diff options
author | Vignesh Raghavendra <vigneshr@ti.com> | 2023-02-16 15:41:14 +0530 |
---|---|---|
committer | Vignesh Raghavendra <vigneshr@ti.com> | 2023-02-16 15:41:14 +0530 |
commit | 8ffeeca907557f941a0dd873f3ad7a63d130b6fa (patch) | |
tree | f1629bee72e4adb24d64464dfbe911818023edfc /kernel | |
parent | 76b3e88d569210a51399e8d8c8babd995af29d11 (diff) | |
parent | 179624a57b78c02de833370b7bdf0b0f4a27ca31 (diff) |
Merge tag 'v5.10.165' of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux into ti-linux-5.10.y-cicd
This is the 5.10.165 stable release
* tag 'v5.10.165' of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux: (951 commits)
Linux 5.10.165
io_uring/rw: remove leftover debug statement
io_uring/rw: ensure kiocb_end_write() is always called
io_uring: fix double poll leak on repolling
io_uring: Clean up a false-positive warning from GCC 9.3.0
mm/khugepaged: fix collapse_pte_mapped_thp() to allow anon_vma
Bluetooth: hci_qca: Fixed issue during suspend
Bluetooth: hci_qca: check for SSR triggered flag while suspend
Bluetooth: hci_qca: Wait for SSR completion during suspend
soc: qcom: apr: Make qcom,protection-domain optional again
Revert "wifi: mac80211: fix memory leak in ieee80211_if_add()"
net/mlx5: fix missing mutex_unlock in mlx5_fw_fatal_reporter_err_work()
net/ulp: use consistent error code when blocking ULP
io_uring/net: fix fast_iov assignment in io_setup_async_msg()
io_uring: io_kiocb_update_pos() should not touch file for non -1 offset
tracing: Use alignof__(struct {type b;}) instead of offsetof()
x86/fpu: Use _Alignof to avoid undefined behavior in TYPE_ALIGN
Revert "drm/amdgpu: make display pinning more flexible (v2)"
efi: rt-wrapper: Add missing include
arm64: efi: Execute runtime services from a dedicated stack
...
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
# Conflicts:
# net/hsr/hsr_device.c
# net/hsr/hsr_forward.c
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 2 | ||||
-rw-r--r-- | kernel/acct.c | 2 | ||||
-rw-r--r-- | kernel/bpf/btf.c | 5 | ||||
-rw-r--r-- | kernel/bpf/verifier.c | 123 | ||||
-rw-r--r-- | kernel/cpu.c | 4 | ||||
-rw-r--r-- | kernel/events/core.c | 14 | ||||
-rw-r--r-- | kernel/futex/Makefile | 3 | ||||
-rw-r--r-- | kernel/futex/core.c (renamed from kernel/futex.c) | 30 | ||||
-rw-r--r-- | kernel/gcov/gcc_4_7.c | 5 | ||||
-rw-r--r-- | kernel/irq/internals.h | 2 | ||||
-rw-r--r-- | kernel/irq/irqdesc.c | 15 | ||||
-rw-r--r-- | kernel/irq/manage.c | 11 | ||||
-rw-r--r-- | kernel/kcsan/core.c | 50 | ||||
-rw-r--r-- | kernel/padata.c | 15 | ||||
-rw-r--r-- | kernel/power/snapshot.c | 4 | ||||
-rw-r--r-- | kernel/rcu/tree.c | 23 | ||||
-rw-r--r-- | kernel/rcu/tree.h | 1 | ||||
-rw-r--r-- | kernel/relay.c | 4 | ||||
-rw-r--r-- | kernel/sched/fair.c | 128 | ||||
-rw-r--r-- | kernel/sys.c | 2 | ||||
-rw-r--r-- | kernel/trace/blktrace.c | 3 | ||||
-rw-r--r-- | kernel/trace/trace.c | 15 | ||||
-rw-r--r-- | kernel/trace/trace_events_hist.c | 13 |
23 files changed, 379 insertions, 95 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index e7905bdf6e97..82e9c843617f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -53,7 +53,7 @@ obj-$(CONFIG_FREEZER) += freezer.o obj-$(CONFIG_PROFILING) += profile.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ -obj-$(CONFIG_FUTEX) += futex.o +obj-$(CONFIG_FUTEX) += futex/ obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o ifneq ($(CONFIG_SMP),y) diff --git a/kernel/acct.c b/kernel/acct.c index f175df8f6aa4..12f7dacf560e 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -331,6 +331,8 @@ static comp_t encode_comp_t(unsigned long value) exp++; } + if (exp > (((comp_t) ~0U) >> MANTSIZE)) + return (comp_t) ~0U; /* * Clean it up and polish it off. */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9232938e3f96..52e704860739 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3675,6 +3675,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env, break; } + if (btf_type_is_resolve_source_only(arg_type)) { + btf_verifier_log_type(env, t, "Invalid arg#%u", i + 1); + return -EINVAL; + } + if (args[i].name_off && (!btf_name_offset_valid(btf, args[i].name_off) || !btf_name_valid_identifier(btf, args[i].name_off))) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 50364031eb4d..232c93357b90 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -562,6 +562,14 @@ const char *kernel_type_name(u32 id) btf_type_by_id(btf_vmlinux, id)->name_off); } +/* The reg state of a pointer or a bounded scalar was saved when + * it was spilled to the stack. + */ +static bool is_spilled_reg(const struct bpf_stack_state *stack) +{ + return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL; +} + static void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_func_state *state) { @@ -666,7 +674,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, continue; verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); print_liveness(env, state->stack[i].spilled_ptr.live); - if (state->stack[i].slot_type[0] == STACK_SPILL) { + if (is_spilled_reg(&state->stack[i])) { reg = &state->stack[i].spilled_ptr; t = reg->type; verbose(env, "=%s", reg_type_str[t]); @@ -2009,7 +2017,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, reg->precise = true; } for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) { - if (func->stack[j].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&func->stack[j])) continue; reg = &func->stack[j].spilled_ptr; if (reg->type != SCALAR_VALUE) @@ -2019,7 +2027,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, } } -static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, +static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno, int spi) { struct bpf_verifier_state *st = env->cur_state; @@ -2036,7 +2044,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, if (!env->bpf_capable) return 0; - func = st->frame[st->curframe]; + func = st->frame[frame]; if (regno >= 0) { reg = &func->regs[regno]; if (reg->type != SCALAR_VALUE) { @@ -2051,7 +2059,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, } while (spi >= 0) { - if (func->stack[spi].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[spi])) { stack_mask = 0; break; } @@ -2117,7 +2125,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, break; new_marks = false; - func = st->frame[st->curframe]; + func = st->frame[frame]; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; @@ -2150,7 +2158,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, return 0; } - if (func->stack[i].slot_type[0] != STACK_SPILL) { + if (!is_spilled_reg(&func->stack[i])) { stack_mask &= ~(1ull << i); continue; } @@ -2183,12 +2191,17 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, static int mark_chain_precision(struct bpf_verifier_env *env, int regno) { - return __mark_chain_precision(env, regno, -1); + return __mark_chain_precision(env, env->cur_state->curframe, regno, -1); } -static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi) +static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno) { - return __mark_chain_precision(env, -1, spi); + return __mark_chain_precision(env, frame, regno, -1); +} + +static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi) +{ + return __mark_chain_precision(env, frame, -1, spi); } static bool is_spillable_regtype(enum bpf_reg_type type) @@ -2348,7 +2361,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, /* regular write of data into stack destroys any spilled ptr */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Mark slots as STACK_MISC if they belonged to spilled ptr. */ - if (state->stack[spi].slot_type[0] == STACK_SPILL) + if (is_spilled_reg(&state->stack[spi])) for (i = 0; i < BPF_REG_SIZE; i++) state->stack[spi].slot_type[i] = STACK_MISC; @@ -2439,14 +2452,17 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, spi = slot / BPF_REG_SIZE; stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE]; - if (!env->allow_ptr_leaks - && *stype != NOT_INIT - && *stype != SCALAR_VALUE) { - /* Reject the write if there's are spilled pointers in - * range. If we didn't reject here, the ptr status - * would be erased below (even though not all slots are - * actually overwritten), possibly opening the door to - * leaks. + if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) { + /* Reject the write if range we may write to has not + * been initialized beforehand. If we didn't reject + * here, the ptr status would be erased below (even + * though not all slots are actually overwritten), + * possibly opening the door to leaks. + * + * We do however catch STACK_INVALID case below, and + * only allow reading possibly uninitialized memory + * later for CAP_PERFMON, as the write may not happen to + * that slot. */ verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d", insn_idx, i); @@ -2559,7 +2575,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, stype = reg_state->stack[spi].slot_type; reg = ®_state->stack[spi].spilled_ptr; - if (stype[0] == STACK_SPILL) { + if (is_spilled_reg(®_state->stack[spi])) { if (size != BPF_REG_SIZE) { if (reg->type != SCALAR_VALUE) { verbose_linfo(env, env->insn_idx, "; "); @@ -4078,11 +4094,11 @@ static int check_stack_range_initialized( goto mark; } - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID) goto mark; - if (state->stack[spi].slot_type[0] == STACK_SPILL && + if (is_spilled_reg(&state->stack[spi]) && (state->stack[spi].spilled_ptr.type == SCALAR_VALUE || env->allow_ptr_leaks)) { if (clobber) { @@ -6989,6 +7005,11 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, return err; return adjust_ptr_min_max_vals(env, insn, dst_reg, src_reg); + } else if (dst_reg->precise) { + /* if dst_reg is precise, src_reg should be precise as well */ + err = mark_chain_precision(env, insn->src_reg); + if (err) + return err; } } else { /* Pretend the src is a reg with a known value, since we only @@ -9274,9 +9295,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * return false to continue verification of this path */ return false; - if (i % BPF_REG_SIZE) + if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1) continue; - if (old->stack[spi].slot_type[0] != STACK_SPILL) + if (!is_spilled_reg(&old->stack[spi])) continue; if (!regsafe(env, &old->stack[spi].spilled_ptr, &cur->stack[spi].spilled_ptr, idmap)) @@ -9467,34 +9488,36 @@ static int propagate_precision(struct bpf_verifier_env *env, { struct bpf_reg_state *state_reg; struct bpf_func_state *state; - int i, err = 0; + int i, err = 0, fr; - state = old->frame[old->curframe]; - state_reg = state->regs; - for (i = 0; i < BPF_REG_FP; i++, state_reg++) { - if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) - continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "propagating r%d\n", i); - err = mark_chain_precision(env, i); - if (err < 0) - return err; - } + for (fr = old->curframe; fr >= 0; fr--) { + state = old->frame[fr]; + state_reg = state->regs; + for (i = 0; i < BPF_REG_FP; i++, state_reg++) { + if (state_reg->type != SCALAR_VALUE || + !state_reg->precise) + continue; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "frame %d: propagating r%d\n", i, fr); + err = mark_chain_precision_frame(env, fr, i); + if (err < 0) + return err; + } - for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] != STACK_SPILL) - continue; - state_reg = &state->stack[i].spilled_ptr; - if (state_reg->type != SCALAR_VALUE || - !state_reg->precise) - continue; - if (env->log.level & BPF_LOG_LEVEL2) - verbose(env, "propagating fp%d\n", - (-i - 1) * BPF_REG_SIZE); - err = mark_chain_precision_stack(env, i); - if (err < 0) - return err; + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (!is_spilled_reg(&state->stack[i])) + continue; + state_reg = &state->stack[i].spilled_ptr; + if (state_reg->type != SCALAR_VALUE || + !state_reg->precise) + continue; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "frame %d: propagating fp%d\n", + (-i - 1) * BPF_REG_SIZE, fr); + err = mark_chain_precision_stack_frame(env, fr, i); + if (err < 0) + return err; + } } return 0; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 3c9ee966c56a..008b50da2224 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2231,8 +2231,10 @@ static ssize_t write_cpuhp_target(struct device *dev, if (st->state < target) ret = cpu_up(dev->id, target); - else + else if (st->state > target) ret = cpu_down(dev->id, target); + else if (WARN_ON(st->target != target)) + st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; diff --git a/kernel/events/core.c b/kernel/events/core.c index e9b354d521a3..d7b61116f15b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10810,13 +10810,15 @@ static int pmu_dev_alloc(struct pmu *pmu) pmu->dev->groups = pmu->attr_groups; device_initialize(pmu->dev); - ret = dev_set_name(pmu->dev, "%s", pmu->name); - if (ret) - goto free_dev; dev_set_drvdata(pmu->dev, pmu); pmu->dev->bus = &pmu_bus; pmu->dev->release = pmu_dev_release; + + ret = dev_set_name(pmu->dev, "%s", pmu->name); + if (ret) + goto free_dev; + ret = device_add(pmu->dev); if (ret) goto free_dev; @@ -11779,12 +11781,12 @@ SYSCALL_DEFINE5(perf_event_open, if (flags & ~PERF_FLAG_ALL) return -EINVAL; - /* Do we allow access to perf_event_open(2) ? */ - err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); + err = perf_copy_attr(attr_uptr, &attr); if (err) return err; - err = perf_copy_attr(attr_uptr, &attr); + /* Do we allow access to perf_event_open(2) ? */ + err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); if (err) return err; diff --git a/kernel/futex/Makefile b/kernel/futex/Makefile new file mode 100644 index 000000000000..b89ba3fba343 --- /dev/null +++ b/kernel/futex/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-y += core.o diff --git a/kernel/futex.c b/kernel/futex/core.c index 98a6e1b80bfe..8dd0bc50ac36 100644 --- a/kernel/futex.c +++ b/kernel/futex/core.c @@ -42,7 +42,7 @@ #include <asm/futex.h> -#include "locking/rtmutex_common.h" +#include "../locking/rtmutex_common.h" /* * READ this before attempting to hack on futexes! @@ -3405,6 +3405,7 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, bool pi, bool pending_op) { u32 uval, nval, mval; + pid_t owner; int err; /* Futex address must be 32bit aligned */ @@ -3426,6 +3427,10 @@ retry: * 2. A woken up waiter is killed before it can acquire the * futex in user space. * + * In the second case, the wake up notification could be generated + * by the unlock path in user space after setting the futex value + * to zero or by the kernel after setting the OWNER_DIED bit below. + * * In both cases the TID validation below prevents a wakeup of * potential waiters which can cause these waiters to block * forever. @@ -3434,24 +3439,27 @@ retry: * * 1) task->robust_list->list_op_pending != NULL * @pending_op == true - * 2) User space futex value == 0 + * 2) The owner part of user space futex value == 0 * 3) Regular futex: @pi == false * * If these conditions are met, it is safe to attempt waking up a * potential waiter without touching the user space futex value and - * trying to set the OWNER_DIED bit. The user space futex value is - * uncontended and the rest of the user space mutex state is - * consistent, so a woken waiter will just take over the - * uncontended futex. Setting the OWNER_DIED bit would create - * inconsistent state and malfunction of the user space owner died - * handling. - */ - if (pending_op && !pi && !uval) { + * trying to set the OWNER_DIED bit. If the futex value is zero, + * the rest of the user space mutex state is consistent, so a woken + * waiter will just take over the uncontended futex. Setting the + * OWNER_DIED bit would create inconsistent state and malfunction + * of the user space owner died handling. Otherwise, the OWNER_DIED + * bit is already set, and the woken waiter is expected to deal with + * this. + */ + owner = uval & FUTEX_TID_MASK; + + if (pending_op && !pi && !owner) { futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); return 0; } - if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr)) + if (owner != task_pid_vnr(curr)) return 0; /* diff --git a/kernel/gcov/gcc_4_7.c b/kernel/gcov/gcc_4_7.c index c699feda21ac..04880d8fba25 100644 --- a/kernel/gcov/gcc_4_7.c +++ b/kernel/gcov/gcc_4_7.c @@ -85,6 +85,7 @@ struct gcov_fn_info { * @version: gcov version magic indicating the gcc version used for compilation * @next: list head for a singly-linked list * @stamp: uniquifying time stamp + * @checksum: unique object checksum * @filename: name of the associated gcov data file * @merge: merge functions (null for unused counter type) * @n_functions: number of instrumented functions @@ -97,6 +98,10 @@ struct gcov_info { unsigned int version; struct gcov_info *next; unsigned int stamp; + /* Since GCC 12.1 a checksum field is added. */ +#if (__GNUC__ >= 12) + unsigned int checksum; +#endif const char *filename; void (*merge[GCOV_COUNTERS])(gcov_type *, unsigned int); unsigned int n_functions; diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index e58342ace11f..f1d83a8b4417 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -52,6 +52,7 @@ enum { * IRQS_PENDING - irq is pending and replayed later * IRQS_SUSPENDED - irq is suspended * IRQS_NMI - irq line is used to deliver NMIs + * IRQS_SYSFS - descriptor has been added to sysfs */ enum { IRQS_AUTODETECT = 0x00000001, @@ -64,6 +65,7 @@ enum { IRQS_SUSPENDED = 0x00000800, IRQS_TIMINGS = 0x00001000, IRQS_NMI = 0x00002000, + IRQS_SYSFS = 0x00004000, }; #include "debug.h" diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index ca36c6179aa7..9b0914a063f9 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -288,22 +288,25 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc) if (irq_kobj_base) { /* * Continue even in case of failure as this is nothing - * crucial. + * crucial and failures in the late irq_sysfs_init() + * cannot be rolled back. */ if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq)) pr_warn("Failed to add kobject for irq %d\n", irq); + else + desc->istate |= IRQS_SYSFS; } } static void irq_sysfs_del(struct irq_desc *desc) { /* - * If irq_sysfs_init() has not yet been invoked (early boot), then - * irq_kobj_base is NULL and the descriptor was never added. - * kobject_del() complains about a object with no parent, so make - * it conditional. + * Only invoke kobject_del() when kobject_add() was successfully + * invoked for the descriptor. This covers both early boot, where + * sysfs is not initialized yet, and the case of a failed + * kobject_add() invocation. */ - if (irq_kobj_base) + if (desc->istate & IRQS_SYSFS) kobject_del(&desc->kobj); } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3cb29835632f..437b073dc487 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1667,7 +1667,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) irqd_set(&desc->irq_data, IRQD_NO_BALANCING); } - if (irq_settings_can_autoenable(desc)) { + if (!(new->flags & IRQF_NO_AUTOEN) && + irq_settings_can_autoenable(desc)) { irq_startup(desc, IRQ_RESEND, IRQ_START_COND); } else { /* @@ -2054,10 +2055,15 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, * which interrupt is which (messes up the interrupt freeing * logic etc). * + * Also shared interrupts do not go well with disabling auto enable. + * The sharing interrupt might request it while it's still disabled + * and then wait for interrupts forever. + * * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and * it cannot be set along with IRQF_NO_SUSPEND. */ if (((irqflags & IRQF_SHARED) && !dev_id) || + ((irqflags & IRQF_SHARED) && (irqflags & IRQF_NO_AUTOEN)) || (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) || ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND))) return -EINVAL; @@ -2213,7 +2219,8 @@ int request_nmi(unsigned int irq, irq_handler_t handler, desc = irq_to_desc(irq); - if (!desc || irq_settings_can_autoenable(desc) || + if (!desc || (irq_settings_can_autoenable(desc) && + !(irqflags & IRQF_NO_AUTOEN)) || !irq_settings_can_request(desc) || WARN_ON(irq_settings_is_per_cpu_devid(desc)) || !irq_supports_nmi(desc)) diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c index 23e7acb5c667..762df6108c58 100644 --- a/kernel/kcsan/core.c +++ b/kernel/kcsan/core.c @@ -9,10 +9,12 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/minmax.h> #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/preempt.h> #include <linux/sched.h> +#include <linux/string.h> #include <linux/uaccess.h> #include "atomic.h" @@ -1045,3 +1047,51 @@ EXPORT_SYMBOL(__tsan_atomic_thread_fence); void __tsan_atomic_signal_fence(int memorder); void __tsan_atomic_signal_fence(int memorder) { } EXPORT_SYMBOL(__tsan_atomic_signal_fence); + +#ifdef __HAVE_ARCH_MEMSET +void *__tsan_memset(void *s, int c, size_t count); +noinline void *__tsan_memset(void *s, int c, size_t count) +{ + /* + * Instead of not setting up watchpoints where accessed size is greater + * than MAX_ENCODABLE_SIZE, truncate checked size to MAX_ENCODABLE_SIZE. + */ + size_t check_len = min_t(size_t, count, MAX_ENCODABLE_SIZE); + + check_access(s, check_len, KCSAN_ACCESS_WRITE); + return memset(s, c, count); +} +#else +void *__tsan_memset(void *s, int c, size_t count) __alias(memset); +#endif +EXPORT_SYMBOL(__tsan_memset); + +#ifdef __HAVE_ARCH_MEMMOVE +void *__tsan_memmove(void *dst, const void *src, size_t len); +noinline void *__tsan_memmove(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE); + check_access(src, check_len, 0); + return memmove(dst, src, len); +} +#else +void *__tsan_memmove(void *dst, const void *src, size_t len) __alias(memmove); +#endif +EXPORT_SYMBOL(__tsan_memmove); + +#ifdef __HAVE_ARCH_MEMCPY +void *__tsan_memcpy(void *dst, const void *src, size_t len); +noinline void *__tsan_memcpy(void *dst, const void *src, size_t len) +{ + size_t check_len = min_t(size_t, len, MAX_ENCODABLE_SIZE); + + check_access(dst, check_len, KCSAN_ACCESS_WRITE); + check_access(src, check_len, 0); + return memcpy(dst, src, len); +} +#else +void *__tsan_memcpy(void *dst, const void *src, size_t len) __alias(memcpy); +#endif +EXPORT_SYMBOL(__tsan_memcpy); diff --git a/kernel/padata.c b/kernel/padata.c index d4d3ba6e1728..11ca3ebd8b12 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -220,14 +220,16 @@ int padata_do_parallel(struct padata_shell *ps, pw = padata_work_alloc(); spin_unlock(&padata_works_lock); + if (!pw) { + /* Maximum works limit exceeded, run in the current task. */ + padata->parallel(padata); + } + rcu_read_unlock_bh(); if (pw) { padata_work_init(pw, padata_parallel_worker, padata, 0); queue_work(pinst->parallel_wq, &pw->pw_work); - } else { - /* Maximum works limit exceeded, run in the current task. */ - padata->parallel(padata); } return 0; @@ -401,13 +403,16 @@ void padata_do_serial(struct padata_priv *padata) int hashed_cpu = padata_cpu_hash(pd, padata->seq_nr); struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu); struct padata_priv *cur; + struct list_head *pos; spin_lock(&reorder->lock); /* Sort in ascending order of sequence number. */ - list_for_each_entry_reverse(cur, &reorder->list, list) + list_for_each_prev(pos, &reorder->list) { + cur = list_entry(pos, struct padata_priv, list); if (cur->seq_nr < padata->seq_nr) break; - list_add(&padata->list, &cur->list); + } + list_add(&padata->list, pos); spin_unlock(&reorder->lock); /* diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 1da013f50059..f5dccd445d36 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1677,8 +1677,8 @@ static unsigned long minimum_image_size(unsigned long saveable) * /sys/power/reserved_size, respectively). To make this happen, we compute the * total number of available page frames and allocate at least * - * ([page frames total] + PAGES_FOR_IO + [metadata pages]) / 2 - * + 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) + * ([page frames total] - PAGES_FOR_IO - [metadata pages]) / 2 + * - 2 * DIV_ROUND_UP(reserved_size, PAGE_SIZE) * * of them, which corresponds to the maximum size of a hibernation image. * diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b10d6bcea77d..9cce4e13af41 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1157,7 +1157,7 @@ bool rcu_lockdep_current_cpu_online(void) preempt_disable_notrace(); rdp = this_cpu_ptr(&rcu_data); rnp = rdp->mynode; - if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) + if (rdp->grpmask & rcu_rnp_online_cpus(rnp) || READ_ONCE(rnp->ofl_seq) & 0x1) ret = true; preempt_enable_notrace(); return ret; @@ -1724,6 +1724,7 @@ static void rcu_strict_gp_boundary(void *unused) */ static bool rcu_gp_init(void) { + unsigned long firstseq; unsigned long flags; unsigned long oldmask; unsigned long mask; @@ -1767,6 +1768,12 @@ static bool rcu_gp_init(void) */ rcu_state.gp_state = RCU_GP_ONOFF; rcu_for_each_leaf_node(rnp) { + smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values. + firstseq = READ_ONCE(rnp->ofl_seq); + if (firstseq & 0x1) + while (firstseq == READ_ONCE(rnp->ofl_seq)) + schedule_timeout_idle(1); // Can't wake unless RCU is watching. + smp_mb(); // Pair with barriers used when updating ->ofl_seq to even values. raw_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irq_rcu_node(rnp); if (rnp->qsmaskinit == rnp->qsmaskinitnext && @@ -2650,7 +2657,7 @@ void rcu_force_quiescent_state(void) struct rcu_node *rnp_old = NULL; /* Funnel through hierarchy to reduce memory contention. */ - rnp = __this_cpu_read(rcu_data.mynode); + rnp = raw_cpu_read(rcu_data.mynode); for (; rnp != NULL; rnp = rnp->parent) { ret = (READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_FQS) || !raw_spin_trylock(&rnp->fqslock); @@ -4107,6 +4114,9 @@ void rcu_cpu_starting(unsigned int cpu) rnp = rdp->mynode; mask = rdp->grpmask; + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(!(rnp->ofl_seq & 0x1)); + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). raw_spin_lock_irqsave_rcu_node(rnp, flags); WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext | mask); newcpu = !(rnp->expmaskinitnext & mask); @@ -4124,6 +4134,9 @@ void rcu_cpu_starting(unsigned int cpu) } else { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(rnp->ofl_seq & 0x1); smp_mb(); /* Ensure RCU read-side usage follows above initialization. */ } @@ -4150,6 +4163,9 @@ void rcu_report_dead(unsigned int cpu) /* Remove outgoing CPU from mask in the leaf rcu_node structure. */ mask = rdp->grpmask; + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(!(rnp->ofl_seq & 0x1)); + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). raw_spin_lock(&rcu_state.ofl_lock); raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */ rdp->rcu_ofl_gp_seq = READ_ONCE(rcu_state.gp_seq); @@ -4162,6 +4178,9 @@ void rcu_report_dead(unsigned int cpu) WRITE_ONCE(rnp->qsmaskinitnext, rnp->qsmaskinitnext & ~mask); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); raw_spin_unlock(&rcu_state.ofl_lock); + smp_mb(); // Pair with rcu_gp_cleanup()'s ->ofl_seq barrier(). + WRITE_ONCE(rnp->ofl_seq, rnp->ofl_seq + 1); + WARN_ON_ONCE(rnp->ofl_seq & 0x1); rdp->cpu_started = false; } diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index e4f66b8f7c47..6e8c77729a47 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -56,6 +56,7 @@ struct rcu_node { /* Initialized from ->qsmaskinitnext at the */ /* beginning of each grace period. */ unsigned long qsmaskinitnext; + unsigned long ofl_seq; /* CPU-hotplug operation sequence count. */ /* Online CPUs for next grace period. */ unsigned long expmask; /* CPUs or groups that need to check in */ /* to allow the current expedited GP */ diff --git a/kernel/relay.c b/kernel/relay.c index b08d936d5fa7..067769b80d4a 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -163,13 +163,13 @@ static struct rchan_buf *relay_create_buf(struct rchan *chan) { struct rchan_buf *buf; - if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t *)) + if (chan->n_subbufs > KMALLOC_MAX_SIZE / sizeof(size_t)) return NULL; buf = kzalloc(sizeof(struct rchan_buf), GFP_KERNEL); if (!buf) return NULL; - buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t *), + buf->padding = kmalloc_array(chan->n_subbufs, sizeof(size_t), GFP_KERNEL); if (!buf->padding) goto free_buf; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index bca0efc03a51..c39d2fc3f994 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4074,7 +4074,131 @@ done: trace_sched_util_est_se_tp(&p->se); } -static inline int task_fits_capacity(struct task_struct *p, long capacity) +static inline int util_fits_cpu(unsigned long util, + unsigned long uclamp_min, + unsigned long uclamp_max, + int cpu) +{ + unsigned long capacity_orig, capacity_orig_thermal; + unsigned long capacity = capacity_of(cpu); + bool fits, uclamp_max_fits; + + /* + * Check if the real util fits without any uclamp boost/cap applied. + */ + fits = fits_capacity(util, capacity); + + if (!uclamp_is_used()) + return fits; + + /* + * We must use capacity_orig_of() for comparing against uclamp_min and + * uclamp_max. We only care about capacity pressure (by using + * capacity_of()) for comparing against the real util. + * + * If a task is boosted to 1024 for example, we don't want a tiny + * pressure to skew the check whether it fits a CPU or not. + * + * Similarly if a task is capped to capacity_orig_of(little_cpu), it + * should fit a little cpu even if there's some pressure. + * + * Only exception is for thermal pressure since it has a direct impact + * on available OPP of the system. + * + * We honour it for uclamp_min only as a drop in performance level + * could result in not getting the requested minimum performance level. + * + * For uclamp_max, we can tolerate a drop in performance level as the + * goal is to cap the task. So it's okay if it's getting less. + * + * In case of capacity inversion, which is not handled yet, we should + * honour the inverted capacity for both uclamp_min and uclamp_max all + * the time. + */ + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); + + /* + * We want to force a task to fit a cpu as implied by uclamp_max. + * But we do have some corner cases to cater for.. + * + * + * C=z + * | ___ + * | C=y | | + * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max + * | C=x | | | | + * | ___ | | | | + * | | | | | | | (util somewhere in this region) + * | | | | | | | + * | | | | | | | + * +---------------------------------------- + * cpu0 cpu1 cpu2 + * + * In the above example if a task is capped to a specific performance + * point, y, then when: + * + * * util = 80% of x then it does not fit on cpu0 and should migrate + * to cpu1 + * * util = 80% of y then it is forced to fit on cpu1 to honour + * uclamp_max request. + * + * which is what we're enforcing here. A task always fits if + * uclamp_max <= capacity_orig. But when uclamp_max > capacity_orig, + * the normal upmigration rules should withhold still. + * + * Only exception is when we are on max capacity, then we need to be + * careful not to block overutilized state. This is so because: + * + * 1. There's no concept of capping at max_capacity! We can't go + * beyond this performance level anyway. + * 2. The system is being saturated when we're operating near + * max capacity, it doesn't make sense to block overutilized. + */ + uclamp_max_fits = (capacity_orig == SCHED_CAPACITY_SCALE) && (uclamp_max == SCHED_CAPACITY_SCALE); + uclamp_max_fits = !uclamp_max_fits && (uclamp_max <= capacity_orig); + fits = fits || uclamp_max_fits; + + /* + * + * C=z + * | ___ (region a, capped, util >= uclamp_max) + * | C=y | | + * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max + * | C=x | | | | + * | ___ | | | | (region b, uclamp_min <= util <= uclamp_max) + * |_ _ _|_ _|_ _ _ _| _ | _ _ _| _ | _ _ _ _ _ uclamp_min + * | | | | | | | + * | | | | | | | (region c, boosted, util < uclamp_min) + * +---------------------------------------- + * cpu0 cpu1 cpu2 + * + * a) If util > uclamp_max, then we're capped, we don't care about + * actual fitness value here. We only care if uclamp_max fits + * capacity without taking margin/pressure into account. + * See comment above. + * + * b) If uclamp_min <= util <= uclamp_max, then the normal + * fits_capacity() rules apply. Except we need to ensure that we + * enforce we remain within uclamp_max, see comment above. + * + * c) If util < uclamp_min, then we are boosted. Same as (b) but we + * need to take into account the boosted value fits the CPU without + * taking margin/pressure into account. + * + * Cases (a) and (b) are handled in the 'fits' variable already. We + * just need to consider an extra check for case (c) after ensuring we + * handle the case uclamp_min > uclamp_max. + */ + uclamp_min = min(uclamp_min, uclamp_max); + if (util < uclamp_min && capacity_orig != SCHED_CAPACITY_SCALE) + fits = fits && (uclamp_min <= capacity_orig_thermal); + + return fits; +} + +static inline int task_fits_capacity(struct task_struct *p, + unsigned long capacity) { return fits_capacity(uclamp_task_util(p), capacity); } @@ -6247,7 +6371,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) return best_cpu; } -static inline bool asym_fits_capacity(int task_util, int cpu) +static inline bool asym_fits_capacity(unsigned long task_util, int cpu) { if (static_branch_unlikely(&sched_asym_cpucapacity)) return fits_capacity(task_util, capacity_of(cpu)); diff --git a/kernel/sys.c b/kernel/sys.c index 24a3a28ae228..9f59cc8ab8f8 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1548,6 +1548,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); + if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 15a376f85e09..ab912cc60760 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -1592,7 +1592,8 @@ blk_trace_event_print_binary(struct trace_iterator *iter, int flags, static enum print_line_t blk_tracer_print_line(struct trace_iterator *iter) { - if (!(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) + if ((iter->ent->type != TRACE_BLK) || + !(blk_tracer_flags.val & TRACE_BLK_OPT_CLASSIC)) return TRACE_TYPE_UNHANDLED; return print_one_line(iter, true); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 146771d6d007..c7c92b0eed04 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6371,7 +6371,20 @@ waitagain: ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { - /* don't print partial lines */ + /* + * If one print_trace_line() fills entire trace_seq in one shot, + * trace_seq_to_user() will returns -EBUSY because save_len == 0, + * In this case, we need to consume it, otherwise, loop will peek + * this event next time, resulting in an infinite loop. + */ + if (save_len == 0) { + iter->seq.full = 0; + trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); + trace_consume(iter); + break; + } + + /* In other cases, don't print partial lines */ iter->seq.seq.len = save_len; break; } diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index fd5416829445..0ae3e4454ff2 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -417,7 +417,7 @@ struct action_data { * event param, and is passed to the synthetic event * invocation. */ - unsigned int var_ref_idx[TRACING_MAP_VARS_MAX]; + unsigned int var_ref_idx[SYNTH_FIELDS_MAX]; struct synth_event *synth_event; bool use_trace_keyword; char *synth_event_name; @@ -1846,7 +1846,9 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, return ref_field; } } - + /* Sanity check to avoid out-of-bound write on 'hist_data->var_refs' */ + if (hist_data->n_var_refs >= TRACING_MAP_VARS_MAX) + return NULL; ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { if (init_var_ref(ref_field, var_field, system, event_name)) { @@ -3113,6 +3115,7 @@ static int parse_action_params(struct trace_array *tr, char *params, while (params) { if (data->n_params >= SYNTH_FIELDS_MAX) { hist_err(tr, HIST_ERR_TOO_MANY_PARAMS, 0); + ret = -EINVAL; goto out; } @@ -3449,6 +3452,10 @@ static int trace_action_create(struct hist_trigger_data *hist_data, lockdep_assert_held(&event_mutex); + /* Sanity check to avoid out-of-bound write on 'data->var_ref_idx' */ + if (data->n_params > SYNTH_FIELDS_MAX) + return -EINVAL; + if (data->use_trace_keyword) synth_event_name = data->synth_event_name; else @@ -5827,7 +5834,7 @@ enable: /* Just return zero, not the number of registered triggers */ ret = 0; out: - if (ret == 0) + if (ret == 0 && glob[0]) hist_err_clear(); return ret; |