Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts.

Adjacent changes:

kernel/bpf/verifier.c
  829955981c55 ("bpf: Fix verifier log for async callback return values")
  a923819fb2c5 ("bpf: Treat first argument as return value for bpf_throw")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 49 insertions, 27 deletions

diff --git a/kernel/bpf/mprog.c b/kernel/bpf/mprog.c
index 007d98c799e2..1394168062e8 100644
--- a/kernel/bpf/mprog.c
+++ b/kernel/bpf/mprog.c
@@ -401,14 +401,16 @@ int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
 	struct bpf_mprog_cp *cp;
 	struct bpf_prog *prog;
 	const u32 flags = 0;
+	u32 id, count = 0;
+	u64 revision = 1;
 	int i, ret = 0;
-	u32 id, count;
-	u64 revision;
 
 	if (attr->query.query_flags || attr->query.attach_flags)
 		return -EINVAL;
-	revision = bpf_mprog_revision(entry);
-	count = bpf_mprog_total(entry);
+	if (entry) {
+		revision = bpf_mprog_revision(entry);
+		count = bpf_mprog_total(entry);
+	}
 	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)))
 		return -EFAULT;
 	if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision)))
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 85c1d908f70f..fc088fd4874f 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3800,7 +3800,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
-	u32 mask;
 	int ret;
 
 	if (CHECK_ATTR(BPF_PROG_ATTACH))
@@ -3809,10 +3808,16 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 	ptype = attach_type_to_prog_type(attr->attach_type);
 	if (ptype == BPF_PROG_TYPE_UNSPEC)
 		return -EINVAL;
-	mask = bpf_mprog_supported(ptype) ?
-	       BPF_F_ATTACH_MASK_MPROG : BPF_F_ATTACH_MASK_BASE;
-	if (attr->attach_flags & ~mask)
-		return -EINVAL;
+	if (bpf_mprog_supported(ptype)) {
+		if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
+			return -EINVAL;
+	} else {
+		if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
+			return -EINVAL;
+		if (attr->relative_fd ||
+		    attr->expected_revision)
+			return -EINVAL;
+	}
 
 	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
 	if (IS_ERR(prog))
@@ -3882,6 +3887,10 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 			if (IS_ERR(prog))
 				return PTR_ERR(prog);
 		}
+	} else if (attr->attach_flags ||
+		   attr->relative_fd ||
+		   attr->expected_revision) {
+		return -EINVAL;
 	}
 
 	switch (ptype) {
@@ -3917,7 +3926,7 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 	return ret;
 }
 
-#define BPF_PROG_QUERY_LAST_FIELD query.link_attach_flags
+#define BPF_PROG_QUERY_LAST_FIELD query.revision
 
 static int bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
index 13f0b5dc8262..1338a13a8b64 100644
--- a/kernel/bpf/tcx.c
+++ b/kernel/bpf/tcx.c
@@ -123,7 +123,6 @@ int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
 {
 	bool ingress = attr->query.attach_type == BPF_TCX_INGRESS;
 	struct net *net = current->nsproxy->net_ns;
-	struct bpf_mprog_entry *entry;
 	struct net_device *dev;
 	int ret;
 
@@ -133,12 +132,7 @@ int tcx_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr)
 		ret = -ENODEV;
 		goto out;
 	}
-	entry = tcx_entry_fetch(dev, ingress);
-	if (!entry) {
-		ret = -ENOENT;
-		goto out;
-	}
-	ret = bpf_mprog_query(attr, uattr, entry);
+	ret = bpf_mprog_query(attr, uattr, tcx_entry_fetch(dev, ingress));
 out:
 	rtnl_unlock();
 	return ret;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index c8dae2fde115..e59d6c2c6bf4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -14727,7 +14727,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 	struct tnum enforce_attach_type_range = tnum_unknown;
 	const struct bpf_prog *prog = env->prog;
 	struct bpf_reg_state *reg;
-	struct tnum range = tnum_range(0, 1);
+	struct tnum range = tnum_range(0, 1), const_0 = tnum_const(0);
 	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
 	int err;
 	struct bpf_func_state *frame = env->cur_state->frame[0];
@@ -14775,8 +14775,8 @@ static int check_return_code(struct bpf_verifier_env *env, int regno)
 			return -EINVAL;
 		}
 
-		if (!tnum_in(tnum_const(0), reg->var_off)) {
-			verbose_invalid_scalar(env, reg, &range, "async callback", "R0");
+		if (!tnum_in(const_0, reg->var_off)) {
+			verbose_invalid_scalar(env, reg, &const_0, "async callback", "R0");
 			return -EINVAL;
 		}
 		return 0;
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 87e9f7e2bdc0..0f12e0a97e43 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -2647,7 +2647,7 @@ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm,
 	memory_bm_free(bm, PG_UNSAFE_KEEP);
 
 	/* Make a copy of zero_bm so it can be created in safe pages */
-	error = memory_bm_create(&tmp, GFP_ATOMIC, PG_ANY);
+	error = memory_bm_create(&tmp, GFP_ATOMIC, PG_SAFE);
 	if (error)
 		goto Free;
 
@@ -2660,7 +2660,7 @@ static int prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm,
 		goto Free;
 
 	duplicate_memory_bitmap(zero_bm, &tmp);
-	memory_bm_free(&tmp, PG_UNSAFE_KEEP);
+	memory_bm_free(&tmp, PG_UNSAFE_CLEAR);
 	/* At this point zero_bm is in safe pages and it can be used for restoring. */
 
 	if (nr_highmem > 0) {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 7e0b4dd02398..0b3af1529778 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -3740,12 +3740,18 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre
 
 	seq = prb_next_seq(prb);
 
+	/* Flush the consoles so that records up to @seq are printed. */
+	console_lock();
+	console_unlock();
+
 	for (;;) {
 		diff = 0;
 
 		/*
 		 * Hold the console_lock to guarantee safe access to
-		 * console->seq.
+		 * console->seq. Releasing console_lock flushes more
+		 * records in case @seq is still not printed on all
+		 * usable consoles.
 		 */
 		console_lock();
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4492608b7d7f..458d359f5991 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	 * Except when the rq is capped by uclamp_max.
 	 */
 	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
-	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
+	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+	    !sg_policy->need_freq_update) {
 		next_f = sg_policy->next_freq;
 
 		/* Restore cached freq as next_freq has changed */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cb225921bbca..ef7490c4b8b4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -664,6 +664,10 @@ void avg_vruntime_update(struct cfs_rq *cfs_rq, s64 delta)
 	cfs_rq->avg_vruntime -= cfs_rq->avg_load * delta;
 }
 
+/*
+ * Specifically: avg_runtime() + 0 must result in entity_eligible() := true
+ * For this to be so, the result of this function must have a left bias.
+ */
 u64 avg_vruntime(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
@@ -677,8 +681,12 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
 		load += weight;
 	}
 
-	if (load)
+	if (load) {
+		/* sign flips effective floor / ceil */
+		if (avg < 0)
+			avg -= (load - 1);
 		avg = div_s64(avg, load);
+	}
 
 	return cfs_rq->min_vruntime + avg;
 }
@@ -4919,10 +4927,12 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
 static void
 place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	u64 vslice = calc_delta_fair(se->slice, se);
-	u64 vruntime = avg_vruntime(cfs_rq);
+	u64 vslice, vruntime = avg_vruntime(cfs_rq);
 	s64 lag = 0;
 
+	se->slice = sysctl_sched_base_slice;
+	vslice = calc_delta_fair(se->slice, se);
+
 	/*
 	 * Due to how V is constructed as the weighted average of entities,
 	 * adding tasks with positive lag, or removing tasks with negative lag