Merge x86 bugfixes from Linux 6.9-rc3

Pull fix for SEV-SNP late disable bugs.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

kernel/bpf/Makefile

@@ -4,7 +4,7 @@ ifneq ($(CONFIG_BPF_JIT_ALWAYS_ON),y)
 # ___bpf_prog_run() needs GCSE disabled on x86; see 3193c0836f203 for details
 cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse
 endif
-CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy)
+CFLAGS_core.o += -Wno-override-init $(cflags-nogcse-yy)
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o
 obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o

kernel/bpf/arena.c

@@ -38,7 +38,7 @@
 
 /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */
 #define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8)
-#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ)
+#define KERN_VM_SZ (SZ_4G + GUARD_SZ)
 
 struct bpf_arena {
 	struct bpf_map map;
@@ -110,7 +110,7 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-EINVAL);
 
 	vm_range = (u64)attr->max_entries * PAGE_SIZE;
-	if (vm_range > (1ull << 32))
+	if (vm_range > SZ_4G)
 		return ERR_PTR(-E2BIG);
 
 	if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32))
@@ -301,7 +301,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad
 
 	if (pgoff)
 		return -EINVAL;
-	if (len > (1ull << 32))
+	if (len > SZ_4G)
 		return -E2BIG;
 
 	/* if user_vm_start was specified at arena creation time */
@@ -322,7 +322,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad
 	if (WARN_ON_ONCE(arena->user_vm_start))
 		/* checks at map creation time should prevent this */
 		return -EFAULT;
-	return round_up(ret, 1ull << 32);
+	return round_up(ret, SZ_4G);
 }
 
 static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
@@ -346,7 +346,7 @@ static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 		return -EBUSY;
 
 	/* Earlier checks should prevent this */
-	if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff))
+	if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > SZ_4G || vma->vm_pgoff))
 		return -EFAULT;
 
 	if (remember_vma(arena, vma))
@@ -420,7 +420,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 		if (uaddr & ~PAGE_MASK)
 			return 0;
 		pgoff = compute_pgoff(arena, uaddr);
-		if (pgoff + page_cnt > page_cnt_max)
+		if (pgoff > page_cnt_max - page_cnt)
 			/* requested address will be outside of user VMA */
 			return 0;
 	}
@@ -447,7 +447,13 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 		goto out;
 
 	uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE);
-	/* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */
+	/* Earlier checks made sure that uaddr32 + page_cnt * PAGE_SIZE - 1
+	 * will not overflow 32-bit. Lower 32-bit need to represent
+	 * contiguous user address range.
+	 * Map these pages at kern_vm_start base.
+	 * kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE - 1 can overflow
+	 * lower 32-bit and it's ok.
+	 */
 	ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32,
 				kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages);
 	if (ret) {
@@ -510,6 +516,11 @@ static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt)
 		if (!page)
 			continue;
 		if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */
+			/* Optimization for the common case of page_cnt==1:
+			 * If page wasn't mapped into some user vma there
+			 * is no need to call zap_pages which is slow. When
+			 * page_cnt is big it's faster to do the batched zap.
+			 */
 			zap_pages(arena, full_uaddr, 1);
 		vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE);
 		__free_page(page);

kernel/bpf/bloom_filter.c

@@ -80,6 +80,18 @@ static int bloom_map_get_next_key(struct bpf_map *map, void *key, void *next_key
 	return -EOPNOTSUPP;
 }
 
+/* Called from syscall */
+static int bloom_map_alloc_check(union bpf_attr *attr)
+{
+	if (attr->value_size > KMALLOC_MAX_SIZE)
+		/* if value_size is bigger, the user space won't be able to
+		 * access the elements.
+		 */
+		return -E2BIG;
+
+	return 0;
+}
+
 static struct bpf_map *bloom_map_alloc(union bpf_attr *attr)
 {
 	u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits;
@@ -191,6 +203,7 @@ static u64 bloom_map_mem_usage(const struct bpf_map *map)
 BTF_ID_LIST_SINGLE(bpf_bloom_map_btf_ids, struct, bpf_bloom_filter)
 const struct bpf_map_ops bloom_filter_map_ops = {
 	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = bloom_map_alloc_check,
 	.map_alloc = bloom_map_alloc,
 	.map_free = bloom_map_free,
 	.map_get_next_key = bloom_map_get_next_key,

kernel/bpf/helpers.c

@@ -2548,7 +2548,7 @@ __bpf_kfunc void bpf_throw(u64 cookie)
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(generic_btf_ids)
-#ifdef CONFIG_KEXEC_CORE
+#ifdef CONFIG_CRASH_DUMP
 BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE)
 #endif
 BTF_ID_FLAGS(func, bpf_obj_new_impl, KF_ACQUIRE | KF_RET_NULL)

kernel/bpf/syscall.c

@@ -3024,17 +3024,46 @@ void bpf_link_inc(struct bpf_link *link)
 	atomic64_inc(&link->refcnt);
 }
 
+static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
+{
+	struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
+
+	/* free bpf_link and its containing memory */
+	link->ops->dealloc_deferred(link);
+}
+
+static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
+{
+	if (rcu_trace_implies_rcu_gp())
+		bpf_link_defer_dealloc_rcu_gp(rcu);
+	else
+		call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp);
+}
+
 /* bpf_link_free is guaranteed to be called from process context */
 static void bpf_link_free(struct bpf_link *link)
 {
+	bool sleepable = false;
+
 	bpf_link_free_id(link->id);
 	if (link->prog) {
+		sleepable = link->prog->sleepable;
 		/* detach BPF program, clean up used resources */
 		link->ops->release(link);
 		bpf_prog_put(link->prog);
 	}
-	/* free bpf_link and its containing memory */
-	link->ops->dealloc(link);
+	if (link->ops->dealloc_deferred) {
+		/* schedule BPF link deallocation; if underlying BPF program
+		 * is sleepable, we need to first wait for RCU tasks trace
+		 * sync, then go through "classic" RCU grace period
+		 */
+		if (sleepable)
+			call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
+		else
+			call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
+	}
+	if (link->ops->dealloc)
+		link->ops->dealloc(link);
 }
 
 static void bpf_link_put_deferred(struct work_struct *work)
@@ -3544,7 +3573,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
 
 static const struct bpf_link_ops bpf_raw_tp_link_lops = {
 	.release = bpf_raw_tp_link_release,
-	.dealloc = bpf_raw_tp_link_dealloc,
+	.dealloc_deferred = bpf_raw_tp_link_dealloc,
 	.show_fdinfo = bpf_raw_tp_link_show_fdinfo,
 	.fill_link_info = bpf_raw_tp_link_fill_link_info,
 };

kernel/bpf/verifier.c

@@ -5682,6 +5682,13 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
 	return reg->type == PTR_TO_FLOW_KEYS;
 }
 
+static bool is_arena_reg(struct bpf_verifier_env *env, int regno)
+{
+	const struct bpf_reg_state *reg = reg_state(env, regno);
+
+	return reg->type == PTR_TO_ARENA;
+}
+
 static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
 #ifdef CONFIG_NET
 	[PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
@@ -6694,6 +6701,11 @@ static int check_stack_access_within_bounds(
 	err = check_stack_slot_within_bounds(env, min_off, state, type);
 	if (!err && max_off > 0)
 		err = -EINVAL; /* out of stack access into non-negative offsets */
+	if (!err && access_size < 0)
+		/* access_size should not be negative (or overflow an int); others checks
+		 * along the way should have prevented such an access.
+		 */
+		err = -EFAULT; /* invalid negative access size; integer overflow? */
 
 	if (err) {
 		if (tnum_is_const(reg->var_off)) {
@@ -7019,7 +7031,8 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg) ||
 	    is_flow_key_reg(env, insn->dst_reg) ||
-	    is_sk_reg(env, insn->dst_reg)) {
+	    is_sk_reg(env, insn->dst_reg) ||
+	    is_arena_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
 			insn->dst_reg,
 			reg_type_str(env, reg_state(env, insn->dst_reg)->type));
@@ -14014,6 +14027,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n");
 					return -EINVAL;
 				}
+				if (!env->prog->aux->arena) {
+					verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n");
+					return -EINVAL;
+				}
 			} else {
 				if ((insn->off != 0 && insn->off != 8 && insn->off != 16 &&
 				     insn->off != 32) || insn->imm) {
@@ -14046,8 +14063,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				if (insn->imm) {
 					/* off == BPF_ADDR_SPACE_CAST */
 					mark_reg_unknown(env, regs, insn->dst_reg);
-					if (insn->imm == 1) /* cast from as(1) to as(0) */
+					if (insn->imm == 1) { /* cast from as(1) to as(0) */
 						dst_reg->type = PTR_TO_ARENA;
+						/* PTR_TO_ARENA is 32-bit */
+						dst_reg->subreg_def = env->insn_idx + 1;
+					}
 				} else if (insn->off == 0) {
 					/* case: R1 = R2
 					 * copy register state to dest reg
@@ -18359,15 +18379,18 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
 				}
 				if (!env->prog->jit_requested) {
 					verbose(env, "JIT is required to use arena\n");
+					fdput(f);
 					return -EOPNOTSUPP;
 				}
 				if (!bpf_jit_supports_arena()) {
 					verbose(env, "JIT doesn't support arena\n");
+					fdput(f);
 					return -EOPNOTSUPP;
 				}
 				env->prog->aux->arena = (void *)map;
 				if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) {
 					verbose(env, "arena's user address must be set via map_extra or mmap()\n");
+					fdput(f);
 					return -EINVAL;
 				}
 			}
@@ -19601,8 +19624,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			    (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) {
 				/* convert to 32-bit mov that clears upper 32-bit */
 				insn->code = BPF_ALU | BPF_MOV | BPF_X;
-				/* clear off, so it's a normal 'wX = wY' from JIT pov */
+				/* clear off and imm, so it's a normal 'wX = wY' from JIT pov */
 				insn->off = 0;
+				insn->imm = 0;
 			} /* cast from as(0) to as(1) should be handled by JIT */
 			goto next_insn;
 		}

kernel/crash_reserve.c

@@ -366,7 +366,9 @@ static int __init reserve_crashkernel_low(unsigned long long low_size)
 
 	crashk_low_res.start = low_base;
 	crashk_low_res.end   = low_base + low_size - 1;
+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 	insert_resource(&iomem_resource, &crashk_low_res);
+#endif
 #endif
 	return 0;
 }
@@ -448,8 +450,12 @@ void __init reserve_crashkernel_generic(char *cmdline,
 
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
+#ifdef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
+	insert_resource(&iomem_resource, &crashk_res);
+#endif
 }
 
+#ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 static __init int insert_crashkernel_resources(void)
 {
 	if (crashk_res.start < crashk_res.end)
@@ -462,3 +468,4 @@ static __init int insert_crashkernel_resources(void)
 }
 early_initcall(insert_crashkernel_resources);
 #endif
+#endif

kernel/irq/manage.c

@@ -1643,8 +1643,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		}
 
 		if (!((old->flags & new->flags) & IRQF_SHARED) ||
-		    (oldtype != (new->flags & IRQF_TRIGGER_MASK)) ||
-		    ((old->flags ^ new->flags) & IRQF_ONESHOT))
+		    (oldtype != (new->flags & IRQF_TRIGGER_MASK)))
+			goto mismatch;
+
+		if ((old->flags & IRQF_ONESHOT) &&
+		    (new->flags & IRQF_COND_ONESHOT))
+			new->flags |= IRQF_ONESHOT;
+		else if ((old->flags ^ new->flags) & IRQF_ONESHOT)
 			goto mismatch;
 
 		/* All handlers must agree on per-cpuness */

kernel/module/Kconfig

@@ -236,6 +236,10 @@ choice
 	  possible to load a signed module containing the algorithm to check
 	  the signature on that module.
 
+config MODULE_SIG_SHA1
+	bool "Sign modules with SHA-1"
+	select CRYPTO_SHA1
+
 config MODULE_SIG_SHA256
 	bool "Sign modules with SHA-256"
 	select CRYPTO_SHA256
@@ -265,6 +269,7 @@ endchoice
 config MODULE_SIG_HASH
 	string
 	depends on MODULE_SIG || IMA_APPRAISE_MODSIG
+	default "sha1" if MODULE_SIG_SHA1
 	default "sha256" if MODULE_SIG_SHA256
 	default "sha384" if MODULE_SIG_SHA384
 	default "sha512" if MODULE_SIG_SHA512

kernel/printk/printk.c

@@ -2009,6 +2009,12 @@ static int console_trylock_spinning(void)
 	 */
 	mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_);
 
+	/*
+	 * Update @console_may_schedule for trylock because the previous
+	 * owner may have been schedulable.
+	 */
+	console_may_schedule = 0;
+
 	return 1;
 }
 

kernel/sys.c

@@ -2408,8 +2408,11 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3,
 	if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN))
 		return -EINVAL;
 
-	/* PARISC cannot allow mdwe as it needs writable stacks */
-	if (IS_ENABLED(CONFIG_PARISC))
+	/*
+	 * EOPNOTSUPP might be more appropriate here in principle, but
+	 * existing userspace depends on EINVAL specifically.
+	 */
+	if (!arch_memory_deny_write_exec_supported())
 		return -EINVAL;
 
 	current_bits = get_current_mdwe();

kernel/time/posix-clock.c

@@ -129,15 +129,17 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 		goto out;
 	}
 	pccontext->clk = clk;
-	fp->private_data = pccontext;
-	if (clk->ops.open)
+	if (clk->ops.open) {
 		err = clk->ops.open(pccontext, fp->f_mode);
-	else
-		err = 0;
-
-	if (!err) {
-		get_device(clk->dev);
+		if (err) {
+			kfree(pccontext);
+			goto out;
+		}
 	}
+
+	fp->private_data = pccontext;
+	get_device(clk->dev);
+	err = 0;
 out:
 	up_read(&clk->rwsem);
 	return err;

kernel/trace/bpf_trace.c

@@ -2728,7 +2728,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
 
 static const struct bpf_link_ops bpf_kprobe_multi_link_lops = {
 	.release = bpf_kprobe_multi_link_release,
-	.dealloc = bpf_kprobe_multi_link_dealloc,
+	.dealloc_deferred = bpf_kprobe_multi_link_dealloc,
 	.fill_link_info = bpf_kprobe_multi_link_fill_link_info,
 };
 
@@ -3157,6 +3157,9 @@ static void bpf_uprobe_multi_link_release(struct bpf_link *link)
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
 	bpf_uprobe_unregister(&umulti_link->path, umulti_link->uprobes, umulti_link->cnt);
+	if (umulti_link->task)
+		put_task_struct(umulti_link->task);
+	path_put(&umulti_link->path);
 }
 
 static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
@@ -3164,9 +3167,6 @@ static void bpf_uprobe_multi_link_dealloc(struct bpf_link *link)
 	struct bpf_uprobe_multi_link *umulti_link;
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
-	if (umulti_link->task)
-		put_task_struct(umulti_link->task);
-	path_put(&umulti_link->path);
 	kvfree(umulti_link->uprobes);
 	kfree(umulti_link);
 }
@@ -3242,7 +3242,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
 
 static const struct bpf_link_ops bpf_uprobe_multi_link_lops = {
 	.release = bpf_uprobe_multi_link_release,
-	.dealloc = bpf_uprobe_multi_link_dealloc,
+	.dealloc_deferred = bpf_uprobe_multi_link_dealloc,
 	.fill_link_info = bpf_uprobe_multi_link_fill_link_info,
 };
 

kernel/trace/trace_probe.c

@@ -839,7 +839,7 @@ int traceprobe_get_entry_data_size(struct trace_probe *tp)
 void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs)
 {
 	struct probe_entry_arg *earg = tp->entry_arg;
-	unsigned long val;
+	unsigned long val = 0;
 	int i;
 
 	if (!earg)