From: Maciej W. Rozycki macro@orcam.me.uk

[ Upstream commit 9906890c89e4dbd900ed87ad3040080339a7f411 ]

A SERIAL_8250_16550A_VARIANTS configuration option has been recently defined that lets one request the 8250 driver not to probe for 16550A device features so as to reduce the driver's device startup time in virtual machines.

Some actual hardware devices require these features to have been fully determined however for their driver to work correctly, so define a flag to let drivers request full 16550A feature probing on a device-by-device basis if required regardless of the SERIAL_8250_16550A_VARIANTS option setting chosen.

Fixes: dc56ecb81a0a ("serial: 8250: Support disabling mdelay-filled probes of 16550A variants") Cc: stable@vger.kernel.org # v5.6+ Reported-by: Anders Blomdell anders.blomdell@control.lth.se Signed-off-by: Maciej W. Rozycki macro@orcam.me.uk Link: https://lore.kernel.org/r/alpine.DEB.2.21.2209202357520.41633@angie.orcam.me... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/tty/serial/8250/8250_port.c | 3 ++- include/linux/serial_core.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 8b3756e4bb05..f648fd1d7548 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1023,7 +1023,8 @@ static void autoconfig_16550a(struct uart_8250_port *up) up->port.type = PORT_16550A; up->capabilities |= UART_CAP_FIFO;

- if (!IS_ENABLED(CONFIG_SERIAL_8250_16550A_VARIANTS)) + if (!IS_ENABLED(CONFIG_SERIAL_8250_16550A_VARIANTS) && + !(up->port.flags & UPF_FULL_PROBE)) return;

/* diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h index 59a8caf3230a..6df4c3356ae6 100644 --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -100,7 +100,7 @@ struct uart_icount { __u32 buf_overrun; };

-typedef unsigned int __bitwise upf_t; +typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t;

struct uart_port { @@ -207,6 +207,7 @@ struct uart_port { #define UPF_FIXED_PORT ((__force upf_t) (1 << 29)) #define UPF_DEAD ((__force upf_t) (1 << 30)) #define UPF_IOREMAP ((__force upf_t) (1 << 31)) +#define UPF_FULL_PROBE ((__force upf_t) (1ULL << 32))

#define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK)

From: Sean Christopherson seanjc@google.com

[ Upstream commit 389ab25216c9d09e0d335e764eeeb84c2089614f ]

When preparing controls for vmcs02, grab KVM's desired controls from vmcs01's shadow state instead of recalculating the controls from scratch, or in the secondary execution controls, instead of using the dedicated cache. Calculating secondary exec controls is eye-poppingly expensive due to the guest CPUID checks, hence the dedicated cache, but the other calculations aren't exactly free either.

Explicitly clear several bits (x2APIC, DESC exiting, and load EFER on exit) as appropriate as they may be set in vmcs01, whereas the previous implementation relied on dynamic bits being cleared in the calculator.

Intentionally propagate VM_{ENTRY,EXIT}_LOAD_IA32_PERF_GLOBAL_CTRL from vmcs01 to vmcs02. Whether or not PERF_GLOBAL_CTRL is loaded depends on whether or not perf itself is active, so unless perf stops between the exit from L1 and entry to L2, vmcs01 will hold the desired value. This is purely an optimization as atomic_switch_perf_msrs() will set/clear the control as needed at VM-Enter, i.e. it avoids two extra VMWRITEs in the case where perf is active (versus starting with the bits clear in vmcs02, which was the previous behavior).

Cc: Zeng Guang guang.zeng@intel.com Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20210810171952.2758100-3-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Stable-dep-of: def9d705c05e ("KVM: nVMX: Don't propagate vmcs12's PERF_GLOBAL_CTRL settings to vmcs02") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/vmx/nested.c | 25 ++++++++++++++++--------- arch/x86/kvm/vmx/vmx.h | 6 +++++- 2 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 7f15e2b2a0d6..2395387945a8 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2232,7 +2232,8 @@ static void prepare_vmcs02_early_rare(struct vcpu_vmx *vmx, } }

-static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) +static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs01, + struct vmcs12 *vmcs12) { u32 exec_control, vmcs12_exec_ctrl; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); @@ -2243,7 +2244,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) /* * PIN CONTROLS */ - exec_control = vmx_pin_based_exec_ctrl(vmx); + exec_control = __pin_controls_get(vmcs01); exec_control |= (vmcs12->pin_based_vm_exec_control & ~PIN_BASED_VMX_PREEMPTION_TIMER);

@@ -2258,7 +2259,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) /* * EXEC CONTROLS */ - exec_control = vmx_exec_control(vmx); /* L0's desires */ + exec_control = __exec_controls_get(vmcs01); /* L0's desires */ exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING; exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING; exec_control &= ~CPU_BASED_TPR_SHADOW; @@ -2295,17 +2296,20 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * SECONDARY EXEC CONTROLS */ if (cpu_has_secondary_exec_ctrls()) { - exec_control = vmx->secondary_exec_control; + exec_control = __secondary_exec_controls_get(vmcs01);

/* Take the following fields only from vmcs12 */ exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | SECONDARY_EXEC_ENABLE_INVPCID | SECONDARY_EXEC_ENABLE_RDTSCP | SECONDARY_EXEC_XSAVES | SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_APIC_REGISTER_VIRT | - SECONDARY_EXEC_ENABLE_VMFUNC); + SECONDARY_EXEC_ENABLE_VMFUNC | + SECONDARY_EXEC_DESC); + if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) { vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control & @@ -2342,8 +2346,9 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * on the related bits (if supported by the CPU) in the hope that * we can avoid VMWrites during vmx_set_efer(). */ - exec_control = (vmcs12->vm_entry_controls | vmx_vmentry_ctrl()) & - ~VM_ENTRY_IA32E_MODE & ~VM_ENTRY_LOAD_IA32_EFER; + exec_control = __vm_entry_controls_get(vmcs01); + exec_control |= vmcs12->vm_entry_controls; + exec_control &= ~(VM_ENTRY_IA32E_MODE | VM_ENTRY_LOAD_IA32_EFER); if (cpu_has_load_ia32_efer()) { if (guest_efer & EFER_LMA) exec_control |= VM_ENTRY_IA32E_MODE; @@ -2359,9 +2364,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER * bits may be modified by vmx_set_efer() in prepare_vmcs02(). */ - exec_control = vmx_vmexit_ctrl(); + exec_control = __vm_exit_controls_get(vmcs01); if (cpu_has_load_ia32_efer() && guest_efer != host_efer) exec_control |= VM_EXIT_LOAD_IA32_EFER; + else + exec_control &= ~VM_EXIT_LOAD_IA32_EFER; vm_exit_controls_set(vmx, exec_control);

/* @@ -3370,7 +3377,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,

vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);

- prepare_vmcs02_early(vmx, vmcs12); + prepare_vmcs02_early(vmx, &vmx->vmcs01, vmcs12);

if (from_vmentry) { if (unlikely(!nested_get_vmcs12_pages(vcpu))) { diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 24903f05c204..ed4b6da83aa8 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -386,9 +386,13 @@ static inline void lname##_controls_set(struct vcpu_vmx *vmx, u32 val) \ vmx->loaded_vmcs->controls_shadow.lname = val; \ } \ } \ +static inline u32 __##lname##_controls_get(struct loaded_vmcs *vmcs) \ +{ \ + return vmcs->controls_shadow.lname; \ +} \ static inline u32 lname##_controls_get(struct vcpu_vmx *vmx) \ { \ - return vmx->loaded_vmcs->controls_shadow.lname; \ + return __##lname##_controls_get(vmx->loaded_vmcs); \ } \ static inline void lname##_controls_setbit(struct vcpu_vmx *vmx, u32 val) \ { \

From: Sean Christopherson seanjc@google.com

[ Upstream commit a61d7c5432ac5a953bbcec17af031661c2bd201d ]

Trace exceptions that are re-injected, not just those that KVM is injecting for the first time. Debugging re-injection bugs is painful enough as is, not having visibility into what KVM is doing only makes things worse.

Delay propagating pending=>injected in the non-reinjection path so that the tracing can properly identify reinjected exceptions.

Signed-off-by: Sean Christopherson seanjc@google.com Reviewed-by: Maxim Levitsky mlevitsk@redhat.com Signed-off-by: Maciej S. Szmigiero maciej.szmigiero@oracle.com Message-Id: 25470690a38b4d2b32b6204875dd35676c65c9f2.1651440202.git.maciej.szmigiero@oracle.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Stable-dep-of: 5623f751bd9c ("KVM: x86: Treat #DBs from the emulator as fault-like (code and DR7.GD=1)") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/trace.h | 12 ++++++++---- arch/x86/kvm/x86.c | 16 +++++++++------- 2 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index a2835d784f4b..3d4988ea8b57 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -304,25 +304,29 @@ TRACE_EVENT(kvm_inj_virq, * Tracepoint for kvm interrupt injection: */ TRACE_EVENT(kvm_inj_exception, - TP_PROTO(unsigned exception, bool has_error, unsigned error_code), - TP_ARGS(exception, has_error, error_code), + TP_PROTO(unsigned exception, bool has_error, unsigned error_code, + bool reinjected), + TP_ARGS(exception, has_error, error_code, reinjected),

TP_STRUCT__entry( __field( u8, exception ) __field( u8, has_error ) __field( u32, error_code ) + __field( bool, reinjected ) ),

TP_fast_assign( __entry->exception = exception; __entry->has_error = has_error; __entry->error_code = error_code; + __entry->reinjected = reinjected; ),

- TP_printk("%s (0x%x)", + TP_printk("%s (0x%x)%s", __print_symbolic(__entry->exception, kvm_trace_sym_exc), /* FIXME: don't print error_code if not present */ - __entry->has_error ? __entry->error_code : 0) + __entry->has_error ? __entry->error_code : 0, + __entry->reinjected ? " [reinjected]" : "") );

/* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f3473418dcd5..17bb3d0e2d13 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -8347,6 +8347,11 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)

static void kvm_inject_exception(struct kvm_vcpu *vcpu) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code, + vcpu->arch.exception.injected); + if (vcpu->arch.exception.error_code && !is_protmode(vcpu)) vcpu->arch.exception.error_code = false; kvm_x86_ops.queue_exception(vcpu); @@ -8404,13 +8409,6 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit

/* try to inject new event if pending */ if (vcpu->arch.exception.pending) { - trace_kvm_inj_exception(vcpu->arch.exception.nr, - vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); - - vcpu->arch.exception.pending = false; - vcpu->arch.exception.injected = true; - if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT) __kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) | X86_EFLAGS_RF); @@ -8424,6 +8422,10 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit }

kvm_inject_exception(vcpu); + + vcpu->arch.exception.pending = false; + vcpu->arch.exception.injected = true; + can_inject = false; }

From: Yazen Ghannam yazen.ghannam@amd.com

[ Upstream commit cb09a379724d299c603a7a79f444f52a9a75b8d2 ]

CPUID Leaf 0x1F defines a DIE_TYPE level (nb: ECX[8:15] level type == 0x5), but CPUID Leaf 0xB does not. However, detect_extended_topology() will set struct cpuinfo_x86.cpu_die_id regardless of whether a valid Die ID was found.

Only set cpu_die_id if a DIE_TYPE level is found. CPU topology code may use another value for cpu_die_id, e.g. the AMD NodeId on AMD-based systems. Code ordering should be maintained so that the CPUID Leaf 0x1F Die ID value will take precedence on systems that may use another value.

Suggested-by: Borislav Petkov bp@alien8.de Signed-off-by: Yazen Ghannam yazen.ghannam@amd.com Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20201109210659.754018-5-Yazen.Ghannam@amd.com Stable-dep-of: 2b12a7a126d6 ("x86/topology: Fix multiple packages shown on a single-package system") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/topology.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 91288da29599..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width; unsigned int core_select_mask, core_level_siblings; unsigned int die_select_mask, die_level_siblings; + bool die_level_present = false; int leaf;

leaf = detect_extended_topology_leaf(c); @@ -126,6 +127,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) { + die_level_present = true; die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); } @@ -139,8 +141,12 @@ int detect_extended_topology(struct cpuinfo_x86 *c)

c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width) & core_select_mask; - c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, - core_plus_mask_width) & die_select_mask; + + if (die_level_present) { + c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, + core_plus_mask_width) & die_select_mask; + } + c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, die_plus_mask_width); /*

From: Zhang Rui rui.zhang@intel.com

[ Upstream commit 71eac7063698b7d7b8fafb1683ac24a034541141 ]

Today, core ID is assumed to be unique within each package.

But an AlderLake-N platform adds a Module level between core and package, Linux excludes the unknown modules bits from the core ID, resulting in duplicate core ID's.

To keep core ID unique within a package, Linux must include all APIC-ID bits for known or unknown levels above the core and below the package in the core ID.

It is important to understand that core ID's have always come directly from the APIC-ID encoding, which comes from the BIOS. Thus there is no guarantee that they start at 0, or that they are contiguous. As such, naively using them for array indexes can be problematic.

[ dhansen: un-known -> unknown ]

Fixes: 7745f03eb395 ("x86/topology: Add CPUID.1F multi-die/package support") Suggested-by: Len Brown len.brown@intel.com Signed-off-by: Zhang Rui rui.zhang@intel.com Signed-off-by: Dave Hansen dave.hansen@linux.intel.com Reviewed-by: Len Brown len.brown@intel.com Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20221014090147.1836-5-rui.zhang@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/topology.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 696309749d62..37d48ab3d077 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -141,7 +141,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) sub_index++; }

- core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width; + core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width; die_select_mask = (~(-1 << die_plus_mask_width)) >> core_plus_mask_width;

From: Alexander Graf graf@amazon.com

[ Upstream commit 2e3272bc1790825c43d2c39690bf2836b81c6d36 ]

In the next patch we want to introduce a second caller to set_msr_filter() which constructs its own filter list on the stack. Refactor the original function so it takes it as argument instead of reading it through copy_from_user().

Signed-off-by: Alexander Graf graf@amazon.com Message-Id: 20221017184541.2658-3-graf@amazon.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kvm/x86.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ed8efd402d05..be4326b143e1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5446,26 +5446,22 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, return r; }

-static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) +static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, + struct kvm_msr_filter *filter) { - struct kvm_msr_filter __user *user_msr_filter = argp; struct kvm_x86_msr_filter *new_filter, *old_filter; - struct kvm_msr_filter filter; bool default_allow; bool empty = true; int r = 0; u32 i;

- if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) - return -EFAULT; - - if (filter.flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) return -EINVAL;

- for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) - empty &= !filter.ranges[i].nmsrs; + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) + empty &= !filter->ranges[i].nmsrs;

- default_allow = !(filter.flags & KVM_MSR_FILTER_DEFAULT_DENY); + default_allow = !(filter->flags & KVM_MSR_FILTER_DEFAULT_DENY); if (empty && !default_allow) return -EINVAL;

@@ -5473,8 +5469,8 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, void __user *argp) if (!new_filter) return -ENOMEM;

- for (i = 0; i < ARRAY_SIZE(filter.ranges); i++) { - r = kvm_add_msr_filter(new_filter, &filter.ranges[i]); + for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) { + r = kvm_add_msr_filter(new_filter, &filter->ranges[i]); if (r) { kvm_free_msr_filter(new_filter); return r; @@ -5803,9 +5799,16 @@ long kvm_arch_vm_ioctl(struct file *filp, case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; - case KVM_X86_SET_MSR_FILTER: - r = kvm_vm_ioctl_set_msr_filter(kvm, argp); + case KVM_X86_SET_MSR_FILTER: { + struct kvm_msr_filter __user *user_msr_filter = argp; + struct kvm_msr_filter filter; + + if (copy_from_user(&filter, user_msr_filter, sizeof(filter))) + return -EFAULT; + + r = kvm_vm_ioctl_set_msr_filter(kvm, &filter); break; + } default: r = -ENOTTY; }

From: Håkon Bugge haakon.bugge@oracle.com

[ Upstream commit eb83f502adb036cd56c27e13b9ca3b2aabfa790b ]

Commit 27cfde795a96 ("RDMA/cma: Fix arguments order in net device validation") swapped the src and dst addresses in the call to validate_net_dev().

As a consequence, the test in validate_ipv4_net_dev() to see if the net_dev is the right one, is incorrect for port 1 <-> 2 communication when the ports are on the same sub-net. This is fixed by denoting the flowi4_oif as the device instead of the incoming one.

The bug has not been observed using IPv6 addresses.

Fixes: 27cfde795a96 ("RDMA/cma: Fix arguments order in net device validation") Signed-off-by: Håkon Bugge haakon.bugge@oracle.com Link: https://lore.kernel.org/r/20221012141542.16925-1-haakon.bugge@oracle.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/core/cma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index b5fa19a033c0..9ed5de38e372 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1437,7 +1437,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev, return false;

memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_iif = net_dev->ifindex; + fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr;

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 1ba04394e028ea8b45d92685cc0d6ab582cf7647 ]

If the server reboots while we are engaged in a delegation return, and there is a pNFS layout with return-on-close set, then the current code can end up deadlocking in pnfs_roc() when nfs_inode_set_delegation() tries to return the old delegation. Now that delegreturn actually uses its own copy of the stateid, it should be safe to just always update the delegation stateid in place.

Fixes: 078000d02d57 ("pNFS: We want return-on-close to complete when evicting the inode") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/delegation.c | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-)

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index d6ac2c4f88b6..1eb6c7a142ff 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -228,8 +228,7 @@ static int nfs_delegation_claim_opens(struct inode *inode, * */ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, - fmode_t type, - const nfs4_stateid *stateid, + fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) { struct nfs_delegation *delegation; @@ -239,25 +238,24 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation != NULL) { spin_lock(&delegation->lock); - if (nfs4_is_valid_delegation(delegation, 0)) { - nfs4_stateid_copy(&delegation->stateid, stateid); - delegation->type = type; - delegation->pagemod_limit = pagemod_limit; - oldcred = delegation->cred; - delegation->cred = get_cred(cred); - clear_bit(NFS_DELEGATION_NEED_RECLAIM, - &delegation->flags); - spin_unlock(&delegation->lock); - rcu_read_unlock(); - put_cred(oldcred); - trace_nfs4_reclaim_delegation(inode, type); - return; - } - /* We appear to have raced with a delegation return. */ + nfs4_stateid_copy(&delegation->stateid, stateid); + delegation->type = type; + delegation->pagemod_limit = pagemod_limit; + oldcred = delegation->cred; + delegation->cred = get_cred(cred); + clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); + if (test_and_clear_bit(NFS_DELEGATION_REVOKED, + &delegation->flags)) + atomic_long_inc(&nfs_active_delegations); spin_unlock(&delegation->lock); + rcu_read_unlock(); + put_cred(oldcred); + trace_nfs4_reclaim_delegation(inode, type); + } else { + rcu_read_unlock(); + nfs_inode_set_delegation(inode, cred, type, stateid, + pagemod_limit); } - rcu_read_unlock(); - nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit); }

static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit e59679f2b7e522ecad99974e5636291ffd47c184 ]

Currently, we are only guaranteed to send RECLAIM_COMPLETE if we have open state to recover. Fix the client to always send RECLAIM_COMPLETE after setting up the lease.

Fixes: fce5c838e133 ("nfs41: RECLAIM_COMPLETE functionality") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Anna Schumaker Anna.Schumaker@Netapp.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfs/nfs4state.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index cd9e84ab3dd7..a77a3d8c0b3f 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1777,6 +1777,7 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp,

static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) { + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); /* Mark all delegations for reclaim */ nfs_delegation_mark_reclaim(clp); nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot);

From: Chen Zhongjin chenzhongjin@huawei.com

[ Upstream commit 633efc8b3dc96f56f5a57f2a49764853a2fa3f50 ]

kmemleak reported memory leaks in dsa_loop_init():

kmemleak: 12 new suspected memory leaks

unreferenced object 0xffff8880138ce000 (size 2048): comm "modprobe", pid 390, jiffies 4295040478 (age 238.976s) backtrace: [<000000006a94f1d5>] kmalloc_trace+0x26/0x60 [<00000000a9c44622>] phy_device_create+0x5d/0x970 [<00000000d0ee2afc>] get_phy_device+0xf3/0x2b0 [<00000000dca0c71f>] __fixed_phy_register.part.0+0x92/0x4e0 [<000000008a834798>] fixed_phy_register+0x84/0xb0 [<0000000055223fcb>] dsa_loop_init+0xa9/0x116 [dsa_loop] ...

There are two reasons for memleak in dsa_loop_init().

First, fixed_phy_register() create and register phy_device:

fixed_phy_register() get_phy_device() phy_device_create() # freed by phy_device_free() phy_device_register() # freed by phy_device_remove()

But fixed_phy_unregister() only calls phy_device_remove(). So the memory allocated in phy_device_create() is leaked.

Second, when mdio_driver_register() fail in dsa_loop_init(), it just returns and there is no cleanup for phydevs.

Fix the problems by catching the error of mdio_driver_register() in dsa_loop_init(), then calling both fixed_phy_unregister() and phy_device_free() to release phydevs. Also add a function for phydevs cleanup to avoid duplacate.

Fixes: 98cd1552ea27 ("net: dsa: Mock-up driver") Signed-off-by: Chen Zhongjin chenzhongjin@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/dsa_loop.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index e38906ae8f23..fbeb99ab9e4d 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -376,6 +376,17 @@ static struct mdio_driver dsa_loop_drv = {

#define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2)

+static void dsa_loop_phydevs_unregister(void) +{ + unsigned int i; + + for (i = 0; i < NUM_FIXED_PHYS; i++) + if (!IS_ERR(phydevs[i])) { + fixed_phy_unregister(phydevs[i]); + phy_device_free(phydevs[i]); + } +} + static int __init dsa_loop_init(void) { struct fixed_phy_status status = { @@ -383,23 +394,23 @@ static int __init dsa_loop_init(void) .speed = SPEED_100, .duplex = DUPLEX_FULL, }; - unsigned int i; + unsigned int i, ret;

for (i = 0; i < NUM_FIXED_PHYS; i++) phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL);

- return mdio_driver_register(&dsa_loop_drv); + ret = mdio_driver_register(&dsa_loop_drv); + if (ret) + dsa_loop_phydevs_unregister(); + + return ret; } module_init(dsa_loop_init);

static void __exit dsa_loop_exit(void) { - unsigned int i; - mdio_driver_unregister(&dsa_loop_drv); - for (i = 0; i < NUM_FIXED_PHYS; i++) - if (!IS_ERR(phydevs[i])) - fixed_phy_unregister(phydevs[i]); + dsa_loop_phydevs_unregister(); } module_exit(dsa_loop_exit);

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit 7a47e077e503feb73d56e491ce89aa73b67a3972 ]

Add a check for if create_singlethread_workqueue() fails and also destroy the work queue on failure paths.

Fixes: e411e0587e0d ("RDMA/qedr: Add iWARP connection management functions") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Link: https://lore.kernel.org/r/Y1gBkDucQhhWj5YM@kili Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/qedr/main.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 967641662b24..d0bb61b7e419 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -374,6 +374,10 @@ static int qedr_alloc_resources(struct qedr_dev *dev) if (IS_IWARP(dev)) { xa_init(&dev->qps); dev->iwarp_wq = create_singlethread_workqueue("qedr_iwarpq"); + if (!dev->iwarp_wq) { + rc = -ENOMEM; + goto err1; + } }

/* Allocate Status blocks for CNQ */ @@ -381,7 +385,7 @@ static int qedr_alloc_resources(struct qedr_dev *dev) GFP_KERNEL); if (!dev->sb_array) { rc = -ENOMEM; - goto err1; + goto err_destroy_wq; }

dev->cnq_array = kcalloc(dev->num_cnq, @@ -432,6 +436,9 @@ static int qedr_alloc_resources(struct qedr_dev *dev) kfree(dev->cnq_array); err2: kfree(dev->sb_array); +err_destroy_wq: + if (IS_IWARP(dev)) + destroy_workqueue(dev->iwarp_wq); err1: kfree(dev->sgid_tbl); return rc;

From: Shang XiaoJing shangxiaojing@huawei.com

[ Upstream commit 8e4aae6b8ca76afb1fb64dcb24be44ba814e7f8a ]

fdp_nci_send() will call fdp_nci_i2c_write that will not free skb in the function. As a result, when fdp_nci_i2c_write() finished, the skb will memleak. fdp_nci_send() should free skb after fdp_nci_i2c_write() finished.

Fixes: a06347c04c13 ("NFC: Add Intel Fields Peak NFC solution driver") Signed-off-by: Shang XiaoJing shangxiaojing@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/fdp/fdp.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index 52c60d11849c..90bea6a1db69 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -252,11 +252,19 @@ static int fdp_nci_close(struct nci_dev *ndev) static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); + int ret;

if (atomic_dec_and_test(&info->data_pkt_counter)) info->data_pkt_counter_cb(ndev);

- return info->phy_ops->write(info->phy, skb); + ret = info->phy_ops->write(info->phy, skb); + if (ret < 0) { + kfree_skb(skb); + return ret; + } + + consume_skb(skb); + return 0; }

static int fdp_nci_request_firmware(struct nci_dev *ndev)

From: Shang XiaoJing shangxiaojing@huawei.com

[ Upstream commit 3a146b7e3099dc7cf3114f627d9b79291e2d2203 ]

s3fwrn5_nci_send() will call s3fwrn5_i2c_write() or s3fwrn82_uart_write(), and free the skb if write() failed. However, even if the write() run succeeds, the skb will not be freed in write(). As the result, the skb will memleak. s3fwrn5_nci_send() should also free the skb when write() succeeds.

Fixes: c04c674fadeb ("nfc: s3fwrn5: Add driver for Samsung S3FWRN5 NFC Chip") Signed-off-by: Shang XiaoJing shangxiaojing@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/s3fwrn5/core.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index ba6c486d6465..9b43cd3a45af 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -97,11 +97,15 @@ static int s3fwrn5_nci_send(struct nci_dev *ndev, struct sk_buff *skb) }

ret = s3fwrn5_write(info, skb); - if (ret < 0) + if (ret < 0) { kfree_skb(skb); + mutex_unlock(&info->mutex); + return ret; + }

+ consume_skb(skb); mutex_unlock(&info->mutex); - return ret; + return 0; }

static int s3fwrn5_nci_post_setup(struct nci_dev *ndev)

From: Shang XiaoJing shangxiaojing@huawei.com

[ Upstream commit 93d904a734a74c54d945a9884b4962977f1176cd ]

nfcmrvl_i2c_nci_send() will be called by nfcmrvl_nci_send(), and skb should be freed in nfcmrvl_i2c_nci_send(). However, nfcmrvl_nci_send() will only free skb when i2c_master_send() return >=0, which means skb will memleak when i2c_master_send() failed. Free skb no matter whether i2c_master_send() succeeds.

Fixes: b5b3e23e4cac ("NFC: nfcmrvl: add i2c driver") Signed-off-by: Shang XiaoJing shangxiaojing@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nfc/nfcmrvl/i2c.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index f81f1cae9324..41f27e1cac20 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -151,10 +151,15 @@ static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv, ret = -EREMOTEIO; } else ret = 0; + } + + if (ret) { kfree_skb(skb); + return ret; }

- return ret; + consume_skb(skb); + return 0; }

static void nfcmrvl_i2c_nci_update_config(struct nfcmrvl_private *priv,

From: Sergey Shtylyov s.shtylyov@omp.ru

[ Upstream commit 171a93182eccd6e6835d2c86b40787f9f832efaa ]

Clang gives a warning when compiling pata_legacy.c with 'make W=1' about the 'rt' local variable in pdc20230_set_piomode() being set but unused. Quite obviously, there is an outb() call missing to write back the updated variable. Moreover, checking the docs by Petr Soucek revealed that bitwise AND should have been done with a negated timing mask and the master/slave timing masks were swapped while updating...

Fixes: 669a5db411d8 ("[libata] Add a bunch of PATA drivers.") Reported-by: Damien Le Moal damien.lemoal@opensource.wdc.com Signed-off-by: Sergey Shtylyov s.shtylyov@omp.ru Signed-off-by: Damien Le Moal damien.lemoal@opensource.wdc.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/ata/pata_legacy.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index d91ba47f2fc4..4405d255e3aa 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -278,9 +278,10 @@ static void pdc20230_set_piomode(struct ata_port *ap, struct ata_device *adev) outb(inb(0x1F4) & 0x07, 0x1F4);

rt = inb(0x1F3); - rt &= 0x07 << (3 * adev->devno); + rt &= ~(0x07 << (3 * !adev->devno)); if (pio) - rt |= (1 + 3 * pio) << (3 * adev->devno); + rt |= (1 + 3 * pio) << (3 * !adev->devno); + outb(rt, 0x1F3);

udelay(100); outb(inb(0x1F2) | 0x01, 0x1F2);

From: Ziyang Xuan william.xuanziyang@huawei.com

[ Upstream commit 363a5328f4b0517e59572118ccfb7c626d81dca9 ]

Recently, we got two syzkaller problems because of oversize packet when napi frags enabled.

One of the problems is because the first seg size of the iov_iter from user space is very big, it is 2147479538 which is bigger than the threshold value for bail out early in __alloc_pages(). And skb->pfmemalloc is true, __kmalloc_reserve() would use pfmemalloc reserves without __GFP_NOWARN flag. Thus we got a warning as following:

======================================================== WARNING: CPU: 1 PID: 17965 at mm/page_alloc.c:5295 __alloc_pages+0x1308/0x16c4 mm/page_alloc.c:5295 ... Call trace: __alloc_pages+0x1308/0x16c4 mm/page_alloc.c:5295 __alloc_pages_node include/linux/gfp.h:550 [inline] alloc_pages_node include/linux/gfp.h:564 [inline] kmalloc_large_node+0x94/0x350 mm/slub.c:4038 __kmalloc_node_track_caller+0x620/0x8e4 mm/slub.c:4545 __kmalloc_reserve.constprop.0+0x1e4/0x2b0 net/core/skbuff.c:151 pskb_expand_head+0x130/0x8b0 net/core/skbuff.c:1654 __skb_grow include/linux/skbuff.h:2779 [inline] tun_napi_alloc_frags+0x144/0x610 drivers/net/tun.c:1477 tun_get_user+0x31c/0x2010 drivers/net/tun.c:1835 tun_chr_write_iter+0x98/0x100 drivers/net/tun.c:2036

The other problem is because odd IPv6 packets without NEXTHDR_NONE extension header and have big packet length, it is 2127925 which is bigger than ETH_MAX_MTU(65535). After ipv6_gso_pull_exthdrs() in ipv6_gro_receive(), network_header offset and transport_header offset are all bigger than U16_MAX. That would trigger skb->network_header and skb->transport_header overflow error, because they are all '__u16' type. Eventually, it would affect the value for __skb_push(skb, value), and make it be a big value. After __skb_push() in ipv6_gro_receive(), skb->data would less than skb->head, an out of bounds memory bug occurred. That would trigger the problem as following:

================================================================== BUG: KASAN: use-after-free in eth_type_trans+0x100/0x260 ... Call trace: dump_backtrace+0xd8/0x130 show_stack+0x1c/0x50 dump_stack_lvl+0x64/0x7c print_address_description.constprop.0+0xbc/0x2e8 print_report+0x100/0x1e4 kasan_report+0x80/0x120 __asan_load8+0x78/0xa0 eth_type_trans+0x100/0x260 napi_gro_frags+0x164/0x550 tun_get_user+0xda4/0x1270 tun_chr_write_iter+0x74/0x130 do_iter_readv_writev+0x130/0x1ec do_iter_write+0xbc/0x1e0 vfs_writev+0x13c/0x26c

To fix the problems, restrict the packet size less than (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN) which has considered reserved skb space in napi_alloc_skb() because transport_header is an offset from skb->head. Add len check in tun_napi_alloc_frags() simply.

Fixes: 90e33d459407 ("tun: enable napi_gro_frags() for TUN/TAP driver") Signed-off-by: Ziyang Xuan william.xuanziyang@huawei.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20221029094101.1653855-1-william.xuanziyang@huawei... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/tun.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a643b2f2f4de..0c09f8e9d383 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1475,7 +1475,8 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, int err; int i;

- if (it->nr_segs > MAX_SKB_FRAGS + 1) + if (it->nr_segs > MAX_SKB_FRAGS + 1 || + len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE);

local_bh_disable();

From: Jason A. Donenfeld Jason@zx2c4.com

[ Upstream commit 5c26159c97b324dc5174a5713eafb8c855cf8106 ]

The `char` type with no explicit sign is sometimes signed and sometimes unsigned. This code will break on platforms such as arm, where char is unsigned. So mark it here as explicitly signed, so that the todrop_counter decrement and subsequent comparison is correct.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Jason A. Donenfeld Jason@zx2c4.com Acked-by: Julian Anastasov ja@ssi.bg Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/ipvs/ip_vs_conn.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index fb67f1ca2495..db13288fddfa 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1265,8 +1265,8 @@ static inline int todrop_entry(struct ip_vs_conn *cp) * The drop rate array needs tuning for real environments. * Called from timer bh only => no locking */ - static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; - static char todrop_counter[9] = {0}; + static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; + static signed char todrop_counter[9] = {0}; int i;

/* if the conn entry hasn't lasted for 60 seconds, don't drop it.

From: Zhengchao Shao shaozhengchao@huawei.com

[ Upstream commit 5663ed63adb9619c98ab7479aa4606fa9b7a548c ]

During the initialization of ip_vs_app_net_init(), if file ip_vs_app fails to be created, the initialization is successful by default. Therefore, the ip_vs_app file doesn't be found during the remove in ip_vs_app_net_cleanup(). It will cause WRNING.

The following is the stack information: name 'ip_vs_app' WARNING: CPU: 1 PID: 9 at fs/proc/generic.c:712 remove_proc_entry+0x389/0x460 Modules linked in: Workqueue: netns cleanup_net RIP: 0010:remove_proc_entry+0x389/0x460 Call Trace: <TASK> ops_exit_list+0x125/0x170 cleanup_net+0x4ea/0xb00 process_one_work+0x9bf/0x1710 worker_thread+0x665/0x1080 kthread+0x2e4/0x3a0 ret_from_fork+0x1f/0x30 </TASK>

Fixes: 457c4cbc5a3d ("[NET]: Make /proc/net per network namespace") Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com Acked-by: Julian Anastasov ja@ssi.bg Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/ipvs/ip_vs_app.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index f9b16f2b2219..fdacbc3c15be 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -599,13 +599,19 @@ static const struct seq_operations ip_vs_app_seq_ops = { int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->app_list); - proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops, - sizeof(struct seq_net_private)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, + &ip_vs_app_seq_ops, + sizeof(struct seq_net_private))) + return -ENOMEM; +#endif return 0; }

void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { unregister_ip_vs_app(ipvs, NULL /* all */); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_app", ipvs->net->proc_net); +#endif }

From: Yang Yingliang yangyingliang@huawei.com

[ Upstream commit e7d1d4d9ac0dfa40be4c2c8abd0731659869b297 ]

Afer commit 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array"), the name of device is allocated dynamically, add put_device() to give up the reference, so that the name can be freed in kobject_cleanup() when the refcount is 0.

Set device class before put_device() to avoid null release() function WARN message in device_release().

Fixes: 1fa5ae857bb1 ("driver core: get rid of struct device's bus_id string array") Signed-off-by: Yang Yingliang yangyingliang@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/isdn/mISDN/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c index a41b4b264594..7ea0100f218a 100644 --- a/drivers/isdn/mISDN/core.c +++ b/drivers/isdn/mISDN/core.c @@ -233,11 +233,12 @@ mISDN_register_device(struct mISDNdevice *dev, if (debug & DEBUG_CORE) printk(KERN_DEBUG "mISDN_register %s %d\n", dev_name(&dev->dev), dev->id); + dev->dev.class = &mISDN_class; + err = create_stack(dev); if (err) goto error1;

- dev->dev.class = &mISDN_class; dev->dev.platform_data = dev; dev->dev.parent = parent; dev_set_drvdata(&dev->dev, dev); @@ -249,8 +250,8 @@ mISDN_register_device(struct mISDNdevice *dev,

error3: delete_stack(dev); - return err; error1: + put_device(&dev->dev); return err;

}

From: Filipe Manana fdmanana@suse.com

[ Upstream commit 5614dc3a47e3310fbc77ea3b67eaadd1c6417bf1 ]

During backref walking, at resolve_indirect_refs(), if we get an error we jump to the 'out' label and call ulist_free() on the 'parents' ulist, which frees all the elements in the ulist - however that does not free any inode lists that may be attached to elements, through the 'aux' field of a ulist node, so we end up leaking lists if we have any attached to the unodes.

Fix this by calling free_leaf_list() instead of ulist_free() when we exit from resolve_indirect_refs(). The static function free_leaf_list() is moved up for this to be possible and it's slightly simplified by removing unnecessary code.

Fixes: 3301958b7c1d ("Btrfs: add inodes before dropping the extent lock in find_all_leafs") Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/backref.c | 36 +++++++++++++++++------------------- 1 file changed, 17 insertions(+), 19 deletions(-)

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 92cb16c0e5ee..70c1c15266d6 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -647,6 +647,18 @@ unode_aux_to_inode_list(struct ulist_node *node) return (struct extent_inode_elem *)(uintptr_t)node->aux; }

+static void free_leaf_list(struct ulist *ulist) +{ + struct ulist_node *node; + struct ulist_iterator uiter; + + ULIST_ITER_INIT(&uiter); + while ((node = ulist_next(ulist, &uiter))) + free_inode_elem_list(unode_aux_to_inode_list(node)); + + ulist_free(ulist); +} + /* * We maintain three separate rbtrees: one for direct refs, one for * indirect refs which have a key, and one for indirect refs which do not @@ -761,7 +773,11 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, cond_resched(); } out: - ulist_free(parents); + /* + * We may have inode lists attached to refs in the parents ulist, so we + * must free them before freeing the ulist and its refs. + */ + free_leaf_list(parents); return ret; }

@@ -1413,24 +1429,6 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans, return ret; }

-static void free_leaf_list(struct ulist *blocks) -{ - struct ulist_node *node = NULL; - struct extent_inode_elem *eie; - struct ulist_iterator uiter; - - ULIST_ITER_INIT(&uiter); - while ((node = ulist_next(blocks, &uiter))) { - if (!node->aux) - continue; - eie = unode_aux_to_inode_list(node); - free_inode_elem_list(eie); - node->aux = 0; - } - - ulist_free(blocks); -} - /* * Finds all leafs with a reference to the specified combination of bytenr and * offset. key_list_head will point to a list of corresponding keys (caller must

From: Filipe Manana fdmanana@suse.com

[ Upstream commit d37de92b38932d40e4a251e876cc388f9aee5f42 ]

In the test_no_shared_qgroup() and test_multiple_refs() qgroup self tests, if we fail to add the tree ref, remove the extent item or remove the extent ref, we are returning from the test function without freeing the "old_roots" ulist that was allocated by the previous calls to btrfs_find_all_roots(). Fix that by calling ulist_free() before returning.

Fixes: 442244c96332 ("btrfs: qgroup: Switch self test to extent-oriented qgroup mechanism.") Signed-off-by: Filipe Manana fdmanana@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/tests/qgroup-tests.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index ce1ca8e73c2d..c4b31dccc184 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -237,8 +237,10 @@ static int test_no_shared_qgroup(struct btrfs_root *root,

ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + }

ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); @@ -273,8 +275,10 @@ static int test_no_shared_qgroup(struct btrfs_root *root, }

ret = remove_extent_item(root, nodesize, nodesize); - if (ret) + if (ret) { + ulist_free(old_roots); return -EINVAL; + }

ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); @@ -338,8 +342,10 @@ static int test_multiple_refs(struct btrfs_root *root,

ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + }

ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); @@ -373,8 +379,10 @@ static int test_multiple_refs(struct btrfs_root *root,

ret = add_tree_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + }

ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); @@ -414,8 +422,10 @@ static int test_multiple_refs(struct btrfs_root *root,

ret = remove_extent_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + }

ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false);

From: Zhengchao Shao shaozhengchao@huawei.com

[ Upstream commit 0d0e2d032811280b927650ff3c15fe5020e82533 ]

When l2cap_recv_frame() is invoked to receive data, and the cid is L2CAP_CID_A2MP, if the channel does not exist, it will create a channel. However, after a channel is created, the hold operation of the channel is not performed. In this case, the value of channel reference counting is 1. As a result, after hci_error_reset() is triggered, l2cap_conn_del() invokes the close hook function of A2MP to release the channel. Then l2cap_chan_unlock(chan) will trigger UAF issue.

The process is as follows: Receive data: l2cap_data_channel() a2mp_channel_create() --->channel ref is 2 l2cap_chan_put() --->channel ref is 1

Triger event: hci_error_reset() hci_dev_do_close() ... l2cap_disconn_cfm() l2cap_conn_del() l2cap_chan_hold() --->channel ref is 2 l2cap_chan_del() --->channel ref is 1 a2mp_chan_close_cb() --->channel ref is 0, release channel l2cap_chan_unlock() --->UAF of channel

The detailed Call Trace is as follows: BUG: KASAN: use-after-free in __mutex_unlock_slowpath+0xa6/0x5e0 Read of size 8 at addr ffff8880160664b8 by task kworker/u11:1/7593 Workqueue: hci0 hci_error_reset Call Trace: <TASK> dump_stack_lvl+0xcd/0x134 print_report.cold+0x2ba/0x719 kasan_report+0xb1/0x1e0 kasan_check_range+0x140/0x190 __mutex_unlock_slowpath+0xa6/0x5e0 l2cap_conn_del+0x404/0x7b0 l2cap_disconn_cfm+0x8c/0xc0 hci_conn_hash_flush+0x11f/0x260 hci_dev_close_sync+0x5f5/0x11f0 hci_dev_do_close+0x2d/0x70 hci_error_reset+0x9e/0x140 process_one_work+0x98a/0x1620 worker_thread+0x665/0x1080 kthread+0x2e4/0x3a0 ret_from_fork+0x1f/0x30 </TASK>

Allocated by task 7593: kasan_save_stack+0x1e/0x40 __kasan_kmalloc+0xa9/0xd0 l2cap_chan_create+0x40/0x930 amp_mgr_create+0x96/0x990 a2mp_channel_create+0x7d/0x150 l2cap_recv_frame+0x51b8/0x9a70 l2cap_recv_acldata+0xaa3/0xc00 hci_rx_work+0x702/0x1220 process_one_work+0x98a/0x1620 worker_thread+0x665/0x1080 kthread+0x2e4/0x3a0 ret_from_fork+0x1f/0x30

Freed by task 7593: kasan_save_stack+0x1e/0x40 kasan_set_track+0x21/0x30 kasan_set_free_info+0x20/0x30 ____kasan_slab_free+0x167/0x1c0 slab_free_freelist_hook+0x89/0x1c0 kfree+0xe2/0x580 l2cap_chan_put+0x22a/0x2d0 l2cap_conn_del+0x3fc/0x7b0 l2cap_disconn_cfm+0x8c/0xc0 hci_conn_hash_flush+0x11f/0x260 hci_dev_close_sync+0x5f5/0x11f0 hci_dev_do_close+0x2d/0x70 hci_error_reset+0x9e/0x140 process_one_work+0x98a/0x1620 worker_thread+0x665/0x1080 kthread+0x2e4/0x3a0 ret_from_fork+0x1f/0x30

Last potentially related work creation: kasan_save_stack+0x1e/0x40 __kasan_record_aux_stack+0xbe/0xd0 call_rcu+0x99/0x740 netlink_release+0xe6a/0x1cf0 __sock_release+0xcd/0x280 sock_close+0x18/0x20 __fput+0x27c/0xa90 task_work_run+0xdd/0x1a0 exit_to_user_mode_prepare+0x23c/0x250 syscall_exit_to_user_mode+0x19/0x50 do_syscall_64+0x42/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Second to last potentially related work creation: kasan_save_stack+0x1e/0x40 __kasan_record_aux_stack+0xbe/0xd0 call_rcu+0x99/0x740 netlink_release+0xe6a/0x1cf0 __sock_release+0xcd/0x280 sock_close+0x18/0x20 __fput+0x27c/0xa90 task_work_run+0xdd/0x1a0 exit_to_user_mode_prepare+0x23c/0x250 syscall_exit_to_user_mode+0x19/0x50 do_syscall_64+0x42/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd

Fixes: d0be8347c623 ("Bluetooth: L2CAP: Fix use-after-free caused by l2cap_chan_put") Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/l2cap_core.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 0327c513191c..7f37e22d9242 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -7604,6 +7604,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, return; }

+ l2cap_chan_hold(chan); l2cap_chan_lock(chan); } else { BT_DBG("unknown cid 0x%4.4x", cid);

From: Chen Zhongjin chenzhongjin@huawei.com

[ Upstream commit f8017317cb0b279b8ab98b0f3901a2e0ac880dad ]

When IPv6 module gets initialized but hits an error in the middle, kenel panic with:

KASAN: null-ptr-deref in range [0x0000000000000598-0x000000000000059f] CPU: 1 PID: 361 Comm: insmod Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) RIP: 0010:__neigh_ifdown.isra.0+0x24b/0x370 RSP: 0018:ffff888012677908 EFLAGS: 00000202 ... Call Trace: <TASK> neigh_table_clear+0x94/0x2d0 ndisc_cleanup+0x27/0x40 [ipv6] inet6_init+0x21c/0x2cb [ipv6] do_one_initcall+0xd3/0x4d0 do_init_module+0x1ae/0x670 ... Kernel panic - not syncing: Fatal exception

When ipv6 initialization fails, it will try to cleanup and calls:

neigh_table_clear() neigh_ifdown(tbl, NULL) pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev == NULL)) # dev_net(NULL) triggers null-ptr-deref.

Fix it by passing NULL to pneigh_queue_purge() in neigh_ifdown() if dev is NULL, to make kernel not panic immediately.

Fixes: 66ba215cb513 ("neigh: fix possible DoS due to net iface start/stop loop") Signed-off-by: Chen Zhongjin chenzhongjin@huawei.com Reviewed-by: Eric Dumazet edumazet@google.com Reviewed-by: Denis V. Lunev den@openvz.org Link: https://lore.kernel.org/r/20221101121552.21890-1-chenzhongjin@huawei.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/neighbour.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 434c5aab83ea..f6f580e9d282 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -373,7 +373,7 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0;

From: Daniel Thompson daniel.thompson@linaro.org

[ Upstream commit 088604d37e23e9ec01a501d0e3630bc4f02027a0 ]

Quoting the header comments, IRQF_ONESHOT is "Used by threaded interrupts which need to keep the irq line disabled until the threaded handler has been run.". When applied to an interrupt that doesn't request a threaded irq then IRQF_ONESHOT has a lesser known (undocumented?) side effect, which it to disable the forced threading of irqs. For "normal" kernels if there is no thread_fn then IRQF_ONESHOT is a nop.

In this case disabling forced threading is not appropriate because the driver calls wake_up_all() (via msm_hdmi_i2c_irq) and also directly uses the regular spinlock API for locking (in msm_hdmi_hdcp_irq() ). Neither of these APIs can be called from no-thread interrupt handlers on PREEMPT_RT systems.

Fix this by removing IRQF_ONESHOT.

Signed-off-by: Daniel Thompson daniel.thompson@linaro.org Reviewed-by: Dmitry Baryshkov dmitry.baryshkov@linaro.org Link: https://lore.kernel.org/r/20220201174734.196718-3-daniel.thompson@linaro.org Signed-off-by: Dmitry Baryshkov dmitry.baryshkov@linaro.org Stable-dep-of: 152d394842bb ("drm/msm/hdmi: fix IRQ lifetime") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/msm/hdmi/hdmi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 47796e12b432..28823fd94f9f 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -327,7 +327,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, }

ret = devm_request_irq(&pdev->dev, hdmi->irq, - msm_hdmi_irq, IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + msm_hdmi_irq, IRQF_TRIGGER_HIGH, "hdmi_isr", hdmi); if (ret < 0) { DRM_DEV_ERROR(dev->dev, "failed to request IRQ%u: %d\n",

From: Sascha Hauer s.hauer@pengutronix.de

[ Upstream commit 1ed5c3b22fc78735c539e4767832aea58db6761c ]

The core issues the warning "drop HS400 support since no 8-bit bus" when one of the ESDHC_FLAG_HS400* flags is set on a non 8bit capable host. To avoid this warning set these flags only on hosts that actually can do 8bit, i.e. have bus-width = <8> set in the device tree.

Signed-off-by: Sascha Hauer s.hauer@pengutronix.de Reviewed-by: Haibo Chen haibo.chen@nxp.com Fixes: 029e2476f9e6 ("mmc: sdhci-esdhc-imx: add HS400_ES support for i.MX8QXP") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221013093248.2220802-1-s.hauer@pengutronix.de Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/sdhci-esdhc-imx.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index a4bd85b200a3..be4e5cdda1fa 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -1692,6 +1692,10 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) host->mmc_host_ops.execute_tuning = usdhc_execute_tuning; }

+ err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); + if (err) + goto disable_ahb_clk; + if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING) sdhci_esdhc_ops.platform_execute_tuning = esdhc_executing_tuning; @@ -1699,13 +1703,15 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536) host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;

- if (imx_data->socdata->flags & ESDHC_FLAG_HS400) + if (host->caps & MMC_CAP_8_BIT_DATA && + imx_data->socdata->flags & ESDHC_FLAG_HS400) host->quirks2 |= SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400;

if (imx_data->socdata->flags & ESDHC_FLAG_BROKEN_AUTO_CMD23) host->quirks2 |= SDHCI_QUIRK2_ACMD23_BROKEN;

- if (imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { + if (host->caps & MMC_CAP_8_BIT_DATA && + imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) { host->mmc->caps2 |= MMC_CAP2_HS400_ES; host->mmc_host_ops.hs400_enhanced_strobe = esdhc_hs400_enhanced_strobe; @@ -1727,13 +1733,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev) goto disable_ahb_clk; }

- if (of_id) - err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data); - else - err = sdhci_esdhc_imx_probe_nondt(pdev, host, imx_data); - if (err) - goto disable_ahb_clk; - sdhci_esdhc_imx_hwinit(host);

err = sdhci_add_host(host);

From: Patrick Thompson ptf@google.com

[ Upstream commit 9dc0033e4658d6f9d9952c3c0c6be3ec25bc2985 ]

Enhanced Strobe (ES) does not work correctly on the ASUS 1100 series of devices. Jasper Lake eMMCs (pci_id 8086:4dc4) are supposed to support ES. There are also two system families under the series, thus this is being scoped to the ASUS BIOS.

The failing ES prevents the installer from writing to disk. Falling back to HS400 without ES fixes the issue.

Signed-off-by: Patrick Thompson ptf@google.com Fixes: 315e3bd7ac19 ("mmc: sdhci-pci: Add support for Intel JSL") Acked-by: Adrian Hunter adrian.hunter@intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221013210017.3751025-1-ptf@google.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/host/sdhci-pci-core.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index 422ea3a1817a..7eb9a62ee074 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -967,6 +967,12 @@ static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) dmi_match(DMI_SYS_VENDOR, "IRBIS")); }

+static bool jsl_broken_hs400es(struct sdhci_pci_slot *slot) +{ + return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_JSL_EMMC && + dmi_match(DMI_BIOS_VENDOR, "ASUSTeK COMPUTER INC."); +} + static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) { int ret = byt_emmc_probe_slot(slot); @@ -975,9 +981,11 @@ static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) slot->host->mmc->caps2 |= MMC_CAP2_CQE;

if (slot->chip->pdev->device != PCI_DEVICE_ID_INTEL_GLK_EMMC) { - slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES; - slot->host->mmc_host_ops.hs400_enhanced_strobe = - intel_hs400_enhanced_strobe; + if (!jsl_broken_hs400es(slot)) { + slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES; + slot->host->mmc_host_ops.hs400_enhanced_strobe = + intel_hs400_enhanced_strobe; + } slot->host->mmc->caps2 |= MMC_CAP2_CQE_DCMD; }

From: Helge Deller deller@gmx.de

[ Upstream commit 776d875fd4cbb3884860ea7f63c3958f02b0c80e ]

When the text console is scrolling text upwards it calls the fillrect() function to empty the new line. The current implementation doesn't seem to work correctly on HCRX cards in 32-bit mode and leave garbage in that line instead. Fix it by falling back to standard cfb_fillrect() in that case.

Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/video/fbdev/stifb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c index 7753e586e65a..3feb6e40d56d 100644 --- a/drivers/video/fbdev/stifb.c +++ b/drivers/video/fbdev/stifb.c @@ -1055,7 +1055,8 @@ stifb_fillrect(struct fb_info *info, const struct fb_fillrect *rect) { struct stifb_info *fb = container_of(info, struct stifb_info, info);

- if (rect->rop != ROP_COPY) + if (rect->rop != ROP_COPY || + (fb->id == S9000_ID_HCRX && fb->info.var.bits_per_pixel == 32)) return cfb_fillrect(info, rect);

SETUP_HW(fb);

From: Linus Walleij linus.walleij@linaro.org

[ Upstream commit 05e258c6ec669d6d18c494ea03d35962d6f5b545 ]

There is some code in the parser that tries to read 0x8000 bytes into a block to "read in the middle" of the block. Well that only works if the block is also 0x10000 bytes all the time, else we get these parse errors as we reach the end of the flash:

spi-nor spi0.0: mx25l1606e (2048 Kbytes) mtd_read error while parsing (offset: 0x200000): -22 mtd_read error while parsing (offset: 0x201000): -22 (...)

Fix the code to do what I think was intended.

Cc: stable@vger.kernel.org Fixes: f0501e81fbaa ("mtd: bcm47xxpart: alternative MAGIC for board_data partition") Cc: Rafał Miłecki zajec5@gmail.com Cc: Florian Fainelli f.fainelli@gmail.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Miquel Raynal miquel.raynal@bootlin.com Link: https://lore.kernel.org/linux-mtd/20221018091129.280026-1-linus.walleij@lina... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mtd/parsers/bcm47xxpart.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/parsers/bcm47xxpart.c b/drivers/mtd/parsers/bcm47xxpart.c index 50fcf4c2174b..13daf9bffd08 100644 --- a/drivers/mtd/parsers/bcm47xxpart.c +++ b/drivers/mtd/parsers/bcm47xxpart.c @@ -233,11 +233,11 @@ static int bcm47xxpart_parse(struct mtd_info *master, }

/* Read middle of the block */ - err = mtd_read(master, offset + 0x8000, 0x4, &bytes_read, + err = mtd_read(master, offset + (blocksize / 2), 0x4, &bytes_read, (uint8_t *)buf); if (err && !mtd_is_bitflip(err)) { pr_err("mtd_read error while parsing (offset: 0x%X): %d\n", - offset + 0x8000, err); + offset + (blocksize / 2), err); continue; }

From: Peter Oberparleiter oberpar@linux.ibm.com

[ Upstream commit aa127a069ef312aca02b730d5137e1778d0c3ba7 ]

This patch enhances the kernel image adding a trailer as required for secure boot by future firmware versions.

Cc: stable@vger.kernel.org # 5.2+ Signed-off-by: Peter Oberparleiter oberpar@linux.ibm.com Reviewed-by: Sven Schnelle svens@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/boot/compressed/vmlinux.lds.S | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S index 9427e2cd0c15..11bf3919610e 100644 --- a/arch/s390/boot/compressed/vmlinux.lds.S +++ b/arch/s390/boot/compressed/vmlinux.lds.S @@ -91,8 +91,17 @@ SECTIONS _compressed_start = .; *(.vmlinux.bin.compressed) _compressed_end = .; - FILL(0xff); - . = ALIGN(4096); + } + +#define SB_TRAILER_SIZE 32 + /* Trailer needed for Secure Boot */ + . += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */ + . = ALIGN(4096) - SB_TRAILER_SIZE; + .sb.trailer : { + QUAD(0) + QUAD(0) + QUAD(0) + QUAD(0x000000207a49504c) } _end = .;

From: Laurent Pinchart laurent.pinchart@ideasonboard.com

[ Upstream commit c53e3a049f35978a150526671587fd46b1ae7ca1 ]

The local sd_fmt variable in rkisp1_capture_link_validate() has uninitialized fields, which causes random failures when calling the subdev .get_fmt() operation. Fix it by initializing the variable when declaring it, which zeros all other fields.

Signed-off-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Reviewed-by: Paul Elder paul.elder@ideasonboard.com Reviewed-by: Dafna Hirschfeld dafna@fastmail.com Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/media/rkisp1/rkisp1-capture.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/staging/media/rkisp1/rkisp1-capture.c b/drivers/staging/media/rkisp1/rkisp1-capture.c index 0c934ca5adaa..8936f5a81680 100644 --- a/drivers/staging/media/rkisp1/rkisp1-capture.c +++ b/drivers/staging/media/rkisp1/rkisp1-capture.c @@ -1258,11 +1258,12 @@ static int rkisp1_capture_link_validate(struct media_link *link) struct rkisp1_capture *cap = video_get_drvdata(vdev); const struct rkisp1_capture_fmt_cfg *fmt = rkisp1_find_fmt_cfg(cap, cap->pix.fmt.pixelformat); - struct v4l2_subdev_format sd_fmt; + struct v4l2_subdev_format sd_fmt = { + .which = V4L2_SUBDEV_FORMAT_ACTIVE, + .pad = link->source->index, + }; int ret;

- sd_fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE; - sd_fmt.pad = link->source->index; ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &sd_fmt); if (ret) return ret;

From: Hans Verkuil hverkuil-cisco@xs4all.nl

[ Upstream commit 2dc73b48665411a08c4e5f0f823dea8510761603 ]

I expect that the hardware will have limited this to 16, but just in case it hasn't, check for this corner case.

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/cec/platform/cros-ec/cros-ec-cec.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/media/cec/platform/cros-ec/cros-ec-cec.c b/drivers/media/cec/platform/cros-ec/cros-ec-cec.c index 2d95e16cd248..f66699d5dc66 100644 --- a/drivers/media/cec/platform/cros-ec/cros-ec-cec.c +++ b/drivers/media/cec/platform/cros-ec/cros-ec-cec.c @@ -44,6 +44,8 @@ static void handle_cec_message(struct cros_ec_cec *cros_ec_cec) uint8_t *cec_message = cros_ec->event_data.data.cec_message; unsigned int len = cros_ec->event_size;

+ if (len > CEC_MAX_MSG_SIZE) + len = CEC_MAX_MSG_SIZE; cros_ec_cec->rx_msg.len = len; memcpy(cros_ec_cec->rx_msg.msg, cec_message, len);

From: Hangyu Hua hbh25y@gmail.com

[ Upstream commit 7718999356234d9cc6a11b4641bb773928f1390f ]

v4l2_device_unregister need to be called to put the refcount got by v4l2_device_register when vdec_probe fails or vdec_remove is called.

Signed-off-by: Hangyu Hua hbh25y@gmail.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/media/meson/vdec/vdec.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/staging/media/meson/vdec/vdec.c b/drivers/staging/media/meson/vdec/vdec.c index 5ccb3846c879..7a818ca15b37 100644 --- a/drivers/staging/media/meson/vdec/vdec.c +++ b/drivers/staging/media/meson/vdec/vdec.c @@ -1109,6 +1109,7 @@ static int vdec_probe(struct platform_device *pdev)

err_vdev_release: video_device_release(vdev); + v4l2_device_unregister(&core->v4l2_dev); return ret; }

@@ -1117,6 +1118,7 @@ static int vdec_remove(struct platform_device *pdev) struct amvdec_core *core = platform_get_drvdata(pdev);

video_unregister_device(core->vdev_dec); + v4l2_device_unregister(&core->v4l2_dev);

return 0; }

From: Uday Shankar ushankar@purestorage.com

[ Upstream commit 2331ce6126be8864b39490e705286b66e2344aac ]

Userspace can currently write to sysfs to transition sdev_state to RUNNING or OFFLINE from any source state. This causes issues because proper transitioning out of some states involves steps besides just changing sdev_state, so allowing userspace to change sdev_state regardless of the source state can result in inconsistencies; e.g. with ISCSI we can end up with sdev_state == SDEV_RUNNING while the device queue is quiesced. Any task attempting I/O on the device will then hang, and in more recent kernels, iscsid will hang as well.

More detail about this bug is provided in my first attempt:

https://groups.google.com/g/open-iscsi/c/PNKca4HgPDs/m/CXaDkntOAQAJ

Link: https://lore.kernel.org/r/20220924000241.2967323-1-ushankar@purestorage.com Signed-off-by: Uday Shankar ushankar@purestorage.com Suggested-by: Mike Christie michael.christie@oracle.com Reviewed-by: Hannes Reinecke hare@suse.de Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/scsi_sysfs.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 42db9c52208e..6cc4d0792e3d 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -815,6 +815,14 @@ store_state_field(struct device *dev, struct device_attribute *attr, }

mutex_lock(&sdev->state_mutex); + switch (sdev->sdev_state) { + case SDEV_RUNNING: + case SDEV_OFFLINE: + break; + default: + mutex_unlock(&sdev->state_mutex); + return -EINVAL; + } if (sdev->sdev_state == SDEV_RUNNING && state == SDEV_RUNNING) { ret = 0; } else {

From: Danijel Slivka danijel.slivka@amd.com

[ Upstream commit 65f8682b9aaae20c2cdee993e6fe52374ad513c9 ]

For asic with VF MMIO access protection avoid using CPU for VM table updates. CPU pagetable updates have issues with HDP flush as VF MMIO access protection blocks write to mmBIF_BX_DEV0_EPF0_VF0_HDP_MEM_COHERENCY_FLUSH_CNTL register during sriov runtime.

v3: introduce virtualization capability flag AMDGPU_VF_MMIO_ACCESS_PROTECT which indicates that VF MMIO write access is not allowed in sriov runtime

Signed-off-by: Danijel Slivka danijel.slivka@amd.com Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 6 ++++++ drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 4 ++++ drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 6 +++++- 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 16bfb36c27e4..d6f295103595 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -670,6 +670,12 @@ void amdgpu_detect_virtualization(struct amdgpu_device *adev) adev->virt.caps |= AMDGPU_PASSTHROUGH_MODE; }

+ if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID) + /* VF MMIO access (except mailbox range) from CPU + * will be blocked during sriov runtime + */ + adev->virt.caps |= AMDGPU_VF_MMIO_ACCESS_PROTECT; + /* we have the ability to check now */ if (amdgpu_sriov_vf(adev)) { switch (adev->asic_type) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 77b9d37bfa1b..aea49bad914f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -31,6 +31,7 @@ #define AMDGPU_SRIOV_CAPS_IS_VF (1 << 2) /* this GPU is a virtual function */ #define AMDGPU_PASSTHROUGH_MODE (1 << 3) /* thw whole GPU is pass through for VM */ #define AMDGPU_SRIOV_CAPS_RUNTIME (1 << 4) /* is out of full access mode */ +#define AMDGPU_VF_MMIO_ACCESS_PROTECT (1 << 5) /* MMIO write access is not allowed in sriov runtime */

/* all asic after AI use this offset */ #define mmRCC_IOV_FUNC_IDENTIFIER 0xDE5 @@ -241,6 +242,9 @@ struct amdgpu_virt { #define amdgpu_passthrough(adev) \ ((adev)->virt.caps & AMDGPU_PASSTHROUGH_MODE)

+#define amdgpu_sriov_vf_mmio_access_protection(adev) \ +((adev)->virt.caps & AMDGPU_VF_MMIO_ACCESS_PROTECT) + static inline bool is_virtual_machine(void) { #ifdef CONFIG_X86 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 635601d8b131..45b1f00c5968 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3200,7 +3200,11 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev) */ #ifdef CONFIG_X86_64 if (amdgpu_vm_update_mode == -1) { - if (amdgpu_gmc_vram_full_visible(&adev->gmc)) + /* For asic with VF MMIO access protection + * avoid using CPU for VM table updates + */ + if (amdgpu_gmc_vram_full_visible(&adev->gmc) && + !amdgpu_sriov_vf_mmio_access_protection(adev)) adev->vm_manager.vm_update_mode = AMDGPU_VM_USE_CPU_FOR_COMPUTE; else

From: Jerry Snitselaar jsnitsel@redhat.com

[ Upstream commit f4cd18c5b2000df0c382f6530eeca9141ea41faf ]

memblock_reserve() expects a physical address, but the address being passed for the TPM final events log is what was returned from early_memremap(). This results in something like the following:

[ 0.000000] memblock_reserve: [0xffffffffff2c0000-0xffffffffff2c00e4] efi_tpm_eventlog_init+0x324/0x370

Pass the address from efi like what is done for the TPM events log.

Fixes: c46f3405692d ("tpm: Reserve the TPM final events table") Cc: Matthew Garrett mjg59@google.com Cc: Jarkko Sakkinen jarkko@kernel.org Cc: Bartosz Szczepanek bsz@semihalf.com Cc: Ard Biesheuvel ardb@kernel.org Signed-off-by: Jerry Snitselaar jsnitsel@redhat.com Acked-by: Jarkko Sakkinen jarkko@kernel.org Signed-off-by: Ard Biesheuvel ardb@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/efi/tpm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 8f665678e9e3..e8d69bd548f3 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -97,7 +97,7 @@ int __init efi_tpm_eventlog_init(void) goto out_calc; }

- memblock_reserve((unsigned long)final_tbl, + memblock_reserve(efi.tpm_final_log, tbl_size + sizeof(*final_tbl)); efi_tpm_final_log_size = tbl_size;

From: Ioana Ciornei ioana.ciornei@nxp.com

[ Upstream commit c126a0abc5dadd7df236f20aae6d8c3d103f095c ]

Up until now, the external MDIO controller frequency values relied either on the default ones out of reset or on those setup by u-boot. Let's just properly specify the MDC frequency in the DTS so that even without u-boot's intervention Linux can drive the MDIO bus.

Fixes: 6e1b8fae892d ("arm64: dts: lx2160a: add emdio1 node") Fixes: 5705b9dcda57 ("arm64: dts: lx2160a: add emdio2 node") Signed-off-by: Ioana Ciornei ioana.ciornei@nxp.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 83072da6f6c6..8115cdcb4574 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1292,6 +1292,9 @@ emdio1: mdio@8b96000 { #address-cells = <1>; #size-cells = <0>; little-endian; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; };

@@ -1302,6 +1305,9 @@ emdio2: mdio@8b97000 { little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; };

From: Cristian Marussi cristian.marussi@arm.com

[ Upstream commit be9ba1f7f9e0b565b19f4294f5871da9d654bc6d ]

SCMI Rx channels are optional and they can fail to be setup when not present but anyway channels setup routines must bail-out on memory errors.

Make channels setup, and related probing, fail when memory errors are reported on Rx channels.

Fixes: 5c8a47a5a91d ("firmware: arm_scmi: Make scmi core independent of the transport type") Signed-off-by: Cristian Marussi cristian.marussi@arm.com Link: https://lore.kernel.org/r/20221028140833.280091-4-cristian.marussi@arm.com Signed-off-by: Sudeep Holla sudeep.holla@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/firmware/arm_scmi/driver.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 4bc974ead02b..8d24082848a8 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -711,8 +711,12 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id) { int ret = scmi_chan_setup(info, dev, prot_id, true);

- if (!ret) /* Rx is optional, hence no error check */ - scmi_chan_setup(info, dev, prot_id, false); + if (!ret) { + /* Rx is optional, report only memory errors */ + ret = scmi_chan_setup(info, dev, prot_id, false); + if (ret && ret != -ENOMEM) + ret = 0; + }

return ret; }

From: Chen Zhongjin chenzhongjin@huawei.com

[ Upstream commit 569bea74c94d37785682b11bab76f557520477cd ]

In piix4_probe(), the piix4 adapter will be registered in:

piix4_probe() piix4_add_adapters_sb800() / piix4_add_adapter() i2c_add_adapter()

Based on the probed device type, piix4_add_adapters_sb800() or single piix4_add_adapter() will be called. For the former case, piix4_adapter_count is set as the number of adapters, while for antoher case it is not set and kept default *zero*.

When piix4 is removed, piix4_remove() removes the adapters added in piix4_probe(), basing on the piix4_adapter_count value. Because the count is zero for the single adapter case, the adapter won't be removed and makes the sources allocated for adapter leaked, such as the i2c client and device.

These sources can still be accessed by i2c or bus and cause problems. An easily reproduced case is that if a new adapter is registered, i2c will get the leaked adapter and try to call smbus_algorithm, which was already freed:

Triggered by: rmmod i2c_piix4 && modprobe max31730

BUG: unable to handle page fault for address: ffffffffc053d860 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page Oops: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 3752 Comm: modprobe Tainted: G Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) RIP: 0010:i2c_default_probe (drivers/i2c/i2c-core-base.c:2259) i2c_core RSP: 0018:ffff888107477710 EFLAGS: 00000246 ... <TASK> i2c_detect (drivers/i2c/i2c-core-base.c:2302) i2c_core __process_new_driver (drivers/i2c/i2c-core-base.c:1336) i2c_core bus_for_each_dev (drivers/base/bus.c:301) i2c_for_each_dev (drivers/i2c/i2c-core-base.c:1823) i2c_core i2c_register_driver (drivers/i2c/i2c-core-base.c:1861) i2c_core do_one_initcall (init/main.c:1296) do_init_module (kernel/module/main.c:2455) ... </TASK> ---[ end trace 0000000000000000 ]---

Fix this problem by correctly set piix4_adapter_count as 1 for the single adapter so it can be normally removed.

Fixes: 528d53a1592b ("i2c: piix4: Fix probing of reserved ports on AMD Family 16h Model 30h") Signed-off-by: Chen Zhongjin chenzhongjin@huawei.com Reviewed-by: Jean Delvare jdelvare@suse.de Signed-off-by: Wolfram Sang wsa@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-piix4.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 8c1b31ed0c42..aa1d3657ab4e 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -961,6 +961,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) "", &piix4_main_adapters[0]); if (retval < 0) return retval; + piix4_adapter_count = 1; }

/* Check for auxiliary SMBus on some AMD chipsets */

From: Luiz Augusto von Dentz luiz.von.dentz@intel.com

commit b1a2cd50c0357f243b7435a732b4e62ba3157a2e upstream.

On l2cap_parse_conf_req the variable efs is only initialized if remote_efs has been set.

CVE: CVE-2022-42895 CC: stable@vger.kernel.org Reported-by: Tamás Koczka poprdi@google.com Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Reviewed-by: Tedd Ho-Jeong An tedd.an@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bluetooth/l2cap_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -3760,7 +3760,8 @@ done: l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc, endptr - ptr);

- if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { + if (remote_efs && + test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->remote_id = efs.id; chan->remote_stype = efs.stype; chan->remote_msdu = le16_to_cpu(efs.msdu);

From: John Veness john-linux@pelago.org.uk

commit 6e2c9105e0b743c92a157389d40f00b81bdd09fe upstream.

Treat the claimed 96kHz 1ch in the descriptors as 48kHz 2ch, so that the audio stream doesn't sound mono. Also fix initial stream alignment, so that left and right channels are in the correct order.

Signed-off-by: John Veness john-linux@pelago.org.uk Link: https://lore.kernel.org/r/20220624140757.28758-1-john-linux@pelago.org.uk Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/quirks-table.h | 52 +++++++++++++++++++++++++++++++++++++++++++++++ sound/usb/quirks.c | 1 2 files changed, 53 insertions(+)

--- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3657,6 +3657,58 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge },

/* + * MacroSilicon MS2100/MS2106 based AV capture cards + * + * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch. + * They also need QUIRK_AUDIO_ALIGN_TRANSFER, which makes one wonder if + * they pretend to be 96kHz mono as a workaround for stereo being broken + * by that... + * + * They also have an issue with initial stream alignment that causes the + * channels to be swapped and out of phase, which is dealt with in quirks.c. + */ +{ + USB_AUDIO_DEVICE(0x534d, 0x0021), + .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) { + .vendor_name = "MacroSilicon", + .product_name = "MS210x", + .ifnum = QUIRK_ANY_INTERFACE, + .type = QUIRK_COMPOSITE, + .data = &(const struct snd_usb_audio_quirk[]) { + { + .ifnum = 2, + .type = QUIRK_AUDIO_ALIGN_TRANSFER, + }, + { + .ifnum = 2, + .type = QUIRK_AUDIO_STANDARD_MIXER, + }, + { + .ifnum = 3, + .type = QUIRK_AUDIO_FIXED_ENDPOINT, + .data = &(const struct audioformat) { + .formats = SNDRV_PCM_FMTBIT_S16_LE, + .channels = 2, + .iface = 3, + .altsetting = 1, + .altset_idx = 1, + .attributes = 0, + .endpoint = 0x82, + .ep_attr = USB_ENDPOINT_XFER_ISOC | + USB_ENDPOINT_SYNC_ASYNC, + .rates = SNDRV_PCM_RATE_CONTINUOUS, + .rate_min = 48000, + .rate_max = 48000, + } + }, + { + .ifnum = -1 + } + } + } +}, + +/* * MacroSilicon MS2109 based HDMI capture cards * * These claim 96kHz 1ch in the descriptors, but are actually 48kHz 2ch. --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1508,6 +1508,7 @@ void snd_usb_set_format_quirk(struct snd case USB_ID(0x2b73, 0x0017): /* Pioneer DJ DJM-250MK2 */ pioneer_djm_set_format_quirk(subs); break; + case USB_ID(0x534d, 0x0021): /* MacroSilicon MS2100/MS2106 */ case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */ subs->stream_offset_adj = 2; break;

From: Eric Biggers ebiggers@google.com

commit d7e7b9af104c7b389a0c21eb26532511bce4b510 upstream.

The approach of fs/crypto/ internally managing the fscrypt_master_key structs as the payloads of "struct key" objects contained in a "struct key" keyring has outlived its usefulness. The original idea was to simplify the code by reusing code from the keyrings subsystem. However, several issues have arisen that can't easily be resolved:

- When a master key struct is destroyed, blk_crypto_evict_key() must be called on any per-mode keys embedded in it. (This started being the case when inline encryption support was added.) Yet, the keyrings subsystem can arbitrarily delay the destruction of keys, even past the time the filesystem was unmounted. Therefore, currently there is no easy way to call blk_crypto_evict_key() when a master key is destroyed. Currently, this is worked around by holding an extra reference to the filesystem's request_queue(s). But it was overlooked that the request_queue reference is *not* guaranteed to pin the corresponding blk_crypto_profile too; for device-mapper devices that support inline crypto, it doesn't. This can cause a use-after-free.

- When the last inode that was using an incompletely-removed master key is evicted, the master key removal is completed by removing the key struct from the keyring. Currently this is done via key_invalidate(). Yet, key_invalidate() takes the key semaphore. This can deadlock when called from the shrinker, since in fscrypt_ioctl_add_key(), memory is allocated with GFP_KERNEL under the same semaphore.

- More generally, the fact that the keyrings subsystem can arbitrarily delay the destruction of keys (via garbage collection delay, or via random processes getting temporary key references) is undesirable, as it means we can't strictly guarantee that all secrets are ever wiped.

- Doing the master key lookups via the keyrings subsystem results in the key_permission LSM hook being called. fscrypt doesn't want this, as all access control for encrypted files is designed to happen via the files themselves, like any other files. The workaround which SELinux users are using is to change their SELinux policy to grant key search access to all domains. This works, but it is an odd extra step that shouldn't really have to be done.

The fix for all these issues is to change the implementation to what I should have done originally: don't use the keyrings subsystem to keep track of the filesystem's fscrypt_master_key structs. Instead, just store them in a regular kernel data structure, and rework the reference counting, locking, and lifetime accordingly. Retain support for RCU-mode key lookups by using a hash table. Replace fscrypt_sb_free() with fscrypt_sb_delete(), which releases the keys synchronously and runs a bit earlier during unmount, so that block devices are still available.

A side effect of this patch is that neither the master keys themselves nor the filesystem keyrings will be listed in /proc/keys anymore. ("Master key users" and the master key users keyrings will still be listed.) However, this was mostly an implementation detail, and it was intended just for debugging purposes. I don't know of anyone using it.

This patch does *not* change how "master key users" (->mk_users) works; that still uses the keyrings subsystem. That is still needed for key quotas, and changing that isn't necessary to solve the issues listed above. If we decide to change that too, it would be a separate patch.

I've marked this as fixing the original commit that added the fscrypt keyring, but as noted above the most important issue that this patch fixes wasn't introduced until the addition of inline encryption support.

Fixes: 22d94f493bfb ("fscrypt: add FS_IOC_ADD_ENCRYPTION_KEY ioctl") Signed-off-by: Eric Biggers ebiggers@google.com Link: https://lore.kernel.org/r/20220901193208.138056-2-ebiggers@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/crypto/fscrypt_private.h | 71 ++++-- fs/crypto/hooks.c | 10 fs/crypto/keyring.c | 484 +++++++++++++++++++++++--------------------- fs/crypto/keysetup.c | 81 ++----- fs/crypto/policy.c | 8 fs/super.c | 2 include/linux/fs.h | 2 include/linux/fscrypt.h | 4 8 files changed, 352 insertions(+), 310 deletions(-)

--- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -220,7 +220,7 @@ struct fscrypt_info { * will be NULL if the master key was found in a process-subscribed * keyring rather than in the filesystem-level keyring. */ - struct key *ci_master_key; + struct fscrypt_master_key *ci_master_key;

/* * Link in list of inodes that were unlocked with the master key. @@ -432,6 +432,40 @@ struct fscrypt_master_key_secret { struct fscrypt_master_key {

/* + * Back-pointer to the super_block of the filesystem to which this + * master key has been added. Only valid if ->mk_active_refs > 0. + */ + struct super_block *mk_sb; + + /* + * Link in ->mk_sb->s_master_keys->key_hashtable. + * Only valid if ->mk_active_refs > 0. + */ + struct hlist_node mk_node; + + /* Semaphore that protects ->mk_secret and ->mk_users */ + struct rw_semaphore mk_sem; + + /* + * Active and structural reference counts. An active ref guarantees + * that the struct continues to exist, continues to be in the keyring + * ->mk_sb->s_master_keys, and that any embedded subkeys (e.g. + * ->mk_direct_keys) that have been prepared continue to exist. + * A structural ref only guarantees that the struct continues to exist. + * + * There is one active ref associated with ->mk_secret being present, + * and one active ref for each inode in ->mk_decrypted_inodes. + * + * There is one structural ref associated with the active refcount being + * nonzero. Finding a key in the keyring also takes a structural ref, + * which is then held temporarily while the key is operated on. + */ + refcount_t mk_active_refs; + refcount_t mk_struct_refs; + + struct rcu_head mk_rcu_head; + + /* * The secret key material. After FS_IOC_REMOVE_ENCRYPTION_KEY is * executed, this is wiped and no new inodes can be unlocked with this * key; however, there may still be inodes in ->mk_decrypted_inodes @@ -439,7 +473,10 @@ struct fscrypt_master_key { * FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or * FS_IOC_ADD_ENCRYPTION_KEY can add the secret again. * - * Locking: protected by this master key's key->sem. + * While ->mk_secret is present, one ref in ->mk_active_refs is held. + * + * Locking: protected by ->mk_sem. The manipulation of ->mk_active_refs + * associated with this field is protected by ->mk_sem as well. */ struct fscrypt_master_key_secret mk_secret;

@@ -460,23 +497,13 @@ struct fscrypt_master_key { * * This is NULL for v1 policy keys; those can only be added by root. * - * Locking: in addition to this keyring's own semaphore, this is - * protected by this master key's key->sem, so we can do atomic - * search+insert. It can also be searched without taking any locks, but - * in that case the returned key may have already been removed. + * Locking: protected by ->mk_sem. (We don't just rely on the keyrings + * subsystem semaphore ->mk_users->sem, as we need support for atomic + * search+insert along with proper synchronization with ->mk_secret.) */ struct key *mk_users;

/* - * Length of ->mk_decrypted_inodes, plus one if mk_secret is present. - * Once this goes to 0, the master key is removed from ->s_master_keys. - * The 'struct fscrypt_master_key' will continue to live as long as the - * 'struct key' whose payload it is, but we won't let this reference - * count rise again. - */ - refcount_t mk_refcount; - - /* * List of inodes that were unlocked using this key. This allows the * inodes to be evicted efficiently if the key is removed. */ @@ -501,10 +528,10 @@ static inline bool is_master_key_secret_present(const struct fscrypt_master_key_secret *secret) { /* - * The READ_ONCE() is only necessary for fscrypt_drop_inode() and - * fscrypt_key_describe(). These run in atomic context, so they can't - * take the key semaphore and thus 'secret' can change concurrently - * which would be a data race. But they only need to know whether the + * The READ_ONCE() is only necessary for fscrypt_drop_inode(). + * fscrypt_drop_inode() runs in atomic context, so it can't take the key + * semaphore and thus 'secret' can change concurrently which would be a + * data race. But fscrypt_drop_inode() only need to know whether the * secret *was* present at the time of check, so READ_ONCE() suffices. */ return READ_ONCE(secret->size) != 0; @@ -533,7 +560,11 @@ static inline int master_key_spec_len(co return 0; }

-struct key * +void fscrypt_put_master_key(struct fscrypt_master_key *mk); + +void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk); + +struct fscrypt_master_key * fscrypt_find_master_key(struct super_block *sb, const struct fscrypt_key_specifier *mk_spec);

--- a/fs/crypto/hooks.c +++ b/fs/crypto/hooks.c @@ -5,8 +5,6 @@ * Encryption hooks for higher-level filesystem operations. */

-#include <linux/key.h> - #include "fscrypt_private.h"

/** @@ -139,7 +137,6 @@ int fscrypt_prepare_setflags(struct inod unsigned int oldflags, unsigned int flags) { struct fscrypt_info *ci; - struct key *key; struct fscrypt_master_key *mk; int err;

@@ -155,14 +152,13 @@ int fscrypt_prepare_setflags(struct inod ci = inode->i_crypt_info; if (ci->ci_policy.version != FSCRYPT_POLICY_V2) return -EINVAL; - key = ci->ci_master_key; - mk = key->payload.data[0]; - down_read(&key->sem); + mk = ci->ci_master_key; + down_read(&mk->mk_sem); if (is_master_key_secret_present(&mk->mk_secret)) err = fscrypt_derive_dirhash_key(ci, mk); else err = -ENOKEY; - up_read(&key->sem); + up_read(&mk->mk_sem); return err; } return 0; --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -18,6 +18,7 @@ * information about these ioctls. */

+#include <asm/unaligned.h> #include <crypto/skcipher.h> #include <linux/key-type.h> #include <linux/random.h> @@ -25,6 +26,18 @@

#include "fscrypt_private.h"

+/* The master encryption keys for a filesystem (->s_master_keys) */ +struct fscrypt_keyring { + /* + * Lock that protects ->key_hashtable. It does *not* protect the + * fscrypt_master_key structs themselves. + */ + spinlock_t lock; + + /* Hash table that maps fscrypt_key_specifier to fscrypt_master_key */ + struct hlist_head key_hashtable[128]; +}; + static void wipe_master_key_secret(struct fscrypt_master_key_secret *secret) { fscrypt_destroy_hkdf(&secret->hkdf); @@ -38,20 +51,70 @@ static void move_master_key_secret(struc memzero_explicit(src, sizeof(*src)); }

-static void free_master_key(struct fscrypt_master_key *mk) +static void fscrypt_free_master_key(struct rcu_head *head) +{ + struct fscrypt_master_key *mk = + container_of(head, struct fscrypt_master_key, mk_rcu_head); + /* + * The master key secret and any embedded subkeys should have already + * been wiped when the last active reference to the fscrypt_master_key + * struct was dropped; doing it here would be unnecessarily late. + * Nevertheless, use kfree_sensitive() in case anything was missed. + */ + kfree_sensitive(mk); +} + +void fscrypt_put_master_key(struct fscrypt_master_key *mk) +{ + if (!refcount_dec_and_test(&mk->mk_struct_refs)) + return; + /* + * No structural references left, so free ->mk_users, and also free the + * fscrypt_master_key struct itself after an RCU grace period ensures + * that concurrent keyring lookups can no longer find it. + */ + WARN_ON(refcount_read(&mk->mk_active_refs) != 0); + key_put(mk->mk_users); + mk->mk_users = NULL; + call_rcu(&mk->mk_rcu_head, fscrypt_free_master_key); +} + +void fscrypt_put_master_key_activeref(struct fscrypt_master_key *mk) { + struct super_block *sb = mk->mk_sb; + struct fscrypt_keyring *keyring = sb->s_master_keys; size_t i;

- wipe_master_key_secret(&mk->mk_secret); + if (!refcount_dec_and_test(&mk->mk_active_refs)) + return; + /* + * No active references left, so complete the full removal of this + * fscrypt_master_key struct by removing it from the keyring and + * destroying any subkeys embedded in it. + */ + + spin_lock(&keyring->lock); + hlist_del_rcu(&mk->mk_node); + spin_unlock(&keyring->lock); + + /* + * ->mk_active_refs == 0 implies that ->mk_secret is not present and + * that ->mk_decrypted_inodes is empty. + */ + WARN_ON(is_master_key_secret_present(&mk->mk_secret)); + WARN_ON(!list_empty(&mk->mk_decrypted_inodes));

for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { fscrypt_destroy_prepared_key(&mk->mk_direct_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_64_keys[i]); fscrypt_destroy_prepared_key(&mk->mk_iv_ino_lblk_32_keys[i]); } + memzero_explicit(&mk->mk_ino_hash_key, + sizeof(mk->mk_ino_hash_key)); + mk->mk_ino_hash_key_initialized = false;

- key_put(mk->mk_users); - kfree_sensitive(mk); + /* Drop the structural ref associated with the active refs. */ + fscrypt_put_master_key(mk); }

static inline bool valid_key_spec(const struct fscrypt_key_specifier *spec) @@ -61,44 +124,6 @@ static inline bool valid_key_spec(const return master_key_spec_len(spec) != 0; }

-static int fscrypt_key_instantiate(struct key *key, - struct key_preparsed_payload *prep) -{ - key->payload.data[0] = (struct fscrypt_master_key *)prep->data; - return 0; -} - -static void fscrypt_key_destroy(struct key *key) -{ - free_master_key(key->payload.data[0]); -} - -static void fscrypt_key_describe(const struct key *key, struct seq_file *m) -{ - seq_puts(m, key->description); - - if (key_is_positive(key)) { - const struct fscrypt_master_key *mk = key->payload.data[0]; - - if (!is_master_key_secret_present(&mk->mk_secret)) - seq_puts(m, ": secret removed"); - } -} - -/* - * Type of key in ->s_master_keys. Each key of this type represents a master - * key which has been added to the filesystem. Its payload is a - * 'struct fscrypt_master_key'. The "." prefix in the key type name prevents - * users from adding keys of this type via the keyrings syscalls rather than via - * the intended method of FS_IOC_ADD_ENCRYPTION_KEY. - */ -static struct key_type key_type_fscrypt = { - .name = "._fscrypt", - .instantiate = fscrypt_key_instantiate, - .destroy = fscrypt_key_destroy, - .describe = fscrypt_key_describe, -}; - static int fscrypt_user_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { @@ -131,32 +156,6 @@ static struct key_type key_type_fscrypt_ .describe = fscrypt_user_key_describe, };

-/* Search ->s_master_keys or ->mk_users */ -static struct key *search_fscrypt_keyring(struct key *keyring, - struct key_type *type, - const char *description) -{ - /* - * We need to mark the keyring reference as "possessed" so that we - * acquire permission to search it, via the KEY_POS_SEARCH permission. - */ - key_ref_t keyref = make_key_ref(keyring, true /* possessed */); - - keyref = keyring_search(keyref, type, description, false); - if (IS_ERR(keyref)) { - if (PTR_ERR(keyref) == -EAGAIN || /* not found */ - PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ - keyref = ERR_PTR(-ENOKEY); - return ERR_CAST(keyref); - } - return key_ref_to_ptr(keyref); -} - -#define FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE \ - (CONST_STRLEN("fscrypt-") + sizeof_field(struct super_block, s_id)) - -#define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1) - #define FSCRYPT_MK_USERS_DESCRIPTION_SIZE \ (CONST_STRLEN("fscrypt-") + 2 * FSCRYPT_KEY_IDENTIFIER_SIZE + \ CONST_STRLEN("-users") + 1) @@ -164,21 +163,6 @@ static struct key *search_fscrypt_keyrin #define FSCRYPT_MK_USER_DESCRIPTION_SIZE \ (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + CONST_STRLEN(".uid.") + 10 + 1)

-static void format_fs_keyring_description( - char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE], - const struct super_block *sb) -{ - sprintf(description, "fscrypt-%s", sb->s_id); -} - -static void format_mk_description( - char description[FSCRYPT_MK_DESCRIPTION_SIZE], - const struct fscrypt_key_specifier *mk_spec) -{ - sprintf(description, "%*phN", - master_key_spec_len(mk_spec), (u8 *)&mk_spec->u); -} - static void format_mk_users_keyring_description( char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE], const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) @@ -199,20 +183,15 @@ static void format_mk_user_description( /* Create ->s_master_keys if needed. Synchronized by fscrypt_add_key_mutex. */ static int allocate_filesystem_keyring(struct super_block *sb) { - char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE]; - struct key *keyring; + struct fscrypt_keyring *keyring;

if (sb->s_master_keys) return 0;

- format_fs_keyring_description(description, sb); - keyring = keyring_alloc(description, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, - current_cred(), KEY_POS_SEARCH | - KEY_USR_SEARCH | KEY_USR_READ | KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); - if (IS_ERR(keyring)) - return PTR_ERR(keyring); - + keyring = kzalloc(sizeof(*keyring), GFP_KERNEL); + if (!keyring) + return -ENOMEM; + spin_lock_init(&keyring->lock); /* * Pairs with the smp_load_acquire() in fscrypt_find_master_key(). * I.e., here we publish ->s_master_keys with a RELEASE barrier so that @@ -222,21 +201,75 @@ static int allocate_filesystem_keyring(s return 0; }

-void fscrypt_sb_free(struct super_block *sb) +/* + * This is called at unmount time to release all encryption keys that have been + * added to the filesystem, along with the keyring that contains them. + * + * Note that besides clearing and freeing memory, this might need to evict keys + * from the keyslots of an inline crypto engine. Therefore, this must be called + * while the filesystem's underlying block device(s) are still available. + */ +void fscrypt_sb_delete(struct super_block *sb) { - key_put(sb->s_master_keys); + struct fscrypt_keyring *keyring = sb->s_master_keys; + size_t i; + + if (!keyring) + return; + + for (i = 0; i < ARRAY_SIZE(keyring->key_hashtable); i++) { + struct hlist_head *bucket = &keyring->key_hashtable[i]; + struct fscrypt_master_key *mk; + struct hlist_node *tmp; + + hlist_for_each_entry_safe(mk, tmp, bucket, mk_node) { + /* + * Since all inodes were already evicted, every key + * remaining in the keyring should have an empty inode + * list, and should only still be in the keyring due to + * the single active ref associated with ->mk_secret. + * There should be no structural refs beyond the one + * associated with the active ref. + */ + WARN_ON(refcount_read(&mk->mk_active_refs) != 1); + WARN_ON(refcount_read(&mk->mk_struct_refs) != 1); + WARN_ON(!is_master_key_secret_present(&mk->mk_secret)); + wipe_master_key_secret(&mk->mk_secret); + fscrypt_put_master_key_activeref(mk); + } + } + kfree_sensitive(keyring); sb->s_master_keys = NULL; }

+static struct hlist_head * +fscrypt_mk_hash_bucket(struct fscrypt_keyring *keyring, + const struct fscrypt_key_specifier *mk_spec) +{ + /* + * Since key specifiers should be "random" values, it is sufficient to + * use a trivial hash function that just takes the first several bits of + * the key specifier. + */ + unsigned long i = get_unaligned((unsigned long *)&mk_spec->u); + + return &keyring->key_hashtable[i % ARRAY_SIZE(keyring->key_hashtable)]; +} + /* - * Find the specified master key in ->s_master_keys. - * Returns ERR_PTR(-ENOKEY) if not found. + * Find the specified master key struct in ->s_master_keys and take a structural + * ref to it. The structural ref guarantees that the key struct continues to + * exist, but it does *not* guarantee that ->s_master_keys continues to contain + * the key struct. The structural ref needs to be dropped by + * fscrypt_put_master_key(). Returns NULL if the key struct is not found. */ -struct key *fscrypt_find_master_key(struct super_block *sb, - const struct fscrypt_key_specifier *mk_spec) +struct fscrypt_master_key * +fscrypt_find_master_key(struct super_block *sb, + const struct fscrypt_key_specifier *mk_spec) { - struct key *keyring; - char description[FSCRYPT_MK_DESCRIPTION_SIZE]; + struct fscrypt_keyring *keyring; + struct hlist_head *bucket; + struct fscrypt_master_key *mk;

/* * Pairs with the smp_store_release() in allocate_filesystem_keyring(). @@ -246,10 +279,38 @@ struct key *fscrypt_find_master_key(stru */ keyring = smp_load_acquire(&sb->s_master_keys); if (keyring == NULL) - return ERR_PTR(-ENOKEY); /* No keyring yet, so no keys yet. */ + return NULL; /* No keyring yet, so no keys yet. */

- format_mk_description(description, mk_spec); - return search_fscrypt_keyring(keyring, &key_type_fscrypt, description); + bucket = fscrypt_mk_hash_bucket(keyring, mk_spec); + rcu_read_lock(); + switch (mk_spec->type) { + case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR: + hlist_for_each_entry_rcu(mk, bucket, mk_node) { + if (mk->mk_spec.type == + FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR && + memcmp(mk->mk_spec.u.descriptor, + mk_spec->u.descriptor, + FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 && + refcount_inc_not_zero(&mk->mk_struct_refs)) + goto out; + } + break; + case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER: + hlist_for_each_entry_rcu(mk, bucket, mk_node) { + if (mk->mk_spec.type == + FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER && + memcmp(mk->mk_spec.u.identifier, + mk_spec->u.identifier, + FSCRYPT_KEY_IDENTIFIER_SIZE) == 0 && + refcount_inc_not_zero(&mk->mk_struct_refs)) + goto out; + } + break; + } + mk = NULL; +out: + rcu_read_unlock(); + return mk; }

static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk) @@ -277,17 +338,30 @@ static int allocate_master_key_users_key static struct key *find_master_key_user(struct fscrypt_master_key *mk) { char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE]; + key_ref_t keyref;

format_mk_user_description(description, mk->mk_spec.u.identifier); - return search_fscrypt_keyring(mk->mk_users, &key_type_fscrypt_user, - description); + + /* + * We need to mark the keyring reference as "possessed" so that we + * acquire permission to search it, via the KEY_POS_SEARCH permission. + */ + keyref = keyring_search(make_key_ref(mk->mk_users, true /*possessed*/), + &key_type_fscrypt_user, description, false); + if (IS_ERR(keyref)) { + if (PTR_ERR(keyref) == -EAGAIN || /* not found */ + PTR_ERR(keyref) == -EKEYREVOKED) /* recently invalidated */ + keyref = ERR_PTR(-ENOKEY); + return ERR_CAST(keyref); + } + return key_ref_to_ptr(keyref); }

/* * Give the current user a "key" in ->mk_users. This charges the user's quota * and marks the master key as added by the current user, so that it cannot be - * removed by another user with the key. Either the master key's key->sem must - * be held for write, or the master key must be still undergoing initialization. + * removed by another user with the key. Either ->mk_sem must be held for + * write, or the master key must be still undergoing initialization. */ static int add_master_key_user(struct fscrypt_master_key *mk) { @@ -309,7 +383,7 @@ static int add_master_key_user(struct fs

/* * Remove the current user's "key" from ->mk_users. - * The master key's key->sem must be held for write. + * ->mk_sem must be held for write. * * Returns 0 if removed, -ENOKEY if not found, or another -errno code. */ @@ -327,63 +401,49 @@ static int remove_master_key_user(struct }

/* - * Allocate a new fscrypt_master_key which contains the given secret, set it as - * the payload of a new 'struct key' of type fscrypt, and link the 'struct key' - * into the given keyring. Synchronized by fscrypt_add_key_mutex. + * Allocate a new fscrypt_master_key, transfer the given secret over to it, and + * insert it into sb->s_master_keys. */ -static int add_new_master_key(struct fscrypt_master_key_secret *secret, - const struct fscrypt_key_specifier *mk_spec, - struct key *keyring) +static int add_new_master_key(struct super_block *sb, + struct fscrypt_master_key_secret *secret, + const struct fscrypt_key_specifier *mk_spec) { + struct fscrypt_keyring *keyring = sb->s_master_keys; struct fscrypt_master_key *mk; - char description[FSCRYPT_MK_DESCRIPTION_SIZE]; - struct key *key; int err;

mk = kzalloc(sizeof(*mk), GFP_KERNEL); if (!mk) return -ENOMEM;

+ mk->mk_sb = sb; + init_rwsem(&mk->mk_sem); + refcount_set(&mk->mk_struct_refs, 1); mk->mk_spec = *mk_spec;

- move_master_key_secret(&mk->mk_secret, secret); - - refcount_set(&mk->mk_refcount, 1); /* secret is present */ INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock);

if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = allocate_master_key_users_keyring(mk); if (err) - goto out_free_mk; + goto out_put; err = add_master_key_user(mk); if (err) - goto out_free_mk; + goto out_put; }

- /* - * Note that we don't charge this key to anyone's quota, since when - * ->mk_users is in use those keys are charged instead, and otherwise - * (when ->mk_users isn't in use) only root can add these keys. - */ - format_mk_description(description, mk_spec); - key = key_alloc(&key_type_fscrypt, description, - GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(), - KEY_POS_SEARCH | KEY_USR_SEARCH | KEY_USR_VIEW, - KEY_ALLOC_NOT_IN_QUOTA, NULL); - if (IS_ERR(key)) { - err = PTR_ERR(key); - goto out_free_mk; - } - err = key_instantiate_and_link(key, mk, sizeof(*mk), keyring, NULL); - key_put(key); - if (err) - goto out_free_mk; + move_master_key_secret(&mk->mk_secret, secret); + refcount_set(&mk->mk_active_refs, 1); /* ->mk_secret is present */

+ spin_lock(&keyring->lock); + hlist_add_head_rcu(&mk->mk_node, + fscrypt_mk_hash_bucket(keyring, mk_spec)); + spin_unlock(&keyring->lock); return 0;

-out_free_mk: - free_master_key(mk); +out_put: + fscrypt_put_master_key(mk); return err; }

@@ -392,42 +452,34 @@ out_free_mk: static int add_existing_master_key(struct fscrypt_master_key *mk, struct fscrypt_master_key_secret *secret) { - struct key *mk_user; - bool rekey; int err;

/* * If the current user is already in ->mk_users, then there's nothing to - * do. (Not applicable for v1 policy keys, which have NULL ->mk_users.) + * do. Otherwise, we need to add the user to ->mk_users. (Neither is + * applicable for v1 policy keys, which have NULL ->mk_users.) */ if (mk->mk_users) { - mk_user = find_master_key_user(mk); + struct key *mk_user = find_master_key_user(mk); + if (mk_user != ERR_PTR(-ENOKEY)) { if (IS_ERR(mk_user)) return PTR_ERR(mk_user); key_put(mk_user); return 0; } - } - - /* If we'll be re-adding ->mk_secret, try to take the reference. */ - rekey = !is_master_key_secret_present(&mk->mk_secret); - if (rekey && !refcount_inc_not_zero(&mk->mk_refcount)) - return KEY_DEAD; - - /* Add the current user to ->mk_users, if applicable. */ - if (mk->mk_users) { err = add_master_key_user(mk); - if (err) { - if (rekey && refcount_dec_and_test(&mk->mk_refcount)) - return KEY_DEAD; + if (err) return err; - } }

/* Re-add the secret if needed. */ - if (rekey) + if (!is_master_key_secret_present(&mk->mk_secret)) { + if (!refcount_inc_not_zero(&mk->mk_active_refs)) + return KEY_DEAD; move_master_key_secret(&mk->mk_secret, secret); + } + return 0; }

@@ -436,38 +488,36 @@ static int do_add_master_key(struct supe const struct fscrypt_key_specifier *mk_spec) { static DEFINE_MUTEX(fscrypt_add_key_mutex); - struct key *key; + struct fscrypt_master_key *mk; int err;

mutex_lock(&fscrypt_add_key_mutex); /* serialize find + link */ -retry: - key = fscrypt_find_master_key(sb, mk_spec); - if (IS_ERR(key)) { - err = PTR_ERR(key); - if (err != -ENOKEY) - goto out_unlock; + + mk = fscrypt_find_master_key(sb, mk_spec); + if (!mk) { /* Didn't find the key in ->s_master_keys. Add it. */ err = allocate_filesystem_keyring(sb); - if (err) - goto out_unlock; - err = add_new_master_key(secret, mk_spec, sb->s_master_keys); + if (!err) + err = add_new_master_key(sb, secret, mk_spec); } else { /* * Found the key in ->s_master_keys. Re-add the secret if * needed, and add the user to ->mk_users if needed. */ - down_write(&key->sem); - err = add_existing_master_key(key->payload.data[0], secret); - up_write(&key->sem); + down_write(&mk->mk_sem); + err = add_existing_master_key(mk, secret); + up_write(&mk->mk_sem); if (err == KEY_DEAD) { - /* Key being removed or needs to be removed */ - key_invalidate(key); - key_put(key); - goto retry; + /* + * We found a key struct, but it's already been fully + * removed. Ignore the old struct and add a new one. + * fscrypt_add_key_mutex means we don't need to worry + * about concurrent adds. + */ + err = add_new_master_key(sb, secret, mk_spec); } - key_put(key); + fscrypt_put_master_key(mk); } -out_unlock: mutex_unlock(&fscrypt_add_key_mutex); return err; } @@ -731,19 +781,19 @@ int fscrypt_verify_key_added(struct supe const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]) { struct fscrypt_key_specifier mk_spec; - struct key *key, *mk_user; struct fscrypt_master_key *mk; + struct key *mk_user; int err;

mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER; memcpy(mk_spec.u.identifier, identifier, FSCRYPT_KEY_IDENTIFIER_SIZE);

- key = fscrypt_find_master_key(sb, &mk_spec); - if (IS_ERR(key)) { - err = PTR_ERR(key); + mk = fscrypt_find_master_key(sb, &mk_spec); + if (!mk) { + err = -ENOKEY; goto out; } - mk = key->payload.data[0]; + down_read(&mk->mk_sem); mk_user = find_master_key_user(mk); if (IS_ERR(mk_user)) { err = PTR_ERR(mk_user); @@ -751,7 +801,8 @@ int fscrypt_verify_key_added(struct supe key_put(mk_user); err = 0; } - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); out: if (err == -ENOKEY && capable(CAP_FOWNER)) err = 0; @@ -913,11 +964,10 @@ static int do_remove_key(struct file *fi struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_remove_key_arg __user *uarg = _uarg; struct fscrypt_remove_key_arg arg; - struct key *key; struct fscrypt_master_key *mk; u32 status_flags = 0; int err; - bool dead; + bool inodes_remain;

if (copy_from_user(&arg, uarg, sizeof(arg))) return -EFAULT; @@ -937,12 +987,10 @@ static int do_remove_key(struct file *fi return -EACCES;

/* Find the key being removed. */ - key = fscrypt_find_master_key(sb, &arg.key_spec); - if (IS_ERR(key)) - return PTR_ERR(key); - mk = key->payload.data[0]; - - down_write(&key->sem); + mk = fscrypt_find_master_key(sb, &arg.key_spec); + if (!mk) + return -ENOKEY; + down_write(&mk->mk_sem);

/* If relevant, remove current user's (or all users) claim to the key */ if (mk->mk_users && mk->mk_users->keys.nr_leaves_on_tree != 0) { @@ -951,7 +999,7 @@ static int do_remove_key(struct file *fi else err = remove_master_key_user(mk); if (err) { - up_write(&key->sem); + up_write(&mk->mk_sem); goto out_put_key; } if (mk->mk_users->keys.nr_leaves_on_tree != 0) { @@ -963,26 +1011,22 @@ static int do_remove_key(struct file *fi status_flags |= FSCRYPT_KEY_REMOVAL_STATUS_FLAG_OTHER_USERS; err = 0; - up_write(&key->sem); + up_write(&mk->mk_sem); goto out_put_key; } }

/* No user claims remaining. Go ahead and wipe the secret. */ - dead = false; + err = -ENOKEY; if (is_master_key_secret_present(&mk->mk_secret)) { wipe_master_key_secret(&mk->mk_secret); - dead = refcount_dec_and_test(&mk->mk_refcount); - } - up_write(&key->sem); - if (dead) { - /* - * No inodes reference the key, and we wiped the secret, so the - * key object is free to be removed from the keyring. - */ - key_invalidate(key); + fscrypt_put_master_key_activeref(mk); err = 0; - } else { + } + inodes_remain = refcount_read(&mk->mk_active_refs) > 0; + up_write(&mk->mk_sem); + + if (inodes_remain) { /* Some inodes still reference this key; try to evict them. */ err = try_to_lock_encrypted_files(sb, mk); if (err == -EBUSY) { @@ -998,7 +1042,7 @@ static int do_remove_key(struct file *fi * has been fully removed including all files locked. */ out_put_key: - key_put(key); + fscrypt_put_master_key(mk); if (err == 0) err = put_user(status_flags, &uarg->removal_status_flags); return err; @@ -1045,7 +1089,6 @@ int fscrypt_ioctl_get_key_status(struct { struct super_block *sb = file_inode(filp)->i_sb; struct fscrypt_get_key_status_arg arg; - struct key *key; struct fscrypt_master_key *mk; int err;

@@ -1062,19 +1105,18 @@ int fscrypt_ioctl_get_key_status(struct arg.user_count = 0; memset(arg.__out_reserved, 0, sizeof(arg.__out_reserved));

- key = fscrypt_find_master_key(sb, &arg.key_spec); - if (IS_ERR(key)) { - if (key != ERR_PTR(-ENOKEY)) - return PTR_ERR(key); + mk = fscrypt_find_master_key(sb, &arg.key_spec); + if (!mk) { arg.status = FSCRYPT_KEY_STATUS_ABSENT; err = 0; goto out; } - mk = key->payload.data[0]; - down_read(&key->sem); + down_read(&mk->mk_sem);

if (!is_master_key_secret_present(&mk->mk_secret)) { - arg.status = FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED; + arg.status = refcount_read(&mk->mk_active_refs) > 0 ? + FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED : + FSCRYPT_KEY_STATUS_ABSENT /* raced with full removal */; err = 0; goto out_release_key; } @@ -1096,8 +1138,8 @@ int fscrypt_ioctl_get_key_status(struct } err = 0; out_release_key: - up_read(&key->sem); - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); out: if (!err && copy_to_user(uarg, &arg, sizeof(arg))) err = -EFAULT; @@ -1109,13 +1151,9 @@ int __init fscrypt_init_keyring(void) { int err;

- err = register_key_type(&key_type_fscrypt); - if (err) - return err; - err = register_key_type(&key_type_fscrypt_user); if (err) - goto err_unregister_fscrypt; + return err;

err = register_key_type(&key_type_fscrypt_provisioning); if (err) @@ -1125,7 +1163,5 @@ int __init fscrypt_init_keyring(void)

err_unregister_fscrypt_user: unregister_key_type(&key_type_fscrypt_user); -err_unregister_fscrypt: - unregister_key_type(&key_type_fscrypt); return err; } --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -9,7 +9,6 @@ */

#include <crypto/skcipher.h> -#include <linux/key.h> #include <linux/random.h>

#include "fscrypt_private.h" @@ -151,6 +150,7 @@ void fscrypt_destroy_prepared_key(struct { crypto_free_skcipher(prep_key->tfm); fscrypt_destroy_inline_crypt_key(prep_key); + memzero_explicit(prep_key, sizeof(*prep_key)); }

/* Given a per-file encryption key, set up the file's crypto transform object */ @@ -404,20 +404,18 @@ static bool fscrypt_valid_master_key_siz /* * Find the master key, then set up the inode's actual encryption key. * - * If the master key is found in the filesystem-level keyring, then the - * corresponding 'struct key' is returned in *master_key_ret with its semaphore - * read-locked. This is needed to ensure that only one task links the - * fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race to create - * an fscrypt_info for the same inode), and to synchronize the master key being - * removed with a new inode starting to use it. + * If the master key is found in the filesystem-level keyring, then it is + * returned in *mk_ret with its semaphore read-locked. This is needed to ensure + * that only one task links the fscrypt_info into ->mk_decrypted_inodes (as + * multiple tasks may race to create an fscrypt_info for the same inode), and to + * synchronize the master key being removed with a new inode starting to use it. */ static int setup_file_encryption_key(struct fscrypt_info *ci, bool need_dirhash_key, - struct key **master_key_ret) + struct fscrypt_master_key **mk_ret) { - struct key *key; - struct fscrypt_master_key *mk = NULL; struct fscrypt_key_specifier mk_spec; + struct fscrypt_master_key *mk; int err;

err = fscrypt_select_encryption_impl(ci); @@ -442,11 +440,10 @@ static int setup_file_encryption_key(str return -EINVAL; }

- key = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); - if (IS_ERR(key)) { - if (key != ERR_PTR(-ENOKEY) || - ci->ci_policy.version != FSCRYPT_POLICY_V1) - return PTR_ERR(key); + mk = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec); + if (!mk) { + if (ci->ci_policy.version != FSCRYPT_POLICY_V1) + return -ENOKEY;

/* * As a legacy fallback for v1 policies, search for the key in @@ -456,9 +453,7 @@ static int setup_file_encryption_key(str */ return fscrypt_setup_v1_file_key_via_subscribed_keyrings(ci); } - - mk = key->payload.data[0]; - down_read(&key->sem); + down_read(&mk->mk_sem);

/* Has the secret been removed (via FS_IOC_REMOVE_ENCRYPTION_KEY)? */ if (!is_master_key_secret_present(&mk->mk_secret)) { @@ -486,18 +481,18 @@ static int setup_file_encryption_key(str if (err) goto out_release_key;

- *master_key_ret = key; + *mk_ret = mk; return 0;

out_release_key: - up_read(&key->sem); - key_put(key); + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); return err; }

static void put_crypt_info(struct fscrypt_info *ci) { - struct key *key; + struct fscrypt_master_key *mk;

if (!ci) return; @@ -507,24 +502,18 @@ static void put_crypt_info(struct fscryp else if (ci->ci_owns_key) fscrypt_destroy_prepared_key(&ci->ci_enc_key);

- key = ci->ci_master_key; - if (key) { - struct fscrypt_master_key *mk = key->payload.data[0]; - + mk = ci->ci_master_key; + if (mk) { /* * Remove this inode from the list of inodes that were unlocked - * with the master key. - * - * In addition, if we're removing the last inode from a key that - * already had its secret removed, invalidate the key so that it - * gets removed from ->s_master_keys. + * with the master key. In addition, if we're removing the last + * inode from a master key struct that already had its secret + * removed, then complete the full removal of the struct. */ spin_lock(&mk->mk_decrypted_inodes_lock); list_del(&ci->ci_master_key_link); spin_unlock(&mk->mk_decrypted_inodes_lock); - if (refcount_dec_and_test(&mk->mk_refcount)) - key_invalidate(key); - key_put(key); + fscrypt_put_master_key_activeref(mk); } memzero_explicit(ci, sizeof(*ci)); kmem_cache_free(fscrypt_info_cachep, ci); @@ -538,7 +527,7 @@ fscrypt_setup_encryption_info(struct ino { struct fscrypt_info *crypt_info; struct fscrypt_mode *mode; - struct key *master_key = NULL; + struct fscrypt_master_key *mk = NULL; int res;

res = fscrypt_initialize(inode->i_sb->s_cop->flags); @@ -561,8 +550,7 @@ fscrypt_setup_encryption_info(struct ino WARN_ON(mode->ivsize > FSCRYPT_MAX_IV_SIZE); crypt_info->ci_mode = mode;

- res = setup_file_encryption_key(crypt_info, need_dirhash_key, - &master_key); + res = setup_file_encryption_key(crypt_info, need_dirhash_key, &mk); if (res) goto out;

@@ -577,12 +565,9 @@ fscrypt_setup_encryption_info(struct ino * We won the race and set ->i_crypt_info to our crypt_info. * Now link it into the master key's inode list. */ - if (master_key) { - struct fscrypt_master_key *mk = - master_key->payload.data[0]; - - refcount_inc(&mk->mk_refcount); - crypt_info->ci_master_key = key_get(master_key); + if (mk) { + crypt_info->ci_master_key = mk; + refcount_inc(&mk->mk_active_refs); spin_lock(&mk->mk_decrypted_inodes_lock); list_add(&crypt_info->ci_master_key_link, &mk->mk_decrypted_inodes); @@ -592,9 +577,9 @@ fscrypt_setup_encryption_info(struct ino } res = 0; out: - if (master_key) { - up_read(&master_key->sem); - key_put(master_key); + if (mk) { + up_read(&mk->mk_sem); + fscrypt_put_master_key(mk); } put_crypt_info(crypt_info); return res; @@ -745,7 +730,6 @@ EXPORT_SYMBOL(fscrypt_free_inode); int fscrypt_drop_inode(struct inode *inode) { const struct fscrypt_info *ci = fscrypt_get_info(inode); - const struct fscrypt_master_key *mk;

/* * If ci is NULL, then the inode doesn't have an encryption key set up @@ -755,7 +739,6 @@ int fscrypt_drop_inode(struct inode *ino */ if (!ci || !ci->ci_master_key) return 0; - mk = ci->ci_master_key->payload.data[0];

/* * With proper, non-racy use of FS_IOC_REMOVE_ENCRYPTION_KEY, all inodes @@ -774,6 +757,6 @@ int fscrypt_drop_inode(struct inode *ino * then the thread removing the key will either evict the inode itself * or will correctly detect that it wasn't evicted due to the race. */ - return !is_master_key_secret_present(&mk->mk_secret); + return !is_master_key_secret_present(&ci->ci_master_key->mk_secret); } EXPORT_SYMBOL_GPL(fscrypt_drop_inode); --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -686,12 +686,8 @@ int fscrypt_set_context(struct inode *in * delayed key setup that requires the inode number. */ if (ci->ci_policy.version == FSCRYPT_POLICY_V2 && - (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) { - const struct fscrypt_master_key *mk = - ci->ci_master_key->payload.data[0]; - - fscrypt_hash_inode_number(ci, mk); - } + (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32)) + fscrypt_hash_inode_number(ci, ci->ci_master_key);

return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, fs_data); } --- a/fs/super.c +++ b/fs/super.c @@ -293,7 +293,6 @@ static void __put_super(struct super_blo WARN_ON(s->s_inode_lru.node); WARN_ON(!list_empty(&s->s_mounts)); security_sb_free(s); - fscrypt_sb_free(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); call_rcu(&s->rcu, destroy_super_rcu); @@ -454,6 +453,7 @@ void generic_shutdown_super(struct super evict_inodes(sb); /* only nonzero refcount inodes can have marks */ fsnotify_sb_delete(sb); + fscrypt_sb_delete(sb);

if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1437,7 +1437,7 @@ struct super_block { const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; - struct key *s_master_keys; /* master crypto keys in use */ + struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ #endif #ifdef CONFIG_FS_VERITY const struct fsverity_operations *s_vop; --- a/include/linux/fscrypt.h +++ b/include/linux/fscrypt.h @@ -193,7 +193,7 @@ fscrypt_free_dummy_policy(struct fscrypt }

/* keyring.c */ -void fscrypt_sb_free(struct super_block *sb); +void fscrypt_sb_delete(struct super_block *sb); int fscrypt_ioctl_add_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key(struct file *filp, void __user *arg); int fscrypt_ioctl_remove_key_all_users(struct file *filp, void __user *arg); @@ -380,7 +380,7 @@ fscrypt_free_dummy_policy(struct fscrypt }

/* keyring.c */ -static inline void fscrypt_sb_free(struct super_block *sb) +static inline void fscrypt_sb_delete(struct super_block *sb) { }

From: Kuniyuki Iwashima kuniyu@amazon.com

commit 3c52c6bb831f6335c176a0fc7214e26f43adbd11 upstream.

syzbot reported a memory leak [0] related to IPV6_ADDRFORM.

The scenario is that while one thread is converting an IPv6 socket into IPv4 with IPV6_ADDRFORM, another thread calls do_ipv6_setsockopt() and allocates memory to inet6_sk(sk)->XXX after conversion.

Then, the converted sk with (tcp|udp)_prot never frees the IPv6 resources, which inet6_destroy_sock() should have cleaned up.

setsockopt(IPV6_ADDRFORM) setsockopt(IPV6_DSTOPTS) +-----------------------+ +----------------------+ - do_ipv6_setsockopt(sk, ...) - sockopt_lock_sock(sk) - do_ipv6_setsockopt(sk, ...) - lock_sock(sk) ^._ called via tcpv6_prot - WRITE_ONCE(sk->sk_prot, &tcp_prot) before WRITE_ONCE() - xchg(&np->opt, NULL) - txopt_put(opt) - sockopt_release_sock(sk) - release_sock(sk) - sockopt_lock_sock(sk) - lock_sock(sk) - ipv6_set_opt_hdr(sk, ...) - ipv6_update_options(sk, opt) - xchg(&inet6_sk(sk)->opt, opt) ^._ opt is never freed.

- sockopt_release_sock(sk) - release_sock(sk)

Since IPV6_DSTOPTS allocates options under lock_sock(), we can avoid this memory leak by testing whether sk_family is changed by IPV6_ADDRFORM after acquiring the lock.

This issue exists from the initial commit between IPV6_ADDRFORM and IPV6_PKTOPTIONS.

[0]: BUG: memory leak unreferenced object 0xffff888009ab9f80 (size 96): comm "syz-executor583", pid 328, jiffies 4294916198 (age 13.034s) hex dump (first 32 bytes): 01 00 00 00 48 00 00 00 08 00 00 00 00 00 00 00 ....H........... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<000000002ee98ae1>] kmalloc include/linux/slab.h:605 [inline] [<000000002ee98ae1>] sock_kmalloc+0xb3/0x100 net/core/sock.c:2566 [<0000000065d7b698>] ipv6_renew_options+0x21e/0x10b0 net/ipv6/exthdrs.c:1318 [<00000000a8c756d7>] ipv6_set_opt_hdr net/ipv6/ipv6_sockglue.c:354 [inline] [<00000000a8c756d7>] do_ipv6_setsockopt.constprop.0+0x28b7/0x4350 net/ipv6/ipv6_sockglue.c:668 [<000000002854d204>] ipv6_setsockopt+0xdf/0x190 net/ipv6/ipv6_sockglue.c:1021 [<00000000e69fdcf8>] tcp_setsockopt+0x13b/0x2620 net/ipv4/tcp.c:3789 [<0000000090da4b9b>] __sys_setsockopt+0x239/0x620 net/socket.c:2252 [<00000000b10d192f>] __do_sys_setsockopt net/socket.c:2263 [inline] [<00000000b10d192f>] __se_sys_setsockopt net/socket.c:2260 [inline] [<00000000b10d192f>] __x64_sys_setsockopt+0xbe/0x160 net/socket.c:2260 [<000000000a80d7aa>] do_syscall_x64 arch/x86/entry/common.c:50 [inline] [<000000000a80d7aa>] do_syscall_64+0x38/0x90 arch/x86/entry/common.c:80 [<000000004562b5c6>] entry_SYSCALL_64_after_hwframe+0x63/0xcd

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Meena Shanmugam meenashanmugam@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ipv6_sockglue.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -417,6 +417,12 @@ static int do_ipv6_setsockopt(struct soc rtnl_lock(); lock_sock(sk);

+ /* Another thread has converted the socket into IPv4 with + * IPV6_ADDRFORM concurrently. + */ + if (unlikely(sk->sk_family != AF_INET6)) + goto unlock; + switch (optname) {

case IPV6_ADDRFORM: @@ -976,6 +982,7 @@ done: break; }

+unlock: release_sock(sk); if (needs_rtnl) rtnl_unlock();

From: Vasily Averin vvs@virtuozzo.com

commit 18319498fdd4cdf8c1c2c48cd432863b1f915d6f upstream.

When user creates IPC objects it forces kernel to allocate memory for these long-living objects.

It makes sense to account them to restrict the host's memory consumption from inside the memcg-limited container.

This patch enables accounting for IPC shared memory segments, messages semaphores and semaphore's undo lists.

Link: https://lkml.kernel.org/r/d6507b06-4df6-78f8-6c54-3ae86e3b5339@virtuozzo.com Signed-off-by: Vasily Averin vvs@virtuozzo.com Reviewed-by: Shakeel Butt shakeelb@google.com Cc: Alexander Viro viro@zeniv.linux.org.uk Cc: Alexey Dobriyan adobriyan@gmail.com Cc: Andrei Vagin avagin@gmail.com Cc: Borislav Petkov bp@alien8.de Cc: Borislav Petkov bp@suse.de Cc: Christian Brauner christian.brauner@ubuntu.com Cc: Dmitry Safonov 0x7f454c46@gmail.com Cc: "Eric W. Biederman" ebiederm@xmission.com Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: "H. Peter Anvin" hpa@zytor.com Cc: Ingo Molnar mingo@redhat.com Cc: "J. Bruce Fields" bfields@fieldses.org Cc: Jeff Layton jlayton@kernel.org Cc: Jens Axboe axboe@kernel.dk Cc: Jiri Slaby jirislaby@kernel.org Cc: Johannes Weiner hannes@cmpxchg.org Cc: Kirill Tkhai ktkhai@virtuozzo.com Cc: Michal Hocko mhocko@kernel.org Cc: Oleg Nesterov oleg@redhat.com Cc: Roman Gushchin guro@fb.com Cc: Serge Hallyn serge@hallyn.com Cc: Tejun Heo tj@kernel.org Cc: Thomas Gleixner tglx@linutronix.de Cc: Vladimir Davydov vdavydov.dev@gmail.com Cc: Yutian Yang nglaive@gmail.com Cc: Zefan Li lizefan.x@bytedance.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Luiz Capitulino luizcap@amazon.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- ipc/msg.c | 2 +- ipc/sem.c | 9 +++++---- ipc/shm.c | 2 +- 3 files changed, 7 insertions(+), 6 deletions(-)

--- a/ipc/msg.c +++ b/ipc/msg.c @@ -147,7 +147,7 @@ static int newque(struct ipc_namespace * key_t key = params->key; int msgflg = params->flg;

- msq = kvmalloc(sizeof(*msq), GFP_KERNEL); + msq = kvmalloc(sizeof(*msq), GFP_KERNEL_ACCOUNT); if (unlikely(!msq)) return -ENOMEM;

--- a/ipc/sem.c +++ b/ipc/sem.c @@ -511,7 +511,7 @@ static struct sem_array *sem_alloc(size_ if (nsems > (INT_MAX - sizeof(*sma)) / sizeof(sma->sems[0])) return NULL;

- sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL); + sma = kvzalloc(struct_size(sma, sems, nsems), GFP_KERNEL_ACCOUNT); if (unlikely(!sma)) return NULL;

@@ -1852,7 +1852,7 @@ static inline int get_undo_list(struct s

undo_list = current->sysvsem.undo_list; if (!undo_list) { - undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL); + undo_list = kzalloc(sizeof(*undo_list), GFP_KERNEL_ACCOUNT); if (undo_list == NULL) return -ENOMEM; spin_lock_init(&undo_list->lock); @@ -1937,7 +1937,7 @@ static struct sem_undo *find_alloc_undo( rcu_read_unlock();

/* step 2: allocate new undo structure */ - new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL); + new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL_ACCOUNT); if (!new) { ipc_rcu_putref(&sma->sem_perm, sem_rcu_free); return ERR_PTR(-ENOMEM); @@ -2001,7 +2001,8 @@ static long do_semtimedop(int semid, str if (nsops > ns->sc_semopm) return -E2BIG; if (nsops > SEMOPM_FAST) { - sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); + sops = kvmalloc_array(nsops, sizeof(*sops), + GFP_KERNEL_ACCOUNT); if (sops == NULL) return -ENOMEM; } --- a/ipc/shm.c +++ b/ipc/shm.c @@ -711,7 +711,7 @@ static int newseg(struct ipc_namespace * ns->shm_tot + numpages > ns->shm_ctlall) return -ENOSPC;

- shp = kvmalloc(sizeof(*shp), GFP_KERNEL); + shp = kvmalloc(sizeof(*shp), GFP_KERNEL_ACCOUNT); if (unlikely(!shp)) return -ENOMEM;

From: James Clark james.clark@arm.com

commit 6746eae4bbaddcc16b40efb33dab79210828b3ce upstream.

cti_enable_hw() and cti_disable_hw() are called from an atomic context so shouldn't use runtime PM because it can result in a sleep when communicating with firmware.

Since commit 3c6656337852 ("Revert "firmware: arm_scmi: Add clock management to the SCMI power domain""), this causes a hang on Juno when running the Perf Coresight tests or running this command:

perf record -e cs_etm//u -- ls

This was also missed until the revert commit because pm_runtime_put() was called with the wrong device until commit 692c9a499b28 ("coresight: cti: Correct the parameter for pm_runtime_put")

With lock and scheduler debugging enabled the following is output:

coresight cti_sys0: cti_enable_hw -- dev:cti_sys0 parent: 20020000.cti BUG: sleeping function called from invalid context at drivers/base/power/runtime.c:1151 in_atomic(): 1, irqs_disabled(): 128, non_block: 0, pid: 330, name: perf-exec preempt_count: 2, expected: 0 RCU nest depth: 0, expected: 0 INFO: lockdep is turned off. irq event stamp: 0 hardirqs last enabled at (0): [<0000000000000000>] 0x0 hardirqs last disabled at (0): [<ffff80000822b394>] copy_process+0xa0c/0x1948 softirqs last enabled at (0): [<ffff80000822b394>] copy_process+0xa0c/0x1948 softirqs last disabled at (0): [<0000000000000000>] 0x0 CPU: 3 PID: 330 Comm: perf-exec Not tainted 6.0.0-00053-g042116d99298 #7 Hardware name: ARM LTD ARM Juno Development Platform/ARM Juno Development Platform, BIOS EDK II Sep 13 2022 Call trace: dump_backtrace+0x134/0x140 show_stack+0x20/0x58 dump_stack_lvl+0x8c/0xb8 dump_stack+0x18/0x34 __might_resched+0x180/0x228 __might_sleep+0x50/0x88 __pm_runtime_resume+0xac/0xb0 cti_enable+0x44/0x120 coresight_control_assoc_ectdev+0xc0/0x150 coresight_enable_path+0xb4/0x288 etm_event_start+0x138/0x170 etm_event_add+0x48/0x70 event_sched_in.isra.122+0xb4/0x280 merge_sched_in+0x1fc/0x3d0 visit_groups_merge.constprop.137+0x16c/0x4b0 ctx_sched_in+0x114/0x1f0 perf_event_sched_in+0x60/0x90 ctx_resched+0x68/0xb0 perf_event_exec+0x138/0x508 begin_new_exec+0x52c/0xd40 load_elf_binary+0x6b8/0x17d0 bprm_execve+0x360/0x7f8 do_execveat_common.isra.47+0x218/0x238 __arm64_sys_execve+0x48/0x60 invoke_syscall+0x4c/0x110 el0_svc_common.constprop.4+0xfc/0x120 do_el0_svc+0x34/0xc0 el0_svc+0x40/0x98 el0t_64_sync_handler+0x98/0xc0 el0t_64_sync+0x170/0x174

Fix the issue by removing the runtime PM calls completely. They are not needed here because it must have already been done when building the path for a trace.

Fixes: 835d722ba10a ("coresight: cti: Initial CoreSight CTI Driver") Cc: stable stable@kernel.org Reported-by: Aishwarya TCV Aishwarya.TCV@arm.com Reported-by: Cristian Marussi Cristian.Marussi@arm.com Suggested-by: Suzuki K Poulose suzuki.poulose@arm.com Signed-off-by: James Clark james.clark@arm.com Reviewed-by: Mike Leach mike.leach@linaro.org Tested-by: Mike Leach mike.leach@linaro.org [ Fix build warnings ] Signed-off-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20221025131032.1149459-1-suzuki.poulose@arm.com Signed-off-by: James Clark james.clark@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hwtracing/coresight/coresight-cti-core.c | 5 ----- 1 file changed, 5 deletions(-)

--- a/drivers/hwtracing/coresight/coresight-cti-core.c +++ b/drivers/hwtracing/coresight/coresight-cti-core.c @@ -90,11 +90,9 @@ void cti_write_all_hw_regs(struct cti_dr static int cti_enable_hw(struct cti_drvdata *drvdata) { struct cti_config *config = &drvdata->config; - struct device *dev = &drvdata->csdev->dev; unsigned long flags; int rc = 0;

- pm_runtime_get_sync(dev->parent); spin_lock_irqsave(&drvdata->spinlock, flags);

/* no need to do anything if enabled or unpowered*/ @@ -119,7 +117,6 @@ cti_state_unchanged: /* cannot enable due to error */ cti_err_not_enabled: spin_unlock_irqrestore(&drvdata->spinlock, flags); - pm_runtime_put(dev->parent); return rc; }

@@ -153,7 +150,6 @@ cti_hp_not_enabled: static int cti_disable_hw(struct cti_drvdata *drvdata) { struct cti_config *config = &drvdata->config; - struct device *dev = &drvdata->csdev->dev;

spin_lock(&drvdata->spinlock);

@@ -174,7 +170,6 @@ static int cti_disable_hw(struct cti_drv coresight_disclaim_device_unlocked(drvdata->base); CS_LOCK(drvdata->base); spin_unlock(&drvdata->spinlock); - pm_runtime_put(dev->parent); return 0;

/* not disabled this call */

From: Li Huafei lihuafei1@huawei.com

commit 0e792b89e6800cd9cb4757a76a96f7ef3e8b6294 upstream.

KASAN reported a use-after-free with ftrace ops [1]. It was found from vmcore that perf had registered two ops with the same content successively, both dynamic. After unregistering the second ops, a use-after-free occurred.

In ftrace_shutdown(), when the second ops is unregistered, the FTRACE_UPDATE_CALLS command is not set because there is another enabled ops with the same content. Also, both ops are dynamic and the ftrace callback function is ftrace_ops_list_func, so the FTRACE_UPDATE_TRACE_FUNC command will not be set. Eventually the value of 'command' will be 0 and ftrace_shutdown() will skip the rcu synchronization.

However, ftrace may be activated. When the ops is released, another CPU may be accessing the ops. Add the missing synchronization to fix this problem.

[1] BUG: KASAN: use-after-free in __ftrace_ops_list_func kernel/trace/ftrace.c:7020 [inline] BUG: KASAN: use-after-free in ftrace_ops_list_func+0x2b0/0x31c kernel/trace/ftrace.c:7049 Read of size 8 at addr ffff56551965bbc8 by task syz-executor.2/14468

CPU: 1 PID: 14468 Comm: syz-executor.2 Not tainted 5.10.0 #7 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x40c arch/arm64/kernel/stacktrace.c:132 show_stack+0x30/0x40 arch/arm64/kernel/stacktrace.c:196 __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x1b4/0x248 lib/dump_stack.c:118 print_address_description.constprop.0+0x28/0x48c mm/kasan/report.c:387 __kasan_report mm/kasan/report.c:547 [inline] kasan_report+0x118/0x210 mm/kasan/report.c:564 check_memory_region_inline mm/kasan/generic.c:187 [inline] __asan_load8+0x98/0xc0 mm/kasan/generic.c:253 __ftrace_ops_list_func kernel/trace/ftrace.c:7020 [inline] ftrace_ops_list_func+0x2b0/0x31c kernel/trace/ftrace.c:7049 ftrace_graph_call+0x0/0x4 __might_sleep+0x8/0x100 include/linux/perf_event.h:1170 __might_fault mm/memory.c:5183 [inline] __might_fault+0x58/0x70 mm/memory.c:5171 do_strncpy_from_user lib/strncpy_from_user.c:41 [inline] strncpy_from_user+0x1f4/0x4b0 lib/strncpy_from_user.c:139 getname_flags+0xb0/0x31c fs/namei.c:149 getname+0x2c/0x40 fs/namei.c:209 [...]

Allocated by task 14445: kasan_save_stack+0x24/0x50 mm/kasan/common.c:48 kasan_set_track mm/kasan/common.c:56 [inline] __kasan_kmalloc mm/kasan/common.c:479 [inline] __kasan_kmalloc.constprop.0+0x110/0x13c mm/kasan/common.c:449 kasan_kmalloc+0xc/0x14 mm/kasan/common.c:493 kmem_cache_alloc_trace+0x440/0x924 mm/slub.c:2950 kmalloc include/linux/slab.h:563 [inline] kzalloc include/linux/slab.h:675 [inline] perf_event_alloc.part.0+0xb4/0x1350 kernel/events/core.c:11230 perf_event_alloc kernel/events/core.c:11733 [inline] __do_sys_perf_event_open kernel/events/core.c:11831 [inline] __se_sys_perf_event_open+0x550/0x15f4 kernel/events/core.c:11723 __arm64_sys_perf_event_open+0x6c/0x80 kernel/events/core.c:11723 [...]

Freed by task 14445: kasan_save_stack+0x24/0x50 mm/kasan/common.c:48 kasan_set_track+0x24/0x34 mm/kasan/common.c:56 kasan_set_free_info+0x20/0x40 mm/kasan/generic.c:358 __kasan_slab_free.part.0+0x11c/0x1b0 mm/kasan/common.c:437 __kasan_slab_free mm/kasan/common.c:445 [inline] kasan_slab_free+0x2c/0x40 mm/kasan/common.c:446 slab_free_hook mm/slub.c:1569 [inline] slab_free_freelist_hook mm/slub.c:1608 [inline] slab_free mm/slub.c:3179 [inline] kfree+0x12c/0xc10 mm/slub.c:4176 perf_event_alloc.part.0+0xa0c/0x1350 kernel/events/core.c:11434 perf_event_alloc kernel/events/core.c:11733 [inline] __do_sys_perf_event_open kernel/events/core.c:11831 [inline] __se_sys_perf_event_open+0x550/0x15f4 kernel/events/core.c:11723 [...]

Link: https://lore.kernel.org/linux-trace-kernel/20221103031010.166498-1-lihuafei1...

Fixes: edb096e00724f ("ftrace: Fix memleak when unregistering dynamic ops when tracing disabled") Cc: stable@vger.kernel.org Suggested-by: Steven Rostedt rostedt@goodmis.org Signed-off-by: Li Huafei lihuafei1@huawei.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/ftrace.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-)

--- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2946,18 +2946,8 @@ int ftrace_shutdown(struct ftrace_ops *o command |= FTRACE_UPDATE_TRACE_FUNC; }

- if (!command || !ftrace_enabled) { - /* - * If these are dynamic or per_cpu ops, they still - * need their data freed. Since, function tracing is - * not currently active, we can just free them - * without synchronizing all CPUs. - */ - if (ops->flags & FTRACE_OPS_FL_DYNAMIC) - goto free_ops; - - return 0; - } + if (!command || !ftrace_enabled) + goto out;

/* * If the ops uses a trampoline, then it needs to be @@ -2994,6 +2984,7 @@ int ftrace_shutdown(struct ftrace_ops *o removed_ops = NULL; ops->flags &= ~FTRACE_OPS_FL_REMOVING;

+out: /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. @@ -3021,7 +3012,6 @@ int ftrace_shutdown(struct ftrace_ops *o if (IS_ENABLED(CONFIG_PREEMPTION)) synchronize_rcu_tasks();

- free_ops: ftrace_trampoline_free(ops); }

From: Shang XiaoJing shangxiaojing@huawei.com

commit 66f0919c953ef7b55e5ab94389a013da2ce80a2c upstream.

test_gen_kprobe_cmd() only free buf in fail path, hence buf will leak when there is no failure. Move kfree(buf) from fail path to common path to prevent the memleak. The same reason and solution in test_gen_kretprobe_cmd().

unreferenced object 0xffff888143b14000 (size 2048): comm "insmod", pid 52490, jiffies 4301890980 (age 40.553s) hex dump (first 32 bytes): 70 3a 6b 70 72 6f 62 65 73 2f 67 65 6e 5f 6b 70 p:kprobes/gen_kp 72 6f 62 65 5f 74 65 73 74 20 64 6f 5f 73 79 73 robe_test do_sys backtrace: [<000000006d7b836b>] kmalloc_trace+0x27/0xa0 [<0000000009528b5b>] 0xffffffffa059006f [<000000008408b580>] do_one_initcall+0x87/0x2a0 [<00000000c4980a7e>] do_init_module+0xdf/0x320 [<00000000d775aad0>] load_module+0x3006/0x3390 [<00000000e9a74b80>] __do_sys_finit_module+0x113/0x1b0 [<000000003726480d>] do_syscall_64+0x35/0x80 [<000000003441e93b>] entry_SYSCALL_64_after_hwframe+0x46/0xb0

Link: https://lore.kernel.org/all/20221102072954.26555-1-shangxiaojing@huawei.com/

Fixes: 64836248dda2 ("tracing: Add kprobe event command generation test module") Cc: stable@vger.kernel.org Signed-off-by: Shang XiaoJing shangxiaojing@huawei.com Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Masami Hiramatsu (Google) mhiramat@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/kprobe_event_gen_test.c | 18 +++++++----------- 1 file changed, 7 insertions(+), 11 deletions(-)

--- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -100,20 +100,20 @@ static int __init test_gen_kprobe_cmd(vo KPROBE_GEN_TEST_FUNC, KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1); if (ret) - goto free; + goto out;

/* Use kprobe_event_add_fields to add the rest of the fields */

ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3); if (ret) - goto free; + goto out;

/* * This actually creates the event. */ ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out;

/* * Now get the gen_kprobe_test event file. We need to prevent @@ -136,13 +136,11 @@ static int __init test_gen_kprobe_cmd(vo goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kprobe_test"); - free: - kfree(buf); - goto out; }

@@ -170,14 +168,14 @@ static int __init test_gen_kretprobe_cmd KPROBE_GEN_TEST_FUNC, "$retval"); if (ret) - goto free; + goto out;

/* * This actually creates the event. */ ret = kretprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out;

/* * Now get the gen_kretprobe_test event file. We need to @@ -201,13 +199,11 @@ static int __init test_gen_kretprobe_cmd goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kretprobe_test"); - free: - kfree(buf); - goto out; }

From: Rasmus Villemoes linux@rasmusvillemoes.dk

commit b3f4f51ea68a495f8a5956064c33dce711a2df91 upstream.

The C standard says that memcmp() must treat the buffers as consisting of "unsigned chars". If char happens to be unsigned, the casts are ok, but then obviously the c1 variable can never contain a negative value. And when char is signed, the casts are wrong, and there's still a problem with using an 8-bit quantity to hold the difference, because that can range from -255 to +255.

For example, assuming char is signed, comparing two 1-byte buffers, one containing 0x00 and another 0x80, the current implementation would return -128 for both memcmp(a, b, 1) and memcmp(b, a, 1), whereas one of those should of course return something positive.

Signed-off-by: Rasmus Villemoes linux@rasmusvillemoes.dk Fixes: 66b6f755ad45 ("rcutorture: Import a copy of nolibc") Cc: stable@vger.kernel.org # v5.0+ Signed-off-by: Willy Tarreau w@1wt.eu Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/include/nolibc/nolibc.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/tools/include/nolibc/nolibc.h +++ b/tools/include/nolibc/nolibc.h @@ -2318,9 +2318,9 @@ static __attribute__((unused)) int memcmp(const void *s1, const void *s2, size_t n) { size_t ofs = 0; - char c1 = 0; + int c1 = 0;

- while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) { ofs++; } return c1;

From: Gaosheng Cui cuigaosheng1@huawei.com

commit 8cf0a1bc12870d148ae830a4ba88cfdf0e879cee upstream.

In cap_inode_getsecurity(), we will use vfs_getxattr_alloc() to complete the memory allocation of tmpbuf, if we have completed the memory allocation of tmpbuf, but failed to call handler->get(...), there will be a memleak in below logic:

|-- ret = (int)vfs_getxattr_alloc(mnt_userns, ...) | /* ^^^ alloc for tmpbuf */ |-- value = krealloc(*xattr_value, error + 1, flags) | /* ^^^ alloc memory */ |-- error = handler->get(handler, ...) | /* error! */ |-- *xattr_value = value | /* xattr_value is &tmpbuf (memory leak!) */

So we will try to free(tmpbuf) after vfs_getxattr_alloc() fails to fix it.

Cc: stable@vger.kernel.org Fixes: 8db6c34f1dbc ("Introduce v3 namespaced file capabilities") Signed-off-by: Gaosheng Cui cuigaosheng1@huawei.com Acked-by: Serge Hallyn serge@hallyn.com [PM: subject line and backtrace tweaks] Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/commoncap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/security/commoncap.c +++ b/security/commoncap.c @@ -391,8 +391,10 @@ int cap_inode_getsecurity(struct inode * &tmpbuf, size, GFP_NOFS); dput(dentry);

- if (ret < 0 || !tmpbuf) - return ret; + if (ret < 0 || !tmpbuf) { + size = ret; + goto out_free; + }

fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf;

From: Ard Biesheuvel ardb@kernel.org

commit 161a438d730dade2ba2b1bf8785f0759aba4ca5f upstream.

We no longer need at least 64 bytes of random seed to permit the early crng init to complete. The RNG is now based on Blake2s, so reduce the EFI seed size to the Blake2s hash size, which is sufficient for our purposes.

While at it, drop the READ_ONCE(), which was supposed to prevent size from being evaluated after seed was unmapped. However, this cannot actually happen, so READ_ONCE() is unnecessary here.

Cc: stable@vger.kernel.org # v4.14+ Signed-off-by: Ard Biesheuvel ardb@kernel.org Reviewed-by: Jason A. Donenfeld Jason@zx2c4.com Acked-by: Ilias Apalodimas ilias.apalodimas@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/firmware/efi/efi.c | 2 +- include/linux/efi.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -590,7 +590,7 @@ int __init efi_config_parse_tables(const

seed = early_memremap(efi_rng_seed, sizeof(*seed)); if (seed != NULL) { - size = READ_ONCE(seed->size); + size = min(seed->size, EFI_RANDOM_SEED_SIZE); early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1161,7 +1161,7 @@ void efi_retrieve_tpm2_eventlog(void); arch_efi_call_virt_teardown(); \ })

-#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE

struct linux_efi_random_seed { u32 size;

From: Kan Liang kan.liang@linux.intel.com

commit acc5568b90c19ac6375508a93b9676cd18a92a35 upstream.

According to the latest event list, update the MEM_INST_RETIRED events which support the DataLA facility.

Fixes: 6017608936c1 ("perf/x86/intel: Add Icelake support") Reported-by: Jannis Klinkenberg jannis.klinkenberg@rwth-aachen.de Signed-off-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20221031154119.571386-1-kan.liang@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/events/intel/ds.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -855,8 +855,13 @@ struct event_constraint intel_icl_pebs_e INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */

INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */

INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */

From: Helge Deller deller@gmx.de

commit e8a18e3f00f3ee8d07c17ab1ea3ad4df4a3b6fe0 upstream.

Although the name of the driver 8250_gsc.c suggests that it handles only serial ports on the GSC bus, it does handle serial ports listed in the parisc machine inventory as well, e.g. the serial ports in a C8000 PCI-only workstation.

Change the dependency to CONFIG_PARISC, so that the driver gets included in the kernel even if CONFIG_GSC isn't set.

Reported-by: Mikulas Patocka mpatocka@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/8250/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -119,7 +119,7 @@ config SERIAL_8250_CONSOLE

config SERIAL_8250_GSC tristate - depends on SERIAL_8250 && GSC + depends on SERIAL_8250 && PARISC default SERIAL_8250

config SERIAL_8250_DMA

From: Helge Deller deller@gmx.de

commit 2b6ae0962b421103feb41a80406732944b0665b3 upstream.

Avoid that the hardware path is shown twice in the kernel log, and clean up the output of the version numbers to show up in the same order as they are listed in the hardware database in the hardware.c file. Additionally, optimize the memory footprint of the hardware database and mark some code as init code.

Fixes: cab56b51ec0e ("parisc: Fix device names in /proc/iomem") Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org # v4.9+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/parisc/include/asm/hardware.h | 12 ++++++------ arch/parisc/kernel/drivers.c | 14 ++++++-------- 2 files changed, 12 insertions(+), 14 deletions(-)

--- a/arch/parisc/include/asm/hardware.h +++ b/arch/parisc/include/asm/hardware.h @@ -10,12 +10,12 @@ #define SVERSION_ANY_ID PA_SVERSION_ANY_ID

struct hp_hardware { - unsigned short hw_type:5; /* HPHW_xxx */ - unsigned short hversion; - unsigned long sversion:28; - unsigned short opt; - const char name[80]; /* The hardware description */ -}; + unsigned int hw_type:8; /* HPHW_xxx */ + unsigned int hversion:12; + unsigned int sversion:12; + unsigned char opt; + unsigned char name[59]; /* The hardware description */ +} __packed;

struct parisc_device;

--- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -883,15 +883,13 @@ void __init walk_central_bus(void) &root); }

-static void print_parisc_device(struct parisc_device *dev) +static __init void print_parisc_device(struct parisc_device *dev) { - char hw_path[64]; - static int count; + static int count __initdata;

- print_pa_hwpath(dev, hw_path); - pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }", - ++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type, - dev->id.hversion_rev, dev->id.hversion, dev->id.sversion); + pr_info("%d. %s at %pap { type:%d, hv:%#x, sv:%#x, rev:%#x }", + ++count, dev->name, &(dev->hpa.start), dev->id.hw_type, + dev->id.hversion, dev->id.sversion, dev->id.hversion_rev);

if (dev->num_addrs) { int k; @@ -1080,7 +1078,7 @@ static __init int qemu_print_iodc_data(s

-static int print_one_device(struct device * dev, void * data) +static __init int print_one_device(struct device * dev, void * data) { struct parisc_device * pdev = to_parisc_device(dev);

From: Luís Henriques lhenriques@suse.de

commit 17a0bc9bd697f75cfdf9b378d5eb2d7409c91340 upstream.

The rec_len field in the directory entry has to be a multiple of 4. A corrupted filesystem image can be used to hit a BUG() in ext4_rec_len_to_disk(), called from make_indexed_dir().

------------[ cut here ]------------ kernel BUG at fs/ext4/ext4.h:2413! ... RIP: 0010:make_indexed_dir+0x53f/0x5f0 ... Call Trace: <TASK> ? add_dirent_to_buf+0x1b2/0x200 ext4_add_entry+0x36e/0x480 ext4_add_nondir+0x2b/0xc0 ext4_create+0x163/0x200 path_openat+0x635/0xe90 do_filp_open+0xb4/0x160 ? __create_object.isra.0+0x1de/0x3b0 ? _raw_spin_unlock+0x12/0x30 do_sys_openat2+0x91/0x150 __x64_sys_open+0x6c/0xa0 do_syscall_64+0x3c/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0

The fix simply adds a call to ext4_check_dir_entry() to validate the directory entry, returning -EFSCORRUPTED if the entry is invalid.

CC: stable@kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=216540 Signed-off-by: Luís Henriques lhenriques@suse.de Link: https://lore.kernel.org/r/20221012131330.32456-1-lhenriques@suse.de Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/namei.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2153,8 +2153,16 @@ static int make_indexed_dir(handle_t *ha memcpy(data2, de, len); de = (struct ext4_dir_entry_2 *) data2; top = data2 + len; - while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) + while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { + if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, + (data2 + (blocksize - csum_size) - + (char *) de))) { + brelse(bh2); + brelse(bh); + return -EFSCORRUPTED; + } de = de2; + } de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - (char *) de, blocksize);

From: Jim Mattson jmattson@google.com

commit 079f6889818dd07903fb36c252532ab47ebb6d48 upstream.

KVM_GET_SUPPORTED_CPUID should only enumerate features that KVM actually supports. In the case of CPUID.8000001AH, only three bits are currently defined. The 125 reserved bits should be masked off.

Fixes: 24c82e576b78 ("KVM: Sanitize cpuid") Signed-off-by: Jim Mattson jmattson@google.com Message-Id: 20220929225203.2234702-4-jmattson@google.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/cpuid.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -860,6 +860,9 @@ static inline int __do_cpuid_func(struct entry->ecx = entry->edx = 0; break; case 0x8000001a: + entry->eax &= GENMASK(2, 0); + entry->ebx = entry->ecx = entry->edx = 0; + break; case 0x8000001e: break; /* Support memory encryption cpuid if host supports it */

From: Jim Mattson jmattson@google.com

commit 0469e56a14bf8cfb80507e51b7aeec0332cdbc13 upstream.

KVM_GET_SUPPORTED_CPUID should only enumerate features that KVM actually supports. CPUID.80000001:EBX[27:16] are reserved bits and should be masked off.

Fixes: 0771671749b5 ("KVM: Enhance guest cpuid management") Signed-off-by: Jim Mattson jmattson@google.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/cpuid.c | 1 + 1 file changed, 1 insertion(+)

--- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -813,6 +813,7 @@ static inline int __do_cpuid_func(struct entry->eax = min(entry->eax, 0x8000001f); break; case 0x80000001: + entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break;

From: Maxim Levitsky mlevitsk@redhat.com

commit d087e0f79fa0dd336a9a6b2f79ec23120f5eff73 upstream.

Some instructions update the cpu execution mode, which needs to update the emulation mode.

Extract this code, and make assign_eip_far use it.

assign_eip_far now reads CS, instead of getting it via a parameter, which is ok, because callers always assign CS to the same value before calling this function.

No functional change is intended.

Signed-off-by: Maxim Levitsky mlevitsk@redhat.com Message-Id: 20221025124741.228045-12-mlevitsk@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/emulate.c | 85 ++++++++++++++++++++++++++++++++----------------- 1 file changed, 57 insertions(+), 28 deletions(-)

--- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -796,8 +796,7 @@ static int linearize(struct x86_emulate_ ctxt->mode, linear); }

-static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -807,41 +806,71 @@ static inline int assign_eip(struct x86_

if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; }

+static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); }

-static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt);

-#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc;

- ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); }

static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -2256,7 +2285,7 @@ static int em_jmp_far(struct x86_emulate if (rc != X86EMUL_CONTINUE) return rc;

- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2337,7 +2366,7 @@ static int em_ret_far(struct x86_emulate &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -3554,7 +3583,7 @@ static int em_call_far(struct x86_emulat if (rc != X86EMUL_CONTINUE) return rc;

- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail;

From: Matthew Wilcox (Oracle) willy@infradead.org

commit 4fa0e3ff217f775cb58d2d6d51820ec519243fb9 upstream.

The recent change of page_cache_ra_unbounded() arguments was buggy in the two callers, causing us to readahead the wrong pages. Move the definition of ractl down to after the index is set correctly. This affected performance on configurations that use fs-verity.

Link: https://lkml.kernel.org/r/20221012193419.1453558-1-willy@infradead.org Fixes: 73bb49da50cd ("mm/readahead: make page_cache_ra_unbounded take a readahead_control") Signed-off-by: Matthew Wilcox (Oracle) willy@infradead.org Reported-by: Jintao Yin nicememory@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Eric Biggers ebiggers@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/verity.c | 3 ++- fs/f2fs/verity.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -370,13 +370,14 @@ static struct page *ext4_read_merkle_tre pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index); struct page *page;

index += ext4_verity_metadata_pos(inode) >> PAGE_SHIFT;

page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1) --- a/fs/f2fs/verity.c +++ b/fs/f2fs/verity.c @@ -261,13 +261,14 @@ static struct page *f2fs_read_merkle_tre pgoff_t index, unsigned long num_ra_pages) { - DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index); struct page *page;

index += f2fs_verity_metadata_pos(inode) >> PAGE_SHIFT;

page = find_get_page_flags(inode->i_mapping, index, FGP_ACCESSED); if (!page || !PageUptodate(page)) { + DEFINE_READAHEAD(ractl, NULL, inode->i_mapping, index); + if (page) put_page(page); else if (num_ra_pages > 1)

From: Ville Syrjälä ville.syrjala@linux.intel.com

commit 3e206b6aa6df7eed4297577e0cf8403169b800a2 upstream.

We try to filter out the corresponding xxx1 output if the xxx0 output is not present. But the way that is being done is pretty awkward. Make it less so.

Cc: stable@vger.kernel.org Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20221026101134.20865-2-ville.s... Reviewed-by: Jani Nikula jani.nikula@intel.com (cherry picked from commit cc1e66394daaa7e9f005e2487a84e34a39f9308b) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_sdvo.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-)

--- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2937,16 +2937,33 @@ err: return false; }

+static u16 intel_sdvo_filter_output_flags(u16 flags) +{ + flags &= SDVO_OUTPUT_MASK; + + /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + if (!(flags & SDVO_OUTPUT_TMDS0)) + flags &= ~SDVO_OUTPUT_TMDS1; + + if (!(flags & SDVO_OUTPUT_RGB0)) + flags &= ~SDVO_OUTPUT_RGB1; + + if (!(flags & SDVO_OUTPUT_LVDS0)) + flags &= ~SDVO_OUTPUT_LVDS1; + + return flags; +} + static bool intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags) { - /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/ + flags = intel_sdvo_filter_output_flags(flags);

if (flags & SDVO_OUTPUT_TMDS0) if (!intel_sdvo_dvi_init(intel_sdvo, 0)) return false;

- if ((flags & SDVO_TMDS_MASK) == SDVO_TMDS_MASK) + if (flags & SDVO_OUTPUT_TMDS1) if (!intel_sdvo_dvi_init(intel_sdvo, 1)) return false;

@@ -2967,7 +2984,7 @@ intel_sdvo_output_setup(struct intel_sdv if (!intel_sdvo_analog_init(intel_sdvo, 0)) return false;

- if ((flags & SDVO_RGB_MASK) == SDVO_RGB_MASK) + if (flags & SDVO_OUTPUT_RGB1) if (!intel_sdvo_analog_init(intel_sdvo, 1)) return false;

@@ -2975,11 +2992,11 @@ intel_sdvo_output_setup(struct intel_sdv if (!intel_sdvo_lvds_init(intel_sdvo, 0)) return false;

- if ((flags & SDVO_LVDS_MASK) == SDVO_LVDS_MASK) + if (flags & SDVO_OUTPUT_LVDS1) if (!intel_sdvo_lvds_init(intel_sdvo, 1)) return false;

- if ((flags & SDVO_OUTPUT_MASK) == 0) { + if (flags == 0) { unsigned char bytes[2];

intel_sdvo->controlled_output = 0;

From: Dokyung Song dokyung.song@gmail.com

commit 6788ba8aed4e28e90f72d68a9d794e34eac17295 upstream.

This patch fixes an intra-object buffer overflow in brcmfmac that occurs when the device provides a 'bsscfgidx' equal to or greater than the buffer size. The patch adds a check that leads to a safe failure if that is the case.

This fixes CVE-2022-3628.

UBSAN: array-index-out-of-bounds in drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c index 52 is out of range for type 'brcmf_if *[16]' CPU: 0 PID: 1898 Comm: kworker/0:2 Tainted: G O 5.14.0+ #132 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Workqueue: events brcmf_fweh_event_worker Call Trace: dump_stack_lvl+0x57/0x7d ubsan_epilogue+0x5/0x40 __ubsan_handle_out_of_bounds+0x69/0x80 ? memcpy+0x39/0x60 brcmf_fweh_event_worker+0xae1/0xc00 ? brcmf_fweh_call_event_handler.isra.0+0x100/0x100 ? rcu_read_lock_sched_held+0xa1/0xd0 ? rcu_read_lock_bh_held+0xb0/0xb0 ? lockdep_hardirqs_on_prepare+0x273/0x3e0 process_one_work+0x873/0x13e0 ? lock_release+0x640/0x640 ? pwq_dec_nr_in_flight+0x320/0x320 ? rwlock_bug.part.0+0x90/0x90 worker_thread+0x8b/0xd10 ? __kthread_parkme+0xd9/0x1d0 ? process_one_work+0x13e0/0x13e0 kthread+0x379/0x450 ? _raw_spin_unlock_irq+0x24/0x30 ? set_kthread_struct+0x100/0x100 ret_from_fork+0x1f/0x30 ================================================================================ general protection fault, probably for non-canonical address 0xe5601c0020023fff: 0000 [#1] SMP KASAN KASAN: maybe wild-memory-access in range [0x2b0100010011fff8-0x2b0100010011ffff] CPU: 0 PID: 1898 Comm: kworker/0:2 Tainted: G O 5.14.0+ #132 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 Workqueue: events brcmf_fweh_event_worker RIP: 0010:brcmf_fweh_call_event_handler.isra.0+0x42/0x100 Code: 89 f5 53 48 89 fb 48 83 ec 08 e8 79 0b 38 fe 48 85 ed 74 7e e8 6f 0b 38 fe 48 89 ea 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 8b 00 00 00 4c 8b 7d 00 44 89 e0 48 ba 00 00 00 RSP: 0018:ffffc9000259fbd8 EFLAGS: 00010207 RAX: dffffc0000000000 RBX: ffff888115d8cd50 RCX: 0000000000000000 RDX: 0560200020023fff RSI: ffffffff8304bc91 RDI: ffff888115d8cd50 RBP: 2b0100010011ffff R08: ffff888112340050 R09: ffffed1023549809 R10: ffff88811aa4c047 R11: ffffed1023549808 R12: 0000000000000045 R13: ffffc9000259fca0 R14: ffff888112340050 R15: ffff888112340000 FS: 0000000000000000(0000) GS:ffff88811aa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000004053ccc0 CR3: 0000000112740000 CR4: 0000000000750ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Call Trace: brcmf_fweh_event_worker+0x117/0xc00 ? brcmf_fweh_call_event_handler.isra.0+0x100/0x100 ? rcu_read_lock_sched_held+0xa1/0xd0 ? rcu_read_lock_bh_held+0xb0/0xb0 ? lockdep_hardirqs_on_prepare+0x273/0x3e0 process_one_work+0x873/0x13e0 ? lock_release+0x640/0x640 ? pwq_dec_nr_in_flight+0x320/0x320 ? rwlock_bug.part.0+0x90/0x90 worker_thread+0x8b/0xd10 ? __kthread_parkme+0xd9/0x1d0 ? process_one_work+0x13e0/0x13e0 kthread+0x379/0x450 ? _raw_spin_unlock_irq+0x24/0x30 ? set_kthread_struct+0x100/0x100 ret_from_fork+0x1f/0x30 Modules linked in: 88XXau(O) 88x2bu(O) ---[ end trace 41d302138f3ff55a ]--- RIP: 0010:brcmf_fweh_call_event_handler.isra.0+0x42/0x100 Code: 89 f5 53 48 89 fb 48 83 ec 08 e8 79 0b 38 fe 48 85 ed 74 7e e8 6f 0b 38 fe 48 89 ea 48 b8 00 00 00 00 00 fc ff df 48 c1 ea 03 <80> 3c 02 00 0f 85 8b 00 00 00 4c 8b 7d 00 44 89 e0 48 ba 00 00 00 RSP: 0018:ffffc9000259fbd8 EFLAGS: 00010207 RAX: dffffc0000000000 RBX: ffff888115d8cd50 RCX: 0000000000000000 RDX: 0560200020023fff RSI: ffffffff8304bc91 RDI: ffff888115d8cd50 RBP: 2b0100010011ffff R08: ffff888112340050 R09: ffffed1023549809 R10: ffff88811aa4c047 R11: ffffed1023549808 R12: 0000000000000045 R13: ffffc9000259fca0 R14: ffff888112340050 R15: ffff888112340000 FS: 0000000000000000(0000) GS:ffff88811aa00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000004053ccc0 CR3: 0000000112740000 CR4: 0000000000750ef0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 PKRU: 55555554 Kernel panic - not syncing: Fatal exception

Reported-by: Dokyung Song dokyungs@yonsei.ac.kr Reported-by: Jisoo Jang jisoo.jang@yonsei.ac.kr Reported-by: Minsuk Kang linuxlovemin@yonsei.ac.kr Reviewed-by: Arend van Spriel aspriel@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Dokyung Song dokyung.song@gmail.com Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://lore.kernel.org/r/20221021061359.GA550858@laguna Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c | 4 ++++ 1 file changed, 4 insertions(+)

--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fweh.c @@ -228,6 +228,10 @@ static void brcmf_fweh_event_worker(stru brcmf_fweh_event_name(event->code), event->code, event->emsg.ifidx, event->emsg.bsscfgidx, event->emsg.addr); + if (event->emsg.bsscfgidx >= BRCMF_MAX_IFS) { + bphy_err(drvr, "invalid bsscfg index: %u\n", event->emsg.bsscfgidx); + goto event_free; + }

/* convert event message */ emsg_be = &event->emsg;