diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst index fb496b2ebfd38..92d3432460d75 100644 --- a/Documentation/process/submitting-patches.rst +++ b/Documentation/process/submitting-patches.rst @@ -77,7 +77,7 @@ as you intend it to. The maintainer will thank you if you write your patch description in a form which can be easily pulled into Linux's source code management -system, ``git``, as a "commit log". See :ref:`explicit_in_reply_to`. +system, ``git``, as a "commit log". See :ref:`the_canonical_patch_format`. Solve only one problem per patch. If your description starts to get long, that's a sign that you probably need to split up your patch. diff --git a/Makefile b/Makefile index 2bb168acb8f43..6b1d606a92f6f 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 18 -SUBLEVEL = 1 +SUBLEVEL = 2 EXTRAVERSION = NAME = Superb Owl diff --git a/arch/arm/boot/dts/s5pv210-aries.dtsi b/arch/arm/boot/dts/s5pv210-aries.dtsi index c8f1c324a6c26..26f2be2d9faa2 100644 --- a/arch/arm/boot/dts/s5pv210-aries.dtsi +++ b/arch/arm/boot/dts/s5pv210-aries.dtsi @@ -895,7 +895,7 @@ device-wakeup-gpios = <&gpg3 4 GPIO_ACTIVE_HIGH>; interrupt-parent = <&gph2>; interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "host-wake"; + interrupt-names = "host-wakeup"; }; }; diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c index 45c993dd05f5e..36f2314c58e5f 100644 --- a/arch/powerpc/kvm/book3s_hv_uvmem.c +++ b/arch/powerpc/kvm/book3s_hv_uvmem.c @@ -361,13 +361,15 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm, static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot, struct kvm *kvm, unsigned long *gfn) { - struct kvmppc_uvmem_slot *p; + struct kvmppc_uvmem_slot *p = NULL, *iter; bool ret = false; unsigned long i; - list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) - if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns) + list_for_each_entry(iter, &kvm->arch.uvmem_pfns, list) + if (*gfn >= iter->base_pfn && *gfn < iter->base_pfn + iter->nr_pfns) { + p = iter; break; + } if (!p) return ret; /* diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index f78e2b3501a19..35f222aa66bfc 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -382,6 +382,103 @@ do { \ #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT +#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm_volatile_goto("\n" \ + "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ + _ASM_EXTABLE_UA(1b, %l[label]) \ + : CC_OUT(z) (success), \ + [ptr] "+m" (*_ptr), \ + [old] "+a" (__old) \ + : [new] ltype (__new) \ + : "memory" \ + : label); \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) + +#ifdef CONFIG_X86_32 +#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm_volatile_goto("\n" \ + "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ + _ASM_EXTABLE_UA(1b, %l[label]) \ + : CC_OUT(z) (success), \ + "+A" (__old), \ + [ptr] "+m" (*_ptr) \ + : "b" ((u32)__new), \ + "c" ((u32)((u64)__new >> 32)) \ + : "memory" \ + : label); \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) +#endif // CONFIG_X86_32 +#else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT +#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ + int __err = 0; \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm volatile("\n" \ + "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ + CC_SET(z) \ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ + %[errout]) \ + : CC_OUT(z) (success), \ + [errout] "+r" (__err), \ + [ptr] "+m" (*_ptr), \ + [old] "+a" (__old) \ + : [new] ltype (__new) \ + : "memory", "cc"); \ + if (unlikely(__err)) \ + goto label; \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) + +#ifdef CONFIG_X86_32 +/* + * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error. + * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are + * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses + * both ESI and EDI for the memory operand, compilation will fail if the error + * is an input+output as there will be no register available for input. + */ +#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ + int __result; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm volatile("\n" \ + "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ + "mov $0, %%ecx\n\t" \ + "setz %%cl\n" \ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \ + : [result]"=c" (__result), \ + "+A" (__old), \ + [ptr] "+m" (*_ptr) \ + : "b" ((u32)__new), \ + "c" ((u32)((u64)__new >> 32)) \ + : "memory", "cc"); \ + if (unlikely(__result < 0)) \ + goto label; \ + if (unlikely(!__result)) \ + *_old = __old; \ + likely(__result); }) +#endif // CONFIG_X86_32 +#endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT + /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct __user *)(x)) @@ -474,6 +571,51 @@ do { \ } while (0) #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT +extern void __try_cmpxchg_user_wrong_size(void); + +#ifndef CONFIG_X86_32 +#define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ + __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) +#endif + +/* + * Force the pointer to u to match the size expected by the asm helper. + * clang/LLVM compiles all cases and only discards the unused paths after + * processing errors, which breaks i386 if the pointer is an 8-byte value. + */ +#define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ + bool __ret; \ + __chk_user_ptr(_ptr); \ + switch (sizeof(*(_ptr))) { \ + case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ + (__force u8 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ + (__force u16 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ + (__force u32 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ + (_nval), _label); \ + break; \ + default: __try_cmpxchg_user_wrong_size(); \ + } \ + __ret; }) + +/* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ +#define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ + int __ret = -EFAULT; \ + __uaccess_begin_nospec(); \ + __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ +_label: \ + __uaccess_end(); \ + __ret; \ + }) + /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 7c63a1911fae9..3c24e6124d955 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -12,6 +12,92 @@ #include "encls.h" #include "sgx.h" +#define PCMDS_PER_PAGE (PAGE_SIZE / sizeof(struct sgx_pcmd)) +/* + * 32 PCMD entries share a PCMD page. PCMD_FIRST_MASK is used to + * determine the page index associated with the first PCMD entry + * within a PCMD page. + */ +#define PCMD_FIRST_MASK GENMASK(4, 0) + +/** + * reclaimer_writing_to_pcmd() - Query if any enclave page associated with + * a PCMD page is in process of being reclaimed. + * @encl: Enclave to which PCMD page belongs + * @start_addr: Address of enclave page using first entry within the PCMD page + * + * When an enclave page is reclaimed some Paging Crypto MetaData (PCMD) is + * stored. The PCMD data of a reclaimed enclave page contains enough + * information for the processor to verify the page at the time + * it is loaded back into the Enclave Page Cache (EPC). + * + * The backing storage to which enclave pages are reclaimed is laid out as + * follows: + * Encrypted enclave pages:SECS page:PCMD pages + * + * Each PCMD page contains the PCMD metadata of + * PAGE_SIZE/sizeof(struct sgx_pcmd) enclave pages. + * + * A PCMD page can only be truncated if it is (a) empty, and (b) not in the + * process of getting data (and thus soon being non-empty). (b) is tested with + * a check if an enclave page sharing the PCMD page is in the process of being + * reclaimed. + * + * The reclaimer sets the SGX_ENCL_PAGE_BEING_RECLAIMED flag when it + * intends to reclaim that enclave page - it means that the PCMD page + * associated with that enclave page is about to get some data and thus + * even if the PCMD page is empty, it should not be truncated. + * + * Context: Enclave mutex (&sgx_encl->lock) must be held. + * Return: 1 if the reclaimer is about to write to the PCMD page + * 0 if the reclaimer has no intention to write to the PCMD page + */ +static int reclaimer_writing_to_pcmd(struct sgx_encl *encl, + unsigned long start_addr) +{ + int reclaimed = 0; + int i; + + /* + * PCMD_FIRST_MASK is based on number of PCMD entries within + * PCMD page being 32. + */ + BUILD_BUG_ON(PCMDS_PER_PAGE != 32); + + for (i = 0; i < PCMDS_PER_PAGE; i++) { + struct sgx_encl_page *entry; + unsigned long addr; + + addr = start_addr + i * PAGE_SIZE; + + /* + * Stop when reaching the SECS page - it does not + * have a page_array entry and its reclaim is + * started and completed with enclave mutex held so + * it does not use the SGX_ENCL_PAGE_BEING_RECLAIMED + * flag. + */ + if (addr == encl->base + encl->size) + break; + + entry = xa_load(&encl->page_array, PFN_DOWN(addr)); + if (!entry) + continue; + + /* + * VA page slot ID uses same bit as the flag so it is important + * to ensure that the page is not already in backing store. + */ + if (entry->epc_page && + (entry->desc & SGX_ENCL_PAGE_BEING_RECLAIMED)) { + reclaimed = 1; + break; + } + } + + return reclaimed; +} + /* * Calculate byte offset of a PCMD struct associated with an enclave page. PCMD's * follow right after the EPC data in the backing storage. In addition to the @@ -47,6 +133,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; struct sgx_encl *encl = encl_page->encl; pgoff_t page_index, page_pcmd_off; + unsigned long pcmd_first_page; struct sgx_pageinfo pginfo; struct sgx_backing b; bool pcmd_page_empty; @@ -58,6 +145,11 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, else page_index = PFN_DOWN(encl->size); + /* + * Address of enclave page using the first entry within the PCMD page. + */ + pcmd_first_page = PFN_PHYS(page_index & ~PCMD_FIRST_MASK) + encl->base; + page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); ret = sgx_encl_get_backing(encl, page_index, &b); @@ -84,6 +176,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, } memset(pcmd_page + b.pcmd_offset, 0, sizeof(struct sgx_pcmd)); + set_page_dirty(b.pcmd); /* * The area for the PCMD in the page was zeroed above. Check if the @@ -94,12 +187,20 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, kunmap_atomic(pcmd_page); kunmap_atomic((void *)(unsigned long)pginfo.contents); - sgx_encl_put_backing(&b, false); + get_page(b.pcmd); + sgx_encl_put_backing(&b); sgx_encl_truncate_backing_page(encl, page_index); - if (pcmd_page_empty) + if (pcmd_page_empty && !reclaimer_writing_to_pcmd(encl, pcmd_first_page)) { sgx_encl_truncate_backing_page(encl, PFN_DOWN(page_pcmd_off)); + pcmd_page = kmap_atomic(b.pcmd); + if (memchr_inv(pcmd_page, 0, PAGE_SIZE)) + pr_warn("PCMD page not empty after truncate.\n"); + kunmap_atomic(pcmd_page); + } + + put_page(b.pcmd); return ret; } @@ -645,15 +746,9 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, /** * sgx_encl_put_backing() - Unpin the backing storage * @backing: data for accessing backing storage for the page - * @do_write: mark pages dirty */ -void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write) +void sgx_encl_put_backing(struct sgx_backing *backing) { - if (do_write) { - set_page_dirty(backing->pcmd); - set_page_dirty(backing->contents); - } - put_page(backing->pcmd); put_page(backing->contents); } diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index fec43ca65065b..d44e7372151f0 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -107,7 +107,7 @@ void sgx_encl_release(struct kref *ref); int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm); int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing); -void sgx_encl_put_backing(struct sgx_backing *backing, bool do_write); +void sgx_encl_put_backing(struct sgx_backing *backing); int sgx_encl_test_and_clear_young(struct mm_struct *mm, struct sgx_encl_page *page); diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 8e4bc6453d263..ab4ec54bbdd94 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -191,6 +191,8 @@ static int __sgx_encl_ewb(struct sgx_epc_page *epc_page, void *va_slot, backing->pcmd_offset; ret = __ewb(&pginfo, sgx_get_epc_virt_addr(epc_page), va_slot); + set_page_dirty(backing->pcmd); + set_page_dirty(backing->contents); kunmap_atomic((void *)(unsigned long)(pginfo.metadata - backing->pcmd_offset)); @@ -308,6 +310,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page, sgx_encl_ewb(epc_page, backing); encl_page->epc_page = NULL; encl->secs_child_cnt--; + sgx_encl_put_backing(backing); if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) { ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size), @@ -320,7 +323,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page, sgx_encl_free_epc_page(encl->secs.epc_page); encl->secs.epc_page = NULL; - sgx_encl_put_backing(&secs_backing, true); + sgx_encl_put_backing(&secs_backing); } out: @@ -379,11 +382,14 @@ static void sgx_reclaim_pages(void) goto skip; page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base); + + mutex_lock(&encl_page->encl->lock); ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]); - if (ret) + if (ret) { + mutex_unlock(&encl_page->encl->lock); goto skip; + } - mutex_lock(&encl_page->encl->lock); encl_page->desc |= SGX_ENCL_PAGE_BEING_RECLAIMED; mutex_unlock(&encl_page->encl->lock); continue; @@ -411,7 +417,6 @@ skip: encl_page = epc_page->owner; sgx_reclaimer_write(epc_page, &backing[i]); - sgx_encl_put_backing(&backing[i], true); kref_put(&encl_page->encl->refcount, sgx_encl_release); epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index e28ab0ecc5378..0fdc807ae13f8 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -14,6 +14,8 @@ #include #include +#include + #include #include #include @@ -232,7 +234,20 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu) gfpu->fpstate = fpstate; gfpu->xfeatures = fpu_user_cfg.default_features; gfpu->perm = fpu_user_cfg.default_features; - gfpu->uabi_size = fpu_user_cfg.default_size; + + /* + * KVM sets the FP+SSE bits in the XSAVE header when copying FPU state + * to userspace, even when XSAVE is unsupported, so that restoring FPU + * state on a different CPU that does support XSAVE can cleanly load + * the incoming state using its natural XSAVE. In other words, KVM's + * uABI size may be larger than this host's default size. Conversely, + * the default size should never be larger than KVM's base uABI size; + * all features that can expand the uABI size must be opt-in. + */ + gfpu->uabi_size = sizeof(struct kvm_xsave); + if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size)) + gfpu->uabi_size = fpu_user_cfg.default_size; + fpu_init_guest_permissions(gfpu); return true; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 8b1c45c9cda87..1a55bf700f926 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -191,7 +191,7 @@ void kvm_async_pf_task_wake(u32 token) { u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS); struct kvm_task_sleep_head *b = &async_pf_sleepers[key]; - struct kvm_task_sleep_node *n; + struct kvm_task_sleep_node *n, *dummy = NULL; if (token == ~0) { apf_task_wake_all(); @@ -203,28 +203,41 @@ again: n = _find_apf_task(b, token); if (!n) { /* - * async PF was not yet handled. - * Add dummy entry for the token. + * Async #PF not yet handled, add a dummy entry for the token. + * Allocating the token must be down outside of the raw lock + * as the allocator is preemptible on PREEMPT_RT kernels. */ - n = kzalloc(sizeof(*n), GFP_ATOMIC); - if (!n) { + if (!dummy) { + raw_spin_unlock(&b->lock); + dummy = kzalloc(sizeof(*dummy), GFP_ATOMIC); + /* - * Allocation failed! Busy wait while other cpu - * handles async PF. + * Continue looping on allocation failure, eventually + * the async #PF will be handled and allocating a new + * node will be unnecessary. + */ + if (!dummy) + cpu_relax(); + + /* + * Recheck for async #PF completion before enqueueing + * the dummy token to avoid duplicate list entries. */ - raw_spin_unlock(&b->lock); - cpu_relax(); goto again; } - n->token = token; - n->cpu = smp_processor_id(); - init_swait_queue_head(&n->wq); - hlist_add_head(&n->link, &b->list); + dummy->token = token; + dummy->cpu = smp_processor_id(); + init_swait_queue_head(&dummy->wq); + hlist_add_head(&dummy->link, &b->list); + dummy = NULL; } else { apf_task_wake_one(n); } raw_spin_unlock(&b->lock); - return; + + /* A dummy token might be allocated and ultimately not used. */ + if (dummy) + kfree(dummy); } EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 45e1573f8f1d3..cf48ac96ceecb 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1843,17 +1843,14 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm, &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \ if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else -static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, +static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { int ret = vcpu->arch.mmu->sync_page(vcpu, sp); - if (ret < 0) { + if (ret < 0) kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); - return false; - } - - return !!ret; + return ret; } static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm, @@ -1975,7 +1972,7 @@ static int mmu_sync_children(struct kvm_vcpu *vcpu, for_each_sp(pages, sp, parents, i) { kvm_unlink_unsync_page(vcpu->kvm, sp); - flush |= kvm_sync_page(vcpu, sp, &invalid_list); + flush |= kvm_sync_page(vcpu, sp, &invalid_list) > 0; mmu_pages_clear_parents(&parents); } if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { @@ -2016,6 +2013,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, struct hlist_head *sp_list; unsigned quadrant; struct kvm_mmu_page *sp; + int ret; int collisions = 0; LIST_HEAD(invalid_list); @@ -2068,11 +2066,13 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, * If the sync fails, the page is zapped. If so, break * in order to rebuild it. */ - if (!kvm_sync_page(vcpu, sp, &invalid_list)) + ret = kvm_sync_page(vcpu, sp, &invalid_list); + if (ret < 0) break; WARN_ON(!list_empty(&invalid_list)); - kvm_flush_remote_tlbs(vcpu->kvm); + if (ret > 0) + kvm_flush_remote_tlbs(vcpu->kvm); } __clear_sp_write_flooding_count(sp); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 01fee5f67ac37..beb3ce8d94eb3 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -144,42 +144,6 @@ static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) FNAME(is_bad_mt_xwr)(&mmu->guest_rsvd_check, gpte); } -static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - pt_element_t __user *ptep_user, unsigned index, - pt_element_t orig_pte, pt_element_t new_pte) -{ - signed char r; - - if (!user_access_begin(ptep_user, sizeof(pt_element_t))) - return -EFAULT; - -#ifdef CMPXCHG - asm volatile("1:" LOCK_PREFIX CMPXCHG " %[new], %[ptr]\n" - "setnz %b[r]\n" - "2:" - _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %k[r]) - : [ptr] "+m" (*ptep_user), - [old] "+a" (orig_pte), - [r] "=q" (r) - : [new] "r" (new_pte) - : "memory"); -#else - asm volatile("1:" LOCK_PREFIX "cmpxchg8b %[ptr]\n" - "setnz %b[r]\n" - "2:" - _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %k[r]) - : [ptr] "+m" (*ptep_user), - [old] "+A" (orig_pte), - [r] "=q" (r) - : [new_lo] "b" ((u32)new_pte), - [new_hi] "c" ((u32)(new_pte >> 32)) - : "memory"); -#endif - - user_access_end(); - return r; -} - static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, u64 gpte) @@ -278,7 +242,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, if (unlikely(!walker->pte_writable[level - 1])) continue; - ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte); + ret = __try_cmpxchg_user(ptep_user, &orig_pte, pte, fault); if (ret) return ret; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 96bab464967f2..1a9b60cb6bcb8 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -819,9 +819,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) struct kvm_host_map map; int rc; - /* Triple faults in L2 should never escape. */ - WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)); - rc = kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.vmcb12_gpa), &map); if (rc) { if (rc == -EINVAL) diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 7c392873626fd..4b7d490c0b639 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -688,7 +688,7 @@ static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp) if (params.len > SEV_FW_BLOB_MAX_SIZE) return -EINVAL; - blob = kmalloc(params.len, GFP_KERNEL_ACCOUNT); + blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT); if (!blob) return -ENOMEM; @@ -808,7 +808,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (!IS_ALIGNED(dst_paddr, 16) || !IS_ALIGNED(paddr, 16) || !IS_ALIGNED(size, 16)) { - tpage = (void *)alloc_page(GFP_KERNEL); + tpage = (void *)alloc_page(GFP_KERNEL | __GFP_ZERO); if (!tpage) return -ENOMEM; @@ -1094,7 +1094,7 @@ static int sev_get_attestation_report(struct kvm *kvm, struct kvm_sev_cmd *argp) if (params.len > SEV_FW_BLOB_MAX_SIZE) return -EINVAL; - blob = kmalloc(params.len, GFP_KERNEL_ACCOUNT); + blob = kzalloc(params.len, GFP_KERNEL_ACCOUNT); if (!blob) return -ENOMEM; @@ -1176,7 +1176,7 @@ static int sev_send_start(struct kvm *kvm, struct kvm_sev_cmd *argp) return -EINVAL; /* allocate the memory to hold the session data blob */ - session_data = kmalloc(params.session_len, GFP_KERNEL_ACCOUNT); + session_data = kzalloc(params.session_len, GFP_KERNEL_ACCOUNT); if (!session_data) return -ENOMEM; @@ -1300,11 +1300,11 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* allocate memory for header and transport buffer */ ret = -ENOMEM; - hdr = kmalloc(params.hdr_len, GFP_KERNEL_ACCOUNT); + hdr = kzalloc(params.hdr_len, GFP_KERNEL_ACCOUNT); if (!hdr) goto e_unpin; - trans_data = kmalloc(params.trans_len, GFP_KERNEL_ACCOUNT); + trans_data = kzalloc(params.trans_len, GFP_KERNEL_ACCOUNT); if (!trans_data) goto e_free_hdr; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 856c875638833..880d0b0c9315b 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4518,9 +4518,6 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); - /* Similarly, triple faults in L2 should never escape. */ - WARN_ON_ONCE(kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)); - if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { /* * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 610355b9ccceb..982df9c000d31 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7856,7 +7856,7 @@ static unsigned int vmx_handle_intel_pt_intr(void) struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); /* '0' on failure so that the !PT case can use a RET0 static call. */ - if (!kvm_arch_pmi_in_guest(vcpu)) + if (!vcpu || !kvm_handling_nmi_from_guest(vcpu)) return 0; kvm_make_request(KVM_REQ_PMI, vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4790f0d7d40b8..39c571224ac28 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7229,15 +7229,8 @@ static int emulator_write_emulated(struct x86_emulate_ctxt *ctxt, exception, &write_emultor); } -#define CMPXCHG_TYPE(t, ptr, old, new) \ - (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old)) - -#ifdef CONFIG_X86_64 -# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new) -#else -# define CMPXCHG64(ptr, old, new) \ - (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) -#endif +#define emulator_try_cmpxchg_user(t, ptr, old, new) \ + (__try_cmpxchg_user((t __user *)(ptr), (t *)(old), *(t *)(new), efault ## t)) static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, @@ -7246,12 +7239,11 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, unsigned int bytes, struct x86_exception *exception) { - struct kvm_host_map map; struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u64 page_line_mask; + unsigned long hva; gpa_t gpa; - char *kaddr; - bool exchanged; + int r; /* guests cmpxchg8b have to be emulated atomically */ if (bytes > 8 || (bytes & (bytes - 1))) @@ -7275,31 +7267,32 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (((gpa + bytes - 1) & page_line_mask) != (gpa & page_line_mask)) goto emul_write; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(gpa), &map)) + hva = kvm_vcpu_gfn_to_hva(vcpu, gpa_to_gfn(gpa)); + if (kvm_is_error_hva(hva)) goto emul_write; - kaddr = map.hva + offset_in_page(gpa); + hva += offset_in_page(gpa); switch (bytes) { case 1: - exchanged = CMPXCHG_TYPE(u8, kaddr, old, new); + r = emulator_try_cmpxchg_user(u8, hva, old, new); break; case 2: - exchanged = CMPXCHG_TYPE(u16, kaddr, old, new); + r = emulator_try_cmpxchg_user(u16, hva, old, new); break; case 4: - exchanged = CMPXCHG_TYPE(u32, kaddr, old, new); + r = emulator_try_cmpxchg_user(u32, hva, old, new); break; case 8: - exchanged = CMPXCHG64(kaddr, old, new); + r = emulator_try_cmpxchg_user(u64, hva, old, new); break; default: BUG(); } - kvm_vcpu_unmap(vcpu, &map, true); - - if (!exchanged) + if (r < 0) + goto emul_write; + if (r) return X86EMUL_CMPXCHG_FAILED; kvm_page_track_write(vcpu, gpa, new, bytes); @@ -8251,7 +8244,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction); -static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) +static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r) { if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { @@ -8320,25 +8313,23 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) } /* - * Decode to be emulated instruction. Return EMULATION_OK if success. + * Decode an instruction for emulation. The caller is responsible for handling + * code breakpoints. Note, manually detecting code breakpoints is unnecessary + * (and wrong) when emulating on an intercepted fault-like exception[*], as + * code breakpoints have higher priority and thus have already been done by + * hardware. + * + * [*] Except #MC, which is higher priority, but KVM should never emulate in + * response to a machine check. */ int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, void *insn, int insn_len) { - int r = EMULATION_OK; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + int r; init_emulate_ctxt(vcpu); - /* - * We will reenter on the same instruction since we do not set - * complete_userspace_io. This does not handle watchpoints yet, - * those would be handled in the emulate_ops. - */ - if (!(emulation_type & EMULTYPE_SKIP) && - kvm_vcpu_check_breakpoint(vcpu, &r)) - return r; - r = x86_decode_insn(ctxt, insn, insn_len, emulation_type); trace_kvm_emulate_insn_start(vcpu); @@ -8371,6 +8362,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); + /* + * Return immediately if RIP hits a code breakpoint, such #DBs + * are fault-like and are higher priority than any faults on + * the code fetch itself. + */ + if (!(emulation_type & EMULTYPE_SKIP) && + kvm_vcpu_check_code_breakpoint(vcpu, &r)) + return r; + r = x86_decode_emulated_instruction(vcpu, emulation_type, insn, insn_len); if (r != EMULATION_OK) { @@ -11747,20 +11747,15 @@ static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) vcpu_put(vcpu); } -static void kvm_free_vcpus(struct kvm *kvm) +static void kvm_unload_vcpu_mmus(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; - /* - * Unpin any mmu pages first. - */ kvm_for_each_vcpu(i, vcpu, kvm) { kvm_clear_async_pf_completion_queue(vcpu); kvm_unload_vcpu_mmu(vcpu); } - - kvm_destroy_vcpus(kvm); } void kvm_arch_sync_events(struct kvm *kvm) @@ -11866,11 +11861,12 @@ void kvm_arch_destroy_vm(struct kvm *kvm) __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } + kvm_unload_vcpu_mmus(kvm); static_call_cond(kvm_x86_vm_destroy)(kvm); kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1)); kvm_pic_destroy(kvm); kvm_ioapic_destroy(kvm); - kvm_free_vcpus(kvm); + kvm_destroy_vcpus(kvm); kvfree(rcu_dereference_check(kvm->arch.apic_map, 1)); kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); diff --git a/crypto/ecrdsa.c b/crypto/ecrdsa.c index b32ffcaad9adf..f3c6b5e15e75b 100644 --- a/crypto/ecrdsa.c +++ b/crypto/ecrdsa.c @@ -113,15 +113,15 @@ static int ecrdsa_verify(struct akcipher_request *req) /* Step 1: verify that 0 < r < q, 0 < s < q */ if (vli_is_zero(r, ndigits) || - vli_cmp(r, ctx->curve->n, ndigits) == 1 || + vli_cmp(r, ctx->curve->n, ndigits) >= 0 || vli_is_zero(s, ndigits) || - vli_cmp(s, ctx->curve->n, ndigits) == 1) + vli_cmp(s, ctx->curve->n, ndigits) >= 0) return -EKEYREJECTED; /* Step 2: calculate hash (h) of the message (passed as input) */ /* Step 3: calculate e = h \mod q */ vli_from_le64(e, digest, ndigits); - if (vli_cmp(e, ctx->curve->n, ndigits) == 1) + if (vli_cmp(e, ctx->curve->n, ndigits) >= 0) vli_sub(e, e, ctx->curve->n, ndigits); if (vli_is_zero(e, ndigits)) e[0] = 1; @@ -137,7 +137,7 @@ static int ecrdsa_verify(struct akcipher_request *req) /* Step 6: calculate point C = z_1P + z_2Q, and R = x_c \mod q */ ecc_point_mult_shamir(&cc, z1, &ctx->curve->g, z2, &ctx->pub_key, ctx->curve); - if (vli_cmp(cc.x, ctx->curve->n, ndigits) == 1) + if (vli_cmp(cc.x, ctx->curve->n, ndigits) >= 0) vli_sub(cc.x, cc.x, ctx->curve->n, ndigits); /* Step 7: if R == r signature is valid */ diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index f6e91fb432a3b..eab34e24d9446 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -696,9 +696,9 @@ static int qca_close(struct hci_uart *hu) skb_queue_purge(&qca->tx_wait_q); skb_queue_purge(&qca->txq); skb_queue_purge(&qca->rx_memdump_q); - del_timer(&qca->tx_idle_timer); - del_timer(&qca->wake_retrans_timer); destroy_workqueue(qca->workqueue); + del_timer_sync(&qca->tx_idle_timer); + del_timer_sync(&qca->wake_retrans_timer); qca->hu = NULL; kfree_skb(qca->rx_skb); diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c index 4704fa553098b..04a3e23a4afc7 100644 --- a/drivers/char/tpm/tpm2-cmd.c +++ b/drivers/char/tpm/tpm2-cmd.c @@ -400,7 +400,16 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id, u32 *value, if (!rc) { out = (struct tpm2_get_cap_out *) &buf.data[TPM_HEADER_SIZE]; - *value = be32_to_cpu(out->value); + /* + * To prevent failing boot up of some systems, Infineon TPM2.0 + * returns SUCCESS on TPM2_Startup in field upgrade mode. Also + * the TPM2_Getcapability command returns a zero length list + * in field upgrade mode. + */ + if (be32_to_cpu(out->property_cnt) > 0) + *value = be32_to_cpu(out->value); + else + rc = -ENODATA; } tpm_buf_destroy(&buf); return rc; diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c index 3af4c07a9342f..d3989b257f422 100644 --- a/drivers/char/tpm/tpm_ibmvtpm.c +++ b/drivers/char/tpm/tpm_ibmvtpm.c @@ -681,6 +681,7 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev, if (!wait_event_timeout(ibmvtpm->crq_queue.wq, ibmvtpm->rtce_buf != NULL, HZ)) { + rc = -ENODEV; dev_err(dev, "CRQ response timed out\n"); goto init_irq_cleanup; } diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c index ca0361b2dbb07..f87aa2169e5f5 100644 --- a/drivers/crypto/caam/ctrl.c +++ b/drivers/crypto/caam/ctrl.c @@ -609,6 +609,13 @@ static bool check_version(struct fsl_mc_version *mc_version, u32 major, } #endif +static bool needs_entropy_delay_adjustment(void) +{ + if (of_machine_is_compatible("fsl,imx6sx")) + return true; + return false; +} + /* Probe routine for CAAM top (controller) level */ static int caam_probe(struct platform_device *pdev) { @@ -855,6 +862,8 @@ static int caam_probe(struct platform_device *pdev) * Also, if a handle was instantiated, do not change * the TRNG parameters. */ + if (needs_entropy_delay_adjustment()) + ent_delay = 12000; if (!(ctrlpriv->rng4_sh_init || inst_handles)) { dev_info(dev, "Entropy delay = %u\n", @@ -871,6 +880,15 @@ static int caam_probe(struct platform_device *pdev) */ ret = instantiate_rng(dev, inst_handles, gen_sk); + /* + * Entropy delay is determined via TRNG characterization. + * TRNG characterization is run across different voltages + * and temperatures. + * If worst case value for ent_dly is identified, + * the loop can be skipped for that platform. + */ + if (needs_entropy_delay_adjustment()) + break; if (ret == -EAGAIN) /* * if here, the loop will rerun, diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h index a03c6cf723312..dfa7ee41c5e9c 100644 --- a/drivers/crypto/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h @@ -152,9 +152,9 @@ struct adf_pfvf_ops { int (*enable_comms)(struct adf_accel_dev *accel_dev); u32 (*get_pf2vf_offset)(u32 i); u32 (*get_vf2pf_offset)(u32 i); - u32 (*get_vf2pf_sources)(void __iomem *pmisc_addr); void (*enable_vf2pf_interrupts)(void __iomem *pmisc_addr, u32 vf_mask); void (*disable_vf2pf_interrupts)(void __iomem *pmisc_addr, u32 vf_mask); + u32 (*disable_pending_vf2pf_interrupts)(void __iomem *pmisc_addr); int (*send_msg)(struct adf_accel_dev *accel_dev, struct pfvf_message msg, u32 pfvf_offset, struct mutex *csr_lock); struct pfvf_message (*recv_msg)(struct adf_accel_dev *accel_dev, diff --git a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c b/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c index 1a9072aac2ca9..def4cc8e1039a 100644 --- a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c +++ b/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c @@ -13,6 +13,7 @@ #include "adf_pfvf_utils.h" /* VF2PF interrupts */ +#define ADF_GEN2_VF_MSK 0xFFFF #define ADF_GEN2_ERR_REG_VF2PF(vf_src) (((vf_src) & 0x01FFFE00) >> 9) #define ADF_GEN2_ERR_MSK_VF2PF(vf_mask) (((vf_mask) & 0xFFFF) << 9) @@ -50,23 +51,6 @@ static u32 adf_gen2_vf_get_pfvf_offset(u32 i) return ADF_GEN2_VF_PF2VF_OFFSET; } -static u32 adf_gen2_get_vf2pf_sources(void __iomem *pmisc_addr) -{ - u32 errsou3, errmsk3, vf_int_mask; - - /* Get the interrupt sources triggered by VFs */ - errsou3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU3); - vf_int_mask = ADF_GEN2_ERR_REG_VF2PF(errsou3); - - /* To avoid adding duplicate entries to work queue, clear - * vf_int_mask_sets bits that are already masked in ERRMSK register. - */ - errmsk3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3); - vf_int_mask &= ~ADF_GEN2_ERR_REG_VF2PF(errmsk3); - - return vf_int_mask; -} - static void adf_gen2_enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) { @@ -89,6 +73,44 @@ static void adf_gen2_disable_vf2pf_interrupts(void __iomem *pmisc_addr, } } +static u32 adf_gen2_disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) +{ + u32 sources, disabled, pending; + u32 errsou3, errmsk3; + + /* Get the interrupt sources triggered by VFs */ + errsou3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU3); + sources = ADF_GEN2_ERR_REG_VF2PF(errsou3); + + if (!sources) + return 0; + + /* Get the already disabled interrupts */ + errmsk3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3); + disabled = ADF_GEN2_ERR_REG_VF2PF(errmsk3); + + pending = sources & ~disabled; + if (!pending) + return 0; + + /* Due to HW limitations, when disabling the interrupts, we can't + * just disable the requested sources, as this would lead to missed + * interrupts if ERRSOU3 changes just before writing to ERRMSK3. + * To work around it, disable all and re-enable only the sources that + * are not in vf_mask and were not already disabled. Re-enabling will + * trigger a new interrupt for the sources that have changed in the + * meantime, if any. + */ + errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + + errmsk3 &= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + + /* Return the sources of the (new) interrupt(s) */ + return pending; +} + static u32 gen2_csr_get_int_bit(enum gen2_csr_pos offset) { return ADF_PFVF_INT << offset; @@ -362,9 +384,9 @@ void adf_gen2_init_pf_pfvf_ops(struct adf_pfvf_ops *pfvf_ops) pfvf_ops->enable_comms = adf_enable_pf2vf_comms; pfvf_ops->get_pf2vf_offset = adf_gen2_pf_get_pfvf_offset; pfvf_ops->get_vf2pf_offset = adf_gen2_pf_get_pfvf_offset; - pfvf_ops->get_vf2pf_sources = adf_gen2_get_vf2pf_sources; pfvf_ops->enable_vf2pf_interrupts = adf_gen2_enable_vf2pf_interrupts; pfvf_ops->disable_vf2pf_interrupts = adf_gen2_disable_vf2pf_interrupts; + pfvf_ops->disable_pending_vf2pf_interrupts = adf_gen2_disable_pending_vf2pf_interrupts; pfvf_ops->send_msg = adf_gen2_pf2vf_send; pfvf_ops->recv_msg = adf_gen2_vf2pf_recv; } diff --git a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c b/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c index d80d493a77568..40fdab857f959 100644 --- a/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c +++ b/drivers/crypto/qat/qat_common/adf_gen4_pfvf.c @@ -15,6 +15,7 @@ /* VF2PF interrupt source registers */ #define ADF_4XXX_VM2PF_SOU 0x41A180 #define ADF_4XXX_VM2PF_MSK 0x41A1C0 +#define ADF_GEN4_VF_MSK 0xFFFF #define ADF_PFVF_GEN4_MSGTYPE_SHIFT 2 #define ADF_PFVF_GEN4_MSGTYPE_MASK 0x3F @@ -36,16 +37,6 @@ static u32 adf_gen4_pf_get_vf2pf_offset(u32 i) return ADF_4XXX_VM2PF_OFFSET(i); } -static u32 adf_gen4_get_vf2pf_sources(void __iomem *pmisc_addr) -{ - u32 sou, mask; - - sou = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_SOU); - mask = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_MSK); - - return sou & ~mask; -} - static void adf_gen4_enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) { @@ -64,6 +55,37 @@ static void adf_gen4_disable_vf2pf_interrupts(void __iomem *pmisc_addr, ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, val); } +static u32 adf_gen4_disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) +{ + u32 sources, disabled, pending; + + /* Get the interrupt sources triggered by VFs */ + sources = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_SOU); + if (!sources) + return 0; + + /* Get the already disabled interrupts */ + disabled = ADF_CSR_RD(pmisc_addr, ADF_4XXX_VM2PF_MSK); + + pending = sources & ~disabled; + if (!pending) + return 0; + + /* Due to HW limitations, when disabling the interrupts, we can't + * just disable the requested sources, as this would lead to missed + * interrupts if VM2PF_SOU changes just before writing to VM2PF_MSK. + * To work around it, disable all and re-enable only the sources that + * are not in vf_mask and were not already disabled. Re-enabling will + * trigger a new interrupt for the sources that have changed in the + * meantime, if any. + */ + ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, ADF_GEN4_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_4XXX_VM2PF_MSK, disabled | sources); + + /* Return the sources of the (new) interrupt(s) */ + return pending; +} + static int adf_gen4_pfvf_send(struct adf_accel_dev *accel_dev, struct pfvf_message msg, u32 pfvf_offset, struct mutex *csr_lock) @@ -115,9 +137,9 @@ void adf_gen4_init_pf_pfvf_ops(struct adf_pfvf_ops *pfvf_ops) pfvf_ops->enable_comms = adf_enable_pf2vf_comms; pfvf_ops->get_pf2vf_offset = adf_gen4_pf_get_pf2vf_offset; pfvf_ops->get_vf2pf_offset = adf_gen4_pf_get_vf2pf_offset; - pfvf_ops->get_vf2pf_sources = adf_gen4_get_vf2pf_sources; pfvf_ops->enable_vf2pf_interrupts = adf_gen4_enable_vf2pf_interrupts; pfvf_ops->disable_vf2pf_interrupts = adf_gen4_disable_vf2pf_interrupts; + pfvf_ops->disable_pending_vf2pf_interrupts = adf_gen4_disable_pending_vf2pf_interrupts; pfvf_ops->send_msg = adf_gen4_pfvf_send; pfvf_ops->recv_msg = adf_gen4_pfvf_recv; } diff --git a/drivers/crypto/qat/qat_common/adf_isr.c b/drivers/crypto/qat/qat_common/adf_isr.c index a35149f8bf1ee..23f7fff32c642 100644 --- a/drivers/crypto/qat/qat_common/adf_isr.c +++ b/drivers/crypto/qat/qat_common/adf_isr.c @@ -76,32 +76,29 @@ void adf_disable_vf2pf_interrupts(struct adf_accel_dev *accel_dev, u32 vf_mask) spin_unlock_irqrestore(&accel_dev->pf.vf2pf_ints_lock, flags); } -static void adf_disable_vf2pf_interrupts_irq(struct adf_accel_dev *accel_dev, - u32 vf_mask) +static u32 adf_disable_pending_vf2pf_interrupts(struct adf_accel_dev *accel_dev) { void __iomem *pmisc_addr = adf_get_pmisc_base(accel_dev); + u32 pending; spin_lock(&accel_dev->pf.vf2pf_ints_lock); - GET_PFVF_OPS(accel_dev)->disable_vf2pf_interrupts(pmisc_addr, vf_mask); + pending = GET_PFVF_OPS(accel_dev)->disable_pending_vf2pf_interrupts(pmisc_addr); spin_unlock(&accel_dev->pf.vf2pf_ints_lock); + + return pending; } static bool adf_handle_vf2pf_int(struct adf_accel_dev *accel_dev) { - void __iomem *pmisc_addr = adf_get_pmisc_base(accel_dev); bool irq_handled = false; unsigned long vf_mask; - /* Get the interrupt sources triggered by VFs */ - vf_mask = GET_PFVF_OPS(accel_dev)->get_vf2pf_sources(pmisc_addr); - + /* Get the interrupt sources triggered by VFs, except for those already disabled */ + vf_mask = adf_disable_pending_vf2pf_interrupts(accel_dev); if (vf_mask) { struct adf_accel_vf_info *vf_info; int i; - /* Disable VF2PF interrupts for VFs with pending ints */ - adf_disable_vf2pf_interrupts_irq(accel_dev, vf_mask); - /* * Handle VF2PF interrupt unless the VF is malicious and * is attempting to flood the host OS with VF2PF interrupts. diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c index 09599fe4d2f3f..1e7bed8b011fe 100644 --- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c +++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c @@ -7,6 +7,8 @@ #include "adf_dh895xcc_hw_data.h" #include "icp_qat_hw.h" +#define ADF_DH895XCC_VF_MSK 0xFFFFFFFF + /* Worker thread to service arbiter mappings */ static const u32 thrd_to_arb_map[ADF_DH895XCC_MAX_ACCELENGINES] = { 0x12222AAA, 0x11666666, 0x12222AAA, 0x11666666, @@ -114,29 +116,6 @@ static void adf_enable_ints(struct adf_accel_dev *accel_dev) ADF_DH895XCC_SMIA1_MASK); } -static u32 get_vf2pf_sources(void __iomem *pmisc_bar) -{ - u32 errsou3, errmsk3, errsou5, errmsk5, vf_int_mask; - - /* Get the interrupt sources triggered by VFs */ - errsou3 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRSOU3); - vf_int_mask = ADF_DH895XCC_ERR_REG_VF2PF_L(errsou3); - - /* To avoid adding duplicate entries to work queue, clear - * vf_int_mask_sets bits that are already masked in ERRMSK register. - */ - errmsk3 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRMSK3); - vf_int_mask &= ~ADF_DH895XCC_ERR_REG_VF2PF_L(errmsk3); - - /* Do the same for ERRSOU5 */ - errsou5 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRSOU5); - errmsk5 = ADF_CSR_RD(pmisc_bar, ADF_GEN2_ERRMSK5); - vf_int_mask |= ADF_DH895XCC_ERR_REG_VF2PF_U(errsou5); - vf_int_mask &= ~ADF_DH895XCC_ERR_REG_VF2PF_U(errmsk5); - - return vf_int_mask; -} - static void enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) { /* Enable VF2PF Messaging Ints - VFs 0 through 15 per vf_mask[15:0] */ @@ -150,7 +129,6 @@ static void enable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) if (vf_mask >> 16) { u32 val = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK5) & ~ADF_DH895XCC_ERR_MSK_VF2PF_U(vf_mask); - ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, val); } } @@ -173,6 +151,54 @@ static void disable_vf2pf_interrupts(void __iomem *pmisc_addr, u32 vf_mask) } } +static u32 disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) +{ + u32 sources, pending, disabled; + u32 errsou3, errmsk3; + u32 errsou5, errmsk5; + + /* Get the interrupt sources triggered by VFs */ + errsou3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU3); + errsou5 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRSOU5); + sources = ADF_DH895XCC_ERR_REG_VF2PF_L(errsou3) + | ADF_DH895XCC_ERR_REG_VF2PF_U(errsou5); + + if (!sources) + return 0; + + /* Get the already disabled interrupts */ + errmsk3 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK3); + errmsk5 = ADF_CSR_RD(pmisc_addr, ADF_GEN2_ERRMSK5); + disabled = ADF_DH895XCC_ERR_REG_VF2PF_L(errmsk3) + | ADF_DH895XCC_ERR_REG_VF2PF_U(errmsk5); + + pending = sources & ~disabled; + if (!pending) + return 0; + + /* Due to HW limitations, when disabling the interrupts, we can't + * just disable the requested sources, as this would lead to missed + * interrupts if sources changes just before writing to ERRMSK3 and + * ERRMSK5. + * To work around it, disable all and re-enable only the sources that + * are not in vf_mask and were not already disabled. Re-enabling will + * trigger a new interrupt for the sources that have changed in the + * meantime, if any. + */ + errmsk3 |= ADF_DH895XCC_ERR_MSK_VF2PF_L(ADF_DH895XCC_VF_MSK); + errmsk5 |= ADF_DH895XCC_ERR_MSK_VF2PF_U(ADF_DH895XCC_VF_MSK); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); + + errmsk3 &= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled); + errmsk5 &= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); + ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); + + /* Return the sources of the (new) interrupt(s) */ + return pending; +} + static void configure_iov_threads(struct adf_accel_dev *accel_dev, bool enable) { adf_gen2_cfg_iov_thds(accel_dev, enable, @@ -220,9 +246,9 @@ void adf_init_hw_data_dh895xcc(struct adf_hw_device_data *hw_data) hw_data->disable_iov = adf_disable_sriov; adf_gen2_init_pf_pfvf_ops(&hw_data->pfvf_ops); - hw_data->pfvf_ops.get_vf2pf_sources = get_vf2pf_sources; hw_data->pfvf_ops.enable_vf2pf_interrupts = enable_vf2pf_interrupts; hw_data->pfvf_ops.disable_vf2pf_interrupts = disable_vf2pf_interrupts; + hw_data->pfvf_ops.disable_pending_vf2pf_interrupts = disable_pending_vf2pf_interrupts; adf_gen2_init_hw_csr_ops(&hw_data->csr_ops); } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 9333f732cda8e..5167d63010b99 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2859,7 +2859,7 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, } static void intel_read_wm_latency(struct drm_i915_private *dev_priv, - u16 wm[8]) + u16 wm[]) { struct intel_uncore *uncore = &dev_priv->uncore; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 053853a891c50..c297c63f3ec5c 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -768,6 +768,7 @@ #define USB_DEVICE_ID_LENOVO_X1_COVER 0x6085 #define USB_DEVICE_ID_LENOVO_X1_TAB 0x60a3 #define USB_DEVICE_ID_LENOVO_X1_TAB3 0x60b5 +#define USB_DEVICE_ID_LENOVO_X12_TAB 0x60fe #define USB_DEVICE_ID_LENOVO_OPTICAL_USB_MOUSE_600E 0x600e #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_608D 0x608d #define USB_DEVICE_ID_LENOVO_PIXART_USB_MOUSE_6019 0x6019 diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 99eabfb4145b5..6bb3890b0f2c9 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -2034,6 +2034,12 @@ static const struct hid_device_id mt_devices[] = { USB_VENDOR_ID_LENOVO, USB_DEVICE_ID_LENOVO_X1_TAB3) }, + /* Lenovo X12 TAB Gen 1 */ + { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_LENOVO, + USB_DEVICE_ID_LENOVO_X12_TAB) }, + /* MosArt panels */ { .driver_data = MT_CLS_CONFIDENCE_MINUS_ONE, MT_USB_DEVICE(USB_VENDOR_ID_ASUS, @@ -2178,6 +2184,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_GOOGLE, HID_DEVICE(HID_BUS_ANY, HID_GROUP_ANY, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_TOUCH_ROSE) }, + { .driver_data = MT_CLS_GOOGLE, + HID_DEVICE(BUS_USB, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_GOOGLE, + USB_DEVICE_ID_GOOGLE_WHISKERS) }, /* Generic MT device */ { HID_DEVICE(HID_BUS_ANY, HID_GROUP_MULTITOUCH, HID_ANY_ID, HID_ANY_ID) }, diff --git a/drivers/i2c/busses/i2c-ismt.c b/drivers/i2c/busses/i2c-ismt.c index c16157ee8c520..6078fa0c0d488 100644 --- a/drivers/i2c/busses/i2c-ismt.c +++ b/drivers/i2c/busses/i2c-ismt.c @@ -528,6 +528,9 @@ static int ismt_access(struct i2c_adapter *adap, u16 addr, case I2C_SMBUS_BLOCK_PROC_CALL: dev_dbg(dev, "I2C_SMBUS_BLOCK_PROC_CALL\n"); + if (data->block[0] > I2C_SMBUS_BLOCK_MAX) + return -EINVAL; + dma_size = I2C_SMBUS_BLOCK_MAX; desc->tgtaddr_rw = ISMT_DESC_ADDR_RW(addr, 1); desc->wr_len_cmd = data->block[0] + 1; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index fb80539865d7c..159c6806c19b8 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -3439,6 +3439,11 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } +static char hex2asc(unsigned char c) +{ + return c + '0' + ((unsigned)(9 - c) >> 4 & 0x27); +} + static void crypt_status(struct dm_target *ti, status_type_t type, unsigned status_flags, char *result, unsigned maxlen) { @@ -3457,9 +3462,12 @@ static void crypt_status(struct dm_target *ti, status_type_t type, if (cc->key_size > 0) { if (cc->key_string) DMEMIT(":%u:%s", cc->key_size, cc->key_string); - else - for (i = 0; i < cc->key_size; i++) - DMEMIT("%02x", cc->key[i]); + else { + for (i = 0; i < cc->key_size; i++) { + DMEMIT("%c%c", hex2asc(cc->key[i] >> 4), + hex2asc(cc->key[i] & 0xf)); + } + } } else DMEMIT("-"); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 36ae30b73a6e0..3d5a0ce123c90 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4494,8 +4494,6 @@ try_smaller_buffer: } if (should_write_sb) { - int r; - init_journal(ic, 0, ic->journal_sections, 0); r = dm_integrity_failed(ic); if (unlikely(r)) { diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c index 0e039a8c0bf2e..a3f2050b9c9b4 100644 --- a/drivers/md/dm-stats.c +++ b/drivers/md/dm-stats.c @@ -225,6 +225,7 @@ void dm_stats_cleanup(struct dm_stats *stats) atomic_read(&shared->in_flight[READ]), atomic_read(&shared->in_flight[WRITE])); } + cond_resched(); } dm_stat_free(&s->rcu_head); } @@ -330,6 +331,7 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end, for (ni = 0; ni < n_entries; ni++) { atomic_set(&s->stat_shared[ni].in_flight[READ], 0); atomic_set(&s->stat_shared[ni].in_flight[WRITE], 0); + cond_resched(); } if (s->n_histogram_entries) { @@ -342,6 +344,7 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end, for (ni = 0; ni < n_entries; ni++) { s->stat_shared[ni].tmp.histogram = hi; hi += s->n_histogram_entries + 1; + cond_resched(); } } @@ -362,6 +365,7 @@ static int dm_stats_create(struct dm_stats *stats, sector_t start, sector_t end, for (ni = 0; ni < n_entries; ni++) { p[ni].histogram = hi; hi += s->n_histogram_entries + 1; + cond_resched(); } } } @@ -497,6 +501,7 @@ static int dm_stats_list(struct dm_stats *stats, const char *program, } DMEMIT("\n"); } + cond_resched(); } mutex_unlock(&stats->mutex); @@ -774,6 +779,7 @@ static void __dm_stat_clear(struct dm_stat *s, size_t idx_start, size_t idx_end, local_irq_enable(); } } + cond_resched(); } } @@ -889,6 +895,8 @@ static int dm_stats_print(struct dm_stats *stats, int id, if (unlikely(sz + 1 >= maxlen)) goto buffer_overflow; + + cond_resched(); } if (clear) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 80133aae0db37..d6dbd47492a85 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -1312,6 +1312,7 @@ bad: static struct target_type verity_target = { .name = "verity", + .features = DM_TARGET_IMMUTABLE, .version = {1, 8, 0}, .module = THIS_MODULE, .ctr = verity_ctr, diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 351d341a1ffa4..d6ce5a09fd358 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -686,17 +686,17 @@ int raid5_calc_degraded(struct r5conf *conf) return degraded; } -static int has_failed(struct r5conf *conf) +static bool has_failed(struct r5conf *conf) { - int degraded; + int degraded = conf->mddev->degraded; - if (conf->mddev->reshape_position == MaxSector) - return conf->mddev->degraded > conf->max_degraded; + if (test_bit(MD_BROKEN, &conf->mddev->flags)) + return true; - degraded = raid5_calc_degraded(conf); - if (degraded > conf->max_degraded) - return 1; - return 0; + if (conf->mddev->reshape_position != MaxSector) + degraded = raid5_calc_degraded(conf); + + return degraded > conf->max_degraded; } struct stripe_head * @@ -2863,34 +2863,31 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev) unsigned long flags; pr_debug("raid456: error called\n"); + pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n", + mdname(mddev), bdevname(rdev->bdev, b)); + spin_lock_irqsave(&conf->device_lock, flags); + set_bit(Faulty, &rdev->flags); + clear_bit(In_sync, &rdev->flags); + mddev->degraded = raid5_calc_degraded(conf); - if (test_bit(In_sync, &rdev->flags) && - mddev->degraded == conf->max_degraded) { - /* - * Don't allow to achieve failed state - * Don't try to recover this device - */ + if (has_failed(conf)) { + set_bit(MD_BROKEN, &conf->mddev->flags); conf->recovery_disabled = mddev->recovery_disabled; - spin_unlock_irqrestore(&conf->device_lock, flags); - return; + + pr_crit("md/raid:%s: Cannot continue operation (%d/%d failed).\n", + mdname(mddev), mddev->degraded, conf->raid_disks); + } else { + pr_crit("md/raid:%s: Operation continuing on %d devices.\n", + mdname(mddev), conf->raid_disks - mddev->degraded); } - set_bit(Faulty, &rdev->flags); - clear_bit(In_sync, &rdev->flags); - mddev->degraded = raid5_calc_degraded(conf); spin_unlock_irqrestore(&conf->device_lock, flags); set_bit(MD_RECOVERY_INTR, &mddev->recovery); set_bit(Blocked, &rdev->flags); set_mask_bits(&mddev->sb_flags, 0, BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING)); - pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n" - "md/raid:%s: Operation continuing on %d devices.\n", - mdname(mddev), - bdevname(rdev->bdev, b), - mdname(mddev), - conf->raid_disks - mddev->degraded); r5c_update_on_rdev_error(mddev, rdev); } diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c index be3f6ea555597..84279a6808730 100644 --- a/drivers/media/i2c/imx412.c +++ b/drivers/media/i2c/imx412.c @@ -1011,7 +1011,7 @@ static int imx412_power_on(struct device *dev) struct imx412 *imx412 = to_imx412(sd); int ret; - gpiod_set_value_cansleep(imx412->reset_gpio, 1); + gpiod_set_value_cansleep(imx412->reset_gpio, 0); ret = clk_prepare_enable(imx412->inclk); if (ret) { @@ -1024,7 +1024,7 @@ static int imx412_power_on(struct device *dev) return 0; error_reset: - gpiod_set_value_cansleep(imx412->reset_gpio, 0); + gpiod_set_value_cansleep(imx412->reset_gpio, 1); return ret; } @@ -1040,10 +1040,10 @@ static int imx412_power_off(struct device *dev) struct v4l2_subdev *sd = dev_get_drvdata(dev); struct imx412 *imx412 = to_imx412(sd); - gpiod_set_value_cansleep(imx412->reset_gpio, 0); - clk_disable_unprepare(imx412->inclk); + gpiod_set_value_cansleep(imx412->reset_gpio, 1); + return 0; } diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index cea7b2e2ce969..53764f3c0c7e4 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -130,9 +130,10 @@ static bool ipa_endpoint_data_valid_one(struct ipa *ipa, u32 count, */ if (data->endpoint.config.aggregation) { limit += SZ_1K * aggr_byte_limit_max(ipa->version); - if (buffer_size > limit) { + if (buffer_size - NET_SKB_PAD > limit) { dev_err(dev, "RX buffer size too large for aggregated RX endpoint %u (%u > %u)\n", - data->endpoint_id, buffer_size, limit); + data->endpoint_id, + buffer_size - NET_SKB_PAD, limit); return false; } @@ -739,6 +740,7 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) if (endpoint->data->aggregation) { if (!endpoint->toward_ipa) { const struct ipa_endpoint_rx_data *rx_data; + u32 buffer_size; bool close_eof; u32 limit; @@ -746,7 +748,8 @@ static void ipa_endpoint_init_aggr(struct ipa_endpoint *endpoint) val |= u32_encode_bits(IPA_ENABLE_AGGR, AGGR_EN_FMASK); val |= u32_encode_bits(IPA_GENERIC, AGGR_TYPE_FMASK); - limit = ipa_aggr_size_kb(rx_data->buffer_size); + buffer_size = rx_data->buffer_size; + limit = ipa_aggr_size_kb(buffer_size - NET_SKB_PAD); val |= aggr_byte_limit_encoded(version, limit); limit = IPA_AGGR_TIME_LIMIT; diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c index 03f1423071749..9f42f25fab920 100644 --- a/fs/exfat/balloc.c +++ b/fs/exfat/balloc.c @@ -148,7 +148,9 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync) struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); - WARN_ON(clu < EXFAT_FIRST_CLUSTER); + if (!is_valid_cluster(sbi, clu)) + return -EINVAL; + ent_idx = CLUSTER_TO_BITMAP_ENT(clu); i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); @@ -166,7 +168,9 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync) struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_mount_options *opts = &sbi->options; - WARN_ON(clu < EXFAT_FIRST_CLUSTER); + if (!is_valid_cluster(sbi, clu)) + return; + ent_idx = CLUSTER_TO_BITMAP_ENT(clu); i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx); b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index c6800b8809203..42d06c68d5c5e 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -381,6 +381,12 @@ static inline int exfat_sector_to_cluster(struct exfat_sb_info *sbi, EXFAT_RESERVED_CLUSTERS; } +static inline bool is_valid_cluster(struct exfat_sb_info *sbi, + unsigned int clus) +{ + return clus >= EXFAT_FIRST_CLUSTER && clus < sbi->num_clusters; +} + /* super.c */ int exfat_set_volume_dirty(struct super_block *sb); int exfat_clear_volume_dirty(struct super_block *sb); diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c index a3464e56a7e16..421c273531049 100644 --- a/fs/exfat/fatent.c +++ b/fs/exfat/fatent.c @@ -81,12 +81,6 @@ int exfat_ent_set(struct super_block *sb, unsigned int loc, return 0; } -static inline bool is_valid_cluster(struct exfat_sb_info *sbi, - unsigned int clus) -{ - return clus >= EXFAT_FIRST_CLUSTER && clus < sbi->num_clusters; -} - int exfat_ent_get(struct super_block *sb, unsigned int loc, unsigned int *content) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 7eefa16ed381b..8f8cd6e2d4dbc 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -841,6 +841,7 @@ static inline bool nfs_error_is_fatal_on_server(int err) case 0: case -ERESTARTSYS: case -EINTR: + case -ENOMEM: return false; } return nfs_error_is_fatal(err); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 234e852fcdfad..d6e1f95ccfd8a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7330,16 +7330,12 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, if (sop->so_is_open_owner || !same_owner_str(sop, owner)) continue; - /* see if there are still any locks associated with it */ - lo = lockowner(sop); - list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) { - if (check_for_locks(stp->st_stid.sc_file, lo)) { - status = nfserr_locks_held; - spin_unlock(&clp->cl_lock); - return status; - } + if (atomic_read(&sop->so_count) != 1) { + spin_unlock(&clp->cl_lock); + return nfserr_locks_held; } + lo = lockowner(sop); nfs4_get_stateowner(sop); break; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 278dcf5024102..b2b54c4553f91 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -668,9 +668,11 @@ static u32 format_size_gb(const u64 bytes, u32 *mb) static u32 true_sectors_per_clst(const struct NTFS_BOOT *boot) { - return boot->sectors_per_clusters <= 0x80 - ? boot->sectors_per_clusters - : (1u << (0 - boot->sectors_per_clusters)); + if (boot->sectors_per_clusters <= 0x80) + return boot->sectors_per_clusters; + if (boot->sectors_per_clusters >= 0xf4) /* limit shift to 2MB max */ + return 1U << (0 - boot->sectors_per_clusters); + return -EINVAL; } /* @@ -713,6 +715,8 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, /* cluster size: 512, 1K, 2K, 4K, ... 2M */ sct_per_clst = true_sectors_per_clst(boot); + if ((int)sct_per_clst < 0) + goto out; if (!is_power_of_2(sct_per_clst)) goto out; diff --git a/fs/pipe.c b/fs/pipe.c index e140ea150bbb1..74ae9fafd25a1 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -653,7 +653,7 @@ pipe_poll(struct file *filp, poll_table *wait) unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ - pipe->poll_usage = 1; + WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. @@ -1245,30 +1245,33 @@ unsigned int round_pipe_size(unsigned long size) /* * Resize the pipe ring to a number of slots. + * + * Note the pipe can be reduced in capacity, but only if the current + * occupancy doesn't exceed nr_slots; if it does, EBUSY will be + * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; - /* - * We can shrink the pipe, if arg is greater than the ring occupancy. - * Since we don't expect a lot of shrink+grow operations, just free and - * allocate again like we would do for growing. If the pipe currently - * contains more buffers than arg, then return busy. - */ - mask = pipe->ring_size - 1; - head = pipe->head; - tail = pipe->tail; - n = pipe_occupancy(pipe->head, pipe->tail); - if (nr_slots < n) - return -EBUSY; - bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; + spin_lock_irq(&pipe->rd_wait.lock); + mask = pipe->ring_size - 1; + head = pipe->head; + tail = pipe->tail; + + n = pipe_occupancy(head, tail); + if (nr_slots < n) { + spin_unlock_irq(&pipe->rd_wait.lock); + kfree(bufs); + return -EBUSY; + } + /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. @@ -1300,6 +1303,8 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) pipe->tail = tail; pipe->head = head; + spin_unlock_irq(&pipe->rd_wait.lock); + /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 493e632584970..7ea18d4da84b8 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -143,9 +143,9 @@ void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_omem); + bool uncharge_omem, bool use_trace_rcu); -void bpf_selem_unlink(struct bpf_local_storage_elem *selem); +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu); void bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index c00c618ef290d..cb0fd633a6106 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -71,7 +71,7 @@ struct pipe_inode_info { unsigned int files; unsigned int r_counter; unsigned int w_counter; - unsigned int poll_usage; + bool poll_usage; struct page *tmp_page; struct fasync_struct *fasync_readers; struct fasync_struct *fasync_writers; diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index 13807ea94cd2b..2d524782f53b7 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -58,8 +58,13 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb) int ret = NF_ACCEPT; if (ct) { - if (!nf_ct_is_confirmed(ct)) + if (!nf_ct_is_confirmed(ct)) { ret = __nf_conntrack_confirm(skb); + + if (ret == NF_ACCEPT) + ct = (struct nf_conn *)skb_nfct(skb); + } + if (likely(ret == NF_ACCEPT)) nf_ct_deliver_cached_events(ct); } diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 96be8d518885c..10424a1cda51d 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -90,7 +90,7 @@ void bpf_inode_storage_free(struct inode *inode) */ bpf_selem_unlink_map(selem); free_inode_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false); + local_storage, selem, false, false); } raw_spin_unlock_bh(&local_storage->lock); rcu_read_unlock(); @@ -149,7 +149,7 @@ static int inode_storage_delete(struct inode *inode, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata), true); return 0; } diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 01aa2b51ec4df..8ce40fd869f6a 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -106,7 +106,7 @@ static void bpf_selem_free_rcu(struct rcu_head *rcu) */ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, - bool uncharge_mem) + bool uncharge_mem, bool use_trace_rcu) { struct bpf_local_storage_map *smap; bool free_local_storage; @@ -150,11 +150,16 @@ bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); - call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); + if (use_trace_rcu) + call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_rcu); + else + kfree_rcu(selem, rcu); + return free_local_storage; } -static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) +static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem, + bool use_trace_rcu) { struct bpf_local_storage *local_storage; bool free_local_storage = false; @@ -169,12 +174,16 @@ static void __bpf_selem_unlink_storage(struct bpf_local_storage_elem *selem) raw_spin_lock_irqsave(&local_storage->lock, flags); if (likely(selem_linked_to_storage(selem))) free_local_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, true); + local_storage, selem, true, use_trace_rcu); raw_spin_unlock_irqrestore(&local_storage->lock, flags); - if (free_local_storage) - call_rcu_tasks_trace(&local_storage->rcu, + if (free_local_storage) { + if (use_trace_rcu) + call_rcu_tasks_trace(&local_storage->rcu, bpf_local_storage_free_rcu); + else + kfree_rcu(local_storage, rcu); + } } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, @@ -214,14 +223,14 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap, raw_spin_unlock_irqrestore(&b->lock, flags); } -void bpf_selem_unlink(struct bpf_local_storage_elem *selem) +void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool use_trace_rcu) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ bpf_selem_unlink_map(selem); - __bpf_selem_unlink_storage(selem); + __bpf_selem_unlink_storage(selem, use_trace_rcu); } struct bpf_local_storage_data * @@ -466,7 +475,7 @@ bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, if (old_sdata) { bpf_selem_unlink_map(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), - false); + false, true); } unlock: @@ -548,7 +557,7 @@ void bpf_local_storage_map_free(struct bpf_local_storage_map *smap, migrate_disable(); __this_cpu_inc(*busy_counter); } - bpf_selem_unlink(selem); + bpf_selem_unlink(selem, false); if (busy_counter) { __this_cpu_dec(*busy_counter); migrate_enable(); diff --git a/kernel/bpf/bpf_task_storage.c b/kernel/bpf/bpf_task_storage.c index 6638a0ecc3d21..57904263a710f 100644 --- a/kernel/bpf/bpf_task_storage.c +++ b/kernel/bpf/bpf_task_storage.c @@ -102,7 +102,7 @@ void bpf_task_storage_free(struct task_struct *task) */ bpf_selem_unlink_map(selem); free_task_storage = bpf_selem_unlink_storage_nolock( - local_storage, selem, false); + local_storage, selem, false, false); } raw_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_task_storage_unlock(); @@ -192,7 +192,7 @@ static int task_storage_delete(struct task_struct *task, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata), true); return 0; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 13e9dbeeedf36..05e701f0da81d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -873,7 +873,7 @@ static size_t select_bpf_prog_pack_size(void) return size; } -static struct bpf_prog_pack *alloc_new_pack(void) +static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_insns) { struct bpf_prog_pack *pack; @@ -886,6 +886,7 @@ static struct bpf_prog_pack *alloc_new_pack(void) kfree(pack); return NULL; } + bpf_fill_ill_insns(pack->ptr, bpf_prog_pack_size); bitmap_zero(pack->bitmap, bpf_prog_pack_size / BPF_PROG_CHUNK_SIZE); list_add_tail(&pack->list, &pack_list); @@ -895,7 +896,7 @@ static struct bpf_prog_pack *alloc_new_pack(void) return pack; } -static void *bpf_prog_pack_alloc(u32 size) +static void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns) { unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size); struct bpf_prog_pack *pack; @@ -910,6 +911,7 @@ static void *bpf_prog_pack_alloc(u32 size) size = round_up(size, PAGE_SIZE); ptr = module_alloc(size); if (ptr) { + bpf_fill_ill_insns(ptr, size); set_vm_flush_reset_perms(ptr); set_memory_ro((unsigned long)ptr, size / PAGE_SIZE); set_memory_x((unsigned long)ptr, size / PAGE_SIZE); @@ -923,7 +925,7 @@ static void *bpf_prog_pack_alloc(u32 size) goto found_free_area; } - pack = alloc_new_pack(); + pack = alloc_new_pack(bpf_fill_ill_insns); if (!pack) goto out; @@ -1102,7 +1104,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr, if (bpf_jit_charge_modmem(size)) return NULL; - ro_header = bpf_prog_pack_alloc(size); + ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns); if (!ro_header) { bpf_jit_uncharge_modmem(size); return NULL; @@ -1434,6 +1436,16 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog) insn = clone->insnsi; for (i = 0; i < insn_cnt; i++, insn++) { + if (bpf_pseudo_func(insn)) { + /* ld_imm64 with an address of bpf subprog is not + * a user controlled constant. Don't randomize it, + * since it will conflict with jit_subprogs() logic. + */ + insn++; + i++; + continue; + } + /* We temporarily need to hold the original ld64 insn * so that we can still access the first part in the * second blinding run. diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 34725bfa1e97b..5c6c96d0e634d 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -100,7 +100,6 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) return ERR_PTR(-E2BIG); cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); - cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) return ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index ada97751ae1b2..5d8bfb5ef239d 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -411,7 +411,7 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) { enum bpf_tramp_prog_type kind; int err = 0; - int cnt; + int cnt = 0, i; kind = bpf_attach_type_to_tramp(prog); mutex_lock(&tr->mutex); @@ -422,7 +422,10 @@ int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) err = -EBUSY; goto out; } - cnt = tr->progs_cnt[BPF_TRAMP_FENTRY] + tr->progs_cnt[BPF_TRAMP_FEXIT]; + + for (i = 0; i < BPF_TRAMP_MAX; i++) + cnt += tr->progs_cnt[i]; + if (kind == BPF_TRAMP_REPLACE) { /* Cannot attach extension if fentry/fexit are in use. */ if (cnt) { @@ -500,16 +503,19 @@ out: void bpf_trampoline_put(struct bpf_trampoline *tr) { + int i; + if (!tr) return; mutex_lock(&trampoline_mutex); if (!refcount_dec_and_test(&tr->refcnt)) goto out; WARN_ON_ONCE(mutex_is_locked(&tr->mutex)); - if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FENTRY]))) - goto out; - if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) - goto out; + + for (i = 0; i < BPF_TRAMP_MAX; i++) + if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[i]))) + goto out; + /* This code will be executed even when the last bpf_tramp_image * is alive. All progs are detached from the trampoline and the * trampoline image is patched with jmp into epilogue to skip diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d175b70067b30..9c1a02b82ecd0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4861,6 +4861,11 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_packet_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MAP_KEY: + if (meta && meta->raw_mode) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } return check_mem_region_access(env, regno, reg->off, access_size, reg->map_ptr->key_size, false); case PTR_TO_MAP_VALUE: @@ -4871,13 +4876,23 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, return check_map_access(env, regno, reg->off, access_size, zero_size_allowed); case PTR_TO_MEM: + if (type_is_rdonly_mem(reg->type)) { + if (meta && meta->raw_mode) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); + return -EACCES; + } + } return check_mem_region_access(env, regno, reg->off, access_size, reg->mem_size, zero_size_allowed); case PTR_TO_BUF: if (type_is_rdonly_mem(reg->type)) { - if (meta && meta->raw_mode) + if (meta && meta->raw_mode) { + verbose(env, "R%d cannot write into %s\n", regno, + reg_type_str(env, reg->type)); return -EACCES; + } max_access = &env->prog->aux->max_rdonly_access; } else { @@ -4919,8 +4934,7 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, * out. Only upper bounds can be learned because retval is an * int type and negative retvals are allowed. */ - if (meta) - meta->msize_max_value = reg->umax_value; + meta->msize_max_value = reg->umax_value; /* The register is SCALAR_VALUE; the access check * happens using its boundaries. @@ -4963,24 +4977,33 @@ static int check_mem_size_reg(struct bpf_verifier_env *env, int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, u32 regno, u32 mem_size) { + bool may_be_null = type_may_be_null(reg->type); + struct bpf_reg_state saved_reg; + struct bpf_call_arg_meta meta; + int err; + if (register_is_null(reg)) return 0; - if (type_may_be_null(reg->type)) { - /* Assuming that the register contains a value check if the memory - * access is safe. Temporarily save and restore the register's state as - * the conversion shouldn't be visible to a caller. - */ - const struct bpf_reg_state saved_reg = *reg; - int rv; - + memset(&meta, 0, sizeof(meta)); + /* Assuming that the register contains a value check if the memory + * access is safe. Temporarily save and restore the register's state as + * the conversion shouldn't be visible to a caller. + */ + if (may_be_null) { + saved_reg = *reg; mark_ptr_not_null_reg(reg); - rv = check_helper_mem_access(env, regno, mem_size, true, NULL); - *reg = saved_reg; - return rv; } - return check_helper_mem_access(env, regno, mem_size, true, NULL); + err = check_helper_mem_access(env, regno, mem_size, true, &meta); + /* Check access for BPF_WRITE */ + meta.raw_mode = true; + err = err ?: check_helper_mem_access(env, regno, mem_size, true, &meta); + + if (may_be_null) + *reg = saved_reg; + + return err; } int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg, @@ -4989,16 +5012,22 @@ int check_kfunc_mem_size_reg(struct bpf_verifier_env *env, struct bpf_reg_state struct bpf_reg_state *mem_reg = &cur_regs(env)[regno - 1]; bool may_be_null = type_may_be_null(mem_reg->type); struct bpf_reg_state saved_reg; + struct bpf_call_arg_meta meta; int err; WARN_ON_ONCE(regno < BPF_REG_2 || regno > BPF_REG_5); + memset(&meta, 0, sizeof(meta)); + if (may_be_null) { saved_reg = *mem_reg; mark_ptr_not_null_reg(mem_reg); } - err = check_mem_size_reg(env, reg, regno, true, NULL); + err = check_mem_size_reg(env, reg, regno, true, &meta); + /* Check access for BPF_WRITE */ + meta.raw_mode = true; + err = err ?: check_mem_size_reg(env, reg, regno, true, &meta); if (may_be_null) *mem_reg = saved_reg; diff --git a/lib/assoc_array.c b/lib/assoc_array.c index 079c72e26493e..ca0b4f360c1a0 100644 --- a/lib/assoc_array.c +++ b/lib/assoc_array.c @@ -1461,6 +1461,7 @@ int assoc_array_gc(struct assoc_array *array, struct assoc_array_ptr *cursor, *ptr; struct assoc_array_ptr *new_root, *new_parent, **new_ptr_pp; unsigned long nr_leaves_on_tree; + bool retained; int keylen, slot, nr_free, next_slot, i; pr_devel("-->%s()\n", __func__); @@ -1536,6 +1537,7 @@ continue_node: goto descend; } +retry_compress: pr_devel("-- compress node %p --\n", new_n); /* Count up the number of empty slots in this node and work out the @@ -1553,6 +1555,7 @@ continue_node: pr_devel("free=%d, leaves=%lu\n", nr_free, new_n->nr_leaves_on_branch); /* See what we can fold in */ + retained = false; next_slot = 0; for (slot = 0; slot < ASSOC_ARRAY_FAN_OUT; slot++) { struct assoc_array_shortcut *s; @@ -1602,9 +1605,14 @@ continue_node: pr_devel("[%d] retain node %lu/%d [nx %d]\n", slot, child->nr_leaves_on_branch, nr_free + 1, next_slot); + retained = true; } } + if (retained && new_n->nr_leaves_on_branch <= ASSOC_ARRAY_FAN_OUT) { + pr_devel("internal nodes remain despite enough space, retrying\n"); + goto retry_compress; + } pr_devel("after: %lu\n", new_n->nr_leaves_on_branch); nr_leaves_on_tree = new_n->nr_leaves_on_branch; diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9152fbde33b50..5d5fc04385b8d 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1718,11 +1718,40 @@ static enum fullness_group putback_zspage(struct size_class *class, */ static void lock_zspage(struct zspage *zspage) { - struct page *page = get_first_page(zspage); + struct page *curr_page, *page; - do { - lock_page(page); - } while ((page = get_next_page(page)) != NULL); + /* + * Pages we haven't locked yet can be migrated off the list while we're + * trying to lock them, so we need to be careful and only attempt to + * lock each page under migrate_read_lock(). Otherwise, the page we lock + * may no longer belong to the zspage. This means that we may wait for + * the wrong page to unlock, so we must take a reference to the page + * prior to waiting for it to unlock outside migrate_read_lock(). + */ + while (1) { + migrate_read_lock(zspage); + page = get_first_page(zspage); + if (trylock_page(page)) + break; + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + } + + curr_page = page; + while ((page = get_next_page(curr_page))) { + if (trylock_page(page)) { + curr_page = page; + } else { + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + migrate_read_lock(zspage); + } + } + migrate_read_unlock(zspage); } static int zs_init_fs_context(struct fs_context *fc) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index e3ac363805203..83d7641ef67b0 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -40,7 +40,7 @@ static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) if (!sdata) return -ENOENT; - bpf_selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata), true); return 0; } @@ -75,8 +75,8 @@ void bpf_sk_storage_free(struct sock *sk) * sk_storage. */ bpf_selem_unlink_map(selem); - free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage, - selem, true); + free_sk_storage = bpf_selem_unlink_storage_nolock( + sk_storage, selem, true, false); } raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); diff --git a/net/core/filter.c b/net/core/filter.c index 64470a727ef77..966796b345e78 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1687,7 +1687,7 @@ BPF_CALL_5(bpf_skb_store_bytes, struct sk_buff *, skb, u32, offset, if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; - if (unlikely(offset > 0xffff)) + if (unlikely(offset > INT_MAX)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; @@ -1722,7 +1722,7 @@ BPF_CALL_4(bpf_skb_load_bytes, const struct sk_buff *, skb, u32, offset, { void *ptr; - if (unlikely(offset > 0xffff)) + if (unlikely(offset > INT_MAX)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a096b9fbbbdff..b6a9208130051 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -222,12 +222,18 @@ err_register: } static void nft_netdev_unregister_hooks(struct net *net, - struct list_head *hook_list) + struct list_head *hook_list, + bool release_netdev) { - struct nft_hook *hook; + struct nft_hook *hook, *next; - list_for_each_entry(hook, hook_list, list) + list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); + if (release_netdev) { + list_del(&hook->list); + kfree_rcu(hook, rcu); + } + } } static int nf_tables_register_hook(struct net *net, @@ -253,9 +259,10 @@ static int nf_tables_register_hook(struct net *net, return nf_register_net_hook(net, &basechain->ops); } -static void nf_tables_unregister_hook(struct net *net, - const struct nft_table *table, - struct nft_chain *chain) +static void __nf_tables_unregister_hook(struct net *net, + const struct nft_table *table, + struct nft_chain *chain, + bool release_netdev) { struct nft_base_chain *basechain; const struct nf_hook_ops *ops; @@ -270,11 +277,19 @@ static void nf_tables_unregister_hook(struct net *net, return basechain->type->ops_unregister(net, ops); if (nft_base_chain_netdev(table->family, basechain->ops.hooknum)) - nft_netdev_unregister_hooks(net, &basechain->hook_list); + nft_netdev_unregister_hooks(net, &basechain->hook_list, + release_netdev); else nf_unregister_net_hook(net, &basechain->ops); } +static void nf_tables_unregister_hook(struct net *net, + const struct nft_table *table, + struct nft_chain *chain) +{ + return __nf_tables_unregister_hook(net, table, chain, false); +} + static void nft_trans_commit_list_add_tail(struct net *net, struct nft_trans *trans) { struct nftables_pernet *nft_net = nft_pernet(net); @@ -2873,27 +2888,31 @@ static struct nft_expr *nft_expr_init(const struct nft_ctx *ctx, err = nf_tables_expr_parse(ctx, nla, &expr_info); if (err < 0) - goto err1; + goto err_expr_parse; + + err = -EOPNOTSUPP; + if (!(expr_info.ops->type->flags & NFT_EXPR_STATEFUL)) + goto err_expr_stateful; err = -ENOMEM; expr = kzalloc(expr_info.ops->size, GFP_KERNEL_ACCOUNT); if (expr == NULL) - goto err2; + goto err_expr_stateful; err = nf_tables_newexpr(ctx, &expr_info, expr); if (err < 0) - goto err3; + goto err_expr_new; return expr; -err3: +err_expr_new: kfree(expr); -err2: +err_expr_stateful: owner = expr_info.ops->type->owner; if (expr_info.ops->type->release_ops) expr_info.ops->type->release_ops(expr_info.ops); module_put(owner); -err1: +err_expr_parse: return ERR_PTR(err); } @@ -4242,6 +4261,9 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, u32 len; int err; + if (desc->field_count >= ARRAY_SIZE(desc->field_len)) + return -E2BIG; + err = nla_parse_nested_deprecated(tb, NFTA_SET_FIELD_MAX, attr, nft_concat_policy, NULL); if (err < 0) @@ -4251,9 +4273,8 @@ static int nft_set_desc_concat_parse(const struct nlattr *attr, return -EINVAL; len = ntohl(nla_get_be32(tb[NFTA_SET_FIELD_LEN])); - - if (len * BITS_PER_BYTE / 32 > NFT_REG32_COUNT) - return -E2BIG; + if (!len || len > U8_MAX) + return -EINVAL; desc->field_len[desc->field_count++] = len; @@ -4264,7 +4285,8 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, const struct nlattr *nla) { struct nlattr *attr; - int rem, err; + u32 num_regs = 0; + int rem, err, i; nla_for_each_nested(attr, nla, rem) { if (nla_type(attr) != NFTA_LIST_ELEM) @@ -4275,6 +4297,12 @@ static int nft_set_desc_concat(struct nft_set_desc *desc, return err; } + for (i = 0; i < desc->field_count; i++) + num_regs += DIV_ROUND_UP(desc->field_len[i], sizeof(u32)); + + if (num_regs > NFT_REG32_COUNT) + return -E2BIG; + return 0; } @@ -5413,9 +5441,6 @@ struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, return expr; err = -EOPNOTSUPP; - if (!(expr->ops->type->flags & NFT_EXPR_STATEFUL)) - goto err_set_elem_expr; - if (expr->ops->type->flags & NFT_EXPR_GC) { if (set->flags & NFT_SET_TIMEOUT) goto err_set_elem_expr; @@ -7291,13 +7316,25 @@ static void nft_unregister_flowtable_hook(struct net *net, FLOW_BLOCK_UNBIND); } -static void nft_unregister_flowtable_net_hooks(struct net *net, - struct list_head *hook_list) +static void __nft_unregister_flowtable_net_hooks(struct net *net, + struct list_head *hook_list, + bool release_netdev) { - struct nft_hook *hook; + struct nft_hook *hook, *next; - list_for_each_entry(hook, hook_list, list) + list_for_each_entry_safe(hook, next, hook_list, list) { nf_unregister_net_hook(net, &hook->ops); + if (release_netdev) { + list_del(&hook->list); + kfree_rcu(hook); + } + } +} + +static void nft_unregister_flowtable_net_hooks(struct net *net, + struct list_head *hook_list) +{ + __nft_unregister_flowtable_net_hooks(net, hook_list, false); } static int nft_register_flowtable_net_hooks(struct net *net, @@ -9741,9 +9778,10 @@ static void __nft_release_hook(struct net *net, struct nft_table *table) struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) - nf_tables_unregister_hook(net, table, chain); + __nf_tables_unregister_hook(net, table, chain, true); list_for_each_entry(flowtable, &table->flowtables, list) - nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list); + __nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list, + true); } static void __nft_release_hooks(struct net *net) @@ -9882,7 +9920,11 @@ static int __net_init nf_tables_init_net(struct net *net) static void __net_exit nf_tables_pre_exit_net(struct net *net) { + struct nftables_pernet *nft_net = nft_pernet(net); + + mutex_lock(&nft_net->commit_mutex); __nft_release_hooks(net); + mutex_unlock(&nft_net->commit_mutex); } static void __net_exit nf_tables_exit_net(struct net *net) diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 04ea8b9bf2028..981addb2d0515 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -213,6 +213,8 @@ static int nft_limit_pkts_clone(struct nft_expr *dst, const struct nft_expr *src struct nft_limit_priv_pkts *priv_dst = nft_expr_priv(dst); struct nft_limit_priv_pkts *priv_src = nft_expr_priv(src); + priv_dst->cost = priv_src->cost; + return nft_limit_clone(&priv_dst->limit, &priv_src->limit); } diff --git a/sound/usb/clock.c b/sound/usb/clock.c index 4dfe76416794f..33db334e65566 100644 --- a/sound/usb/clock.c +++ b/sound/usb/clock.c @@ -572,6 +572,17 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, /* continue processing */ } + /* FIXME - TEAC devices require the immediate interface setup */ + if (USB_ID_VENDOR(chip->usb_id) == 0x0644) { + bool cur_base_48k = (rate % 48000 == 0); + bool prev_base_48k = (prev_rate % 48000 == 0); + if (cur_base_48k != prev_base_48k) { + usb_set_interface(chip->dev, fmt->iface, fmt->altsetting); + if (chip->quirk_flags & QUIRK_FLAG_IFACE_DELAY) + msleep(50); + } + } + validation: /* validate clock after rate change */ if (!uac_clock_source_is_valid(chip, fmt, clock)) diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 6d699065e81a2..b470404a5376c 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -439,16 +439,21 @@ static int configure_endpoints(struct snd_usb_audio *chip, /* stop any running stream beforehand */ if (stop_endpoints(subs, false)) sync_pending_stops(subs); + if (subs->sync_endpoint) { + err = snd_usb_endpoint_configure(chip, subs->sync_endpoint); + if (err < 0) + return err; + } err = snd_usb_endpoint_configure(chip, subs->data_endpoint); if (err < 0) return err; snd_usb_set_format_quirk(subs, subs->cur_audiofmt); - } - - if (subs->sync_endpoint) { - err = snd_usb_endpoint_configure(chip, subs->sync_endpoint); - if (err < 0) - return err; + } else { + if (subs->sync_endpoint) { + err = snd_usb_endpoint_configure(chip, subs->sync_endpoint); + if (err < 0) + return err; + } } return 0; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index 40a5e3eb4ef26..78eb41b621d63 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -2672,6 +2672,7 @@ YAMAHA_DEVICE(0x7010, "UB99"), .altset_idx = 1, .attributes = 0, .endpoint = 0x82, + .ep_idx = 1, .ep_attr = USB_ENDPOINT_XFER_ISOC, .datainterval = 1, .maxpacksize = 0x0126, @@ -2875,6 +2876,7 @@ YAMAHA_DEVICE(0x7010, "UB99"), .altset_idx = 1, .attributes = 0x4, .endpoint = 0x81, + .ep_idx = 1, .ep_attr = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC, .maxpacksize = 0x130, @@ -3391,6 +3393,7 @@ YAMAHA_DEVICE(0x7010, "UB99"), .altset_idx = 1, .attributes = 0, .endpoint = 0x03, + .ep_idx = 1, .rates = SNDRV_PCM_RATE_96000, .ep_attr = USB_ENDPOINT_XFER_ISOC | USB_ENDPOINT_SYNC_ASYNC, diff --git a/tools/memory-model/README b/tools/memory-model/README index 9edd402704c4f..dab38904206a0 100644 --- a/tools/memory-model/README +++ b/tools/memory-model/README @@ -54,7 +54,8 @@ klitmus7 Compatibility Table -- 4.14 7.48 -- 4.15 -- 4.19 7.49 -- 4.20 -- 5.5 7.54 -- - 5.6 -- 7.56 -- + 5.6 -- 5.16 7.56 -- + 5.17 -- 7.56.1 -- ============ ==========