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

Pull networking updates from David Miller:
 "Here is what we have this merge window:

   1) Support SW steering for mlx5 Connect-X6Dx, from Yevgeny Kliteynik.

   2) Add RSS multi group support to octeontx2-pf driver, from Geetha
      Sowjanya.

   3) Add support for KS8851 PHY. From Marek Vasut.

   4) Add support for GarfieldPeak bluetooth controller from Kiran K.

   5) Add support for half-duplex tcan4x5x can controllers.

   6) Add batch skb rx processing to bcrm63xx_enet, from Sieng Piaw
      Liew.

   7) Rework RX port offload infrastructure, particularly wrt, UDP
      tunneling, from Jakub Kicinski.

   8) Add BCM72116 PHY support, from Florian Fainelli.

   9) Remove Dsa specific notifiers, they are unnecessary. From Vladimir
      Oltean.

  10) Add support for picosecond rx delay in dwmac-meson8b chips. From
      Martin Blumenstingl.

  11) Support TSO on xfrm interfaces from Eyal Birger.

  12) Add support for MP_PRIO to mptcp stack, from Geliang Tang.

  13) Support BCM4908 integrated switch, from Rafał Miłecki.

  14) Support for directly accessing kernel module variables via module
      BTF info, from Andrii Naryiko.

  15) Add DASH (esktop and mobile Architecture for System Hardware)
      support to r8169 driver, from Heiner Kallweit.

  16) Add rx vlan filtering to dpaa2-eth, from Ionut-robert Aron.

  17) Add support for 100 base0x SFP devices, from Bjarni Jonasson.

  18) Support link aggregation in DSA, from Tobias Waldekranz.

  19) Support for bitwidse atomics in bpf, from Brendan Jackman.

  20) SmartEEE support in at803x driver, from Russell King.

  21) Add support for flow based tunneling to GTP, from Pravin B Shelar.

  22) Allow arbitrary number of interconnrcts in ipa, from Alex Elder.

  23) TLS RX offload for bonding, from Tariq Toukan.

  24) RX decap offklload support in mac80211, from Felix Fietkou.

  25) devlink health saupport in octeontx2-af, from George Cherian.

  26) Add TTL attr to SCM_TIMESTAMP_OPT_STATS, from Yousuk Seung

  27) Delegated actionss support in mptcp, from Paolo Abeni.

  28) Support receive timestamping when doin zerocopy tcp receive. From
      Arjun Ray.

  29) HTB offload support for mlx5, from Maxim Mikityanskiy.

  30) UDP GRO forwarding, from Maxim Mikityanskiy.

  31) TAPRIO offloading in dsa hellcreek driver, from Kurt Kanzenbach.

  32) Weighted random twos choice algorithm for ipvs, from Darby Payne.

  33) Fix netdev registration deadlock, from Johannes Berg.

  34) Various conversions to new tasklet api, from EmilRenner Berthing.

  35) Bulk skb allocations in veth, from Lorenzo Bianconi.

  36) New ethtool interface for lane setting, from Danielle Ratson.

  37) Offload failiure notifications for routes, from Amit Cohen.

  38) BCM4908 support, from Rafał Miłecki.

  39) Support several new iwlwifi chips, from Ihab Zhaika.

  40) Flow drector support for ipv6 in i40e, from Przemyslaw Patynowski.

  41) Support for mhi prrotocols, from Loic Poulain.

  42) Optimize bpf program stats.

  43) Implement RFC6056, for better port randomization, from Eric
      Dumazet.

  44) hsr tag offloading support from George McCollister.

  45) Netpoll support in qede, from Bhaskar Upadhaya.

  46) 2005/400g speed support in bonding 3ad mode, from Nikolay
      Aleksandrov.

  47) Netlink event support in mptcp, from Florian Westphal.

  48) Better skbuff caching, from Alexander Lobakin.

  49) MRP (Media Redundancy Protocol) offloading in DSA and a few
      drivers, from Horatiu Vultur.

  50) mqprio saupport in mvneta, from Maxime Chevallier.

  51) Remove of_phy_attach, no longer needed, from Florian Fainelli"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1766 commits)
  octeontx2-pf: Fix otx2_get_fecparam()
  cteontx2-pf: cn10k: Prevent harmless double shift bugs
  net: stmmac: Add PCI bus info to ethtool driver query output
  ptp: ptp_clockmatrix: clean-up - parenthesis around a == b are unnecessary
  ptp: ptp_clockmatrix: Simplify code - remove unnecessary `err` variable.
  ptp: ptp_clockmatrix: Coding style - tighten vertical spacing.
  ptp: ptp_clockmatrix: Clean-up dev_*() messages.
  ptp: ptp_clockmatrix: Remove unused header declarations.
  ptp: ptp_clockmatrix: Add alignment of 1 PPS to idtcm_perout_enable.
  ptp: ptp_clockmatrix: Add wait_for_sys_apll_dpll_lock.
  net: stmmac: dwmac-sun8i: Add a shutdown callback
  net: stmmac: dwmac-sun8i: Minor probe function cleanup
  net: stmmac: dwmac-sun8i: Use reset_control_reset
  net: stmmac: dwmac-sun8i: Remove unnecessary PHY power check
  net: stmmac: dwmac-sun8i: Return void from PHY unpower
  r8169: use macro pm_ptr
  net: mdio: Remove of_phy_attach()
  net: mscc: ocelot: select PACKING in the Kconfig
  net: re-solve some conflicts after net -> net-next merge
  net: dsa: tag_rtl4_a: Support also egress tags
  ...

1 files changed, 266 insertions, 1 deletions

diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c
index 175b7b42bfc4..b68cb5d6d6eb 100644
--- a/kernel/bpf/task_iter.c
+++ b/kernel/bpf/task_iter.c
@@ -286,9 +286,248 @@ static const struct seq_operations task_file_seq_ops = {
 	.show	= task_file_seq_show,
 };
 
+struct bpf_iter_seq_task_vma_info {
+	/* The first field must be struct bpf_iter_seq_task_common.
+	 * this is assumed by {init, fini}_seq_pidns() callback functions.
+	 */
+	struct bpf_iter_seq_task_common common;
+	struct task_struct *task;
+	struct vm_area_struct *vma;
+	u32 tid;
+	unsigned long prev_vm_start;
+	unsigned long prev_vm_end;
+};
+
+enum bpf_task_vma_iter_find_op {
+	task_vma_iter_first_vma,   /* use mm->mmap */
+	task_vma_iter_next_vma,    /* use curr_vma->vm_next */
+	task_vma_iter_find_vma,    /* use find_vma() to find next vma */
+};
+
+static struct vm_area_struct *
+task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
+{
+	struct pid_namespace *ns = info->common.ns;
+	enum bpf_task_vma_iter_find_op op;
+	struct vm_area_struct *curr_vma;
+	struct task_struct *curr_task;
+	u32 curr_tid = info->tid;
+
+	/* If this function returns a non-NULL vma, it holds a reference to
+	 * the task_struct, and holds read lock on vma->mm->mmap_lock.
+	 * If this function returns NULL, it does not hold any reference or
+	 * lock.
+	 */
+	if (info->task) {
+		curr_task = info->task;
+		curr_vma = info->vma;
+		/* In case of lock contention, drop mmap_lock to unblock
+		 * the writer.
+		 *
+		 * After relock, call find(mm, prev_vm_end - 1) to find
+		 * new vma to process.
+		 *
+		 *   +------+------+-----------+
+		 *   | VMA1 | VMA2 | VMA3      |
+		 *   +------+------+-----------+
+		 *   |      |      |           |
+		 *  4k     8k     16k         400k
+		 *
+		 * For example, curr_vma == VMA2. Before unlock, we set
+		 *
+		 *    prev_vm_start = 8k
+		 *    prev_vm_end   = 16k
+		 *
+		 * There are a few cases:
+		 *
+		 * 1) VMA2 is freed, but VMA3 exists.
+		 *
+		 *    find_vma() will return VMA3, just process VMA3.
+		 *
+		 * 2) VMA2 still exists.
+		 *
+		 *    find_vma() will return VMA2, process VMA2->next.
+		 *
+		 * 3) no more vma in this mm.
+		 *
+		 *    Process the next task.
+		 *
+		 * 4) find_vma() returns a different vma, VMA2'.
+		 *
+		 *    4.1) If VMA2 covers same range as VMA2', skip VMA2',
+		 *         because we already covered the range;
+		 *    4.2) VMA2 and VMA2' covers different ranges, process
+		 *         VMA2'.
+		 */
+		if (mmap_lock_is_contended(curr_task->mm)) {
+			info->prev_vm_start = curr_vma->vm_start;
+			info->prev_vm_end = curr_vma->vm_end;
+			op = task_vma_iter_find_vma;
+			mmap_read_unlock(curr_task->mm);
+			if (mmap_read_lock_killable(curr_task->mm))
+				goto finish;
+		} else {
+			op = task_vma_iter_next_vma;
+		}
+	} else {
+again:
+		curr_task = task_seq_get_next(ns, &curr_tid, true);
+		if (!curr_task) {
+			info->tid = curr_tid + 1;
+			goto finish;
+		}
+
+		if (curr_tid != info->tid) {
+			info->tid = curr_tid;
+			/* new task, process the first vma */
+			op = task_vma_iter_first_vma;
+		} else {
+			/* Found the same tid, which means the user space
+			 * finished data in previous buffer and read more.
+			 * We dropped mmap_lock before returning to user
+			 * space, so it is necessary to use find_vma() to
+			 * find the next vma to process.
+			 */
+			op = task_vma_iter_find_vma;
+		}
+
+		if (!curr_task->mm)
+			goto next_task;
+
+		if (mmap_read_lock_killable(curr_task->mm))
+			goto finish;
+	}
+
+	switch (op) {
+	case task_vma_iter_first_vma:
+		curr_vma = curr_task->mm->mmap;
+		break;
+	case task_vma_iter_next_vma:
+		curr_vma = curr_vma->vm_next;
+		break;
+	case task_vma_iter_find_vma:
+		/* We dropped mmap_lock so it is necessary to use find_vma
+		 * to find the next vma. This is similar to the  mechanism
+		 * in show_smaps_rollup().
+		 */
+		curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
+		/* case 1) and 4.2) above just use curr_vma */
+
+		/* check for case 2) or case 4.1) above */
+		if (curr_vma &&
+		    curr_vma->vm_start == info->prev_vm_start &&
+		    curr_vma->vm_end == info->prev_vm_end)
+			curr_vma = curr_vma->vm_next;
+		break;
+	}
+	if (!curr_vma) {
+		/* case 3) above, or case 2) 4.1) with vma->next == NULL */
+		mmap_read_unlock(curr_task->mm);
+		goto next_task;
+	}
+	info->task = curr_task;
+	info->vma = curr_vma;
+	return curr_vma;
+
+next_task:
+	put_task_struct(curr_task);
+	info->task = NULL;
+	curr_tid++;
+	goto again;
+
+finish:
+	if (curr_task)
+		put_task_struct(curr_task);
+	info->task = NULL;
+	info->vma = NULL;
+	return NULL;
+}
+
+static void *task_vma_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+	struct vm_area_struct *vma;
+
+	vma = task_vma_seq_get_next(info);
+	if (vma && *pos == 0)
+		++*pos;
+
+	return vma;
+}
+
+static void *task_vma_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+
+	++*pos;
+	return task_vma_seq_get_next(info);
+}
+
+struct bpf_iter__task_vma {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct task_struct *, task);
+	__bpf_md_ptr(struct vm_area_struct *, vma);
+};
+
+DEFINE_BPF_ITER_FUNC(task_vma, struct bpf_iter_meta *meta,
+		     struct task_struct *task, struct vm_area_struct *vma)
+
+static int __task_vma_seq_show(struct seq_file *seq, bool in_stop)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+	struct bpf_iter__task_vma ctx;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, in_stop);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.task = info->task;
+	ctx.vma = info->vma;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int task_vma_seq_show(struct seq_file *seq, void *v)
+{
+	return __task_vma_seq_show(seq, false);
+}
+
+static void task_vma_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_seq_task_vma_info *info = seq->private;
+
+	if (!v) {
+		(void)__task_vma_seq_show(seq, true);
+	} else {
+		/* info->vma has not been seen by the BPF program. If the
+		 * user space reads more, task_vma_seq_get_next should
+		 * return this vma again. Set prev_vm_start to ~0UL,
+		 * so that we don't skip the vma returned by the next
+		 * find_vma() (case task_vma_iter_find_vma in
+		 * task_vma_seq_get_next()).
+		 */
+		info->prev_vm_start = ~0UL;
+		info->prev_vm_end = info->vma->vm_end;
+		mmap_read_unlock(info->task->mm);
+		put_task_struct(info->task);
+		info->task = NULL;
+	}
+}
+
+static const struct seq_operations task_vma_seq_ops = {
+	.start	= task_vma_seq_start,
+	.next	= task_vma_seq_next,
+	.stop	= task_vma_seq_stop,
+	.show	= task_vma_seq_show,
+};
+
 BTF_ID_LIST(btf_task_file_ids)
 BTF_ID(struct, task_struct)
 BTF_ID(struct, file)
+BTF_ID(struct, vm_area_struct)
 
 static const struct bpf_iter_seq_info task_seq_info = {
 	.seq_ops		= &task_seq_ops,
@@ -328,6 +567,26 @@ static struct bpf_iter_reg task_file_reg_info = {
 	.seq_info		= &task_file_seq_info,
 };
 
+static const struct bpf_iter_seq_info task_vma_seq_info = {
+	.seq_ops		= &task_vma_seq_ops,
+	.init_seq_private	= init_seq_pidns,
+	.fini_seq_private	= fini_seq_pidns,
+	.seq_priv_size		= sizeof(struct bpf_iter_seq_task_vma_info),
+};
+
+static struct bpf_iter_reg task_vma_reg_info = {
+	.target			= "task_vma",
+	.feature		= BPF_ITER_RESCHED,
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__task_vma, task),
+		  PTR_TO_BTF_ID_OR_NULL },
+		{ offsetof(struct bpf_iter__task_vma, vma),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+	.seq_info		= &task_vma_seq_info,
+};
+
 static int __init task_iter_init(void)
 {
 	int ret;
@@ -339,6 +598,12 @@ static int __init task_iter_init(void)
 
 	task_file_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
 	task_file_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[1];
-	return bpf_iter_reg_target(&task_file_reg_info);
+	ret =  bpf_iter_reg_target(&task_file_reg_info);
+	if (ret)
+		return ret;
+
+	task_vma_reg_info.ctx_arg_info[0].btf_id = btf_task_file_ids[0];
+	task_vma_reg_info.ctx_arg_info[1].btf_id = btf_task_file_ids[2];
+	return bpf_iter_reg_target(&task_vma_reg_info);
 }
 late_initcall(task_iter_init);