Commit 2865ba82 authored by David S. Miller's avatar David S. Miller
Browse files

Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf 



Daniel Borkmann says:

====================
pull-request: bpf 2021-09-14

The following pull-request contains BPF updates for your *net* tree.

We've added 7 non-merge commits during the last 13 day(s) which contain
a total of 18 files changed, 334 insertions(+), 193 deletions(-).

The main changes are:

1) Fix mmap_lock lockdep splat in BPF stack map's build_id lookup, from Yonghong Song.

2) Fix BPF cgroup v2 program bypass upon net_cls/prio activation, from Daniel Borkmann.

3) Fix kvcalloc() BTF line info splat on oversized allocation attempts, from Bixuan Cui.

4) Fix BPF selftest build of task_pt_regs test for arm64/s390, from Jean-Philippe Brucker.

5) Fix BPF's disasm.{c,h} to dual-license so that it is aligned with bpftool given the former
   is a build dependency for the latter, from Daniel Borkmann with ACKs from contributors.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 550ac9c1 43d2b88c

include/linux/cgroup-defs.h

+27 −80
Original line number Diff line number Diff line
@@ -752,107 +752,54 @@ static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} 
 * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains

 * per-socket cgroup information except for memcg association.

 *

 * On legacy hierarchies, net_prio and net_cls controllers directly set

 * attributes on each sock which can then be tested by the network layer.

 * On the default hierarchy, each sock is associated with the cgroup it was

 * created in and the networking layer can match the cgroup directly.

 *

 * To avoid carrying all three cgroup related fields separately in sock,

 * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.

 * On boot, sock_cgroup_data records the cgroup that the sock was created

 * in so that cgroup2 matches can be made; however, once either net_prio or

 * net_cls starts being used, the area is overridden to carry prioidx and/or

 * classid.  The two modes are distinguished by whether the lowest bit is

 * set.  Clear bit indicates cgroup pointer while set bit prioidx and

 * classid.

 *

 * While userland may start using net_prio or net_cls at any time, once

 * either is used, cgroup2 matching no longer works.  There is no reason to

 * mix the two and this is in line with how legacy and v2 compatibility is

 * handled.  On mode switch, cgroup references which are already being

 * pointed to by socks may be leaked.  While this can be remedied by adding

 * synchronization around sock_cgroup_data, given that the number of leaked

 * cgroups is bound and highly unlikely to be high, this seems to be the

 * better trade-off.

 * On legacy hierarchies, net_prio and net_cls controllers directly

 * set attributes on each sock which can then be tested by the network

 * layer. On the default hierarchy, each sock is associated with the

 * cgroup it was created in and the networking layer can match the

 * cgroup directly.

 */

struct sock_cgroup_data {

	union {

#ifdef __LITTLE_ENDIAN

		struct {

			u8	is_data : 1;

			u8	no_refcnt : 1;

			u8	unused : 6;

			u8	padding;

			u16	prioidx;

			u32	classid;

		} __packed;

#else

		struct {

			u32	classid;

			u16	prioidx;

			u8	padding;

			u8	unused : 6;

			u8	no_refcnt : 1;

			u8	is_data : 1;

		} __packed;

	struct cgroup	*cgroup; /* v2 */

#ifdef CONFIG_CGROUP_NET_CLASSID

	u32		classid; /* v1 */

#endif

#ifdef CONFIG_CGROUP_NET_PRIO

	u16		prioidx; /* v1 */

#endif

		u64		val;

	};

};



/*

 * There's a theoretical window where the following accessors race with

 * updaters and return part of the previous pointer as the prioidx or

 * classid.  Such races are short-lived and the result isn't critical.

 */

static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)

{

	/* fallback to 1 which is always the ID of the root cgroup */

	return (skcd->is_data & 1) ? skcd->prioidx : 1;

#ifdef CONFIG_CGROUP_NET_PRIO

	return READ_ONCE(skcd->prioidx);

#else

	return 1;

#endif

}



static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)

{

	/* fallback to 0 which is the unconfigured default classid */

	return (skcd->is_data & 1) ? skcd->classid : 0;

#ifdef CONFIG_CGROUP_NET_CLASSID

	return READ_ONCE(skcd->classid);

#else

	return 0;

#endif

}



/*

 * If invoked concurrently, the updaters may clobber each other.  The

 * caller is responsible for synchronization.

 */

static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,

					   u16 prioidx)

{

	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};



	if (sock_cgroup_prioidx(&skcd_buf) == prioidx)

		return;



	if (!(skcd_buf.is_data & 1)) {

		skcd_buf.val = 0;

		skcd_buf.is_data = 1;

	}



	skcd_buf.prioidx = prioidx;

	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */

#ifdef CONFIG_CGROUP_NET_PRIO

	WRITE_ONCE(skcd->prioidx, prioidx);

#endif

}



static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,

					   u32 classid)

{

	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};



	if (sock_cgroup_classid(&skcd_buf) == classid)

		return;



	if (!(skcd_buf.is_data & 1)) {

		skcd_buf.val = 0;

		skcd_buf.is_data = 1;

	}



	skcd_buf.classid = classid;

	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */

#ifdef CONFIG_CGROUP_NET_CLASSID

	WRITE_ONCE(skcd->classid, classid);

#endif

}



#else	/* CONFIG_SOCK_CGROUP_DATA */

include/linux/cgroup.h

+1 −21
Original line number Diff line number Diff line
@@ -829,33 +829,13 @@ static inline void cgroup_account_cputime_field(struct task_struct *task, 
 */

#ifdef CONFIG_SOCK_CGROUP_DATA



#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)

extern spinlock_t cgroup_sk_update_lock;

#endif



void cgroup_sk_alloc_disable(void);

void cgroup_sk_alloc(struct sock_cgroup_data *skcd);

void cgroup_sk_clone(struct sock_cgroup_data *skcd);

void cgroup_sk_free(struct sock_cgroup_data *skcd);



static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)

{

#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)

	unsigned long v;



	/*

	 * @skcd->val is 64bit but the following is safe on 32bit too as we

	 * just need the lower ulong to be written and read atomically.

	 */

	v = READ_ONCE(skcd->val);



	if (v & 3)

		return &cgrp_dfl_root.cgrp;



	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;

#else

	return (struct cgroup *)(unsigned long)skcd->val;

#endif

	return skcd->cgroup;

}



#else	/* CONFIG_CGROUP_DATA */

include/linux/mmap_lock.h

+0 −9
Original line number Diff line number Diff line
@@ -144,15 +144,6 @@ static inline void mmap_read_unlock(struct mm_struct *mm) 
	__mmap_lock_trace_released(mm, false);

}



static inline bool mmap_read_trylock_non_owner(struct mm_struct *mm)

{

	if (mmap_read_trylock(mm)) {

		rwsem_release(&mm->mmap_lock.dep_map, _RET_IP_);

		return true;

	}

	return false;

}



static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)

{

	up_read_non_owner(&mm->mmap_lock);

kernel/bpf/disasm.c

+1 −1
Original line number Diff line number Diff line 
// SPDX-License-Identifier: GPL-2.0-only

// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com

 * Copyright (c) 2016 Facebook

 */

kernel/bpf/disasm.h

+1 −1
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: GPL-2.0-only */

/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com

 * Copyright (c) 2016 Facebook

 */