From: Zhang Qiao zhangqiao22@huawei.com

commit 05c7b7a92cc87ff8d7fde189d0fade250697573c upstream.

As previously discussed(https://lkml.org/lkml/2022/1/20/51), cpuset_attach() is affected with similar cpu hotplug race, as follow scenario:

cpuset_attach() cpu hotplug --------------------------- ---------------------- down_write(cpuset_rwsem) guarantee_online_cpus() // (load cpus_attach) sched_cpu_deactivate set_cpu_active() // will change cpu_active_mask set_cpus_allowed_ptr(cpus_attach) __set_cpus_allowed_ptr_locked() // (if the intersection of cpus_attach and cpu_active_mask is empty, will return -EINVAL) up_write(cpuset_rwsem)

To avoid races such as described above, protect cpuset_attach() call with cpu_hotplug_lock.

Fixes: be367d099270 ("cgroups: let ss->can_attach and ss->attach do whole threadgroups at a time") Cc: stable@vger.kernel.org # v2.6.32+ Reported-by: Zhao Gongyi zhaogongyi@huawei.com Signed-off-by: Zhang Qiao zhangqiao22@huawei.com Acked-by: Waiman Long longman@redhat.com Reviewed-by: Michal Koutný mkoutny@suse.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/cgroup/cpuset.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2249,6 +2249,7 @@ static void cpuset_attach(struct cgroup_ cgroup_taskset_first(tset, &css); cs = css_cs(css);

+ cpus_read_lock(); percpu_down_write(&cpuset_rwsem);

guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2302,6 +2303,7 @@ static void cpuset_attach(struct cgroup_ wake_up(&cpuset_attach_wq);

percpu_up_write(&cpuset_rwsem); + cpus_read_unlock(); }

/* The various types of files and directories in a cpuset file system */

From: Andy Lutomirski luto@kernel.org

commit 44cad52cc14ae10062f142ec16ede489bccf4469 upstream.

xfpregs_set() handles 32-bit REGSET_XFP and 64-bit REGSET_FP. The actual code treats these regsets as modern FX state (i.e. the beginning part of XSTATE). The declarations of the regsets thought they were the legacy i387 format. The code thought they were the 32-bit (no xmm8..15) variant of XSTATE and, for good measure, made the high bits disappear by zeroing the wrong part of the buffer. The latter broke ptrace, and everything else confused anyone trying to understand the code. In particular, the nonsense definitions of the regsets confused me when I wrote this code.

Clean this all up. Change the declarations to match reality (which shouldn't change the generated code, let alone the ABI) and fix xfpregs_set() to clear the correct bits and to only do so for 32-bit callers.

Fixes: 6164331d15f7 ("x86/fpu: Rewrite xfpregs_set()") Reported-by: Luís Ferreira contact@lsferreira.net Signed-off-by: Andy Lutomirski luto@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=215524 Link: https://lore.kernel.org/r/YgpFnZpF01WwR8wU@zn.tnic Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/fpu/regset.c | 9 ++++----- arch/x86/kernel/ptrace.c | 4 ++-- 2 files changed, 6 insertions(+), 7 deletions(-)

--- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -87,11 +87,9 @@ int xfpregs_set(struct task_struct *targ const void *kbuf, const void __user *ubuf) { struct fpu *fpu = &target->thread.fpu; - struct user32_fxsr_struct newstate; + struct fxregs_state newstate; int ret;

- BUILD_BUG_ON(sizeof(newstate) != sizeof(struct fxregs_state)); - if (!cpu_feature_enabled(X86_FEATURE_FXSR)) return -ENODEV;

@@ -112,9 +110,10 @@ int xfpregs_set(struct task_struct *targ /* Copy the state */ memcpy(&fpu->state.fxsave, &newstate, sizeof(newstate));

- /* Clear xmm8..15 */ + /* Clear xmm8..15 for 32-bit callers */ BUILD_BUG_ON(sizeof(fpu->state.fxsave.xmm_space) != 16 * 16); - memset(&fpu->state.fxsave.xmm_space[8], 0, 8 * 16); + if (in_ia32_syscall()) + memset(&fpu->state.fxsave.xmm_space[8*4], 0, 8 * 16);

/* Mark FP and SSE as in use when XSAVE is enabled */ if (use_xsave()) --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -1224,7 +1224,7 @@ static struct user_regset x86_64_regsets }, [REGSET_FP] = { .core_note_type = NT_PRFPREG, - .n = sizeof(struct user_i387_struct) / sizeof(long), + .n = sizeof(struct fxregs_state) / sizeof(long), .size = sizeof(long), .align = sizeof(long), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set }, @@ -1271,7 +1271,7 @@ static struct user_regset x86_32_regsets }, [REGSET_XFP] = { .core_note_type = NT_PRXFPREG, - .n = sizeof(struct user32_fxsr_struct) / sizeof(u32), + .n = sizeof(struct fxregs_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set },

From: Su Yue l@damenly.su

commit ea1d1ca4025ac6c075709f549f9aa036b5b6597d upstream.

Check item size before accessing the device item to avoid out of bound access, similar to inode_item check.

Signed-off-by: Su Yue l@damenly.su Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/tree-checker.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -965,6 +965,7 @@ static int check_dev_item(struct extent_ struct btrfs_key *key, int slot) { struct btrfs_dev_item *ditem; + const u32 item_size = btrfs_item_size_nr(leaf, slot);

if (unlikely(key->objectid != BTRFS_DEV_ITEMS_OBJECTID)) { dev_item_err(leaf, slot, @@ -972,6 +973,13 @@ static int check_dev_item(struct extent_ key->objectid, BTRFS_DEV_ITEMS_OBJECTID); return -EUCLEAN; } + + if (unlikely(item_size != sizeof(*ditem))) { + dev_item_err(leaf, slot, "invalid item size: has %u expect %zu", + item_size, sizeof(*ditem)); + return -EUCLEAN; + } + ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item); if (unlikely(btrfs_device_id(leaf, ditem) != key->offset)) { dev_item_err(leaf, slot,

From: Jens Axboe axboe@kernel.dk

commit 228339662b398a59b3560cd571deb8b25b253c7e upstream.

If an application calls io_uring_enter(2) with a timespec passed in, convert that timespec to ktime_t rather than jiffies. The latter does not provide the granularity the application may expect, and may in fact provided different granularity on different systems, depending on what the HZ value is configured at.

Turn the timespec into an absolute ktime_t, and use that with schedule_hrtimeout() instead.

Link: https://github.com/axboe/liburing/issues/531 Cc: stable@vger.kernel.org Reported-by: Bob Chen chenbo.chen@alibaba-inc.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -7590,7 +7590,7 @@ static int io_run_task_work_sig(void) /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, - signed long *timeout) + ktime_t timeout) { int ret;

@@ -7602,8 +7602,9 @@ static inline int io_cqring_wait_schedul if (test_bit(0, &ctx->check_cq_overflow)) return 1;

- *timeout = schedule_timeout(*timeout); - return !*timeout ? -ETIME : 1; + if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + return -ETIME; + return 1; }

/* @@ -7616,7 +7617,7 @@ static int io_cqring_wait(struct io_ring { struct io_wait_queue iowq; struct io_rings *rings = ctx->rings; - signed long timeout = MAX_SCHEDULE_TIMEOUT; + ktime_t timeout = KTIME_MAX; int ret;

do { @@ -7632,7 +7633,7 @@ static int io_cqring_wait(struct io_ring

if (get_timespec64(&ts, uts)) return -EFAULT; - timeout = timespec64_to_jiffies(&ts); + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); }

if (sig) { @@ -7664,7 +7665,7 @@ static int io_cqring_wait(struct io_ring } prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); - ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); + ret = io_cqring_wait_schedule(ctx, &iowq, timeout); finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0);

From: Ondrej Mosnacek omosnace@redhat.com

commit ce2fc710c9d2b25afc710f49bb2065b4439a62bc upstream.

mutex_is_locked() tests whether the mutex is locked *by any task*, while here we want to test if it is held *by the current task*. To avoid false/missed WARNINGs, use lockdep_assert_is_held() and lockdep_assert_is_not_held() instead, which do the right thing (though they are a no-op if CONFIG_LOCKDEP=n).

Cc: stable@vger.kernel.org Fixes: 2554a48f4437 ("selinux: measure state and policy capabilities") Signed-off-by: Ondrej Mosnacek omosnace@redhat.com Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/selinux/ima.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/security/selinux/ima.c +++ b/security/selinux/ima.c @@ -77,7 +77,7 @@ void selinux_ima_measure_state_locked(st size_t policy_len; int rc = 0;

- WARN_ON(!mutex_is_locked(&state->policy_mutex)); + lockdep_assert_held(&state->policy_mutex);

state_str = selinux_ima_collect_state(state); if (!state_str) { @@ -117,7 +117,7 @@ void selinux_ima_measure_state_locked(st */ void selinux_ima_measure_state(struct selinux_state *state) { - WARN_ON(mutex_is_locked(&state->policy_mutex)); + lockdep_assert_not_held(&state->policy_mutex);

mutex_lock(&state->policy_mutex); selinux_ima_measure_state_locked(state);

From: Helge Deller deller@gmx.de

commit dd2288f4a020d693360e3e8d72f8b9d9c25f5ef6 upstream.

Usually the kernel provides fixup routines to emulate the fldd and fstd floating-point instructions if they load or store 8-byte from/to a not natuarally aligned memory location.

On a 32-bit kernel I noticed that those unaligned handlers didn't worked and instead the application got a SEGV. While checking the code I found two problems:

First, the OPCODE_FLDD_L and OPCODE_FSTD_L cases were ifdef'ed out by the CONFIG_PA20 option, and as such those weren't built on a pure 32-bit kernel. This is now fixed by moving the CONFIG_PA20 #ifdef to prevent the compilation of OPCODE_LDD_L and OPCODE_FSTD_L only, and handling the fldd and fstd instructions.

The second problem are two bugs in the 32-bit inline assembly code, where the wrong registers where used. The calculation of the natural alignment used %2 (vall) instead of %3 (ior), and the first word was stored back to address %1 (valh) instead of %3 (ior).

Signed-off-by: Helge Deller deller@gmx.de Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/parisc/kernel/unaligned.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -397,7 +397,7 @@ static int emulate_std(struct pt_regs *r __asm__ __volatile__ ( " mtsp %4, %%sr1\n" " zdep %2, 29, 2, %%r19\n" -" dep %%r0, 31, 2, %2\n" +" dep %%r0, 31, 2, %3\n" " mtsar %%r19\n" " zvdepi -2, 32, %%r19\n" "1: ldw 0(%%sr1,%3),%%r20\n" @@ -409,7 +409,7 @@ static int emulate_std(struct pt_regs *r " andcm %%r21, %%r19, %%r21\n" " or %1, %%r20, %1\n" " or %2, %%r21, %2\n" -"3: stw %1,0(%%sr1,%1)\n" +"3: stw %1,0(%%sr1,%3)\n" "4: stw %%r1,4(%%sr1,%3)\n" "5: stw %2,8(%%sr1,%3)\n" " copy %%r0, %0\n" @@ -596,7 +596,6 @@ void handle_unaligned(struct pt_regs *re ret = ERR_NOTHANDLED; /* "undefined", but lets kill them. */ break; } -#ifdef CONFIG_PA20 switch (regs->iir & OPCODE2_MASK) { case OPCODE_FLDD_L: @@ -607,14 +606,15 @@ void handle_unaligned(struct pt_regs *re flop=1; ret = emulate_std(regs, R2(regs->iir),1); break; +#ifdef CONFIG_PA20 case OPCODE_LDD_L: ret = emulate_ldd(regs, R2(regs->iir),0); break; case OPCODE_STD_L: ret = emulate_std(regs, R2(regs->iir),0); break; - } #endif + } switch (regs->iir & OPCODE3_MASK) { case OPCODE_FLDW_L:

From: Liang Zhang zhangliang5@huawei.com

commit 6f3c1fc53d86d580d8d6d749c4af23705e4f6f79 upstream.

In current async pagefault logic, when a page is ready, KVM relies on kvm_arch_can_dequeue_async_page_present() to determine whether to deliver a READY event to the Guest. This function test token value of struct kvm_vcpu_pv_apf_data, which must be reset to zero by Guest kernel when a READY event is finished by Guest. If value is zero meaning that a READY event is done, so the KVM can deliver another. But the kvm_arch_setup_async_pf() may produce a valid token with zero value, which is confused with previous mention and may lead the loss of this READY event.

This bug may cause task blocked forever in Guest: INFO: task stress:7532 blocked for more than 1254 seconds. Not tainted 5.10.0 #16 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:stress state:D stack: 0 pid: 7532 ppid: 1409 flags:0x00000080 Call Trace: __schedule+0x1e7/0x650 schedule+0x46/0xb0 kvm_async_pf_task_wait_schedule+0xad/0xe0 ? exit_to_user_mode_prepare+0x60/0x70 __kvm_handle_async_pf+0x4f/0xb0 ? asm_exc_page_fault+0x8/0x30 exc_page_fault+0x6f/0x110 ? asm_exc_page_fault+0x8/0x30 asm_exc_page_fault+0x1e/0x30 RIP: 0033:0x402d00 RSP: 002b:00007ffd31912500 EFLAGS: 00010206 RAX: 0000000000071000 RBX: ffffffffffffffff RCX: 00000000021a32b0 RDX: 000000000007d011 RSI: 000000000007d000 RDI: 00000000021262b0 RBP: 00000000021262b0 R08: 0000000000000003 R09: 0000000000000086 R10: 00000000000000eb R11: 00007fefbdf2baa0 R12: 0000000000000000 R13: 0000000000000002 R14: 000000000007d000 R15: 0000000000001000

Signed-off-by: Liang Zhang zhangliang5@huawei.com Message-Id: 20220222031239.1076682-1-zhangliang5@huawei.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/mmu/mmu.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)

--- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3889,12 +3889,23 @@ static void shadow_page_table_clear_floo walk_shadow_page_lockless_end(vcpu); }

+static u32 alloc_apf_token(struct kvm_vcpu *vcpu) +{ + /* make sure the token value is not 0 */ + u32 id = vcpu->arch.apf.id; + + if (id << 12 == 0) + vcpu->arch.apf.id = 1; + + return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; +} + static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, gfn_t gfn) { struct kvm_arch_async_pf arch;

- arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; + arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu);

From: Evan Quan evan.quan@amd.com

commit e3f3824874da78db5775a5cb9c0970cd1c6978bc upstream.

Add a quirk in sienna_cichlid_ppt.c to fix some OEM SKU specific stability issues.

Signed-off-by: Evan Quan evan.quan@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c | 32 +++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -418,6 +418,36 @@ static int sienna_cichlid_store_powerpla return 0; }

+static int sienna_cichlid_patch_pptable_quirk(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t *board_reserved; + uint16_t *freq_table_gfx; + uint32_t i; + + /* Fix some OEM SKU specific stability issues */ + GET_PPTABLE_MEMBER(BoardReserved, &board_reserved); + if ((adev->pdev->device == 0x73DF) && + (adev->pdev->revision == 0XC3) && + (adev->pdev->subsystem_device == 0x16C2) && + (adev->pdev->subsystem_vendor == 0x1043)) + board_reserved[0] = 1387; + + GET_PPTABLE_MEMBER(FreqTableGfx, &freq_table_gfx); + if ((adev->pdev->device == 0x73DF) && + (adev->pdev->revision == 0XC3) && + ((adev->pdev->subsystem_device == 0x16C2) || + (adev->pdev->subsystem_device == 0x133C)) && + (adev->pdev->subsystem_vendor == 0x1043)) { + for (i = 0; i < NUM_GFXCLK_DPM_LEVELS; i++) { + if (freq_table_gfx[i] > 2500) + freq_table_gfx[i] = 2500; + } + } + + return 0; +} + static int sienna_cichlid_setup_pptable(struct smu_context *smu) { int ret = 0; @@ -438,7 +468,7 @@ static int sienna_cichlid_setup_pptable( if (ret) return ret;

- return ret; + return sienna_cichlid_patch_pptable_quirk(smu); }

static int sienna_cichlid_tables_init(struct smu_context *smu)

From: Evan Quan evan.quan@amd.com

commit f626dd0ff05043e5a7154770cc7cda66acee33a3 upstream.

MMHUB PG needs to be disabled for Picasso for stability reasons.

Signed-off-by: Evan Quan evan.quan@amd.com Reviewed-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/soc15.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1273,8 +1273,11 @@ static int soc15_common_early_init(void AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_VCN_MGCG;

+ /* + * MMHUB PG needs to be disabled for Picasso for + * stability reasons. + */ adev->pg_flags = AMD_PG_SUPPORT_SDMA | - AMD_PG_SUPPORT_MMHUB | AMD_PG_SUPPORT_VCN; } else { adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |

From: Qiang Yu qiang.yu@amd.com

commit c1a66c3bc425ff93774fb2f6eefa67b83170dd7e upstream.

Workstation application ANSA/META v21.1.4 get this error dmesg when running CI test suite provided by ANSA/META: [drm:amdgpu_gem_va_ioctl [amdgpu]] *ERROR* Couldn't update BO_VA (-16)

This is caused by: 1. create a 256MB buffer in invisible VRAM 2. CPU map the buffer and access it causes vm_fault and try to move it to visible VRAM 3. force visible VRAM space and traverse all VRAM bos to check if evicting this bo is valuable 4. when checking a VM bo (in invisible VRAM), amdgpu_vm_evictable() will set amdgpu_vm->evicting, but latter due to not in visible VRAM, won't really evict it so not add it to amdgpu_vm->evicted 5. before next CS to clear the amdgpu_vm->evicting, user VM ops ioctl will pass amdgpu_vm_ready() (check amdgpu_vm->evicted) but fail in amdgpu_vm_bo_update_mapping() (check amdgpu_vm->evicting) and get this error log

This error won't affect functionality as next CS will finish the waiting VM ops. But we'd better clear the error log by checking the amdgpu_vm->evicting flag in amdgpu_vm_ready() to stop calling amdgpu_vm_bo_update_mapping() later.

Another reason is amdgpu_vm->evicted list holds all BOs (both user buffer and page table), but only page table BOs' eviction prevent VM ops. amdgpu_vm->evicting flag is set only for page table BOs, so we should use evicting flag instead of evicted list in amdgpu_vm_ready().

The side effect of this change is: previously blocked VM op (user buffer in "evicted" list but no page table in it) gets done immediately.

v2: update commit comments.

Acked-by: Paul Menzel pmenzel@molgen.mpg.de Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Qiang Yu qiang.yu@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -768,11 +768,16 @@ int amdgpu_vm_validate_pt_bos(struct amd * Check if all VM PDs/PTs are ready for updates * * Returns: - * True if eviction list is empty. + * True if VM is not evicting. */ bool amdgpu_vm_ready(struct amdgpu_vm *vm) { - return list_empty(&vm->evicted); + bool ret; + + amdgpu_vm_eviction_lock(vm); + ret = !vm->evicting; + amdgpu_vm_eviction_unlock(vm); + return ret; }

/**

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

commit 3f33364836aacc28cd430d22cf22379e3b5ecd77 upstream.

adlp+ adds some extra bits to the QGV point mask. The code attempts to handle that but forgot to actually make sure we can store those bits in the bw state. Fix it.

Cc: stable@vger.kernel.org Cc: Stanislav Lisovskiy stanislav.lisovskiy@intel.com Fixes: 192fbfb76744 ("drm/i915: Implement PSF GV point support") Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220214091811.13725-4-ville.s... Reviewed-by: Stanislav Lisovskiy stanislav.lisovskiy@intel.com (cherry picked from commit c0299cc9840b3805205173cc77782f317b78ea0e) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_bw.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/gpu/drm/i915/display/intel_bw.h +++ b/drivers/gpu/drm/i915/display/intel_bw.h @@ -30,19 +30,19 @@ struct intel_bw_state { */ u8 pipe_sagv_reject;

+ /* bitmask of active pipes */ + u8 active_pipes; + /* * Current QGV points mask, which restricts * some particular SAGV states, not to confuse * with pipe_sagv_mask. */ - u8 qgv_points_mask; + u16 qgv_points_mask;

unsigned int data_rate[I915_MAX_PIPES]; u8 num_active_planes[I915_MAX_PIPES];

- /* bitmask of active pipes */ - u8 active_pipes; - int min_cdclk; };

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

commit ec663bca9128f13eada25cd0446e7fcb5fcdc088 upstream.

If the only thing that is changing is SAGV vs. no SAGV but the number of active planes and the total data rates end up unchanged we currently bail out of intel_bw_atomic_check() early and forget to actually compute the new WGV point mask and thus won't actually enable/disable SAGV as requested. This ends up poorly if we end up running with SAGV enabled when we shouldn't. Usually ends up in underruns.

To fix this let's go through the QGV point mask computation if either the data rates/number of planes, or the state of SAGV is changing.

v2: Check more carefully if things are changing to avoid the extra calculations/debugs from introducing unwanted overhead

Cc: stable@vger.kernel.org Reviewed-by: Stanislav Lisovskiy stanislav.lisovskiy@intel.com #v1 Fixes: 20f505f22531 ("drm/i915: Restrict qgv points which don't have enough bandwidth.") Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220218064039.12834-3-ville.s... (cherry picked from commit 6b728595ffa51c087343c716bccbfc260f120e72) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_bw.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -681,6 +681,7 @@ int intel_bw_atomic_check(struct intel_a unsigned int max_bw_point = 0, max_bw = 0; unsigned int num_qgv_points = dev_priv->max_bw[0].num_qgv_points; unsigned int num_psf_gv_points = dev_priv->max_bw[0].num_psf_gv_points; + bool changed = false; u32 mask = 0;

/* FIXME earlier gens need some checks too */ @@ -724,6 +725,8 @@ int intel_bw_atomic_check(struct intel_a new_bw_state->data_rate[crtc->pipe] = new_data_rate; new_bw_state->num_active_planes[crtc->pipe] = new_active_planes;

+ changed = true; + drm_dbg_kms(&dev_priv->drm, "pipe %c data rate %u num active planes %u\n", pipe_name(crtc->pipe), @@ -731,7 +734,19 @@ int intel_bw_atomic_check(struct intel_a new_bw_state->num_active_planes[crtc->pipe]); }

- if (!new_bw_state) + old_bw_state = intel_atomic_get_old_bw_state(state); + new_bw_state = intel_atomic_get_new_bw_state(state); + + if (new_bw_state && + intel_can_enable_sagv(dev_priv, old_bw_state) != + intel_can_enable_sagv(dev_priv, new_bw_state)) + changed = true; + + /* + * If none of our inputs (data rates, number of active + * planes, SAGV yes/no) changed then nothing to do here. + */ + if (!changed) return 0;

ret = intel_atomic_lock_global_state(&new_bw_state->base); @@ -814,7 +829,6 @@ int intel_bw_atomic_check(struct intel_a */ new_bw_state->qgv_points_mask = ~allowed_points & mask;

- old_bw_state = intel_atomic_get_old_bw_state(state); /* * If the actual mask had changed we need to make sure that * the commits are serialized(in case this is a nomodeset, nonblocking)

From: Oliver Neukum oneukum@suse.com

commit 6605cc67ca18b9d583eb96e18a20f5f4e726103c upstream.

This SL-6000 says Direct Line, not Ethernet

v2: added Reporter and Link

Signed-off-by: Oliver Neukum oneukum@suse.com Reported-by: Ross Maynard bids.7405@bigpond.com Link: https://bugzilla.kernel.org/show_bug.cgi?id=215361 Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/usb/cdc_ether.c | 12 ++++++++++++ drivers/net/usb/zaurus.c | 12 ++++++++++++ 2 files changed, 24 insertions(+)

--- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -583,6 +583,11 @@ static const struct usb_device_id produc .bInterfaceSubClass = USB_CDC_SUBCLASS_ETHERNET, \ .bInterfaceProtocol = USB_CDC_PROTO_NONE

+#define ZAURUS_FAKE_INTERFACE \ + .bInterfaceClass = USB_CLASS_COMM, \ + .bInterfaceSubClass = USB_CDC_SUBCLASS_MDLM, \ + .bInterfaceProtocol = USB_CDC_PROTO_NONE + /* SA-1100 based Sharp Zaurus ("collie"), or compatible; * wire-incompatible with true CDC Ethernet implementations. * (And, it seems, needlessly so...) @@ -638,6 +643,13 @@ static const struct usb_device_id produc .driver_info = 0, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x9032, /* SL-6000 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = 0, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, /* reported with some C860 units */ --- a/drivers/net/usb/zaurus.c +++ b/drivers/net/usb/zaurus.c @@ -256,6 +256,11 @@ static const struct usb_device_id produc .bInterfaceSubClass = USB_CDC_SUBCLASS_ETHERNET, \ .bInterfaceProtocol = USB_CDC_PROTO_NONE

+#define ZAURUS_FAKE_INTERFACE \ + .bInterfaceClass = USB_CLASS_COMM, \ + .bInterfaceSubClass = USB_CDC_SUBCLASS_MDLM, \ + .bInterfaceProtocol = USB_CDC_PROTO_NONE + /* SA-1100 based Sharp Zaurus ("collie"), or compatible. */ { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO @@ -315,6 +320,13 @@ static const struct usb_device_id produc .driver_info = ZAURUS_PXA_INFO, }, { .match_flags = USB_DEVICE_ID_MATCH_INT_INFO + | USB_DEVICE_ID_MATCH_DEVICE, + .idVendor = 0x04DD, + .idProduct = 0x9032, /* SL-6000 */ + ZAURUS_FAKE_INTERFACE, + .driver_info = (unsigned long)&bogus_mdlm_info, +}, { + .match_flags = USB_DEVICE_ID_MATCH_INT_INFO | USB_DEVICE_ID_MATCH_DEVICE, .idVendor = 0x04DD, /* reported with some C860 units */

From: Eric Dumazet edumazet@google.com

commit 75063c9294fb239bbe64eb72141b6871fe526d29 upstream.

Calling nf_defrag_ipv4_disable() instead of nf_defrag_ipv6_disable() was probably not the intent.

I found this by code inspection, while chasing a possible issue in TPROXY.

Fixes: de8c12110a13 ("netfilter: disable defrag once its no longer needed") Signed-off-by: Eric Dumazet edumazet@google.com Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/xt_socket.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -221,7 +221,7 @@ static void socket_mt_destroy(const stru if (par->family == NFPROTO_IPV4) nf_defrag_ipv4_disable(par->net); else if (par->family == NFPROTO_IPV6) - nf_defrag_ipv4_disable(par->net); + nf_defrag_ipv6_disable(par->net); }

static struct xt_match socket_mt_reg[] __read_mostly = {

From: Pablo Neira Ayuso pablo@netfilter.org

commit b1a5983f56e371046dcf164f90bfaf704d2b89f6 upstream.

immediate verdict expression needs to allocate one slot in the flow offload action array, however, immediate data expression does not need to do so.

fwd and dup expression need to allocate one slot, this is missing.

Add a new offload_action interface to report if this expression needs to allocate one slot in the flow offload action array.

Fixes: be2861dc36d7 ("netfilter: nft_{fwd,dup}_netdev: add offload support") Reported-and-tested-by: Nick Gregory Nick.Gregory@Sophos.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/netfilter/nf_tables.h | 2 +- include/net/netfilter/nf_tables_offload.h | 2 -- net/netfilter/nf_tables_offload.c | 3 ++- net/netfilter/nft_dup_netdev.c | 6 ++++++ net/netfilter/nft_fwd_netdev.c | 6 ++++++ net/netfilter/nft_immediate.c | 12 +++++++++++- 6 files changed, 26 insertions(+), 5 deletions(-)

--- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -883,9 +883,9 @@ struct nft_expr_ops { int (*offload)(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr); + bool (*offload_action)(const struct nft_expr *expr); void (*offload_stats)(struct nft_expr *expr, const struct flow_stats *stats); - u32 offload_flags; const struct nft_expr_type *type; void *data; }; --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -67,8 +67,6 @@ struct nft_flow_rule { struct flow_rule *rule; };

-#define NFT_OFFLOAD_F_ACTION (1 << 0) - void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type);

--- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -94,7 +94,8 @@ struct nft_flow_rule *nft_flow_rule_crea

expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { - if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION) + if (expr->ops->offload_action && + expr->ops->offload_action(expr)) num_actions++;

expr = nft_expr_next(expr); --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -67,6 +67,11 @@ static int nft_dup_netdev_offload(struct return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_MIRRED, oif); }

+static bool nft_dup_netdev_offload_action(const struct nft_expr *expr) +{ + return true; +} + static struct nft_expr_type nft_dup_netdev_type; static const struct nft_expr_ops nft_dup_netdev_ops = { .type = &nft_dup_netdev_type, @@ -75,6 +80,7 @@ static const struct nft_expr_ops nft_dup .init = nft_dup_netdev_init, .dump = nft_dup_netdev_dump, .offload = nft_dup_netdev_offload, + .offload_action = nft_dup_netdev_offload_action, };

static struct nft_expr_type nft_dup_netdev_type __read_mostly = { --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -77,6 +77,11 @@ static int nft_fwd_netdev_offload(struct return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_REDIRECT, oif); }

+static bool nft_fwd_netdev_offload_action(const struct nft_expr *expr) +{ + return true; +} + struct nft_fwd_neigh { u8 sreg_dev; u8 sreg_addr; @@ -219,6 +224,7 @@ static const struct nft_expr_ops nft_fwd .dump = nft_fwd_netdev_dump, .validate = nft_fwd_validate, .offload = nft_fwd_netdev_offload, + .offload_action = nft_fwd_netdev_offload_action, };

static const struct nft_expr_ops * --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -213,6 +213,16 @@ static int nft_immediate_offload(struct return 0; }

+static bool nft_immediate_offload_action(const struct nft_expr *expr) +{ + const struct nft_immediate_expr *priv = nft_expr_priv(expr); + + if (priv->dreg == NFT_REG_VERDICT) + return true; + + return false; +} + static const struct nft_expr_ops nft_imm_ops = { .type = &nft_imm_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)), @@ -224,7 +234,7 @@ static const struct nft_expr_ops nft_imm .dump = nft_immediate_dump, .validate = nft_immediate_validate, .offload = nft_immediate_offload, - .offload_flags = NFT_OFFLOAD_F_ACTION, + .offload_action = nft_immediate_offload_action, };

struct nft_expr_type nft_imm_type __read_mostly = {

From: Jens Wiklander jens.wiklander@linaro.org

commit aceeafefff736057e8f93f19bbfbef26abd94604 upstream.

Adds a driver private tee_context by moving the tee_context in struct optee_notif to struct optee. This tee_context was previously used when doing internal calls to secure world to deliver notification.

The new driver internal tee_context is now also when allocating driver private shared memory. This decouples the shared memory object from its original tee_context. This is needed when the life time of such a memory allocation outlives the client tee_context.

This patch fixes the problem described below:

The addition of a shutdown hook by commit f25889f93184 ("optee: fix tee out of memory failure seen during kexec reboot") introduced a kernel shutdown regression that can be triggered after running the OP-TEE xtest suites.

Once the shutdown hook is called it is not possible to communicate any more with the supplicant process because the system is not scheduling task any longer. Thus if the optee driver shutdown path receives a supplicant RPC request from the OP-TEE we will deadlock the kernel's shutdown.

Fixes: f25889f93184 ("optee: fix tee out of memory failure seen during kexec reboot") Fixes: 217e0250cccb ("tee: use reference counting for tee_context") Reported-by: Lars Persson larper@axis.com Cc: stable@vger.kernel.org Reviewed-by: Sumit Garg sumit.garg@linaro.org Signed-off-by: Jens Wiklander jens.wiklander@linaro.org [JW: backport to 5.15-stable + update commit message] Signed-off-by: Jens Wiklander jens.wiklander@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tee/optee/core.c | 8 ++++++++ drivers/tee/optee/optee_private.h | 2 ++ drivers/tee/optee/rpc.c | 8 +++++--- 3 files changed, 15 insertions(+), 3 deletions(-)

--- a/drivers/tee/optee/core.c +++ b/drivers/tee/optee/core.c @@ -588,6 +588,7 @@ static int optee_remove(struct platform_ /* Unregister OP-TEE specific client devices on TEE bus */ optee_unregister_devices();

+ teedev_close_context(optee->ctx); /* * Ask OP-TEE to free all cached shared memory objects to decrease * reference counters and also avoid wild pointers in secure world @@ -633,6 +634,7 @@ static int optee_probe(struct platform_d struct optee *optee = NULL; void *memremaped_shm = NULL; struct tee_device *teedev; + struct tee_context *ctx; u32 sec_caps; int rc;

@@ -719,6 +721,12 @@ static int optee_probe(struct platform_d optee_supp_init(&optee->supp); optee->memremaped_shm = memremaped_shm; optee->pool = pool; + ctx = teedev_open(optee->teedev); + if (IS_ERR(ctx)) { + rc = PTR_ERR(ctx); + goto err; + } + optee->ctx = ctx;

/* * Ensure that there are no pre-existing shm objects before enabling --- a/drivers/tee/optee/optee_private.h +++ b/drivers/tee/optee/optee_private.h @@ -70,6 +70,7 @@ struct optee_supp { * struct optee - main service struct * @supp_teedev: supplicant device * @teedev: client device + * @ctx: driver internal TEE context * @invoke_fn: function to issue smc or hvc * @call_queue: queue of threads waiting to call @invoke_fn * @wait_queue: queue of threads from secure world waiting for a @@ -87,6 +88,7 @@ struct optee { struct tee_device *supp_teedev; struct tee_device *teedev; optee_invoke_fn *invoke_fn; + struct tee_context *ctx; struct optee_call_queue call_queue; struct optee_wait_queue wait_queue; struct optee_supp supp; --- a/drivers/tee/optee/rpc.c +++ b/drivers/tee/optee/rpc.c @@ -285,6 +285,7 @@ static struct tee_shm *cmd_alloc_suppl(s }

static void handle_rpc_func_cmd_shm_alloc(struct tee_context *ctx, + struct optee *optee, struct optee_msg_arg *arg, struct optee_call_ctx *call_ctx) { @@ -314,7 +315,8 @@ static void handle_rpc_func_cmd_shm_allo shm = cmd_alloc_suppl(ctx, sz); break; case OPTEE_RPC_SHM_TYPE_KERNEL: - shm = tee_shm_alloc(ctx, sz, TEE_SHM_MAPPED | TEE_SHM_PRIV); + shm = tee_shm_alloc(optee->ctx, sz, + TEE_SHM_MAPPED | TEE_SHM_PRIV); break; default: arg->ret = TEEC_ERROR_BAD_PARAMETERS; @@ -471,7 +473,7 @@ static void handle_rpc_func_cmd(struct t break; case OPTEE_RPC_CMD_SHM_ALLOC: free_pages_list(call_ctx); - handle_rpc_func_cmd_shm_alloc(ctx, arg, call_ctx); + handle_rpc_func_cmd_shm_alloc(ctx, optee, arg, call_ctx); break; case OPTEE_RPC_CMD_SHM_FREE: handle_rpc_func_cmd_shm_free(ctx, arg); @@ -502,7 +504,7 @@ void optee_handle_rpc(struct tee_context

switch (OPTEE_SMC_RETURN_GET_RPC_FUNC(param->a0)) { case OPTEE_SMC_RPC_FUNC_ALLOC: - shm = tee_shm_alloc(ctx, param->a1, + shm = tee_shm_alloc(optee->ctx, param->a1, TEE_SHM_MAPPED | TEE_SHM_PRIV); if (!IS_ERR(shm) && !tee_shm_get_pa(shm, 0, &pa)) { reg_pair_from_64(&param->a1, &param->a2, pa);

From: Mateusz Palczewski mateusz.palczewski@intel.com

commit fe20371578ef640069e6ae9fa8038f60e7908565 upstream.

Revert of a patch that instead of fixing a AQ error when trying to reset BW limit introduced several regressions related to creation and managing TC. Currently there are errors when creating a TC on both PF and VF.

Error log: [17428.783095] i40e 0000:3b:00.1: AQ command Config VSI BW allocation per TC failed = 14 [17428.783107] i40e 0000:3b:00.1: Failed configuring TC map 0 for VSI 391 [17428.783254] i40e 0000:3b:00.1: AQ command Config VSI BW allocation per TC failed = 14 [17428.783259] i40e 0000:3b:00.1: Unable to configure TC map 0 for VSI 391

This reverts commit 3d2504663c41104b4359a15f35670cfa82de1bbf.

Fixes: 3d2504663c41 (i40e: Fix reset bw limit when DCB enabled with 1 TC) Signed-off-by: Mateusz Palczewski mateusz.palczewski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Link: https://lore.kernel.org/r/20220223175347.1690692-1-anthony.l.nguyen@intel.co... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-)

--- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5372,15 +5372,7 @@ static int i40e_vsi_configure_bw_alloc(s /* There is no need to reset BW when mqprio mode is on. */ if (pf->flags & I40E_FLAG_TC_MQPRIO) return 0; - - if (!vsi->mqprio_qopt.qopt.hw) { - if (pf->flags & I40E_FLAG_DCB_ENABLED) - goto skip_reset; - - if (IS_ENABLED(CONFIG_I40E_DCB) && - i40e_dcb_hw_get_num_tc(&pf->hw) == 1) - goto skip_reset; - + if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { ret = i40e_set_bw_limit(vsi, vsi->seid, 0); if (ret) dev_info(&pf->pdev->dev, @@ -5388,8 +5380,6 @@ static int i40e_vsi_configure_bw_alloc(s vsi->seid); return ret; } - -skip_reset: memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)

From: Zhengjun Xing zhengjun.xing@linux.intel.com

commit 8a3d2ee0de3828e0d01f9682d35ee53704659bd0 upstream.

The 'perf record' and 'perf stat' commands have supported the option '-C/--cpus' to count or collect only on the list of CPUs provided.

Commit 1d3351e631fc34d7 ("perf tools: Enable on a list of CPUs for hybrid") add it to be supported for hybrid. For hybrid support, it checks the cpu list are available on hybrid PMU. But when we test only uncore events(or events not in cpu_core and cpu_atom), there is a bug:

Before:

# perf stat -C0 -e uncore_clock/clockticks/ sleep 1 failed to use cpu list 0

In this case, for uncore event, its pmu_name is not cpu_core or cpu_atom, so in evlist__fix_hybrid_cpus, perf_pmu__find_hybrid_pmu should return NULL,both events_nr and unmatched_count should be 0 ,then the cpu list check function evlist__fix_hybrid_cpus return -1 and the error "failed to use cpu list 0" will happen. Bypass "events_nr=0" case then the issue is fixed.

After:

# perf stat -C0 -e uncore_clock/clockticks/ sleep 1

Performance counter stats for 'CPU(s) 0':

195,476,873 uncore_clock/clockticks/

1.004518677 seconds time elapsed

When testing with at least one core event and uncore events, it has no issue.

# perf stat -C0 -e cpu_core/cpu-cycles/,uncore_clock/clockticks/ sleep 1

Performance counter stats for 'CPU(s) 0':

5,993,774 cpu_core/cpu-cycles/ 301,025,912 uncore_clock/clockticks/

1.003964934 seconds time elapsed

Fixes: 1d3351e631fc34d7 ("perf tools: Enable on a list of CPUs for hybrid") Reviewed-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Zhengjun Xing zhengjun.xing@linux.intel.com Cc: Adrian Hunter adrian.hunter@intel.com Cc: alexander.shishkin@intel.com Cc: Andi Kleen ak@linux.intel.com Cc: Ian Rogers irogers@google.com Cc: Jin Yao yao.jin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/20220218093127.1844241-1-zhengjun.xing@linux.int... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/perf/util/evlist-hybrid.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/tools/perf/util/evlist-hybrid.c +++ b/tools/perf/util/evlist-hybrid.c @@ -153,8 +153,8 @@ int evlist__fix_hybrid_cpus(struct evlis perf_cpu_map__put(matched_cpus); perf_cpu_map__put(unmatched_cpus); } - - ret = (unmatched_count == events_nr) ? -1 : 0; + if (events_nr) + ret = (unmatched_count == events_nr) ? -1 : 0; out: perf_cpu_map__put(cpus); return ret;

From: Paolo Abeni pabeni@redhat.com

commit 837cf45df163a3780bc04b555700231e95b31dc9 upstream.

If an MPTCP endpoint received multiple consecutive incoming ADD_ADDR options, mptcp_pm_add_addr_received() can overwrite the current remote address value after the PM lock is released in mptcp_pm_nl_add_addr_received() and before such address is echoed.

Fix the issue caching the remote address value a little earlier and always using the cached value after releasing the PM lock.

Fixes: f7efc7771eac ("mptcp: drop argument port from mptcp_pm_announce_addr") Reviewed-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/mptcp/pm_netlink.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)

--- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -606,6 +606,7 @@ static void mptcp_pm_nl_add_addr_receive unsigned int add_addr_accept_max; struct mptcp_addr_info remote; unsigned int subflows_max; + bool reset_port = false; int i, nr;

add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); @@ -615,15 +616,19 @@ static void mptcp_pm_nl_add_addr_receive msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family);

- if (lookup_subflow_by_daddr(&msk->conn_list, &msk->pm.remote)) + remote = msk->pm.remote; + if (lookup_subflow_by_daddr(&msk->conn_list, &remote)) goto add_addr_echo;

+ /* pick id 0 port, if none is provided the remote address */ + if (!remote.port) { + reset_port = true; + remote.port = sk->sk_dport; + } + /* connect to the specified remote address, using whatever * local address the routing configuration will pick. */ - remote = msk->pm.remote; - if (!remote.port) - remote.port = sk->sk_dport; nr = fill_local_addresses_vec(msk, addrs);

msk->pm.add_addr_accepted++; @@ -636,8 +641,12 @@ static void mptcp_pm_nl_add_addr_receive __mptcp_subflow_connect(sk, &addrs[i], &remote); spin_lock_bh(&msk->pm.lock);

+ /* be sure to echo exactly the received address */ + if (reset_port) + remote.port = 0; + add_addr_echo: - mptcp_pm_announce_addr(msk, &msk->pm.remote, true); + mptcp_pm_announce_addr(msk, &remote, true); mptcp_pm_nl_addr_send_ack(msk); }

From: Paolo Abeni pabeni@redhat.com

commit 0cd33c5ffec12bd77a1c02db2469fac08f840939 upstream.

Instead of waiting for an arbitrary amount of time for the MPTCP MP_CAPABLE handshake to complete, explicitly wait for the relevant socket to enter into the established status.

Additionally let the data transfer application use the slowest transfer mode available (-r), to cope with very slow host, or high jitter caused by hosting VMs.

Fixes: df62f2ec3df6 ("selftests/mptcp: add diag interface tests") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/258 Reported-and-tested-by: Matthieu Baerts matthieu.baerts@tessares.net Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- tools/testing/selftests/net/mptcp/diag.sh | 44 +++++++++++++++++++++++++----- 1 file changed, 37 insertions(+), 7 deletions(-)

--- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -71,6 +71,36 @@ chk_msk_remote_key_nr() __chk_nr "grep -c remote_key" $* }

+# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp | \ + awk "BEGIN {rc=1} {if ($2 ~ /:${port_hex}$/ && $4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +wait_connected() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break + sleep 0.1 + done +}

trap cleanup EXIT ip netns add $ns @@ -81,15 +111,15 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10000 -l -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10000 chk_msk_nr 0 "no msk on netns creation"

echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10000 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" @@ -101,13 +131,13 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10001 echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10001 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" flush_pids

@@ -119,7 +149,7 @@ for I in `seq 1 $NR_CLIENTS`; do ./mptcp_connect -p $((I+10001)) -l -w 10 \ -t ${timeout_poll} 0.0.0.0 >/dev/null & done -sleep 0.1 +wait_local_port_listen $ns $((NR_CLIENTS + 10001))

for I in `seq 1 $NR_CLIENTS`; do echo "b" | \

From: Manish Chopra manishc@marvell.com

commit e13ad1443684f7afaff24cf207e85e97885256bd upstream.

Commit b7a49f73059f ("bnx2x: Utilize firmware 7.13.21.0") added new firmware support in the driver with maintaining older firmware compatibility. However, older firmware was not added in MODULE_FIRMWARE() which caused missing firmware files in initrd image leading to driver load failure from initrd. This patch adds MODULE_FIRMWARE() for older firmware version to have firmware files included in initrd.

Fixes: b7a49f73059f ("bnx2x: Utilize firmware 7.13.21.0") Link: https://bugzilla.kernel.org/show_bug.cgi?id=215627 Signed-off-by: Manish Chopra manishc@marvell.com Signed-off-by: Alok Prasad palok@marvell.com Signed-off-by: Ariel Elior aelior@marvell.com Link: https://lore.kernel.org/r/20220223085720.12021-1-manishc@marvell.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -100,6 +100,9 @@ MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FW_FILE_NAME_E1); MODULE_FIRMWARE(FW_FILE_NAME_E1H); MODULE_FIRMWARE(FW_FILE_NAME_E2); +MODULE_FIRMWARE(FW_FILE_NAME_E1_V15); +MODULE_FIRMWARE(FW_FILE_NAME_E1H_V15); +MODULE_FIRMWARE(FW_FILE_NAME_E2_V15);

int bnx2x_num_queues; module_param_named(num_queues, bnx2x_num_queues, int, 0444);

From: Michael Chan michael.chan@broadcom.com

commit 6758f937669dba14c6aac7ca004edda42ec1b18d upstream.

For offline (destructive) self tests, we need to stop the RDMA driver first. Otherwise, the RDMA driver will run into unrecoverable errors when destructive firmware tests are being performed.

The irq_re_init parameter used in the half close and half open sequence when preparing the NIC for offline tests should be set to true because the RDMA driver will free all IRQs before the offline tests begin.

Fixes: 55fd0cf320c3 ("bnxt_en: Add external loopback test to ethtool selftest.") Reviewed-by: Edwin Peer edwin.peer@broadcom.com Reviewed-by: Ben Li ben.li@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 10 +++++----- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 12 +++++++++--- 2 files changed, 14 insertions(+), 8 deletions(-)

--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -10295,12 +10295,12 @@ int bnxt_half_open_nic(struct bnxt *bp) goto half_open_err; }

- rc = bnxt_alloc_mem(bp, false); + rc = bnxt_alloc_mem(bp, true); if (rc) { netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc); goto half_open_err; } - rc = bnxt_init_nic(bp, false); + rc = bnxt_init_nic(bp, true); if (rc) { netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); goto half_open_err; @@ -10309,7 +10309,7 @@ int bnxt_half_open_nic(struct bnxt *bp)

half_open_err: bnxt_free_skbs(bp); - bnxt_free_mem(bp, false); + bnxt_free_mem(bp, true); dev_close(bp->dev); return rc; } @@ -10319,9 +10319,9 @@ half_open_err: */ void bnxt_half_close_nic(struct bnxt *bp) { - bnxt_hwrm_resource_free(bp, false, false); + bnxt_hwrm_resource_free(bp, false, true); bnxt_free_skbs(bp); - bnxt_free_mem(bp, false); + bnxt_free_mem(bp, true); }

static void bnxt_reenable_sriov(struct bnxt *bp) --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -25,6 +25,7 @@ #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_hwrm.h" +#include "bnxt_ulp.h" #include "bnxt_xdp.h" #include "bnxt_ptp.h" #include "bnxt_ethtool.h" @@ -3502,9 +3503,12 @@ static void bnxt_self_test(struct net_de if (!offline) { bnxt_run_fw_tests(bp, test_mask, &test_results); } else { - rc = bnxt_close_nic(bp, false, false); - if (rc) + bnxt_ulp_stop(bp); + rc = bnxt_close_nic(bp, true, false); + if (rc) { + bnxt_ulp_start(bp, rc); return; + } bnxt_run_fw_tests(bp, test_mask, &test_results);

buf[BNXT_MACLPBK_TEST_IDX] = 1; @@ -3514,6 +3518,7 @@ static void bnxt_self_test(struct net_de if (rc) { bnxt_hwrm_mac_loopback(bp, false); etest->flags |= ETH_TEST_FL_FAILED; + bnxt_ulp_start(bp, rc); return; } if (bnxt_run_loopback(bp)) @@ -3539,7 +3544,8 @@ static void bnxt_self_test(struct net_de } bnxt_hwrm_phy_loopback(bp, false, false); bnxt_half_close_nic(bp); - rc = bnxt_open_nic(bp, false, true); + rc = bnxt_open_nic(bp, true, true); + bnxt_ulp_start(bp, rc); } if (rc || bnxt_test_irq(bp)) { buf[BNXT_IRQ_TEST_IDX] = 1;

From: Guenter Roeck linux@roeck-us.net

commit 1b5f517cca36292076d9e38fa6e33a257703e62e upstream.

If an attempt is made to a sensor with a thermal zone and it fails, the call to devm_thermal_zone_of_sensor_register() may return -ENODEV. This may result in crashes similar to the following.

Unable to handle kernel NULL pointer dereference at virtual address 00000000000003cd ... Internal error: Oops: 96000021 [#1] PREEMPT SMP ... pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : mutex_lock+0x18/0x60 lr : thermal_zone_device_update+0x40/0x2e0 sp : ffff800014c4fc60 x29: ffff800014c4fc60 x28: ffff365ee3f6e000 x27: ffffdde218426790 x26: ffff365ee3f6e000 x25: 0000000000000000 x24: ffff365ee3f6e000 x23: ffffdde218426870 x22: ffff365ee3f6e000 x21: 00000000000003cd x20: ffff365ee8bf3308 x19: ffffffffffffffed x18: 0000000000000000 x17: ffffdde21842689c x16: ffffdde1cb7a0b7c x15: 0000000000000040 x14: ffffdde21a4889a0 x13: 0000000000000228 x12: 0000000000000000 x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000 x8 : 0000000001120000 x7 : 0000000000000001 x6 : 0000000000000000 x5 : 0068000878e20f07 x4 : 0000000000000000 x3 : 00000000000003cd x2 : ffff365ee3f6e000 x1 : 0000000000000000 x0 : 00000000000003cd Call trace: mutex_lock+0x18/0x60 hwmon_notify_event+0xfc/0x110 0xffffdde1cb7a0a90 0xffffdde1cb7a0b7c irq_thread_fn+0x2c/0xa0 irq_thread+0x134/0x240 kthread+0x178/0x190 ret_from_fork+0x10/0x20 Code: d503201f d503201f d2800001 aa0103e4 (c8e47c02)

Jon Hunter reports that the exact call sequence is:

hwmon_notify_event() --> hwmon_thermal_notify() --> thermal_zone_device_update() --> update_temperature() --> mutex_lock()

The hwmon core needs to handle all errors returned from calls to devm_thermal_zone_of_sensor_register(). If the call fails with -ENODEV, report that the sensor was not attached to a thermal zone but continue to register the hwmon device.

Reported-by: Jon Hunter jonathanh@nvidia.com Cc: Dmitry Osipenko digetx@gmail.com Fixes: 1597b374af222 ("hwmon: Add notification support") Reviewed-by: Dmitry Osipenko dmitry.osipenko@collabora.com Tested-by: Jon Hunter jonathanh@nvidia.com Signed-off-by: Guenter Roeck linux@roeck-us.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hwmon/hwmon.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

--- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -214,12 +214,14 @@ static int hwmon_thermal_add_sensor(stru

tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata, &hwmon_thermal_ops); - /* - * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV, - * so ignore that error but forward any other error. - */ - if (IS_ERR(tzd) && (PTR_ERR(tzd) != -ENODEV)) - return PTR_ERR(tzd); + if (IS_ERR(tzd)) { + if (PTR_ERR(tzd) != -ENODEV) + return PTR_ERR(tzd); + dev_info(dev, "temp%d_input not attached to any thermal zone\n", + index + 1); + devm_kfree(dev, tdata); + return 0; + }

err = devm_add_action(dev, hwmon_thermal_remove_sensor, &tdata->node); if (err)

From: Tom Rix trix@redhat.com

commit ed22d9c8d128293fc7b0b086c7d3654bcb99a8dd upstream.

Clang static analysis reports this issue time64.h:69:50: warning: The left operand of '+' is a garbage value set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, ~~~~~~~~~~ ^ In ice_ptp_adjtime_nonatomic(), the timespec64 variable 'now' is set by ice_ptp_gettimex64(). This function can fail with -EBUSY, so 'now' can have a gargbage value. So check the return.

Fixes: 06c16d89d2cb ("ice: register 1588 PTP clock device object for E810 devices") Signed-off-by: Tom Rix trix@redhat.com Tested-by: Gurucharan G gurucharanx.g@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/ice/ice_ptp.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -846,9 +846,12 @@ exit: static int ice_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta) { struct timespec64 now, then; + int ret;

then = ns_to_timespec64(delta); - ice_ptp_gettimex64(info, &now, NULL); + ret = ice_ptp_gettimex64(info, &now, NULL); + if (ret) + return ret; now = timespec64_add(now, then);

return ice_ptp_settime64(info, (const struct timespec64 *)&now);

From: Meir Lichtinger meirl@nvidia.com

commit f908a35b22180c4da64cf2647e4f5f0cd3054da7 upstream.

Add the upcoming BlueField-4 and ConnectX-8 device IDs.

Fixes: 2e9d3e83ab82 ("net/mlx5: Update the list of the PCI supported devices") Signed-off-by: Meir Lichtinger meirl@nvidia.com Reviewed-by: Gal Pressman gal@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1762,10 +1762,12 @@ static const struct pci_device_id mlx5_c { PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */ { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */ + { PCI_VDEVICE(MELLANOX, 0x1023) }, /* ConnectX-8 */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ { PCI_VDEVICE(MELLANOX, 0xa2dc) }, /* BlueField-3 integrated ConnectX-7 network controller */ + { PCI_VDEVICE(MELLANOX, 0xa2df) }, /* BlueField-4 integrated ConnectX-8 network controller */ { 0, } };

From: Felix Maurer fmaurer@redhat.com

commit 4a11678f683814df82fca9018d964771e02d7e6d upstream.

If bpf_msg_push_data() is called with len 0 (as it happens during selftests/bpf/test_sockmap), we do not need to do anything and can return early.

Calling bpf_msg_push_data() with len 0 previously lead to a wrong ENOMEM error: we later called get_order(copy + len); if len was 0, copy + len was also often 0 and get_order() returned some undefined value (at the moment 52). alloc_pages() caught that and failed, but then bpf_msg_push_data() returned ENOMEM. This was wrong because we are most probably not out of memory and actually do not need any additional memory.

Fixes: 6fff607e2f14b ("bpf: sk_msg program helper bpf_msg_push_data") Signed-off-by: Felix Maurer fmaurer@redhat.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Acked-by: Yonghong Song yhs@fb.com Acked-by: John Fastabend john.fastabend@gmail.com Link: https://lore.kernel.org/bpf/df69012695c7094ccb1943ca02b4920db3537466.1644421... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/core/filter.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/core/filter.c +++ b/net/core/filter.c @@ -2711,6 +2711,9 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_ if (unlikely(flags)) return -EINVAL;

+ if (unlikely(len == 0)) + return 0; + /* First find the starting scatterlist element */ i = msg->sg.start; do {

From: Yonghong Song yhs@fb.com

commit 5eaed6eedbe9612f642ad2b880f961d1c6c8ec2b upstream.

The patch in [1] intends to fix a bpf_timer related issue, but the fix caused existing 'timer' selftest to fail with hang or some random errors. After some debug, I found an issue with check_and_init_map_value() in the hashtab.c. More specifically, in hashtab.c, we have code l_new = bpf_map_kmalloc_node(&htab->map, ...) check_and_init_map_value(&htab->map, l_new...) Note that bpf_map_kmalloc_node() does not do initialization so l_new contains random value.

The function check_and_init_map_value() intends to zero the bpf_spin_lock and bpf_timer if they exist in the map. But I found bpf_spin_lock is zero'ed but bpf_timer is not zero'ed. With [1], later copy_map_value() skips copying of bpf_spin_lock and bpf_timer. The non-zero bpf_timer caused random failures for 'timer' selftest. Without [1], for both bpf_spin_lock and bpf_timer case, bpf_timer will be zero'ed, so 'timer' self test is okay.

For check_and_init_map_value(), why bpf_spin_lock is zero'ed properly while bpf_timer not. In bpf uapi header, we have struct bpf_spin_lock { __u32 val; }; struct bpf_timer { __u64 :64; __u64 :64; } __attribute__((aligned(8)));

The initialization code: *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = (struct bpf_spin_lock){}; *(struct bpf_timer *)(dst + map->timer_off) = (struct bpf_timer){}; It appears the compiler has no obligation to initialize anonymous fields. For example, let us use clang with bpf target as below: $ cat t.c struct bpf_timer { unsigned long long :64; }; struct bpf_timer2 { unsigned long long a; };

void test(struct bpf_timer *t) { *t = (struct bpf_timer){}; } void test2(struct bpf_timer2 *t) { *t = (struct bpf_timer2){}; } $ clang -target bpf -O2 -c -g t.c $ llvm-objdump -d t.o ... 0000000000000000 <test>: 0: 95 00 00 00 00 00 00 00 exit 0000000000000008 <test2>: 1: b7 02 00 00 00 00 00 00 r2 = 0 2: 7b 21 00 00 00 00 00 00 *(u64 *)(r1 + 0) = r2 3: 95 00 00 00 00 00 00 00 exit

gcc11.2 does not have the above issue. But from INTERNATIONAL STANDARD ©ISO/IEC ISO/IEC 9899:201x Programming languages — C http://www.open-std.org/Jtc1/sc22/wg14/www/docs/n1547.pdf page 157: Except where explicitly stated otherwise, for the purposes of this subclause unnamed members of objects of structure and union type do not participate in initialization. Unnamed members of structure objects have indeterminate value even after initialization.

To fix the problem, let use memset for bpf_timer case in check_and_init_map_value(). For consistency, memset is also used for bpf_spin_lock case.

[1] https://lore.kernel.org/bpf/20220209070324.1093182-2-memxor@gmail.com/

Fixes: 68134668c17f3 ("bpf: Add map side support for bpf timers.") Signed-off-by: Yonghong Song yhs@fb.com Signed-off-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/bpf/20220211194953.3142152-1-yhs@fb.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/bpf.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-)

--- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -206,11 +206,9 @@ static inline bool map_value_has_timer(c static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) - *(struct bpf_timer *)(dst + map->timer_off) = - (struct bpf_timer){}; + memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); }

/* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */

From: Eric Dumazet edumazet@google.com

commit f240762f88b4b1b58561939ffd44837759756477 upstream.

Looping ~65535 times doing kmalloc() calls can trigger soft lockups, especially with DEBUG features (like KASAN).

[ 253.536212] watchdog: BUG: soft lockup - CPU#64 stuck for 26s! [b219417889:12575] [ 253.544433] Modules linked in: vfat fat i2c_mux_pca954x i2c_mux spidev cdc_acm xhci_pci xhci_hcd sha3_generic gq(O) [ 253.544451] CPU: 64 PID: 12575 Comm: b219417889 Tainted: G S O 5.17.0-smp-DEV #801 [ 253.544457] RIP: 0010:kernel_text_address (./include/asm-generic/sections.h:192 ./include/linux/kallsyms.h:29 kernel/extable.c:67 kernel/extable.c:98) [ 253.544464] Code: 0f 93 c0 48 c7 c1 e0 63 d7 a4 48 39 cb 0f 92 c1 20 c1 0f b6 c1 5b 5d c3 90 0f 1f 44 00 00 55 48 89 e5 41 57 41 56 53 48 89 fb <48> c7 c0 00 00 80 a0 41 be 01 00 00 00 48 39 c7 72 0c 48 c7 c0 40 [ 253.544468] RSP: 0018:ffff8882d8baf4c0 EFLAGS: 00000246 [ 253.544471] RAX: 1ffff1105b175e00 RBX: ffffffffa13ef09a RCX: 00000000a13ef001 [ 253.544474] RDX: ffffffffa13ef09a RSI: ffff8882d8baf558 RDI: ffffffffa13ef09a [ 253.544476] RBP: ffff8882d8baf4d8 R08: ffff8882d8baf5e0 R09: 0000000000000004 [ 253.544479] R10: ffff8882d8baf5e8 R11: ffffffffa0d59a50 R12: ffff8882eab20380 [ 253.544481] R13: ffffffffa0d59a50 R14: dffffc0000000000 R15: 1ffff1105b175eb0 [ 253.544483] FS: 00000000016d3380(0000) GS:ffff88af48c00000(0000) knlGS:0000000000000000 [ 253.544486] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 253.544488] CR2: 00000000004af0f0 CR3: 00000002eabfa004 CR4: 00000000003706e0 [ 253.544491] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 253.544492] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 253.544494] Call Trace: [ 253.544496] <TASK> [ 253.544498] ? io_queue_sqe (fs/io_uring.c:7143) [ 253.544505] __kernel_text_address (kernel/extable.c:78) [ 253.544508] unwind_get_return_address (arch/x86/kernel/unwind_frame.c:19) [ 253.544514] arch_stack_walk (arch/x86/kernel/stacktrace.c:27) [ 253.544517] ? io_queue_sqe (fs/io_uring.c:7143) [ 253.544521] stack_trace_save (kernel/stacktrace.c:123) [ 253.544527] ____kasan_kmalloc (mm/kasan/common.c:39 mm/kasan/common.c:45 mm/kasan/common.c:436 mm/kasan/common.c:515) [ 253.544531] ? ____kasan_kmalloc (mm/kasan/common.c:39 mm/kasan/common.c:45 mm/kasan/common.c:436 mm/kasan/common.c:515) [ 253.544533] ? __kasan_kmalloc (mm/kasan/common.c:524) [ 253.544535] ? kmem_cache_alloc_trace (./include/linux/kasan.h:270 mm/slab.c:3567) [ 253.544541] ? io_issue_sqe (fs/io_uring.c:4556 fs/io_uring.c:4589 fs/io_uring.c:6828) [ 253.544544] ? __io_queue_sqe (fs/io_uring.c:?) [ 253.544551] __kasan_kmalloc (mm/kasan/common.c:524) [ 253.544553] kmem_cache_alloc_trace (./include/linux/kasan.h:270 mm/slab.c:3567) [ 253.544556] ? io_issue_sqe (fs/io_uring.c:4556 fs/io_uring.c:4589 fs/io_uring.c:6828) [ 253.544560] io_issue_sqe (fs/io_uring.c:4556 fs/io_uring.c:4589 fs/io_uring.c:6828) [ 253.544564] ? __kasan_slab_alloc (mm/kasan/common.c:45 mm/kasan/common.c:436 mm/kasan/common.c:469) [ 253.544567] ? __kasan_slab_alloc (mm/kasan/common.c:39 mm/kasan/common.c:45 mm/kasan/common.c:436 mm/kasan/common.c:469) [ 253.544569] ? kmem_cache_alloc_bulk (mm/slab.h:732 mm/slab.c:3546) [ 253.544573] ? __io_alloc_req_refill (fs/io_uring.c:2078) [ 253.544578] ? io_submit_sqes (fs/io_uring.c:7441) [ 253.544581] ? __se_sys_io_uring_enter (fs/io_uring.c:10154 fs/io_uring.c:10096) [ 253.544584] ? __x64_sys_io_uring_enter (fs/io_uring.c:10096) [ 253.544587] ? do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) [ 253.544590] ? entry_SYSCALL_64_after_hwframe (??:?) [ 253.544596] __io_queue_sqe (fs/io_uring.c:?) [ 253.544600] io_queue_sqe (fs/io_uring.c:7143) [ 253.544603] io_submit_sqe (fs/io_uring.c:?) [ 253.544608] io_submit_sqes (fs/io_uring.c:?) [ 253.544612] __se_sys_io_uring_enter (fs/io_uring.c:10154 fs/io_uring.c:10096) [ 253.544616] __x64_sys_io_uring_enter (fs/io_uring.c:10096) [ 253.544619] do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) [ 253.544623] entry_SYSCALL_64_after_hwframe (??:?)

Fixes: ddf0322db79c ("io_uring: add IORING_OP_PROVIDE_BUFFERS") Signed-off-by: Eric Dumazet edumazet@google.com Cc: Jens Axboe axboe@kernel.dk Cc: Pavel Begunkov asml.silence@gmail.com Cc: io-uring io-uring@vger.kernel.org Reported-by: syzbot syzkaller@googlegroups.com Link: https://lore.kernel.org/r/20220215041003.2394784-1-eric.dumazet@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/io_uring.c | 1 + 1 file changed, 1 insertion(+)

--- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4454,6 +4454,7 @@ static int io_add_buffers(struct io_prov } else { list_add_tail(&buf->list, &(*head)->list); } + cond_resched(); }

return i ? i : -ENOMEM;

From: Christoph Hellwig hch@lst.de

commit 602e57c9799c19f27e440639deed3ec45cfe1651 upstream.

Commit e7d65803e2bb ("nvme-multipath: revalidate paths during rescan") introduced the NVME_NS_READY flag, which nvme_path_is_disabled() uses to check if a path can be used or not. We also need to set this flag for devices that fail the ZNS feature validation and which are available through passthrough devices only to that they can be used in multipathing setups.

Fixes: e7d65803e2bb ("nvme-multipath: revalidate paths during rescan") Reported-by: Kanchan Joshi joshi.k@samsung.com Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Daniel Wagner dwagner@suse.de Tested-by: Kanchan Joshi joshi.k@samsung.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvme/host/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1914,7 +1914,7 @@ static int nvme_update_ns_info(struct nv if (blk_queue_is_zoned(ns->queue)) { ret = nvme_revalidate_zones(ns); if (ret && !nvme_first_scan(ns->disk)) - goto out; + return ret; }

if (nvme_ns_head_multipath(ns->head)) { @@ -1929,16 +1929,16 @@ static int nvme_update_ns_info(struct nv return 0;

out_unfreeze: - blk_mq_unfreeze_queue(ns->disk->queue); -out: /* * If probing fails due an unsupported feature, hide the block device, * but still allow other access. */ if (ret == -ENODEV) { ns->disk->flags |= GENHD_FL_HIDDEN; + set_bit(NVME_NS_READY, &ns->flags); ret = 0; } + blk_mq_unfreeze_queue(ns->disk->queue); return ret; }

From: Tao Liu thomas.liu@ucloud.cn

commit cc20cced0598d9a5ff91ae4ab147b3b5e99ee819 upstream.

We encounter a tcp drop issue in our cloud environment. Packet GROed in host forwards to a VM virtio_net nic with net_failover enabled. VM acts as a IPVS LB with ipip encapsulation. The full path like: host gro -> vm virtio_net rx -> net_failover rx -> ipvs fullnat -> ipip encap -> net_failover tx -> virtio_net tx

When net_failover transmits a ipip pkt (gso_type = 0x0103, which means SKB_GSO_TCPV4, SKB_GSO_DODGY and SKB_GSO_IPXIP4), there is no gso did because it supports TSO and GSO_IPXIP4. But network_header points to inner ip header.

Call Trace: tcp4_gso_segment ------> return NULL inet_gso_segment ------> inner iph, network_header points to ipip_gso_segment inet_gso_segment ------> outer iph skb_mac_gso_segment

Afterwards virtio_net transmits the pkt, only inner ip header is modified. And the outer one just keeps unchanged. The pkt will be dropped in remote host.

Call Trace: inet_gso_segment ------> inner iph, outer iph is skipped skb_mac_gso_segment __skb_gso_segment validate_xmit_skb validate_xmit_skb_list sch_direct_xmit __qdisc_run __dev_queue_xmit ------> virtio_net dev_hard_start_xmit __dev_queue_xmit ------> net_failover ip_finish_output2 ip_output iptunnel_xmit ip_tunnel_xmit ipip_tunnel_xmit ------> ipip dev_hard_start_xmit __dev_queue_xmit ip_finish_output2 ip_output ip_forward ip_rcv __netif_receive_skb_one_core netif_receive_skb_internal napi_gro_receive receive_buf virtnet_poll net_rx_action

The root cause of this issue is specific with the rare combination of SKB_GSO_DODGY and a tunnel device that adds an SKB_GSO_ tunnel option. SKB_GSO_DODGY is set from external virtio_net. We need to reset network header when callbacks.gso_segment() returns NULL.

This patch also includes ipv6_gso_segment(), considering SIT, etc.

Fixes: cb32f511a70b ("ipip: add GSO/TSO support") Signed-off-by: Tao Liu thomas.liu@ucloud.cn Reviewed-by: Willem de Bruijn willemb@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/af_inet.c | 5 ++++- net/ipv6/ip6_offload.c | 2 ++ 2 files changed, 6 insertions(+), 1 deletion(-)

--- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1380,8 +1380,11 @@ struct sk_buff *inet_gso_segment(struct }

ops = rcu_dereference(inet_offloads[proto]); - if (likely(ops && ops->callbacks.gso_segment)) + if (likely(ops && ops->callbacks.gso_segment)) { segs = ops->callbacks.gso_segment(skb, features); + if (!segs) + skb->network_header = skb_mac_header(skb) + nhoff - skb->head; + }

if (IS_ERR_OR_NULL(segs)) goto out; --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -114,6 +114,8 @@ static struct sk_buff *ipv6_gso_segment( if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); segs = ops->callbacks.gso_segment(skb, features); + if (!segs) + skb->network_header = skb_mac_header(skb) + nhoff - skb->head; }

if (IS_ERR_OR_NULL(segs))

From: Paul Blakey paulb@nvidia.com

commit d9b5ae5c1b241b91480aa30408be12fe91af834a upstream.

Ipv6 ttl, label and tos fields are modified without first pulling/pushing the ipv6 header, which would have updated the hw csum (if available). This might cause csum validation when sending the packet to the stack, as can be seen in the trace below.

Fix this by updating skb->csum if available.

Trace resulted by ipv6 ttl dec and then sending packet to conntrack [actions: set(ipv6(hlimit=63)),ct(zone=99)]: [295241.900063] s_pf0vf2: hw csum failure [295241.923191] Call Trace: [295241.925728] <IRQ> [295241.927836] dump_stack+0x5c/0x80 [295241.931240] __skb_checksum_complete+0xac/0xc0 [295241.935778] nf_conntrack_tcp_packet+0x398/0xba0 [nf_conntrack] [295241.953030] nf_conntrack_in+0x498/0x5e0 [nf_conntrack] [295241.958344] __ovs_ct_lookup+0xac/0x860 [openvswitch] [295241.968532] ovs_ct_execute+0x4a7/0x7c0 [openvswitch] [295241.979167] do_execute_actions+0x54a/0xaa0 [openvswitch] [295242.001482] ovs_execute_actions+0x48/0x100 [openvswitch] [295242.006966] ovs_dp_process_packet+0x96/0x1d0 [openvswitch] [295242.012626] ovs_vport_receive+0x6c/0xc0 [openvswitch] [295242.028763] netdev_frame_hook+0xc0/0x180 [openvswitch] [295242.034074] __netif_receive_skb_core+0x2ca/0xcb0 [295242.047498] netif_receive_skb_internal+0x3e/0xc0 [295242.052291] napi_gro_receive+0xba/0xe0 [295242.056231] mlx5e_handle_rx_cqe_mpwrq_rep+0x12b/0x250 [mlx5_core] [295242.062513] mlx5e_poll_rx_cq+0xa0f/0xa30 [mlx5_core] [295242.067669] mlx5e_napi_poll+0xe1/0x6b0 [mlx5_core] [295242.077958] net_rx_action+0x149/0x3b0 [295242.086762] __do_softirq+0xd7/0x2d6 [295242.090427] irq_exit+0xf7/0x100 [295242.093748] do_IRQ+0x7f/0xd0 [295242.096806] common_interrupt+0xf/0xf [295242.100559] </IRQ> [295242.102750] RIP: 0033:0x7f9022e88cbd [295242.125246] RSP: 002b:00007f9022282b20 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffda [295242.132900] RAX: 0000000000000005 RBX: 0000000000000010 RCX: 0000000000000000 [295242.140120] RDX: 00007f9022282ba8 RSI: 00007f9022282a30 RDI: 00007f9014005c30 [295242.147337] RBP: 00007f9014014d60 R08: 0000000000000020 R09: 00007f90254a8340 [295242.154557] R10: 00007f9022282a28 R11: 0000000000000246 R12: 0000000000000000 [295242.161775] R13: 00007f902308c000 R14: 000000000000002b R15: 00007f9022b71f40

Fixes: 3fdbd1ce11e5 ("openvswitch: add ipv6 'set' action") Signed-off-by: Paul Blakey paulb@nvidia.com Link: https://lore.kernel.org/r/20220223163416.24096-1-paulb@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/checksum.h | 5 +++++ net/openvswitch/actions.c | 46 ++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 43 insertions(+), 8 deletions(-)

--- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -141,6 +141,11 @@ static inline void csum_replace2(__sum16 *sum = ~csum16_add(csum16_sub(~(*sum), old), new); }

+static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) +{ + *csum = csum_add(csum_sub(*csum, old), new); +} + struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -423,12 +423,43 @@ static void set_ipv6_addr(struct sk_buff memcpy(addr, new_addr, sizeof(__be32[4])); }

-static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask) +static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask) { + u8 old_ipv6_tclass = ipv6_get_dsfield(nh); + + ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12), + (__force __wsum)(ipv6_tclass << 12)); + + ipv6_change_dsfield(nh, ~mask, ipv6_tclass); +} + +static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask) +{ + u32 ofl; + + ofl = nh->flow_lbl[0] << 16 | nh->flow_lbl[1] << 8 | nh->flow_lbl[2]; + fl = OVS_MASKED(ofl, fl, mask); + /* Bits 21-24 are always unmasked, so this retains their values. */ - OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16)); - OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8)); - OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask); + nh->flow_lbl[0] = (u8)(fl >> 16); + nh->flow_lbl[1] = (u8)(fl >> 8); + nh->flow_lbl[2] = (u8)fl; + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl)); +} + +static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask) +{ + new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8), + (__force __wsum)(new_ttl << 8)); + nh->hop_limit = new_ttl; }

static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl, @@ -546,18 +577,17 @@ static int set_ipv6(struct sk_buff *skb, } } if (mask->ipv6_tclass) { - ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass); + set_ipv6_dsfield(skb, nh, key->ipv6_tclass, mask->ipv6_tclass); flow_key->ip.tos = ipv6_get_dsfield(nh); } if (mask->ipv6_label) { - set_ipv6_fl(nh, ntohl(key->ipv6_label), + set_ipv6_fl(skb, nh, ntohl(key->ipv6_label), ntohl(mask->ipv6_label)); flow_key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); } if (mask->ipv6_hlimit) { - OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit, - mask->ipv6_hlimit); + set_ipv6_ttl(skb, nh, key->ipv6_hlimit, mask->ipv6_hlimit); flow_key->ip.ttl = nh->hop_limit; } return 0;

From: Gal Pressman gal@nvidia.com

commit 0b89429722353d112f8b8b29ca397e95fa994d27 upstream.

The ioctl EEPROM query wrongly returns success on read failures, fix that by returning the appropriate error code.

Fixes: bb64143eee8c ("net/mlx5e: Add ethtool support for dump module EEPROM") Signed-off-by: Gal Pressman gal@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1754,7 +1754,7 @@ static int mlx5e_get_module_eeprom(struc if (size_read < 0) { netdev_err(priv->netdev, "%s: mlx5_query_eeprom failed:0x%x\n", __func__, size_read); - return 0; + return size_read; }

i += size_read;

From: Matt Roper matthew.d.roper@intel.com

commit 28adef861233c6fce47372ebd2070b55eaa8e899 upstream.

We need to use phy_name() to convert the PHY value into a human-readable character in the error message.

Fixes: a6a128116e55 ("drm/i915/dg2: Wait for SNPS PHY calibration during display init") Signed-off-by: Matt Roper matthew.d.roper@intel.com Reviewed-by: Swathi Dhanavanthri swathi.dhanavanthri@intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20220215163545.2175730-1-matth... (cherry picked from commit 84073e568eec7b586b2f6fd5fb2fb08f59edec54) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/display/intel_snps_phy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -32,7 +32,7 @@ void intel_snps_phy_wait_for_calibration if (intel_de_wait_for_clear(dev_priv, ICL_PHY_MISC(phy), DG2_PHY_DP_TX_ACK_MASK, 25)) DRM_ERROR("SNPS PHY %c failed to calibrate after 25ms.\n", - phy); + phy_name(phy)); } }

From: Xiaoke Wang xkernel.wang@foxmail.com

commit b352c3465bb808ab700d03f5bac2f7a6f37c5350 upstream.

devm_kmalloc() returns a pointer to allocated memory on success, NULL on failure. While lp->indirect_lock is allocated by devm_kmalloc() without proper check. It is better to check the value of it to prevent potential wrong memory access.

Fixes: f14f5c11f051 ("net: ll_temac: Support indirect_mutex share within TEMAC IP") Signed-off-by: Xiaoke Wang xkernel.wang@foxmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/xilinx/ll_temac_main.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1427,6 +1427,8 @@ static int temac_probe(struct platform_d lp->indirect_lock = devm_kmalloc(&pdev->dev, sizeof(*lp->indirect_lock), GFP_KERNEL); + if (!lp->indirect_lock) + return -ENOMEM; spin_lock_init(lp->indirect_lock); }

From: Pablo Neira Ayuso pablo@netfilter.org

commit 6069da443bf65f513bb507bb21e2f87cfb1ad0b6 upstream.

Unregister flowtable hooks before they are releases via nf_tables_flowtable_destroy() otherwise hook core reports UAF.

BUG: KASAN: use-after-free in nf_hook_entries_grow+0x5a7/0x700 net/netfilter/core.c:142 net/netfilter/core.c:142 Read of size 4 at addr ffff8880736f7438 by task syz-executor579/3666

CPU: 0 PID: 3666 Comm: syz-executor579 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] __dump_stack lib/dump_stack.c:88 [inline] lib/dump_stack.c:106 dump_stack_lvl+0x1dc/0x2d8 lib/dump_stack.c:106 lib/dump_stack.c:106 print_address_description+0x65/0x380 mm/kasan/report.c:247 mm/kasan/report.c:247 __kasan_report mm/kasan/report.c:433 [inline] __kasan_report mm/kasan/report.c:433 [inline] mm/kasan/report.c:450 kasan_report+0x19a/0x1f0 mm/kasan/report.c:450 mm/kasan/report.c:450 nf_hook_entries_grow+0x5a7/0x700 net/netfilter/core.c:142 net/netfilter/core.c:142 __nf_register_net_hook+0x27e/0x8d0 net/netfilter/core.c:429 net/netfilter/core.c:429 nf_register_net_hook+0xaa/0x180 net/netfilter/core.c:571 net/netfilter/core.c:571 nft_register_flowtable_net_hooks+0x3c5/0x730 net/netfilter/nf_tables_api.c:7232 net/netfilter/nf_tables_api.c:7232 nf_tables_newflowtable+0x2022/0x2cf0 net/netfilter/nf_tables_api.c:7430 net/netfilter/nf_tables_api.c:7430 nfnetlink_rcv_batch net/netfilter/nfnetlink.c:513 [inline] nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:634 [inline] nfnetlink_rcv_batch net/netfilter/nfnetlink.c:513 [inline] net/netfilter/nfnetlink.c:652 nfnetlink_rcv_skb_batch net/netfilter/nfnetlink.c:634 [inline] net/netfilter/nfnetlink.c:652 nfnetlink_rcv+0x10e6/0x2550 net/netfilter/nfnetlink.c:652 net/netfilter/nfnetlink.c:652

__nft_release_hook() calls nft_unregister_flowtable_net_hooks() which only unregisters the hooks, then after RCU grace period, it is guaranteed that no packets add new entries to the flowtable (no flow offload rules and flowtable hooks are reachable from packet path), so it is safe to call nf_flow_table_free() which cleans up the remaining entries from the flowtable (both software and hardware) and it unbinds the flow_block.

Fixes: ff4bf2f42a40 ("netfilter: nf_tables: add nft_unregister_flowtable_hook()") Reported-by: syzbot+e918523f77e62790d6d9@syzkaller.appspotmail.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/nf_tables_api.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -9574,10 +9574,13 @@ EXPORT_SYMBOL_GPL(__nft_release_basechai

static void __nft_release_hook(struct net *net, struct nft_table *table) { + struct nft_flowtable *flowtable; struct nft_chain *chain;

list_for_each_entry(chain, &table->chains, list) nf_tables_unregister_hook(net, table, chain); + list_for_each_entry(flowtable, &table->flowtables, list) + nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list); }

static void __nft_release_hooks(struct net *net)

From: Baruch Siach baruch.siach@siklu.com

commit b6ad6261d27708567b309fdb3102b12c42a070cc upstream.

Experimentation shows that PHY detect might fail when the code attempts MDIO bus read immediately after clock enable. Add delay to stabilize the clock before bus access.

PHY detect failure started to show after commit 7590fc6f80ac ("net: mdio: Demote probed message to debug print") that removed coincidental delay between clock enable and bus access.

10ms is meant to match the time it take to send the probed message over UART at 115200 bps. This might be a far overshoot.

Fixes: 23a890d493e3 ("net: mdio: Add the reset function for IPQ MDIO driver") Signed-off-by: Baruch Siach baruch.siach@siklu.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/mdio/mdio-ipq4019.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/net/mdio/mdio-ipq4019.c +++ b/drivers/net/mdio/mdio-ipq4019.c @@ -200,7 +200,11 @@ static int ipq_mdio_reset(struct mii_bus if (ret) return ret;

- return clk_prepare_enable(priv->mdio_clk); + ret = clk_prepare_enable(priv->mdio_clk); + if (ret == 0) + mdelay(10); + + return ret; }

static int ipq4019_mdio_probe(struct platform_device *pdev)

From: Fabio M. De Francesco fmdefrancesco@gmail.com

commit 7ff57e98fb78ad94edafbdc7435f2d745e9e6bb5 upstream.

smc_pnetid_by_table_ib() uses read_lock() and then it calls smc_pnet_apply_ib() which, in turn, calls mutex_lock(&smc_ib_devices.mutex).

read_lock() disables preemption. Therefore, the code acquires a mutex while in atomic context and it leads to a SAC bug.

Fix this bug by replacing the rwlock with a mutex.

Reported-and-tested-by: syzbot+4f322a6d84e991c38775@syzkaller.appspotmail.com Fixes: 64e28b52c7a6 ("net/smc: add pnet table namespace support") Confirmed-by: Tony Lu tonylu@linux.alibaba.com Signed-off-by: Fabio M. De Francesco fmdefrancesco@gmail.com Acked-by: Karsten Graul kgraul@linux.ibm.com Link: https://lore.kernel.org/r/20220223100252.22562-1-fmdefrancesco@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/smc/smc_pnet.c | 42 +++++++++++++++++++++--------------------- net/smc/smc_pnet.h | 2 +- 2 files changed, 22 insertions(+), 22 deletions(-)

--- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -112,7 +112,7 @@ static int smc_pnet_remove_by_pnetid(str pnettable = &sn->pnettable;

/* remove table entry */ - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || @@ -130,7 +130,7 @@ static int smc_pnet_remove_by_pnetid(str rc = 0; } } - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock);

/* if this is not the initial namespace, stop here */ if (net != &init_net) @@ -191,7 +191,7 @@ static int smc_pnet_add_by_ndev(struct n sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable;

- write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { @@ -205,7 +205,7 @@ static int smc_pnet_add_by_ndev(struct n break; } } - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; }

@@ -223,7 +223,7 @@ static int smc_pnet_remove_by_ndev(struc sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable;

- write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { dev_put(pnetelem->ndev); @@ -236,7 +236,7 @@ static int smc_pnet_remove_by_ndev(struc break; } } - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; }

@@ -371,7 +371,7 @@ static int smc_pnet_add_eth(struct smc_p

rc = -EEXIST; new_netdev = true; - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { @@ -381,9 +381,9 @@ static int smc_pnet_add_eth(struct smc_p } if (new_netdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); } else { - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } @@ -444,7 +444,7 @@ static int smc_pnet_add_ib(struct smc_pn new_pe->ib_port = ib_port;

new_ibdev = true; - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { @@ -454,9 +454,9 @@ static int smc_pnet_add_ib(struct smc_pn } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); } else { - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; @@ -601,7 +601,7 @@ static int _smc_pnet_dump(struct net *ne pnettable = &sn->pnettable;

/* dump pnettable entries */ - read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; @@ -616,7 +616,7 @@ static int _smc_pnet_dump(struct net *ne break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return idx; }

@@ -860,7 +860,7 @@ int smc_pnet_net_init(struct net *net) struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev;

INIT_LIST_HEAD(&pnettable->pnetlist); - rwlock_init(&pnettable->lock); + mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock);

@@ -940,7 +940,7 @@ static int smc_pnet_find_ndev_pnetid_by_ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable;

- read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ @@ -949,7 +949,7 @@ static int smc_pnet_find_ndev_pnetid_by_ break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; }

@@ -1130,7 +1130,7 @@ int smc_pnetid_by_table_ib(struct smc_ib sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable;

- read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && @@ -1140,7 +1140,7 @@ int smc_pnetid_by_table_ib(struct smc_ib break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock);

return rc; } @@ -1159,7 +1159,7 @@ int smc_pnetid_by_table_smcd(struct smcd sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable;

- read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { @@ -1168,7 +1168,7 @@ int smc_pnetid_by_table_smcd(struct smcd break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock);

return rc; } --- a/net/smc/smc_pnet.h +++ b/net/smc/smc_pnet.h @@ -29,7 +29,7 @@ struct smc_link_group; * @pnetlist: List of PNETIDs */ struct smc_pnettable { - rwlock_t lock; + struct mutex lock; struct list_head pnetlist; };

From: Dan Carpenter dan.carpenter@oracle.com

commit de7b2efacf4e83954aed3f029d347dfc0b7a4f49 upstream.

This test is checking if we exited the list via break or not. However if it did not exit via a break then "node" does not point to a valid udp_tunnel_nic_shared_node struct. It will work because of the way the structs are laid out it's the equivalent of "if (info->shared->udp_tunnel_nic_info != dev)" which will always be true, but it's not the right way to test.

Fixes: 74cc6d182d03 ("udp_tunnel: add the ability to share port tables") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/udp_tunnel_nic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -846,7 +846,7 @@ udp_tunnel_nic_unregister(struct net_dev list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; - if (node->dev != dev) + if (list_entry_is_head(node, &info->shared->devices, list)) return;

list_del(&node->list);

From: Sukadev Bhattiprolu sukadev@linux.ibm.com

commit 277f2bb14361790a70e4b3c649e794b75a91a597 upstream.

If client is unable to initiate a failover reset via H_VIOCTL hcall, then it should schedule a failover reset as a last resort. Otherwise, there is no need to do a last resort.

Fixes: 334c42414729 ("ibmvnic: improve failover sysfs entry") Reported-by: Cris Forno cforno12@outlook.com Signed-off-by: Sukadev Bhattiprolu sukadev@linux.ibm.com Signed-off-by: Dany Madden drt@linux.ibm.com Link: https://lore.kernel.org/r/20220221210545.115283-1-drt@linux.ibm.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/ibm/ibmvnic.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -5733,10 +5733,14 @@ static ssize_t failover_store(struct dev be64_to_cpu(session_token)); rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, H_SESSION_ERR_DETECTED, session_token, 0, 0); - if (rc) + if (rc) { netdev_err(netdev, "H_VIOCTL initiated failover failed, rc %ld\n", rc); + goto last_resort; + } + + return count;

last_resort: netdev_dbg(netdev, "Trying to send CRQ_CMD, the last resort\n");

From: Maor Gottlieb maorg@nvidia.com

commit b645e57debca846f51b3209907546ea857ddd3f5 upstream.

Add missing call to up_write_ref_node() which releases the semaphore in case the FTE doesn't have destinations, such in drop rule case.

Fixes: 465e7baab6d9 ("net/mlx5: Fix deletion of duplicate rules") Signed-off-by: Maor Gottlieb maorg@nvidia.com Reviewed-by: Mark Bloch mbloch@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2041,6 +2041,8 @@ void mlx5_del_flow_rules(struct mlx5_flo fte->node.del_hw_func = NULL; up_write_ref_node(&fte->node, false); tree_put_node(&fte->node, false); + } else { + up_write_ref_node(&fte->node, false); } kfree(handle); }

From: Yevgeny Kliteynik kliteyn@nvidia.com

commit ecd9c5cd46e013659e2fad433057bad1ba66888e upstream.

When deciding whether to start syncing and actually free all the "hot" ICM chunks, we need to consider the type of the ICM chunks that we're dealing with. For instance, the amount of available ICM for MODIFY_ACTION is significantly lower than the usual STE ICM, so the threshold should account for that - otherwise we can deplete MODIFY_ACTION memory just by creating and deleting the same modify header action in a continuous loop.

This patch replaces the hard-coded threshold with a dynamic value.

Fixes: 1c58651412bb ("net/mlx5: DR, ICM memory pools sync optimization") Signed-off-by: Yevgeny Kliteynik kliteyn@nvidia.com Reviewed-by: Alex Vesker valex@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c | 11 ++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -4,7 +4,6 @@ #include "dr_types.h"

#define DR_ICM_MODIFY_HDR_ALIGN_BASE 64 -#define DR_ICM_SYNC_THRESHOLD_POOL (64 * 1024 * 1024)

struct mlx5dr_icm_pool { enum mlx5dr_icm_type icm_type; @@ -324,10 +323,14 @@ dr_icm_chunk_create(struct mlx5dr_icm_po

static bool dr_icm_pool_is_sync_required(struct mlx5dr_icm_pool *pool) { - if (pool->hot_memory_size > DR_ICM_SYNC_THRESHOLD_POOL) - return true; + int allow_hot_size;

- return false; + /* sync when hot memory reaches half of the pool size */ + allow_hot_size = + mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, + pool->icm_type) / 2; + + return pool->hot_memory_size > allow_hot_size; }

static int dr_icm_pool_sync_all_buddy_pools(struct mlx5dr_icm_pool *pool)

From: Tariq Toukan tariqt@nvidia.com

commit 7eaf1f37b8817c608c4e959d69986ef459d345cd upstream.

For RX TLS device-offloaded packets, the HW spec guarantees checksum validation for the offloaded packets, but does not define whether the CQE.checksum field matches the original packet (ciphertext) or the decrypted one (plaintext). This latitude allows architetctural improvements between generations of chips, resulting in different decisions regarding the value type of CQE.checksum.

Hence, for these packets, the device driver should not make use of this CQE field. Here we block CHECKSUM_COMPLETE usage for RX TLS device-offloaded packets, and use CHECKSUM_UNNECESSARY instead.

Value of the packet's tcp_hdr.csum is not modified by the HW, and it always matches the original ciphertext.

Fixes: 1182f3659357 ("net/mlx5e: kTLS, Add kTLS RX HW offload support") Signed-off-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -987,7 +987,8 @@ static inline void mlx5e_handle_csum(str }

/* True when explicitly set via priv flag, or XDP prog is loaded */ - if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)) + if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state) || + get_cqe_tls_offload(cqe)) goto csum_unnecessary;

/* CQE csum doesn't cover padding octets in short ethernet

From: Zhou Qingyang zhou1615@umn.edu

[ Upstream commit ab3824427b848da10e9fe2727f035bbeecae6ff4 ]

In zynq_qspi_exec_mem_op(), kzalloc() is directly used in memset(), which could lead to a NULL pointer dereference on failure of kzalloc().

Fix this bug by adding a check of tmpbuf.

This bug was found by a static analyzer. The analysis employs differential checking to identify inconsistent security operations (e.g., checks or kfrees) between two code paths and confirms that the inconsistent operations are not recovered in the current function or the callers, so they constitute bugs.

Note that, as a bug found by static analysis, it can be a false positive or hard to trigger. Multiple researchers have cross-reviewed the bug.

Builds with CONFIG_SPI_ZYNQ_QSPI=m show no new warnings, and our static analyzer no longer warns about this code.

Fixes: 67dca5e580f1 ("spi: spi-mem: Add support for Zynq QSPI controller") Signed-off-by: Zhou Qingyang zhou1615@umn.edu Link: https://lore.kernel.org/r/20211130172253.203700-1-zhou1615@umn.edu Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-zynq-qspi.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index cfa222c9bd5e7..78f31b61a2aac 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -570,6 +570,9 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem,

if (op->dummy.nbytes) { tmpbuf = kzalloc(op->dummy.nbytes, GFP_KERNEL); + if (!tmpbuf) + return -ENOMEM; + memset(tmpbuf, 0xff, op->dummy.nbytes); reinit_completion(&xqspi->data_completion); xqspi->txbuf = tmpbuf;

From: Prasad Kumpatla quic_pkumpatl@quicinc.com

[ Upstream commit d04ad245d67a3991dfea5e108e4c452c2ab39bac ]

With the existing logic where clear_ack is true (HW doesn’t support auto clear for ICR), interrupt clear register reset is not handled properly. Due to this only the first interrupts get processed properly and further interrupts are blocked due to not resetting interrupt clear register.

Example for issue case where Invert_ack is false and clear_ack is true:

Say Default ISR=0x00 & ICR=0x00 and ISR is triggered with 2 interrupts making ISR = 0x11.

Step 1: Say ISR is set 0x11 (store status_buff = ISR). ISR needs to be cleared with the help of ICR once the Interrupt is processed.

Step 2: Write ICR = 0x11 (status_buff), this will clear the ISR to 0x00.

Step 3: Issue - In the existing code, ICR is written with ICR = ~(status_buff) i.e ICR = 0xEE -> This will block all the interrupts from raising except for interrupts 0 and 4. So expectation here is to reset ICR, which will unblock all the interrupts.

if (chip->clear_ack) { if (chip->ack_invert && !ret) ........ else if (!ret) ret = regmap_write(map, reg, ~data->status_buf[i]);

So writing 0 and 0xff (when ack_invert is true) should have no effect, other than clearing the ACKs just set.

Fixes: 3a6f0fb7b8eb ("regmap: irq: Add support to clear ack registers") Signed-off-by: Prasad Kumpatla quic_pkumpatl@quicinc.com Reviewed-by: Charles Keepax ckeepax@opensource.cirrus.com Tested-by: Marek Szyprowski m.szyprowski@samsung.com Link: https://lore.kernel.org/r/20220217085007.30218-1-quic_pkumpatl@quicinc.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/regmap/regmap-irq.c | 20 ++++++-------------- 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index d2656581a6085..4a446259a184e 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -189,11 +189,9 @@ static void regmap_irq_sync_unlock(struct irq_data *data) ret = regmap_write(map, reg, d->mask_buf[i]); if (d->chip->clear_ack) { if (d->chip->ack_invert && !ret) - ret = regmap_write(map, reg, - d->mask_buf[i]); + ret = regmap_write(map, reg, UINT_MAX); else if (!ret) - ret = regmap_write(map, reg, - ~d->mask_buf[i]); + ret = regmap_write(map, reg, 0); } if (ret != 0) dev_err(d->map->dev, "Failed to ack 0x%x: %d\n", @@ -556,11 +554,9 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) data->status_buf[i]); if (chip->clear_ack) { if (chip->ack_invert && !ret) - ret = regmap_write(map, reg, - data->status_buf[i]); + ret = regmap_write(map, reg, UINT_MAX); else if (!ret) - ret = regmap_write(map, reg, - ~data->status_buf[i]); + ret = regmap_write(map, reg, 0); } if (ret != 0) dev_err(map->dev, "Failed to ack 0x%x: %d\n", @@ -817,13 +813,9 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, d->status_buf[i] & d->mask_buf[i]); if (chip->clear_ack) { if (chip->ack_invert && !ret) - ret = regmap_write(map, reg, - (d->status_buf[i] & - d->mask_buf[i])); + ret = regmap_write(map, reg, UINT_MAX); else if (!ret) - ret = regmap_write(map, reg, - ~(d->status_buf[i] & - d->mask_buf[i])); + ret = regmap_write(map, reg, 0); } if (ret != 0) { dev_err(map->dev, "Failed to ack 0x%x: %d\n",

From: Md Haris Iqbal haris.iqbal@ionos.com

[ Upstream commit 8700af2cc18c919b2a83e74e0479038fd113c15d ]

Callback function rtrs_clt_dev_release() for put_device() calls kfree(clt) to free memory. We shouldn't call kfree(clt) again, and we can't use the clt after kfree too.

Replace device_register() with device_initialize() and device_add() so that dev_set_name can() be used appropriately.

Move mutex_destroy() to the release function so it can be called in the alloc_clt err path.

Fixes: eab098246625 ("RDMA/rtrs-clt: Refactor the failure cases in alloc_clt") Link: https://lore.kernel.org/r/20220217030929.323849-1-haris.iqbal@ionos.com Reported-by: Miaoqian Lin linmq006@gmail.com Signed-off-by: Md Haris Iqbal haris.iqbal@ionos.com Reviewed-by: Jack Wang jinpu.wang@ionos.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 37 ++++++++++++++------------ 1 file changed, 20 insertions(+), 17 deletions(-)

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 55ebe01ec9951..3272514f05405 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -2664,6 +2664,8 @@ static void rtrs_clt_dev_release(struct device *dev) { struct rtrs_clt *clt = container_of(dev, struct rtrs_clt, dev);

+ mutex_destroy(&clt->paths_ev_mutex); + mutex_destroy(&clt->paths_mutex); kfree(clt); }

@@ -2693,6 +2695,8 @@ static struct rtrs_clt *alloc_clt(const char *sessname, size_t paths_num, return ERR_PTR(-ENOMEM); }

+ clt->dev.class = rtrs_clt_dev_class; + clt->dev.release = rtrs_clt_dev_release; uuid_gen(&clt->paths_uuid); INIT_LIST_HEAD_RCU(&clt->paths_list); clt->paths_num = paths_num; @@ -2709,43 +2713,41 @@ static struct rtrs_clt *alloc_clt(const char *sessname, size_t paths_num, init_waitqueue_head(&clt->permits_wait); mutex_init(&clt->paths_ev_mutex); mutex_init(&clt->paths_mutex); + device_initialize(&clt->dev);

- clt->dev.class = rtrs_clt_dev_class; - clt->dev.release = rtrs_clt_dev_release; err = dev_set_name(&clt->dev, "%s", sessname); if (err) - goto err; + goto err_put; + /* * Suppress user space notification until * sysfs files are created */ dev_set_uevent_suppress(&clt->dev, true); - err = device_register(&clt->dev); - if (err) { - put_device(&clt->dev); - goto err; - } + err = device_add(&clt->dev); + if (err) + goto err_put;

clt->kobj_paths = kobject_create_and_add("paths", &clt->dev.kobj); if (!clt->kobj_paths) { err = -ENOMEM; - goto err_dev; + goto err_del; } err = rtrs_clt_create_sysfs_root_files(clt); if (err) { kobject_del(clt->kobj_paths); kobject_put(clt->kobj_paths); - goto err_dev; + goto err_del; } dev_set_uevent_suppress(&clt->dev, false); kobject_uevent(&clt->dev.kobj, KOBJ_ADD);

return clt; -err_dev: - device_unregister(&clt->dev); -err: +err_del: + device_del(&clt->dev); +err_put: free_percpu(clt->pcpu_path); - kfree(clt); + put_device(&clt->dev); return ERR_PTR(err); }

@@ -2753,9 +2755,10 @@ static void free_clt(struct rtrs_clt *clt) { free_permits(clt); free_percpu(clt->pcpu_path); - mutex_destroy(&clt->paths_ev_mutex); - mutex_destroy(&clt->paths_mutex); - /* release callback will free clt in last put */ + + /* + * release callback will free clt and destroy mutexes in last put + */ device_unregister(&clt->dev); }

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit b891106da52b2c12dbaf73400f6d225b06a38d80 ]

When polling for the firmware message response, we first poll for the response message header. Once the valid length is detected in the header, we poll for the valid bit at the end of the message which signals DMA completion. Normally, this poll time for DMA completion is extremely short (0 to a few usec). But on some devices under some rare conditions, it can be up to about 20 msec.

Increase this delay to 50 msec and use udelay() for the first 10 usec for the common case, and usleep_range() beyond that.

Also, change the error message to include the above delay time when printing the timeout value.

Fixes: 3c8c20db769c ("bnxt_en: move HWRM API implementation into separate file") Reviewed-by: Vladimir Olovyannikov vladimir.olovyannikov@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c | 12 +++++++++--- drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h | 2 +- 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c index 8171f4912fa01..3a0eeb3737767 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c @@ -595,18 +595,24 @@ static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx)

/* Last byte of resp contains valid bit */ valid = ((u8 *)ctx->resp) + len - 1; - for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) { + for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; ) { /* make sure we read from updated DMA memory */ dma_rmb(); if (*valid) break; - usleep_range(1, 5); + if (j < 10) { + udelay(1); + j++; + } else { + usleep_range(20, 30); + j += 20; + } }

if (j >= HWRM_VALID_BIT_DELAY_USEC) { if (!(ctx->flags & BNXT_HWRM_CTX_SILENT)) netdev_err(bp->dev, "Error (timeout: %u) msg {0x%x 0x%x} len:%d v:%d\n", - hwrm_total_timeout(i), + hwrm_total_timeout(i) + j, le16_to_cpu(ctx->req->req_type), le16_to_cpu(ctx->req->seq_id), len, *valid); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h index 9a9fc4e8041b6..380ef69afb51b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h @@ -94,7 +94,7 @@ static inline unsigned int hwrm_total_timeout(unsigned int n) }

-#define HWRM_VALID_BIT_DELAY_USEC 150 +#define HWRM_VALID_BIT_DELAY_USEC 50000

static inline bool bnxt_cfa_hwrm_message(u16 req_type) {

From: Bart Van Assche bvanassche@acm.org

[ Upstream commit 081bdc9fe05bb23248f5effb6f811da3da4b8252 ]

Remove the flush_workqueue(system_long_wq) call since flushing system_long_wq is deadlock-prone and since that call is redundant with a preceding cancel_work_sync()

Link: https://lore.kernel.org/r/20220215210511.28303-3-bvanassche@acm.org Fixes: ef6c49d87c34 ("IB/srp: Eliminate state SRP_TARGET_DEAD") Reported-by: syzbot+831661966588c802aae9@syzkaller.appspotmail.com Signed-off-by: Bart Van Assche bvanassche@acm.org Reviewed-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/ulp/srp/ib_srp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index 71eda91e810cf..5d416ec228717 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -4038,9 +4038,11 @@ static void srp_remove_one(struct ib_device *device, void *client_data) spin_unlock(&host->target_lock);

/* - * Wait for tl_err and target port removal tasks. + * srp_queue_remove_work() queues a call to + * srp_remove_target(). The latter function cancels + * target->tl_err_work so waiting for the remove works to + * finish is sufficient. */ - flush_workqueue(system_long_wq); flush_workqueue(srp_remove_wq);

kfree(host);

From: Steven Rostedt (Google) rostedt@goodmis.org

commit 302e9edd54985f584cfc180098f3554774126969 upstream.

If a trigger is set on an event to disable or enable tracing within an instance, then tracing should be disabled or enabled in the instance and not at the top level, which is confusing to users.

Link: https://lkml.kernel.org/r/20220223223837.14f94ec3@rorschach.local.home

Cc: stable@vger.kernel.org Fixes: ae63b31e4d0e2 ("tracing: Separate out trace events from global variables") Tested-by: Daniel Bristot de Oliveira bristot@kernel.org Reviewed-by: Tom Zanussi zanussi@kernel.org Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_events_trigger.c | 52 +++++++++++++++++++++++++++++++----- 1 file changed, 46 insertions(+), 6 deletions(-)

--- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -955,6 +955,16 @@ traceon_trigger(struct event_trigger_dat struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_on(file->tr); + return; + } + if (tracing_is_on()) return;

@@ -966,8 +976,15 @@ traceon_count_trigger(struct event_trigg struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - if (tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + } else { + if (tracing_is_on()) + return; + }

if (!data->count) return; @@ -975,7 +992,10 @@ traceon_count_trigger(struct event_trigg if (data->count != -1) (data->count)--;

- tracing_on(); + if (file) + tracer_tracing_on(file->tr); + else + tracing_on(); }

static void @@ -983,6 +1003,16 @@ traceoff_trigger(struct event_trigger_da struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_off(file->tr); + return; + } + if (!tracing_is_on()) return;

@@ -994,8 +1024,15 @@ traceoff_count_trigger(struct event_trig struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - if (!tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + } else { + if (!tracing_is_on()) + return; + }

if (!data->count) return; @@ -1003,7 +1040,10 @@ traceoff_count_trigger(struct event_trig if (data->count != -1) (data->count)--;

- tracing_off(); + if (file) + tracer_tracing_off(file->tr); + else + tracing_off(); }

static int

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

commit e0a2e37f303828d030a83f33ffe14b36cb88d563 upstream.

If iio_device_register() fails, a previous ioremap() is left unbalanced.

Update the error handling path and add the missing iounmap() call, as already done in the remove function.

Fixes: 74aeac4da66f ("iio: adc: Add MEN 16z188 ADC driver") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Link: https://lore.kernel.org/r/320fc777863880247c2aff4a9d1a54ba69abf080.164344514... Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/adc/men_z188_adc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

--- a/drivers/iio/adc/men_z188_adc.c +++ b/drivers/iio/adc/men_z188_adc.c @@ -103,6 +103,7 @@ static int men_z188_probe(struct mcb_dev struct z188_adc *adc; struct iio_dev *indio_dev; struct resource *mem; + int ret;

indio_dev = devm_iio_device_alloc(&dev->dev, sizeof(struct z188_adc)); if (!indio_dev) @@ -128,8 +129,14 @@ static int men_z188_probe(struct mcb_dev adc->mem = mem; mcb_set_drvdata(dev, indio_dev);

- return iio_device_register(indio_dev); + ret = iio_device_register(indio_dev); + if (ret) + goto err_unmap;

+ return 0; + +err_unmap: + iounmap(adc->base); err: mcb_release_mem(mem); return -ENXIO;

From: Cosmin Tanislav demonsingur@gmail.com

commit 0e33d15f1dce9e3a80a970ea7f0b27837168aeca upstream.

According to page 90 of the datasheet [1], AIN_BUFP is bit 6 and AIN_BUFM is bit 5 of the CONFIG_0 -> CONFIG_7 registers.

Fix the mask used for setting these bits.

[1]: https://www.analog.com/media/en/technical-documentation/data-sheets/ad7124-8...

Fixes: 0eaecea6e487 ("iio: adc: ad7124: Add buffered input support") Signed-off-by: Cosmin Tanislav cosmin.tanislav@analog.com Link: https://lore.kernel.org/r/20220112200036.694490-1-cosmin.tanislav@analog.com Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/adc/ad7124.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -76,7 +76,7 @@ #define AD7124_CONFIG_REF_SEL(x) FIELD_PREP(AD7124_CONFIG_REF_SEL_MSK, x) #define AD7124_CONFIG_PGA_MSK GENMASK(2, 0) #define AD7124_CONFIG_PGA(x) FIELD_PREP(AD7124_CONFIG_PGA_MSK, x) -#define AD7124_CONFIG_IN_BUFF_MSK GENMASK(7, 6) +#define AD7124_CONFIG_IN_BUFF_MSK GENMASK(6, 5) #define AD7124_CONFIG_IN_BUFF(x) FIELD_PREP(AD7124_CONFIG_IN_BUFF_MSK, x)

/* AD7124_FILTER_X */

From: Lorenzo Bianconi lorenzo@kernel.org

commit ea85bf906466191b58532bb19f4fbb4591f0a77e upstream.

We need to wait for sensor settling time (~ 3/ODR) before reading data in st_lsm6dsx_read_oneshot routine in order to avoid corrupted samples.

Fixes: 290a6ce11d93 ("iio: imu: add support to lsm6dsx driver") Reported-by: Mario Tesi mario.tesi@st.com Tested-by: Mario Tesi mario.tesi@st.com Signed-off-by: Lorenzo Bianconi lorenzo@kernel.org Link: https://lore.kernel.org/r/b41ebda5535895298716c76d939f9f165fcd2d13.164409812... Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -1372,8 +1372,12 @@ static int st_lsm6dsx_read_oneshot(struc if (err < 0) return err;

+ /* + * we need to wait for sensor settling time before + * reading data in order to avoid corrupted samples + */ delay = 1000000000 / sensor->odr; - usleep_range(delay, 2 * delay); + usleep_range(3 * delay, 4 * delay);

err = st_lsm6dsx_read_locked(hw, addr, &data, sizeof(data)); if (err < 0)

From: Phil Elwell phil@raspberrypi.com

commit eebb0f4e894f1e9577a56b337693d1051dd6ebfd upstream.

UART drivers are meant to use the port spinlock within certain methods, to protect against reentrancy. The sc16is7xx driver does very little locking, presumably because when added it triggers "scheduling while atomic" errors. This is due to the use of mutexes within the regmap abstraction layer, and the mutex implementation's habit of sleeping the current thread while waiting for access. Unfortunately this lack of interlocking can lead to corruption of outbound data, which occurs when the buffer used for I2C transmission is used simultaneously by two threads - a work queue thread running sc16is7xx_tx_proc, and an IRQ thread in sc16is7xx_port_irq, both of which can call sc16is7xx_handle_tx.

An earlier patch added efr_lock, a mutex that controls access to the EFR register. This mutex is already claimed in the IRQ handler, and all that is required is to claim the same mutex in sc16is7xx_tx_proc.

See: https://github.com/raspberrypi/linux/issues/4885

Fixes: 6393ff1c4435 ("sc16is7xx: Use threaded IRQ") Cc: stable stable@vger.kernel.org Signed-off-by: Phil Elwell phil@raspberrypi.com Link: https://lore.kernel.org/r/20220216160802.1026013-1-phil@raspberrypi.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/sc16is7xx.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -734,12 +734,15 @@ static irqreturn_t sc16is7xx_irq(int irq static void sc16is7xx_tx_proc(struct kthread_work *ws) { struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port); + struct sc16is7xx_port *s = dev_get_drvdata(port->dev);

if ((port->rs485.flags & SER_RS485_ENABLED) && (port->rs485.delay_rts_before_send > 0)) msleep(port->rs485.delay_rts_before_send);

+ mutex_lock(&s->efr_lock); sc16is7xx_handle_tx(port); + mutex_unlock(&s->efr_lock); }

static void sc16is7xx_reconf_rs485(struct uart_port *port)

From: Dmytro Bagrii dimich.dmb@gmail.com

commit 198a7ebd5fa17b4d0be8cb70240ee1be885175c0 upstream.

This reverts commit 46ee4abb10a07bd8f8ce910ee6b4ae6a947d7f63.

CH341 has Product ID 0x5512 in EPP/MEM mode which is used for I2C/SPI/GPIO interfaces. In asynchronous serial interface mode CH341 has PID 0x5523 which is already in the table.

Mode is selected by corresponding jumper setting.

Signed-off-by: Dmytro Bagrii dimich.dmb@gmail.com Link: https://lore.kernel.org/r/20220210164137.4376-1-dimich.dmb@gmail.com Link: https://lore.kernel.org/r/YJ0OCS/sh+1ifD/q@hovoldconsulting.com Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/ch341.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -81,7 +81,6 @@ #define CH341_QUIRK_SIMULATE_BREAK BIT(1)

static const struct usb_device_id id_table[] = { - { USB_DEVICE(0x1a86, 0x5512) }, { USB_DEVICE(0x1a86, 0x5523) }, { USB_DEVICE(0x1a86, 0x7522) }, { USB_DEVICE(0x1a86, 0x7523) },

From: Szymon Heidrich szymon.heidrich@gmail.com

commit 7f14c7227f342d9932f9b918893c8814f86d2a0d upstream.

Assure that host may not manipulate the index to point past endpoint array.

Signed-off-by: Szymon Heidrich szymon.heidrich@gmail.com Cc: stable stable@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/gadget/udc/udc-xilinx.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/usb/gadget/udc/udc-xilinx.c +++ b/drivers/usb/gadget/udc/udc-xilinx.c @@ -1612,6 +1612,8 @@ static void xudc_getstatus(struct xusb_u break; case USB_RECIP_ENDPOINT: epnum = udc->setup.wIndex & USB_ENDPOINT_NUMBER_MASK; + if (epnum >= XUSB_MAX_ENDPOINTS) + goto stall; target_ep = &udc->ep[epnum]; epcfgreg = udc->read_fn(udc->addr + target_ep->offset); halt = epcfgreg & XUSB_EP_CFG_STALL_MASK; @@ -1679,6 +1681,10 @@ static void xudc_set_clear_feature(struc case USB_RECIP_ENDPOINT: if (!udc->setup.wValue) { endpoint = udc->setup.wIndex & USB_ENDPOINT_NUMBER_MASK; + if (endpoint >= XUSB_MAX_ENDPOINTS) { + xudc_ep0_stall(udc); + return; + } target_ep = &udc->ep[endpoint]; outinbit = udc->setup.wIndex & USB_ENDPOINT_DIR_MASK; outinbit = outinbit >> 7;

From: Slark Xiao slark_xiao@163.com

commit 6ecb3f0b18b320320460a42e40d6fb603f6ded96 upstream.

Dell DW5829e same as DW5821e except CAT level. DW5821e supports CAT16 but DW5829e supports CAT9. There are 2 types product of DW5829e: normal and eSIM. So we will add 2 PID for DW5829e. And for each PID, it support MBIM or RMNET. Let's see test evidence as below:

DW5829e MBIM mode: T: Bus=04 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 4 Spd=5000 MxCh= 0 D: Ver= 3.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 2 P: Vendor=413c ProdID=81e6 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5829e Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 7 Cfg#= 2 Atr=a0 MxPwr=896mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#=0x6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)

DW5829e RMNET mode: T: Bus=04 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 5 Spd=5000 MxCh= 0 D: Ver= 3.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 1 P: Vendor=413c ProdID=81e6 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5829e Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=896mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID ) Sub=00 Prot=00 Driver=usbhid I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option

DW5829e-eSIM MBIM mode: T: Bus=04 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 6 Spd=5000 MxCh= 0 D: Ver= 3.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 2 P: Vendor=413c ProdID=81e4 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5829e-eSIM Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 7 Cfg#= 2 Atr=a0 MxPwr=896mA I: If#=0x0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim I: If#=0x1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#=0x6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=ff Driver=(none)

DW5829e-eSIM RMNET mode: T: Bus=04 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 7 Spd=5000 MxCh= 0 D: Ver= 3.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS= 9 #Cfgs= 1 P: Vendor=413c ProdID=81e4 Rev=03.18 S: Manufacturer=Dell Inc. S: Product=DW5829e-eSIM Snapdragon X20 LTE S: SerialNumber=0123456789ABCDEF C: #Ifs= 6 Cfg#= 1 Atr=a0 MxPwr=896mA I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#=0x1 Alt= 0 #EPs= 1 Cls=03(HID ) Sub=00 Prot=00 Driver=usbhid I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I: If#=0x5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option

BTW, the interface 0x6 of MBIM mode is GNSS port, which not same as NMEA port. So it's banned from serial option driver. The remaining interfaces 0x2-0x5 are: MODEM, MODEM, NMEA, DIAG.

Signed-off-by: Slark Xiao slark_xiao@163.com Link: https://lore.kernel.org/r/20220214021401.6264-1-slark_xiao@163.com [ johan: drop unnecessary reservation of interface 1 ] Cc: stable@vger.kernel.org Signed-off-by: Johan Hovold johan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/serial/option.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -198,6 +198,8 @@ static void option_instat_callback(struc

#define DELL_PRODUCT_5821E 0x81d7 #define DELL_PRODUCT_5821E_ESIM 0x81e0 +#define DELL_PRODUCT_5829E_ESIM 0x81e4 +#define DELL_PRODUCT_5829E 0x81e6

#define KYOCERA_VENDOR_ID 0x0c88 #define KYOCERA_PRODUCT_KPC650 0x17da @@ -1063,6 +1065,10 @@ static const struct usb_device_id option .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5821E_ESIM), .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5829E), + .driver_info = RSVD(0) | RSVD(6) }, + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5829E_ESIM), + .driver_info = RSVD(0) | RSVD(6) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_E100A) }, /* ADU-E100, ADU-310 */ { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_500A) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_620UW) },

From: Fabrice Gasnier fabrice.gasnier@foss.st.com

commit 32fde84362c40961726a5c91f35ad37355ccc0c6 upstream.

When the gadget driver hasn't been (yet) configured, and the cable is connected to a HOST, the SFTDISCON gets cleared unconditionally, so the HOST tries to enumerate it. At the host side, this can result in a stuck USB port or worse. When getting lucky, some dmesg can be observed at the host side: new high-speed USB device number ... device descriptor read/64, error -110

Fix it in drd, by checking the enabled flag before calling dwc2_hsotg_core_connect(). It will be called later, once configured, by the normal flow: - udc_bind_to_driver - usb_gadget_connect - dwc2_hsotg_pullup - dwc2_hsotg_core_connect

Fixes: 17f934024e84 ("usb: dwc2: override PHY input signals with usb role switch support") Cc: stable stable@vger.kernel.org Signed-off-by: Fabrice Gasnier fabrice.gasnier@foss.st.com Link: https://lore.kernel.org/r/1644999135-13478-1-git-send-email-fabrice.gasnier@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc2/core.h | 2 ++ drivers/usb/dwc2/drd.c | 6 ++++-- 2 files changed, 6 insertions(+), 2 deletions(-)

--- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -1417,6 +1417,7 @@ void dwc2_hsotg_core_connect(struct dwc2 void dwc2_hsotg_disconnect(struct dwc2_hsotg *dwc2); int dwc2_hsotg_set_test_mode(struct dwc2_hsotg *hsotg, int testmode); #define dwc2_is_device_connected(hsotg) (hsotg->connected) +#define dwc2_is_device_enabled(hsotg) (hsotg->enabled) int dwc2_backup_device_registers(struct dwc2_hsotg *hsotg); int dwc2_restore_device_registers(struct dwc2_hsotg *hsotg, int remote_wakeup); int dwc2_gadget_enter_hibernation(struct dwc2_hsotg *hsotg); @@ -1453,6 +1454,7 @@ static inline int dwc2_hsotg_set_test_mo int testmode) { return 0; } #define dwc2_is_device_connected(hsotg) (0) +#define dwc2_is_device_enabled(hsotg) (0) static inline int dwc2_backup_device_registers(struct dwc2_hsotg *hsotg) { return 0; } static inline int dwc2_restore_device_registers(struct dwc2_hsotg *hsotg, --- a/drivers/usb/dwc2/drd.c +++ b/drivers/usb/dwc2/drd.c @@ -109,8 +109,10 @@ static int dwc2_drd_role_sw_set(struct u already = dwc2_ovr_avalid(hsotg, true); } else if (role == USB_ROLE_DEVICE) { already = dwc2_ovr_bvalid(hsotg, true); - /* This clear DCTL.SFTDISCON bit */ - dwc2_hsotg_core_connect(hsotg); + if (dwc2_is_device_enabled(hsotg)) { + /* This clear DCTL.SFTDISCON bit */ + dwc2_hsotg_core_connect(hsotg); + } } else { if (dwc2_is_device_mode(hsotg)) { if (!dwc2_ovr_bvalid(hsotg, false))

From: Hans de Goede hdegoede@redhat.com

commit 62e3f0afe246720f7646eb1b034a6897dac34405 upstream.

When the Bay Trail phy GPIO mappings where added cs and reset were swapped, this did not cause any issues sofar, because sofar they were always driven high/low at the same time.

Note the new mapping has been verified both in /sys/kernel/debug/gpio output on Android factory images on multiple devices, as well as in the schematics for some devices.

Fixes: 5741022cbdf3 ("usb: dwc3: pci: Add GPIO lookup table on platforms without ACPI GPIO resources") Cc: stable stable@vger.kernel.org Signed-off-by: Hans de Goede hdegoede@redhat.com Link: https://lore.kernel.org/r/20220213130524.18748-3-hdegoede@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/dwc3/dwc3-pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -85,8 +85,8 @@ static const struct acpi_gpio_mapping ac static struct gpiod_lookup_table platform_bytcr_gpios = { .dev_id = "0000:00:16.0", .table = { - GPIO_LOOKUP("INT33FC:00", 54, "reset", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("INT33FC:02", 14, "cs", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("INT33FC:00", 54, "cs", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("INT33FC:02", 14, "reset", GPIO_ACTIVE_HIGH), {} }, };

From: Puma Hsu pumahsu@google.com

commit 8b328f8002bcf29ef517ee4bf234e09aabec4d2e upstream.

When HCE(Host Controller Error) is set, it means an internal error condition has been detected. Software needs to re-initialize the HC, so add this check in xhci resume.

Cc: stable@vger.kernel.org Signed-off-by: Puma Hsu pumahsu@google.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20220215123320.1253947-2-mathias.nyman@linux.intel... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci.c | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-)

--- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1091,6 +1091,7 @@ int xhci_resume(struct xhci_hcd *xhci, b int retval = 0; bool comp_timer_running = false; bool pending_portevent = false; + bool reinit_xhc = false;

if (!hcd->state) return 0; @@ -1107,10 +1108,11 @@ int xhci_resume(struct xhci_hcd *xhci, b set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);

spin_lock_irq(&xhci->lock); - if ((xhci->quirks & XHCI_RESET_ON_RESUME) || xhci->broken_suspend) - hibernated = true;

- if (!hibernated) { + if (hibernated || xhci->quirks & XHCI_RESET_ON_RESUME || xhci->broken_suspend) + reinit_xhc = true; + + if (!reinit_xhc) { /* * Some controllers might lose power during suspend, so wait * for controller not ready bit to clear, just as in xHC init. @@ -1143,12 +1145,17 @@ int xhci_resume(struct xhci_hcd *xhci, b spin_unlock_irq(&xhci->lock); return -ETIMEDOUT; } - temp = readl(&xhci->op_regs->status); }

- /* If restore operation fails, re-initialize the HC during resume */ - if ((temp & STS_SRE) || hibernated) { + temp = readl(&xhci->op_regs->status); + + /* re-initialize the HC on Restore Error, or Host Controller Error */ + if (temp & (STS_SRE | STS_HCE)) { + reinit_xhc = true; + xhci_warn(xhci, "xHC error in resume, USBSTS 0x%x, Reinit\n", temp); + }

+ if (reinit_xhc) { if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) && !(xhci_all_ports_seen_u0(xhci))) { del_timer_sync(&xhci->comp_mode_recovery_timer);

From: Christophe Kerello christophe.kerello@foss.st.com

commit f6c052afe6f802d87c74153b7a57c43b2e9faf07 upstream.

Wp-gpios property can be used on NVMEM nodes and the same property can be also used on MTD NAND nodes. In case of the wp-gpios property is defined at NAND level node, the GPIO management is done at NAND driver level. Write protect is disabled when the driver is probed or resumed and is enabled when the driver is released or suspended.

When no partitions are defined in the NAND DT node, then the NAND DT node will be passed to NVMEM framework. If wp-gpios property is defined in this node, the GPIO resource is taken twice and the NAND controller driver fails to probe.

It would be possible to set config->wp_gpio at MTD level before calling nvmem_register function but NVMEM framework will toggle this GPIO on each write when this GPIO should only be controlled at NAND level driver to ensure that the Write Protect has not been enabled.

A way to fix this conflict is to add a new boolean flag in nvmem_config named ignore_wp. In case ignore_wp is set, the GPIO resource will be managed by the provider.

Fixes: 2a127da461a9 ("nvmem: add support for the write-protect pin") Cc: stable@vger.kernel.org Signed-off-by: Christophe Kerello christophe.kerello@foss.st.com Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20220220151432.16605-2-srinivas.kandagatla@linaro.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvmem/core.c | 2 +- include/linux/nvmem-provider.h | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -768,7 +768,7 @@ struct nvmem_device *nvmem_register(cons

if (config->wp_gpio) nvmem->wp_gpio = config->wp_gpio; - else + else if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -66,7 +66,8 @@ struct nvmem_keepout { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin + * @wp-gpio: Write protect pin + * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem<id>" name will be assigned to the device if * no name is specified in its configuration. In such case "<id>" is @@ -88,6 +89,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + bool ignore_wp; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read;

From: Mårten Lindahl marten.lindahl@axis.com

commit d8f7a5484f2188e9af2d9e4e587587d724501b12 upstream.

When unbinding/binding a driver with DMA mapped memory, the DMA map is not freed before the driver is reloaded. This leads to a memory leak when the DMA map is overwritten when reprobing the driver.

This can be reproduced with a platform driver having a dma-range:

dummy { ... #address-cells = <0x2>; #size-cells = <0x2>; ranges; dma-ranges = <...>; ... };

and then unbinding/binding it:

~# echo soc:dummy >/sys/bus/platform/drivers/<driver>/unbind

DMA map object 0xffffff800b0ae540 still being held by &pdev->dev

~# echo soc:dummy >/sys/bus/platform/drivers/<driver>/bind ~# echo scan > /sys/kernel/debug/kmemleak ~# cat /sys/kernel/debug/kmemleak unreferenced object 0xffffff800b0ae540 (size 64): comm "sh", pid 833, jiffies 4295174550 (age 2535.352s) hex dump (first 32 bytes): 00 00 00 80 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 80 00 00 00 00 00 00 00 80 00 00 00 00 ................ backtrace: [<ffffffefd1694708>] create_object.isra.0+0x108/0x344 [<ffffffefd1d1a850>] kmemleak_alloc+0x8c/0xd0 [<ffffffefd167e2d0>] __kmalloc+0x440/0x6f0 [<ffffffefd1a960a4>] of_dma_get_range+0x124/0x220 [<ffffffefd1a8ce90>] of_dma_configure_id+0x40/0x2d0 [<ffffffefd198b68c>] platform_dma_configure+0x5c/0xa4 [<ffffffefd198846c>] really_probe+0x8c/0x514 [<ffffffefd1988990>] __driver_probe_device+0x9c/0x19c [<ffffffefd1988cd8>] device_driver_attach+0x54/0xbc [<ffffffefd1986634>] bind_store+0xc4/0x120 [<ffffffefd19856e0>] drv_attr_store+0x30/0x44 [<ffffffefd173c9b0>] sysfs_kf_write+0x50/0x60 [<ffffffefd173c1c4>] kernfs_fop_write_iter+0x124/0x1b4 [<ffffffefd16a013c>] new_sync_write+0xdc/0x160 [<ffffffefd16a256c>] vfs_write+0x23c/0x2a0 [<ffffffefd16a2758>] ksys_write+0x64/0xec

To prevent this we should free the dma_range_map when the device is released.

Fixes: e0d072782c73 ("dma-mapping: introduce DMA range map, supplanting dma_pfn_offset") Cc: stable stable@vger.kernel.org Suggested-by: Rob Herring robh@kernel.org Reviewed-by: Rob Herring robh@kernel.org Signed-off-by: Mårten Lindahl marten.lindahl@axis.com Link: https://lore.kernel.org/r/20220216094128.4025861-1-marten.lindahl@axis.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/base/dd.c | 5 +++++ 1 file changed, 5 insertions(+)

--- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -629,6 +629,9 @@ re_probe: drv->remove(dev);

devres_release_all(dev); + arch_teardown_dma_ops(dev); + kfree(dev->dma_range_map); + dev->dma_range_map = NULL; driver_sysfs_remove(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); @@ -1208,6 +1211,8 @@ static void __device_release_driver(stru

devres_release_all(dev); arch_teardown_dma_ops(dev); + kfree(dev->dma_range_map); + dev->dma_range_map = NULL; dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss)

From: Jason Gunthorpe jgg@nvidia.com

commit 22e9f71072fa605cbf033158db58e0790101928d upstream.

If the state is not idle then resolve_prepare_src() should immediately fail and no change to global state should happen. However, it unconditionally overwrites the src_addr trying to build a temporary any address.

For instance if the state is already RDMA_CM_LISTEN then this will corrupt the src_addr and would cause the test in cma_cancel_operation():

if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev)

Which would manifest as this trace from syzkaller:

BUG: KASAN: use-after-free in __list_add_valid+0x93/0xa0 lib/list_debug.c:26 Read of size 8 at addr ffff8881546491e0 by task syz-executor.1/32204

CPU: 1 PID: 32204 Comm: syz-executor.1 Not tainted 5.12.0-rc8-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:79 [inline] dump_stack+0x141/0x1d7 lib/dump_stack.c:120 print_address_description.constprop.0.cold+0x5b/0x2f8 mm/kasan/report.c:232 __kasan_report mm/kasan/report.c:399 [inline] kasan_report.cold+0x7c/0xd8 mm/kasan/report.c:416 __list_add_valid+0x93/0xa0 lib/list_debug.c:26 __list_add include/linux/list.h:67 [inline] list_add_tail include/linux/list.h:100 [inline] cma_listen_on_all drivers/infiniband/core/cma.c:2557 [inline] rdma_listen+0x787/0xe00 drivers/infiniband/core/cma.c:3751 ucma_listen+0x16a/0x210 drivers/infiniband/core/ucma.c:1102 ucma_write+0x259/0x350 drivers/infiniband/core/ucma.c:1732 vfs_write+0x28e/0xa30 fs/read_write.c:603 ksys_write+0x1ee/0x250 fs/read_write.c:658 do_syscall_64+0x2d/0x70 arch/x86/entry/common.c:46 entry_SYSCALL_64_after_hwframe+0x44/0xae

This is indicating that an rdma_id_private was destroyed without doing cma_cancel_listens().

Instead of trying to re-use the src_addr memory to indirectly create an any address derived from the dst build one explicitly on the stack and bind to that as any other normal flow would do. rdma_bind_addr() will copy it over the src_addr once it knows the state is valid.

This is similar to commit bc0bdc5afaa7 ("RDMA/cma: Do not change route.addr.src_addr.ss_family")

Link: https://lore.kernel.org/r/0-v2-e975c8fd9ef2+11e-syz_cma_srcaddr_jgg@nvidia.c... Cc: stable@vger.kernel.org Fixes: 732d41c545bb ("RDMA/cma: Make the locking for automatic state transition more clear") Reported-by: syzbot+c94a3675a626f6333d74@syzkaller.appspotmail.com Reviewed-by: Leon Romanovsky leonro@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/core/cma.c | 38 +++++++++++++++++++++++--------------- 1 file changed, 23 insertions(+), 15 deletions(-)

--- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3368,22 +3368,30 @@ err: static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { - if (!src_addr || !src_addr->sa_family) { - src_addr = (struct sockaddr *) &id->route.addr.src_addr; - src_addr->sa_family = dst_addr->sa_family; - if (IS_ENABLED(CONFIG_IPV6) && - dst_addr->sa_family == AF_INET6) { - struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *) src_addr; - struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *) dst_addr; - src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; - if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - id->route.addr.dev_addr.bound_dev_if = dst_addr6->sin6_scope_id; - } else if (dst_addr->sa_family == AF_IB) { - ((struct sockaddr_ib *) src_addr)->sib_pkey = - ((struct sockaddr_ib *) dst_addr)->sib_pkey; - } + struct sockaddr_storage zero_sock = {}; + + if (src_addr && src_addr->sa_family) + return rdma_bind_addr(id, src_addr); + + /* + * When the src_addr is not specified, automatically supply an any addr + */ + zero_sock.ss_family = dst_addr->sa_family; + if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { + struct sockaddr_in6 *src_addr6 = + (struct sockaddr_in6 *)&zero_sock; + struct sockaddr_in6 *dst_addr6 = + (struct sockaddr_in6 *)dst_addr; + + src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; + if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) + id->route.addr.dev_addr.bound_dev_if = + dst_addr6->sin6_scope_id; + } else if (dst_addr->sa_family == AF_IB) { + ((struct sockaddr_ib *)&zero_sock)->sib_pkey = + ((struct sockaddr_ib *)dst_addr)->sib_pkey; } - return rdma_bind_addr(id, src_addr); + return rdma_bind_addr(id, (struct sockaddr *)&zero_sock); }

/*

From: Oliver Graute oliver.graute@kococonnector.com

commit b6821b0d9b56386d2bf14806f90ec401468c799f upstream.

In rare cases the display is flipped or mirrored. This was observed more often in a low temperature environment. A clean reset on init_display() should help to get registers in a sane state.

Fixes: ef8f317795da (staging: fbtft: use init function instead of init sequence) Cc: stable@vger.kernel.org Signed-off-by: Oliver Graute oliver.graute@kococonnector.com Link: https://lore.kernel.org/r/20220210085322.15676-1-oliver.graute@kococonnector... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/staging/fbtft/fb_st7789v.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/drivers/staging/fbtft/fb_st7789v.c +++ b/drivers/staging/fbtft/fb_st7789v.c @@ -144,6 +144,8 @@ static int init_display(struct fbtft_par { int rc;

+ par->fbtftops.reset(par); + rc = init_tearing_effect_line(par); if (rc) return rc;

From: Mike Marciniszyn mike.marciniszyn@cornelisnetworks.com

commit 32f57cb1b2c8d6f20aefec7052b1bfeb7e3b69d4 upstream.

The qib driver load has been failing with the following message:

sysfs: cannot create duplicate filename '/devices/pci0000:80/0000:80:02.0/0000:81:00.0/infiniband/qib0/ports/1/linkcontrol'

The patch below has two "linkcontrol" names causing the duplication.

Fix by using the correct "diag_counters" name on the second instance.

Fixes: 4a7aaf88c89f ("RDMA/qib: Use attributes for the port sysfs") Link: https://lore.kernel.org/r/1645106372-23004-1-git-send-email-mike.marciniszyn... Cc: stable@vger.kernel.org Reviewed-by: Dennis Dalessandro dennis.dalessandro@cornelisnetworks.com Signed-off-by: Mike Marciniszyn mike.marciniszyn@cornelisnetworks.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/hw/qib/qib_sysfs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -541,7 +541,7 @@ static struct attribute *port_diagc_attr };

static const struct attribute_group port_diagc_group = { - .name = "linkcontrol", + .name = "diag_counters", .attrs = port_diagc_attributes, };

From: Changbin Du changbin.du@gmail.com

commit 22e2100b1b07d6f5acc71cc1acb53f680c677d77 upstream.

The trace_hardirqs_{on,off}() require the caller to setup frame pointer properly. This because these two functions use macro 'CALLER_ADDR1' (aka. __builtin_return_address(1)) to acquire caller info. If the $fp is used for other purpose, the code generated this macro (as below) could trigger memory access fault.

0xffffffff8011510e <+80>: ld a1,-16(s0) 0xffffffff80115112 <+84>: ld s2,-8(a1) # <-- paging fault here

The oops message during booting if compiled with 'irqoff' tracer enabled: [ 0.039615][ T0] Unable to handle kernel NULL pointer dereference at virtual address 00000000000000f8 [ 0.041925][ T0] Oops [#1] [ 0.042063][ T0] Modules linked in: [ 0.042864][ T0] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.17.0-rc1-00233-g9a20c48d1ed2 #29 [ 0.043568][ T0] Hardware name: riscv-virtio,qemu (DT) [ 0.044343][ T0] epc : trace_hardirqs_on+0x56/0xe2 [ 0.044601][ T0] ra : restore_all+0x12/0x6e [ 0.044721][ T0] epc : ffffffff80126a5c ra : ffffffff80003b94 sp : ffffffff81403db0 [ 0.044801][ T0] gp : ffffffff8163acd8 tp : ffffffff81414880 t0 : 0000000000000020 [ 0.044882][ T0] t1 : 0098968000000000 t2 : 0000000000000000 s0 : ffffffff81403de0 [ 0.044967][ T0] s1 : 0000000000000000 a0 : 0000000000000001 a1 : 0000000000000100 [ 0.045046][ T0] a2 : 0000000000000000 a3 : 0000000000000000 a4 : 0000000000000000 [ 0.045124][ T0] a5 : 0000000000000000 a6 : 0000000000000000 a7 : 0000000054494d45 [ 0.045210][ T0] s2 : ffffffff80003b94 s3 : ffffffff81a8f1b0 s4 : ffffffff80e27b50 [ 0.045289][ T0] s5 : ffffffff81414880 s6 : ffffffff8160fa00 s7 : 00000000800120e8 [ 0.045389][ T0] s8 : 0000000080013100 s9 : 000000000000007f s10: 0000000000000000 [ 0.045474][ T0] s11: 0000000000000000 t3 : 7fffffffffffffff t4 : 0000000000000000 [ 0.045548][ T0] t5 : 0000000000000000 t6 : ffffffff814aa368 [ 0.045620][ T0] status: 0000000200000100 badaddr: 00000000000000f8 cause: 000000000000000d [ 0.046402][ T0] [<ffffffff80003b94>] restore_all+0x12/0x6e

This because the $fp(aka. $s0) register is not used as frame pointer in the assembly entry code.

resume_kernel: REG_L s0, TASK_TI_PREEMPT_COUNT(tp) bnez s0, restore_all REG_L s0, TASK_TI_FLAGS(tp) andi s0, s0, _TIF_NEED_RESCHED beqz s0, restore_all call preempt_schedule_irq j restore_all

To fix above issue, here we add one extra level wrapper for function trace_hardirqs_{on,off}() so they can be safely called by low level entry code.

Signed-off-by: Changbin Du changbin.du@gmail.com Fixes: 3c4697982982 ("riscv: Enable LOCKDEP_SUPPORT & fixup TRACE_IRQFLAGS_SUPPORT") Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/riscv/kernel/Makefile | 2 ++ arch/riscv/kernel/entry.S | 10 +++++----- arch/riscv/kernel/trace_irq.c | 27 +++++++++++++++++++++++++++ arch/riscv/kernel/trace_irq.h | 11 +++++++++++ 4 files changed, 45 insertions(+), 5 deletions(-) create mode 100644 arch/riscv/kernel/trace_irq.c create mode 100644 arch/riscv/kernel/trace_irq.h

--- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -50,6 +50,8 @@ obj-$(CONFIG_MODULE_SECTIONS) += module- obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o

+obj-$(CONFIG_TRACE_IRQFLAGS) += trace_irq.o + obj-$(CONFIG_RISCV_BASE_PMU) += perf_event.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -108,7 +108,7 @@ _save_context: .option pop

#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_off + call __trace_hardirqs_off #endif

#ifdef CONFIG_CONTEXT_TRACKING @@ -144,7 +144,7 @@ skip_context_tracking: li t0, EXC_BREAKPOINT beq s4, t0, 1f #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on + call __trace_hardirqs_on #endif csrs CSR_STATUS, SR_IE

@@ -235,7 +235,7 @@ ret_from_exception: REG_L s0, PT_STATUS(sp) csrc CSR_STATUS, SR_IE #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_off + call __trace_hardirqs_off #endif #ifdef CONFIG_RISCV_M_MODE /* the MPP value is too large to be used as an immediate arg for addi */ @@ -271,10 +271,10 @@ restore_all: REG_L s1, PT_STATUS(sp) andi t0, s1, SR_PIE beqz t0, 1f - call trace_hardirqs_on + call __trace_hardirqs_on j 2f 1: - call trace_hardirqs_off + call __trace_hardirqs_off 2: #endif REG_L a0, PT_STATUS(sp) --- /dev/null +++ b/arch/riscv/kernel/trace_irq.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Changbin Du changbin.du@gmail.com + */ + +#include <linux/irqflags.h> +#include <linux/kprobes.h> +#include "trace_irq.h" + +/* + * trace_hardirqs_on/off require the caller to setup frame pointer properly. + * Otherwise, CALLER_ADDR1 might trigger an pagging exception in kernel. + * Here we add one extra level so they can be safely called by low + * level entry code which $fp is used for other purpose. + */ + +void __trace_hardirqs_on(void) +{ + trace_hardirqs_on(); +} +NOKPROBE_SYMBOL(__trace_hardirqs_on); + +void __trace_hardirqs_off(void) +{ + trace_hardirqs_off(); +} +NOKPROBE_SYMBOL(__trace_hardirqs_off); --- /dev/null +++ b/arch/riscv/kernel/trace_irq.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Changbin Du changbin.du@gmail.com + */ +#ifndef __TRACE_IRQ_H +#define __TRACE_IRQ_H + +void __trace_hardirqs_on(void); +void __trace_hardirqs_off(void); + +#endif /* __TRACE_IRQ_H */

From: daniel.starke@siemens.com daniel.starke@siemens.com

commit e3b7468f082d106459e86e8dc6fb9bdd65553433 upstream.

Trying to open a DLCI by sending a SABM frame may fail with a timeout. The link is closed on the initiator side without informing the responder about this event. The responder assumes the link is open after sending a UA frame to answer the SABM frame. The link gets stuck in a half open state.

This patch fixes this by initiating the proper link termination procedure after link setup timeout instead of silently closing it down.

Fixes: e1eaea46bb40 ("tty: n_gsm line discipline") Cc: stable@vger.kernel.org Signed-off-by: Daniel Starke daniel.starke@siemens.com Link: https://lore.kernel.org/r/20220218073123.2121-3-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/n_gsm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -1488,7 +1488,7 @@ static void gsm_dlci_t1(struct timer_lis dlci->mode = DLCI_MODE_ADM; gsm_dlci_open(dlci); } else { - gsm_dlci_close(dlci); + gsm_dlci_begin_close(dlci); /* prevent half open link */ }

break;

From: daniel.starke@siemens.com daniel.starke@siemens.com

commit c19d93542a6081577e6da9bf5e887979c72e80c1 upstream.

tty flow control is handled via gsmtty_throttle() and gsmtty_unthrottle(). Both functions propagate the outgoing hardware flow control state to the remote side via MSC (modem status command) frames. The local state is taken from the RTS (ready to send) flag of the tty. However, RTS gets mapped to DTR (data terminal ready), which is wrong. This patch corrects this by mapping RTS to RTS.

Fixes: e1eaea46bb40 ("tty: n_gsm line discipline") Cc: stable@vger.kernel.org Signed-off-by: Daniel Starke daniel.starke@siemens.com Link: https://lore.kernel.org/r/20220218073123.2121-5-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/n_gsm.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -3180,9 +3180,9 @@ static void gsmtty_throttle(struct tty_s if (dlci->state == DLCI_CLOSED) return; if (C_CRTSCTS(tty)) - dlci->modem_tx &= ~TIOCM_DTR; + dlci->modem_tx &= ~TIOCM_RTS; dlci->throttled = true; - /* Send an MSC with DTR cleared */ + /* Send an MSC with RTS cleared */ gsmtty_modem_update(dlci, 0); }

@@ -3192,9 +3192,9 @@ static void gsmtty_unthrottle(struct tty if (dlci->state == DLCI_CLOSED) return; if (C_CRTSCTS(tty)) - dlci->modem_tx |= TIOCM_DTR; + dlci->modem_tx |= TIOCM_RTS; dlci->throttled = false; - /* Send an MSC with DTR set */ + /* Send an MSC with RTS set */ gsmtty_modem_update(dlci, 0); }

From: daniel.starke@siemens.com daniel.starke@siemens.com

commit a2ab75b8e76e455af7867e3835fd9cdf386b508f upstream.

In the current implementation the user may open a virtual tty which then could fail to establish the underlying DLCI. The function gsmtty_open() gets stuck in tty_port_block_til_ready() while waiting for a carrier rise. This happens if the remote side fails to acknowledge the link establishment request in time or completely. At some point gsm_dlci_close() is called to abort the link establishment attempt. The function tries to inform the associated virtual tty by performing a hangup. But the blocking loop within tty_port_block_til_ready() is not informed about this event. The patch proposed here fixes this by resetting the initialization state of the virtual tty to ensure the loop exits and triggering it to make tty_port_block_til_ready() return.

Fixes: e1eaea46bb40 ("tty: n_gsm line discipline") Cc: stable@vger.kernel.org Signed-off-by: Daniel Starke daniel.starke@siemens.com Link: https://lore.kernel.org/r/20220218073123.2121-7-daniel.starke@siemens.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/n_gsm.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -1431,6 +1431,9 @@ static void gsm_dlci_close(struct gsm_dl if (dlci->addr != 0) { tty_port_tty_hangup(&dlci->port, false); kfifo_reset(&dlci->fifo); + /* Ensure that gsmtty_open() can return. */ + tty_port_set_initialized(&dlci->port, 0); + wake_up_interruptible(&dlci->port.open_wait); } else dlci->gsm->dead = true; wake_up(&dlci->gsm->event);

From: Sean Anderson seanga2@gmail.com

commit e9f7b9228a94778edb7a63fde3c0a3c5bb793064 upstream.

Using bias-pull-up would actually cause the pin to have its pull-down enabled. Fix this.

Signed-off-by: Sean Anderson seanga2@gmail.com Reviewed-by: Damien Le Moal damien.lemoal@opensource.wdc.com Fixes: d4c34d09ab03 ("pinctrl: Add RISC-V Canaan Kendryte K210 FPIOA driver") Link: https://lore.kernel.org/r/20220209182822.640905-1-seanga2@gmail.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pinctrl/pinctrl-k210.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/pinctrl/pinctrl-k210.c +++ b/drivers/pinctrl/pinctrl-k210.c @@ -527,7 +527,7 @@ static int k210_pinconf_set_param(struct case PIN_CONFIG_BIAS_PULL_UP: if (!arg) return -EINVAL; - val |= K210_PC_PD; + val |= K210_PC_PU; break; case PIN_CONFIG_DRIVE_STRENGTH: arg *= 1000;

From: Miaohe Lin linmiaohe@huawei.com

commit c94afc46cae7ad41b2ad6a99368147879f4b0e56 upstream.

memblock.{reserved,memory}.regions may be allocated using kmalloc() in memblock_double_array(). Use kfree() to release these kmalloced regions indicated by memblock_{reserved,memory}_in_slab.

Signed-off-by: Miaohe Lin linmiaohe@huawei.com Fixes: 3010f876500f ("mm: discard memblock data later") Signed-off-by: Mike Rapoport rppt@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memblock.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

--- a/mm/memblock.c +++ b/mm/memblock.c @@ -366,14 +366,20 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - __memblock_free_late(addr, size); + if (memblock_reserved_in_slab) + kfree(memblock.reserved.regions); + else + __memblock_free_late(addr, size); }

if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - __memblock_free_late(addr, size); + if (memblock_memory_in_slab) + kfree(memblock.memory.regions); + else + __memblock_free_late(addr, size); }

memblock_memory = NULL;

From: Jacob Keller jacob.e.keller@intel.com

commit fadead80fe4c033b5e514fcbadd20b55c4494112 upstream.

Commit c503e63200c6 ("ice: Stop processing VF messages during teardown") introduced a driver state flag, ICE_VF_DEINIT_IN_PROGRESS, which is intended to prevent some issues with concurrently handling messages from VFs while tearing down the VFs.

This change was motivated by crashes caused while tearing down and bringing up VFs in rapid succession.

It turns out that the fix actually introduces issues with the VF driver caused because the PF no longer responds to any messages sent by the VF during its .remove routine. This results in the VF potentially removing its DMA memory before the PF has shut down the device queues.

Additionally, the fix doesn't actually resolve concurrency issues within the ice driver. It is possible for a VF to initiate a reset just prior to the ice driver removing VFs. This can result in the remove task concurrently operating while the VF is being reset. This results in similar memory corruption and panics purportedly fixed by that commit.

Fix this concurrency at its root by protecting both the reset and removal flows using the existing VF cfg_lock. This ensures that we cannot remove the VF while any outstanding critical tasks such as a virtchnl message or a reset are occurring.

This locking change also fixes the root cause originally fixed by commit c503e63200c6 ("ice: Stop processing VF messages during teardown"), so we can simply revert it.

Note that I kept these two changes together because simply reverting the original commit alone would leave the driver vulnerable to worse race conditions.

Fixes: c503e63200c6 ("ice: Stop processing VF messages during teardown") Cc: stable@vger.kernel.org # e6ba5273d4ed: ice: Fix race conditions between virtchnl handling and VF ndo ops Cc: stable@vger.kernel.org Signed-off-by: Jacob Keller jacob.e.keller@intel.com Tested-by: Konrad Jankowski konrad0.jankowski@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/ice/ice.h | 1 drivers/net/ethernet/intel/ice/ice_main.c | 2 + drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c | 42 +++++++++++++---------- 3 files changed, 27 insertions(+), 18 deletions(-)

--- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -231,7 +231,6 @@ enum ice_pf_state { ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, ICE_VF_DIS, - ICE_VF_DEINIT_IN_PROGRESS, ICE_CFG_BUSY, ICE_SERVICE_SCHED, ICE_SERVICE_DIS, --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1679,7 +1679,9 @@ static void ice_handle_mdd_event(struct * reset, so print the event prior to reset. */ ice_print_vf_rx_mdd_event(vf); + mutex_lock(&pf->vf[i].cfg_lock); ice_reset_vf(&pf->vf[i], false); + mutex_unlock(&pf->vf[i].cfg_lock); } } } --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -615,8 +615,6 @@ void ice_free_vfs(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; unsigned int tmp, i;

- set_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); - if (!pf->vf) return;

@@ -632,22 +630,26 @@ void ice_free_vfs(struct ice_pf *pf) else dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n");

- /* Avoid wait time by stopping all VFs at the same time */ - ice_for_each_vf(pf, i) - ice_dis_vf_qs(&pf->vf[i]); - tmp = pf->num_alloc_vfs; pf->num_qps_per_vf = 0; pf->num_alloc_vfs = 0; for (i = 0; i < tmp; i++) { - if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { + struct ice_vf *vf = &pf->vf[i]; + + mutex_lock(&vf->cfg_lock); + + ice_dis_vf_qs(vf); + + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { /* disable VF qp mappings and set VF disable state */ - ice_dis_vf_mappings(&pf->vf[i]); - set_bit(ICE_VF_STATE_DIS, pf->vf[i].vf_states); - ice_free_vf_res(&pf->vf[i]); + ice_dis_vf_mappings(vf); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + ice_free_vf_res(vf); }

- mutex_destroy(&pf->vf[i].cfg_lock); + mutex_unlock(&vf->cfg_lock); + + mutex_destroy(&vf->cfg_lock); }

if (ice_sriov_free_msix_res(pf)) @@ -683,7 +685,6 @@ void ice_free_vfs(struct ice_pf *pf) i);

clear_bit(ICE_VF_DIS, pf->state); - clear_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); }

@@ -1567,6 +1568,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf ice_for_each_vf(pf, v) { vf = &pf->vf[v];

+ mutex_lock(&vf->cfg_lock); + vf->driver_caps = 0; ice_vc_set_default_allowlist(vf);

@@ -1581,6 +1584,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi(vf); ice_vf_post_vsi_rebuild(vf); + + mutex_unlock(&vf->cfg_lock); }

ice_flush(hw); @@ -1627,6 +1632,8 @@ bool ice_reset_vf(struct ice_vf *vf, boo u32 reg; int i;

+ lockdep_assert_held(&vf->cfg_lock); + dev = ice_pf_to_dev(pf);

if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { @@ -2113,9 +2120,12 @@ void ice_process_vflr_event(struct ice_p bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; /* read GLGEN_VFLRSTAT register to find out the flr VFs */ reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); - if (reg & BIT(bit_idx)) + if (reg & BIT(bit_idx)) { /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + mutex_lock(&vf->cfg_lock); ice_reset_vf(vf, true); + mutex_unlock(&vf->cfg_lock); + } } }

@@ -2192,7 +2202,9 @@ ice_vf_lan_overflow_event(struct ice_pf if (!vf) return;

+ mutex_lock(&vf->cfg_lock); ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); }

/** @@ -4429,10 +4441,6 @@ void ice_vc_process_vf_msg(struct ice_pf struct device *dev; int err = 0;

- /* if de-init is underway, don't process messages from VF */ - if (test_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state)) - return; - dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) { err = -EINVAL;