diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index f53ef1ac3122..4df6bd7d01ed 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2402,6 +2402,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted. 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 096d7e867b6c..151477d4d5e5 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 4 -SUBLEVEL = 129 +SUBLEVEL = 130 EXTRAVERSION = NAME = Blurry Fish Butt diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 2ee95ece0498..9bdaeb38a768 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -111,6 +111,7 @@ 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 @@ -705,6 +706,51 @@ config SECCOMP 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 "Power Management" @@ -754,6 +800,7 @@ 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 e8d4423e4f85..d924f9b6dc73 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -77,6 +77,16 @@ 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 d68e11e0df5e..e903b28e7358 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -53,4 +53,28 @@ do { \ ___p1; \ }) +/** + * 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; +} + #endif /* __ASM_BARRIER_H */ diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index 0aa6a7ed95a3..155fcc7bcba6 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -13,6 +13,24 @@ #define MAX_FACILITY_BIT (256*8) /* stfle_fac_list has 256 bytes */ +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 e9a983f40a24..7d9c5917da2b 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -136,7 +136,8 @@ struct kvm_s390_sie_block { __u16 ipa; /* 0x0056 */ __u32 ipb; /* 0x0058 */ __u32 scaoh; /* 0x005c */ - __u8 reserved60; /* 0x0060 */ +#define FPF_BPBC 0x20 + __u8 fpf; /* 0x0060 */ __u8 ecb; /* 0x0061 */ __u8 ecb2; /* 0x0062 */ #define ECB3_AES 0x04 diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h index afe1cfebf1a4..8520c23e419b 100644 --- a/arch/s390/include/asm/lowcore.h +++ b/arch/s390/include/asm/lowcore.h @@ -155,7 +155,9 @@ 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 @@ -170,7 +172,8 @@ 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 vector register 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 c61ed7890cef..f915a0f1b0fc 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -69,6 +69,7 @@ extern void s390_adjust_jiffies(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. @@ -315,6 +316,9 @@ extern void memcpy_absolute(void *, void *, size_t); memcpy_absolute(&(dest), &__tmp, sizeof(__tmp)); \ } +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 692b9247c019..b2504163c8fa 100644 --- a/arch/s390/include/asm/thread_info.h +++ b/arch/s390/include/asm/thread_info.h @@ -78,6 +78,8 @@ void arch_release_task_struct(struct task_struct *tsk); #define TIF_SECCOMP 5 /* secure computing */ #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ #define TIF_UPROBE 7 /* breakpointed or single-stepping */ +#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 */ #define TIF_RESTORE_SIGMASK 18 /* restore signal mask in do_signal() */ @@ -93,6 +95,8 @@ void arch_release_task_struct(struct task_struct *tsk); #define _TIF_SECCOMP _BITUL(TIF_SECCOMP) #define _TIF_SYSCALL_TRACEPOINT _BITUL(TIF_SYSCALL_TRACEPOINT) #define _TIF_UPROBE _BITUL(TIF_UPROBE) +#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 ef1a5fcc6c66..beb508a9e72c 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -151,6 +151,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_ARCH0 (1UL << 4) #define KVM_SYNC_PFAULT (1UL << 5) #define KVM_SYNC_VRS (1UL << 6) +#define KVM_SYNC_BPBC (1UL << 10) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -168,6 +169,8 @@ struct kvm_sync_regs { __u64 vrs[32][2]; /* vector registers */ __u8 reserved[512]; /* for future vector expansion */ __u32 fpc; /* only valid with vector registers */ + __u8 bpbc : 1; /* bp mode */ + __u8 reserved2 : 7; }; #define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1) diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index dc167a23b920..8ccfbf22ecbb 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -44,10 +44,13 @@ 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 sclp.o vdso.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 dumpstack.o -obj-y += entry.o reipl.o relocate_kernel.o +obj-y += entry.o reipl.o relocate_kernel.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) += s390_ksyms.o module.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_SCHED_BOOK) += 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 ee7b8e7ca4f8..8eccead675d4 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -279,6 +279,11 @@ 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 4612ed7ec2e5..c63730326215 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -104,6 +104,7 @@ _PIF_WORK = (_PIF_PER_TRAP) j 3f 1: LAST_BREAK %r14 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 @@ -162,8 +163,137 @@ _PIF_WORK = (_PIF_PER_TRAP) 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" +ENTRY(__bpon) + .globl __bpon + BPON + BR_R1USE_R14 + /* * Scheduler resume function, called by switch_to * gpr2 = (task_struct *) prev @@ -190,9 +320,9 @@ 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: @@ -204,9 +334,11 @@ 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 @@ -223,7 +355,11 @@ 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) 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 @@ -244,9 +380,15 @@ 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 @@ -267,6 +409,7 @@ ENTRY(system_call) stpt __LC_SYNC_ENTER_TIMER .Lsysc_stmg: stmg %r8,%r15,__LC_SAVE_AREA_SYNC + BPOFF lg %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO lghi %r14,_PIF_SYSCALL @@ -276,12 +419,15 @@ ENTRY(system_call) LAST_BREAK %r13 .Lsysc_vtime: UPDATE_VTIME %r10,%r13,__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 lg %r10,__TI_sysc_table(%r12) # address of system call table llgh %r8,__PT_INT_CODE+2(%r11) slag %r8,%r8,2 # shift and test for svc 0 @@ -299,7 +445,7 @@ 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: @@ -311,6 +457,7 @@ 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) @@ -438,7 +585,7 @@ 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 @@ -462,7 +609,7 @@ 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 /* @@ -471,6 +618,7 @@ 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_THREAD_INFO @@ -495,6 +643,7 @@ ENTRY(pgm_check_handler) j 3f 2: LAST_BREAK %r14 UPDATE_VTIME %r14,%r15,__LC_SYNC_ENTER_TIMER + BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP lg %r15,__LC_KERNEL_STACK lg %r14,__TI_task(%r12) aghi %r14,__TASK_thread # pointer to thread_struct @@ -504,6 +653,15 @@ ENTRY(pgm_check_handler) mvc __THREAD_trap_tdb(256,%r14),0(%r13) 3: 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 @@ -525,9 +683,9 @@ 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 ? @@ -560,6 +718,7 @@ 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 %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO @@ -567,6 +726,16 @@ ENTRY(io_int_handler) 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 @@ -601,9 +770,13 @@ 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: @@ -735,6 +908,7 @@ 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 %r10,__LC_LAST_BREAK lg %r12,__LC_THREAD_INFO @@ -742,6 +916,16 @@ ENTRY(ext_int_handler) 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 @@ -773,11 +957,12 @@ ENTRY(psw_idle) .insn rsy,0xeb0000000017,%r1,5,__SF_EMPTY+16(%r15) .Lpsw_idle_stcctm: #endif + 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: /* @@ -791,7 +976,7 @@ 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) .Lsave_fpu_regs_fpc_end: lg %r3,__THREAD_FPU_regs(%r2) @@ -821,7 +1006,8 @@ 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: /* @@ -838,7 +1024,7 @@ 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 @@ -867,7 +1053,8 @@ 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: @@ -877,6 +1064,7 @@ 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 @@ -908,6 +1096,16 @@ 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) @@ -933,6 +1131,7 @@ 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) @@ -1028,7 +1227,7 @@ 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: @@ -1053,11 +1252,12 @@ cleanup_critical: .quad .Lsie_done .Lcleanup_sie: + 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: @@ -1099,7 +1299,8 @@ cleanup_critical: srag %r9,%r9,23 jz 0f mvc __TI_last_break(8,%r12),16(%r11) -0: # set up saved register r11 +0: BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP + # set up saved register r11 lg %r15,__LC_KERNEL_STACK la %r9,STACK_FRAME_OVERHEAD(%r15) stg %r9,24(%r11) # r11 pt_regs pointer @@ -1114,7 +1315,7 @@ 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 @@ -1124,7 +1325,7 @@ cleanup_critical: .Lcleanup_sysc_tif: larl %r9,.Lsysc_tif - br %r14 + BR_R11USE_R14 .Lcleanup_sysc_restore: # check if stpt has been executed @@ -1141,14 +1342,14 @@ 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 @@ -1162,7 +1363,7 @@ 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 @@ -1214,17 +1415,17 @@ 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 @@ -1240,7 +1441,6 @@ cleanup_critical: .Lsie_critical_length: .quad .Lsie_done - .Lsie_gmap #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 e73979236659..837bb301023f 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -563,6 +563,7 @@ static struct kset *ipl_kset; static void __ipl_run(void *unused) { + __bpon(); diag308(DIAG308_IPL, 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 0c1a679314dd..9bd1933848b8 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 @@ -163,7 +166,11 @@ int module_frob_arch_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, me->arch.got_offset = me->core_size; me->core_size += me->arch.got_size; me->arch.plt_offset = me->core_size; - me->core_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_size += me->arch.plt_size; + } return 0; } @@ -317,9 +324,20 @@ static int apply_rela(Elf_Rela *rela, Elf_Addr base, Elf_Sym *symtab, unsigned int *ip; ip = me->module_core + 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->module_core + + 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; @@ -424,6 +442,45 @@ 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->module_core + 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); vfree(me->arch.syminfo); me->arch.syminfo = NULL; 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 7ce00e7a709a..ab236bd970bb 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -113,3 +114,20 @@ const struct seq_operations cpuinfo_op = { .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 d097d71685df..e7a43a30e3ff 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -63,6 +63,8 @@ #include #include #include +#include +#include #include "entry.h" /* @@ -333,7 +335,9 @@ static void __init setup_lowcore(void) lc->machine_flags = S390_lowcore.machine_flags; 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) lc->vector_save_area_addr = (unsigned long) &lc->vector_save_area; @@ -370,6 +374,7 @@ 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; @@ -841,6 +846,9 @@ 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(); os_info_init(); setup_ipl(); @@ -893,6 +901,10 @@ 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 9062df575afe..77f4f334a465 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -200,6 +200,7 @@ static int pcpu_alloc_lowcore(struct pcpu *pcpu, int cpu) lc->panic_stack = panic_stack + PANIC_FRAME_OFFSET; lc->cpu_nr = cpu; lc->spinlock_lockval = arch_spin_lockval(cpu); + lc->br_r1_trampoline = 0x07f1; /* br %r1 */ if (MACHINE_HAS_VX) lc->vector_save_area_addr = (unsigned long) &lc->vector_save_area; @@ -250,7 +251,9 @@ 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) @@ -299,6 +302,7 @@ 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" @@ -888,6 +892,7 @@ 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 66956c09d5bf..3d04dfdabc9f 100644 --- a/arch/s390/kernel/uprobes.c +++ b/arch/s390/kernel/uprobes.c @@ -147,6 +147,15 @@ 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 6c553f6e791a..a4ae08e416e6 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -78,6 +78,43 @@ 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 23e3f5d77a24..b011140e6b06 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -257,6 +257,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_VECTOR_REGISTERS: r = MACHINE_HAS_VX; break; + case KVM_CAP_S390_BPB: + r = test_facility(82); + break; default: r = 0; } @@ -1264,6 +1267,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_PFAULT; if (test_kvm_facility(vcpu->kvm, 129)) vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; + if (test_kvm_facility(vcpu->kvm, 82)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_BPBC; if (kvm_is_ucontrol(vcpu->kvm)) return __kvm_ucontrol_vcpu_init(vcpu); @@ -1327,6 +1332,7 @@ 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)) @@ -2145,6 +2151,11 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (vcpu->arch.pfault_token == KVM_S390_PFAULT_TOKEN_INVALID) kvm_clear_async_pf_completion_queue(vcpu); } + 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; + } kvm_run->kvm_dirty_regs = 0; } @@ -2162,6 +2173,7 @@ 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; } int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index eb02087650d2..c42d4a3d9494 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -408,7 +408,7 @@ static unsigned long calc_hpet_ref(u64 deltatsc, u64 hpet1, u64 hpet2) hpet2 -= hpet1; tmp = ((u64)hpet2 * hpet_readl(HPET_PERIOD)); do_div(tmp, 1000000); - do_div(deltatsc, tmp); + deltatsc = div64_u64(deltatsc, tmp); return (unsigned long) deltatsc; } diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index c206ccda899b..b5f245d2875c 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2358,7 +2358,7 @@ 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/input/misc/drv260x.c b/drivers/input/misc/drv260x.c index 930424e55439..251d64ca41ce 100644 --- a/drivers/input/misc/drv260x.c +++ b/drivers/input/misc/drv260x.c @@ -521,7 +521,7 @@ static int drv260x_probe(struct i2c_client *client, if (!haptics) return -ENOMEM; - haptics->rated_voltage = DRV260X_DEF_OD_CLAMP_VOLT; + haptics->overdrive_voltage = DRV260X_DEF_OD_CLAMP_VOLT; haptics->rated_voltage = DRV260X_DEF_RATED_VOLT; if (pdata) { diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c index 7ebccfa8072a..cb790b68920f 100644 --- a/drivers/message/fusion/mptsas.c +++ b/drivers/message/fusion/mptsas.c @@ -1994,6 +1994,7 @@ 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 278d12888cab..339118f3c718 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1614,8 +1614,7 @@ 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/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index b7b859c3a0c7..583d50f80b24 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -638,6 +638,10 @@ 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 9bca36e1fefd..e74709e4b5dd 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -247,6 +247,17 @@ 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) @@ -1039,14 +1050,11 @@ 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; @@ -1060,6 +1068,14 @@ 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; @@ -1074,7 +1090,7 @@ 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; } @@ -1181,7 +1197,7 @@ 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); @@ -1889,7 +1905,7 @@ 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; @@ -2544,6 +2560,14 @@ 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/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 6578127db847..f71abe50ea6f 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -461,6 +461,7 @@ static const struct driver_info wwan_info = { #define REALTEK_VENDOR_ID 0x0bda #define SAMSUNG_VENDOR_ID 0x04e8 #define LENOVO_VENDOR_ID 0x17ef +#define LINKSYS_VENDOR_ID 0x13b1 #define NVIDIA_VENDOR_ID 0x0955 #define HP_VENDOR_ID 0x03f0 @@ -650,6 +651,15 @@ static const struct usb_device_id products[] = { .driver_info = 0, }, +#if IS_ENABLED(CONFIG_USB_RTL8152) +/* Linksys USB3GIGV1 Ethernet Adapter */ +{ + USB_DEVICE_AND_INTERFACE_INFO(LINKSYS_VENDOR_ID, 0x0041, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = 0, +}, +#endif + /* Lenovo Thinkpad USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */ { USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0x7205, USB_CLASS_COMM, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 89950f5cea71..b2c1a435357f 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -506,6 +506,7 @@ enum rtl8152_flags { #define VENDOR_ID_REALTEK 0x0bda #define VENDOR_ID_SAMSUNG 0x04e8 #define VENDOR_ID_LENOVO 0x17ef +#define VENDOR_ID_LINKSYS 0x13b1 #define VENDOR_ID_NVIDIA 0x0955 #define MCU_TYPE_PLA 0x0100 @@ -4376,6 +4377,7 @@ static struct usb_device_id rtl8152_table[] = { {REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x7205)}, {REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f)}, + {REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)}, {REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff)}, {} }; diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 09e14ce85dd0..0c8efdff4843 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -5285,9 +5285,8 @@ 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/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 41382f89abe1..4435c7bbb625 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -1595,6 +1595,10 @@ bool ath9k_hw_check_alive(struct ath_hw *ah) int count = 50; u32 reg, last_val; + /* Check if chip failed to wake up */ + if (REG_READ(ah, AR_CFG) == 0xdeadbeef) + return false; + if (AR_SREV_9300(ah)) return !ath9k_hw_detect_mac_hang(ah); diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile index 6fa9364d1c07..835f1054976b 100644 --- a/drivers/s390/char/Makefile +++ b/drivers/s390/char/Makefile @@ -2,6 +2,8 @@ # S/390 character devices # +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 diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c index 1e16331891a9..f9d6a9f00640 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/drivers/staging/android/ion/ion_system_heap.c b/drivers/staging/android/ion/ion_system_heap.c index d4c3e5512dd5..b69dfc706440 100644 --- a/drivers/staging/android/ion/ion_system_heap.c +++ b/drivers/staging/android/ion/ion_system_heap.c @@ -27,7 +27,7 @@ #include "ion_priv.h" static gfp_t high_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN | - __GFP_NORETRY) & ~__GFP_DIRECT_RECLAIM; + __GFP_NORETRY) & ~__GFP_RECLAIM; static gfp_t low_order_gfp_flags = (GFP_HIGHUSER | __GFP_ZERO | __GFP_NOWARN); static const unsigned int orders[] = {8, 4, 0}; static const int num_orders = ARRAY_SIZE(orders); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 49a0d6b027c1..76dacd5307b9 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -673,6 +673,9 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, goto mknod_out; } + if (!S_ISCHR(mode) && !S_ISBLK(mode)) + goto mknod_out; + if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) goto mknod_out; @@ -681,10 +684,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); if (buf == NULL) { - kfree(full_path); rc = -ENOMEM; - free_xid(xid); - return rc; + goto mknod_out; } if (backup_cred(cifs_sb)) @@ -731,7 +732,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, umode_t mode, pdev->minor = cpu_to_le64(MINOR(device_number)); rc = tcon->ses->server->ops->sync_write(xid, &fid, &io_parms, &bytes_written, iov, 1); - } /* else if (S_ISFIFO) */ + } tcon->ses->server->ops->close(xid, tcon, &fid); d_drop(direntry); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 4759df4eb8ce..9398d1b70545 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -275,11 +275,11 @@ loop: goto loop; end_loop: - write_unlock(&journal->j_state_lock); del_timer_sync(&journal->j_commit_timer); journal->j_task = NULL; wake_up(&journal->j_wait_done_commit); jbd_debug(1, "Journal thread exiting.\n"); + write_unlock(&journal->j_state_lock); return 0; } diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 19db03dbbd00..dd676ba758ee 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -585,7 +585,7 @@ 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; @@ -596,6 +596,9 @@ static inline bool skb_vlan_tagged_multi(const struct sk_buff *skb) protocol != htons(ETH_P_8021AD))) 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; } @@ -613,7 +616,7 @@ 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/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/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 03f3618612aa..376d0ab5b9f2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -831,6 +831,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_GUEST_DEBUG_HW_WPS 120 #define KVM_CAP_SPLIT_IRQCHIP 121 #define KVM_CAP_IOEVENTFD_ANY_LENGTH 122 +#define KVM_CAP_S390_BPB 152 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/kernel/events/core.c b/kernel/events/core.c index 835ac4d9f349..6aeb0ef4fe70 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8133,9 +8133,9 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, * __u16 sample size limit. */ if (attr->sample_stack_user >= USHRT_MAX) - ret = -EINVAL; + return -EINVAL; else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64))) - ret = -EINVAL; + return -EINVAL; } if (attr->sample_type & PERF_SAMPLE_REGS_INTR) diff --git a/net/core/dev.c b/net/core/dev.c index dc63c37d5301..3bcbf931a910 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2706,7 +2706,7 @@ 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 33432e64804c..f60b93627876 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -54,7 +54,8 @@ do { \ static void neigh_timer_handler(unsigned long arg); static void __neigh_notify(struct neighbour *n, int type, int flags); static void neigh_update_notify(struct neighbour *neigh); -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; @@ -254,8 +255,7 @@ 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); @@ -645,9 +645,10 @@ 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++) { @@ -655,16 +656,23 @@ 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; } @@ -2280,12 +2288,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); 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 6abc5012200b..e26df2764e83 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/ipv4/tcp.c b/net/ipv4/tcp.c index 23d77ff1da59..82d2b55c953a 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2589,8 +2589,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: - /* Read the IP->Key mappings from userspace */ - err = tp->af_specific->md5_parse(sk, optval, optlen); + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + err = tp->af_specific->md5_parse(sk, 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 96115d1e0d90..ed018760502e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3869,11 +3869,8 @@ 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 99920fcea97c..2f6d8f57fdd4 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2711,6 +2711,7 @@ 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 }, @@ -2719,6 +2720,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, + [RTA_TABLE] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 67f2e72723b2..2764c4bd072c 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -606,6 +606,13 @@ 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 1e698768aca8..09f2f3471ad6 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -197,9 +197,19 @@ 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 8bc5a1bd2d45..d861b74ad068 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -951,6 +951,26 @@ out: 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 92ca3e106c2b..f165514a4db5 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -332,11 +332,11 @@ 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); @@ -351,8 +351,13 @@ 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 @@ -362,6 +367,8 @@ 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) @@ -2892,6 +2899,7 @@ 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); @@ -2901,6 +2909,7 @@ 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); @@ -3134,7 +3143,7 @@ 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); @@ -3570,6 +3579,7 @@ 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: @@ -3580,14 +3590,21 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv len = sizeof(req_u.req3); break; } - if (optlen < len) - return -EINVAL; - if (pkt_sk(sk)->has_vnet_hdr) - 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 (pkt_sk(sk)->has_vnet_hdr) { + 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: { @@ -3653,12 +3670,18 @@ 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: { @@ -3669,7 +3692,9 @@ 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: @@ -3681,7 +3706,9 @@ 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: @@ -3690,15 +3717,20 @@ 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: { @@ -3736,11 +3768,17 @@ 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: @@ -4116,7 +4154,6 @@ 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); /* Opening a Tx-ring is NOT supported in TPACKET_V3 */ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) { WARN(1, "Tx-ring is not supported.\n"); @@ -4252,7 +4289,6 @@ 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 d55bfc34d6b3..1309e2a7baad 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -109,10 +109,12 @@ 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; @@ -122,8 +124,6 @@ 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/sctp/ipv6.c b/net/sctp/ipv6.c index edb8514b4e00..1cd7b7e33fa3 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -519,46 +519,49 @@ 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) { @@ -843,8 +846,8 @@ 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); @@ -860,10 +863,7 @@ 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/tipc/net.c b/net/tipc/net.c index 77bf9113c7a7..2763bd369b79 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -44,7 +44,8 @@ static 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 }, }; /*