads the file arch/$(SRCARCH)/include/$(src)/Kbuild # and for each file listed in this file with generic-y creates -# a small wrapper file in $(obj) (arch/$(SRCARCH)/include/generated/asm) +# a small wrapper file in $(obj) (arch/$(SRCARCH)/include/generated/$(src)) kbuild-file := $(srctree)/arch/$(SRCARCH)/include/$(src)/Kbuild -include $(kbuild-file) diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 4a9a2cec0a1b..f6152c70f7f4 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -229,8 +229,8 @@ ifeq ("$(origin RECORDMCOUNT_WARN)", "command line") endif # Due to recursion, we must skip empty.o. # The empty.o file is created in the make process in order to determine -# the target endianness and word size. It is made before all other C -# files, including recordmcount. +# the target endianness and word size. It is made before all other C +# files, including recordmcount. sub_cmd_record_mcount = \ if [ $(@) != "scripts/mod/empty.o" ]; then \ $(objtree)/scripts/recordmcount $(RECORDMCOUNT_FLAGS) "$(@)"; \ @@ -245,13 +245,13 @@ sub_cmd_record_mcount = set -e ; perl $(srctree)/scripts/recordmcount.pl "$(ARCH "$(LD)" "$(NM)" "$(RM)" "$(MV)" \ "$(if $(part-of-module),1,0)" "$(@)"; recordmcount_source := $(srctree)/scripts/recordmcount.pl -endif +endif # BUILD_C_RECORDMCOUNT cmd_record_mcount = \ if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" = \ "$(CC_FLAGS_FTRACE)" ]; then \ $(sub_cmd_record_mcount) \ fi; -endif +endif # CONFIG_FTRACE_MCOUNT_RECORD ifdef CONFIG_STACK_VALIDATION ifneq ($(SKIP_STACK_VALIDATION),1) diff --git a/scripts/Makefile.dtbinst b/scripts/Makefile.dtbinst index 34614a48b717..993fb85982df 100644 --- a/scripts/Makefile.dtbinst +++ b/scripts/Makefile.dtbinst @@ -14,7 +14,7 @@ src := $(obj) PHONY := __dtbs_install __dtbs_install: -export dtbinst-root ?= $(obj) +export dtbinst_root ?= $(obj) include include/config/auto.conf include scripts/Kbuild.include @@ -27,7 +27,7 @@ dtbinst-dirs := $(dts-dirs) quiet_cmd_dtb_install = INSTALL $< cmd_dtb_install = mkdir -p $(2); cp $< $(2) -install-dir = $(patsubst $(dtbinst-root)%,$(INSTALL_DTBS_PATH)%,$(obj)) +install-dir = $(patsubst $(dtbinst_root)%,$(INSTALL_DTBS_PATH)%,$(obj)) $(dtbinst-files): %.dtb: $(obj)/%.dtb $(call cmd,dtb_install,$(install-dir)) diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile index ec10d9345bc2..0372b33febe5 100644 --- a/scripts/basic/Makefile +++ b/scripts/basic/Makefile @@ -1,5 +1,5 @@ ### -# Makefile.basic lists the most basic programs used during the build process. +# This Makefile lists the most basic programs used during the build process. # The programs listed herein are what are needed to do the basic stuff, # such as fix file dependencies. # This initial step is needed to avoid files to be recompiled diff --git a/scripts/basic/fixdep.c b/scripts/basic/fixdep.c index fff818b92acb..bbf62cb1f819 100644 --- a/scripts/basic/fixdep.c +++ b/scripts/basic/fixdep.c @@ -25,7 +25,7 @@ * * So we play the same trick that "mkdep" played before. We replace * the dependency on autoconf.h by a dependency on every config - * option which is mentioned in any of the listed prequisites. + * option which is mentioned in any of the listed prerequisites. * * kconfig populates a tree in include/config/ with an empty file * for each config symbol and when the configuration is updated @@ -34,7 +34,7 @@ * the config symbols are rebuilt. * * So if the user changes his CONFIG_HIS_DRIVER option, only the objects - * which depend on "include/linux/config/his/driver.h" will be rebuilt, + * which depend on "include/config/his/driver.h" will be rebuilt, * so most likely only his driver ;-) * * The idea above dates, by the way, back to Michael E Chastain, AFAIK. @@ -75,7 +75,7 @@ * and then basically copies the .<target>.d file to stdout, in the * process filtering out the dependency on autoconf.h and adding * dependencies on include/config/my/option.h for every - * CONFIG_MY_OPTION encountered in any of the prequisites. + * CONFIG_MY_OPTION encountered in any of the prerequisites. * * It will also filter out all the dependencies on *.ver. We need * to make sure that the generated version checksum are globally up diff --git a/scripts/dtc/checks.c b/scripts/dtc/checks.c index 4b72b530c84f..62ea8f83d4a0 100644 --- a/scripts/dtc/checks.c +++ b/scripts/dtc/checks.c @@ -873,7 +873,7 @@ static void check_simple_bus_reg(struct check *c, struct dt_info *dti, struct no while (size--) reg = (reg << 32) | fdt32_to_cpu(*(cells++)); - snprintf(unit_addr, sizeof(unit_addr), "%zx", reg); + snprintf(unit_addr, sizeof(unit_addr), "%llx", (unsigned long long)reg); if (!streq(unitname, unit_addr)) FAIL(c, dti, "Node %s simple-bus unit address format error, expected \"%s\"", node->fullpath, unit_addr); diff --git a/sound/core/control.c b/sound/core/control.c index 3c6be1452e35..4525e127afd9 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1137,7 +1137,7 @@ static int snd_ctl_elem_user_tlv(struct snd_kcontrol *kcontrol, mutex_lock(&ue->card->user_ctl_lock); change = ue->tlv_data_size != size; if (!change) - change = memcmp(ue->tlv_data, new_data, size); + change = memcmp(ue->tlv_data, new_data, size) != 0; kfree(ue->tlv_data); ue->tlv_data = new_data; ue->tlv_data_size = size; diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index 22995cb3bd44..cf0433f80067 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -3064,6 +3064,7 @@ int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream, { snd_pcm_uframes_t *frames = arg; snd_pcm_sframes_t result; + int err; switch (cmd) { case SNDRV_PCM_IOCTL_FORWARD: @@ -3083,7 +3084,10 @@ int snd_pcm_kernel_ioctl(struct snd_pcm_substream *substream, case SNDRV_PCM_IOCTL_START: return snd_pcm_start_lock_irq(substream); case SNDRV_PCM_IOCTL_DRAIN: - return snd_pcm_drain(substream, NULL); + snd_power_lock(substream->pcm->card); + err = snd_pcm_drain(substream, NULL); + snd_power_unlock(substream->pcm->card); + return err; case SNDRV_PCM_IOCTL_DROP: return snd_pcm_drop(substream); case SNDRV_PCM_IOCTL_DELAY: diff --git a/sound/core/seq/Kconfig b/sound/core/seq/Kconfig index a536760a94c2..45c1336c6597 100644 --- a/sound/core/seq/Kconfig +++ b/sound/core/seq/Kconfig @@ -47,10 +47,10 @@ config SND_SEQ_HRTIMER_DEFAULT timer. config SND_SEQ_MIDI_EVENT - def_tristate SND_RAWMIDI + tristate config SND_SEQ_MIDI - tristate + def_tristate SND_RAWMIDI select SND_SEQ_MIDI_EVENT config SND_SEQ_MIDI_EMUL diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c index 272c55fe17c8..ea2d0ae85bd3 100644 --- a/sound/core/seq/seq_clientmgr.c +++ b/sound/core/seq/seq_clientmgr.c @@ -1502,16 +1502,11 @@ static int snd_seq_ioctl_unsubscribe_port(struct snd_seq_client *client, static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, void *arg) { struct snd_seq_queue_info *info = arg; - int result; struct snd_seq_queue *q; - result = snd_seq_queue_alloc(client->number, info->locked, info->flags); - if (result < 0) - return result; - - q = queueptr(result); - if (q == NULL) - return -EINVAL; + q = snd_seq_queue_alloc(client->number, info->locked, info->flags); + if (IS_ERR(q)) + return PTR_ERR(q); info->queue = q->queue; info->locked = q->locked; @@ -1521,7 +1516,7 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, void *arg) if (!info->name[0]) snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue); strlcpy(q->name, info->name, sizeof(q->name)); - queuefree(q); + snd_use_lock_free(&q->use_lock); return 0; } diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c index 450c5187eecb..79e0c5604ef8 100644 --- a/sound/core/seq/seq_queue.c +++ b/sound/core/seq/seq_queue.c @@ -184,22 +184,26 @@ void __exit snd_seq_queues_delete(void) static void queue_use(struct snd_seq_queue *queue, int client, int use); /* allocate a new queue - - * return queue index value or negative value for error + * return pointer to new queue or ERR_PTR(-errno) for error + * The new queue's use_lock is set to 1. It is the caller's responsibility to + * call snd_use_lock_free(&q->use_lock). */ -int snd_seq_queue_alloc(int client, int locked, unsigned int info_flags) +struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int info_flags) { struct snd_seq_queue *q; q = queue_new(client, locked); if (q == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); q->info_flags = info_flags; queue_use(q, client, 1); + snd_use_lock_use(&q->use_lock); if (queue_list_add(q) < 0) { + snd_use_lock_free(&q->use_lock); queue_delete(q); - return -ENOMEM; + return ERR_PTR(-ENOMEM); } - return q->queue; + return q; } /* delete a queue - queue must be owned by the client */ diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h index 30c8111477f6..719093489a2c 100644 --- a/sound/core/seq/seq_queue.h +++ b/sound/core/seq/seq_queue.h @@ -71,7 +71,7 @@ void snd_seq_queues_delete(void); /* create new queue (constructor) */ -int snd_seq_queue_alloc(int client, int locked, unsigned int flags); +struct snd_seq_queue *snd_seq_queue_alloc(int client, int locked, unsigned int flags); /* delete queue (destructor) */ int snd_seq_queue_delete(int client, int queueid); diff --git a/sound/firewire/iso-resources.c b/sound/firewire/iso-resources.c index f0e4d502d604..066b5df666f4 100644 --- a/sound/firewire/iso-resources.c +++ b/sound/firewire/iso-resources.c @@ -210,9 +210,14 @@ EXPORT_SYMBOL(fw_iso_resources_update); */ void fw_iso_resources_free(struct fw_iso_resources *r) { - struct fw_card *card = fw_parent_device(r->unit)->card; + struct fw_card *card; int bandwidth, channel; + /* Not initialized. */ + if (r->unit == NULL) + return; + card = fw_parent_device(r->unit)->card; + mutex_lock(&r->mutex); if (r->allocated) { diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c index bf779cfeef0d..59a270406353 100644 --- a/sound/firewire/motu/motu.c +++ b/sound/firewire/motu/motu.c @@ -128,6 +128,7 @@ static void do_registration(struct work_struct *work) return; error: snd_motu_transaction_unregister(motu); + snd_motu_stream_destroy_duplex(motu); snd_card_free(motu->card); dev_info(&motu->unit->device, "Sound card registration failed: %d\n", err); diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c index dc585959ca32..a2b56b188be4 100644 --- a/sound/pci/emu10k1/emufx.c +++ b/sound/pci/emu10k1/emufx.c @@ -698,10 +698,18 @@ static int copy_gctl(struct snd_emu10k1 *emu, { struct snd_emu10k1_fx8010_control_old_gpr __user *octl; - if (emu->support_tlv) - return copy_from_user(gctl, &_gctl[idx], sizeof(*gctl)); + if (emu->support_tlv) { + if (in_kernel) + memcpy(gctl, (void *)&_gctl[idx], sizeof(*gctl)); + else if (copy_from_user(gctl, &_gctl[idx], sizeof(*gctl))) + return -EFAULT; + return 0; + } + octl = (struct snd_emu10k1_fx8010_control_old_gpr __user *)_gctl; - if (copy_from_user(gctl, &octl[idx], sizeof(*octl))) + if (in_kernel) + memcpy(gctl, (void *)&octl[idx], sizeof(*octl)); + else if (copy_from_user(gctl, &octl[idx], sizeof(*octl))) return -EFAULT; gctl->tlv = NULL; return 0; diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 8c1289963c80..a81aacf684b2 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -947,6 +947,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x17aa, 0x390b, "Lenovo G50-80", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3975, "Lenovo U300s", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x3977, "Lenovo IdeaPad U310", CXT_FIXUP_STEREO_DMIC), + SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo G50-70", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x17aa, 0x397b, "Lenovo S205", CXT_FIXUP_STEREO_DMIC), SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI), SND_PCI_QUIRK(0x1c06, 0x2011, "Lemote A1004", CXT_PINCFG_LEMOTE_A1004), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index a91a9ef00c40..217bb582aff1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -6647,7 +6647,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0299, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x12, 0xb7a60130}, - {0x13, 0xb8a61140}, {0x17, 0x90170110}), {} }; diff --git a/sound/soc/codecs/rt5670.c b/sound/soc/codecs/rt5670.c index 0ec7985ed306..054b613cb0d0 100644 --- a/sound/soc/codecs/rt5670.c +++ b/sound/soc/codecs/rt5670.c @@ -567,7 +567,7 @@ int rt5670_set_jack_detect(struct snd_soc_codec *codec, rt5670->jack = jack; rt5670->hp_gpio.gpiod_dev = codec->dev; - rt5670->hp_gpio.name = "headphone detect"; + rt5670->hp_gpio.name = "headset"; rt5670->hp_gpio.report = SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 | SND_JACK_BTN_2; rt5670->hp_gpio.debounce_time = 150; diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c index 36e530a36c82..6f629278d982 100644 --- a/sound/soc/codecs/rt5677.c +++ b/sound/soc/codecs/rt5677.c @@ -5021,6 +5021,7 @@ static const struct regmap_config rt5677_regmap = { static const struct i2c_device_id rt5677_i2c_id[] = { { "rt5677", RT5677 }, { "rt5676", RT5676 }, + { "RT5677CE:00", RT5677 }, { } }; MODULE_DEVICE_TABLE(i2c, rt5677_i2c_id); diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index 7d7ab4aee42e..d72f7d58102f 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -132,7 +132,7 @@ int asoc_simple_card_parse_card_name(struct snd_soc_card *card, /* Parse the card name from DT */ ret = snd_soc_of_parse_card_name(card, "label"); - if (ret < 0) { + if (ret < 0 || !card->name) { char prop[128]; snprintf(prop, sizeof(prop), "%sname", prefix); diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c index bc2a52de06a3..f597d5582223 100644 --- a/sound/soc/intel/boards/cht_bsw_rt5672.c +++ b/sound/soc/intel/boards/cht_bsw_rt5672.c @@ -184,6 +184,13 @@ static int cht_aif1_hw_params(struct snd_pcm_substream *substream, return 0; } +static const struct acpi_gpio_params headset_gpios = { 0, 0, false }; + +static const struct acpi_gpio_mapping cht_rt5672_gpios[] = { + { "headset-gpios", &headset_gpios, 1 }, + {}, +}; + static int cht_codec_init(struct snd_soc_pcm_runtime *runtime) { int ret; @@ -191,6 +198,9 @@ static int cht_codec_init(struct snd_soc_pcm_runtime *runtime) struct snd_soc_codec *codec = codec_dai->codec; struct cht_mc_private *ctx = snd_soc_card_get_drvdata(runtime->card); + if (devm_acpi_dev_add_driver_gpios(codec->dev, cht_rt5672_gpios)) + dev_warn(runtime->dev, "Unable to add GPIO mapping table\n"); + /* TDM 4 slots 24 bit, set Rx & Tx bitmask to 4 active slots */ ret = snd_soc_dai_set_tdm_slot(codec_dai, 0xF, 0xF, 4, 24); if (ret < 0) { diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 082736c539bc..e630813c5008 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -542,6 +542,8 @@ int snd_usb_mixer_vol_tlv(struct snd_kcontrol *kcontrol, int op_flag, if (size < sizeof(scale)) return -ENOMEM; + if (cval->min_mute) + scale[0] = SNDRV_CTL_TLVT_DB_MINMAX_MUTE; scale[2] = cval->dBmin; scale[3] = cval->dBmax; if (copy_to_user(_tlv, scale, sizeof(scale))) diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h index 3417ef347e40..2b4b067646ab 100644 --- a/sound/usb/mixer.h +++ b/sound/usb/mixer.h @@ -64,6 +64,7 @@ struct usb_mixer_elem_info { int cached; int cache_val[MAX_CHANNELS]; u8 initialized; + u8 min_mute; void *private_data; }; diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c index e3d1dec48ee4..e1e7ce9ab217 100644 --- a/sound/usb/mixer_quirks.c +++ b/sound/usb/mixer_quirks.c @@ -1878,6 +1878,12 @@ void snd_usb_mixer_fu_apply_quirk(struct usb_mixer_interface *mixer, if (unitid == 7 && cval->control == UAC_FU_VOLUME) snd_dragonfly_quirk_db_scale(mixer, cval, kctl); break; + /* lowest playback value is muted on C-Media devices */ + case USB_ID(0x0d8c, 0x000c): + case USB_ID(0x0d8c, 0x0014): + if (strstr(kctl->id.name, "Playback")) + cval->min_mute = 1; + break; } } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index d7b0b0a3a2db..5d2a63248b1d 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1142,6 +1142,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ + case USB_ID(0x1395, 0x740a): /* Sennheiser DECT */ case USB_ID(0x1901, 0x0191): /* GE B850V3 CP2114 audio interface */ case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */ case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ @@ -1308,10 +1309,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(20); - /* Zoom R16/24 needs a tiny delay here, otherwise requests like - * get/set frequency return as failed despite actually succeeding. + /* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here, + * otherwise requests like get/set frequency return as failed despite + * actually succeeding. */ - if (chip->usb_id == USB_ID(0x1686, 0x00dd) && + if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || + chip->usb_id == USB_ID(0x046d, 0x0a46) || + chip->usb_id == USB_ID(0x0b0e, 0x0349)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) mdelay(1); } @@ -1374,6 +1378,10 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, } } break; + case USB_ID(0x16d0, 0x0a23): + if (fp->altsetting == 2) + return SNDRV_PCM_FMTBIT_DSD_U32_BE; + break; default: break; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 1a2c07eb7795..8c67a90dbd82 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -879,7 +879,8 @@ bpf_object__create_maps(struct bpf_object *obj) size_t j; int err = *pfd; - pr_warning("failed to create map: %s\n", + pr_warning("failed to create map (name: '%s'): %s\n", + obj->maps[i].name, strerror(errno)); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index a36c2eba64e7..4559a21a8de2 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -271,7 +271,7 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, case 0x8d: if (rex == 0x48 && modrm == 0x65) { - /* lea -disp(%rbp), %rsp */ + /* lea disp(%rbp), %rsp */ *type = INSN_STACK; op->src.type = OP_SRC_ADD; op->src.reg = CFI_BP; @@ -281,6 +281,30 @@ int arch_decode_instruction(struct elf *elf, struct section *sec, break; } + if (rex == 0x48 && (modrm == 0xa4 || modrm == 0x64) && + sib == 0x24) { + + /* lea disp(%rsp), %rsp */ + *type = INSN_STACK; + op->src.type = OP_SRC_ADD; + op->src.reg = CFI_SP; + op->src.offset = insn.displacement.value; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_SP; + break; + } + + if (rex == 0x48 && modrm == 0x2c && sib == 0x24) { + + /* lea (%rsp), %rbp */ + *type = INSN_STACK; + op->src.type = OP_SRC_REG; + op->src.reg = CFI_SP; + op->dest.type = OP_DEST_REG; + op->dest.reg = CFI_BP; + break; + } + if (rex == 0x4c && modrm == 0x54 && sib == 0x24 && insn.displacement.value == 8) { diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile index e2fbb890aef9..7c647f619d63 100644 --- a/tools/testing/selftests/futex/Makefile +++ b/tools/testing/selftests/futex/Makefile @@ -14,7 +14,7 @@ all: done override define RUN_TESTS - @if [ `dirname $(OUTPUT)` = $(PWD) ]; then ./run.sh; fi + $(OUTPUT)/run.sh endef override define INSTALL_RULE diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh index 8cecae9a8bca..7956ea3be667 100644..100755 --- a/tools/testing/selftests/kmod/kmod.sh +++ b/tools/testing/selftests/kmod/kmod.sh @@ -473,8 +473,8 @@ usage() echo " all Runs all tests (default)" echo " -t Run test ID the number amount of times is recommended" echo " -w Watch test ID run until it runs into an error" - echo " -c Run test ID once" - echo " -s Run test ID x test-count number of times" + echo " -s Run test ID once" + echo " -c Run test ID x test-count number of times" echo " -l List all test ID list" echo " -h|--help Help" echo diff --git a/tools/testing/selftests/ntb/ntb_test.sh b/tools/testing/selftests/ntb/ntb_test.sh index 1c12b5855e4f..5fc7ad359e21 100755 --- a/tools/testing/selftests/ntb/ntb_test.sh +++ b/tools/testing/selftests/ntb/ntb_test.sh @@ -333,6 +333,10 @@ function ntb_tool_tests() link_test $LOCAL_TOOL $REMOTE_TOOL link_test $REMOTE_TOOL $LOCAL_TOOL + #Ensure the link is up on both sides before continuing + write_file Y $LOCAL_TOOL/link_event + write_file Y $REMOTE_TOOL/link_event + for PEER_TRANS in $(ls $LOCAL_TOOL/peer_trans*); do PT=$(basename $PEER_TRANS) write_file $MW_SIZE $LOCAL_TOOL/$PT diff --git a/tools/testing/selftests/sysctl/sysctl.sh b/tools/testing/selftests/sysctl/sysctl.sh index ec232c3cfcaa..ec232c3cfcaa 100644..100755 --- a/tools/testing/selftests/sysctl/sysctl.sh +++ b/tools/testing/selftests/sysctl/sysctl.sh diff --git a/tools/testing/selftests/timers/freq-step.c b/tools/testing/selftests/timers/freq-step.c index e8c61830825a..22312eb4c941 100644 --- a/tools/testing/selftests/timers/freq-step.c +++ b/tools/testing/selftests/timers/freq-step.c @@ -229,10 +229,9 @@ static void init_test(void) printf("CLOCK_MONOTONIC_RAW+CLOCK_MONOTONIC precision: %.0f ns\t\t", 1e9 * precision); - if (precision > MAX_PRECISION) { - printf("[SKIP]\n"); - ksft_exit_skip(); - } + if (precision > MAX_PRECISION) + ksft_exit_skip("precision: %.0f ns > MAX_PRECISION: %.0f ns\n", + 1e9 * precision, 1e9 * MAX_PRECISION); printf("[OK]\n"); srand(ts.tv_sec ^ ts.tv_nsec); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 15252d723b54..4d81f6ded88e 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -322,47 +322,6 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) return container_of(mn, struct kvm, mmu_notifier); } -static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long address) -{ - struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush, idx; - - /* - * When ->invalidate_page runs, the linux pte has been zapped - * already but the page is still allocated until - * ->invalidate_page returns. So if we increase the sequence - * here the kvm page fault will notice if the spte can't be - * established because the page is going to be freed. If - * instead the kvm page fault establishes the spte before - * ->invalidate_page runs, kvm_unmap_hva will release it - * before returning. - * - * The sequence increase only need to be seen at spin_unlock - * time, and not at spin_lock time. - * - * Increasing the sequence after the spin_unlock would be - * unsafe because the kvm page fault could then establish the - * pte after kvm_unmap_hva returned, without noticing the page - * is going to be freed. - */ - idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); - - kvm->mmu_notifier_seq++; - need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty; - /* we've to flush the tlb before the pages can be freed */ - if (need_tlb_flush) - kvm_flush_remote_tlbs(kvm); - - spin_unlock(&kvm->mmu_lock); - - kvm_arch_mmu_notifier_invalidate_page(kvm, address); - - srcu_read_unlock(&kvm->srcu, idx); -} - static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address, @@ -510,7 +469,6 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { - .invalidate_page = kvm_mmu_notifier_invalidate_page, .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, |