diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index fb385af482ff..8cfb44ffe853 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2541,6 +2541,9 @@ noalign [KNL,ARM] + noaltinstr [S390] Disables alternative instructions patching + (CPU alternatives feature). + noapic [SMP,APIC] Tells the kernel to not make use of any IOAPICs that may be present in the system. diff --git a/Makefile b/Makefile index ee330f5449e6..27a8d5c37180 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 37 +SUBLEVEL = 38 EXTRAVERSION = NAME = Petit Gorille diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 910628d18add..1fc5060d7027 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -155,17 +155,6 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; }; - - vdd_log: vdd-log { - compatible = "pwm-regulator"; - pwms = <&pwm2 0 25000 0>; - regulator-name = "vdd_log"; - regulator-min-microvolt = <800000>; - regulator-max-microvolt = <1400000>; - regulator-always-on; - regulator-boot-on; - status = "okay"; - }; }; &cpu_b0 { diff --git a/arch/microblaze/Kconfig.platform b/arch/microblaze/Kconfig.platform index 1b3d8c849101..f7f1739c11b9 100644 --- a/arch/microblaze/Kconfig.platform +++ b/arch/microblaze/Kconfig.platform @@ -20,6 +20,7 @@ config OPT_LIB_FUNCTION config OPT_LIB_ASM bool "Optimalized lib function ASM" depends on OPT_LIB_FUNCTION && (XILINX_MICROBLAZE0_USE_BARREL = 1) + depends on CPU_BIG_ENDIAN default n help Allows turn on optimalized library function (memcpy and memmove). diff --git a/arch/microblaze/lib/fastcopy.S b/arch/microblaze/lib/fastcopy.S index 62021d7e249e..fdc48bb065d8 100644 --- a/arch/microblaze/lib/fastcopy.S +++ b/arch/microblaze/lib/fastcopy.S @@ -29,10 +29,6 @@ * between mem locations with size of xfer spec'd in bytes */ -#ifdef __MICROBLAZEEL__ -#error Microblaze LE not support ASM optimized lib func. Disable OPT_LIB_ASM. -#endif - #include .text .globl memcpy diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index ae55e715cc74..49fb6614ea8c 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -121,6 +121,7 @@ config S390 select GENERIC_CLOCKEVENTS select GENERIC_CPU_AUTOPROBE select GENERIC_CPU_DEVICES if !SMP + select GENERIC_CPU_VULNERABILITIES select GENERIC_FIND_FIRST_BIT select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL @@ -538,6 +539,51 @@ config ARCH_RANDOM If unsure, say Y. +config KERNEL_NOBP + def_bool n + prompt "Enable modified branch prediction for the kernel by default" + help + If this option is selected the kernel will switch to a modified + branch prediction mode if the firmware interface is available. + The modified branch prediction mode improves the behaviour in + regard to speculative execution. + + With the option enabled the kernel parameter "nobp=0" or "nospec" + can be used to run the kernel in the normal branch prediction mode. + + With the option disabled the modified branch prediction mode is + enabled with the "nobp=1" kernel parameter. + + If unsure, say N. + +config EXPOLINE + def_bool n + prompt "Avoid speculative indirect branches in the kernel" + help + Compile the kernel with the expoline compiler options to guard + against kernel-to-user data leaks by avoiding speculative indirect + branches. + Requires a compiler with -mindirect-branch=thunk support for full + protection. The kernel may run slower. + + If unsure, say N. + +choice + prompt "Expoline default" + depends on EXPOLINE + default EXPOLINE_FULL + +config EXPOLINE_OFF + bool "spectre_v2=off" + +config EXPOLINE_AUTO + bool "spectre_v2=auto" + +config EXPOLINE_FULL + bool "spectre_v2=on" + +endchoice + endmenu menu "Memory setup" @@ -812,6 +858,7 @@ config PFAULT config SHARED_KERNEL bool "VM shared kernel support" depends on !JUMP_LABEL + depends on !ALTERNATIVES help Select this option, if you want to share the text segment of the Linux kernel between different VM guests. This reduces memory diff --git a/arch/s390/Makefile b/arch/s390/Makefile index dac821cfcd43..ec3fa105f448 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -81,6 +81,16 @@ ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y) cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack endif +ifdef CONFIG_EXPOLINE + ifeq ($(call cc-option-yn,$(CC_FLAGS_MARCH) -mindirect-branch=thunk),y) + CC_FLAGS_EXPOLINE := -mindirect-branch=thunk + CC_FLAGS_EXPOLINE += -mfunction-return=thunk + CC_FLAGS_EXPOLINE += -mindirect-branch-table + export CC_FLAGS_EXPOLINE + cflags-y += $(CC_FLAGS_EXPOLINE) -DCC_USING_EXPOLINE + endif +endif + ifdef CONFIG_FUNCTION_TRACER # make use of hotpatch feature if the compiler supports it cc_hotpatch := -mhotpatch=0,3 diff --git a/arch/s390/include/asm/alternative.h b/arch/s390/include/asm/alternative.h new file mode 100644 index 000000000000..a72002056b54 --- /dev/null +++ b/arch/s390/include/asm/alternative.h @@ -0,0 +1,149 @@ +#ifndef _ASM_S390_ALTERNATIVE_H +#define _ASM_S390_ALTERNATIVE_H + +#ifndef __ASSEMBLY__ + +#include +#include +#include + +struct alt_instr { + s32 instr_offset; /* original instruction */ + s32 repl_offset; /* offset to replacement instruction */ + u16 facility; /* facility bit set for replacement */ + u8 instrlen; /* length of original instruction */ + u8 replacementlen; /* length of new instruction */ +} __packed; + +void apply_alternative_instructions(void); +void apply_alternatives(struct alt_instr *start, struct alt_instr *end); + +/* + * |661: |662: |6620 |663: + * +-----------+---------------------+ + * | oldinstr | oldinstr_padding | + * | +----------+----------+ + * | | | | + * | | >6 bytes |6/4/2 nops| + * | |6 bytes jg-----------> + * +-----------+---------------------+ + * ^^ static padding ^^ + * + * .altinstr_replacement section + * +---------------------+-----------+ + * |6641: |6651: + * | alternative instr 1 | + * +-----------+---------+- - - - - -+ + * |6642: |6652: | + * | alternative instr 2 | padding + * +---------------------+- - - - - -+ + * ^ runtime ^ + * + * .altinstructions section + * +---------------------------------+ + * | alt_instr entries for each | + * | alternative instr | + * +---------------------------------+ + */ + +#define b_altinstr(num) "664"#num +#define e_altinstr(num) "665"#num + +#define e_oldinstr_pad_end "663" +#define oldinstr_len "662b-661b" +#define oldinstr_total_len e_oldinstr_pad_end"b-661b" +#define altinstr_len(num) e_altinstr(num)"b-"b_altinstr(num)"b" +#define oldinstr_pad_len(num) \ + "-(((" altinstr_len(num) ")-(" oldinstr_len ")) > 0) * " \ + "((" altinstr_len(num) ")-(" oldinstr_len "))" + +#define INSTR_LEN_SANITY_CHECK(len) \ + ".if " len " > 254\n" \ + "\t.error \"cpu alternatives does not support instructions " \ + "blocks > 254 bytes\"\n" \ + ".endif\n" \ + ".if (" len ") %% 2\n" \ + "\t.error \"cpu alternatives instructions length is odd\"\n" \ + ".endif\n" + +#define OLDINSTR_PADDING(oldinstr, num) \ + ".if " oldinstr_pad_len(num) " > 6\n" \ + "\tjg " e_oldinstr_pad_end "f\n" \ + "6620:\n" \ + "\t.fill (" oldinstr_pad_len(num) " - (6620b-662b)) / 2, 2, 0x0700\n" \ + ".else\n" \ + "\t.fill " oldinstr_pad_len(num) " / 6, 6, 0xc0040000\n" \ + "\t.fill " oldinstr_pad_len(num) " %% 6 / 4, 4, 0x47000000\n" \ + "\t.fill " oldinstr_pad_len(num) " %% 6 %% 4 / 2, 2, 0x0700\n" \ + ".endif\n" + +#define OLDINSTR(oldinstr, num) \ + "661:\n\t" oldinstr "\n662:\n" \ + OLDINSTR_PADDING(oldinstr, num) \ + e_oldinstr_pad_end ":\n" \ + INSTR_LEN_SANITY_CHECK(oldinstr_len) + +#define OLDINSTR_2(oldinstr, num1, num2) \ + "661:\n\t" oldinstr "\n662:\n" \ + ".if " altinstr_len(num1) " < " altinstr_len(num2) "\n" \ + OLDINSTR_PADDING(oldinstr, num2) \ + ".else\n" \ + OLDINSTR_PADDING(oldinstr, num1) \ + ".endif\n" \ + e_oldinstr_pad_end ":\n" \ + INSTR_LEN_SANITY_CHECK(oldinstr_len) + +#define ALTINSTR_ENTRY(facility, num) \ + "\t.long 661b - .\n" /* old instruction */ \ + "\t.long " b_altinstr(num)"b - .\n" /* alt instruction */ \ + "\t.word " __stringify(facility) "\n" /* facility bit */ \ + "\t.byte " oldinstr_total_len "\n" /* source len */ \ + "\t.byte " altinstr_len(num) "\n" /* alt instruction len */ + +#define ALTINSTR_REPLACEMENT(altinstr, num) /* replacement */ \ + b_altinstr(num)":\n\t" altinstr "\n" e_altinstr(num) ":\n" \ + INSTR_LEN_SANITY_CHECK(altinstr_len(num)) + +/* alternative assembly primitive: */ +#define ALTERNATIVE(oldinstr, altinstr, facility) \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(altinstr, 1) \ + ".popsection\n" \ + OLDINSTR(oldinstr, 1) \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(facility, 1) \ + ".popsection\n" + +#define ALTERNATIVE_2(oldinstr, altinstr1, facility1, altinstr2, facility2)\ + ".pushsection .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(altinstr1, 1) \ + ALTINSTR_REPLACEMENT(altinstr2, 2) \ + ".popsection\n" \ + OLDINSTR_2(oldinstr, 1, 2) \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(facility1, 1) \ + ALTINSTR_ENTRY(facility2, 2) \ + ".popsection\n" + +/* + * Alternative instructions for different CPU types or capabilities. + * + * This allows to use optimized instructions even on generic binary + * kernels. + * + * oldinstr is padded with jump and nops at compile time if altinstr is + * longer. altinstr is padded with jump and nops at run-time during patching. + * + * For non barrier like inlines please define new variants + * without volatile and memory clobber. + */ +#define alternative(oldinstr, altinstr, facility) \ + asm volatile(ALTERNATIVE(oldinstr, altinstr, facility) : : : "memory") + +#define alternative_2(oldinstr, altinstr1, facility1, altinstr2, facility2) \ + asm volatile(ALTERNATIVE_2(oldinstr, altinstr1, facility1, \ + altinstr2, facility2) ::: "memory") + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_S390_ALTERNATIVE_H */ diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index 10432607a573..f9eddbca79d2 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -49,6 +49,30 @@ do { \ #define __smp_mb__before_atomic() barrier() #define __smp_mb__after_atomic() barrier() +/** + * array_index_mask_nospec - generate a mask for array_idx() that is + * ~0UL when the bounds check succeeds and 0 otherwise + * @index: array element index + * @size: number of elements in array + */ +#define array_index_mask_nospec array_index_mask_nospec +static inline unsigned long array_index_mask_nospec(unsigned long index, + unsigned long size) +{ + unsigned long mask; + + if (__builtin_constant_p(size) && size > 0) { + asm(" clgr %2,%1\n" + " slbgr %0,%0\n" + :"=d" (mask) : "d" (size-1), "d" (index) :"cc"); + return mask; + } + asm(" clgr %1,%2\n" + " slbgr %0,%0\n" + :"=d" (mask) : "d" (size), "d" (index) :"cc"); + return ~mask; +} + #include #endif /* __ASM_BARRIER_H */ diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index f040644575b7..2d58478c2745 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -15,6 +15,24 @@ #define MAX_FACILITY_BIT (sizeof(((struct lowcore *)0)->stfle_fac_list) * 8) +static inline void __set_facility(unsigned long nr, void *facilities) +{ + unsigned char *ptr = (unsigned char *) facilities; + + if (nr >= MAX_FACILITY_BIT) + return; + ptr[nr >> 3] |= 0x80 >> (nr & 7); +} + +static inline void __clear_facility(unsigned long nr, void *facilities) +{ + unsigned char *ptr = (unsigned char *) facilities; + + if (nr >= MAX_FACILITY_BIT) + return; + ptr[nr >> 3] &= ~(0x80 >> (nr & 7)); +} + static inline int __test_facility(unsigned long nr, void *facilities) { unsigned char *ptr; diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 51375e766e90..d660e784e445 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -210,7 +210,8 @@ struct kvm_s390_sie_block { __u16 ipa; /* 0x0056 */ __u32 ipb; /* 0x0058 */ __u32 scaoh; /* 0x005c */ - __u8 reserved60; /* 0x0060 */ +#define FPF_BPBC 0x20 + __u8 fpf; /* 0x0060 */ #define ECB_GS 0x40 #define ECB_TE 0x10 #define ECB_SRSI 0x04 diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index 917f7344cab6..88a212df0dbc 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -140,7 +140,9 @@ struct lowcore { /* Per cpu primary space access list */ __u32 paste[16]; /* 0x0400 */ - __u8 pad_0x04c0[0x0e00-0x0440]; /* 0x0440 */ + /* br %r1 trampoline */ + __u16 br_r1_trampoline; /* 0x0440 */ + __u8 pad_0x0442[0x0e00-0x0442]; /* 0x0442 */ /* * 0xe00 contains the address of the IPL Parameter Information @@ -155,7 +157,8 @@ struct lowcore { __u8 pad_0x0e20[0x0f00-0x0e20]; /* 0x0e20 */ /* Extended facility list */ - __u64 stfle_fac_list[32]; /* 0x0f00 */ + __u64 stfle_fac_list[16]; /* 0x0f00 */ + __u64 alt_stfle_fac_list[16]; /* 0x0f80 */ __u8 pad_0x1000[0x11b0-0x1000]; /* 0x1000 */ /* Pointer to the machine check extended save area */ diff --git a/arch/s390/include/asm/nospec-branch.h b/arch/s390/include/asm/nospec-branch.h new file mode 100644 index 000000000000..b4bd8c41e9d3 --- /dev/null +++ b/arch/s390/include/asm/nospec-branch.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_EXPOLINE_H +#define _ASM_S390_EXPOLINE_H + +#ifndef __ASSEMBLY__ + +#include + +extern int nospec_disable; + +void nospec_init_branches(void); +void nospec_auto_detect(void); +void nospec_revert(s32 *start, s32 *end); + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_S390_EXPOLINE_H */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 9cf92abe23c3..0a39cd102c49 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -89,6 +89,7 @@ void cpu_detect_mhz_feature(void); extern const struct seq_operations cpuinfo_op; extern int sysctl_ieee_emulation_warnings; extern void execve_tail(void); +extern void __bpon(void); /* * User space process size: 2GB for 31 bit, 4TB or 8PT for 64 bit. @@ -377,6 +378,9 @@ extern void memcpy_absolute(void *, void *, size_t); memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ } while (0) +extern int s390_isolate_bp(void); +extern int s390_isolate_bp_guest(void); + #endif /* __ASSEMBLY__ */ #endif /* __ASM_S390_PROCESSOR_H */ diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h index 0880a37b6d3b..301b4f70bf31 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -60,6 +60,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #define TIF_GUARDED_STORAGE 4 /* load guarded storage control block */ #define TIF_PATCH_PENDING 5 /* pending live patching update */ #define TIF_PGSTE 6 /* New mm's will use 4K page tables */ +#define TIF_ISOLATE_BP 8 /* Run process with isolated BP */ +#define TIF_ISOLATE_BP_GUEST 9 /* Run KVM guests with isolated BP */ #define TIF_31BIT 16 /* 32bit process */ #define TIF_MEMDIE 17 /* is terminating due to OOM killer */ @@ -80,6 +82,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #define _TIF_UPROBE _BITUL(TIF_UPROBE) #define _TIF_GUARDED_STORAGE _BITUL(TIF_GUARDED_STORAGE) #define _TIF_PATCH_PENDING _BITUL(TIF_PATCH_PENDING) +#define _TIF_ISOLATE_BP _BITUL(TIF_ISOLATE_BP) +#define _TIF_ISOLATE_BP_GUEST _BITUL(TIF_ISOLATE_BP_GUEST) #define _TIF_31BIT _BITUL(TIF_31BIT) #define _TIF_SINGLE_STEP _BITUL(TIF_SINGLE_STEP) diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index 9ad172dcd912..a3938db010f7 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -228,6 +228,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_RICCB (1UL << 7) #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) +#define KVM_SYNC_BPBC (1UL << 10) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -251,7 +252,9 @@ struct kvm_sync_regs { }; __u8 reserved[512]; /* for future vector expansion */ __u32 fpc; /* valid on KVM_SYNC_VRS or KVM_SYNC_FPRS */ - __u8 padding1[52]; /* riccb needs to be 64byte aligned */ + __u8 bpbc : 1; /* bp mode */ + __u8 reserved2 : 7; + __u8 padding1[51]; /* riccb needs to be 64byte aligned */ __u8 riccb[64]; /* runtime instrumentation controls block */ __u8 padding2[192]; /* sdnx needs to be 256byte aligned */ union { diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 4ce2d05929a7..a3a4cafb6080 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -29,6 +29,7 @@ UBSAN_SANITIZE_early.o := n # ifneq ($(CC_FLAGS_MARCH),-march=z900) CFLAGS_REMOVE_als.o += $(CC_FLAGS_MARCH) +CFLAGS_REMOVE_als.o += $(CC_FLAGS_EXPOLINE) CFLAGS_als.o += -march=z900 AFLAGS_REMOVE_head.o += $(CC_FLAGS_MARCH) AFLAGS_head.o += -march=z900 @@ -57,10 +58,13 @@ obj-y += processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o als.o obj-y += sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o -obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o +obj-y += entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o +obj-y += nospec-branch.o extra-y += head.o head64.o vmlinux.lds +CFLAGS_REMOVE_nospec-branch.o += $(CC_FLAGS_EXPOLINE) + obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCHED_TOPOLOGY) += topology.o diff --git a/arch/s390/kernel/alternative.c b/arch/s390/kernel/alternative.c new file mode 100644 index 000000000000..b57b293998dc --- /dev/null +++ b/arch/s390/kernel/alternative.c @@ -0,0 +1,112 @@ +#include +#include +#include +#include + +#define MAX_PATCH_LEN (255 - 1) + +static int __initdata_or_module alt_instr_disabled; + +static int __init disable_alternative_instructions(char *str) +{ + alt_instr_disabled = 1; + return 0; +} + +early_param("noaltinstr", disable_alternative_instructions); + +struct brcl_insn { + u16 opc; + s32 disp; +} __packed; + +static u16 __initdata_or_module nop16 = 0x0700; +static u32 __initdata_or_module nop32 = 0x47000000; +static struct brcl_insn __initdata_or_module nop48 = { + 0xc004, 0 +}; + +static const void *nops[] __initdata_or_module = { + &nop16, + &nop32, + &nop48 +}; + +static void __init_or_module add_jump_padding(void *insns, unsigned int len) +{ + struct brcl_insn brcl = { + 0xc0f4, + len / 2 + }; + + memcpy(insns, &brcl, sizeof(brcl)); + insns += sizeof(brcl); + len -= sizeof(brcl); + + while (len > 0) { + memcpy(insns, &nop16, 2); + insns += 2; + len -= 2; + } +} + +static void __init_or_module add_padding(void *insns, unsigned int len) +{ + if (len > 6) + add_jump_padding(insns, len); + else if (len >= 2) + memcpy(insns, nops[len / 2 - 1], len); +} + +static void __init_or_module __apply_alternatives(struct alt_instr *start, + struct alt_instr *end) +{ + struct alt_instr *a; + u8 *instr, *replacement; + u8 insnbuf[MAX_PATCH_LEN]; + + /* + * The scan order should be from start to end. A later scanned + * alternative code can overwrite previously scanned alternative code. + */ + for (a = start; a < end; a++) { + int insnbuf_sz = 0; + + instr = (u8 *)&a->instr_offset + a->instr_offset; + replacement = (u8 *)&a->repl_offset + a->repl_offset; + + if (!__test_facility(a->facility, + S390_lowcore.alt_stfle_fac_list)) + continue; + + if (unlikely(a->instrlen % 2 || a->replacementlen % 2)) { + WARN_ONCE(1, "cpu alternatives instructions length is " + "odd, skipping patching\n"); + continue; + } + + memcpy(insnbuf, replacement, a->replacementlen); + insnbuf_sz = a->replacementlen; + + if (a->instrlen > a->replacementlen) { + add_padding(insnbuf + a->replacementlen, + a->instrlen - a->replacementlen); + insnbuf_sz += a->instrlen - a->replacementlen; + } + + s390_kernel_write(instr, insnbuf, insnbuf_sz); + } +} + +void __init_or_module apply_alternatives(struct alt_instr *start, + struct alt_instr *end) +{ + if (!alt_instr_disabled) + __apply_alternatives(start, end); +} + +extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; +void __init apply_alternative_instructions(void) +{ + apply_alternatives(__alt_instructions, __alt_instructions_end); +} diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index f7b280f0ab16..a3219837fa70 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -329,6 +329,11 @@ static noinline __init void setup_facility_list(void) { stfle(S390_lowcore.stfle_fac_list, ARRAY_SIZE(S390_lowcore.stfle_fac_list)); + memcpy(S390_lowcore.alt_stfle_fac_list, + S390_lowcore.stfle_fac_list, + sizeof(S390_lowcore.alt_stfle_fac_list)); + if (!IS_ENABLED(CONFIG_KERNEL_NOBP)) + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); } static __init void detect_diag9c(void) diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 7c6904d616d8..ed9aaa212d4a 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -106,6 +106,7 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 3f 1: UPDATE_VTIME %r14,%r15,\timer + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP 2: lg %r15,__LC_ASYNC_STACK # load async stack 3: la %r11,STACK_FRAME_OVERHEAD(%r15) .endm @@ -158,6 +159,130 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) tm off+\addr, \mask .endm + .macro BPOFF + .pushsection .altinstr_replacement, "ax" +660: .long 0xb2e8c000 + .popsection +661: .long 0x47000000 + .pushsection .altinstructions, "a" + .long 661b - . + .long 660b - . + .word 82 + .byte 4 + .byte 4 + .popsection + .endm + + .macro BPON + .pushsection .altinstr_replacement, "ax" +662: .long 0xb2e8d000 + .popsection +663: .long 0x47000000 + .pushsection .altinstructions, "a" + .long 663b - . + .long 662b - . + .word 82 + .byte 4 + .byte 4 + .popsection + .endm + + .macro BPENTER tif_ptr,tif_mask + .pushsection .altinstr_replacement, "ax" +662: .word 0xc004, 0x0000, 0x0000 # 6 byte nop + .word 0xc004, 0x0000, 0x0000 # 6 byte nop + .popsection +664: TSTMSK \tif_ptr,\tif_mask + jz . + 8 + .long 0xb2e8d000 + .pushsection .altinstructions, "a" + .long 664b - . + .long 662b - . + .word 82 + .byte 12 + .byte 12 + .popsection + .endm + + .macro BPEXIT tif_ptr,tif_mask + TSTMSK \tif_ptr,\tif_mask + .pushsection .altinstr_replacement, "ax" +662: jnz . + 8 + .long 0xb2e8d000 + .popsection +664: jz . + 8 + .long 0xb2e8c000 + .pushsection .altinstructions, "a" + .long 664b - . + .long 662b - . + .word 82 + .byte 8 + .byte 8 + .popsection + .endm + +#ifdef CONFIG_EXPOLINE + + .macro GEN_BR_THUNK name,reg,tmp + .section .text.\name,"axG",@progbits,\name,comdat + .globl \name + .hidden \name + .type \name,@function +\name: + .cfi_startproc +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + exrl 0,0f +#else + larl \tmp,0f + ex 0,0(\tmp) +#endif + j . +0: br \reg + .cfi_endproc + .endm + + GEN_BR_THUNK __s390x_indirect_jump_r1use_r9,%r9,%r1 + GEN_BR_THUNK __s390x_indirect_jump_r1use_r14,%r14,%r1 + GEN_BR_THUNK __s390x_indirect_jump_r11use_r14,%r14,%r11 + + .macro BASR_R14_R9 +0: brasl %r14,__s390x_indirect_jump_r1use_r9 + .pushsection .s390_indirect_branches,"a",@progbits + .long 0b-. + .popsection + .endm + + .macro BR_R1USE_R14 +0: jg __s390x_indirect_jump_r1use_r14 + .pushsection .s390_indirect_branches,"a",@progbits + .long 0b-. + .popsection + .endm + + .macro BR_R11USE_R14 +0: jg __s390x_indirect_jump_r11use_r14 + .pushsection .s390_indirect_branches,"a",@progbits + .long 0b-. + .popsection + .endm + +#else /* CONFIG_EXPOLINE */ + + .macro BASR_R14_R9 + basr %r14,%r9 + .endm + + .macro BR_R1USE_R14 + br %r14 + .endm + + .macro BR_R11USE_R14 + br %r14 + .endm + +#endif /* CONFIG_EXPOLINE */ + + .section .kprobes.text, "ax" .Ldummy: /* @@ -170,6 +295,11 @@ _PIF_WORK = (_PIF_PER_TRAP | _PIF_SYSCALL_RESTART) */ nop 0 +ENTRY(__bpon) + .globl __bpon + BPON + BR_R1USE_R14 + /* * Scheduler resume function, called by switch_to * gpr2 = (task_struct *) prev @@ -193,9 +323,9 @@ ENTRY(__switch_to) mvc __LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next lmg %r6,%r15,__SF_GPRS(%r15) # load gprs of next task TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_LPP - bzr %r14 + jz 0f .insn s,0xb2800000,__LC_LPP # set program parameter - br %r14 +0: BR_R1USE_R14 .L__critical_start: @@ -207,9 +337,11 @@ ENTRY(__switch_to) */ ENTRY(sie64a) stmg %r6,%r14,__SF_GPRS(%r15) # save kernel registers + lg %r12,__LC_CURRENT stg %r2,__SF_EMPTY(%r15) # save control block pointer stg %r3,__SF_EMPTY+8(%r15) # save guest register save area xc __SF_EMPTY+16(8,%r15),__SF_EMPTY+16(%r15) # reason code = 0 + mvc __SF_EMPTY+24(8,%r15),__TI_flags(%r12) # copy thread flags TSTMSK __LC_CPU_FLAGS,_CIF_FPU # load guest fp/vx registers ? jno .Lsie_load_guest_gprs brasl %r14,load_fpu_regs # load guest fp/vx regs @@ -226,8 +358,12 @@ ENTRY(sie64a) jnz .Lsie_skip TSTMSK __LC_CPU_FLAGS,_CIF_FPU jo .Lsie_skip # exit if fp/vx regs changed + BPEXIT __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) .Lsie_entry: sie 0(%r14) +.Lsie_exit: + BPOFF + BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) .Lsie_skip: ni __SIE_PROG0C+3(%r14),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce @@ -248,9 +384,15 @@ ENTRY(sie64a) sie_exit: lg %r14,__SF_EMPTY+8(%r15) # load guest register save area stmg %r0,%r13,0(%r14) # save guest gprs 0-13 + xgr %r0,%r0 # clear guest registers to + xgr %r1,%r1 # prevent speculative use + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 lmg %r6,%r14,__SF_GPRS(%r15) # restore kernel registers lg %r2,__SF_EMPTY+16(%r15) # return exit reason code - br %r14 + BR_R1USE_R14 .Lsie_fault: lghi %r14,-EFAULT stg %r14,__SF_EMPTY+16(%r15) # set exit reason code @@ -273,6 +415,7 @@ ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER .Lsysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC + BPOFF lg %r12,__LC_CURRENT lghi %r13,__TASK_thread lghi %r14,_PIF_SYSCALL @@ -281,12 +424,15 @@ ENTRY(system_call) la %r11,STACK_FRAME_OVERHEAD(%r15) # pointer to pt_regs .Lsysc_vtime: UPDATE_VTIME %r8,%r9,__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP stmg %r0,%r7,__PT_R0(%r11) mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC mvc __PT_PSW(16,%r11),__LC_SVC_OLD_PSW mvc __PT_INT_CODE(4,%r11),__LC_SVC_ILC stg %r14,__PT_FLAGS(%r11) .Lsysc_do_svc: + # clear user controlled register to prevent speculative use + xgr %r0,%r0 # load address of system call table lg %r10,__THREAD_sysc_table(%r13,%r12) llgh %r8,__PT_INT_CODE+2(%r11) @@ -305,7 +451,7 @@ ENTRY(system_call) lgf %r9,0(%r8,%r10) # get system call add. TSTMSK __TI_flags(%r12),_TIF_TRACE jnz .Lsysc_tracesys - basr %r14,%r9 # call sys_xxxx + BASR_R14_R9 # call sys_xxxx stg %r2,__PT_R2(%r11) # store return value .Lsysc_return: @@ -317,6 +463,7 @@ ENTRY(system_call) jnz .Lsysc_work # check for work TSTMSK __LC_CPU_FLAGS,_CIF_WORK jnz .Lsysc_work + BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP .Lsysc_restore: lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) @@ -481,7 +628,7 @@ ENTRY(system_call) lmg %r3,%r7,__PT_R3(%r11) stg %r7,STACK_FRAME_OVERHEAD(%r15) lg %r2,__PT_ORIG_GPR2(%r11) - basr %r14,%r9 # call sys_xxx + BASR_R14_R9 # call sys_xxx stg %r2,__PT_R2(%r11) # store return value .Lsysc_tracenogo: TSTMSK __TI_flags(%r12),_TIF_TRACE @@ -505,7 +652,7 @@ ENTRY(ret_from_fork) lmg %r9,%r10,__PT_R9(%r11) # load gprs ENTRY(kernel_thread_starter) la %r2,0(%r10) - basr %r14,%r9 + BASR_R14_R9 j .Lsysc_tracenogo /* @@ -514,6 +661,7 @@ ENTRY(kernel_thread_starter) ENTRY(pgm_check_handler) stpt __LC_SYNC_ENTER_TIMER + BPOFF stmg %r8,%r15,__LC_SAVE_AREA_SYNC lg %r10,__LC_LAST_BREAK lg %r12,__LC_CURRENT @@ -540,6 +688,7 @@ ENTRY(pgm_check_handler) aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 4f 2: UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP lg %r15,__LC_KERNEL_STACK lgr %r14,%r12 aghi %r14,__TASK_thread # pointer to thread_struct @@ -550,6 +699,15 @@ ENTRY(pgm_check_handler) 3: stg %r10,__THREAD_last_break(%r14) 4: la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_SYNC stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_INT_CODE(4,%r11),__LC_PGM_ILC @@ -571,9 +729,9 @@ ENTRY(pgm_check_handler) nill %r10,0x007f sll %r10,2 je .Lpgm_return - lgf %r1,0(%r10,%r1) # load address of handler routine + lgf %r9,0(%r10,%r1) # load address of handler routine lgr %r2,%r11 # pass pointer to pt_regs - basr %r14,%r1 # branch to interrupt-handler + BASR_R14_R9 # branch to interrupt-handler .Lpgm_return: LOCKDEP_SYS_EXIT tm __PT_PSW+1(%r11),0x01 # returning to user ? @@ -609,12 +767,23 @@ ENTRY(pgm_check_handler) ENTRY(io_int_handler) STCK __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER + BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC lg %r12,__LC_CURRENT larl %r13,cleanup_critical lmg %r8,%r9,__LC_IO_OLD_PSW SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 + xgr %r10,%r10 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) mvc __PT_INT_CODE(12,%r11),__LC_SUBCHANNEL_ID @@ -649,9 +818,13 @@ ENTRY(io_int_handler) lg %r14,__LC_VDSO_PER_CPU lmg %r0,%r10,__PT_R0(%r11) mvc __LC_RETURN_PSW(16),__PT_PSW(%r11) + tm __PT_PSW+1(%r11),0x01 # returning to user ? + jno .Lio_exit_kernel + BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP .Lio_exit_timer: stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER +.Lio_exit_kernel: lmg %r11,%r15,__PT_R11(%r11) lpswe __LC_RETURN_PSW .Lio_done: @@ -814,12 +987,23 @@ ENTRY(io_int_handler) ENTRY(ext_int_handler) STCK __LC_INT_CLOCK stpt __LC_ASYNC_ENTER_TIMER + BPOFF stmg %r8,%r15,__LC_SAVE_AREA_ASYNC lg %r12,__LC_CURRENT larl %r13,cleanup_critical lmg %r8,%r9,__LC_EXT_OLD_PSW SWITCH_ASYNC __LC_SAVE_AREA_ASYNC,__LC_ASYNC_ENTER_TIMER stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 + xgr %r10,%r10 mvc __PT_R8(64,%r11),__LC_SAVE_AREA_ASYNC stmg %r8,%r9,__PT_PSW(%r11) lghi %r1,__LC_EXT_PARAMS2 @@ -852,11 +1036,12 @@ ENTRY(psw_idle) .Lpsw_idle_stcctm: #endif oi __LC_CPU_FLAGS+7,_CIF_ENABLED_WAIT + BPON STCK __CLOCK_IDLE_ENTER(%r2) stpt __TIMER_IDLE_ENTER(%r2) .Lpsw_idle_lpsw: lpswe __SF_EMPTY(%r15) - br %r14 + BR_R1USE_R14 .Lpsw_idle_end: /* @@ -870,7 +1055,7 @@ ENTRY(save_fpu_regs) lg %r2,__LC_CURRENT aghi %r2,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bor %r14 + jo .Lsave_fpu_regs_exit stfpc __THREAD_FPU_fpc(%r2) lg %r3,__THREAD_FPU_regs(%r2) TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX @@ -897,7 +1082,8 @@ ENTRY(save_fpu_regs) std 15,120(%r3) .Lsave_fpu_regs_done: oi __LC_CPU_FLAGS+7,_CIF_FPU - br %r14 +.Lsave_fpu_regs_exit: + BR_R1USE_R14 .Lsave_fpu_regs_end: EXPORT_SYMBOL(save_fpu_regs) @@ -915,7 +1101,7 @@ load_fpu_regs: lg %r4,__LC_CURRENT aghi %r4,__TASK_thread TSTMSK __LC_CPU_FLAGS,_CIF_FPU - bnor %r14 + jno .Lload_fpu_regs_exit lfpc __THREAD_FPU_fpc(%r4) TSTMSK __LC_MACHINE_FLAGS,MACHINE_FLAG_VX lg %r4,__THREAD_FPU_regs(%r4) # %r4 <- reg save area @@ -942,7 +1128,8 @@ load_fpu_regs: ld 15,120(%r4) .Lload_fpu_regs_done: ni __LC_CPU_FLAGS+7,255-_CIF_FPU - br %r14 +.Lload_fpu_regs_exit: + BR_R1USE_R14 .Lload_fpu_regs_end: .L__critical_end: @@ -952,6 +1139,7 @@ load_fpu_regs: */ ENTRY(mcck_int_handler) STCK __LC_MCCK_CLOCK + BPOFF la %r1,4095 # revalidate r1 spt __LC_CPU_TIMER_SAVE_AREA-4095(%r1) # revalidate cpu timer lmg %r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)# revalidate gprs @@ -982,6 +1170,16 @@ ENTRY(mcck_int_handler) .Lmcck_skip: lghi %r14,__LC_GPREGS_SAVE_AREA+64 stmg %r0,%r7,__PT_R0(%r11) + # clear user controlled registers to prevent speculative use + xgr %r0,%r0 + xgr %r1,%r1 + xgr %r2,%r2 + xgr %r3,%r3 + xgr %r4,%r4 + xgr %r5,%r5 + xgr %r6,%r6 + xgr %r7,%r7 + xgr %r10,%r10 mvc __PT_R8(64,%r11),0(%r14) stmg %r8,%r9,__PT_PSW(%r11) xc __PT_FLAGS(8,%r11),__PT_FLAGS(%r11) @@ -1007,6 +1205,7 @@ ENTRY(mcck_int_handler) mvc __LC_RETURN_MCCK_PSW(16),__PT_PSW(%r11) # move return PSW tm __LC_RETURN_MCCK_PSW+1,0x01 # returning to user ? jno 0f + BPEXIT __TI_flags(%r12),_TIF_ISOLATE_BP stpt __LC_EXIT_TIMER mvc __VDSO_ECTG_BASE(16,%r14),__LC_EXIT_TIMER 0: lmg %r11,%r15,__PT_R11(%r11) @@ -1102,7 +1301,7 @@ cleanup_critical: jl 0f clg %r9,BASED(.Lcleanup_table+104) # .Lload_fpu_regs_end jl .Lcleanup_load_fpu_regs -0: br %r14 +0: BR_R11USE_R14 .align 8 .Lcleanup_table: @@ -1133,11 +1332,12 @@ cleanup_critical: clg %r9,BASED(.Lsie_crit_mcck_length) jh 1f oi __LC_CPU_FLAGS+7, _CIF_MCCK_GUEST -1: lg %r9,__SF_EMPTY(%r15) # get control block pointer +1: BPENTER __SF_EMPTY+24(%r15),(_TIF_ISOLATE_BP|_TIF_ISOLATE_BP_GUEST) + lg %r9,__SF_EMPTY(%r15) # get control block pointer ni __SIE_PROG0C+3(%r9),0xfe # no longer in SIE lctlg %c1,%c1,__LC_USER_ASCE # load primary asce larl %r9,sie_exit # skip forward to sie_exit - br %r14 + BR_R11USE_R14 #endif .Lcleanup_system_call: @@ -1175,6 +1375,7 @@ cleanup_critical: stg %r15,__LC_SYSTEM_TIMER 0: # update accounting time stamp mvc __LC_LAST_UPDATE_TIMER(8),__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP # set up saved register r11 lg %r15,__LC_KERNEL_STACK la %r9,STACK_FRAME_OVERHEAD(%r15) @@ -1190,7 +1391,7 @@ cleanup_critical: stg %r15,56(%r11) # r15 stack pointer # set new psw address and exit larl %r9,.Lsysc_do_svc - br %r14 + BR_R11USE_R14 .Lcleanup_system_call_insn: .quad system_call .quad .Lsysc_stmg @@ -1202,7 +1403,7 @@ cleanup_critical: .Lcleanup_sysc_tif: larl %r9,.Lsysc_tif - br %r14 + BR_R11USE_R14 .Lcleanup_sysc_restore: # check if stpt has been executed @@ -1219,14 +1420,14 @@ cleanup_critical: mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) 1: lmg %r8,%r9,__LC_RETURN_PSW - br %r14 + BR_R11USE_R14 .Lcleanup_sysc_restore_insn: .quad .Lsysc_exit_timer .quad .Lsysc_done - 4 .Lcleanup_io_tif: larl %r9,.Lio_tif - br %r14 + BR_R11USE_R14 .Lcleanup_io_restore: # check if stpt has been executed @@ -1240,7 +1441,7 @@ cleanup_critical: mvc 0(64,%r11),__PT_R8(%r9) lmg %r0,%r7,__PT_R0(%r9) 1: lmg %r8,%r9,__LC_RETURN_PSW - br %r14 + BR_R11USE_R14 .Lcleanup_io_restore_insn: .quad .Lio_exit_timer .quad .Lio_done - 4 @@ -1293,17 +1494,17 @@ cleanup_critical: # prepare return psw nihh %r8,0xfcfd # clear irq & wait state bits lg %r9,48(%r11) # return from psw_idle - br %r14 + BR_R11USE_R14 .Lcleanup_idle_insn: .quad .Lpsw_idle_lpsw .Lcleanup_save_fpu_regs: larl %r9,save_fpu_regs - br %r14 + BR_R11USE_R14 .Lcleanup_load_fpu_regs: larl %r9,load_fpu_regs - br %r14 + BR_R11USE_R14 /* * Integer constants @@ -1323,7 +1524,6 @@ cleanup_critical: .Lsie_crit_mcck_length: .quad .Lsie_skip - .Lsie_entry #endif - .section .rodata, "a" #define SYSCALL(esame,emu) .long esame .globl sys_call_table diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index d1a0e2c521d7..b565e784bae8 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -564,6 +564,7 @@ static struct kset *ipl_kset; static void __ipl_run(void *unused) { + __bpon(); diag308(DIAG308_LOAD_CLEAR, NULL); if (MACHINE_IS_VM) __cpcmd("IPL", NULL, 0, NULL); diff --git a/arch/s390/kernel/module.c b/arch/s390/kernel/module.c index 1a27f307a920..b441e069e674 100644 --- a/arch/s390/kernel/module.c +++ b/arch/s390/kernel/module.c @@ -31,6 +31,9 @@ #include #include #include +#include +#include +#include #if 0 #define DEBUGP printk @@ -168,7 +171,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, me->arch.got_offset = me->core_layout.size; me->core_layout.size += me->arch.got_size; me->arch.plt_offset = me->core_layout.size; - me->core_layout.size += me->arch.plt_size; + if (me->arch.plt_size) { + if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) + me->arch.plt_size += PLT_ENTRY_SIZE; + me->core_layout.size += me->arch.plt_size; + } return 0; } @@ -322,9 +329,20 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, unsigned int *ip; ip = me->core_layout.base + me->arch.plt_offset + info->plt_offset; - ip[0] = 0x0d10e310; /* basr 1,0; lg 1,10(1); br 1 */ - ip[1] = 0x100a0004; - ip[2] = 0x07f10000; + ip[0] = 0x0d10e310; /* basr 1,0 */ + ip[1] = 0x100a0004; /* lg 1,10(1) */ + if (IS_ENABLED(CONFIG_EXPOLINE) && !nospec_disable) { + unsigned int *ij; + ij = me->core_layout.base + + me->arch.plt_offset + + me->arch.plt_size - PLT_ENTRY_SIZE; + ip[2] = 0xa7f40000 + /* j __jump_r1 */ + (unsigned int)(u16) + (((unsigned long) ij - 8 - + (unsigned long) ip) / 2); + } else { + ip[2] = 0x07f10000; /* br %r1 */ + } ip[3] = (unsigned int) (val >> 32); ip[4] = (unsigned int) val; info->plt_initialized = 1; @@ -429,6 +447,45 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { + const Elf_Shdr *s; + char *secstrings, *secname; + void *aseg; + + if (IS_ENABLED(CONFIG_EXPOLINE) && + !nospec_disable && me->arch.plt_size) { + unsigned int *ij; + + ij = me->core_layout.base + me->arch.plt_offset + + me->arch.plt_size - PLT_ENTRY_SIZE; + if (test_facility(35)) { + ij[0] = 0xc6000000; /* exrl %r0,.+10 */ + ij[1] = 0x0005a7f4; /* j . */ + ij[2] = 0x000007f1; /* br %r1 */ + } else { + ij[0] = 0x44000000 | (unsigned int) + offsetof(struct lowcore, br_r1_trampoline); + ij[1] = 0xa7f40000; /* j . */ + } + } + + secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { + aseg = (void *) s->sh_addr; + secname = secstrings + s->sh_name; + + if (!strcmp(".altinstructions", secname)) + /* patch .altinstructions */ + apply_alternatives(aseg, aseg + s->sh_size); + + if (IS_ENABLED(CONFIG_EXPOLINE) && + (!strncmp(".s390_indirect", secname, 14))) + nospec_revert(aseg, aseg + s->sh_size); + + if (IS_ENABLED(CONFIG_EXPOLINE) && + (!strncmp(".s390_return", secname, 12))) + nospec_revert(aseg, aseg + s->sh_size); + } + jump_label_apply_nops(me); return 0; } diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c new file mode 100644 index 000000000000..9f3b5b382743 --- /dev/null +++ b/arch/s390/kernel/nospec-branch.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +static int __init nobp_setup_early(char *str) +{ + bool enabled; + int rc; + + rc = kstrtobool(str, &enabled); + if (rc) + return rc; + if (enabled && test_facility(82)) { + /* + * The user explicitely requested nobp=1, enable it and + * disable the expoline support. + */ + __set_facility(82, S390_lowcore.alt_stfle_fac_list); + if (IS_ENABLED(CONFIG_EXPOLINE)) + nospec_disable = 1; + } else { + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); + } + return 0; +} +early_param("nobp", nobp_setup_early); + +static int __init nospec_setup_early(char *str) +{ + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); + return 0; +} +early_param("nospec", nospec_setup_early); + +static int __init nospec_report(void) +{ + if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) + pr_info("Spectre V2 mitigation: execute trampolines.\n"); + if (__test_facility(82, S390_lowcore.alt_stfle_fac_list)) + pr_info("Spectre V2 mitigation: limited branch prediction.\n"); + return 0; +} +arch_initcall(nospec_report); + +#ifdef CONFIG_SYSFS +ssize_t cpu_show_spectre_v1(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +ssize_t cpu_show_spectre_v2(struct device *dev, + struct device_attribute *attr, char *buf) +{ + if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) + return sprintf(buf, "Mitigation: execute trampolines\n"); + if (__test_facility(82, S390_lowcore.alt_stfle_fac_list)) + return sprintf(buf, "Mitigation: limited branch prediction.\n"); + return sprintf(buf, "Vulnerable\n"); +} +#endif + +#ifdef CONFIG_EXPOLINE + +int nospec_disable = IS_ENABLED(CONFIG_EXPOLINE_OFF); + +static int __init nospectre_v2_setup_early(char *str) +{ + nospec_disable = 1; + return 0; +} +early_param("nospectre_v2", nospectre_v2_setup_early); + +void __init nospec_auto_detect(void) +{ + if (IS_ENABLED(CC_USING_EXPOLINE)) { + /* + * The kernel has been compiled with expolines. + * Keep expolines enabled and disable nobp. + */ + nospec_disable = 0; + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); + } + /* + * If the kernel has not been compiled with expolines the + * nobp setting decides what is done, this depends on the + * CONFIG_KERNEL_NP option and the nobp/nospec parameters. + */ +} + +static int __init spectre_v2_setup_early(char *str) +{ + if (str && !strncmp(str, "on", 2)) { + nospec_disable = 0; + __clear_facility(82, S390_lowcore.alt_stfle_fac_list); + } + if (str && !strncmp(str, "off", 3)) + nospec_disable = 1; + if (str && !strncmp(str, "auto", 4)) + nospec_auto_detect(); + return 0; +} +early_param("spectre_v2", spectre_v2_setup_early); + +static void __init_or_module __nospec_revert(s32 *start, s32 *end) +{ + enum { BRCL_EXPOLINE, BRASL_EXPOLINE } type; + u8 *instr, *thunk, *br; + u8 insnbuf[6]; + s32 *epo; + + /* Second part of the instruction replace is always a nop */ + memcpy(insnbuf + 2, (char[]) { 0x47, 0x00, 0x00, 0x00 }, 4); + for (epo = start; epo < end; epo++) { + instr = (u8 *) epo + *epo; + if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x04) + type = BRCL_EXPOLINE; /* brcl instruction */ + else if (instr[0] == 0xc0 && (instr[1] & 0x0f) == 0x05) + type = BRASL_EXPOLINE; /* brasl instruction */ + else + continue; + thunk = instr + (*(int *)(instr + 2)) * 2; + if (thunk[0] == 0xc6 && thunk[1] == 0x00) + /* exrl %r0, */ + br = thunk + (*(int *)(thunk + 2)) * 2; + else if (thunk[0] == 0xc0 && (thunk[1] & 0x0f) == 0x00 && + thunk[6] == 0x44 && thunk[7] == 0x00 && + (thunk[8] & 0x0f) == 0x00 && thunk[9] == 0x00 && + (thunk[1] & 0xf0) == (thunk[8] & 0xf0)) + /* larl %rx, + ex %r0,0(%rx) */ + br = thunk + (*(int *)(thunk + 2)) * 2; + else + continue; + if (br[0] != 0x07 || (br[1] & 0xf0) != 0xf0) + continue; + switch (type) { + case BRCL_EXPOLINE: + /* brcl to thunk, replace with br + nop */ + insnbuf[0] = br[0]; + insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f); + break; + case BRASL_EXPOLINE: + /* brasl to thunk, replace with basr + nop */ + insnbuf[0] = 0x0d; + insnbuf[1] = (instr[1] & 0xf0) | (br[1] & 0x0f); + break; + } + + s390_kernel_write(instr, insnbuf, 6); + } +} + +void __init_or_module nospec_revert(s32 *start, s32 *end) +{ + if (nospec_disable) + __nospec_revert(start, end); +} + +extern s32 __nospec_call_start[], __nospec_call_end[]; +extern s32 __nospec_return_start[], __nospec_return_end[]; +void __init nospec_init_branches(void) +{ + nospec_revert(__nospec_call_start, __nospec_call_end); + nospec_revert(__nospec_return_start, __nospec_return_end); +} + +#endif /* CONFIG_EXPOLINE */ diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 5362fd868d0d..6fe2e1875058 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -197,3 +197,21 @@ const struct seq_operations cpuinfo_op = { .stop = c_stop, .show = show_cpuinfo, }; + +int s390_isolate_bp(void) +{ + if (!test_facility(82)) + return -EOPNOTSUPP; + set_thread_flag(TIF_ISOLATE_BP); + return 0; +} +EXPORT_SYMBOL(s390_isolate_bp); + +int s390_isolate_bp_guest(void) +{ + if (!test_facility(82)) + return -EOPNOTSUPP; + set_thread_flag(TIF_ISOLATE_BP_GUEST); + return 0; +} +EXPORT_SYMBOL(s390_isolate_bp_guest); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 164a1e16b53e..98c1f7941142 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -66,6 +66,8 @@ #include #include #include +#include +#include #include "entry.h" /* @@ -338,7 +340,9 @@ static void __init setup_lowcore(void) lc->preempt_count = S390_lowcore.preempt_count; lc->stfl_fac_list = S390_lowcore.stfl_fac_list; memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, - MAX_FACILITY_BIT/8); + sizeof(lc->stfle_fac_list)); + memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list, + sizeof(lc->alt_stfle_fac_list)); if (MACHINE_HAS_VX || MACHINE_HAS_GS) { unsigned long bits, size; @@ -381,6 +385,7 @@ static void __init setup_lowcore(void) #ifdef CONFIG_SMP lc->spinlock_lockval = arch_spin_lockval(0); #endif + lc->br_r1_trampoline = 0x07f1; /* br %r1 */ set_prefix((u32)(unsigned long) lc); lowcore_ptr[0] = lc; @@ -892,6 +897,9 @@ void __init setup_arch(char **cmdline_p) init_mm.end_data = (unsigned long) &_edata; init_mm.brk = (unsigned long) &_end; + if (IS_ENABLED(CONFIG_EXPOLINE_AUTO)) + nospec_auto_detect(); + parse_early_param(); #ifdef CONFIG_CRASH_DUMP /* Deactivate elfcorehdr= kernel parameter */ @@ -955,6 +963,10 @@ void __init setup_arch(char **cmdline_p) conmode_default(); set_preferred_console(); + apply_alternative_instructions(); + if (IS_ENABLED(CONFIG_EXPOLINE)) + nospec_init_branches(); + /* Setup zfcpdump support */ setup_zfcpdump(); diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 7ffaf9fd6d19..ae5df4177803 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -228,6 +228,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) lc->mcesad = mcesa_origin | mcesa_bits; lc->cpu_nr = cpu; lc->spinlock_lockval = arch_spin_lockval(cpu); + lc->br_r1_trampoline = 0x07f1; /* br %r1 */ if (vdso_alloc_per_cpu(lc)) goto out; lowcore_ptr[cpu] = lc; @@ -282,7 +283,9 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu) __ctl_store(lc->cregs_save_area, 0, 15); save_access_regs((unsigned int *) lc->access_regs_save_area); memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list, - MAX_FACILITY_BIT/8); + sizeof(lc->stfle_fac_list)); + memcpy(lc->alt_stfle_fac_list, S390_lowcore.alt_stfle_fac_list, + sizeof(lc->alt_stfle_fac_list)); } static void pcpu_attach_task(struct pcpu *pcpu, struct task_struct *tsk) @@ -332,6 +335,7 @@ static void pcpu_delegate(struct pcpu *pcpu, void (*func)(void *), mem_assign_absolute(lc->restart_fn, (unsigned long) func); mem_assign_absolute(lc->restart_data, (unsigned long) data); mem_assign_absolute(lc->restart_source, source_cpu); + __bpon(); asm volatile( "0: sigp 0,%0,%2 # sigp restart to target cpu\n" " brc 2,0b # busy, try again\n" @@ -907,6 +911,7 @@ void __cpu_die(unsigned int cpu) void __noreturn cpu_die(void) { idle_task_exit(); + __bpon(); pcpu_sigp_retry(pcpu_devices + smp_processor_id(), SIGP_STOP, 0); for (;;) ; } diff --git a/arch/s390/kernel/uprobes.c b/arch/s390/kernel/uprobes.c index d9d1f512f019..5007fac01bb5 100644 --- a/arch/s390/kernel/uprobes.c +++ b/arch/s390/kernel/uprobes.c @@ -150,6 +150,15 @@ unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline, return orig; } +bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, + struct pt_regs *regs) +{ + if (ctx == RP_CHECK_CHAIN_CALL) + return user_stack_pointer(regs) <= ret->stack; + else + return user_stack_pointer(regs) < ret->stack; +} + /* Instruction Emulation */ static void adjust_psw_addr(psw_t *psw, unsigned long len) diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 96a713a470e7..85dd3c7bdd86 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -105,6 +105,43 @@ SECTIONS EXIT_DATA } + /* + * struct alt_inst entries. From the header (alternative.h): + * "Alternative instructions for different CPU types or capabilities" + * Think locking instructions on spinlocks. + * Note, that it is a part of __init region. + */ + . = ALIGN(8); + .altinstructions : { + __alt_instructions = .; + *(.altinstructions) + __alt_instructions_end = .; + } + + /* + * And here are the replacement instructions. The linker sticks + * them as binary blobs. The .altinstructions has enough data to + * get the address and the length of them to patch the kernel safely. + * Note, that it is a part of __init region. + */ + .altinstr_replacement : { + *(.altinstr_replacement) + } + + /* + * Table with the patch locations to undo expolines + */ + .nospec_call_table : { + __nospec_call_start = . ; + *(.s390_indirect*) + __nospec_call_end = . ; + } + .nospec_return_table : { + __nospec_return_start = . ; + *(.s390_return*) + __nospec_return_end = . ; + } + /* early.c uses stsi, which requires page aligned data. */ . = ALIGN(PAGE_SIZE); INIT_DATA_SECTION(0x100) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 0bce918db11a..4f6adbea592b 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -449,6 +449,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_GS: r = test_facility(133); break; + case KVM_CAP_S390_BPB: + r = test_facility(82); + break; default: r = 0; } @@ -2231,6 +2234,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; + if (test_kvm_facility(vcpu->kvm, 82)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; if (test_kvm_facility(vcpu->kvm, 133)) vcpu->run->kvm_valid_regs |= KVM_SYNC_GSCB; /* fprs can be synchronized via vrs, even if the guest has no vx. With @@ -2372,6 +2377,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu) current->thread.fpu.fpc = 0; vcpu->arch.sie_block->gbea = 1; vcpu->arch.sie_block->pp = 0; + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; kvm_clear_async_pf_completion_queue(vcpu); if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) @@ -3318,6 +3324,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.sie_block->ecd |= ECD_HOSTREGMGMT; vcpu->arch.gs_enabled = 1; } + if ((kvm_run->kvm_dirty_regs & KVM_SYNC_BPBC) && + test_kvm_facility(vcpu->kvm, 82)) { + vcpu->arch.sie_block->fpf &= ~FPF_BPBC; + vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0; + } save_access_regs(vcpu->arch.host_acrs); restore_access_regs(vcpu->run->s.regs.acrs); /* save host (userspace) fprs/vrs */ @@ -3364,6 +3375,7 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_run->s.regs.pft = vcpu->arch.pfault_token; kvm_run->s.regs.pfs = vcpu->arch.pfault_select; kvm_run->s.regs.pfc = vcpu->arch.pfault_compare; + kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC; save_access_regs(vcpu->run->s.regs.acrs); restore_access_regs(vcpu->arch.host_acrs); /* Save guest register state */ diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index a74204db759b..eb7b530d1783 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -234,6 +234,12 @@ static void unshadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) memcpy(scb_o->gcr, scb_s->gcr, 128); scb_o->pp = scb_s->pp; + /* branch prediction */ + if (test_kvm_facility(vcpu->kvm, 82)) { + scb_o->fpf &= ~FPF_BPBC; + scb_o->fpf |= scb_s->fpf & FPF_BPBC; + } + /* interrupt intercept */ switch (scb_s->icptcode) { case ICPT_PROGI: @@ -280,6 +286,7 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) scb_s->ecb3 = 0; scb_s->ecd = 0; scb_s->fac = 0; + scb_s->fpf = 0; rc = prepare_cpuflags(vcpu, vsie_page); if (rc) @@ -339,6 +346,9 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) prefix_unmapped(vsie_page); scb_s->ecb |= ECB_TE; } + /* branch prediction */ + if (test_kvm_facility(vcpu->kvm, 82)) + scb_s->fpf |= scb_o->fpf & FPF_BPBC; /* SIMD */ if (test_kvm_facility(vcpu->kvm, 129)) { scb_s->eca |= scb_o->eca & ECA_VX; @@ -821,6 +831,7 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) { struct kvm_s390_sie_block *scb_s = &vsie_page->scb_s; struct kvm_s390_sie_block *scb_o = vsie_page->scb_o; + int guest_bp_isolation; int rc; handle_last_fault(vcpu, vsie_page); @@ -831,6 +842,20 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) s390_handle_mcck(); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + + /* save current guest state of bp isolation override */ + guest_bp_isolation = test_thread_flag(TIF_ISOLATE_BP_GUEST); + + /* + * The guest is running with BPBC, so we have to force it on for our + * nested guest. This is done by enabling BPBC globally, so the BPBC + * control in the SCB (which the nested guest can modify) is simply + * ignored. + */ + if (test_kvm_facility(vcpu->kvm, 82) && + vcpu->arch.sie_block->fpf & FPF_BPBC) + set_thread_flag(TIF_ISOLATE_BP_GUEST); + local_irq_disable(); guest_enter_irqoff(); local_irq_enable(); @@ -840,6 +865,11 @@ static int do_vsie_run(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) local_irq_disable(); guest_exit_irqoff(); local_irq_enable(); + + /* restore guest state for bp isolation override */ + if (!guest_bp_isolation) + clear_thread_flag(TIF_ISOLATE_BP_GUEST); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (rc == -EINTR) { diff --git a/drivers/acpi/acpi_video.c b/drivers/acpi/acpi_video.c index f53ccc680238..dbdd460a9958 100644 --- a/drivers/acpi/acpi_video.c +++ b/drivers/acpi/acpi_video.c @@ -2123,6 +2123,25 @@ static int __init intel_opregion_present(void) return opregion; } +static bool dmi_is_desktop(void) +{ + const char *chassis_type; + + chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE); + if (!chassis_type) + return false; + + if (!strcmp(chassis_type, "3") || /* 3: Desktop */ + !strcmp(chassis_type, "4") || /* 4: Low Profile Desktop */ + !strcmp(chassis_type, "5") || /* 5: Pizza Box */ + !strcmp(chassis_type, "6") || /* 6: Mini Tower */ + !strcmp(chassis_type, "7") || /* 7: Tower */ + !strcmp(chassis_type, "11")) /* 11: Main Server Chassis */ + return true; + + return false; +} + int acpi_video_register(void) { int ret = 0; @@ -2143,8 +2162,12 @@ int acpi_video_register(void) * win8 ready (where we also prefer the native backlight driver, so * normally the acpi_video code should not register there anyways). */ - if (only_lcd == -1) - only_lcd = acpi_osi_is_win8(); + if (only_lcd == -1) { + if (dmi_is_desktop() && acpi_osi_is_win8()) + only_lcd = true; + else + only_lcd = false; + } dmi_check_system(video_dmi_table); diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 84434d3ea19b..e88d50f75a4a 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -110,7 +110,7 @@ struct iwm { /* Select values for swim_select and swim_readbit */ #define READ_DATA_0 0x074 -#define TWOMEG_DRIVE 0x075 +#define ONEMEG_DRIVE 0x075 #define SINGLE_SIDED 0x076 #define DRIVE_PRESENT 0x077 #define DISK_IN 0x170 @@ -118,9 +118,9 @@ struct iwm { #define TRACK_ZERO 0x172 #define TACHO 0x173 #define READ_DATA_1 0x174 -#define MFM_MODE 0x175 +#define GCR_MODE 0x175 #define SEEK_COMPLETE 0x176 -#define ONEMEG_MEDIA 0x177 +#define TWOMEG_MEDIA 0x177 /* Bits in handshake register */ @@ -612,7 +612,6 @@ static void setup_medium(struct floppy_state *fs) struct floppy_struct *g; fs->disk_in = 1; fs->write_protected = swim_readbit(base, WRITE_PROT); - fs->type = swim_readbit(base, ONEMEG_MEDIA); if (swim_track00(base)) printk(KERN_ERR @@ -620,6 +619,9 @@ static void setup_medium(struct floppy_state *fs) swim_track00(base); + fs->type = swim_readbit(base, TWOMEG_MEDIA) ? + HD_MEDIA : DD_MEDIA; + fs->head_number = swim_readbit(base, SINGLE_SIDED) ? 1 : 2; get_floppy_geometry(fs, 0, &g); fs->total_secs = g->size; fs->secpercyl = g->head * g->sect; @@ -646,7 +648,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) swim_write(base, setup, S_IBM_DRIVE | S_FCLK_DIV2); udelay(10); - swim_drive(base, INTERNAL_DRIVE); + swim_drive(base, fs->location); swim_motor(base, ON); swim_action(base, SETMFM); if (fs->ejected) @@ -656,6 +658,8 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) goto out; } + set_capacity(fs->disk, fs->total_secs); + if (mode & FMODE_NDELAY) return 0; @@ -727,14 +731,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode, if (copy_to_user((void __user *) param, (void *) &floppy_type, sizeof(struct floppy_struct))) return -EFAULT; - break; - - default: - printk(KERN_DEBUG "SWIM floppy_ioctl: unknown cmd %d\n", - cmd); - return -ENOSYS; + return 0; } - return 0; + return -ENOTTY; } static int floppy_getgeo(struct block_device *bdev, struct hd_geometry *geo) @@ -795,7 +794,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data) struct swim_priv *swd = data; int drive = (*part & 3); - if (drive > swd->floppy_count) + if (drive >= swd->floppy_count) return NULL; *part = 0; @@ -813,10 +812,9 @@ static int swim_add_floppy(struct swim_priv *swd, enum drive_location location) swim_motor(base, OFF); - if (swim_readbit(base, SINGLE_SIDED)) - fs->head_number = 1; - else - fs->head_number = 2; + fs->type = HD_MEDIA; + fs->head_number = 2; + fs->ref_count = 0; fs->ejected = 1; @@ -834,10 +832,12 @@ static int swim_floppy_init(struct swim_priv *swd) /* scan floppy drives */ swim_drive(base, INTERNAL_DRIVE); - if (swim_readbit(base, DRIVE_PRESENT)) + if (swim_readbit(base, DRIVE_PRESENT) && + !swim_readbit(base, ONEMEG_DRIVE)) swim_add_floppy(swd, INTERNAL_DRIVE); swim_drive(base, EXTERNAL_DRIVE); - if (swim_readbit(base, DRIVE_PRESENT)) + if (swim_readbit(base, DRIVE_PRESENT) && + !swim_readbit(base, ONEMEG_DRIVE)) swim_add_floppy(swd, EXTERNAL_DRIVE); /* register floppy drives */ @@ -861,7 +861,6 @@ static int swim_floppy_init(struct swim_priv *swd) &swd->lock); if (!swd->unit[drive].disk->queue) { err = -ENOMEM; - put_disk(swd->unit[drive].disk); goto exit_put_disks; } blk_queue_bounce_limit(swd->unit[drive].disk->queue, @@ -911,7 +910,7 @@ static int swim_probe(struct platform_device *dev) goto out; } - swim_base = ioremap(res->start, resource_size(res)); + swim_base = (struct swim __iomem *)res->start; if (!swim_base) { ret = -ENOMEM; goto out_release_io; @@ -923,7 +922,7 @@ static int swim_probe(struct platform_device *dev) if (!get_swim_mode(swim_base)) { printk(KERN_INFO "SWIM device not found !\n"); ret = -ENODEV; - goto out_iounmap; + goto out_release_io; } /* set platform driver data */ @@ -931,7 +930,7 @@ static int swim_probe(struct platform_device *dev) swd = kzalloc(sizeof(struct swim_priv), GFP_KERNEL); if (!swd) { ret = -ENOMEM; - goto out_iounmap; + goto out_release_io; } platform_set_drvdata(dev, swd); @@ -945,8 +944,6 @@ static int swim_probe(struct platform_device *dev) out_kfree: kfree(swd); -out_iounmap: - iounmap(swim_base); out_release_io: release_mem_region(res->start, resource_size(res)); out: @@ -974,8 +971,6 @@ static int swim_remove(struct platform_device *dev) for (drive = 0; drive < swd->floppy_count; drive++) floppy_eject(&swd->unit[drive]); - iounmap(swd->base); - res = platform_get_resource(dev, IORESOURCE_MEM, 0); if (res) release_mem_region(res->start, resource_size(res)); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 9f931f8f6b4c..0d7527c6825a 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -148,7 +148,7 @@ struct swim3 { #define MOTOR_ON 2 #define RELAX 3 /* also eject in progress */ #define READ_DATA_0 4 -#define TWOMEG_DRIVE 5 +#define ONEMEG_DRIVE 5 #define SINGLE_SIDED 6 /* drive or diskette is 4MB type? */ #define DRIVE_PRESENT 7 #define DISK_IN 8 @@ -156,9 +156,9 @@ struct swim3 { #define TRACK_ZERO 10 #define TACHO 11 #define READ_DATA_1 12 -#define MFM_MODE 13 +#define GCR_MODE 13 #define SEEK_COMPLETE 14 -#define ONEMEG_MEDIA 15 +#define TWOMEG_MEDIA 15 /* Definitions of values used in writing and formatting */ #define DATA_ESCAPE 0x99 diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index e36d160c458f..5f7d86509f2f 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2374,7 +2374,7 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, if (!CDROM_CAN(CDC_SELECT_DISC) || arg == CDSL_CURRENT) return media_changed(cdi, 1); - if ((unsigned int)arg >= cdi->capacity) + if (arg >= cdi->capacity) return -EINVAL; info = kmalloc(sizeof(*info), GFP_KERNEL); diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c index 1d01a8f77db1..dba5259def60 100644 --- a/drivers/char/tpm/tpm-interface.c +++ b/drivers/char/tpm/tpm-interface.c @@ -369,20 +369,40 @@ static int tpm_validate_command(struct tpm_chip *chip, return -EINVAL; } -/** - * tmp_transmit - Internal kernel interface to transmit TPM commands. - * - * @chip: TPM chip to use - * @buf: TPM command buffer - * @bufsiz: length of the TPM command buffer - * @flags: tpm transmit flags - bitmap - * - * Return: - * 0 when the operation is successful. - * A negative number for system errors (errno). - */ -ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, - u8 *buf, size_t bufsiz, unsigned int flags) +static int tpm_request_locality(struct tpm_chip *chip) +{ + int rc; + + if (!chip->ops->request_locality) + return 0; + + rc = chip->ops->request_locality(chip, 0); + if (rc < 0) + return rc; + + chip->locality = rc; + + return 0; +} + +static void tpm_relinquish_locality(struct tpm_chip *chip) +{ + int rc; + + if (!chip->ops->relinquish_locality) + return; + + rc = chip->ops->relinquish_locality(chip, chip->locality); + if (rc) + dev_err(&chip->dev, "%s: : error %d\n", __func__, rc); + + chip->locality = -1; +} + +static ssize_t tpm_try_transmit(struct tpm_chip *chip, + struct tpm_space *space, + u8 *buf, size_t bufsiz, + unsigned int flags) { struct tpm_output_header *header = (void *)buf; int rc; @@ -422,8 +442,6 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, if (!(flags & TPM_TRANSMIT_UNLOCKED)) mutex_lock(&chip->tpm_mutex); - if (chip->dev.parent) - pm_runtime_get_sync(chip->dev.parent); if (chip->ops->clk_enable != NULL) chip->ops->clk_enable(chip, true); @@ -431,14 +449,15 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, /* Store the decision as chip->locality will be changed. */ need_locality = chip->locality == -1; - if (!(flags & TPM_TRANSMIT_RAW) && - need_locality && chip->ops->request_locality) { - rc = chip->ops->request_locality(chip, 0); + if (!(flags & TPM_TRANSMIT_RAW) && need_locality) { + rc = tpm_request_locality(chip); if (rc < 0) goto out_no_locality; - chip->locality = rc; } + if (chip->dev.parent) + pm_runtime_get_sync(chip->dev.parent); + rc = tpm2_prepare_space(chip, space, ordinal, buf); if (rc) goto out; @@ -499,27 +518,83 @@ ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, rc = tpm2_commit_space(chip, space, ordinal, buf, &len); out: - if (need_locality && chip->ops->relinquish_locality) { - chip->ops->relinquish_locality(chip, chip->locality); - chip->locality = -1; - } + if (chip->dev.parent) + pm_runtime_put_sync(chip->dev.parent); + + if (need_locality) + tpm_relinquish_locality(chip); + out_no_locality: if (chip->ops->clk_enable != NULL) chip->ops->clk_enable(chip, false); - if (chip->dev.parent) - pm_runtime_put_sync(chip->dev.parent); - if (!(flags & TPM_TRANSMIT_UNLOCKED)) mutex_unlock(&chip->tpm_mutex); return rc ? rc : len; } /** - * tmp_transmit_cmd - send a tpm command to the device + * tpm_transmit - Internal kernel interface to transmit TPM commands. + * + * @chip: TPM chip to use + * @space: tpm space + * @buf: TPM command buffer + * @bufsiz: length of the TPM command buffer + * @flags: tpm transmit flags - bitmap + * + * A wrapper around tpm_try_transmit that handles TPM2_RC_RETRY + * returns from the TPM and retransmits the command after a delay up + * to a maximum wait of TPM2_DURATION_LONG. + * + * Note: TPM1 never returns TPM2_RC_RETRY so the retry logic is TPM2 + * only + * + * Return: + * the length of the return when the operation is successful. + * A negative number for system errors (errno). + */ +ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space, + u8 *buf, size_t bufsiz, unsigned int flags) +{ + struct tpm_output_header *header = (struct tpm_output_header *)buf; + /* space for header and handles */ + u8 save[TPM_HEADER_SIZE + 3*sizeof(u32)]; + unsigned int delay_msec = TPM2_DURATION_SHORT; + u32 rc = 0; + ssize_t ret; + const size_t save_size = min(space ? sizeof(save) : TPM_HEADER_SIZE, + bufsiz); + + /* + * Subtlety here: if we have a space, the handles will be + * transformed, so when we restore the header we also have to + * restore the handles. + */ + memcpy(save, buf, save_size); + + for (;;) { + ret = tpm_try_transmit(chip, space, buf, bufsiz, flags); + if (ret < 0) + break; + rc = be32_to_cpu(header->return_code); + if (rc != TPM2_RC_RETRY) + break; + delay_msec *= 2; + if (delay_msec > TPM2_DURATION_LONG) { + dev_err(&chip->dev, "TPM is in retry loop\n"); + break; + } + tpm_msleep(delay_msec); + memcpy(buf, save, save_size); + } + return ret; +} +/** + * tpm_transmit_cmd - send a tpm command to the device * The function extracts tpm out header return code * * @chip: TPM chip to use + * @space: tpm space * @buf: TPM command buffer * @bufsiz: length of the buffer * @min_rsp_body_length: minimum expected length of response body diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h index 0b5b499f726a..b83b30a3eea5 100644 --- a/drivers/char/tpm/tpm.h +++ b/drivers/char/tpm/tpm.h @@ -106,6 +106,7 @@ enum tpm2_return_codes { TPM2_RC_COMMAND_CODE = 0x0143, TPM2_RC_TESTING = 0x090A, /* RC_WARN */ TPM2_RC_REFERENCE_H0 = 0x0910, + TPM2_RC_RETRY = 0x0922, }; enum tpm2_algorithms { diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 8f0a98dea327..bb756ad7897e 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -117,6 +117,25 @@ struct tpm2_crb_smc { u32 smc_func_id; }; +static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, + unsigned long timeout) +{ + ktime_t start; + ktime_t stop; + + start = ktime_get(); + stop = ktime_add(start, ms_to_ktime(timeout)); + + do { + if ((ioread32(reg) & mask) == value) + return true; + + usleep_range(50, 100); + } while (ktime_before(ktime_get(), stop)); + + return ((ioread32(reg) & mask) == value); +} + /** * crb_go_idle - request tpm crb device to go the idle state * @@ -132,37 +151,24 @@ struct tpm2_crb_smc { * * Return: 0 always */ -static int __maybe_unused crb_go_idle(struct device *dev, struct crb_priv *priv) +static int crb_go_idle(struct device *dev, struct crb_priv *priv) { if ((priv->flags & CRB_FL_ACPI_START) || (priv->flags & CRB_FL_CRB_SMC_START)) return 0; iowrite32(CRB_CTRL_REQ_GO_IDLE, &priv->regs_t->ctrl_req); - /* we don't really care when this settles */ + if (!crb_wait_for_reg_32(&priv->regs_t->ctrl_req, + CRB_CTRL_REQ_GO_IDLE/* mask */, + 0, /* value */ + TPM2_TIMEOUT_C)) { + dev_warn(dev, "goIdle timed out\n"); + return -ETIME; + } return 0; } -static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, - unsigned long timeout) -{ - ktime_t start; - ktime_t stop; - - start = ktime_get(); - stop = ktime_add(start, ms_to_ktime(timeout)); - - do { - if ((ioread32(reg) & mask) == value) - return true; - - usleep_range(50, 100); - } while (ktime_before(ktime_get(), stop)); - - return false; -} - /** * crb_cmd_ready - request tpm crb device to enter ready state * @@ -177,8 +183,7 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value, * * Return: 0 on success -ETIME on timeout; */ -static int __maybe_unused crb_cmd_ready(struct device *dev, - struct crb_priv *priv) +static int crb_cmd_ready(struct device *dev, struct crb_priv *priv) { if ((priv->flags & CRB_FL_ACPI_START) || (priv->flags & CRB_FL_CRB_SMC_START)) @@ -196,11 +201,11 @@ static int __maybe_unused crb_cmd_ready(struct device *dev, return 0; } -static int crb_request_locality(struct tpm_chip *chip, int loc) +static int __crb_request_locality(struct device *dev, + struct crb_priv *priv, int loc) { - struct crb_priv *priv = dev_get_drvdata(&chip->dev); u32 value = CRB_LOC_STATE_LOC_ASSIGNED | - CRB_LOC_STATE_TPM_REG_VALID_STS; + CRB_LOC_STATE_TPM_REG_VALID_STS; if (!priv->regs_h) return 0; @@ -208,21 +213,45 @@ static int crb_request_locality(struct tpm_chip *chip, int loc) iowrite32(CRB_LOC_CTRL_REQUEST_ACCESS, &priv->regs_h->loc_ctrl); if (!crb_wait_for_reg_32(&priv->regs_h->loc_state, value, value, TPM2_TIMEOUT_C)) { - dev_warn(&chip->dev, "TPM_LOC_STATE_x.requestAccess timed out\n"); + dev_warn(dev, "TPM_LOC_STATE_x.requestAccess timed out\n"); return -ETIME; } return 0; } -static void crb_relinquish_locality(struct tpm_chip *chip, int loc) +static int crb_request_locality(struct tpm_chip *chip, int loc) { struct crb_priv *priv = dev_get_drvdata(&chip->dev); + return __crb_request_locality(&chip->dev, priv, loc); +} + +static int __crb_relinquish_locality(struct device *dev, + struct crb_priv *priv, int loc) +{ + u32 mask = CRB_LOC_STATE_LOC_ASSIGNED | + CRB_LOC_STATE_TPM_REG_VALID_STS; + u32 value = CRB_LOC_STATE_TPM_REG_VALID_STS; + if (!priv->regs_h) - return; + return 0; iowrite32(CRB_LOC_CTRL_RELINQUISH, &priv->regs_h->loc_ctrl); + if (!crb_wait_for_reg_32(&priv->regs_h->loc_state, mask, value, + TPM2_TIMEOUT_C)) { + dev_warn(dev, "TPM_LOC_STATE_x.requestAccess timed out\n"); + return -ETIME; + } + + return 0; +} + +static int crb_relinquish_locality(struct tpm_chip *chip, int loc) +{ + struct crb_priv *priv = dev_get_drvdata(&chip->dev); + + return __crb_relinquish_locality(&chip->dev, priv, loc); } static u8 crb_status(struct tpm_chip *chip) @@ -466,6 +495,10 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, dev_warn(dev, FW_BUG "Bad ACPI memory layout"); } + ret = __crb_request_locality(dev, priv, 0); + if (ret) + return ret; + priv->regs_t = crb_map_res(dev, priv, &io_res, buf->control_address, sizeof(struct crb_regs_tail)); if (IS_ERR(priv->regs_t)) @@ -522,6 +555,8 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, crb_go_idle(dev, priv); + __crb_relinquish_locality(dev, priv, 0); + return ret; } @@ -589,10 +624,14 @@ static int crb_acpi_add(struct acpi_device *device) chip->acpi_dev_handle = device->handle; chip->flags = TPM_CHIP_FLAG_TPM2; - rc = crb_cmd_ready(dev, priv); + rc = __crb_request_locality(dev, priv, 0); if (rc) return rc; + rc = crb_cmd_ready(dev, priv); + if (rc) + goto out; + pm_runtime_get_noresume(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); @@ -602,12 +641,15 @@ static int crb_acpi_add(struct acpi_device *device) crb_go_idle(dev, priv); pm_runtime_put_noidle(dev); pm_runtime_disable(dev); - return rc; + goto out; } - pm_runtime_put(dev); + pm_runtime_put_sync(dev); - return 0; +out: + __crb_relinquish_locality(dev, priv, 0); + + return rc; } static int crb_acpi_remove(struct acpi_device *device) diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index a21e31c2b952..58123df6b5f6 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -77,11 +77,13 @@ static bool check_locality(struct tpm_chip *chip, int l) return false; } -static void release_locality(struct tpm_chip *chip, int l) +static int release_locality(struct tpm_chip *chip, int l) { struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); tpm_tis_write8(priv, TPM_ACCESS(l), TPM_ACCESS_ACTIVE_LOCALITY); + + return 0; } static int request_locality(struct tpm_chip *chip, int l) diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index bf14214fa464..4db31b89507c 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1634,6 +1634,8 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi) * (and possibly on the platform). So far only i.MX6Q (v1.30a) and * i.MX6DL (v1.31a) have been identified as needing the workaround, with * 4 and 1 iterations respectively. + * The Amlogic Meson GX SoCs (v2.01a) have been identified as needing + * the workaround with a single iteration. */ switch (hdmi->version) { @@ -1641,6 +1643,7 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi) count = 4; break; case 0x131a: + case 0x201a: count = 1; break; default: diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c index 345f6035599e..f1d93676b0fc 100644 --- a/drivers/message/fusion/mptsas.c +++ b/drivers/message/fusion/mptsas.c @@ -1995,6 +1995,7 @@ static struct scsi_host_template mptsas_driver_template = { .cmd_per_lun = 7, .use_clustering = ENABLE_CLUSTERING, .shost_attrs = mptscsih_host_attrs, + .no_write_same = 1, }; static int mptsas_get_linkerrors(struct sas_phy *phy) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 82f28ffccddf..bf3be2e6d4a8 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1656,8 +1656,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } /* switch(bond_mode) */ #ifdef CONFIG_NET_POLL_CONTROLLER - slave_dev->npinfo = bond->dev->npinfo; - if (slave_dev->npinfo) { + if (bond->dev->npinfo) { if (slave_enable_netpoll(new_slave)) { netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n"); res = -EBUSY; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h index 7ea72ef11a55..d272dc6984ac 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h @@ -1321,6 +1321,10 @@ #define MDIO_VEND2_AN_STAT 0x8002 #endif +#ifndef MDIO_VEND2_PMA_CDR_CONTROL +#define MDIO_VEND2_PMA_CDR_CONTROL 0x8056 +#endif + #ifndef MDIO_CTRL1_SPEED1G #define MDIO_CTRL1_SPEED1G (MDIO_CTRL1_SPEED10G & ~BMCR_SPEED100) #endif @@ -1369,6 +1373,10 @@ #define XGBE_AN_CL37_TX_CONFIG_MASK 0x08 #define XGBE_AN_CL37_MII_CTRL_8BIT 0x0100 +#define XGBE_PMA_CDR_TRACK_EN_MASK 0x01 +#define XGBE_PMA_CDR_TRACK_EN_OFF 0x00 +#define XGBE_PMA_CDR_TRACK_EN_ON 0x01 + /* Bit setting and getting macros * The get macro will extract the current bit field value from within * the variable diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index 7d128be61310..b91143947ed2 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -519,6 +519,22 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata) "debugfs_create_file failed\n"); } + if (pdata->vdata->an_cdr_workaround) { + pfile = debugfs_create_bool("an_cdr_workaround", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_workaround); + if (!pfile) + netdev_err(pdata->netdev, + "debugfs_create_bool failed\n"); + + pfile = debugfs_create_bool("an_cdr_track_early", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_track_early); + if (!pfile) + netdev_err(pdata->netdev, + "debugfs_create_bool failed\n"); + } + kfree(buf); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-main.c b/drivers/net/ethernet/amd/xgbe/xgbe-main.c index d91fa595be98..e31d9d1fb6a6 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-main.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-main.c @@ -349,6 +349,7 @@ int xgbe_config_netdev(struct xgbe_prv_data *pdata) XGMAC_SET_BITS(pdata->rss_options, MAC_RSSCR, UDP4TE, 1); /* Call MDIO/PHY initialization routine */ + pdata->debugfs_an_cdr_workaround = pdata->vdata->an_cdr_workaround; ret = pdata->phy_if.phy_init(pdata); if (ret) return ret; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 072b9f664597..1b45cd73a258 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -432,11 +432,16 @@ static void xgbe_an73_disable(struct xgbe_prv_data *pdata) xgbe_an73_set(pdata, false, false); xgbe_an73_disable_interrupts(pdata); + pdata->an_start = 0; + netif_dbg(pdata, link, pdata->netdev, "CL73 AN disabled\n"); } static void xgbe_an_restart(struct xgbe_prv_data *pdata) { + if (pdata->phy_if.phy_impl.an_pre) + pdata->phy_if.phy_impl.an_pre(pdata); + switch (pdata->an_mode) { case XGBE_AN_MODE_CL73: case XGBE_AN_MODE_CL73_REDRV: @@ -453,6 +458,9 @@ static void xgbe_an_restart(struct xgbe_prv_data *pdata) static void xgbe_an_disable(struct xgbe_prv_data *pdata) { + if (pdata->phy_if.phy_impl.an_post) + pdata->phy_if.phy_impl.an_post(pdata); + switch (pdata->an_mode) { case XGBE_AN_MODE_CL73: case XGBE_AN_MODE_CL73_REDRV: @@ -505,11 +513,11 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata, XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg); - if (pdata->phy_if.phy_impl.kr_training_post) - pdata->phy_if.phy_impl.kr_training_post(pdata); - netif_dbg(pdata, link, pdata->netdev, "KR training initiated\n"); + + if (pdata->phy_if.phy_impl.kr_training_post) + pdata->phy_if.phy_impl.kr_training_post(pdata); } return XGBE_AN_PAGE_RECEIVED; @@ -637,11 +645,11 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata) return XGBE_AN_NO_LINK; } - xgbe_an73_disable(pdata); + xgbe_an_disable(pdata); xgbe_switch_mode(pdata); - xgbe_an73_restart(pdata); + xgbe_an_restart(pdata); return XGBE_AN_INCOMPAT_LINK; } @@ -820,6 +828,9 @@ static void xgbe_an37_state_machine(struct xgbe_prv_data *pdata) pdata->an_result = pdata->an_state; pdata->an_state = XGBE_AN_READY; + if (pdata->phy_if.phy_impl.an_post) + pdata->phy_if.phy_impl.an_post(pdata); + netif_dbg(pdata, link, pdata->netdev, "CL37 AN result: %s\n", xgbe_state_as_string(pdata->an_result)); } @@ -903,6 +914,9 @@ static void xgbe_an73_state_machine(struct xgbe_prv_data *pdata) pdata->kx_state = XGBE_RX_BPA; pdata->an_start = 0; + if (pdata->phy_if.phy_impl.an_post) + pdata->phy_if.phy_impl.an_post(pdata); + netif_dbg(pdata, link, pdata->netdev, "CL73 AN result: %s\n", xgbe_state_as_string(pdata->an_result)); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c index eb23f9ba1a9a..82d1f416ee2a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c @@ -456,6 +456,7 @@ static const struct xgbe_version_data xgbe_v2a = { .irq_reissue_support = 1, .tx_desc_prefetch = 5, .rx_desc_prefetch = 5, + .an_cdr_workaround = 1, }; static const struct xgbe_version_data xgbe_v2b = { @@ -470,6 +471,7 @@ static const struct xgbe_version_data xgbe_v2b = { .irq_reissue_support = 1, .tx_desc_prefetch = 5, .rx_desc_prefetch = 5, + .an_cdr_workaround = 1, }; static const struct pci_device_id xgbe_pci_table[] = { diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 3304a291aa96..aac884314000 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -147,6 +147,14 @@ /* Rate-change complete wait/retry count */ #define XGBE_RATECHANGE_COUNT 500 +/* CDR delay values for KR support (in usec) */ +#define XGBE_CDR_DELAY_INIT 10000 +#define XGBE_CDR_DELAY_INC 10000 +#define XGBE_CDR_DELAY_MAX 100000 + +/* RRC frequency during link status check */ +#define XGBE_RRC_FREQUENCY 10 + enum xgbe_port_mode { XGBE_PORT_MODE_RSVD = 0, XGBE_PORT_MODE_BACKPLANE, @@ -245,6 +253,10 @@ enum xgbe_sfp_speed { #define XGBE_SFP_BASE_VENDOR_SN 4 #define XGBE_SFP_BASE_VENDOR_SN_LEN 16 +#define XGBE_SFP_EXTD_OPT1 1 +#define XGBE_SFP_EXTD_OPT1_RX_LOS BIT(1) +#define XGBE_SFP_EXTD_OPT1_TX_FAULT BIT(3) + #define XGBE_SFP_EXTD_DIAG 28 #define XGBE_SFP_EXTD_DIAG_ADDR_CHANGE BIT(2) @@ -324,6 +336,7 @@ struct xgbe_phy_data { unsigned int sfp_gpio_address; unsigned int sfp_gpio_mask; + unsigned int sfp_gpio_inputs; unsigned int sfp_gpio_rx_los; unsigned int sfp_gpio_tx_fault; unsigned int sfp_gpio_mod_absent; @@ -355,6 +368,10 @@ struct xgbe_phy_data { unsigned int redrv_addr; unsigned int redrv_lane; unsigned int redrv_model; + + /* KR AN support */ + unsigned int phy_cdr_notrack; + unsigned int phy_cdr_delay; }; /* I2C, MDIO and GPIO lines are muxed, so only one device at a time */ @@ -974,6 +991,49 @@ static void xgbe_phy_sfp_external_phy(struct xgbe_prv_data *pdata) phy_data->sfp_phy_avail = 1; } +static bool xgbe_phy_check_sfp_rx_los(struct xgbe_phy_data *phy_data) +{ + u8 *sfp_extd = phy_data->sfp_eeprom.extd; + + if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_RX_LOS)) + return false; + + if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) + return false; + + if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_rx_los)) + return true; + + return false; +} + +static bool xgbe_phy_check_sfp_tx_fault(struct xgbe_phy_data *phy_data) +{ + u8 *sfp_extd = phy_data->sfp_eeprom.extd; + + if (!(sfp_extd[XGBE_SFP_EXTD_OPT1] & XGBE_SFP_EXTD_OPT1_TX_FAULT)) + return false; + + if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) + return false; + + if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_tx_fault)) + return true; + + return false; +} + +static bool xgbe_phy_check_sfp_mod_absent(struct xgbe_phy_data *phy_data) +{ + if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) + return false; + + if (phy_data->sfp_gpio_inputs & (1 << phy_data->sfp_gpio_mod_absent)) + return true; + + return false; +} + static bool xgbe_phy_belfuse_parse_quirks(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -1019,6 +1079,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata) if (sfp_base[XGBE_SFP_BASE_EXT_ID] != XGBE_SFP_EXT_ID_SFP) return; + /* Update transceiver signals (eeprom extd/options) */ + phy_data->sfp_tx_fault = xgbe_phy_check_sfp_tx_fault(phy_data); + phy_data->sfp_rx_los = xgbe_phy_check_sfp_rx_los(phy_data); + if (xgbe_phy_sfp_parse_quirks(pdata)) return; @@ -1184,7 +1248,6 @@ static int xgbe_phy_sfp_read_eeprom(struct xgbe_prv_data *pdata) static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; - unsigned int gpio_input; u8 gpio_reg, gpio_ports[2]; int ret; @@ -1199,23 +1262,9 @@ static void xgbe_phy_sfp_signals(struct xgbe_prv_data *pdata) return; } - gpio_input = (gpio_ports[1] << 8) | gpio_ports[0]; - - if (phy_data->sfp_gpio_mask & XGBE_GPIO_NO_MOD_ABSENT) { - /* No GPIO, just assume the module is present for now */ - phy_data->sfp_mod_absent = 0; - } else { - if (!(gpio_input & (1 << phy_data->sfp_gpio_mod_absent))) - phy_data->sfp_mod_absent = 0; - } - - if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_RX_LOS) && - (gpio_input & (1 << phy_data->sfp_gpio_rx_los))) - phy_data->sfp_rx_los = 1; + phy_data->sfp_gpio_inputs = (gpio_ports[1] << 8) | gpio_ports[0]; - if (!(phy_data->sfp_gpio_mask & XGBE_GPIO_NO_TX_FAULT) && - (gpio_input & (1 << phy_data->sfp_gpio_tx_fault))) - phy_data->sfp_tx_fault = 1; + phy_data->sfp_mod_absent = xgbe_phy_check_sfp_mod_absent(phy_data); } static void xgbe_phy_sfp_mod_absent(struct xgbe_prv_data *pdata) @@ -2361,7 +2410,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart) return 1; /* No link, attempt a receiver reset cycle */ - if (phy_data->rrc_count++) { + if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) { phy_data->rrc_count = 0; xgbe_phy_rrc(pdata); } @@ -2669,6 +2718,103 @@ static bool xgbe_phy_port_enabled(struct xgbe_prv_data *pdata) return true; } +static void xgbe_phy_cdr_track(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + if (!pdata->debugfs_an_cdr_workaround) + return; + + if (!phy_data->phy_cdr_notrack) + return; + + usleep_range(phy_data->phy_cdr_delay, + phy_data->phy_cdr_delay + 500); + + XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL, + XGBE_PMA_CDR_TRACK_EN_MASK, + XGBE_PMA_CDR_TRACK_EN_ON); + + phy_data->phy_cdr_notrack = 0; +} + +static void xgbe_phy_cdr_notrack(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + if (!pdata->debugfs_an_cdr_workaround) + return; + + if (phy_data->phy_cdr_notrack) + return; + + XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_CDR_CONTROL, + XGBE_PMA_CDR_TRACK_EN_MASK, + XGBE_PMA_CDR_TRACK_EN_OFF); + + xgbe_phy_rrc(pdata); + + phy_data->phy_cdr_notrack = 1; +} + +static void xgbe_phy_kr_training_post(struct xgbe_prv_data *pdata) +{ + if (!pdata->debugfs_an_cdr_track_early) + xgbe_phy_cdr_track(pdata); +} + +static void xgbe_phy_kr_training_pre(struct xgbe_prv_data *pdata) +{ + if (pdata->debugfs_an_cdr_track_early) + xgbe_phy_cdr_track(pdata); +} + +static void xgbe_phy_an_post(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + switch (pdata->an_mode) { + case XGBE_AN_MODE_CL73: + case XGBE_AN_MODE_CL73_REDRV: + if (phy_data->cur_mode != XGBE_MODE_KR) + break; + + xgbe_phy_cdr_track(pdata); + + switch (pdata->an_result) { + case XGBE_AN_READY: + case XGBE_AN_COMPLETE: + break; + default: + if (phy_data->phy_cdr_delay < XGBE_CDR_DELAY_MAX) + phy_data->phy_cdr_delay += XGBE_CDR_DELAY_INC; + else + phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT; + break; + } + break; + default: + break; + } +} + +static void xgbe_phy_an_pre(struct xgbe_prv_data *pdata) +{ + struct xgbe_phy_data *phy_data = pdata->phy_data; + + switch (pdata->an_mode) { + case XGBE_AN_MODE_CL73: + case XGBE_AN_MODE_CL73_REDRV: + if (phy_data->cur_mode != XGBE_MODE_KR) + break; + + xgbe_phy_cdr_notrack(pdata); + break; + default: + break; + } +} + static void xgbe_phy_stop(struct xgbe_prv_data *pdata) { struct xgbe_phy_data *phy_data = pdata->phy_data; @@ -2680,6 +2826,9 @@ static void xgbe_phy_stop(struct xgbe_prv_data *pdata) xgbe_phy_sfp_reset(phy_data); xgbe_phy_sfp_mod_absent(pdata); + /* Reset CDR support */ + xgbe_phy_cdr_track(pdata); + /* Power off the PHY */ xgbe_phy_power_off(pdata); @@ -2712,6 +2861,9 @@ static int xgbe_phy_start(struct xgbe_prv_data *pdata) /* Start in highest supported mode */ xgbe_phy_set_mode(pdata, phy_data->start_mode); + /* Reset CDR support */ + xgbe_phy_cdr_track(pdata); + /* After starting the I2C controller, we can check for an SFP */ switch (phy_data->port_mode) { case XGBE_PORT_MODE_SFP: @@ -3019,6 +3171,8 @@ static int xgbe_phy_init(struct xgbe_prv_data *pdata) } } + phy_data->phy_cdr_delay = XGBE_CDR_DELAY_INIT; + /* Register for driving external PHYs */ mii = devm_mdiobus_alloc(pdata->dev); if (!mii) { @@ -3071,4 +3225,10 @@ void xgbe_init_function_ptrs_phy_v2(struct xgbe_phy_if *phy_if) phy_impl->an_advertising = xgbe_phy_an_advertising; phy_impl->an_outcome = xgbe_phy_an_outcome; + + phy_impl->an_pre = xgbe_phy_an_pre; + phy_impl->an_post = xgbe_phy_an_post; + + phy_impl->kr_training_pre = xgbe_phy_kr_training_pre; + phy_impl->kr_training_post = xgbe_phy_kr_training_post; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index ad102c8bac7b..95d4b56448c6 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -833,6 +833,7 @@ struct xgbe_hw_if { /* This structure represents implementation specific routines for an * implementation of a PHY. All routines are required unless noted below. * Optional routines: + * an_pre, an_post * kr_training_pre, kr_training_post */ struct xgbe_phy_impl_if { @@ -875,6 +876,10 @@ struct xgbe_phy_impl_if { /* Process results of auto-negotiation */ enum xgbe_mode (*an_outcome)(struct xgbe_prv_data *); + /* Pre/Post auto-negotiation support */ + void (*an_pre)(struct xgbe_prv_data *); + void (*an_post)(struct xgbe_prv_data *); + /* Pre/Post KR training enablement support */ void (*kr_training_pre)(struct xgbe_prv_data *); void (*kr_training_post)(struct xgbe_prv_data *); @@ -989,6 +994,7 @@ struct xgbe_version_data { unsigned int irq_reissue_support; unsigned int tx_desc_prefetch; unsigned int rx_desc_prefetch; + unsigned int an_cdr_workaround; }; struct xgbe_vxlan_data { @@ -1257,6 +1263,9 @@ struct xgbe_prv_data { unsigned int debugfs_xprop_reg; unsigned int debugfs_xi2c_reg; + + bool debugfs_an_cdr_workaround; + bool debugfs_an_cdr_track_early; }; /* Function prototypes*/ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index e368b0237a1b..4a85a24ced1c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2781,6 +2781,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) int ret = 0; struct hlist_node *h; int bkt; + u8 i; /* validate the request */ if (vf_id >= pf->num_alloc_vfs) { @@ -2792,6 +2793,16 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) vf = &(pf->vf[vf_id]); vsi = pf->vsi[vf->lan_vsi_idx]; + + /* When the VF is resetting wait until it is done. + * It can take up to 200 milliseconds, + * but wait for up to 300 milliseconds to be safe. + */ + for (i = 0; i < 15; i++) { + if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) + break; + msleep(20); + } if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { dev_err(&pf->pdev->dev, "VF %d still in reset. Try again.\n", vf_id); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index a5bb7b19040e..992c43b1868f 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -124,7 +124,7 @@ do { \ #define RX_PRIORITY_MAPPING 0x76543210 #define TX_PRIORITY_MAPPING 0x33221100 -#define CPDMA_TX_PRIORITY_MAP 0x01234567 +#define CPDMA_TX_PRIORITY_MAP 0x76543210 #define CPSW_VLAN_AWARE BIT(1) #define CPSW_ALE_VLAN_AWARE 1 diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 5aa59f41bf8c..71e2aef6b7a1 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -620,6 +620,10 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); error = -EINVAL; + + if (sockaddr_len != sizeof(struct sockaddr_pppox)) + goto end; + if (sp->sa_protocol != PX_PROTO_OE) goto end; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 2a366554c503..8a222ae5950e 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -261,6 +261,17 @@ static void __team_option_inst_mark_removed_port(struct team *team, } } +static bool __team_option_inst_tmp_find(const struct list_head *opts, + const struct team_option_inst *needle) +{ + struct team_option_inst *opt_inst; + + list_for_each_entry(opt_inst, opts, tmp_list) + if (opt_inst == needle) + return true; + return false; +} + static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) @@ -1061,14 +1072,11 @@ static void team_port_leave(struct team *team, struct team_port *port) } #ifdef CONFIG_NET_POLL_CONTROLLER -static int team_port_enable_netpoll(struct team *team, struct team_port *port) +static int __team_port_enable_netpoll(struct team_port *port) { struct netpoll *np; int err; - if (!team->dev->npinfo) - return 0; - np = kzalloc(sizeof(*np), GFP_KERNEL); if (!np) return -ENOMEM; @@ -1082,6 +1090,14 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port) return err; } +static int team_port_enable_netpoll(struct team_port *port) +{ + if (!port->team->dev->npinfo) + return 0; + + return __team_port_enable_netpoll(port); +} + static void team_port_disable_netpoll(struct team_port *port) { struct netpoll *np = port->np; @@ -1096,7 +1112,7 @@ static void team_port_disable_netpoll(struct team_port *port) kfree(np); } #else -static int team_port_enable_netpoll(struct team *team, struct team_port *port) +static int team_port_enable_netpoll(struct team_port *port) { return 0; } @@ -1204,7 +1220,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_vids_add; } - err = team_port_enable_netpoll(team, port); + err = team_port_enable_netpoll(port); if (err) { netdev_err(dev, "Failed to enable netpoll on device %s\n", portname); @@ -1901,7 +1917,7 @@ static int team_netpoll_setup(struct net_device *dev, mutex_lock(&team->lock); list_for_each_entry(port, &team->port_list, list) { - err = team_port_enable_netpoll(team, port); + err = __team_port_enable_netpoll(port); if (err) { __team_netpoll_cleanup(team); break; @@ -2561,6 +2577,14 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) if (err) goto team_put; opt_inst->changed = true; + + /* dumb/evil user-space can send us duplicate opt, + * keep only the last one + */ + if (__team_option_inst_tmp_find(&opt_inst_list, + opt_inst)) + continue; + list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index b0a038e6fda0..bb15b3012aa5 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -116,6 +116,17 @@ struct receive_queue { char name[40]; }; +/* Control VQ buffers: protected by the rtnl lock */ +struct control_buf { + struct virtio_net_ctrl_hdr hdr; + virtio_net_ctrl_ack status; + struct virtio_net_ctrl_mq mq; + u8 promisc; + u8 allmulti; + __virtio16 vid; + u64 offloads; +}; + struct virtnet_info { struct virtio_device *vdev; struct virtqueue *cvq; @@ -164,14 +175,7 @@ struct virtnet_info { struct hlist_node node; struct hlist_node node_dead; - /* Control VQ buffers: protected by the rtnl lock */ - struct virtio_net_ctrl_hdr ctrl_hdr; - virtio_net_ctrl_ack ctrl_status; - struct virtio_net_ctrl_mq ctrl_mq; - u8 ctrl_promisc; - u8 ctrl_allmulti; - u16 ctrl_vid; - u64 ctrl_offloads; + struct control_buf *ctrl; /* Ethtool settings */ u8 duplex; @@ -1340,25 +1344,25 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, /* Caller should know better */ BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ)); - vi->ctrl_status = ~0; - vi->ctrl_hdr.class = class; - vi->ctrl_hdr.cmd = cmd; + vi->ctrl->status = ~0; + vi->ctrl->hdr.class = class; + vi->ctrl->hdr.cmd = cmd; /* Add header */ - sg_init_one(&hdr, &vi->ctrl_hdr, sizeof(vi->ctrl_hdr)); + sg_init_one(&hdr, &vi->ctrl->hdr, sizeof(vi->ctrl->hdr)); sgs[out_num++] = &hdr; if (out) sgs[out_num++] = out; /* Add return status. */ - sg_init_one(&stat, &vi->ctrl_status, sizeof(vi->ctrl_status)); + sg_init_one(&stat, &vi->ctrl->status, sizeof(vi->ctrl->status)); sgs[out_num] = &stat; BUG_ON(out_num + 1 > ARRAY_SIZE(sgs)); virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC); if (unlikely(!virtqueue_kick(vi->cvq))) - return vi->ctrl_status == VIRTIO_NET_OK; + return vi->ctrl->status == VIRTIO_NET_OK; /* Spin for a response, the kick causes an ioport write, trapping * into the hypervisor, so the request should be handled immediately. @@ -1367,7 +1371,7 @@ static bool virtnet_send_command(struct virtnet_info *vi, u8 class, u8 cmd, !virtqueue_is_broken(vi->cvq)) cpu_relax(); - return vi->ctrl_status == VIRTIO_NET_OK; + return vi->ctrl->status == VIRTIO_NET_OK; } static int virtnet_set_mac_address(struct net_device *dev, void *p) @@ -1478,8 +1482,8 @@ static int _virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) if (!vi->has_cvq || !virtio_has_feature(vi->vdev, VIRTIO_NET_F_MQ)) return 0; - vi->ctrl_mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); - sg_init_one(&sg, &vi->ctrl_mq, sizeof(vi->ctrl_mq)); + vi->ctrl->mq.virtqueue_pairs = cpu_to_virtio16(vi->vdev, queue_pairs); + sg_init_one(&sg, &vi->ctrl->mq, sizeof(vi->ctrl->mq)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ, VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET, &sg)) { @@ -1537,22 +1541,22 @@ static void virtnet_set_rx_mode(struct net_device *dev) if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_RX)) return; - vi->ctrl_promisc = ((dev->flags & IFF_PROMISC) != 0); - vi->ctrl_allmulti = ((dev->flags & IFF_ALLMULTI) != 0); + vi->ctrl->promisc = ((dev->flags & IFF_PROMISC) != 0); + vi->ctrl->allmulti = ((dev->flags & IFF_ALLMULTI) != 0); - sg_init_one(sg, &vi->ctrl_promisc, sizeof(vi->ctrl_promisc)); + sg_init_one(sg, &vi->ctrl->promisc, sizeof(vi->ctrl->promisc)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_PROMISC, sg)) dev_warn(&dev->dev, "Failed to %sable promisc mode.\n", - vi->ctrl_promisc ? "en" : "dis"); + vi->ctrl->promisc ? "en" : "dis"); - sg_init_one(sg, &vi->ctrl_allmulti, sizeof(vi->ctrl_allmulti)); + sg_init_one(sg, &vi->ctrl->allmulti, sizeof(vi->ctrl->allmulti)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_RX, VIRTIO_NET_CTRL_RX_ALLMULTI, sg)) dev_warn(&dev->dev, "Failed to %sable allmulti mode.\n", - vi->ctrl_allmulti ? "en" : "dis"); + vi->ctrl->allmulti ? "en" : "dis"); uc_count = netdev_uc_count(dev); mc_count = netdev_mc_count(dev); @@ -1598,8 +1602,8 @@ static int virtnet_vlan_rx_add_vid(struct net_device *dev, struct virtnet_info *vi = netdev_priv(dev); struct scatterlist sg; - vi->ctrl_vid = vid; - sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid)); + vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid); + sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_ADD, &sg)) @@ -1613,8 +1617,8 @@ static int virtnet_vlan_rx_kill_vid(struct net_device *dev, struct virtnet_info *vi = netdev_priv(dev); struct scatterlist sg; - vi->ctrl_vid = vid; - sg_init_one(&sg, &vi->ctrl_vid, sizeof(vi->ctrl_vid)); + vi->ctrl->vid = cpu_to_virtio16(vi->vdev, vid); + sg_init_one(&sg, &vi->ctrl->vid, sizeof(vi->ctrl->vid)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN, VIRTIO_NET_CTRL_VLAN_DEL, &sg)) @@ -1912,9 +1916,9 @@ static int virtnet_restore_up(struct virtio_device *vdev) static int virtnet_set_guest_offloads(struct virtnet_info *vi, u64 offloads) { struct scatterlist sg; - vi->ctrl_offloads = cpu_to_virtio64(vi->vdev, offloads); + vi->ctrl->offloads = cpu_to_virtio64(vi->vdev, offloads); - sg_init_one(&sg, &vi->ctrl_offloads, sizeof(vi->ctrl_offloads)); + sg_init_one(&sg, &vi->ctrl->offloads, sizeof(vi->ctrl->offloads)); if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_GUEST_OFFLOADS, VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET, &sg)) { @@ -2134,6 +2138,7 @@ static void virtnet_free_queues(struct virtnet_info *vi) kfree(vi->rq); kfree(vi->sq); + kfree(vi->ctrl); } static void _free_receive_bufs(struct virtnet_info *vi) @@ -2326,6 +2331,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi) { int i; + vi->ctrl = kzalloc(sizeof(*vi->ctrl), GFP_KERNEL); + if (!vi->ctrl) + goto err_ctrl; vi->sq = kzalloc(sizeof(*vi->sq) * vi->max_queue_pairs, GFP_KERNEL); if (!vi->sq) goto err_sq; @@ -2351,6 +2359,8 @@ static int virtnet_alloc_queues(struct virtnet_info *vi) err_rq: kfree(vi->sq); err_sq: + kfree(vi->ctrl); +err_ctrl: return -ENOMEM; } diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 252c2206cbb5..c1772215702a 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -5955,9 +5955,8 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk) sta->addr, smps, err); } - if (changed & IEEE80211_RC_SUPP_RATES_CHANGED || - changed & IEEE80211_RC_NSS_CHANGED) { - ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM supp rates/nss\n", + if (changed & IEEE80211_RC_SUPP_RATES_CHANGED) { + ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM supp rates\n", sta->addr); err = ath10k_station_assoc(ar, arvif->vif, sta, true); diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 72b4527d690f..71df0f70b61f 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -427,18 +427,6 @@ static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input) writel(value, padcfg0); } -static void intel_gpio_set_gpio_mode(void __iomem *padcfg0) -{ - u32 value; - - /* Put the pad into GPIO mode */ - value = readl(padcfg0) & ~PADCFG0_PMODE_MASK; - /* Disable SCI/SMI/NMI generation */ - value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI); - value &= ~(PADCFG0_GPIROUTSMI | PADCFG0_GPIROUTNMI); - writel(value, padcfg0); -} - static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range, unsigned pin) @@ -446,6 +434,7 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, struct intel_pinctrl *pctrl = pinctrl_dev_get_drvdata(pctldev); void __iomem *padcfg0; unsigned long flags; + u32 value; raw_spin_lock_irqsave(&pctrl->lock, flags); @@ -455,7 +444,13 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev, } padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0); - intel_gpio_set_gpio_mode(padcfg0); + /* Put the pad into GPIO mode */ + value = readl(padcfg0) & ~PADCFG0_PMODE_MASK; + /* Disable SCI/SMI/NMI generation */ + value &= ~(PADCFG0_GPIROUTIOXAPIC | PADCFG0_GPIROUTSCI); + value &= ~(PADCFG0_GPIROUTSMI | PADCFG0_GPIROUTNMI); + writel(value, padcfg0); + /* Disable TX buffer and enable RX (this will be input) */ __intel_gpio_set_direction(padcfg0, true); @@ -940,8 +935,6 @@ static int intel_gpio_irq_type(struct irq_data *d, unsigned type) raw_spin_lock_irqsave(&pctrl->lock, flags); - intel_gpio_set_gpio_mode(reg); - value = readl(reg); value &= ~(PADCFG0_RXEVCFG_MASK | PADCFG0_RXINV); diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 62f5f04d8f61..5e963fe0e38d 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -592,13 +592,22 @@ static int _schedule_lcu_update(struct alias_lcu *lcu, int dasd_alias_add_device(struct dasd_device *device) { struct dasd_eckd_private *private = device->private; - struct alias_lcu *lcu; + __u8 uaddr = private->uid.real_unit_addr; + struct alias_lcu *lcu = private->lcu; unsigned long flags; int rc; - lcu = private->lcu; rc = 0; spin_lock_irqsave(&lcu->lock, flags); + /* + * Check if device and lcu type differ. If so, the uac data may be + * outdated and needs to be updated. + */ + if (private->uid.type != lcu->uac->unit[uaddr].ua_type) { + lcu->flags |= UPDATE_PENDING; + DBF_DEV_EVENT(DBF_WARNING, device, "%s", + "uid type mismatch - trigger rescan"); + } if (!(lcu->flags & UPDATE_PENDING)) { rc = _add_device_to_lcu(lcu, device, device); if (rc) diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile index 05ac6ba15a53..ecc24a46e71a 100644 --- a/drivers/s390/char/Makefile +++ b/drivers/s390/char/Makefile @@ -17,6 +17,8 @@ CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_MARCH) CFLAGS_sclp_early_core.o += -march=z900 endif +CFLAGS_REMOVE_sclp_early_core.o += $(CC_FLAGS_EXPOLINE) + obj-y += ctrlchar.o keyboard.o defkeymap.o sclp.o sclp_rw.o sclp_quiesce.o \ sclp_cmd.o sclp_config.o sclp_cpi_sys.o sclp_ocf.o sclp_ctl.o \ sclp_early.o sclp_early_core.o diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 7b0b295b2313..69687c16a150 100644 --- a/drivers/s390/cio/chsc.c +++ b/drivers/s390/cio/chsc.c @@ -451,6 +451,7 @@ static void chsc_process_sei_link_incident(struct chsc_sei_nt0_area *sei_area) static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area) { + struct channel_path *chp; struct chp_link link; struct chp_id chpid; int status; @@ -463,10 +464,17 @@ static void chsc_process_sei_res_acc(struct chsc_sei_nt0_area *sei_area) chpid.id = sei_area->rsid; /* allocate a new channel path structure, if needed */ status = chp_get_status(chpid); - if (status < 0) - chp_new(chpid); - else if (!status) + if (!status) return; + + if (status < 0) { + chp_new(chpid); + } else { + chp = chpid_to_chp(chpid); + mutex_lock(&chp->lock); + chp_update_desc(chp); + mutex_unlock(&chp->lock); + } memset(&link, 0, sizeof(struct chp_link)); link.chpid = chpid; if ((sei_area->vf & 0xc0) != 0) { diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 3597ef78df4d..ce74278a454a 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -217,12 +217,10 @@ struct fsnotify_mark_connector { union { /* Object pointer [lock] */ struct inode *inode; struct vfsmount *mnt; - }; - union { - struct hlist_head list; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; + struct hlist_head list; }; /* diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 8198faf16ed6..96e69979f84d 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -498,16 +498,23 @@ struct hmm_device { struct hmm_device *hmm_device_new(void *drvdata); void hmm_device_put(struct hmm_device *hmm_device); #endif /* CONFIG_DEVICE_PRIVATE || CONFIG_DEVICE_PUBLIC */ +#endif /* IS_ENABLED(CONFIG_HMM) */ /* Below are for HMM internal use only! Not to be used by device driver! */ +#if IS_ENABLED(CONFIG_HMM_MIRROR) void hmm_mm_destroy(struct mm_struct *mm); static inline void hmm_mm_init(struct mm_struct *mm) { mm->hmm = NULL; } +#else /* IS_ENABLED(CONFIG_HMM_MIRROR) */ +static inline void hmm_mm_destroy(struct mm_struct *mm) {} +static inline void hmm_mm_init(struct mm_struct *mm) {} +#endif /* IS_ENABLED(CONFIG_HMM_MIRROR) */ + + #else /* IS_ENABLED(CONFIG_HMM) */ static inline void hmm_mm_destroy(struct mm_struct *mm) {} static inline void hmm_mm_init(struct mm_struct *mm) {} -#endif /* IS_ENABLED(CONFIG_HMM) */ #endif /* LINUX_HMM_H */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 5e6a2d4dc366..ab927383c99d 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -584,7 +584,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb) * Returns true if the skb is tagged with multiple vlan headers, regardless * of whether it is hardware accelerated or not. */ -static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) +static inline bool skb_vlan_tagged_multi(struct sk_buff *skb) { __be16 protocol = skb->protocol; @@ -594,6 +594,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) if (likely(!eth_type_vlan(protocol))) return false; + if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) + return false; + veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } @@ -611,7 +614,7 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) * * Returns features without unsafe ones if the skb has multiple tags. */ -static inline netdev_features_t vlan_features_check(const struct sk_buff *skb, +static inline netdev_features_t vlan_features_check(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tagged_multi(skb)) { diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 881312d85574..2a6c3d96b31f 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -49,7 +49,7 @@ struct tpm_class_ops { bool (*update_timeouts)(struct tpm_chip *chip, unsigned long *timeout_cap); int (*request_locality)(struct tpm_chip *chip, int loc); - void (*relinquish_locality)(struct tpm_chip *chip, int loc); + int (*relinquish_locality)(struct tpm_chip *chip, int loc); void (*clk_enable)(struct tpm_chip *chip, bool value); }; diff --git a/include/net/ife.h b/include/net/ife.h index 44b9c00f7223..e117617e3c34 100644 --- a/include/net/ife.h +++ b/include/net/ife.h @@ -12,7 +12,8 @@ void *ife_encode(struct sk_buff *skb, u16 metalen); void *ife_decode(struct sk_buff *skb, u16 *metalen); -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen); +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen); int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval); diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index fe994d2e5286..ea985aa7a6c5 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -97,6 +97,7 @@ static __inline__ char llc_backlog_type(struct sk_buff *skb) struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct proto *prot, int kern); +void llc_sk_stop_all_timers(struct sock *sk, bool sync); void llc_sk_free(struct sock *sk); void llc_sk_reset(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index d323d4fa742c..fb653736f335 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1616,6 +1616,7 @@ static inline void tcp_write_queue_purge(struct sock *sk) sk_mem_reclaim(sk); tcp_clear_all_retrans_hints(tcp_sk(sk)); tcp_init_send_head(sk); + tcp_sk(sk)->packets_out = 0; } static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 7e99999d6236..857bad91c454 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -931,6 +931,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_PPC_SMT_POSSIBLE 147 #define KVM_CAP_HYPERV_SYNIC2 148 #define KVM_CAP_HYPERV_VP_INDEX 149 +#define KVM_CAP_S390_BPB 152 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h index e954ae3d82c0..e3a658bac10f 100644 --- a/kernel/trace/trace_entries.h +++ b/kernel/trace/trace_entries.h @@ -356,7 +356,7 @@ FTRACE_ENTRY(hwlat, hwlat_entry, __field( unsigned int, seqnum ) ), - F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llunmi-ts:%llu\tnmi-count:%u\n", + F_printk("cnt:%u\tts:%010llu.%010lu\tinner:%llu\touter:%llu\tnmi-ts:%llu\tnmi-count:%u\n", __entry->seqnum, __entry->tv_sec, __entry->tv_nsec, diff --git a/net/core/dev.c b/net/core/dev.c index 4be2a4047640..e7d56c5adde6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2903,7 +2903,7 @@ netdev_features_t passthru_features_check(struct sk_buff *skb, } EXPORT_SYMBOL(passthru_features_check); -static netdev_features_t dflt_features_check(const struct sk_buff *skb, +static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 741ae2554190..514d697d4691 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -55,7 +55,8 @@ static void neigh_timer_handler(unsigned long arg); static void __neigh_notify(struct neighbour *n, int type, int flags, u32 pid); static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid); -static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev); +static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, + struct net_device *dev); #ifdef CONFIG_PROC_FS static const struct file_operations neigh_stat_seq_fops; @@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev) { write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev); - pneigh_ifdown(tbl, dev); - write_unlock_bh(&tbl->lock); + pneigh_ifdown_and_unlock(tbl, dev); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); @@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey, return -ENOENT; } -static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) +static int pneigh_ifdown_and_unlock(struct neigh_table *tbl, + struct net_device *dev) { - struct pneigh_entry *n, **np; + struct pneigh_entry *n, **np, *freelist = NULL; u32 h; for (h = 0; h <= PNEIGH_HASHMASK; h++) { @@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev) while ((n = *np) != NULL) { if (!dev || n->dev == dev) { *np = n->next; - if (tbl->pdestructor) - tbl->pdestructor(n); - if (n->dev) - dev_put(n->dev); - kfree(n); + n->next = freelist; + freelist = n; continue; } np = &n->next; } } + write_unlock_bh(&tbl->lock); + while ((n = freelist)) { + freelist = n->next; + n->next = NULL; + if (tbl->pdestructor) + tbl->pdestructor(n); + if (n->dev) + dev_put(n->dev); + kfree(n); + } return -ENOENT; } @@ -2323,12 +2331,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL, NULL); if (!err) { - if (tb[NDA_IFINDEX]) + if (tb[NDA_IFINDEX]) { + if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32)) + return -EINVAL; filter_idx = nla_get_u32(tb[NDA_IFINDEX]); - - if (tb[NDA_MASTER]) + } + if (tb[NDA_MASTER]) { + if (nla_len(tb[NDA_MASTER]) != sizeof(u32)) + return -EINVAL; filter_master_idx = nla_get_u32(tb[NDA_MASTER]); - + } if (filter_idx || filter_master_idx) flags |= NLM_F_DUMP_FILTERED; } diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index e1d4d898a007..f0252768ecf4 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -91,9 +92,9 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (!opt_len) { - printk(KERN_WARNING - "Empty option to dns_resolver key\n"); + if (opt_len <= 0 || opt_len > 128) { + pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", + opt_len); return -EINVAL; } @@ -127,10 +128,8 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) } bad_option_value: - printk(KERN_WARNING - "Option '%*.*s' to dns_resolver key:" - " bad/missing value\n", - opt_nlen, opt_nlen, opt); + pr_warn_ratelimited("Option '%*.*s' to dns_resolver key: bad/missing value\n", + opt_nlen, opt_nlen, opt); return -EINVAL; } while (opt = next_opt + 1, opt < end); } diff --git a/net/ife/ife.c b/net/ife/ife.c index 7d1ec76e7f43..13bbf8cb6a39 100644 --- a/net/ife/ife.c +++ b/net/ife/ife.c @@ -69,6 +69,9 @@ void *ife_decode(struct sk_buff *skb, u16 *metalen) int total_pull; u16 ifehdrln; + if (!pskb_may_pull(skb, skb->dev->hard_header_len + IFE_METAHDRLEN)) + return NULL; + ifehdr = (struct ifeheadr *) (skb->data + skb->dev->hard_header_len); ifehdrln = ntohs(ifehdr->metalen); total_pull = skb->dev->hard_header_len + ifehdrln; @@ -92,12 +95,43 @@ struct meta_tlvhdr { __be16 len; }; +static bool __ife_tlv_meta_valid(const unsigned char *skbdata, + const unsigned char *ifehdr_end) +{ + const struct meta_tlvhdr *tlv; + u16 tlvlen; + + if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end)) + return false; + + tlv = (const struct meta_tlvhdr *)skbdata; + tlvlen = ntohs(tlv->len); + + /* tlv length field is inc header, check on minimum */ + if (tlvlen < NLA_HDRLEN) + return false; + + /* overflow by NLA_ALIGN check */ + if (NLA_ALIGN(tlvlen) < tlvlen) + return false; + + if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end)) + return false; + + return true; +} + /* Caller takes care of presenting data in network order */ -void *ife_tlv_meta_decode(void *skbdata, u16 *attrtype, u16 *dlen, u16 *totlen) +void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype, + u16 *dlen, u16 *totlen) { - struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata; + struct meta_tlvhdr *tlv; + + if (!__ife_tlv_meta_valid(skbdata, ifehdr_end)) + return NULL; + tlv = (struct meta_tlvhdr *)skbdata; *dlen = ntohs(tlv->len) - NLA_HDRLEN; *attrtype = ntohs(tlv->type); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 38b9a6276a9d..d023f879e7bb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2354,7 +2354,6 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; - tp->packets_out = 0; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; @@ -2742,8 +2741,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); + else + err = -EINVAL; break; #endif case TCP_USER_TIMEOUT: diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 14474acea0bb..ebbb54bcbcac 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3892,11 +3892,8 @@ const u8 *tcp_parse_md5sig_option(const struct tcphdr *th) int length = (th->doff << 2) - sizeof(*th); const u8 *ptr = (const u8 *)(th + 1); - /* If the TCP option is too short, we can short cut */ - if (length < TCPOLEN_MD5SIG) - return NULL; - - while (length > 0) { + /* If not enough data remaining, we can short cut */ + while (length >= TCPOLEN_MD5SIG) { int opcode = *ptr++; int opsize; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0126d9bfa670..e04c534b573e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2959,6 +2959,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu) static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, + [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, @@ -2970,6 +2971,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index f343e6f0fc95..5fe139484919 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -136,7 +136,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) isrh->nexthdr = proto; hdr->daddr = isrh->segments[isrh->first_segment]; - set_tun_src(net, ip6_dst_idev(dst)->dev, &hdr->daddr, &hdr->saddr); + set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr); #ifdef CONFIG_IPV6_SEG6_HMAC if (sr_has_hmac(isrh)) { diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 0c2738349442..8bef35aa8786 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -591,6 +591,13 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, lock_sock(sk); error = -EINVAL; + + if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) && + sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6)) + goto end; + if (sp->sa_protocol != PX_PROTO_OL2TP) goto end; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index c38d16f22d2a..cf41d9b4a0b8 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -199,9 +199,19 @@ static int llc_ui_release(struct socket *sock) llc->laddr.lsap, llc->daddr.lsap); if (!llc_send_disc(sk)) llc_ui_wait_for_disc(sk, sk->sk_rcvtimeo); - if (!sock_flag(sk, SOCK_ZAPPED)) + if (!sock_flag(sk, SOCK_ZAPPED)) { + struct llc_sap *sap = llc->sap; + + /* Hold this for release_sock(), so that llc_backlog_rcv() + * could still use it. + */ + llc_sap_hold(sap); llc_sap_remove_socket(llc->sap, sk); - release_sock(sk); + release_sock(sk); + llc_sap_put(sap); + } else { + release_sock(sk); + } if (llc->dev) dev_put(llc->dev); sock_put(sk); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index ea225bd2672c..f8d4ab8ca1a5 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -1096,14 +1096,7 @@ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb) int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb) { - struct llc_sock *llc = llc_sk(sk); - - del_timer(&llc->pf_cycle_timer.timer); - del_timer(&llc->ack_timer.timer); - del_timer(&llc->rej_sent_timer.timer); - del_timer(&llc->busy_state_timer.timer); - llc->ack_must_be_send = 0; - llc->ack_pf = 0; + llc_sk_stop_all_timers(sk, false); return 0; } diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 5e91b47f0d2a..9a42448eb182 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -951,6 +951,26 @@ struct sock *llc_sk_alloc(struct net *net, int family, gfp_t priority, struct pr return sk; } +void llc_sk_stop_all_timers(struct sock *sk, bool sync) +{ + struct llc_sock *llc = llc_sk(sk); + + if (sync) { + del_timer_sync(&llc->pf_cycle_timer.timer); + del_timer_sync(&llc->ack_timer.timer); + del_timer_sync(&llc->rej_sent_timer.timer); + del_timer_sync(&llc->busy_state_timer.timer); + } else { + del_timer(&llc->pf_cycle_timer.timer); + del_timer(&llc->ack_timer.timer); + del_timer(&llc->rej_sent_timer.timer); + del_timer(&llc->busy_state_timer.timer); + } + + llc->ack_must_be_send = 0; + llc->ack_pf = 0; +} + /** * llc_sk_free - Frees a LLC socket * @sk - socket to free @@ -963,7 +983,7 @@ void llc_sk_free(struct sock *sk) llc->state = LLC_CONN_OUT_OF_SVC; /* Stop all (possibly) running timers */ - llc_conn_ac_stop_all_timers(sk, NULL); + llc_sk_stop_all_timers(sk, true); #ifdef DEBUG_LLC_CONN_ALLOC printk(KERN_INFO "%s: unackq=%d, txq=%d\n", __func__, skb_queue_len(&llc->pdu_unack_q), diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index f4a0587b7d5e..3994b71f8197 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -331,11 +331,11 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) skb_set_queue_mapping(skb, queue_index); } -/* register_prot_hook must be invoked with the po->bind_lock held, +/* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ -static void register_prot_hook(struct sock *sk) +static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); @@ -350,8 +350,13 @@ static void register_prot_hook(struct sock *sk) } } -/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock - * held. If the sync parameter is true, we will temporarily drop +static void register_prot_hook(struct sock *sk) +{ + lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); + __register_prot_hook(sk); +} + +/* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the @@ -361,6 +366,8 @@ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); + lockdep_assert_held_once(&po->bind_lock); + po->running = 0; if (po->fanout) @@ -3017,6 +3024,7 @@ static int packet_release(struct socket *sock) packet_flush_mclist(sk); + lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); @@ -3026,6 +3034,7 @@ static int packet_release(struct socket *sock) memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } + release_sock(sk); f = fanout_release(sk); @@ -3259,7 +3268,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, if (proto) { po->prot_hook.type = proto; - register_prot_hook(sk); + __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); @@ -3654,6 +3663,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv union tpacket_req_u req_u; int len; + lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: @@ -3664,12 +3674,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv len = sizeof(req_u.req3); break; } - if (optlen < len) - return -EINVAL; - if (copy_from_user(&req_u.req, optval, len)) - return -EFAULT; - return packet_set_ring(sk, &req_u, 0, - optname == PACKET_TX_RING); + if (optlen < len) { + ret = -EINVAL; + } else { + if (copy_from_user(&req_u.req, optval, len)) + ret = -EFAULT; + else + ret = packet_set_ring(sk, &req_u, 0, + optname == PACKET_TX_RING); + } + release_sock(sk); + return ret; } case PACKET_COPY_THRESH: { @@ -3735,12 +3750,18 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_loss = !!val; - return 0; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_loss = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_AUXDATA: { @@ -3751,7 +3772,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->auxdata = !!val; + release_sock(sk); return 0; } case PACKET_ORIGDEV: @@ -3763,7 +3786,9 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; + lock_sock(sk); po->origdev = !!val; + release_sock(sk); return 0; } case PACKET_VNET_HDR: @@ -3772,15 +3797,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (sock->type != SOCK_RAW) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->has_vnet_hdr = !!val; - return 0; + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->has_vnet_hdr = !!val; + ret = 0; + } + release_sock(sk); + return ret; } case PACKET_TIMESTAMP: { @@ -3818,11 +3848,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv if (optlen != sizeof(val)) return -EINVAL; - if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) - return -EBUSY; if (copy_from_user(&val, optval, sizeof(val))) return -EFAULT; - po->tp_tx_has_off = !!val; + + lock_sock(sk); + if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { + ret = -EBUSY; + } else { + po->tp_tx_has_off = !!val; + ret = 0; + } + release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: @@ -4219,8 +4255,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; - lock_sock(sk); - rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; @@ -4358,7 +4392,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: - release_sock(sk); return err; } diff --git a/net/packet/internal.h b/net/packet/internal.h index a1d2b2319ae9..3bb7c5fb3bff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -112,10 +112,12 @@ struct packet_sock { int copy_thresh; spinlock_t bind_lock; struct mutex pg_vec_lock; - unsigned int running:1, /* prot_hook is attached*/ - auxdata:1, + unsigned int running; /* bind_lock must be held */ + unsigned int auxdata:1, /* writer must hold sock lock */ origdev:1, - has_vnet_hdr:1; + has_vnet_hdr:1, + tp_loss:1, + tp_tx_has_off:1; int pressure; int ifindex; /* bound device */ __be16 num; @@ -125,8 +127,6 @@ struct packet_sock { enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve; - unsigned int tp_loss:1; - unsigned int tp_tx_has_off:1; unsigned int tp_tstamp; struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 8ccd35825b6b..85757af7f150 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -605,7 +605,7 @@ static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, } } - return 0; + return -ENOENT; } static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, @@ -639,7 +639,12 @@ static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, u16 mtype; u16 dlen; - curr_data = ife_tlv_meta_decode(tlv_data, &mtype, &dlen, NULL); + curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, + &dlen, NULL); + if (!curr_data) { + qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); + return TC_ACT_SHOT; + } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 08b5705e7381..7219a1c041f7 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -521,46 +521,49 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr, addr->v6.sin6_scope_id = 0; } -/* Compare addresses exactly. - * v4-mapped-v6 is also in consideration. - */ -static int sctp_v6_cmp_addr(const union sctp_addr *addr1, - const union sctp_addr *addr2) +static int __sctp_v6_cmp_addr(const union sctp_addr *addr1, + const union sctp_addr *addr2) { if (addr1->sa.sa_family != addr2->sa.sa_family) { if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr2->v6.sin6_addr)) { - if (addr2->v6.sin6_port == addr1->v4.sin_port && - addr2->v6.sin6_addr.s6_addr32[3] == - addr1->v4.sin_addr.s_addr) - return 1; - } + ipv6_addr_v4mapped(&addr2->v6.sin6_addr) && + addr2->v6.sin6_addr.s6_addr32[3] == + addr1->v4.sin_addr.s_addr) + return 1; + if (addr2->sa.sa_family == AF_INET && addr1->sa.sa_family == AF_INET6 && - ipv6_addr_v4mapped(&addr1->v6.sin6_addr)) { - if (addr1->v6.sin6_port == addr2->v4.sin_port && - addr1->v6.sin6_addr.s6_addr32[3] == - addr2->v4.sin_addr.s_addr) - return 1; - } + ipv6_addr_v4mapped(&addr1->v6.sin6_addr) && + addr1->v6.sin6_addr.s6_addr32[3] == + addr2->v4.sin_addr.s_addr) + return 1; + return 0; } - if (addr1->v6.sin6_port != addr2->v6.sin6_port) - return 0; + if (!ipv6_addr_equal(&addr1->v6.sin6_addr, &addr2->v6.sin6_addr)) return 0; + /* If this is a linklocal address, compare the scope_id. */ - if (ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) { - if (addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id && - (addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id)) { - return 0; - } - } + if ((ipv6_addr_type(&addr1->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL) && + addr1->v6.sin6_scope_id && addr2->v6.sin6_scope_id && + addr1->v6.sin6_scope_id != addr2->v6.sin6_scope_id) + return 0; return 1; } +/* Compare addresses exactly. + * v4-mapped-v6 is also in consideration. + */ +static int sctp_v6_cmp_addr(const union sctp_addr *addr1, + const union sctp_addr *addr2) +{ + return __sctp_v6_cmp_addr(addr1, addr2) && + addr1->v6.sin6_port == addr2->v6.sin6_port; +} + /* Initialize addr struct to INADDR_ANY. */ static void sctp_v6_inaddr_any(union sctp_addr *addr, __be16 port) { @@ -845,8 +848,8 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, const union sctp_addr *addr2, struct sctp_sock *opt) { - struct sctp_af *af1, *af2; struct sock *sk = sctp_opt2sk(opt); + struct sctp_af *af1, *af2; af1 = sctp_get_af_specific(addr1->sa.sa_family); af2 = sctp_get_af_specific(addr2->sa.sa_family); @@ -862,10 +865,7 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2)) return 1; - if (addr1->sa.sa_family != addr2->sa.sa_family) - return 0; - - return af1->cmp_addr(addr1, addr2); + return __sctp_v6_cmp_addr(addr1, addr2); } /* Verify that the provided sockaddr looks bindable. Common verification, diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a6d604fd9695..f9c289e05707 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1203,14 +1203,12 @@ static int smc_shutdown(struct socket *sock, int how) rc = smc_close_shutdown_write(smc); break; case SHUT_RD: - if (sk->sk_state == SMC_LISTEN) - rc = smc_close_active(smc); - else - rc = 0; - /* nothing more to do because peer is not involved */ + rc = 0; + /* nothing more to do because peer is not involved */ break; } - rc1 = kernel_sock_shutdown(smc->clcsock, how); + if (smc->clcsock) + rc1 = kernel_sock_shutdown(smc->clcsock, how); /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 4a3a3f1331ee..c741365f77da 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -67,7 +67,7 @@ static void strp_abort_strp(struct strparser *strp, int err) static void strp_start_timer(struct strparser *strp, long timeo) { - if (timeo) + if (timeo && timeo != LONG_MAX) mod_delayed_work(strp_wq, &strp->msg_timer_work, timeo); } @@ -296,9 +296,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, strp_start_timer(strp, timeo); } + stm->accum_len += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; - stm->accum_len += cand_len; stm->early_eaten = cand_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ @@ -321,6 +321,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, /* Hurray, we have a new message! */ cancel_delayed_work(&strp->msg_timer_work); strp->skb_head = NULL; + strp->need_bytes = 0; STRP_STATS_INCR(strp->stats.msgs); /* Give skb to upper layer */ @@ -410,9 +411,7 @@ void strp_data_ready(struct strparser *strp) return; if (strp->need_bytes) { - if (strp_peek_len(strp) >= strp->need_bytes) - strp->need_bytes = 0; - else + if (strp_peek_len(strp) < strp->need_bytes) return; } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index b76f13f6fea1..d4e0bbeee727 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -79,7 +79,8 @@ const struct nla_policy tipc_nl_sock_policy[TIPC_NLA_SOCK_MAX + 1] = { const struct nla_policy tipc_nl_net_policy[TIPC_NLA_NET_MAX + 1] = { [TIPC_NLA_NET_UNSPEC] = { .type = NLA_UNSPEC }, - [TIPC_NLA_NET_ID] = { .type = NLA_U32 } + [TIPC_NLA_NET_ID] = { .type = NLA_U32 }, + [TIPC_NLA_NET_ADDR] = { .type = NLA_U32 }, }; const struct nla_policy tipc_nl_link_policy[TIPC_NLA_LINK_MAX + 1] = { diff --git a/security/commoncap.c b/security/commoncap.c index 7b01431d1e19..1c1f64582bb5 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -449,6 +449,8 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, magic |= VFS_CAP_FLAGS_EFFECTIVE; memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); cap->magic_etc = cpu_to_le32(magic); + } else { + size = -ENOMEM; } } kfree(tmpbuf);