From f68a09c7944eca3bdfce2ef18b43dfd2359346b7 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 8 Feb 2017 11:52:29 +0100 Subject: [PATCH 01/17] xfrm: policy: init locks early commit c282222a45cb9503cbfbebfdb60491f06ae84b49 upstream. Dmitry reports following splat: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 0 PID: 13059 Comm: syz-executor1 Not tainted 4.10.0-rc7-next-20170207 #1 [..] spin_lock_bh include/linux/spinlock.h:304 [inline] xfrm_policy_flush+0x32/0x470 net/xfrm/xfrm_policy.c:963 xfrm_policy_fini+0xbf/0x560 net/xfrm/xfrm_policy.c:3041 xfrm_net_init+0x79f/0x9e0 net/xfrm/xfrm_policy.c:3091 ops_init+0x10a/0x530 net/core/net_namespace.c:115 setup_net+0x2ed/0x690 net/core/net_namespace.c:291 copy_net_ns+0x26c/0x530 net/core/net_namespace.c:396 create_new_namespaces+0x409/0x860 kernel/nsproxy.c:106 unshare_nsproxy_namespaces+0xae/0x1e0 kernel/nsproxy.c:205 SYSC_unshare kernel/fork.c:2281 [inline] Problem is that when we get error during xfrm_net_init we will call xfrm_policy_fini which will acquire xfrm_policy_lock before it was initialized. Just move it around so locks get set up first. Reported-by: Dmitry Vyukov Fixes: 283bc9f35bbbcb0e9 ("xfrm: Namespacify xfrm state/policy locks") Signed-off-by: Florian Westphal Signed-off-by: Steffen Klassert Signed-off-by: Greg Kroah-Hartman --- net/xfrm/xfrm_policy.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5bf7e1bfeac7..e0437a7aa1a2 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -3062,6 +3062,11 @@ static int __net_init xfrm_net_init(struct net *net) { int rv; + /* Initialize the per-net locks here */ + spin_lock_init(&net->xfrm.xfrm_state_lock); + spin_lock_init(&net->xfrm.xfrm_policy_lock); + mutex_init(&net->xfrm.xfrm_cfg_mutex); + rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; @@ -3078,11 +3083,6 @@ static int __net_init xfrm_net_init(struct net *net) if (rv < 0) goto out; - /* Initialize the per-net locks here */ - spin_lock_init(&net->xfrm.xfrm_state_lock); - spin_lock_init(&net->xfrm.xfrm_policy_lock); - mutex_init(&net->xfrm.xfrm_cfg_mutex); - return 0; out: From 64a5465799ee40e3d54d9da3037934cd4b7b502f Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Wed, 22 Mar 2017 07:29:31 +0000 Subject: [PATCH 02/17] xfrm_user: validate XFRM_MSG_NEWAE XFRMA_REPLAY_ESN_VAL replay_window commit 677e806da4d916052585301785d847c3b3e6186a upstream. When a new xfrm state is created during an XFRM_MSG_NEWSA call we validate the user supplied replay_esn to ensure that the size is valid and to ensure that the replay_window size is within the allocated buffer. However later it is possible to update this replay_esn via a XFRM_MSG_NEWAE call. There we again validate the size of the supplied buffer matches the existing state and if so inject the contents. We do not at this point check that the replay_window is within the allocated memory. This leads to out-of-bounds reads and writes triggered by netlink packets. This leads to memory corruption and the potential for priviledge escalation. We already attempt to validate the incoming replay information in xfrm_new_ae() via xfrm_replay_verify_len(). This confirms that the user is not trying to change the size of the replay state buffer which includes the replay_esn. It however does not check the replay_window remains within that buffer. Add validation of the contained replay_window. CVE-2017-7184 Signed-off-by: Andy Whitcroft Acked-by: Steffen Klassert Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- net/xfrm/xfrm_user.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 671a1d0333f0..98420bf914ce 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -415,6 +415,9 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen) return -EINVAL; + if (up->replay_window > up->bmp_len * sizeof(__u32) * 8) + return -EINVAL; + return 0; } From 79191ea36dc9be10a9c9b03d6b341ed2d2f76045 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Thu, 23 Mar 2017 07:45:44 +0000 Subject: [PATCH 03/17] xfrm_user: validate XFRM_MSG_NEWAE incoming ESN size harder commit f843ee6dd019bcece3e74e76ad9df0155655d0df upstream. Kees Cook has pointed out that xfrm_replay_state_esn_len() is subject to wrapping issues. To ensure we are correctly ensuring that the two ESN structures are the same size compare both the overall size as reported by xfrm_replay_state_esn_len() and the internal length are the same. CVE-2017-7184 Signed-off-by: Andy Whitcroft Acked-by: Steffen Klassert Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- net/xfrm/xfrm_user.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 98420bf914ce..a7e27e1140dd 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -412,7 +412,11 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es up = nla_data(rp); ulen = xfrm_replay_state_esn_len(up); - if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen) + /* Check the overall length and the internal bitmap length to avoid + * potential overflow. */ + if (nla_len(rp) < ulen || + xfrm_replay_state_esn_len(replay_esn) != ulen || + replay_esn->bmp_len != up->bmp_len) return -EINVAL; if (up->replay_window > up->bmp_len * sizeof(__u32) * 8) From 3e8c6bd9dbc44630199892ad27ef745a45335191 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 27 Mar 2017 17:53:50 +0200 Subject: [PATCH 04/17] KVM: x86: cleanup the page tracking SRCU instance commit 2beb6dad2e8f95d710159d5befb390e4f62ab5cf upstream. SRCU uses a delayed work item. Skip cleaning it up, and the result is use-after-free in the work item callbacks. Reported-by: Dmitry Vyukov Suggested-by: Dmitry Vyukov Fixes: 0eb05bf290cfe8610d9680b49abef37febd1c38a Reviewed-by: Xiao Guangrong Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman --- arch/x86/include/asm/kvm_page_track.h | 1 + arch/x86/kvm/page_track.c | 8 ++++++++ arch/x86/kvm/x86.c | 1 + 3 files changed, 10 insertions(+) diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index c2b8d24a235c..6226cb0eca23 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -35,6 +35,7 @@ struct kvm_page_track_notifier_node { }; void kvm_page_track_init(struct kvm *kvm); +void kvm_page_track_cleanup(struct kvm *kvm); void kvm_page_track_free_memslot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont); diff --git a/arch/x86/kvm/page_track.c b/arch/x86/kvm/page_track.c index b431539c3714..85024e0cfaa5 100644 --- a/arch/x86/kvm/page_track.c +++ b/arch/x86/kvm/page_track.c @@ -156,6 +156,14 @@ bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn, return !!ACCESS_ONCE(slot->arch.gfn_track[mode][index]); } +void kvm_page_track_cleanup(struct kvm *kvm) +{ + struct kvm_page_track_notifier_head *head; + + head = &kvm->arch.track_notifier_head; + cleanup_srcu_struct(&head->track_srcu); +} + void kvm_page_track_init(struct kvm *kvm) { struct kvm_page_track_notifier_head *head; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 731044efb195..e5bc139d1ba7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7976,6 +7976,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_free_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kvm_mmu_uninit_vm(kvm); + kvm_page_track_cleanup(kvm); } void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, From b82b2f930c2b090a51d429664454252c87b45a47 Mon Sep 17 00:00:00 2001 From: Ladi Prosek Date: Thu, 23 Mar 2017 08:04:18 +0100 Subject: [PATCH 05/17] virtio_balloon: init 1st buffer in stats vq commit fc8653228c8588a120f6b5dad6983b7b61ff669e upstream. When init_vqs runs, virtio_balloon.stats is either uninitialized or contains stale values. The host updates its state with garbage data because it has no way of knowing that this is just a marker buffer used for signaling. This patch updates the stats before pushing the initial buffer. Alternative fixes: * Push an empty buffer in init_vqs. Not easily done with the current virtio implementation and violates the spec "Driver MUST supply the same subset of statistics in all buffers submitted to the statsq". * Push a buffer with invalid tags in init_vqs. Violates the same spec clause, plus "invalid tag" is not really defined. Note: the spec says: When using the legacy interface, the device SHOULD ignore all values in the first buffer in the statsq supplied by the driver after device initialization. Note: Historically, drivers supplied an uninitialized buffer in the first buffer. Unfortunately QEMU does not seem to implement the recommendation even for the legacy interface. Signed-off-by: Ladi Prosek Signed-off-by: Michael S. Tsirkin Signed-off-by: Greg Kroah-Hartman --- drivers/virtio/virtio_balloon.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 9d2738e9217f..2c2e6792f7e0 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -427,6 +427,8 @@ static int init_vqs(struct virtio_balloon *vb) * Prime this virtqueue with one buffer so the hypervisor can * use it to signal us later (it can't be broken yet!). */ + update_balloon_stats(vb); + sg_init_one(&sg, vb->stats, sizeof vb->stats); if (virtqueue_add_outbuf(vb->stats_vq, &sg, 1, vb, GFP_KERNEL) < 0) From dd6054234bd82065134f62ca0b5e2695c0d859b7 Mon Sep 17 00:00:00 2001 From: Bjorn Andersson Date: Tue, 14 Mar 2017 08:23:26 -0700 Subject: [PATCH 06/17] pinctrl: qcom: Don't clear status bit on irq_unmask commit a6566710adaa4a7dd5e0d99820ff9c9c30ee5951 upstream. Clearing the status bit on irq_unmask will discard any pending interrupt that did arrive after the irq_ack, i.e. while the IRQ handler function was executing. Fixes: f365be092572 ("pinctrl: Add Qualcomm TLMM driver") Cc: Stephen Boyd Reported-by: Timur Tabi Signed-off-by: Bjorn Andersson Signed-off-by: Linus Walleij Signed-off-by: Greg Kroah-Hartman --- drivers/pinctrl/qcom/pinctrl-msm.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 775c88303017..bedce3453dd3 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -594,10 +594,6 @@ static void msm_gpio_irq_unmask(struct irq_data *d) spin_lock_irqsave(&pctrl->lock, flags); - val = readl(pctrl->regs + g->intr_status_reg); - val &= ~BIT(g->intr_status_bit); - writel(val, pctrl->regs + g->intr_status_reg); - val = readl(pctrl->regs + g->intr_cfg_reg); val |= BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); From d77bd2d6a478468127da79e6920b44c467baaa9e Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 27 Mar 2017 15:10:53 +0100 Subject: [PATCH 07/17] c6x/ptrace: Remove useless PTRACE_SETREGSET implementation commit fb411b837b587a32046dc4f369acb93a10b1def8 upstream. gpr_set won't work correctly and can never have been tested, and the correct behaviour is not clear due to the endianness-dependent task layout. So, just remove it. The core code will now return -EOPNOTSUPPORT when trying to set NT_PRSTATUS on this architecture until/unless a correct implementation is supplied. Signed-off-by: Dave Martin Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/c6x/kernel/ptrace.c | 41 ---------------------------------------- 1 file changed, 41 deletions(-) diff --git a/arch/c6x/kernel/ptrace.c b/arch/c6x/kernel/ptrace.c index 3c494e84444d..a511ac16a8e3 100644 --- a/arch/c6x/kernel/ptrace.c +++ b/arch/c6x/kernel/ptrace.c @@ -69,46 +69,6 @@ static int gpr_get(struct task_struct *target, 0, sizeof(*regs)); } -static int gpr_set(struct task_struct *target, - const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) -{ - int ret; - struct pt_regs *regs = task_pt_regs(target); - - /* Don't copyin TSR or CSR */ - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s, - 0, PT_TSR * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - PT_TSR * sizeof(long), - (PT_TSR + 1) * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s, - (PT_TSR + 1) * sizeof(long), - PT_CSR * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, - PT_CSR * sizeof(long), - (PT_CSR + 1) * sizeof(long)); - if (ret) - return ret; - - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - ®s, - (PT_CSR + 1) * sizeof(long), -1); - return ret; -} - enum c6x_regset { REGSET_GPR, }; @@ -120,7 +80,6 @@ static const struct user_regset c6x_regsets[] = { .size = sizeof(u32), .align = sizeof(u32), .get = gpr_get, - .set = gpr_set }, }; From 616fe993f410c589cd928dfb015ccaf9c931dcc1 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 27 Mar 2017 15:10:54 +0100 Subject: [PATCH 08/17] h8300/ptrace: Fix incorrect register transfer count commit 502585c7555083d4a949c08350306b9ec196779e upstream. regs_set() and regs_get() are vulnerable to an off-by-1 buffer overrun if CONFIG_CPU_H8S is set, since this adds an extra entry to register_offset[] but not to user_regs_struct. So, iterate over user_regs_struct based on its actual size, not based on the length of register_offset[]. Signed-off-by: Dave Martin Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/h8300/kernel/ptrace.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/h8300/kernel/ptrace.c b/arch/h8300/kernel/ptrace.c index 92075544a19a..0dc1c8f622bc 100644 --- a/arch/h8300/kernel/ptrace.c +++ b/arch/h8300/kernel/ptrace.c @@ -95,7 +95,8 @@ static int regs_get(struct task_struct *target, long *reg = (long *)®s; /* build user regs in buffer */ - for (r = 0; r < ARRAY_SIZE(register_offset); r++) + BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0); + for (r = 0; r < sizeof(regs) / sizeof(long); r++) *reg++ = h8300_get_reg(target, r); return user_regset_copyout(&pos, &count, &kbuf, &ubuf, @@ -113,7 +114,8 @@ static int regs_set(struct task_struct *target, long *reg; /* build user regs in buffer */ - for (reg = (long *)®s, r = 0; r < ARRAY_SIZE(register_offset); r++) + BUILD_BUG_ON(sizeof(regs) % sizeof(long) != 0); + for (reg = (long *)®s, r = 0; r < sizeof(regs) / sizeof(long); r++) *reg++ = h8300_get_reg(target, r); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, @@ -122,7 +124,7 @@ static int regs_set(struct task_struct *target, return ret; /* write back to pt_regs */ - for (reg = (long *)®s, r = 0; r < ARRAY_SIZE(register_offset); r++) + for (reg = (long *)®s, r = 0; r < sizeof(regs) / sizeof(long); r++) h8300_put_reg(target, r, *reg++); return 0; } From 0ba34c87f7ce04232295ebf4991cd3ff36ea5abd Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 27 Mar 2017 15:10:58 +0100 Subject: [PATCH 09/17] mips/ptrace: Preserve previous registers for short regset write commit d614fd58a2834cfe4efa472c33c8f3ce2338b09b upstream. Ensure that if userspace supplies insufficient data to PTRACE_SETREGSET to fill all the registers, the thread's old registers are preserved. Signed-off-by: Dave Martin Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/mips/kernel/ptrace.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index a92994d60e91..bf83dc1eecfb 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -485,7 +485,8 @@ static int fpr_set(struct task_struct *target, &target->thread.fpu, 0, sizeof(elf_fpregset_t)); - for (i = 0; i < NUM_FPU_REGS; i++) { + BUILD_BUG_ON(sizeof(fpr_val) != sizeof(elf_fpreg_t)); + for (i = 0; i < NUM_FPU_REGS && count >= sizeof(elf_fpreg_t); i++) { err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpr_val, i * sizeof(elf_fpreg_t), (i + 1) * sizeof(elf_fpreg_t)); From 84b94c4356c668ebe4532b3a999cf375f0089310 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 27 Mar 2017 15:10:59 +0100 Subject: [PATCH 10/17] sparc/ptrace: Preserve previous registers for short regset write commit d3805c546b275c8cc7d40f759d029ae92c7175f2 upstream. Ensure that if userspace supplies insufficient data to PTRACE_SETREGSET to fill all the registers, the thread's old registers are preserved. Signed-off-by: Dave Martin Acked-by: David S. Miller Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/sparc/kernel/ptrace_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/sparc/kernel/ptrace_64.c b/arch/sparc/kernel/ptrace_64.c index ac082dd8c67d..7037ca3b4328 100644 --- a/arch/sparc/kernel/ptrace_64.c +++ b/arch/sparc/kernel/ptrace_64.c @@ -313,7 +313,7 @@ static int genregs64_set(struct task_struct *target, } if (!ret) { - unsigned long y; + unsigned long y = regs->y; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &y, From 2739b4874165acc5ce07e643c363e6768f44cf4f Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 27 Mar 2017 15:10:55 +0100 Subject: [PATCH 11/17] metag/ptrace: Preserve previous registers for short regset write commit a78ce80d2c9178351b34d78fec805140c29c193e upstream. Ensure that if userspace supplies insufficient data to PTRACE_SETREGSET to fill all the registers, the thread's old registers are preserved. Signed-off-by: Dave Martin Acked-by: James Hogan Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/metag/kernel/ptrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c index 7563628822bd..ae659ba61948 100644 --- a/arch/metag/kernel/ptrace.c +++ b/arch/metag/kernel/ptrace.c @@ -303,7 +303,7 @@ static int metag_tls_set(struct task_struct *target, const void *kbuf, const void __user *ubuf) { int ret; - void __user *tls; + void __user *tls = target->thread.tls_ptr; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); if (ret) From 2d6532ceb45bffcc05036f93a0590ffa82c7794f Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 27 Mar 2017 15:10:56 +0100 Subject: [PATCH 12/17] metag/ptrace: Provide default TXSTATUS for short NT_PRSTATUS commit 5fe81fe98123ce41265c65e95d34418d30d005d1 upstream. Ensure that if userspace supplies insufficient data to PTRACE_SETREGSET to fill TXSTATUS, a well-defined default value is used, based on the task's current value. Suggested-by: James Hogan Signed-off-by: Dave Martin Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/metag/kernel/ptrace.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c index ae659ba61948..2e4dfc15abd3 100644 --- a/arch/metag/kernel/ptrace.c +++ b/arch/metag/kernel/ptrace.c @@ -24,6 +24,16 @@ * user_regset definitions. */ +static unsigned long user_txstatus(const struct pt_regs *regs) +{ + unsigned long data = (unsigned long)regs->ctx.Flags; + + if (regs->ctx.SaveMask & TBICTX_CBUF_BIT) + data |= USER_GP_REGS_STATUS_CATCH_BIT; + + return data; +} + int metag_gp_regs_copyout(const struct pt_regs *regs, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) @@ -62,9 +72,7 @@ int metag_gp_regs_copyout(const struct pt_regs *regs, if (ret) goto out; /* TXSTATUS */ - data = (unsigned long)regs->ctx.Flags; - if (regs->ctx.SaveMask & TBICTX_CBUF_BIT) - data |= USER_GP_REGS_STATUS_CATCH_BIT; + data = user_txstatus(regs); ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &data, 4*25, 4*26); if (ret) @@ -119,6 +127,7 @@ int metag_gp_regs_copyin(struct pt_regs *regs, if (ret) goto out; /* TXSTATUS */ + data = user_txstatus(regs); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &data, 4*25, 4*26); if (ret) From 21c95eca627bf63fa56dc19f5fb5fb2a770dadc0 Mon Sep 17 00:00:00 2001 From: Dave Martin Date: Mon, 27 Mar 2017 15:10:57 +0100 Subject: [PATCH 13/17] metag/ptrace: Reject partial NT_METAG_RPIPE writes commit 7195ee3120d878259e8d94a5d9f808116f34d5ea upstream. It's not clear what behaviour is sensible when doing partial write of NT_METAG_RPIPE, so just don't bother. This patch assumes that userspace will never rely on a partial SETREGSET in this case, since it's not clear what should happen anyway. Signed-off-by: Dave Martin Acked-by: James Hogan Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/metag/kernel/ptrace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/metag/kernel/ptrace.c b/arch/metag/kernel/ptrace.c index 2e4dfc15abd3..5e2dc7defd2c 100644 --- a/arch/metag/kernel/ptrace.c +++ b/arch/metag/kernel/ptrace.c @@ -253,6 +253,8 @@ int metag_rp_state_copyin(struct pt_regs *regs, unsigned long long *ptr; int ret, i; + if (count < 4*13) + return -EINVAL; /* Read the entire pipeline before making any changes */ ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &rp, 0, 4*13); From 2984e52c75c657db7901f6189f02e0251ca963c2 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 21 Feb 2017 15:07:11 -0800 Subject: [PATCH 14/17] fscrypt: remove broken support for detecting keyring key revocation commit 1b53cf9815bb4744958d41f3795d5d5a1d365e2d upstream. Filesystem encryption ostensibly supported revoking a keyring key that had been used to "unlock" encrypted files, causing those files to become "locked" again. This was, however, buggy for several reasons, the most severe of which was that when key revocation happened to be detected for an inode, its fscrypt_info was immediately freed, even while other threads could be using it for encryption or decryption concurrently. This could be exploited to crash the kernel or worse. This patch fixes the use-after-free by removing the code which detects the keyring key having been revoked, invalidated, or expired. Instead, an encrypted inode that is "unlocked" now simply remains unlocked until it is evicted from memory. Note that this is no worse than the case for block device-level encryption, e.g. dm-crypt, and it still remains possible for a privileged user to evict unused pages, inodes, and dentries by running 'sync; echo 3 > /proc/sys/vm/drop_caches', or by simply unmounting the filesystem. In fact, one of those actions was already needed anyway for key revocation to work even somewhat sanely. This change is not expected to break any applications. In the future I'd like to implement a real API for fscrypt key revocation that interacts sanely with ongoing filesystem operations --- waiting for existing operations to complete and blocking new operations, and invalidating and sanitizing key material and plaintext from the VFS caches. But this is a hard problem, and for now this bug must be fixed. This bug affected almost all versions of ext4, f2fs, and ubifs encryption, and it was potentially reachable in any kernel configured with encryption support (CONFIG_EXT4_ENCRYPTION=y, CONFIG_EXT4_FS_ENCRYPTION=y, CONFIG_F2FS_FS_ENCRYPTION=y, or CONFIG_UBIFS_FS_ENCRYPTION=y). Note that older kernels did not use the shared fs/crypto/ code, but due to the potential security implications of this bug, it may still be worthwhile to backport this fix to them. Fixes: b7236e21d55f ("ext4 crypto: reorganize how we store keys in the inode") Signed-off-by: Eric Biggers Signed-off-by: Theodore Ts'o Acked-by: Michael Halcrow Signed-off-by: Greg Kroah-Hartman --- fs/crypto/crypto.c | 10 +------- fs/crypto/fname.c | 2 +- fs/crypto/keyinfo.c | 52 +++++++--------------------------------- include/linux/fscrypto.h | 2 -- 4 files changed, 11 insertions(+), 55 deletions(-) diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c index 98f87fe8f186..61cfccea77bc 100644 --- a/fs/crypto/crypto.c +++ b/fs/crypto/crypto.c @@ -352,7 +352,6 @@ EXPORT_SYMBOL(fscrypt_zeroout_range); static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) { struct dentry *dir; - struct fscrypt_info *ci; int dir_has_key, cached_with_key; if (flags & LOOKUP_RCU) @@ -364,18 +363,11 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags) return 0; } - ci = d_inode(dir)->i_crypt_info; - if (ci && ci->ci_keyring_key && - (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED) | - (1 << KEY_FLAG_DEAD)))) - ci = NULL; - /* this should eventually be an flag in d_flags */ spin_lock(&dentry->d_lock); cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY; spin_unlock(&dentry->d_lock); - dir_has_key = (ci != NULL); + dir_has_key = (d_inode(dir)->i_crypt_info != NULL); dput(dir); /* diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c index 9b774f4b50c8..80bb956e14e5 100644 --- a/fs/crypto/fname.c +++ b/fs/crypto/fname.c @@ -350,7 +350,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, fname->disk_name.len = iname->len; return 0; } - ret = get_crypt_info(dir); + ret = fscrypt_get_encryption_info(dir); if (ret && ret != -EOPNOTSUPP) return ret; diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c index 67fb6d8876d0..bb4606368eb1 100644 --- a/fs/crypto/keyinfo.c +++ b/fs/crypto/keyinfo.c @@ -99,6 +99,7 @@ static int validate_user_key(struct fscrypt_info *crypt_info, kfree(full_key_descriptor); if (IS_ERR(keyring_key)) return PTR_ERR(keyring_key); + down_read(&keyring_key->sem); if (keyring_key->type != &key_type_logon) { printk_once(KERN_WARNING @@ -106,11 +107,9 @@ static int validate_user_key(struct fscrypt_info *crypt_info, res = -ENOKEY; goto out; } - down_read(&keyring_key->sem); ukp = user_key_payload(keyring_key); if (ukp->datalen != sizeof(struct fscrypt_key)) { res = -EINVAL; - up_read(&keyring_key->sem); goto out; } master_key = (struct fscrypt_key *)ukp->data; @@ -121,17 +120,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info, "%s: key size incorrect: %d\n", __func__, master_key->size); res = -ENOKEY; - up_read(&keyring_key->sem); goto out; } res = derive_key_aes(ctx->nonce, master_key->raw, raw_key); - up_read(&keyring_key->sem); - if (res) - goto out; - - crypt_info->ci_keyring_key = keyring_key; - return 0; out: + up_read(&keyring_key->sem); key_put(keyring_key); return res; } @@ -173,12 +166,11 @@ static void put_crypt_info(struct fscrypt_info *ci) if (!ci) return; - key_put(ci->ci_keyring_key); crypto_free_skcipher(ci->ci_ctfm); kmem_cache_free(fscrypt_info_cachep, ci); } -int get_crypt_info(struct inode *inode) +int fscrypt_get_encryption_info(struct inode *inode) { struct fscrypt_info *crypt_info; struct fscrypt_context ctx; @@ -188,21 +180,15 @@ int get_crypt_info(struct inode *inode) u8 *raw_key = NULL; int res; + if (inode->i_crypt_info) + return 0; + res = fscrypt_initialize(); if (res) return res; if (!inode->i_sb->s_cop->get_context) return -EOPNOTSUPP; -retry: - crypt_info = ACCESS_ONCE(inode->i_crypt_info); - if (crypt_info) { - if (!crypt_info->ci_keyring_key || - key_validate(crypt_info->ci_keyring_key) == 0) - return 0; - fscrypt_put_encryption_info(inode, crypt_info); - goto retry; - } res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx)); if (res < 0) { @@ -230,7 +216,6 @@ retry: crypt_info->ci_data_mode = ctx.contents_encryption_mode; crypt_info->ci_filename_mode = ctx.filenames_encryption_mode; crypt_info->ci_ctfm = NULL; - crypt_info->ci_keyring_key = NULL; memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor, sizeof(crypt_info->ci_master_key)); @@ -285,14 +270,8 @@ got_key: if (res) goto out; - kzfree(raw_key); - raw_key = NULL; - if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) { - put_crypt_info(crypt_info); - goto retry; - } - return 0; - + if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL) + crypt_info = NULL; out: if (res == -ENOKEY) res = 0; @@ -300,6 +279,7 @@ out: kzfree(raw_key); return res; } +EXPORT_SYMBOL(fscrypt_get_encryption_info); void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) { @@ -317,17 +297,3 @@ void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci) put_crypt_info(ci); } EXPORT_SYMBOL(fscrypt_put_encryption_info); - -int fscrypt_get_encryption_info(struct inode *inode) -{ - struct fscrypt_info *ci = inode->i_crypt_info; - - if (!ci || - (ci->ci_keyring_key && - (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | - (1 << KEY_FLAG_REVOKED) | - (1 << KEY_FLAG_DEAD))))) - return get_crypt_info(inode); - return 0; -} -EXPORT_SYMBOL(fscrypt_get_encryption_info); diff --git a/include/linux/fscrypto.h b/include/linux/fscrypto.h index ff8b11b26f31..f6dfc2950f76 100644 --- a/include/linux/fscrypto.h +++ b/include/linux/fscrypto.h @@ -79,7 +79,6 @@ struct fscrypt_info { u8 ci_filename_mode; u8 ci_flags; struct crypto_skcipher *ci_ctfm; - struct key *ci_keyring_key; u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE]; }; @@ -256,7 +255,6 @@ extern int fscrypt_has_permitted_context(struct inode *, struct inode *); extern int fscrypt_inherit_context(struct inode *, struct inode *, void *, bool); /* keyinfo.c */ -extern int get_crypt_info(struct inode *); extern int fscrypt_get_encryption_info(struct inode *); extern void fscrypt_put_encryption_info(struct inode *, struct fscrypt_info *); From 916c5cfeab400f5260d20dc2e5c8e0ec52e64cfc Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Tue, 24 Jan 2017 15:40:06 +0100 Subject: [PATCH 15/17] sched/rt: Add a missing rescheduling point commit 619bd4a71874a8fd78eb6ccf9f272c5e98bcc7b7 upstream. Since the change in commit: fd7a4bed1835 ("sched, rt: Convert switched_{from, to}_rt() / prio_changed_rt() to balance callbacks") ... we don't reschedule a task under certain circumstances: Lets say task-A, SCHED_OTHER, is running on CPU0 (and it may run only on CPU0) and holds a PI lock. This task is removed from the CPU because it used up its time slice and another SCHED_OTHER task is running. Task-B on CPU1 runs at RT priority and asks for the lock owned by task-A. This results in a priority boost for task-A. Task-B goes to sleep until the lock has been made available. Task-A is already runnable (but not active), so it receives no wake up. The reality now is that task-A gets on the CPU once the scheduler decides to remove the current task despite the fact that a high priority task is enqueued and waiting. This may take a long time. The desired behaviour is that CPU0 immediately reschedules after the priority boost which made task-A the task with the lowest priority. Suggested-by: Peter Zijlstra Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Thomas Gleixner Fixes: fd7a4bed1835 ("sched, rt: Convert switched_{from, to}_rt() prio_changed_rt() to balance callbacks") Link: http://lkml.kernel.org/r/20170124144006.29821-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- kernel/sched/deadline.c | 3 +-- kernel/sched/rt.c | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 37e2449186c4..c95c5122b105 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1729,12 +1729,11 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) #ifdef CONFIG_SMP if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded) queue_push_tasks(rq); -#else +#endif if (dl_task(rq->curr)) check_preempt_curr_dl(rq, p, 0); else resched_curr(rq); -#endif } } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2516b8df6dbb..f139f22ce30d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -2198,10 +2198,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) #ifdef CONFIG_SMP if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded) queue_push_tasks(rq); -#else +#endif /* CONFIG_SMP */ if (p->prio < rq->curr->prio) resched_curr(rq); -#endif /* CONFIG_SMP */ } } From 1dc3a068cc1123cbfb1d6340cfd795bfd453870a Mon Sep 17 00:00:00 2001 From: Bin Liu Date: Fri, 10 Mar 2017 14:43:37 -0600 Subject: [PATCH 16/17] usb: musb: fix possible spinlock deadlock commit bc1e2154542071e3cfe1734b143af9b8bdacf8bd upstream. The DSPS glue calls del_timer_sync() in its musb_platform_disable() implementation, which requires the caller to not hold a lock. But musb_remove() calls musb_platform_disable() will musb->lock held. This could causes spinlock deadlock. So change musb_remove() to call musb_platform_disable() without holds musb->lock. This doesn't impact the musb_platform_disable implementation in other glue drivers. root@am335x-evm:~# modprobe -r musb-dsps [ 126.134879] musb-hdrc musb-hdrc.1: remove, state 1 [ 126.140465] usb usb2: USB disconnect, device number 1 [ 126.146178] usb 2-1: USB disconnect, device number 2 [ 126.416985] musb-hdrc musb-hdrc.1: USB bus 2 deregistered [ 126.423943] [ 126.425525] ====================================================== [ 126.431997] [ INFO: possible circular locking dependency detected ] [ 126.438564] 4.11.0-rc1-00003-g1557f13bca04-dirty #77 Not tainted [ 126.444852] ------------------------------------------------------- [ 126.451414] modprobe/778 is trying to acquire lock: [ 126.456523] (((&glue->timer))){+.-...}, at: [] del_timer_sync+0x0/0xd0 [ 126.464403] [ 126.464403] but task is already holding lock: [ 126.470511] (&(&musb->lock)->rlock){-.-...}, at: [] musb_remove+0x50/0x1 30 [musb_hdrc] [ 126.479965] [ 126.479965] which lock already depends on the new lock. [ 126.479965] [ 126.488531] [ 126.488531] the existing dependency chain (in reverse order) is: [ 126.496368] [ 126.496368] -> #1 (&(&musb->lock)->rlock){-.-...}: [ 126.502968] otg_timer+0x80/0xec [musb_dsps] [ 126.507990] call_timer_fn+0xb4/0x390 [ 126.512372] expire_timers+0xf0/0x1fc [ 126.516754] run_timer_softirq+0x80/0x178 [ 126.521511] __do_softirq+0xc4/0x554 [ 126.525802] irq_exit+0xe8/0x158 [ 126.529735] __handle_domain_irq+0x58/0xb8 [ 126.534583] __irq_usr+0x54/0x80 [ 126.538507] [ 126.538507] -> #0 (((&glue->timer))){+.-...}: [ 126.544636] del_timer_sync+0x40/0xd0 [ 126.549066] musb_remove+0x6c/0x130 [musb_hdrc] [ 126.554370] platform_drv_remove+0x24/0x3c [ 126.559206] device_release_driver_internal+0x14c/0x1e0 [ 126.565225] bus_remove_device+0xd8/0x108 [ 126.569970] device_del+0x1e4/0x308 [ 126.574170] platform_device_del+0x24/0x8c [ 126.579006] platform_device_unregister+0xc/0x20 [ 126.584394] dsps_remove+0x14/0x30 [musb_dsps] [ 126.589595] platform_drv_remove+0x24/0x3c [ 126.594432] device_release_driver_internal+0x14c/0x1e0 [ 126.600450] driver_detach+0x38/0x6c [ 126.604740] bus_remove_driver+0x4c/0xa0 [ 126.609407] SyS_delete_module+0x11c/0x1e4 [ 126.614252] __sys_trace_return+0x0/0x10 Fixes: ea2f35c01d5ea ("usb: musb: Fix sleeping function called from invalid context for hdrc glue") Acked-by: Tony Lindgren Signed-off-by: Bin Liu Signed-off-by: Greg Kroah-Hartman --- drivers/usb/musb/musb_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 338575fb2d27..358feca54945 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2467,8 +2467,8 @@ static int musb_remove(struct platform_device *pdev) pm_runtime_get_sync(musb->controller); musb_host_cleanup(musb); musb_gadget_cleanup(musb); - spin_lock_irqsave(&musb->lock, flags); musb_platform_disable(musb); + spin_lock_irqsave(&musb->lock, flags); musb_generic_disable(musb); spin_unlock_irqrestore(&musb->lock, flags); musb_writeb(musb->mregs, MUSB_DEVCTL, 0); From f6767727467056943bf6d3433ffce0a8b2b05681 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 31 Mar 2017 10:32:02 +0200 Subject: [PATCH 17/17] Linux 4.9.20 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index ba1c6a8e6a70..44960184701a 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 19 +SUBLEVEL = 20 EXTRAVERSION = NAME = Roaring Lionus