Merge keystone/android12-5.10-keystone-qcom-release.81+ (2c95d7c) into msm-5.10

* refs/heads/tmp-2c95d7c:
  Revert "BACKPORT: FROMLIST: scsi: core: Reserve one tag for the UFS driver"
  UPSTREAM: binder: Add invalid handle info in user error log
  UPSTREAM: ARM: fix Thumb2 regression with Spectre BHB
  UPSTREAM: ARM: Spectre-BHB: provide empty stub for non-config
  UPSTREAM: ARM: fix build warning in proc-v7-bugs.c
  UPSTREAM: ARM: Do not use NOCROSSREFS directive with ld.lld
  UPSTREAM: ARM: fix co-processor register typo
  UPSTREAM: ARM: fix build error when BPF_SYSCALL is disabled
  UPSTREAM: ARM: include unprivileged BPF status in Spectre V2 reporting
  UPSTREAM: ARM: Spectre-BHB workaround
  UPSTREAM: ARM: use LOADADDR() to get load address of sections
  UPSTREAM: ARM: early traps initialisation
  UPSTREAM: ARM: report Spectre v2 status through sysfs
  UPSTREAM: x86/speculation: Warn about eIBRS + LFENCE + Unprivileged eBPF + SMT
  UPSTREAM: x86/speculation: Warn about Spectre v2 LFENCE mitigation
  UPSTREAM: x86/speculation: Update link to AMD speculation whitepaper
  UPSTREAM: x86/speculation: Use generic retpoline by default on AMD
  UPSTREAM: x86/speculation: Include unprivileged eBPF status in Spectre v2 mitigation reporting
  UPSTREAM: Documentation/hw-vuln: Update spectre doc
  UPSTREAM: x86/speculation: Add eIBRS + Retpoline options
  UPSTREAM: x86/speculation: Rename RETPOLINE_AMD to RETPOLINE_LFENCE
  UPSTREAM: x86,bugs: Unconditionally allow spectre_v2=retpoline,amd
  UPSTREAM: bpf: Add kconfig knob for disabling unpriv bpf by default
  ANDROID: dm-bow: Protect Ranges fetched and erased from the RB tree
  ANDROID: mm: page_pinner: fix build warning
  ANDROID: fault: Add vendor hook for TLB conflict
  BACKPORT: sched: Fix yet more sched_fork() races
  ANDROID: mm/slub: Fix Kasan issue with for_each_object_track
  ANDROID: dm kcopyd: Use reserved memory for the copy buffer
  ANDROID: GKI: add allowed list file for xiaomi
  ANDROID: GKI: Update symbols to symbol list
  FROMGIT: f2fs: quota: fix loop condition at f2fs_quota_sync()
  FROMGIT: f2fs: Restore rwsem lockdep support
  ANDROID: ABI: update allowed list for galaxy
  UPSTREAM: mac80211_hwsim: initialize ieee80211_tx_info at hw_scan_work
  ANDROID: GKI: remove vfs-only namespace from 2 symbols

Change-Id: I54118d206503f63d289dc825d51819e1e34540cc
Signed-off-by: Sivasri Kumar, Vanka <quic_svanka@quicinc.com>

kernel/bpf/syscall.c

@@ -52,7 +52,8 @@ static DEFINE_SPINLOCK(map_idr_lock);
 static DEFINE_IDR(link_idr);
 static DEFINE_SPINLOCK(link_idr_lock);
 
-int sysctl_unprivileged_bpf_disabled __read_mostly;
+int sysctl_unprivileged_bpf_disabled __read_mostly =
+	IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0;
 
 static const struct bpf_map_ops * const bpf_map_types[] = {
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type)

kernel/fork.c

@@ -2249,6 +2249,17 @@ static __latent_entropy struct task_struct *copy_process(
 	if (retval)
 		goto bad_fork_put_pidfd;
 
+	/*
+	 * Now that the cgroups are pinned, re-clone the parent cgroup and put
+	 * the new task on the correct runqueue. All this *before* the task
+	 * becomes visible.
+	 *
+	 * This isn't part of ->can_fork() because while the re-cloning is
+	 * cgroup specific, it unconditionally needs to place the task on a
+	 * runqueue.
+	 */
+	sched_cgroup_fork(p, args);
+
 	/*
 	 * From this point on we must avoid any synchronous user-space
 	 * communication until we take the tasklist-lock. In particular, we do
@@ -2357,7 +2368,7 @@ static __latent_entropy struct task_struct *copy_process(
 	write_unlock_irq(&tasklist_lock);
 
 	proc_fork_connector(p);
-	sched_post_fork(p, args);
+	sched_post_fork(p);
 	cgroup_post_fork(p, args);
 	perf_event_fork(p);
 

kernel/sched/core.c

@@ -880,9 +880,8 @@ int tg_nop(struct task_group *tg, void *data)
 }
 #endif
 
-static void set_load_weight(struct task_struct *p)
+static void set_load_weight(struct task_struct *p, bool update_load)
 {
-	bool update_load = !(READ_ONCE(p->state) & TASK_NEW);
 	int prio = p->static_prio - MAX_RT_PRIO;
 	struct load_weight *load = &p->se.load;
 
@@ -3485,7 +3484,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 			p->static_prio = NICE_TO_PRIO(0);
 
 		p->prio = p->normal_prio = p->static_prio;
-		set_load_weight(p);
+		set_load_weight(p, false);
 
 		/*
 		 * We don't need the reset flag anymore after the fork. It has
@@ -3504,6 +3503,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	init_entity_runnable_average(&p->se);
 	trace_android_rvh_finish_prio_fork(p);
 
+
 #ifdef CONFIG_SCHED_INFO
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
@@ -3519,18 +3519,24 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
-void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs)
+void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 {
 	unsigned long flags;
-#ifdef CONFIG_CGROUP_SCHED
-	struct task_group *tg;
-#endif
 
+	/*
+	 * Because we're not yet on the pid-hash, p->pi_lock isn't strictly
+	 * required yet, but lockdep gets upset if rules are violated.
+	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 #ifdef CONFIG_CGROUP_SCHED
-	tg = container_of(kargs->cset->subsys[cpu_cgrp_id],
-			  struct task_group, css);
-	p->sched_task_group = autogroup_task_group(p, tg);
+	if (1) {
+		struct task_group *tg;
+
+		tg = container_of(kargs->cset->subsys[cpu_cgrp_id],
+				  struct task_group, css);
+		tg = autogroup_task_group(p, tg);
+		p->sched_task_group = tg;
+	}
 #endif
 	rseq_migrate(p);
 	/*
@@ -3541,7 +3547,10 @@ void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+}
 
+void sched_post_fork(struct task_struct *p)
+{
 	uclamp_post_fork(p);
 }
 
@@ -5253,7 +5262,7 @@ void set_user_nice(struct task_struct *p, long nice)
 		put_prev_task(rq, p);
 
 	p->static_prio = NICE_TO_PRIO(nice);
-	set_load_weight(p);
+	set_load_weight(p, true);
 	old_prio = p->prio;
 	p->prio = effective_prio(p);
 
@@ -5427,7 +5436,7 @@ static void __setscheduler_params(struct task_struct *p,
 	 */
 	p->rt_priority = attr->sched_priority;
 	p->normal_prio = normal_prio(p);
-	set_load_weight(p);
+	set_load_weight(p, true);
 }
 
 /*
@@ -7570,7 +7579,7 @@ void __init sched_init(void)
 		atomic_set(&rq->nr_iowait, 0);
 	}
 
-	set_load_weight(&init_task);
+	set_load_weight(&init_task, false);
 
 	/*
 	 * The boot idle thread does lazy MMU switching as well:

kernel/sysctl.c

@@ -236,7 +236,34 @@ static int bpf_stats_handler(struct ctl_table *table, int write,
 	mutex_unlock(&bpf_stats_enabled_mutex);
 	return ret;
 }
-#endif
+
+void __weak unpriv_ebpf_notify(int new_state)
+{
+}
+
+static int bpf_unpriv_handler(struct ctl_table *table, int write,
+			      void *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret, unpriv_enable = *(int *)table->data;
+	bool locked_state = unpriv_enable == 1;
+	struct ctl_table tmp = *table;
+
+	if (write && !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	tmp.data = &unpriv_enable;
+	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
+	if (write && !ret) {
+		if (locked_state && unpriv_enable != 1)
+			return -EPERM;
+		*(int *)table->data = unpriv_enable;
+	}
+
+	unpriv_ebpf_notify(unpriv_enable);
+
+	return ret;
+}
+#endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */
 
 /*
  * /proc/sys support
@@ -2629,10 +2656,9 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_unprivileged_bpf_disabled,
 		.maxlen		= sizeof(sysctl_unprivileged_bpf_disabled),
 		.mode		= 0644,
-		/* only handle a transition from default "0" to "1" */
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ONE,
-		.extra2		= SYSCTL_ONE,
+		.proc_handler	= bpf_unpriv_handler,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &two,
 	},
 	{
 		.procname	= "bpf_stats_enabled",