Adding upstream version 6.9.8.upstream/6.9.8

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 116 insertions, 19 deletions

diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 343c3456c8..a59ae9c582 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -212,6 +212,7 @@ static u64 arena_map_mem_usage(const struct bpf_map *map)
 struct vma_list {
 	struct vm_area_struct *vma;
 	struct list_head head;
+	atomic_t mmap_count;
 };
 
 static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
@@ -221,20 +222,30 @@ static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma)
 	vml = kmalloc(sizeof(*vml), GFP_KERNEL);
 	if (!vml)
 		return -ENOMEM;
+	atomic_set(&vml->mmap_count, 1);
 	vma->vm_private_data = vml;
 	vml->vma = vma;
 	list_add(&vml->head, &arena->vma_list);
 	return 0;
 }
 
+static void arena_vm_open(struct vm_area_struct *vma)
+{
+	struct vma_list *vml = vma->vm_private_data;
+
+	atomic_inc(&vml->mmap_count);
+}
+
 static void arena_vm_close(struct vm_area_struct *vma)
 {
 	struct bpf_map *map = vma->vm_file->private_data;
 	struct bpf_arena *arena = container_of(map, struct bpf_arena, map);
-	struct vma_list *vml;
+	struct vma_list *vml = vma->vm_private_data;
 
+	if (!atomic_dec_and_test(&vml->mmap_count))
+		return;
 	guard(mutex)(&arena->lock);
-	vml = vma->vm_private_data;
+	/* update link list under lock */
 	list_del(&vml->head);
 	vma->vm_private_data = NULL;
 	kfree(vml);
@@ -287,6 +298,7 @@ out:
 }
 
 static const struct vm_operations_struct arena_vm_ops = {
+	.open		= arena_vm_open,
 	.close		= arena_vm_close,
 	.fault          = arena_vm_fault,
 };
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1ea5ce5bb5..80bcfde927 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2204,6 +2204,7 @@ static unsigned int PROG_NAME(stack_size)(const void *ctx, const struct bpf_insn
 	u64 stack[stack_size / sizeof(u64)]; \
 	u64 regs[MAX_BPF_EXT_REG] = {}; \
 \
+	kmsan_unpoison_memory(stack, sizeof(stack)); \
 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
 	ARG1 = (u64) (unsigned long) ctx; \
 	return ___bpf_prog_run(regs, insn); \
@@ -2217,6 +2218,7 @@ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
 	u64 stack[stack_size / sizeof(u64)]; \
 	u64 regs[MAX_BPF_EXT_REG]; \
 \
+	kmsan_unpoison_memory(stack, sizeof(stack)); \
 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
 	BPF_R1 = r1; \
 	BPF_R2 = r2; \
@@ -2403,7 +2405,9 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
 	}
 
 finalize:
-	bpf_prog_lock_ro(fp);
+	*err = bpf_prog_lock_ro(fp);
+	if (*err)
+		return fp;
 
 	/* The tail call compatibility check can only be done at
 	 * this late stage as we need to determine, if we deal
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 0ee653a936..e20b90c361 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -51,7 +51,8 @@ struct bpf_ringbuf {
 	 * This prevents a user-space application from modifying the
 	 * position and ruining in-kernel tracking. The permissions of the
 	 * pages depend on who is producing samples: user-space or the
-	 * kernel.
+	 * kernel. Note that the pending counter is placed in the same
+	 * page as the producer, so that it shares the same cache line.
 	 *
 	 * Kernel-producer
 	 * ---------------
@@ -70,6 +71,7 @@ struct bpf_ringbuf {
 	 */
 	unsigned long consumer_pos __aligned(PAGE_SIZE);
 	unsigned long producer_pos __aligned(PAGE_SIZE);
+	unsigned long pending_pos;
 	char data[] __aligned(PAGE_SIZE);
 };
 
@@ -179,6 +181,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node)
 	rb->mask = data_sz - 1;
 	rb->consumer_pos = 0;
 	rb->producer_pos = 0;
+	rb->pending_pos = 0;
 
 	return rb;
 }
@@ -404,9 +407,9 @@ bpf_ringbuf_restore_from_rec(struct bpf_ringbuf_hdr *hdr)
 
 static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 {
-	unsigned long cons_pos, prod_pos, new_prod_pos, flags;
-	u32 len, pg_off;
+	unsigned long cons_pos, prod_pos, new_prod_pos, pend_pos, flags;
 	struct bpf_ringbuf_hdr *hdr;
+	u32 len, pg_off, tmp_size, hdr_len;
 
 	if (unlikely(size > RINGBUF_MAX_RECORD_SZ))
 		return NULL;
@@ -424,13 +427,29 @@ static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
 		spin_lock_irqsave(&rb->spinlock, flags);
 	}
 
+	pend_pos = rb->pending_pos;
 	prod_pos = rb->producer_pos;
 	new_prod_pos = prod_pos + len;
 
-	/* check for out of ringbuf space by ensuring producer position
-	 * doesn't advance more than (ringbuf_size - 1) ahead
+	while (pend_pos < prod_pos) {
+		hdr = (void *)rb->data + (pend_pos & rb->mask);
+		hdr_len = READ_ONCE(hdr->len);
+		if (hdr_len & BPF_RINGBUF_BUSY_BIT)
+			break;
+		tmp_size = hdr_len & ~BPF_RINGBUF_DISCARD_BIT;
+		tmp_size = round_up(tmp_size + BPF_RINGBUF_HDR_SZ, 8);
+		pend_pos += tmp_size;
+	}
+	rb->pending_pos = pend_pos;
+
+	/* check for out of ringbuf space:
+	 * - by ensuring producer position doesn't advance more than
+	 *   (ringbuf_size - 1) ahead
+	 * - by ensuring oldest not yet committed record until newest
+	 *   record does not span more than (ringbuf_size - 1)
 	 */
-	if (new_prod_pos - cons_pos > rb->mask) {
+	if (new_prod_pos - cons_pos > rb->mask ||
+	    new_prod_pos - pend_pos > rb->mask) {
 		spin_unlock_irqrestore(&rb->spinlock, flags);
 		return NULL;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0ef18ae40b..d5fca9deac 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6223,6 +6223,7 @@ static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
 	}
 	reg->u32_min_value = 0;
 	reg->u32_max_value = U32_MAX;
+	reg->var_off = tnum_subreg(tnum_unknown);
 }
 
 static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
@@ -6267,6 +6268,7 @@ static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
 		reg->s32_max_value = s32_max;
 		reg->u32_min_value = (u32)s32_min;
 		reg->u32_max_value = (u32)s32_max;
+		reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max));
 		return;
 	}
 
@@ -12544,6 +12546,16 @@ static bool signed_add32_overflows(s32 a, s32 b)
 	return res < a;
 }
 
+static bool signed_add16_overflows(s16 a, s16 b)
+{
+	/* Do the add in u16, where overflow is well-defined */
+	s16 res = (s16)((u16)a + (u16)b);
+
+	if (b < 0)
+		return res > a;
+	return res < a;
+}
+
 static bool signed_sub_overflows(s64 a, s64 b)
 {
 	/* Do the sub in u64, where overflow is well-defined */
@@ -17296,11 +17308,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 				goto skip_inf_loop_check;
 			}
 			if (is_may_goto_insn_at(env, insn_idx)) {
-				if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
+				if (sl->state.may_goto_depth != cur->may_goto_depth &&
+				    states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
 					update_loop_entry(cur, &sl->state);
 					goto hit;
 				}
-				goto skip_inf_loop_check;
 			}
 			if (calls_callback(env, insn_idx)) {
 				if (states_equal(env, &sl->state, cur, RANGE_WITHIN))
@@ -18562,6 +18574,39 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	return new_prog;
 }
 
+/*
+ * For all jmp insns in a given 'prog' that point to 'tgt_idx' insn adjust the
+ * jump offset by 'delta'.
+ */
+static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta)
+{
+	struct bpf_insn *insn = prog->insnsi;
+	u32 insn_cnt = prog->len, i;
+
+	for (i = 0; i < insn_cnt; i++, insn++) {
+		u8 code = insn->code;
+
+		if ((BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32) ||
+		    BPF_OP(code) == BPF_CALL || BPF_OP(code) == BPF_EXIT)
+			continue;
+
+		if (insn->code == (BPF_JMP32 | BPF_JA)) {
+			if (i + 1 + insn->imm != tgt_idx)
+				continue;
+			if (signed_add32_overflows(insn->imm, delta))
+				return -ERANGE;
+			insn->imm += delta;
+		} else {
+			if (i + 1 + insn->off != tgt_idx)
+				continue;
+			if (signed_add16_overflows(insn->imm, delta))
+				return -ERANGE;
+			insn->off += delta;
+		}
+	}
+	return 0;
+}
+
 static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
 					      u32 off, u32 cnt)
 {
@@ -19309,10 +19354,14 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	 * bpf_prog_load will add the kallsyms for the main program.
 	 */
 	for (i = 1; i < env->subprog_cnt; i++) {
-		bpf_prog_lock_ro(func[i]);
-		bpf_prog_kallsyms_add(func[i]);
+		err = bpf_prog_lock_ro(func[i]);
+		if (err)
+			goto out_free;
 	}
 
+	for (i = 1; i < env->subprog_cnt; i++)
+		bpf_prog_kallsyms_add(func[i]);
+
 	/* Last step: make now unused interpreter insns from main
 	 * prog consistent for later dump requests, so they can
 	 * later look the same as if they were interpreted only.
@@ -19808,7 +19857,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 
 			stack_depth_extra = 8;
 			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off);
-			insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2);
+			if (insn->off >= 0)
+				insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2);
+			else
+				insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off - 1);
 			insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1);
 			insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off);
 			cnt = 4;
@@ -20266,6 +20318,13 @@ next_insn:
 		if (!new_prog)
 			return -ENOMEM;
 		env->prog = prog = new_prog;
+		/*
+		 * If may_goto is a first insn of a prog there could be a jmp
+		 * insn that points to it, hence adjust all such jmps to point
+		 * to insn after BPF_ST that inits may_goto count.
+		 * Adjustment will succeed because bpf_patch_insn_data() didn't fail.
+		 */
+		WARN_ON(adjust_jmp_off(env->prog, subprog_start, 1));
 	}
 
 	/* Since poke tab is now finalized, publish aux to tracker. */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 563877d6c2..3d2bf1d50a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1859,6 +1859,9 @@ static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return fals
 
 void __init bringup_nonboot_cpus(unsigned int max_cpus)
 {
+	if (!max_cpus)
+		return;
+
 	/* Try parallel bringup optimization if enabled */
 	if (cpuhp_bringup_cpus_parallel(max_cpus))
 		return;
@@ -2446,7 +2449,7 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
  * The caller needs to hold cpus read locked while calling this function.
  * Return:
  *   On success:
- *      Positive state number if @state is CPUHP_AP_ONLINE_DYN;
+ *      Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN;
  *      0 for all other states
  *   On failure: proper (negative) error code
  */
@@ -2469,7 +2472,7 @@ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
 	ret = cpuhp_store_callbacks(state, name, startup, teardown,
 				    multi_instance);
 
-	dynstate = state == CPUHP_AP_ONLINE_DYN;
+	dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN;
 	if (ret > 0 && dynstate) {
 		state = ret;
 		ret = 0;
@@ -2500,8 +2503,8 @@ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
 out:
 	mutex_unlock(&cpuhp_state_mutex);
 	/*
-	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
-	 * dynamically allocated state in case of success.
+	 * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN,
+	 * return the dynamically allocated state in case of success.
 	 */
 	if (!ret && dynstate)
 		return state;
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index faad00cce2..858196ff9b 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -46,8 +46,8 @@ COND_SYSCALL(io_getevents_time32);
 COND_SYSCALL(io_getevents);
 COND_SYSCALL(io_pgetevents_time32);
 COND_SYSCALL(io_pgetevents);
-COND_SYSCALL_COMPAT(io_pgetevents_time32);
 COND_SYSCALL_COMPAT(io_pgetevents);
+COND_SYSCALL_COMPAT(io_pgetevents_time64);
 COND_SYSCALL(io_uring_setup);
 COND_SYSCALL(io_uring_enter);
 COND_SYSCALL(io_uring_register);