From 844f7eaaed9267ae17d33778efe65548cc940205 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Sun, 12 Sep 2021 14:22:34 +0200 Subject: include/uapi/linux/xfrm.h: Fix XFRM_MSG_MAPPING ABI breakage Commit 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") broke ABI by changing the value of the XFRM_MSG_MAPPING enum item, thus also evading the build-time check in security/selinux/nlmsgtab.c:selinux_nlmsg_lookup for presence of proper security permission checks in nlmsg_xfrm_perms. Fix it by placing XFRM_MSG_SETDEFAULT/XFRM_MSG_GETDEFAULT to the end of the enum, right before __XFRM_MSG_MAX, and updating the nlmsg_xfrm_perms accordingly. Fixes: 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") References: https://lore.kernel.org/netdev/20210901151402.GA2557@altlinux.org/ Signed-off-by: Eugene Syromiatnikov Acked-by: Antony Antony Acked-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index b96c1ea7166d..26f456b1f33e 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -213,13 +213,13 @@ enum { XFRM_MSG_GETSPDINFO, #define XFRM_MSG_GETSPDINFO XFRM_MSG_GETSPDINFO + XFRM_MSG_MAPPING, +#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING + XFRM_MSG_SETDEFAULT, #define XFRM_MSG_SETDEFAULT XFRM_MSG_SETDEFAULT XFRM_MSG_GETDEFAULT, #define XFRM_MSG_GETDEFAULT XFRM_MSG_GETDEFAULT - - XFRM_MSG_MAPPING, -#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING __XFRM_MSG_MAX }; #define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1) -- cgit v1.2.3 From 356ed64991c6847a0c4f2e8fa3b1133f7a14f1fc Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Tue, 14 Sep 2021 10:33:51 +0800 Subject: bpf: Handle return value of BPF_PROG_TYPE_STRUCT_OPS prog Currently if a function ptr in struct_ops has a return value, its caller will get a random return value from it, because the return value of related BPF_PROG_TYPE_STRUCT_OPS prog is just dropped. So adding a new flag BPF_TRAMP_F_RET_FENTRY_RET to tell bpf trampoline to save and return the return value of struct_ops prog if ret_size of the function ptr is greater than 0. Also restricting the flag to be used alone. Fixes: 85d33df357b6 ("bpf: Introduce BPF_MAP_TYPE_STRUCT_OPS") Signed-off-by: Hou Tao Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210914023351.3664499-1-houtao1@huawei.com --- arch/x86/net/bpf_jit_comp.c | 53 ++++++++++++++++++++++++++++++++++----------- include/linux/bpf.h | 3 ++- kernel/bpf/bpf_struct_ops.c | 7 ++++-- 3 files changed, 47 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 0fe6aacef3db..d24a512fd6f3 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1744,7 +1744,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args, } static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, - struct bpf_prog *p, int stack_size, bool mod_ret) + struct bpf_prog *p, int stack_size, bool save_ret) { u8 *prog = *pprog; u8 *jmp_insn; @@ -1777,11 +1777,15 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, if (emit_call(&prog, p->bpf_func, prog)) return -EINVAL; - /* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return + /* + * BPF_TRAMP_MODIFY_RETURN trampolines can modify the return * of the previous call which is then passed on the stack to * the next BPF program. + * + * BPF_TRAMP_FENTRY trampoline may need to return the return + * value of BPF_PROG_TYPE_STRUCT_OPS prog. */ - if (mod_ret) + if (save_ret) emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); /* replace 2 nops with JE insn, since jmp target is known */ @@ -1828,13 +1832,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) } static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, - struct bpf_tramp_progs *tp, int stack_size) + struct bpf_tramp_progs *tp, int stack_size, + bool save_ret) { int i; u8 *prog = *pprog; for (i = 0; i < tp->nr_progs; i++) { - if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false)) + if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, + save_ret)) return -EINVAL; } *pprog = prog; @@ -1877,6 +1883,23 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, return 0; } +static bool is_valid_bpf_tramp_flags(unsigned int flags) +{ + if ((flags & BPF_TRAMP_F_RESTORE_REGS) && + (flags & BPF_TRAMP_F_SKIP_FRAME)) + return false; + + /* + * BPF_TRAMP_F_RET_FENTRY_RET is only used by bpf_struct_ops, + * and it must be used alone. + */ + if ((flags & BPF_TRAMP_F_RET_FENTRY_RET) && + (flags & ~BPF_TRAMP_F_RET_FENTRY_RET)) + return false; + + return true; +} + /* Example: * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); * its 'struct btf_func_model' will be nr_args=2 @@ -1949,17 +1972,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN]; u8 **branches = NULL; u8 *prog; + bool save_ret; /* x86-64 supports up to 6 arguments. 7+ can be added in the future */ if (nr_args > 6) return -ENOTSUPP; - if ((flags & BPF_TRAMP_F_RESTORE_REGS) && - (flags & BPF_TRAMP_F_SKIP_FRAME)) + if (!is_valid_bpf_tramp_flags(flags)) return -EINVAL; - if (flags & BPF_TRAMP_F_CALL_ORIG) - stack_size += 8; /* room for return value of orig_call */ + /* room for return value of orig_call or fentry prog */ + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) + stack_size += 8; if (flags & BPF_TRAMP_F_IP_ARG) stack_size += 8; /* room for IP address argument */ @@ -2005,7 +2030,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fentry->nr_progs) - if (invoke_bpf(m, &prog, fentry, stack_size)) + if (invoke_bpf(m, &prog, fentry, stack_size, + flags & BPF_TRAMP_F_RET_FENTRY_RET)) return -EINVAL; if (fmod_ret->nr_progs) { @@ -2052,7 +2078,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i } if (fexit->nr_progs) - if (invoke_bpf(m, &prog, fexit, stack_size)) { + if (invoke_bpf(m, &prog, fexit, stack_size, false)) { ret = -EINVAL; goto cleanup; } @@ -2072,9 +2098,10 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - /* restore original return value back into RAX */ - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); } + /* restore return value of orig_call or fentry prog back into RAX */ + if (save_ret) + emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); EMIT1(0x5B); /* pop rbx */ EMIT1(0xC9); /* leave */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f4c16f19f83e..020a7d5bf470 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -578,11 +578,12 @@ struct btf_func_model { * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) - /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) +/* Return the return value of fentry prog. Only used by bpf_struct_ops. */ +#define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. Pick a number to fit into BPF_IMAGE_SIZE / 2 diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index d6731c32864e..9abcc33f02cf 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -368,6 +368,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, const struct btf_type *mtype, *ptype; struct bpf_prog *prog; u32 moff; + u32 flags; moff = btf_member_bit_offset(t, member) / 8; ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); @@ -431,10 +432,12 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; + flags = st_ops->func_models[i].ret_size > 0 ? + BPF_TRAMP_F_RET_FENTRY_RET : 0; err = arch_prepare_bpf_trampoline(NULL, image, st_map->image + PAGE_SIZE, - &st_ops->func_models[i], 0, - tprogs, NULL); + &st_ops->func_models[i], + flags, tprogs, NULL); if (err < 0) goto reset_unlock; -- cgit v1.2.3 From f8d858e607b2a36808ac6d4218f5f5203d7a7d63 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 14 Sep 2021 16:46:33 +0200 Subject: xfrm: make user policy API complete >From a userland POV, this API was based on some magic values: - dirmask and action were bitfields but meaning of bits (XFRM_POL_DEFAULT_*) are not exported; - action is confusing, if a bit is set, does it mean drop or accept? Let's try to simplify this uapi by using explicit field and macros. Fixes: 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") Signed-off-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 9 ++++++--- net/xfrm/xfrm_user.c | 36 +++++++++++++++++++----------------- 2 files changed, 25 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 26f456b1f33e..eda0426ec4c2 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -514,9 +514,12 @@ struct xfrm_user_offload { #define XFRM_OFFLOAD_INBOUND 2 struct xfrm_userpolicy_default { -#define XFRM_USERPOLICY_DIRMASK_MAX (sizeof(__u8) * 8) - __u8 dirmask; - __u8 action; +#define XFRM_USERPOLICY_UNSPEC 0 +#define XFRM_USERPOLICY_BLOCK 1 +#define XFRM_USERPOLICY_ACCEPT 2 + __u8 in; + __u8 fwd; + __u8 out; }; #ifndef __KERNEL__ diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4719a6d54aa6..90c88390f1fe 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1966,16 +1966,21 @@ static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct xfrm_userpolicy_default *up = nlmsg_data(nlh); - u8 dirmask; - u8 old_default = net->xfrm.policy_default; - if (up->dirmask >= XFRM_USERPOLICY_DIRMASK_MAX) - return -EINVAL; + if (up->in == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_IN; + else if (up->in == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_IN; - dirmask = (1 << up->dirmask) & XFRM_POL_DEFAULT_MASK; + if (up->fwd == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_FWD; + else if (up->fwd == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_FWD; - net->xfrm.policy_default = (old_default & (0xff ^ dirmask)) - | (up->action << up->dirmask); + if (up->out == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_OUT; + else if (up->out == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_OUT; rt_genid_bump_all(net); @@ -1988,13 +1993,11 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, struct sk_buff *r_skb; struct nlmsghdr *r_nlh; struct net *net = sock_net(skb->sk); - struct xfrm_userpolicy_default *r_up, *up; + struct xfrm_userpolicy_default *r_up; int len = NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_default)); u32 portid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; - up = nlmsg_data(nlh); - r_skb = nlmsg_new(len, GFP_ATOMIC); if (!r_skb) return -ENOMEM; @@ -2005,15 +2008,14 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, return -EMSGSIZE; } - if (up->dirmask >= XFRM_USERPOLICY_DIRMASK_MAX) { - kfree_skb(r_skb); - return -EINVAL; - } - r_up = nlmsg_data(r_nlh); - r_up->action = ((net->xfrm.policy_default & (1 << up->dirmask)) >> up->dirmask); - r_up->dirmask = up->dirmask; + r_up->in = net->xfrm.policy_default & XFRM_POL_DEFAULT_IN ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + r_up->fwd = net->xfrm.policy_default & XFRM_POL_DEFAULT_FWD ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + r_up->out = net->xfrm.policy_default & XFRM_POL_DEFAULT_OUT ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; nlmsg_end(r_skb, r_nlh); return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid); -- cgit v1.2.3 From e840f42a49925707fca90e6c7a4095118fdb8c4d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 19 Sep 2021 14:09:49 +0100 Subject: KVM: arm64: Fix PMU probe ordering Russell reported that since 5.13, KVM's probing of the PMU has started to fail on his HW. As it turns out, there is an implicit ordering dependency between the architectural PMU probing code and and KVM's own probing. If, due to probe ordering reasons, KVM probes before the PMU driver, it will fail to detect the PMU and prevent it from being advertised to guests as well as the VMM. Obviously, this is one probing too many, and we should be able to deal with any ordering. Add a callback from the PMU code into KVM to advertise the registration of a host CPU PMU, allowing for any probing order. Fixes: 5421db1be3b1 ("KVM: arm64: Divorce the perf code from oprofile helpers") Reported-by: "Russell King (Oracle)" Tested-by: Russell King (Oracle) Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/YUYRKVflRtUytzy5@shell.armlinux.org.uk Cc: stable@vger.kernel.org --- arch/arm64/kvm/perf.c | 3 --- arch/arm64/kvm/pmu-emul.c | 9 ++++++++- drivers/perf/arm_pmu.c | 2 ++ include/kvm/arm_pmu.h | 3 --- include/linux/perf/arm_pmu.h | 6 ++++++ 5 files changed, 16 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c index f9bb3b14130e..c84fe24b2ea1 100644 --- a/arch/arm64/kvm/perf.c +++ b/arch/arm64/kvm/perf.c @@ -50,9 +50,6 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { int kvm_perf_init(void) { - if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled()) - static_branch_enable(&kvm_arm_pmu_available); - return perf_register_guest_info_callbacks(&kvm_guest_cbs); } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index f5065f23b413..2af3c37445e0 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -740,7 +740,14 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data, kvm_pmu_create_perf_event(vcpu, select_idx); } -int kvm_pmu_probe_pmuver(void) +void kvm_host_pmu_init(struct arm_pmu *pmu) +{ + if (pmu->pmuver != 0 && pmu->pmuver != ID_AA64DFR0_PMUVER_IMP_DEF && + !kvm_arm_support_pmu_v3() && !is_protected_kvm_enabled()) + static_branch_enable(&kvm_arm_pmu_available); +} + +static int kvm_pmu_probe_pmuver(void) { struct perf_event_attr attr = { }; struct perf_event *event; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 3cbc3baf087f..295cc7952d0e 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -952,6 +952,8 @@ int armpmu_register(struct arm_pmu *pmu) pmu->name, pmu->num_events, has_nmi ? ", using NMIs" : ""); + kvm_host_pmu_init(pmu); + return 0; out_destroy: diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h index 864b9997efb2..90f21898aad8 100644 --- a/include/kvm/arm_pmu.h +++ b/include/kvm/arm_pmu.h @@ -61,7 +61,6 @@ int kvm_arm_pmu_v3_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu); -int kvm_pmu_probe_pmuver(void); #else struct kvm_pmu { }; @@ -118,8 +117,6 @@ static inline u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) return 0; } -static inline int kvm_pmu_probe_pmuver(void) { return 0xf; } - #endif #endif diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 505480217cf1..2512e2f9cd4e 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -163,6 +163,12 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn); static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; } #endif +#ifdef CONFIG_KVM +void kvm_host_pmu_init(struct arm_pmu *pmu); +#else +#define kvm_host_pmu_init(x) do { } while(0) +#endif + /* Internal functions only for core arm_pmu code */ struct arm_pmu *armpmu_alloc(void); struct arm_pmu *armpmu_alloc_atomic(void); -- cgit v1.2.3 From c86a2d9058c5a4a05d20ef89e699b7a6b2c89da6 Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Fri, 17 Sep 2021 00:27:05 +0200 Subject: cpumask: Omit terminating null byte in cpumap_print_{list,bitmask}_to_buf The changes in the patch series [1] introduced a terminating null byte when reading from cpulist or cpumap sysfs files, for example: $ xxd /sys/devices/system/node/node0/cpulist 00000000: 302d 310a 00 0-1.. Before this change, the output looked as follows: $ xxd /sys/devices/system/node/node0/cpulist 00000000: 302d 310a 0-1. Fix this regression by excluding the terminating null byte from the returned length in cpumap_print_list_to_buf and cpumap_print_bitmask_to_buf. [1] https://lore.kernel.org/all/20210806110251.560-1-song.bao.hua@hisilicon.com/ Fixes: 1fae562983ca ("cpumask: introduce cpumap_print_list/bitmask_to_buf to support large bitmask and list") Acked-by: Barry Song Acked-by: Yury Norov Signed-off-by: Tobias Klauser Link: https://lore.kernel.org/r/20210916222705.13554-1-tklauser@distanz.ch Signed-off-by: Greg Kroah-Hartman --- include/linux/cpumask.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 5d4d07a9e1ed..1e7399fc69c0 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -996,14 +996,15 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) * cpumask; Typically used by bin_attribute to export cpumask bitmask * ABI. * - * Returns the length of how many bytes have been copied. + * Returns the length of how many bytes have been copied, excluding + * terminating '\0'. */ static inline ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } /** @@ -1018,7 +1019,7 @@ cpumap_print_list_to_buf(char *buf, const struct cpumask *mask, loff_t off, size_t count) { return bitmap_print_list_to_buf(buf, cpumask_bits(mask), - nr_cpu_ids, off, count); + nr_cpu_ids, off, count) - 1; } #if NR_CPUS <= BITS_PER_LONG -- cgit v1.2.3 From 4eeef2424153e79910d65248b5e1abf137d050e9 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Fri, 10 Sep 2021 11:32:19 -0700 Subject: KVM: x86: Query vcpu->vcpu_idx directly and drop its accessor Read vcpu->vcpu_idx directly instead of bouncing through the one-line wrapper, kvm_vcpu_get_idx(), and drop the wrapper. The wrapper is a remnant of the original implementation and serves no purpose; remove it before it gains more users. Back when kvm_vcpu_get_idx() was added by commit 497d72d80a78 ("KVM: Add kvm_vcpu_get_idx to get vcpu index in kvm->vcpus"), the implementation was more than just a simple wrapper as vcpu->vcpu_idx did not exist and retrieving the index meant walking over the vCPU array to find the given vCPU. When vcpu_idx was introduced by commit 8750e72a79dd ("KVM: remember position in kvm->vcpus array"), the helper was left behind, likely to avoid extra thrash (but even then there were only two users, the original arm usage having been removed at some point in the past). No functional change intended. Suggested-by: Vitaly Kuznetsov Signed-off-by: Sean Christopherson Reviewed-by: Maxim Levitsky Reviewed-by: Vitaly Kuznetsov Message-Id: <20210910183220.2397812-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/s390/kvm/interrupt.c | 4 ++-- arch/s390/kvm/kvm-s390.c | 2 +- arch/s390/kvm/kvm-s390.h | 2 +- arch/x86/kvm/hyperv.c | 7 +++---- arch/x86/kvm/hyperv.h | 2 +- include/linux/kvm_host.h | 5 ----- 6 files changed, 8 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 16256e17a544..10722455fd02 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -419,13 +419,13 @@ static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu) static void __set_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_set_cpuflags(vcpu, CPUSTAT_WAIT); - set_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + set_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __unset_cpu_idle(struct kvm_vcpu *vcpu) { kvm_s390_clear_cpuflags(vcpu, CPUSTAT_WAIT); - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static void __reset_intercept_indicators(struct kvm_vcpu *vcpu) diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 752a0ffab9bf..6a6dd5e1daf6 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -4066,7 +4066,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) kvm_s390_patch_guest_per_regs(vcpu); } - clear_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.gisa_int.kicked_mask); + clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask); vcpu->arch.sie_block->icptcode = 0; cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index ecd741ee3276..52bc8fbaa60a 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -79,7 +79,7 @@ static inline int is_vcpu_stopped(struct kvm_vcpu *vcpu) static inline int is_vcpu_idle(struct kvm_vcpu *vcpu) { - return test_bit(kvm_vcpu_get_idx(vcpu), vcpu->kvm->arch.idle_mask); + return test_bit(vcpu->vcpu_idx, vcpu->kvm->arch.idle_mask); } static inline int kvm_is_ucontrol(struct kvm *kvm) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 232a86a6faaf..d5124b520f76 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -939,7 +939,7 @@ static int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) stimer_init(&hv_vcpu->stimer[i], i); - hv_vcpu->vp_index = kvm_vcpu_get_idx(vcpu); + hv_vcpu->vp_index = vcpu->vcpu_idx; return 0; } @@ -1444,7 +1444,6 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) switch (msr) { case HV_X64_MSR_VP_INDEX: { struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); - int vcpu_idx = kvm_vcpu_get_idx(vcpu); u32 new_vp_index = (u32)data; if (!host || new_vp_index >= KVM_MAX_VCPUS) @@ -1459,9 +1458,9 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) * VP index is changing, adjust num_mismatched_vp_indexes if * it now matches or no longer matches vcpu_idx. */ - if (hv_vcpu->vp_index == vcpu_idx) + if (hv_vcpu->vp_index == vcpu->vcpu_idx) atomic_inc(&hv->num_mismatched_vp_indexes); - else if (new_vp_index == vcpu_idx) + else if (new_vp_index == vcpu->vcpu_idx) atomic_dec(&hv->num_mismatched_vp_indexes); hv_vcpu->vp_index = new_vp_index; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 730da8537d05..ed1c4e546d04 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -83,7 +83,7 @@ static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - return hv_vcpu ? hv_vcpu->vp_index : kvm_vcpu_get_idx(vcpu); + return hv_vcpu ? hv_vcpu->vp_index : vcpu->vcpu_idx; } int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 041ca7f15ea4..000ea73dd324 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -721,11 +721,6 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id) return NULL; } -static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu) -{ - return vcpu->vcpu_idx; -} - #define kvm_for_each_memslot(memslot, slots) \ for (memslot = &slots->memslots[0]; \ memslot < slots->memslots + slots->used_slots; memslot++) \ -- cgit v1.2.3 From 09d23174402da0f10e98da2c61bb5ac8e7d79fdd Mon Sep 17 00:00:00 2001 From: Jaroslav Kysela Date: Mon, 20 Sep 2021 19:18:50 +0200 Subject: ALSA: rawmidi: introduce SNDRV_RAWMIDI_IOCTL_USER_PVERSION The new framing mode causes the user space regression, because the alsa-lib code does not initialize the reserved space in the params structure when the device is opened. This change adds SNDRV_RAWMIDI_IOCTL_USER_PVERSION like we do for the PCM interface for the protocol acknowledgment. Cc: David Henningsson Cc: Fixes: 08fdced60ca0 ("ALSA: rawmidi: Add framing mode") BugLink: https://github.com/alsa-project/alsa-lib/issues/178 Signed-off-by: Jaroslav Kysela Link: https://lore.kernel.org/r/20210920171850.154186-1-perex@perex.cz Signed-off-by: Takashi Iwai --- include/sound/rawmidi.h | 1 + include/uapi/sound/asound.h | 1 + sound/core/rawmidi.c | 9 +++++++++ 3 files changed, 11 insertions(+) (limited to 'include') diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index 989e1517332d..7a08ed2acd60 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -98,6 +98,7 @@ struct snd_rawmidi_file { struct snd_rawmidi *rmidi; struct snd_rawmidi_substream *input; struct snd_rawmidi_substream *output; + unsigned int user_pversion; /* supported protocol version */ }; struct snd_rawmidi_str { diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index 1d84ec9db93b..5859ca0a1439 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -784,6 +784,7 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) +#define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) #define SNDRV_RAWMIDI_IOCTL_PARAMS _IOWR('W', 0x10, struct snd_rawmidi_params) #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 6c0a4a67ad2e..6f30231bdb88 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -873,12 +873,21 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long return -EINVAL; } } + case SNDRV_RAWMIDI_IOCTL_USER_PVERSION: + if (get_user(rfile->user_pversion, (unsigned int __user *)arg)) + return -EFAULT; + return 0; + case SNDRV_RAWMIDI_IOCTL_PARAMS: { struct snd_rawmidi_params params; if (copy_from_user(¶ms, argp, sizeof(struct snd_rawmidi_params))) return -EFAULT; + if (rfile->user_pversion < SNDRV_PROTOCOL_VERSION(2, 0, 2)) { + params.mode = 0; + memset(params.reserved, 0, sizeof(params.reserved)); + } switch (params.stream) { case SNDRV_RAWMIDI_STREAM_OUTPUT: if (rfile->output == NULL) -- cgit v1.2.3 From 6bc6db000295332bae2c1e8815d7450b72923d23 Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sat, 18 Sep 2021 08:56:29 +0800 Subject: KVM: Remove tlbs_dirty There is no user of tlbs_dirty. Signed-off-by: Lai Jiangshan Signed-off-by: Paolo Bonzini Message-Id: <20210918005636.3675-4-jiangshanlai@gmail.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 - virt/kvm/kvm_main.c | 10 ++-------- 2 files changed, 2 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 000ea73dd324..0f18df7fe874 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -608,7 +608,6 @@ struct kvm { unsigned long mmu_notifier_range_start; unsigned long mmu_notifier_range_end; #endif - long tlbs_dirty; struct list_head devices; u64 manual_dirty_log_protect; struct dentry *debugfs_dentry; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e95e7a9e4d53..7851f3a1b5f7 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -326,13 +326,8 @@ EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) { - /* - * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in - * kvm_make_all_cpus_request. - */ - long dirty_count = smp_load_acquire(&kvm->tlbs_dirty); - ++kvm->stat.generic.remote_tlb_flush_requests; + /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. @@ -347,7 +342,6 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) if (!kvm_arch_flush_remote_tlb(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.generic.remote_tlb_flush; - cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif @@ -552,7 +546,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, } } - if (range->flush_on_ret && (ret || kvm->tlbs_dirty)) + if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); if (locked) -- cgit v1.2.3 From 5501765a02a6c324f78581e6bb8209d054fe13ae Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 15 Sep 2021 10:09:38 -0700 Subject: driver core: fw_devlink: Add support for FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD If a parent device is also a supplier to a child device, fw_devlink=on by design delays the probe() of the child device until the probe() of the parent finishes successfully. However, some drivers of such parent devices (where parent is also a supplier) expect the child device to finish probing successfully as soon as they are added using device_add() and before the probe() of the parent device has completed successfully. One example of such a case is discussed in the link mentioned below. Add a flag to make fw_devlink=on not enforce these supplier-consumer relationships, so these drivers can continue working. Link: https://lore.kernel.org/netdev/CAGETcx_uj0V4DChME-gy5HGKTYnxLBX=TH2rag29f_p=UcG+Tg@mail.gmail.com/ Fixes: ea718c699055 ("Revert "Revert "driver core: Set fw_devlink=on by default""") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20210915170940.617415-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman --- drivers/base/core.c | 19 +++++++++++++++++++ include/linux/fwnode.h | 11 ++++++++--- 2 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/base/core.c b/drivers/base/core.c index 316df6027093..21d4cb5d3767 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1722,6 +1722,25 @@ static int fw_devlink_create_devlink(struct device *con, struct device *sup_dev; int ret = 0; + /* + * In some cases, a device P might also be a supplier to its child node + * C. However, this would defer the probe of C until the probe of P + * completes successfully. This is perfectly fine in the device driver + * model. device_add() doesn't guarantee probe completion of the device + * by the time it returns. + * + * However, there are a few drivers that assume C will finish probing + * as soon as it's added and before P finishes probing. So, we provide + * a flag to let fw_devlink know not to delay the probe of C until the + * probe of P completes successfully. + * + * When such a flag is set, we can't create device links where P is the + * supplier of C as that would delay the probe of C. + */ + if (sup_handle->flags & FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD && + fwnode_is_ancestor_of(sup_handle, con->fwnode)) + return -EINVAL; + sup_dev = get_dev_from_fwnode(sup_handle); if (sup_dev) { /* diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h index 59828516ebaf..9f4ad719bfe3 100644 --- a/include/linux/fwnode.h +++ b/include/linux/fwnode.h @@ -22,10 +22,15 @@ struct device; * LINKS_ADDED: The fwnode has already be parsed to add fwnode links. * NOT_DEVICE: The fwnode will never be populated as a struct device. * INITIALIZED: The hardware corresponding to fwnode has been initialized. + * NEEDS_CHILD_BOUND_ON_ADD: For this fwnode/device to probe successfully, its + * driver needs its child devices to be bound with + * their respective drivers as soon as they are + * added. */ -#define FWNODE_FLAG_LINKS_ADDED BIT(0) -#define FWNODE_FLAG_NOT_DEVICE BIT(1) -#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_LINKS_ADDED BIT(0) +#define FWNODE_FLAG_NOT_DEVICE BIT(1) +#define FWNODE_FLAG_INITIALIZED BIT(2) +#define FWNODE_FLAG_NEEDS_CHILD_BOUND_ON_ADD BIT(3) struct fwnode_handle { struct fwnode_handle *secondary; -- cgit v1.2.3 From 597aa16c782496bf74c5dc3b45ff472ade6cee64 Mon Sep 17 00:00:00 2001 From: Xiao Liang Date: Thu, 23 Sep 2021 23:03:19 +0800 Subject: net: ipv4: Fix rtnexthop len when RTA_FLOW is present Multipath RTA_FLOW is embedded in nexthop. Dump it in fib_add_nexthop() to get the length of rtnexthop correct. Fixes: b0f60193632e ("ipv4: Refactor nexthop attributes in fib_dump_info") Signed-off-by: Xiao Liang Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/net/ip_fib.h | 2 +- include/net/nexthop.h | 2 +- net/ipv4/fib_semantics.c | 16 +++++++++------- net/ipv6/route.c | 5 +++-- 4 files changed, 14 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 21c5386d4a6d..ab5348e57db1 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -597,5 +597,5 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, - int nh_weight, u8 rt_family); + int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 10e1777877e6..28085b995ddc 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -325,7 +325,7 @@ int nexthop_mpath_fill_node(struct sk_buff *skb, struct nexthop *nh, struct fib_nh_common *nhc = &nhi->fib_nhc; int weight = nhg->nh_entries[i].weight; - if (fib_add_nexthop(skb, nhc, weight, rt_family) < 0) + if (fib_add_nexthop(skb, nhc, weight, rt_family, 0) < 0) return -EMSGSIZE; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b42c429cebbe..3364cb9c67e0 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1661,7 +1661,7 @@ EXPORT_SYMBOL_GPL(fib_nexthop_info); #if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6) int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, - int nh_weight, u8 rt_family) + int nh_weight, u8 rt_family, u32 nh_tclassid) { const struct net_device *dev = nhc->nhc_dev; struct rtnexthop *rtnh; @@ -1679,6 +1679,9 @@ int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, rtnh->rtnh_flags = flags; + if (nh_tclassid && nla_put_u32(skb, RTA_FLOW, nh_tclassid)) + goto nla_put_failure; + /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *)rtnh; @@ -1706,14 +1709,13 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) } for_nexthops(fi) { - if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, - AF_INET) < 0) - goto nla_put_failure; + u32 nh_tclassid = 0; #ifdef CONFIG_IP_ROUTE_CLASSID - if (nh->nh_tclassid && - nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) - goto nla_put_failure; + nh_tclassid = nh->nh_tclassid; #endif + if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, + AF_INET, nh_tclassid) < 0) + goto nla_put_failure; } endfor_nexthops(fi); mp_end: diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dbc224023977..9b9ef09382ab 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5681,14 +5681,15 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, - rt->fib6_nh->fib_nh_weight, AF_INET6) < 0) + rt->fib6_nh->fib_nh_weight, AF_INET6, + 0) < 0) goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, - AF_INET6) < 0) + AF_INET6, 0) < 0) goto nla_put_failure; } -- cgit v1.2.3 From b193e15ac69d56f35e1d8e2b5d16cbd47764d053 Mon Sep 17 00:00:00 2001 From: 王贇 Date: Fri, 24 Sep 2021 10:35:58 +0800 Subject: net: prevent user from passing illegal stab size We observed below report when playing with netlink sock: UBSAN: shift-out-of-bounds in net/sched/sch_api.c:580:10 shift exponent 249 is too large for 32-bit type CPU: 0 PID: 685 Comm: a.out Not tainted Call Trace: dump_stack_lvl+0x8d/0xcf ubsan_epilogue+0xa/0x4e __ubsan_handle_shift_out_of_bounds+0x161/0x182 __qdisc_calculate_pkt_len+0xf0/0x190 __dev_queue_xmit+0x2ed/0x15b0 it seems like kernel won't check the stab log value passing from user, and will use the insane value later to calculate pkt_len. This patch just add a check on the size/cell_log to avoid insane calculation. Reported-by: Abaci Signed-off-by: Michael Wang Signed-off-by: David S. Miller --- include/net/pkt_sched.h | 1 + net/sched/sch_api.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 6d7b12cba015..bf79f3a890af 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -11,6 +11,7 @@ #include #define DEFAULT_TX_QUEUE_LEN 1000 +#define STAB_SIZE_LOG_MAX 30 struct qdisc_walker { int stop; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 5e90e9b160e3..12f39a2dffd4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -513,6 +513,12 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, return stab; } + if (s->size_log > STAB_SIZE_LOG_MAX || + s->cell_log > STAB_SIZE_LOG_MAX) { + NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); + return ERR_PTR(-EINVAL); + } + stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); -- cgit v1.2.3 From 33092aca857bf35a8e9cac0e8340c685a4796e90 Mon Sep 17 00:00:00 2001 From: Alexander Wetzel Date: Fri, 24 Sep 2021 22:05:14 +0200 Subject: mac80211: Fix Ptk0 rekey documentation @IEEE80211_KEY_FLAG_GENERATE_IV setting is irrelevant for RX. Move the requirement to the correct section in the PTK0 rekey documentation. Signed-off-by: Alexander Wetzel Link: https://lore.kernel.org/r/20210924200514.7936-1-alexander@wetzel-home.de Signed-off-by: Johannes Berg --- include/net/mac80211.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/mac80211.h b/include/net/mac80211.h index af0fc13cea34..618d1f427cb2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2818,13 +2818,13 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag * when they are able to replace in-use PTK keys according to the following * requirements: - * 1) They do not hand over frames decrypted with the old key to - mac80211 once the call to set_key() with command %DISABLE_KEY has been - completed when also setting @IEEE80211_KEY_FLAG_GENERATE_IV for any key, + * 1) They do not hand over frames decrypted with the old key to mac80211 + once the call to set_key() with command %DISABLE_KEY has been completed, 2) either drop or continue to use the old key for any outgoing frames queued at the time of the key deletion (including re-transmits), 3) never send out a frame queued prior to the set_key() %SET_KEY command - encrypted with the new key and + encrypted with the new key when also needing + @IEEE80211_KEY_FLAG_GENERATE_IV and 4) never send out a frame unencrypted when it should be encrypted. Mac80211 will not queue any new frames for a deleted key to the driver. */ -- cgit v1.2.3 From 339031bafe6b281cf2dcb8364217288b9fdab555 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 23 Sep 2021 16:44:34 +0200 Subject: netfilter: conntrack: fix boot failure with nf_conntrack.enable_hooks=1 This is a revert of 7b1957b049 ("netfilter: nf_defrag_ipv4: use net_generic infra") and a partial revert of 8b0adbe3e3 ("netfilter: nf_defrag_ipv6: use net_generic infra"). If conntrack is builtin and kernel is booted with: nf_conntrack.enable_hooks=1 .... kernel will fail to boot due to a NULL deref in nf_defrag_ipv4_enable(): Its called before the ipv4 defrag initcall is made, so net_generic() returns NULL. To resolve this, move the user refcount back to struct net so calls to those functions are possible even before their initcalls have run. Fixes: 7b1957b04956 ("netfilter: nf_defrag_ipv4: use net_generic infra") Fixes: 8b0adbe3e38d ("netfilter: nf_defrag_ipv6: use net_generic infra"). Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/ipv6/nf_defrag_ipv6.h | 1 - include/net/netns/netfilter.h | 6 ++++++ net/ipv4/netfilter/nf_defrag_ipv4.c | 30 +++++++++-------------------- net/ipv6/netfilter/nf_conntrack_reasm.c | 2 +- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 25 +++++++++--------------- 5 files changed, 25 insertions(+), 39 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h index 0fd8a4159662..ceadf8ba25a4 100644 --- a/include/net/netfilter/ipv6/nf_defrag_ipv6.h +++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h @@ -17,7 +17,6 @@ struct inet_frags_ctl; struct nft_ct_frag6_pernet { struct ctl_table_header *nf_frag_frags_hdr; struct fqdir *fqdir; - unsigned int users; }; #endif /* _NF_DEFRAG_IPV6_H */ diff --git a/include/net/netns/netfilter.h b/include/net/netns/netfilter.h index 986a2a9cfdfa..b593f95e9991 100644 --- a/include/net/netns/netfilter.h +++ b/include/net/netns/netfilter.h @@ -27,5 +27,11 @@ struct netns_nf { #if IS_ENABLED(CONFIG_DECNET) struct nf_hook_entries __rcu *hooks_decnet[NF_DN_NUMHOOKS]; #endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) + unsigned int defrag_ipv4_users; +#endif +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) + unsigned int defrag_ipv6_users; +#endif }; #endif diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 613432a36f0a..e61ea428ea18 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -20,13 +20,8 @@ #endif #include -static unsigned int defrag4_pernet_id __read_mostly; static DEFINE_MUTEX(defrag4_mutex); -struct defrag4_pernet { - unsigned int users; -}; - static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb, u_int32_t user) { @@ -111,19 +106,15 @@ static const struct nf_hook_ops ipv4_defrag_ops[] = { static void __net_exit defrag4_net_exit(struct net *net) { - struct defrag4_pernet *nf_defrag = net_generic(net, defrag4_pernet_id); - - if (nf_defrag->users) { + if (net->nf.defrag_ipv4_users) { nf_unregister_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); - nf_defrag->users = 0; + net->nf.defrag_ipv4_users = 0; } } static struct pernet_operations defrag4_net_ops = { .exit = defrag4_net_exit, - .id = &defrag4_pernet_id, - .size = sizeof(struct defrag4_pernet), }; static int __init nf_defrag_init(void) @@ -138,24 +129,23 @@ static void __exit nf_defrag_fini(void) int nf_defrag_ipv4_enable(struct net *net) { - struct defrag4_pernet *nf_defrag = net_generic(net, defrag4_pernet_id); int err = 0; mutex_lock(&defrag4_mutex); - if (nf_defrag->users == UINT_MAX) { + if (net->nf.defrag_ipv4_users == UINT_MAX) { err = -EOVERFLOW; goto out_unlock; } - if (nf_defrag->users) { - nf_defrag->users++; + if (net->nf.defrag_ipv4_users) { + net->nf.defrag_ipv4_users++; goto out_unlock; } err = nf_register_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); if (err == 0) - nf_defrag->users = 1; + net->nf.defrag_ipv4_users = 1; out_unlock: mutex_unlock(&defrag4_mutex); @@ -165,12 +155,10 @@ EXPORT_SYMBOL_GPL(nf_defrag_ipv4_enable); void nf_defrag_ipv4_disable(struct net *net) { - struct defrag4_pernet *nf_defrag = net_generic(net, defrag4_pernet_id); - mutex_lock(&defrag4_mutex); - if (nf_defrag->users) { - nf_defrag->users--; - if (nf_defrag->users == 0) + if (net->nf.defrag_ipv4_users) { + net->nf.defrag_ipv4_users--; + if (net->nf.defrag_ipv4_users == 0) nf_unregister_net_hooks(net, ipv4_defrag_ops, ARRAY_SIZE(ipv4_defrag_ops)); } diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index a0108415275f..5c47be29b9ee 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -33,7 +33,7 @@ static const char nf_frags_cache_name[] = "nf-frags"; -unsigned int nf_frag_pernet_id __read_mostly; +static unsigned int nf_frag_pernet_id __read_mostly; static struct inet_frags nf_frags; static struct nft_ct_frag6_pernet *nf_frag_pernet(struct net *net) diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index e8a59d8bf2ad..cb4eb1d2c620 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -25,8 +25,6 @@ #include #include -extern unsigned int nf_frag_pernet_id; - static DEFINE_MUTEX(defrag6_mutex); static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, @@ -91,12 +89,10 @@ static const struct nf_hook_ops ipv6_defrag_ops[] = { static void __net_exit defrag6_net_exit(struct net *net) { - struct nft_ct_frag6_pernet *nf_frag = net_generic(net, nf_frag_pernet_id); - - if (nf_frag->users) { + if (net->nf.defrag_ipv6_users) { nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); - nf_frag->users = 0; + net->nf.defrag_ipv6_users = 0; } } @@ -134,24 +130,23 @@ static void __exit nf_defrag_fini(void) int nf_defrag_ipv6_enable(struct net *net) { - struct nft_ct_frag6_pernet *nf_frag = net_generic(net, nf_frag_pernet_id); int err = 0; mutex_lock(&defrag6_mutex); - if (nf_frag->users == UINT_MAX) { + if (net->nf.defrag_ipv6_users == UINT_MAX) { err = -EOVERFLOW; goto out_unlock; } - if (nf_frag->users) { - nf_frag->users++; + if (net->nf.defrag_ipv6_users) { + net->nf.defrag_ipv6_users++; goto out_unlock; } err = nf_register_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); if (err == 0) - nf_frag->users = 1; + net->nf.defrag_ipv6_users = 1; out_unlock: mutex_unlock(&defrag6_mutex); @@ -161,12 +156,10 @@ EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); void nf_defrag_ipv6_disable(struct net *net) { - struct nft_ct_frag6_pernet *nf_frag = net_generic(net, nf_frag_pernet_id); - mutex_lock(&defrag6_mutex); - if (nf_frag->users) { - nf_frag->users--; - if (nf_frag->users == 0) + if (net->nf.defrag_ipv6_users) { + net->nf.defrag_ipv6_users--; + if (net->nf.defrag_ipv6_users == 0) nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); } -- cgit v1.2.3 From 49054556289e8787501630b7c7a9d407da02e296 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 29 Sep 2021 11:59:17 +0200 Subject: net: introduce and use lock_sock_fast_nested() Syzkaller reported a false positive deadlock involving the nl socket lock and the subflow socket lock: MPTCP: kernel_bind error, err=-98 ============================================ WARNING: possible recursive locking detected 5.15.0-rc1-syzkaller #0 Not tainted -------------------------------------------- syz-executor998/6520 is trying to acquire lock: ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 but task is already holding lock: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-sk_lock-AF_INET); lock(k-sk_lock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by syz-executor998/6520: #0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802 #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline] #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790 #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 stack backtrace: CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2944 [inline] check_deadlock kernel/locking/lockdep.c:2987 [inline] validate_chain kernel/locking/lockdep.c:3776 [inline] __lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015 lock_acquire kernel/locking/lockdep.c:5625 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590 lock_sock_fast+0x36/0x100 net/core/sock.c:3229 mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 __sock_release net/socket.c:649 [inline] sock_release+0x87/0x1b0 net/socket.c:677 mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900 mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170 genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731 genl_family_rcv_msg net/netlink/genetlink.c:775 [inline] genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 genl_rcv+0x24/0x40 net/netlink/genetlink.c:803 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_no_sendpage+0x101/0x150 net/core/sock.c:2980 kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504 kernel_sendpage net/socket.c:3501 [inline] sock_sendpage+0xe5/0x140 net/socket.c:1003 pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364 splice_from_pipe_feed fs/splice.c:418 [inline] __splice_from_pipe+0x43e/0x8a0 fs/splice.c:562 splice_from_pipe fs/splice.c:597 [inline] generic_splice_sendpage+0xd4/0x140 fs/splice.c:746 do_splice_from fs/splice.c:767 [inline] direct_splice_actor+0x110/0x180 fs/splice.c:936 splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891 do_splice_direct+0x1b3/0x280 fs/splice.c:979 do_sendfile+0xae9/0x1240 fs/read_write.c:1249 __do_sys_sendfile64 fs/read_write.c:1314 [inline] __se_sys_sendfile64 fs/read_write.c:1300 [inline] __x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f215cb69969 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969 RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005 RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08 R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000 the problem originates from uncorrect lock annotation in the mptcp code and is only visible since commit 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations"), but is present since the port-based endpoint support initial implementation. This patch addresses the issue introducing a nested variant of lock_sock_fast() and using it in the relevant code path. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations") Suggested-by: Thomas Gleixner Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni Reviewed-by: Thomas Gleixner Signed-off-by: David S. Miller --- include/net/sock.h | 31 ++++++++++++++++++++++++++++++- net/core/sock.c | 20 ++------------------ net/mptcp/protocol.c | 2 +- 3 files changed, 33 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index c005c3c750e8..dc3f8169312e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1623,7 +1623,36 @@ void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); + +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken: + * + * sk_lock.slock locked, owned = 0, BH disabled + * + * return true if slow path is taken: + * + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +static inline bool lock_sock_fast(struct sock *sk) +{ + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} + +/* fast socket lock variant for caller already holding a [different] socket lock */ +static inline bool lock_sock_fast_nested(struct sock *sk) +{ + mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} /** * unlock_sock_fast - complement of lock_sock_fast diff --git a/net/core/sock.c b/net/core/sock.c index 512e629f9780..7060d183216e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3210,24 +3210,8 @@ void release_sock(struct sock *sk) } EXPORT_SYMBOL(release_sock); -/** - * lock_sock_fast - fast version of lock_sock - * @sk: socket - * - * This version should be used for very small section, where process wont block - * return false if fast path is taken: - * - * sk_lock.slock locked, owned = 0, BH disabled - * - * return true if slow path is taken: - * - * sk_lock.slock unlocked, owned = 1, BH enabled - */ -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { - /* The sk_lock has mutex_lock() semantics here. */ - mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); - might_sleep(); spin_lock_bh(&sk->sk_lock.slock); @@ -3256,7 +3240,7 @@ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) spin_unlock_bh(&sk->sk_lock.slock); return true; } -EXPORT_SYMBOL(lock_sock_fast); +EXPORT_SYMBOL(__lock_sock_fast); int sock_gettstamp(struct socket *sock, void __user *userstamp, bool timeval, bool time32) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index dbcebf56798f..e5df0b5971c8 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2735,7 +2735,7 @@ cleanup: inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; mptcp_for_each_subflow(mptcp_sk(sk), subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - bool slow = lock_sock_fast(ssk); + bool slow = lock_sock_fast_nested(ssk); sock_orphan(ssk); unlock_sock_fast(ssk, slow); -- cgit v1.2.3 From 35306eb23814444bd4021f8a1c3047d3cb0c8b2b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 Sep 2021 15:57:50 -0700 Subject: af_unix: fix races in sk_peer_pid and sk_peer_cred accesses Jann Horn reported that SO_PEERCRED and SO_PEERGROUPS implementations are racy, as af_unix can concurrently change sk_peer_pid and sk_peer_cred. In order to fix this issue, this patch adds a new spinlock that needs to be used whenever these fields are read or written. Jann also pointed out that l2cap_sock_get_peer_pid_cb() is currently reading sk->sk_peer_pid which makes no sense, as this field is only possibly set by AF_UNIX sockets. We will have to clean this in a separate patch. This could be done by reverting b48596d1dc25 "Bluetooth: L2CAP: Add get_peer_pid callback" or implementing what was truly expected. Fixes: 109f6e39fa07 ("af_unix: Allow SO_PEERCRED to work across namespaces.") Signed-off-by: Eric Dumazet Reported-by: Jann Horn Cc: Eric W. Biederman Cc: Luiz Augusto von Dentz Cc: Marcel Holtmann Signed-off-by: David S. Miller --- include/net/sock.h | 2 ++ net/core/sock.c | 32 ++++++++++++++++++++++++++------ net/unix/af_unix.c | 34 ++++++++++++++++++++++++++++------ 3 files changed, 56 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index dc3f8169312e..ae929e21a376 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -488,8 +488,10 @@ struct sock { u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; #endif + spinlock_t sk_peer_lock; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; + long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 diff --git a/net/core/sock.c b/net/core/sock.c index 7060d183216e..c1601f75ec4b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1376,6 +1376,16 @@ set_sndbuf: } EXPORT_SYMBOL(sock_setsockopt); +static const struct cred *sk_get_peer_cred(struct sock *sk) +{ + const struct cred *cred; + + spin_lock(&sk->sk_peer_lock); + cred = get_cred(sk->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + return cred; +} static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) @@ -1552,7 +1562,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); + + spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + spin_unlock(&sk->sk_peer_lock); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; @@ -1560,20 +1574,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_PEERGROUPS: { + const struct cred *cred; int ret, n; - if (!sk->sk_peer_cred) + cred = sk_get_peer_cred(sk); + if (!cred) return -ENODATA; - n = sk->sk_peer_cred->group_info->ngroups; + n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); + put_cred(cred); return put_user(len, optlen) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, - sk->sk_peer_cred->group_info); + ret = groups_to_user((gid_t __user *)optval, cred->group_info); + put_cred(cred); if (ret) return ret; goto lenout; @@ -1935,9 +1952,10 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_frag.page = NULL; } - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ + put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); + if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); @@ -3145,6 +3163,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; + spin_lock_init(&sk->sk_peer_lock); + sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f505b89bda6a..efac5989edb5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -608,20 +608,42 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + spin_lock(&sk->sk_peer_lock); + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(task_tgid(current)); sk->sk_peer_cred = get_current_cred(); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static void copy_peercred(struct sock *sk, struct sock *peersk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + if (sk < peersk) { + spin_lock(&sk->sk_peer_lock); + spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&peersk->sk_peer_lock); + spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); + + spin_unlock(&sk->sk_peer_lock); + spin_unlock(&peersk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) -- cgit v1.2.3 From f792565326825ed806626da50c6f9a928f1079c1 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Wed, 29 Sep 2021 12:43:13 -0700 Subject: perf/core: fix userpage->time_enabled of inactive events Users of rdpmc rely on the mmapped user page to calculate accurate time_enabled. Currently, userpage->time_enabled is only updated when the event is added to the pmu. As a result, inactive event (due to counter multiplexing) does not have accurate userpage->time_enabled. This can be reproduced with something like: /* open 20 task perf_event "cycles", to create multiplexing */ fd = perf_event_open(); /* open task perf_event "cycles" */ userpage = mmap(fd); /* use mmap and rdmpc */ while (true) { time_enabled_mmap = xxx; /* use logic in perf_event_mmap_page */ time_enabled_read = read(fd).time_enabled; if (time_enabled_mmap > time_enabled_read) BUG(); } Fix this by updating userpage for inactive events in merge_sched_in. Suggested-by: Peter Zijlstra (Intel) Reported-and-tested-by: Lucian Grijincu Signed-off-by: Song Liu Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210929194313.2398474-1-songliubraving@fb.com --- include/linux/perf_event.h | 4 +++- kernel/events/core.c | 34 ++++++++++++++++++++++++++++++---- 2 files changed, 33 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fe156a8170aa..9b60bb89d86a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -683,7 +683,9 @@ struct perf_event { /* * timestamp shadows the actual context timing but it can * be safely used in NMI interrupt context. It reflects the - * context time as it was when the event was last scheduled in. + * context time as it was when the event was last scheduled in, + * or when ctx_sched_in failed to schedule the event because we + * run out of PMC. * * ctx_time already accounts for ctx->timestamp. Therefore to * compute ctx_time for a sample, simply add perf_clock(). diff --git a/kernel/events/core.c b/kernel/events/core.c index 0c000cb01eeb..f23ca260307f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3707,6 +3707,29 @@ static noinline int visit_groups_merge(struct perf_cpu_context *cpuctx, return 0; } +static inline bool event_update_userpage(struct perf_event *event) +{ + if (likely(!atomic_read(&event->mmap_count))) + return false; + + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); + perf_event_update_userpage(event); + + return true; +} + +static inline void group_update_userpage(struct perf_event *group_event) +{ + struct perf_event *event; + + if (!event_update_userpage(group_event)) + return; + + for_each_sibling_event(event, group_event) + event_update_userpage(event); +} + static int merge_sched_in(struct perf_event *event, void *data) { struct perf_event_context *ctx = event->ctx; @@ -3725,14 +3748,15 @@ static int merge_sched_in(struct perf_event *event, void *data) } if (event->state == PERF_EVENT_STATE_INACTIVE) { + *can_add_hw = 0; if (event->attr.pinned) { perf_cgroup_event_disable(event, ctx); perf_event_set_state(event, PERF_EVENT_STATE_ERROR); + } else { + ctx->rotate_necessary = 1; + perf_mux_hrtimer_restart(cpuctx); + group_update_userpage(event); } - - *can_add_hw = 0; - ctx->rotate_necessary = 1; - perf_mux_hrtimer_restart(cpuctx); } return 0; @@ -6324,6 +6348,8 @@ accounting: ring_buffer_attach(event, rb); + perf_event_update_time(event); + perf_set_shadow_time(event, event->ctx); perf_event_init_userpage(event); perf_event_update_userpage(event); } else { -- cgit v1.2.3 From 83d40a61046f73103b4e5d8f1310261487ff63b0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 20 Sep 2021 15:31:11 +0200 Subject: sched: Always inline is_percpu_thread() vmlinux.o: warning: objtool: check_preemption_disabled()+0x81: call to is_percpu_thread() leaves .noinstr.text section Reported-by: Stephen Rothwell Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210928084218.063371959@infradead.org --- include/linux/sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 39039ce8ac4c..c1a927ddec64 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1720,7 +1720,7 @@ extern struct pid *cad_pid; #define tsk_used_math(p) ((p)->flags & PF_USED_MATH) #define used_math() tsk_used_math(current) -static inline bool is_percpu_thread(void) +static __always_inline bool is_percpu_thread(void) { #ifdef CONFIG_SMP return (current->flags & PF_NO_SETAFFINITY) && -- cgit v1.2.3 From 5fb14d20f8241461d351bef73e49871e4b2330ab Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 1 Oct 2021 09:46:22 -0700 Subject: net: add kerneldoc comment for sk_peer_lock Fixes following warning: include/net/sock.h:533: warning: Function parameter or member 'sk_peer_lock' not described in 'sock' Fixes: 35306eb23814 ("af_unix: fix races in sk_peer_pid and sk_peer_cred accesses") Signed-off-by: Eric Dumazet Reported-by: Stephen Rothwell Link: https://lore.kernel.org/r/20211001164622.58520-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski --- include/net/sock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index ae929e21a376..ea6fbc88c8f9 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -307,6 +307,7 @@ struct bpf_local_storage; * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family + * @sk_peer_lock: lock protecting @sk_peer_pid and @sk_peer_cred * @sk_peer_pid: &struct pid for this socket's peer * @sk_peer_cred: %SO_PEERCRED setting * @sk_rcvlowat: %SO_RCVLOWAT setting -- cgit v1.2.3 From 019d9329e7481cfaccbd8ed17b1e04ca76970f13 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Thu, 30 Sep 2021 15:53:30 +0300 Subject: net: mscc: ocelot: fix VCAP filters remaining active after being deleted When ocelot_flower.c calls ocelot_vcap_filter_add(), the filter has a given filter->id.cookie. This filter is added to the block->rules list. However, when ocelot_flower.c calls ocelot_vcap_block_find_filter_by_id() which passes the cookie as argument, the filter is never found by filter->id.cookie when searching through the block->rules list. This is unsurprising, since the filter->id.cookie is an unsigned long, but the cookie argument provided to ocelot_vcap_block_find_filter_by_id() is a signed int, and the comparison fails. Fixes: 50c6cc5b9283 ("net: mscc: ocelot: store a namespaced VCAP filter ID") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20210930125330.2078625-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mscc/ocelot_vcap.c | 4 ++-- include/soc/mscc/ocelot_vcap.h | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c index 7945393a0655..99d7376a70a7 100644 --- a/drivers/net/ethernet/mscc/ocelot_vcap.c +++ b/drivers/net/ethernet/mscc/ocelot_vcap.c @@ -998,8 +998,8 @@ ocelot_vcap_block_find_filter_by_index(struct ocelot_vcap_block *block, } struct ocelot_vcap_filter * -ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int cookie, - bool tc_offload) +ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, + unsigned long cookie, bool tc_offload) { struct ocelot_vcap_filter *filter; diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 25fd525aaf92..4869ebbd438d 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -694,7 +694,7 @@ int ocelot_vcap_filter_add(struct ocelot *ocelot, int ocelot_vcap_filter_del(struct ocelot *ocelot, struct ocelot_vcap_filter *rule); struct ocelot_vcap_filter * -ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, int id, - bool tc_offload); +ocelot_vcap_block_find_filter_by_id(struct ocelot_vcap_block *block, + unsigned long cookie, bool tc_offload); #endif /* _OCELOT_VCAP_H_ */ -- cgit v1.2.3 From 6fb721cf781808ee2ca5e737fb0592cc68de3381 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 26 Sep 2021 09:59:35 +0200 Subject: netfilter: nf_tables: honor NLM_F_CREATE and NLM_F_EXCL in event notification Include the NLM_F_CREATE and NLM_F_EXCL flags in netlink event notifications, otherwise userspace cannot distiguish between create and add commands. Fixes: 96518518cc41 ("netfilter: add nftables") Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 47 +++++++++++++++++++++++++++++---------- net/netfilter/nft_quota.c | 2 +- 3 files changed, 37 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 148f5d8ee5ab..a16171c5fd9e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1202,7 +1202,7 @@ struct nft_object *nft_obj_lookup(const struct net *net, void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, - int event, int family, int report, gfp_t gfp); + int event, u16 flags, int family, int report, gfp_t gfp); /** * struct nft_object_type - stateful object type diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c8acd26c7201..c0851fec11d4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -780,6 +780,7 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -790,8 +791,11 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_table_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table); + event, flags, ctx->family, ctx->table); if (err < 0) { kfree_skb(skb); goto err; @@ -1563,6 +1567,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) { struct nftables_pernet *nft_net; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -1573,8 +1578,11 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_chain_info(skb, ctx->net, ctx->portid, ctx->seq, - event, 0, ctx->family, ctx->table, + event, flags, ctx->family, ctx->table, ctx->chain); if (err < 0) { kfree_skb(skb); @@ -2945,6 +2953,8 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, } if (ctx->flags & (NLM_F_APPEND | NLM_F_REPLACE)) flags |= NLM_F_APPEND; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, @@ -3957,8 +3967,9 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, gfp_t gfp_flags) { struct nftables_pernet *nft_net = nft_pernet(ctx->net); - struct sk_buff *skb; u32 portid = ctx->portid; + struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -3969,7 +3980,10 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; - err = nf_tables_fill_set(skb, ctx, set, event, 0); + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + + err = nf_tables_fill_set(skb, ctx, set, event, flags); if (err < 0) { kfree_skb(skb); goto err; @@ -5245,12 +5259,13 @@ static int nf_tables_getsetelem(struct sk_buff *skb, static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, const struct nft_set_elem *elem, - int event, u16 flags) + int event) { struct nftables_pernet *nft_net; struct net *net = ctx->net; u32 portid = ctx->portid; struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES)) @@ -5260,6 +5275,9 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, set, elem); if (err < 0) { @@ -6935,7 +6953,7 @@ static int nf_tables_delobj(struct sk_buff *skb, const struct nfnl_info *info, void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, - int family, int report, gfp_t gfp) + u16 flags, int family, int report, gfp_t gfp) { struct nftables_pernet *nft_net = nft_pernet(net); struct sk_buff *skb; @@ -6960,8 +6978,9 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, if (skb == NULL) goto err; - err = nf_tables_fill_obj_info(skb, net, portid, seq, event, 0, family, - table, obj, false); + err = nf_tables_fill_obj_info(skb, net, portid, seq, event, + flags & (NLM_F_CREATE | NLM_F_EXCL), + family, table, obj, false); if (err < 0) { kfree_skb(skb); goto err; @@ -6978,7 +6997,7 @@ static void nf_tables_obj_notify(const struct nft_ctx *ctx, struct nft_object *obj, int event) { nft_obj_notify(ctx->net, ctx->table, obj, ctx->portid, ctx->seq, event, - ctx->family, ctx->report, GFP_KERNEL); + ctx->flags, ctx->family, ctx->report, GFP_KERNEL); } /* @@ -7759,6 +7778,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, { struct nftables_pernet *nft_net = nft_pernet(ctx->net); struct sk_buff *skb; + u16 flags = 0; int err; if (!ctx->report && @@ -7769,8 +7789,11 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, if (skb == NULL) goto err; + if (ctx->flags & (NLM_F_CREATE | NLM_F_EXCL)) + flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); + err = nf_tables_fill_flowtable_info(skb, ctx->net, ctx->portid, - ctx->seq, event, 0, + ctx->seq, event, flags, ctx->family, flowtable, hook_list); if (err < 0) { kfree_skb(skb); @@ -8648,7 +8671,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_setelem_activate(net, te->set, &te->elem); nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_NEWSETELEM, 0); + NFT_MSG_NEWSETELEM); nft_trans_destroy(trans); break; case NFT_MSG_DELSETELEM: @@ -8656,7 +8679,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_setelem_notify(&trans->ctx, te->set, &te->elem, - NFT_MSG_DELSETELEM, 0); + NFT_MSG_DELSETELEM); nft_setelem_remove(net, te->set, &te->elem); if (!nft_setelem_is_catchall(te->set, &te->elem)) { atomic_dec(&te->set->nelems); diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 0363f533a42b..c4d1389f7185 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -60,7 +60,7 @@ static void nft_quota_obj_eval(struct nft_object *obj, if (overquota && !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0, - NFT_MSG_NEWOBJ, nft_pf(pkt), 0, GFP_ATOMIC); + NFT_MSG_NEWOBJ, 0, nft_pf(pkt), 0, GFP_ATOMIC); } static int nft_quota_do_init(const struct nlattr * const tb[], -- cgit v1.2.3 From 6e9bfdcf0a3b1c8126878c21adcfc343f89d4a6a Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Fri, 1 Oct 2021 15:37:31 +0100 Subject: cachefiles: Fix oops in trace_cachefiles_mark_buried due to NULL object In cachefiles_mark_object_buried, the dentry in question may not have an owner, and thus our cachefiles_object pointer may be NULL when calling the tracepoint, in which case we will also not have a valid debug_id to print in the tracepoint. Check for NULL object in the tracepoint and if so, just set debug_id to MAX_UINT as was done in 2908f5e101e3 ("fscache: Add a cookie debug ID and use that in traces"). This fixes the following oops: FS-Cache: Cache "mycache" added (type cachefiles) CacheFiles: File cache on vdc registered ... Workqueue: fscache_object fscache_object_work_func [fscache] RIP: 0010:trace_event_raw_event_cachefiles_mark_buried+0x4e/0xa0 [cachefiles] .... Call Trace: cachefiles_mark_object_buried+0xa5/0xb0 [cachefiles] cachefiles_bury_object+0x270/0x430 [cachefiles] cachefiles_walk_to_object+0x195/0x9c0 [cachefiles] cachefiles_lookup_object+0x5a/0xc0 [cachefiles] fscache_look_up_object+0xd7/0x160 [fscache] fscache_object_work_func+0xb2/0x340 [fscache] process_one_work+0x1f1/0x390 worker_thread+0x53/0x3e0 kthread+0x127/0x150 Fixes: 2908f5e101e3 ("fscache: Add a cookie debug ID and use that in traces") Signed-off-by: Dave Wysochanski Signed-off-by: David Howells cc: linux-cachefs@redhat.com Signed-off-by: Linus Torvalds --- include/trace/events/cachefiles.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 9a448fe9355d..695bfdbfdcad 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -305,7 +305,7 @@ TRACE_EVENT(cachefiles_mark_buried, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->why = why; ), -- cgit v1.2.3 From 97315723c463679a9ecf803d6479fca24c3efda0 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 22 Sep 2021 12:18:25 +0200 Subject: xen/privcmd: drop "pages" parameter from xen_remap_pfn() The function doesn't use it and all of its callers say in a comment that their respective arguments are to be non-NULL only in auto-translated mode. Since xen_remap_domain_mfn_array() isn't supposed to be used by non-PV, drop the parameter there as well. It was bogusly passed as non- NULL (PRIV_VMA_LOCKED) by its only caller anyway. For xen_remap_domain_gfn_range(), otoh, it's not clear at all why this wouldn't want / might not need to gain auto-translated support down the road, so the parameter is retained there despite now remaining unused (and the only caller passing NULL); correct a respective comment as well. Signed-off-by: Jan Beulich Reviewed-by: Boris Ostrovsky Link: https://lore.kernel.org/r/036ad8a2-46f9-ac3d-6219-bdc93ab9e10b@suse.com Signed-off-by: Juergen Gross --- arch/x86/xen/mmu_pv.c | 2 +- drivers/xen/privcmd.c | 5 ++--- include/xen/xen-ops.h | 15 ++++++--------- 3 files changed, 9 insertions(+), 13 deletions(-) (limited to 'include') diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 8d751939c6f3..3359c23573c5 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2398,7 +2398,7 @@ static int remap_area_pfn_pte_fn(pte_t *ptep, unsigned long addr, void *data) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages) + unsigned int domid, bool no_translate) { int err = 0; struct remap_data rmd; diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c index 5af2a295e32f..3369734108af 100644 --- a/drivers/xen/privcmd.c +++ b/drivers/xen/privcmd.c @@ -257,7 +257,7 @@ static long privcmd_ioctl_mmap(struct file *file, void __user *udata) LIST_HEAD(pagelist); struct mmap_gfn_state state; - /* We only support privcmd_ioctl_mmap_batch for auto translated. */ + /* We only support privcmd_ioctl_mmap_batch for non-auto-translated. */ if (xen_feature(XENFEAT_auto_translated_physmap)) return -ENOSYS; @@ -810,8 +810,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file, kdata.addr & PAGE_MASK, pfns, kdata.num, errs, vma->vm_page_prot, - domid, - vma->vm_private_data); + domid); if (num < 0) rc = num; else if (num != kdata.num) { diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index db28e79b77ee..a3584a357f35 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -52,12 +52,12 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); #if defined(CONFIG_XEN_PV) int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, - unsigned int domid, bool no_translate, struct page **pages); + unsigned int domid, bool no_translate); #else static inline int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *pfn, int nr, int *err_ptr, pgprot_t prot, unsigned int domid, - bool no_translate, struct page **pages) + bool no_translate) { BUG(); return 0; @@ -134,7 +134,7 @@ static inline int xen_remap_domain_gfn_array(struct vm_area_struct *vma, */ BUG_ON(err_ptr == NULL); return xen_remap_pfn(vma, addr, gfn, nr, err_ptr, prot, domid, - false, pages); + false); } /* @@ -146,7 +146,6 @@ static inline int xen_remap_domain_gfn_array(struct vm_area_struct *vma, * @err_ptr: Returns per-MFN error status. * @prot: page protection mask * @domid: Domain owning the pages - * @pages: Array of pages if this domain has an auto-translated physmap * * @mfn and @err_ptr may point to the same buffer, the MFNs will be * overwritten by the error codes after they are mapped. @@ -157,14 +156,13 @@ static inline int xen_remap_domain_gfn_array(struct vm_area_struct *vma, static inline int xen_remap_domain_mfn_array(struct vm_area_struct *vma, unsigned long addr, xen_pfn_t *mfn, int nr, int *err_ptr, - pgprot_t prot, unsigned int domid, - struct page **pages) + pgprot_t prot, unsigned int domid) { if (xen_feature(XENFEAT_auto_translated_physmap)) return -EOPNOTSUPP; return xen_remap_pfn(vma, addr, mfn, nr, err_ptr, prot, domid, - true, pages); + true); } /* xen_remap_domain_gfn_range() - map a range of foreign frames @@ -188,8 +186,7 @@ static inline int xen_remap_domain_gfn_range(struct vm_area_struct *vma, if (xen_feature(XENFEAT_auto_translated_physmap)) return -EOPNOTSUPP; - return xen_remap_pfn(vma, addr, &gfn, nr, NULL, prot, domid, false, - pages); + return xen_remap_pfn(vma, addr, &gfn, nr, NULL, prot, domid, false); } int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, -- cgit v1.2.3 From a0e25f0a0d39d66c048d5dbac1e7ebaa6ec885d7 Mon Sep 17 00:00:00 2001 From: Dave Wysochanski Date: Sun, 3 Oct 2021 12:14:00 -0400 Subject: cachefiles: Fix oops with cachefiles_cull() due to NULL object When cachefiles_cull() calls cachefiles_bury_object(), it passes a NULL object. When this occurs, either trace_cachefiles_unlink() or trace_cachefiles_rename() may oops due to the NULL object. Check for NULL object in the tracepoint and if so, set debug_id to MAX_UINT as was done in 2908f5e101e3. The following oops was seen with xfstests generic/100. BUG: kernel NULL pointer dereference, address: 0000000000000010 ... RIP: 0010:trace_event_raw_event_cachefiles_unlink+0x4e/0xa0 [cachefiles] ... Call Trace: cachefiles_bury_object+0x242/0x430 [cachefiles] ? __vfs_removexattr_locked+0x10f/0x150 ? vfs_removexattr+0x51/0xd0 cachefiles_cull+0x84/0x120 [cachefiles] cachefiles_daemon_cull+0xd1/0x120 [cachefiles] cachefiles_daemon_write+0x158/0x190 [cachefiles] vfs_write+0xbc/0x260 ksys_write+0x4f/0xc0 do_syscall_64+0x3b/0x90 The following oops was seen with xfstests generic/290. BUG: kernel NULL pointer dereference, address: 0000000000000010 ... RIP: 0010:trace_event_raw_event_cachefiles_rename+0x54/0xa0 [cachefiles] ... Call Trace: cachefiles_bury_object+0x35c/0x430 [cachefiles] cachefiles_cull+0x84/0x120 [cachefiles] cachefiles_daemon_cull+0xd1/0x120 [cachefiles] cachefiles_daemon_write+0x158/0x190 [cachefiles] vfs_write+0xbc/0x260 ksys_write+0x4f/0xc0 do_syscall_64+0x3b/0x90 Fixes: 2908f5e101e3 ("fscache: Add a cookie debug ID and use that in traces") Signed-off-by: Dave Wysochanski Signed-off-by: David Howells Link: https://listman.redhat.com/archives/linux-cachefs/2021-October/msg00009.html --- include/trace/events/cachefiles.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index 695bfdbfdcad..920b6a303d60 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -178,7 +178,7 @@ TRACE_EVENT(cachefiles_unlink, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->why = why; ), @@ -205,7 +205,7 @@ TRACE_EVENT(cachefiles_rename, ), TP_fast_assign( - __entry->obj = obj->fscache.debug_id; + __entry->obj = obj ? obj->fscache.debug_id : UINT_MAX; __entry->de = de; __entry->to = to; __entry->why = why; -- cgit v1.2.3 From 3f6cffb8604b537e3d7ea040d7f4368689638eaf Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 4 Oct 2021 16:01:40 -0700 Subject: etherdevice: use __dev_addr_set() Andrew points out that eth_hw_addr_set() replaces memcpy() calls so we can't use ether_addr_copy() which assumes both arguments are 2-bytes aligned. Reported-by: Andrew Lunn Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index 928c411bd509..c58d50451485 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -308,7 +308,7 @@ static inline void ether_addr_copy(u8 *dst, const u8 *src) */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { - ether_addr_copy(dev->dev_addr, addr); + __dev_addr_set(dev, addr, ETH_ALEN); } /** -- cgit v1.2.3 From 94ad8aacbc2d4908b052c8bdb5ae13bc702f77ea Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 27 Sep 2021 16:40:50 +0200 Subject: ARM: omap1: move omap15xx local bus handling to usb.c Commit 38225f2ef2f4 ("ARM/omap1: switch to use dma_direct_set_offset for lbus DMA offsets") removed a lot of mach/memory.h, but left the USB offset handling split into arch/arm/mach-omap1/usb.c and drivers/usb/host/ohci-omap.c. This can cause a randconfig build warning that now fails the build with -Werror: arch/arm/mach-omap1/usb.c:561:30: error: 'omap_1510_usb_ohci_nb' defined but not used [-Werror=unused-variable] 561 | static struct notifier_block omap_1510_usb_ohci_nb = { | ^~~~~~~~~~~~~~~~~~~~~ Move it all into the platform file to get rid of the final location that relies on mach/memory.h. Acked-by: Felipe Balbi Acked-by: Alan Stern Acked-by: Tony Lindgren Acked-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20210927144118.2464881-1-arnd@kernel.org' Signed-off-by: Arnd Bergmann --- arch/arm/mach-omap1/include/mach/memory.h | 12 ---- arch/arm/mach-omap1/usb.c | 116 +++++++++++++++++++++--------- drivers/usb/host/ohci-omap.c | 72 +------------------ include/linux/platform_data/usb-omap1.h | 2 + 4 files changed, 86 insertions(+), 116 deletions(-) (limited to 'include') diff --git a/arch/arm/mach-omap1/include/mach/memory.h b/arch/arm/mach-omap1/include/mach/memory.h index 36bc0000cb6a..ba3a350479c8 100644 --- a/arch/arm/mach-omap1/include/mach/memory.h +++ b/arch/arm/mach-omap1/include/mach/memory.h @@ -9,16 +9,4 @@ /* REVISIT: omap1 legacy drivers still rely on this */ #include -/* - * Bus address is physical address, except for OMAP-1510 Local Bus. - * OMAP-1510 bus address is translated into a Local Bus address if the - * OMAP bus type is lbus. We do the address translation based on the - * device overriding the defaults used in the dma-mapping API. - */ - -/* - * OMAP-1510 Local Bus address offset - */ -#define OMAP1510_LB_OFFSET UL(0x30000000) - #endif diff --git a/arch/arm/mach-omap1/usb.c b/arch/arm/mach-omap1/usb.c index 86d3b3c157af..e60831c82b78 100644 --- a/arch/arm/mach-omap1/usb.c +++ b/arch/arm/mach-omap1/usb.c @@ -11,6 +11,7 @@ #include #include #include +#include #include @@ -206,8 +207,6 @@ static inline void udc_device_init(struct omap_usb_config *pdata) #endif -#if IS_ENABLED(CONFIG_USB_OHCI_HCD) - /* The dmamask must be set for OHCI to work */ static u64 ohci_dmamask = ~(u32)0; @@ -236,20 +235,15 @@ static struct platform_device ohci_device = { static inline void ohci_device_init(struct omap_usb_config *pdata) { + if (!IS_ENABLED(CONFIG_USB_OHCI_HCD)) + return; + if (cpu_is_omap7xx()) ohci_resources[1].start = INT_7XX_USB_HHC_1; pdata->ohci_device = &ohci_device; pdata->ocpi_enable = &ocpi_enable; } -#else - -static inline void ohci_device_init(struct omap_usb_config *pdata) -{ -} - -#endif - #if defined(CONFIG_USB_OTG) && defined(CONFIG_ARCH_OMAP_OTG) static struct resource otg_resources[] = { @@ -534,33 +528,87 @@ bad: } #ifdef CONFIG_ARCH_OMAP15XX +/* OMAP-1510 OHCI has its own MMU for DMA */ +#define OMAP1510_LB_MEMSIZE 32 /* Should be same as SDRAM size */ +#define OMAP1510_LB_CLOCK_DIV 0xfffec10c +#define OMAP1510_LB_MMU_CTL 0xfffec208 +#define OMAP1510_LB_MMU_LCK 0xfffec224 +#define OMAP1510_LB_MMU_LD_TLB 0xfffec228 +#define OMAP1510_LB_MMU_CAM_H 0xfffec22c +#define OMAP1510_LB_MMU_CAM_L 0xfffec230 +#define OMAP1510_LB_MMU_RAM_H 0xfffec234 +#define OMAP1510_LB_MMU_RAM_L 0xfffec238 -/* ULPD_DPLL_CTRL */ -#define DPLL_IOB (1 << 13) -#define DPLL_PLL_ENABLE (1 << 4) -#define DPLL_LOCK (1 << 0) +/* + * Bus address is physical address, except for OMAP-1510 Local Bus. + * OMAP-1510 bus address is translated into a Local Bus address if the + * OMAP bus type is lbus. + */ +#define OMAP1510_LB_OFFSET UL(0x30000000) -/* ULPD_APLL_CTRL */ -#define APLL_NDPLL_SWITCH (1 << 0) +/* + * OMAP-1510 specific Local Bus clock on/off + */ +static int omap_1510_local_bus_power(int on) +{ + if (on) { + omap_writel((1 << 1) | (1 << 0), OMAP1510_LB_MMU_CTL); + udelay(200); + } else { + omap_writel(0, OMAP1510_LB_MMU_CTL); + } -static int omap_1510_usb_ohci_notifier(struct notifier_block *nb, - unsigned long event, void *data) + return 0; +} + +/* + * OMAP-1510 specific Local Bus initialization + * NOTE: This assumes 32MB memory size in OMAP1510LB_MEMSIZE. + * See also arch/mach-omap/memory.h for __virt_to_dma() and + * __dma_to_virt() which need to match with the physical + * Local Bus address below. + */ +static int omap_1510_local_bus_init(void) { - struct device *dev = data; + unsigned int tlb; + unsigned long lbaddr, physaddr; + + omap_writel((omap_readl(OMAP1510_LB_CLOCK_DIV) & 0xfffffff8) | 0x4, + OMAP1510_LB_CLOCK_DIV); + + /* Configure the Local Bus MMU table */ + for (tlb = 0; tlb < OMAP1510_LB_MEMSIZE; tlb++) { + lbaddr = tlb * 0x00100000 + OMAP1510_LB_OFFSET; + physaddr = tlb * 0x00100000 + PHYS_OFFSET; + omap_writel((lbaddr & 0x0fffffff) >> 22, OMAP1510_LB_MMU_CAM_H); + omap_writel(((lbaddr & 0x003ffc00) >> 6) | 0xc, + OMAP1510_LB_MMU_CAM_L); + omap_writel(physaddr >> 16, OMAP1510_LB_MMU_RAM_H); + omap_writel((physaddr & 0x0000fc00) | 0x300, OMAP1510_LB_MMU_RAM_L); + omap_writel(tlb << 4, OMAP1510_LB_MMU_LCK); + omap_writel(0x1, OMAP1510_LB_MMU_LD_TLB); + } - if (event != BUS_NOTIFY_ADD_DEVICE) - return NOTIFY_DONE; + /* Enable the walking table */ + omap_writel(omap_readl(OMAP1510_LB_MMU_CTL) | (1 << 3), OMAP1510_LB_MMU_CTL); + udelay(200); - if (strncmp(dev_name(dev), "ohci", 4) == 0 && - dma_direct_set_offset(dev, PHYS_OFFSET, OMAP1510_LB_OFFSET, - (u64)-1)) - WARN_ONCE(1, "failed to set DMA offset\n"); - return NOTIFY_OK; + return 0; } -static struct notifier_block omap_1510_usb_ohci_nb = { - .notifier_call = omap_1510_usb_ohci_notifier, -}; +static void omap_1510_local_bus_reset(void) +{ + omap_1510_local_bus_power(1); + omap_1510_local_bus_init(); +} + +/* ULPD_DPLL_CTRL */ +#define DPLL_IOB (1 << 13) +#define DPLL_PLL_ENABLE (1 << 4) +#define DPLL_LOCK (1 << 0) + +/* ULPD_APLL_CTRL */ +#define APLL_NDPLL_SWITCH (1 << 0) static void __init omap_1510_usb_init(struct omap_usb_config *config) { @@ -616,19 +664,19 @@ static void __init omap_1510_usb_init(struct omap_usb_config *config) } #endif -#if IS_ENABLED(CONFIG_USB_OHCI_HCD) - if (config->register_host) { + if (IS_ENABLED(CONFIG_USB_OHCI_HCD) && config->register_host) { int status; - bus_register_notifier(&platform_bus_type, - &omap_1510_usb_ohci_nb); ohci_device.dev.platform_data = config; + dma_direct_set_offset(&ohci_device.dev, PHYS_OFFSET, + OMAP1510_LB_OFFSET, (u64)-1); status = platform_device_register(&ohci_device); if (status) pr_debug("can't register OHCI device, %d\n", status); /* hcd explicitly gates 48MHz */ + + config->lb_reset = omap_1510_local_bus_reset; } -#endif } #else diff --git a/drivers/usb/host/ohci-omap.c b/drivers/usb/host/ohci-omap.c index 0b3722770760..ded9738392e4 100644 --- a/drivers/usb/host/ohci-omap.c +++ b/drivers/usb/host/ohci-omap.c @@ -40,17 +40,6 @@ #include -/* OMAP-1510 OHCI has its own MMU for DMA */ -#define OMAP1510_LB_MEMSIZE 32 /* Should be same as SDRAM size */ -#define OMAP1510_LB_CLOCK_DIV 0xfffec10c -#define OMAP1510_LB_MMU_CTL 0xfffec208 -#define OMAP1510_LB_MMU_LCK 0xfffec224 -#define OMAP1510_LB_MMU_LD_TLB 0xfffec228 -#define OMAP1510_LB_MMU_CAM_H 0xfffec22c -#define OMAP1510_LB_MMU_CAM_L 0xfffec230 -#define OMAP1510_LB_MMU_RAM_H 0xfffec234 -#define OMAP1510_LB_MMU_RAM_L 0xfffec238 - #define DRIVER_DESC "OHCI OMAP driver" struct ohci_omap_priv { @@ -104,61 +93,6 @@ static int omap_ohci_transceiver_power(struct ohci_omap_priv *priv, int on) return 0; } -#ifdef CONFIG_ARCH_OMAP15XX -/* - * OMAP-1510 specific Local Bus clock on/off - */ -static int omap_1510_local_bus_power(int on) -{ - if (on) { - omap_writel((1 << 1) | (1 << 0), OMAP1510_LB_MMU_CTL); - udelay(200); - } else { - omap_writel(0, OMAP1510_LB_MMU_CTL); - } - - return 0; -} - -/* - * OMAP-1510 specific Local Bus initialization - * NOTE: This assumes 32MB memory size in OMAP1510LB_MEMSIZE. - * See also arch/mach-omap/memory.h for __virt_to_dma() and - * __dma_to_virt() which need to match with the physical - * Local Bus address below. - */ -static int omap_1510_local_bus_init(void) -{ - unsigned int tlb; - unsigned long lbaddr, physaddr; - - omap_writel((omap_readl(OMAP1510_LB_CLOCK_DIV) & 0xfffffff8) | 0x4, - OMAP1510_LB_CLOCK_DIV); - - /* Configure the Local Bus MMU table */ - for (tlb = 0; tlb < OMAP1510_LB_MEMSIZE; tlb++) { - lbaddr = tlb * 0x00100000 + OMAP1510_LB_OFFSET; - physaddr = tlb * 0x00100000 + PHYS_OFFSET; - omap_writel((lbaddr & 0x0fffffff) >> 22, OMAP1510_LB_MMU_CAM_H); - omap_writel(((lbaddr & 0x003ffc00) >> 6) | 0xc, - OMAP1510_LB_MMU_CAM_L); - omap_writel(physaddr >> 16, OMAP1510_LB_MMU_RAM_H); - omap_writel((physaddr & 0x0000fc00) | 0x300, OMAP1510_LB_MMU_RAM_L); - omap_writel(tlb << 4, OMAP1510_LB_MMU_LCK); - omap_writel(0x1, OMAP1510_LB_MMU_LD_TLB); - } - - /* Enable the walking table */ - omap_writel(omap_readl(OMAP1510_LB_MMU_CTL) | (1 << 3), OMAP1510_LB_MMU_CTL); - udelay(200); - - return 0; -} -#else -#define omap_1510_local_bus_power(x) {} -#define omap_1510_local_bus_init() {} -#endif - #ifdef CONFIG_USB_OTG static void start_hnp(struct ohci_hcd *ohci) @@ -229,10 +163,8 @@ static int ohci_omap_reset(struct usb_hcd *hcd) omap_ohci_clock_power(priv, 1); - if (cpu_is_omap15xx()) { - omap_1510_local_bus_power(1); - omap_1510_local_bus_init(); - } + if (config->lb_reset) + config->lb_reset(); ret = ohci_setup(hcd); if (ret < 0) diff --git a/include/linux/platform_data/usb-omap1.h b/include/linux/platform_data/usb-omap1.h index 43b5ce139c37..878e572a78bf 100644 --- a/include/linux/platform_data/usb-omap1.h +++ b/include/linux/platform_data/usb-omap1.h @@ -48,6 +48,8 @@ struct omap_usb_config { u32 (*usb2_init)(unsigned nwires, unsigned alt_pingroup); int (*ocpi_enable)(void); + + void (*lb_reset)(void); }; #endif /* __LINUX_USB_OMAP1_H */ -- cgit v1.2.3 From 95a13ee858c9e426e63c97063677736f74af7163 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Oct 2021 16:55:44 +0300 Subject: hyper-v: Replace uuid.h with types.h There is no user of anything in uuid.h in the hyperv.h. Replace it with more appropriate types.h. Fixes: f081bbb3fd03 ("hyper-v: Remove internal types from UAPI header") Reported-by: Greg Kroah-Hartman Signed-off-by: Andy Shevchenko Reviewed-by: Haiyang Zhang Link: https://lore.kernel.org/r/20211001135544.1823-1-andriy.shevchenko@linux.intel.com Signed-off-by: Wei Liu --- include/uapi/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index 6135d92e0d47..daf82a230c0e 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -26,7 +26,7 @@ #ifndef _UAPI_HYPERV_H #define _UAPI_HYPERV_H -#include +#include /* * Framework version for util services. -- cgit v1.2.3 From 424953cf3c6657f1e67e1a2c5d6e3bb518ea4e9a Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 28 Sep 2021 09:50:27 +0200 Subject: qcom_scm: hide Kconfig symbol Now that SCM can be a loadable module, we have to add another dependency to avoid link failures when ipa or adreno-gpu are built-in: aarch64-linux-ld: drivers/net/ipa/ipa_main.o: in function `ipa_probe': ipa_main.c:(.text+0xfc4): undefined reference to `qcom_scm_is_available' ld.lld: error: undefined symbol: qcom_scm_is_available >>> referenced by adreno_gpu.c >>> gpu/drm/msm/adreno/adreno_gpu.o:(adreno_zap_shader_load) in archive drivers/built-in.a This can happen when CONFIG_ARCH_QCOM is disabled and we don't select QCOM_MDT_LOADER, but some other module selects QCOM_SCM. Ideally we'd use a similar dependency here to what we have for QCOM_RPROC_COMMON, but that causes dependency loops from other things selecting QCOM_SCM. This appears to be an endless problem, so try something different this time: - CONFIG_QCOM_SCM becomes a hidden symbol that nothing 'depends on' but that is simply selected by all of its users - All the stubs in include/linux/qcom_scm.h can go away - arm-smccc.h needs to provide a stub for __arm_smccc_smc() to allow compile-testing QCOM_SCM on all architectures. - To avoid a circular dependency chain involving RESET_CONTROLLER and PINCTRL_SUNXI, drop the 'select RESET_CONTROLLER' statement. According to my testing this still builds fine, and the QCOM platform selects this symbol already. Acked-by: Kalle Valo Acked-by: Alex Elder Signed-off-by: Arnd Bergmann --- drivers/firmware/Kconfig | 5 +-- drivers/gpu/drm/msm/Kconfig | 4 +- drivers/iommu/Kconfig | 3 +- drivers/iommu/arm/arm-smmu/Makefile | 3 +- drivers/iommu/arm/arm-smmu/arm-smmu-impl.c | 3 +- drivers/media/platform/Kconfig | 2 +- drivers/mmc/host/Kconfig | 2 +- drivers/net/ipa/Kconfig | 1 + drivers/net/wireless/ath/ath10k/Kconfig | 2 +- drivers/pinctrl/qcom/Kconfig | 3 +- include/linux/arm-smccc.h | 10 +++++ include/linux/qcom_scm.h | 71 ------------------------------ 12 files changed, 24 insertions(+), 85 deletions(-) (limited to 'include') diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 220a58cf0a44..cda7d7162cbb 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -203,10 +203,7 @@ config INTEL_STRATIX10_RSU Say Y here if you want Intel RSU support. config QCOM_SCM - tristate "Qcom SCM driver" - depends on ARM || ARM64 - depends on HAVE_ARM_SMCCC - select RESET_CONTROLLER + tristate config QCOM_SCM_DOWNLOAD_MODE_DEFAULT bool "Qualcomm download mode enabled by default" diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index e9c6af78b1d7..3ddf739a6f9b 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -17,7 +17,7 @@ config DRM_MSM select DRM_SCHED select SHMEM select TMPFS - select QCOM_SCM if ARCH_QCOM + select QCOM_SCM select WANT_DEV_COREDUMP select SND_SOC_HDMI_CODEC if SND_SOC select SYNC_FILE @@ -55,7 +55,7 @@ config DRM_MSM_GPU_SUDO config DRM_MSM_HDMI_HDCP bool "Enable HDMI HDCP support in MSM DRM driver" - depends on DRM_MSM && QCOM_SCM + depends on DRM_MSM default y help Choose this option to enable HDCP state machine diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 124c41adeca1..c5c71b7ab7e8 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -308,7 +308,6 @@ config APPLE_DART config ARM_SMMU tristate "ARM Ltd. System MMU (SMMU) Support" depends on ARM64 || ARM || (COMPILE_TEST && !GENERIC_ATOMIC64) - depends on QCOM_SCM || !QCOM_SCM #if QCOM_SCM=m this can't be =y select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU if ARM @@ -438,7 +437,7 @@ config QCOM_IOMMU # Note: iommu drivers cannot (yet?) be built as modules bool "Qualcomm IOMMU Support" depends on ARCH_QCOM || (COMPILE_TEST && !GENERIC_ATOMIC64) - depends on QCOM_SCM=y + select QCOM_SCM select IOMMU_API select IOMMU_IO_PGTABLE_LPAE select ARM_DMA_USE_IOMMU diff --git a/drivers/iommu/arm/arm-smmu/Makefile b/drivers/iommu/arm/arm-smmu/Makefile index e240a7bcf310..b0cc01aa20c9 100644 --- a/drivers/iommu/arm/arm-smmu/Makefile +++ b/drivers/iommu/arm/arm-smmu/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_QCOM_IOMMU) += qcom_iommu.o obj-$(CONFIG_ARM_SMMU) += arm_smmu.o -arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o arm-smmu-qcom.o +arm_smmu-objs += arm-smmu.o arm-smmu-impl.o arm-smmu-nvidia.o +arm_smmu-$(CONFIG_ARM_SMMU_QCOM) += arm-smmu-qcom.o diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c index 9f465e146799..2c25cce38060 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu-impl.c @@ -215,7 +215,8 @@ struct arm_smmu_device *arm_smmu_impl_init(struct arm_smmu_device *smmu) of_device_is_compatible(np, "nvidia,tegra186-smmu")) return nvidia_smmu_impl_init(smmu); - smmu = qcom_smmu_impl_init(smmu); + if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM)) + smmu = qcom_smmu_impl_init(smmu); if (of_device_is_compatible(np, "marvell,ap806-smmu-500")) smmu->impl = &mrvl_mmu500_impl; diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig index 157c924686e4..80321e03809a 100644 --- a/drivers/media/platform/Kconfig +++ b/drivers/media/platform/Kconfig @@ -565,7 +565,7 @@ config VIDEO_QCOM_VENUS depends on VIDEO_DEV && VIDEO_V4L2 && QCOM_SMEM depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST select QCOM_MDT_LOADER if ARCH_QCOM - select QCOM_SCM if ARCH_QCOM + select QCOM_SCM select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV help diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig index 71313961cc54..95b3511b0560 100644 --- a/drivers/mmc/host/Kconfig +++ b/drivers/mmc/host/Kconfig @@ -547,7 +547,7 @@ config MMC_SDHCI_MSM depends on MMC_SDHCI_PLTFM select MMC_SDHCI_IO_ACCESSORS select MMC_CQHCI - select QCOM_SCM if MMC_CRYPTO && ARCH_QCOM + select QCOM_SCM if MMC_CRYPTO help This selects the Secure Digital Host Controller Interface (SDHCI) support present in Qualcomm SOCs. The controller supports diff --git a/drivers/net/ipa/Kconfig b/drivers/net/ipa/Kconfig index 8f99cfa14680..d037682fb7ad 100644 --- a/drivers/net/ipa/Kconfig +++ b/drivers/net/ipa/Kconfig @@ -4,6 +4,7 @@ config QCOM_IPA depends on ARCH_QCOM || COMPILE_TEST depends on QCOM_RPROC_COMMON || (QCOM_RPROC_COMMON=n && COMPILE_TEST) select QCOM_MDT_LOADER if ARCH_QCOM + select QCOM_SCM select QCOM_QMI_HELPERS help Choose Y or M here to include support for the Qualcomm diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig index 741289e385d5..ca007b800f75 100644 --- a/drivers/net/wireless/ath/ath10k/Kconfig +++ b/drivers/net/wireless/ath/ath10k/Kconfig @@ -44,7 +44,7 @@ config ATH10K_SNOC tristate "Qualcomm ath10k SNOC support" depends on ATH10K depends on ARCH_QCOM || COMPILE_TEST - depends on QCOM_SCM || !QCOM_SCM #if QCOM_SCM=m this can't be =y + select QCOM_SCM select QCOM_QMI_HELPERS help This module adds support for integrated WCN3990 chip connected diff --git a/drivers/pinctrl/qcom/Kconfig b/drivers/pinctrl/qcom/Kconfig index 32ea2a8ec02b..5ff4207df66e 100644 --- a/drivers/pinctrl/qcom/Kconfig +++ b/drivers/pinctrl/qcom/Kconfig @@ -3,7 +3,8 @@ if (ARCH_QCOM || COMPILE_TEST) config PINCTRL_MSM tristate "Qualcomm core pin controller driver" - depends on GPIOLIB && (QCOM_SCM || !QCOM_SCM) #if QCOM_SCM=m this can't be =y + depends on GPIOLIB + select QCOM_SCM select PINMUX select PINCONF select GENERIC_PINCONF diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 7d1cabe15262..63ccb5252190 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -321,10 +321,20 @@ asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0); * from register 0 to 3 on return from the SMC instruction. An optional * quirk structure provides vendor specific behavior. */ +#ifdef CONFIG_HAVE_ARM_SMCCC asmlinkage void __arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3, unsigned long a4, unsigned long a5, unsigned long a6, unsigned long a7, struct arm_smccc_res *res, struct arm_smccc_quirk *quirk); +#else +static inline void __arm_smccc_smc(unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, unsigned long a4, + unsigned long a5, unsigned long a6, unsigned long a7, + struct arm_smccc_res *res, struct arm_smccc_quirk *quirk) +{ + *res = (struct arm_smccc_res){}; +} +#endif /** * __arm_smccc_hvc() - make HVC calls diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h index c0475d1c9885..81cad9e1e412 100644 --- a/include/linux/qcom_scm.h +++ b/include/linux/qcom_scm.h @@ -61,7 +61,6 @@ enum qcom_scm_ice_cipher { #define QCOM_SCM_PERM_RW (QCOM_SCM_PERM_READ | QCOM_SCM_PERM_WRITE) #define QCOM_SCM_PERM_RWX (QCOM_SCM_PERM_RW | QCOM_SCM_PERM_EXEC) -#if IS_ENABLED(CONFIG_QCOM_SCM) extern bool qcom_scm_is_available(void); extern int qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus); @@ -115,74 +114,4 @@ extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, extern int qcom_scm_lmh_profile_change(u32 profile_id); extern bool qcom_scm_lmh_dcvsh_available(void); -#else - -#include - -static inline bool qcom_scm_is_available(void) { return false; } - -static inline int qcom_scm_set_cold_boot_addr(void *entry, - const cpumask_t *cpus) { return -ENODEV; } -static inline int qcom_scm_set_warm_boot_addr(void *entry, - const cpumask_t *cpus) { return -ENODEV; } -static inline void qcom_scm_cpu_power_down(u32 flags) {} -static inline u32 qcom_scm_set_remote_state(u32 state,u32 id) - { return -ENODEV; } - -static inline int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, - size_t size) { return -ENODEV; } -static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, - phys_addr_t size) { return -ENODEV; } -static inline int qcom_scm_pas_auth_and_reset(u32 peripheral) - { return -ENODEV; } -static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; } -static inline bool qcom_scm_pas_supported(u32 peripheral) { return false; } - -static inline int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val) - { return -ENODEV; } -static inline int qcom_scm_io_writel(phys_addr_t addr, unsigned int val) - { return -ENODEV; } - -static inline bool qcom_scm_restore_sec_cfg_available(void) { return false; } -static inline int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare) - { return -ENODEV; } -static inline int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size) - { return -ENODEV; } -static inline int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare) - { return -ENODEV; } -extern inline int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size, - u32 cp_nonpixel_start, - u32 cp_nonpixel_size) - { return -ENODEV; } -static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, - unsigned int *src, const struct qcom_scm_vmperm *newvm, - unsigned int dest_cnt) { return -ENODEV; } - -static inline bool qcom_scm_ocmem_lock_available(void) { return false; } -static inline int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, - u32 size, u32 mode) { return -ENODEV; } -static inline int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, - u32 offset, u32 size) { return -ENODEV; } - -static inline bool qcom_scm_ice_available(void) { return false; } -static inline int qcom_scm_ice_invalidate_key(u32 index) { return -ENODEV; } -static inline int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size, - enum qcom_scm_ice_cipher cipher, - u32 data_unit_size) { return -ENODEV; } - -static inline bool qcom_scm_hdcp_available(void) { return false; } -static inline int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, - u32 *resp) { return -ENODEV; } - -static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en) - { return -ENODEV; } - -static inline int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val, - u64 limit_node, u32 node_id, u64 version) - { return -ENODEV; } - -static inline int qcom_scm_lmh_profile_change(u32 profile_id) { return -ENODEV; } - -static inline bool qcom_scm_lmh_dcvsh_available(void) { return -ENODEV; } -#endif #endif -- cgit v1.2.3 From 2fbc349911e45d4ea5187b608c8d58db66496260 Mon Sep 17 00:00:00 2001 From: Adam Borowski Date: Sun, 12 Sep 2021 23:26:06 +0200 Subject: asm-generic/io.h: give stub iounmap() on !MMU same prototype as elsewhere It made -Werror sad. Signed-off-by: Adam Borowski Signed-off-by: Arnd Bergmann --- include/asm-generic/io.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index e93375c710b9..dea1d36a6402 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -957,7 +957,7 @@ static inline void __iomem *ioremap(phys_addr_t offset, size_t size) #ifndef iounmap #define iounmap iounmap -static inline void iounmap(void __iomem *addr) +static inline void iounmap(volatile void __iomem *addr) { } #endif -- cgit v1.2.3