This is a note to let you know that I've just added the patch titled
netfilter: nat: Revert "netfilter: nat: convert nat bysrc hash to rhashtable"
to the 4.13-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
netfilter-nat-revert-netfilter-nat-convert-nat-bysrc-hash-to-rhashtable.patch
and it can be found in the queue-4.13 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From e1bf1687740ce1a3598a1c5e452b852ff2190682 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw(a)strlen.de>
Date: Wed, 6 Sep 2017 14:39:51 +0200
Subject: netfilter: nat: Revert "netfilter: nat: convert nat bysrc hash to rhashtable"
From: Florian Westphal <fw(a)strlen.de>
commit e1bf1687740ce1a3598a1c5e452b852ff2190682 upstream.
This reverts commit 870190a9ec9075205c0fa795a09fa931694a3ff1.
It was not a good idea. The custom hash table was a much better
fit for this purpose.
A fast lookup is not essential, in fact for most cases there is no lookup
at all because original tuple is not taken and can be used as-is.
What needs to be fast is insertion and deletion.
rhlist removal however requires a rhlist walk.
We can have thousands of entries in such a list if source port/addresses
are reused for multiple flows, if this happens removal requests are so
expensive that deletions of a few thousand flows can take several
seconds(!).
The advantages that we got from rhashtable are:
1) table auto-sizing
2) multiple locks
1) would be nice to have, but it is not essential as we have at
most one lookup per new flow, so even a million flows in the bysource
table are not a problem compared to current deletion cost.
2) is easy to add to custom hash table.
I tried to add hlist_node to rhlist to speed up rhltable_remove but this
isn't doable without changing semantics. rhltable_remove_fast will
check that the to-be-deleted object is part of the table and that
requires a list walk that we want to avoid.
Furthermore, using hlist_node increases size of struct rhlist_head, which
in turn increases nf_conn size.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=196821
Reported-by: Ivan Babrou <ibobrik(a)gmail.com>
Signed-off-by: Florian Westphal <fw(a)strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
include/net/netfilter/nf_conntrack.h | 3
include/net/netfilter/nf_nat.h | 1
net/netfilter/nf_nat_core.c | 128 ++++++++++++++---------------------
3 files changed, 53 insertions(+), 79 deletions(-)
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -17,7 +17,6 @@
#include <linux/bitops.h>
#include <linux/compiler.h>
#include <linux/atomic.h>
-#include <linux/rhashtable.h>
#include <linux/netfilter/nf_conntrack_tcp.h>
#include <linux/netfilter/nf_conntrack_dccp.h>
@@ -83,7 +82,7 @@ struct nf_conn {
possible_net_t ct_net;
#if IS_ENABLED(CONFIG_NF_NAT)
- struct rhlist_head nat_bysource;
+ struct hlist_node nat_bysource;
#endif
/* all members below initialized via memset */
u8 __nfct_init_offset[0];
--- a/include/net/netfilter/nf_nat.h
+++ b/include/net/netfilter/nf_nat.h
@@ -1,6 +1,5 @@
#ifndef _NF_NAT_H
#define _NF_NAT_H
-#include <linux/rhashtable.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter/nf_nat.h>
#include <net/netfilter/nf_conntrack_tuple.h>
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -30,19 +30,17 @@
#include <net/netfilter/nf_conntrack_zones.h>
#include <linux/netfilter/nf_nat.h>
+static DEFINE_SPINLOCK(nf_nat_lock);
+
static DEFINE_MUTEX(nf_nat_proto_mutex);
static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO]
__read_mostly;
static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO]
__read_mostly;
-struct nf_nat_conn_key {
- const struct net *net;
- const struct nf_conntrack_tuple *tuple;
- const struct nf_conntrack_zone *zone;
-};
-
-static struct rhltable nf_nat_bysource_table;
+static struct hlist_head *nf_nat_bysource __read_mostly;
+static unsigned int nf_nat_htable_size __read_mostly;
+static unsigned int nf_nat_hash_rnd __read_mostly;
inline const struct nf_nat_l3proto *
__nf_nat_l3proto_find(u8 family)
@@ -118,17 +116,19 @@ int nf_xfrm_me_harder(struct net *net, s
EXPORT_SYMBOL(nf_xfrm_me_harder);
#endif /* CONFIG_XFRM */
-static u32 nf_nat_bysource_hash(const void *data, u32 len, u32 seed)
+/* We keep an extra hash for each conntrack, for fast searching. */
+static unsigned int
+hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple)
{
- const struct nf_conntrack_tuple *t;
- const struct nf_conn *ct = data;
+ unsigned int hash;
+
+ get_random_once(&nf_nat_hash_rnd, sizeof(nf_nat_hash_rnd));
- t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
/* Original src, to ensure we map it consistently if poss. */
+ hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32),
+ tuple->dst.protonum ^ nf_nat_hash_rnd ^ net_hash_mix(n));
- seed ^= net_hash_mix(nf_ct_net(ct));
- return jhash2((const u32 *)&t->src, sizeof(t->src) / sizeof(u32),
- t->dst.protonum ^ seed);
+ return reciprocal_scale(hash, nf_nat_htable_size);
}
/* Is this tuple already taken? (not by us) */
@@ -184,28 +184,6 @@ same_src(const struct nf_conn *ct,
t->src.u.all == tuple->src.u.all);
}
-static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg,
- const void *obj)
-{
- const struct nf_nat_conn_key *key = arg->key;
- const struct nf_conn *ct = obj;
-
- if (!same_src(ct, key->tuple) ||
- !net_eq(nf_ct_net(ct), key->net) ||
- !nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL))
- return 1;
-
- return 0;
-}
-
-static struct rhashtable_params nf_nat_bysource_params = {
- .head_offset = offsetof(struct nf_conn, nat_bysource),
- .obj_hashfn = nf_nat_bysource_hash,
- .obj_cmpfn = nf_nat_bysource_cmp,
- .nelem_hint = 256,
- .min_size = 1024,
-};
-
/* Only called for SRC manip */
static int
find_appropriate_src(struct net *net,
@@ -216,26 +194,22 @@ find_appropriate_src(struct net *net,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
+ unsigned int h = hash_by_src(net, tuple);
const struct nf_conn *ct;
- struct nf_nat_conn_key key = {
- .net = net,
- .tuple = tuple,
- .zone = zone
- };
- struct rhlist_head *hl, *h;
-
- hl = rhltable_lookup(&nf_nat_bysource_table, &key,
- nf_nat_bysource_params);
- rhl_for_each_entry_rcu(ct, h, hl, nat_bysource) {
- nf_ct_invert_tuplepr(result,
- &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
- result->dst = tuple->dst;
+ hlist_for_each_entry_rcu(ct, &nf_nat_bysource[h], nat_bysource) {
+ if (same_src(ct, tuple) &&
+ net_eq(net, nf_ct_net(ct)) &&
+ nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) {
+ /* Copy source part from reply tuple. */
+ nf_ct_invert_tuplepr(result,
+ &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
+ result->dst = tuple->dst;
- if (in_range(l3proto, l4proto, result, range))
- return 1;
+ if (in_range(l3proto, l4proto, result, range))
+ return 1;
+ }
}
-
return 0;
}
@@ -408,6 +382,7 @@ nf_nat_setup_info(struct nf_conn *ct,
const struct nf_nat_range *range,
enum nf_nat_manip_type maniptype)
{
+ struct net *net = nf_ct_net(ct);
struct nf_conntrack_tuple curr_tuple, new_tuple;
/* Can't setup nat info for confirmed ct. */
@@ -447,19 +422,14 @@ nf_nat_setup_info(struct nf_conn *ct,
}
if (maniptype == NF_NAT_MANIP_SRC) {
- struct nf_nat_conn_key key = {
- .net = nf_ct_net(ct),
- .tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
- .zone = nf_ct_zone(ct),
- };
- int err;
-
- err = rhltable_insert_key(&nf_nat_bysource_table,
- &key,
- &ct->nat_bysource,
- nf_nat_bysource_params);
- if (err)
- return NF_DROP;
+ unsigned int srchash;
+
+ srchash = hash_by_src(net,
+ &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ spin_lock_bh(&nf_nat_lock);
+ hlist_add_head_rcu(&ct->nat_bysource,
+ &nf_nat_bysource[srchash]);
+ spin_unlock_bh(&nf_nat_lock);
}
/* It's done. */
@@ -568,8 +538,9 @@ static int nf_nat_proto_clean(struct nf_
* will delete entry from already-freed table.
*/
clear_bit(IPS_SRC_NAT_DONE_BIT, &ct->status);
- rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource,
- nf_nat_bysource_params);
+ spin_lock_bh(&nf_nat_lock);
+ hlist_del_rcu(&ct->nat_bysource);
+ spin_unlock_bh(&nf_nat_lock);
/* don't delete conntrack. Although that would make things a lot
* simpler, we'd end up flushing all conntracks on nat rmmod.
@@ -697,9 +668,11 @@ EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregis
/* No one using conntrack by the time this called. */
static void nf_nat_cleanup_conntrack(struct nf_conn *ct)
{
- if (ct->status & IPS_SRC_NAT_DONE)
- rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource,
- nf_nat_bysource_params);
+ if (ct->status & IPS_SRC_NAT_DONE) {
+ spin_lock_bh(&nf_nat_lock);
+ hlist_del_rcu(&ct->nat_bysource);
+ spin_unlock_bh(&nf_nat_lock);
+ }
}
static struct nf_ct_ext_type nat_extend __read_mostly = {
@@ -823,13 +796,16 @@ static int __init nf_nat_init(void)
{
int ret;
- ret = rhltable_init(&nf_nat_bysource_table, &nf_nat_bysource_params);
- if (ret)
- return ret;
+ /* Leave them the same for the moment. */
+ nf_nat_htable_size = nf_conntrack_htable_size;
+
+ nf_nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size, 0);
+ if (!nf_nat_bysource)
+ return -ENOMEM;
ret = nf_ct_extend_register(&nat_extend);
if (ret < 0) {
- rhltable_destroy(&nf_nat_bysource_table);
+ nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
printk(KERN_ERR "nf_nat_core: Unable to register extension\n");
return ret;
}
@@ -863,8 +839,8 @@ static void __exit nf_nat_cleanup(void)
for (i = 0; i < NFPROTO_NUMPROTO; i++)
kfree(nf_nat_l4protos[i]);
-
- rhltable_destroy(&nf_nat_bysource_table);
+ synchronize_net();
+ nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
}
MODULE_LICENSE("GPL");
Patches currently in stable-queue which might be from fw(a)strlen.de are
queue-4.13/netfilter-nat-revert-netfilter-nat-convert-nat-bysrc-hash-to-rhashtable.patch
This is a note to let you know that I've just added the patch titled
KEYS: trusted: sanitize all key material
to the 3.18-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
keys-trusted-sanitize-all-key-material.patch
and it can be found in the queue-3.18 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From ee618b4619b72527aaed765f0f0b74072b281159 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers(a)google.com>
Date: Thu, 8 Jun 2017 14:49:18 +0100
Subject: KEYS: trusted: sanitize all key material
From: Eric Biggers <ebiggers(a)google.com>
commit ee618b4619b72527aaed765f0f0b74072b281159 upstream.
As the previous patch did for encrypted-keys, zero sensitive any
potentially sensitive data related to the "trusted" key type before it
is freed. Notably, we were not zeroing the tpm_buf structures in which
the actual key is stored for TPM seal and unseal, nor were we zeroing
the trusted_key_payload in certain error paths.
Cc: Mimi Zohar <zohar(a)linux.vnet.ibm.com>
Cc: David Safford <safford(a)us.ibm.com>
Signed-off-by: Eric Biggers <ebiggers(a)google.com>
Signed-off-by: David Howells <dhowells(a)redhat.com>
Signed-off-by: James Morris <james.l.morris(a)oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
security/keys/trusted.c | 35 +++++++++++++++++------------------
1 file changed, 17 insertions(+), 18 deletions(-)
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -69,7 +69,7 @@ static int TSS_sha1(const unsigned char
}
ret = crypto_shash_digest(&sdesc->shash, data, datalen, digest);
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
@@ -113,7 +113,7 @@ static int TSS_rawhmac(unsigned char *di
if (!ret)
ret = crypto_shash_final(&sdesc->shash, digest);
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
@@ -164,7 +164,7 @@ static int TSS_authhmac(unsigned char *d
paramdigest, TPM_NONCE_SIZE, h1,
TPM_NONCE_SIZE, h2, 1, &c, 0, 0);
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
@@ -245,7 +245,7 @@ static int TSS_checkhmac1(unsigned char
if (memcmp(testhmac, authdata, SHA1_DIGEST_SIZE))
ret = -EINVAL;
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
@@ -346,7 +346,7 @@ static int TSS_checkhmac2(unsigned char
if (memcmp(testhmac2, authdata2, SHA1_DIGEST_SIZE))
ret = -EINVAL;
out:
- kfree(sdesc);
+ kzfree(sdesc);
return ret;
}
@@ -563,7 +563,7 @@ static int tpm_seal(struct tpm_buf *tb,
*bloblen = storedsize;
}
out:
- kfree(td);
+ kzfree(td);
return ret;
}
@@ -677,7 +677,7 @@ static int key_seal(struct trusted_key_p
if (ret < 0)
pr_info("trusted_key: srkseal failed (%d)\n", ret);
- kfree(tb);
+ kzfree(tb);
return ret;
}
@@ -702,7 +702,7 @@ static int key_unseal(struct trusted_key
/* pull migratable flag out of sealed key */
p->migratable = p->key[--p->key_len];
- kfree(tb);
+ kzfree(tb);
return ret;
}
@@ -961,12 +961,12 @@ static int trusted_instantiate(struct ke
if (!ret && options->pcrlock)
ret = pcrlock(options->pcrlock);
out:
- kfree(datablob);
- kfree(options);
+ kzfree(datablob);
+ kzfree(options);
if (!ret)
rcu_assign_keypointer(key, payload);
else
- kfree(payload);
+ kzfree(payload);
return ret;
}
@@ -975,8 +975,7 @@ static void trusted_rcu_free(struct rcu_
struct trusted_key_payload *p;
p = container_of(rcu, struct trusted_key_payload, rcu);
- memset(p->key, 0, p->key_len);
- kfree(p);
+ kzfree(p);
}
/*
@@ -1018,7 +1017,7 @@ static int trusted_update(struct key *ke
ret = datablob_parse(datablob, new_p, new_o);
if (ret != Opt_update) {
ret = -EINVAL;
- kfree(new_p);
+ kzfree(new_p);
goto out;
}
/* copy old key values, and reseal with new pcrs */
@@ -1031,22 +1030,22 @@ static int trusted_update(struct key *ke
ret = key_seal(new_p, new_o);
if (ret < 0) {
pr_info("trusted_key: key_seal failed (%d)\n", ret);
- kfree(new_p);
+ kzfree(new_p);
goto out;
}
if (new_o->pcrlock) {
ret = pcrlock(new_o->pcrlock);
if (ret < 0) {
pr_info("trusted_key: pcrlock failed (%d)\n", ret);
- kfree(new_p);
+ kzfree(new_p);
goto out;
}
}
rcu_assign_keypointer(key, new_p);
call_rcu(&p->rcu, trusted_rcu_free);
out:
- kfree(datablob);
- kfree(new_o);
+ kzfree(datablob);
+ kzfree(new_o);
return ret;
}
Patches currently in stable-queue which might be from ebiggers(a)google.com are
queue-3.18/keys-trusted-sanitize-all-key-material.patch
The patch below does not apply to the 3.18-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable(a)vger.kernel.org>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From a3c812f7cfd80cf51e8f5b7034f7418f6beb56c1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers(a)google.com>
Date: Thu, 2 Nov 2017 00:47:12 +0000
Subject: [PATCH] KEYS: trusted: fix writing past end of buffer in
trusted_read()
When calling keyctl_read() on a key of type "trusted", if the
user-supplied buffer was too small, the kernel ignored the buffer length
and just wrote past the end of the buffer, potentially corrupting
userspace memory. Fix it by instead returning the size required, as per
the documentation for keyctl_read().
We also don't even fill the buffer at all in this case, as this is
slightly easier to implement than doing a short read, and either
behavior appears to be permitted. It also makes it match the behavior
of the "encrypted" key type.
Fixes: d00a1c72f7f4 ("keys: add new trusted key-type")
Reported-by: Ben Hutchings <ben(a)decadent.org.uk>
Cc: <stable(a)vger.kernel.org> # v2.6.38+
Signed-off-by: Eric Biggers <ebiggers(a)google.com>
Signed-off-by: David Howells <dhowells(a)redhat.com>
Reviewed-by: Mimi Zohar <zohar(a)linux.vnet.ibm.com>
Reviewed-by: James Morris <james.l.morris(a)oracle.com>
Signed-off-by: James Morris <james.l.morris(a)oracle.com>
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index bd85315cbfeb..98aa89ff7bfd 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -1147,20 +1147,21 @@ static long trusted_read(const struct key *key, char __user *buffer,
p = dereference_key_locked(key);
if (!p)
return -EINVAL;
- if (!buffer || buflen <= 0)
- return 2 * p->blob_len;
- ascii_buf = kmalloc(2 * p->blob_len, GFP_KERNEL);
- if (!ascii_buf)
- return -ENOMEM;
- bufp = ascii_buf;
- for (i = 0; i < p->blob_len; i++)
- bufp = hex_byte_pack(bufp, p->blob[i]);
- if ((copy_to_user(buffer, ascii_buf, 2 * p->blob_len)) != 0) {
+ if (buffer && buflen >= 2 * p->blob_len) {
+ ascii_buf = kmalloc(2 * p->blob_len, GFP_KERNEL);
+ if (!ascii_buf)
+ return -ENOMEM;
+
+ bufp = ascii_buf;
+ for (i = 0; i < p->blob_len; i++)
+ bufp = hex_byte_pack(bufp, p->blob[i]);
+ if (copy_to_user(buffer, ascii_buf, 2 * p->blob_len) != 0) {
+ kzfree(ascii_buf);
+ return -EFAULT;
+ }
kzfree(ascii_buf);
- return -EFAULT;
}
- kzfree(ascii_buf);
return 2 * p->blob_len;
}
Hello,
please integrate/backport the following commit into stable kernel release 4.4:
Commit-ID: 2b02c20ce0c28974b44e69a2e2f5ddc6a470ad6f (see https://github.com/torvalds/linux/commit/2b02c20ce0c28974b44e69a2e2f5ddc6a4…)
Subject: "cdc_ncm: Set NTB format again after altsetting switch for Huawei devices"
(The patch has been submitted and merged into the mainline.)
We regard this commit as a fix/workaround for a change in firmware behavior observed in some recent huawei devices (e.g.: Huawei MS2131 LTE stick).
As these devices are unusable with the 4.4.x LTS kernel we suggest to include this workarround as there will be more and more LTE sticks to expect until EOS in 2022...
See also the mail below of the originator of the commit.
(It may also make sense to integrate it into the other stable kernel release)
Thank you very much!
Kind regards,
Matthias
----
Sender: Enrico Mioso <mrkiko.rs(a)gmail.com>
Date: 08.11.2017 23:21
Subject: Re: Question regarding commit: cdc_ncm: Set NTB format again after altsetting switch for Huawei devices
Hello Mathias.
First of all, thank you for your interest in huawei_cdc_ncm driver and contacting me.
This commit could be backported to 4.4 kernel, I didn't send that to stable(a)vger.kernel.org .
Let me know if there are any difficulties doing so. Or I might do the submission in some days.
I think that commit could be related to a bug: even if it's arguable. That bug infact, is not related to the Linux kernel itself, but to the huawei firmware.
So I don't think there will be a bug tracker entry.
Thanks for all,
Enrico
On Mon, Nov 06, 2017 at 04:57:21PM -0800, Dan Williams wrote:
> Until there is a solution to the dma-to-dax vs truncate problem it is
> not safe to allow RDMA to create long standing memory registrations
> against filesytem-dax vmas.
Looks good:
Reviewed-by: Christoph Hellwig <hch(a)lst.de>
> +long get_user_pages_longterm(unsigned long start, unsigned long nr_pages,
> + unsigned int gup_flags, struct page **pages,
> + struct vm_area_struct **vmas)
> +{
> + struct vm_area_struct **__vmas = vmas;
How about calling the vma argument vma_arg, and the one used vma to
make thigns a little more readable?
> + struct vm_area_struct *vma_prev = NULL;
> + long rc, i;
> +
> + if (!pages)
> + return -EINVAL;
> +
> + if (!vmas && IS_ENABLED(CONFIG_FS_DAX)) {
> + __vmas = kzalloc(sizeof(struct vm_area_struct *) * nr_pages,
> + GFP_KERNEL);
> + if (!__vmas)
> + return -ENOMEM;
> + }
> +
> + rc = get_user_pages(start, nr_pages, gup_flags, pages, __vmas);
> +
> + /* skip scan for fs-dax vmas if they are compile time disabled */
> + if (!IS_ENABLED(CONFIG_FS_DAX))
> + goto out;
Instead of all this IS_ENABLED magic I'd recomment to just conditionally
compile this function and define it to get_user_pages in the header
if FS_DAX is disabled.
Else this looks fine to me.
Currently only get_user_pages_fast() can safely handle the writable gup
case due to its use of pud_access_permitted() to check whether the pud
entry is writable. In the gup slow path pud_write() is used instead of
pud_access_permitted() and to date it has been unimplemented, just calls
BUG_ON().
kernel BUG at ./include/linux/hugetlb.h:244!
[..]
RIP: 0010:follow_devmap_pud+0x482/0x490
[..]
Call Trace:
follow_page_mask+0x28c/0x6e0
__get_user_pages+0xe4/0x6c0
get_user_pages_unlocked+0x130/0x1b0
get_user_pages_fast+0x89/0xb0
iov_iter_get_pages_alloc+0x114/0x4a0
nfs_direct_read_schedule_iovec+0xd2/0x350
? nfs_start_io_direct+0x63/0x70
nfs_file_direct_read+0x1e0/0x250
nfs_file_read+0x90/0xc0
Use pud_access_permitted() to implement pud_write(), a later cleanup can
remove {pte,pmd,pud}_write and replace them with
{pte,pmd,pud}_access_permitted() drectly so that we only have one set of
helpers these kinds of checks. For now, implementing pud_write()
simplifies -stable backports.
Cc: <stable(a)vger.kernel.org>
Cc: Dave Hansen <dave.hansen(a)intel.com>
Fixes: a00cc7d9dd93 ("mm, x86: add support for PUD-sized transparent hugepages")
Signed-off-by: Dan Williams <dan.j.williams(a)intel.com>
---
Sending this as RFC for opinion on whether this should just be a
pud_flags() & _PAGE_RW check, like pmd_write, or pud_access_permitted()
that also takes protection keys into account.
include/linux/hugetlb.h | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index fbf5b31d47ee..6a142b240ef7 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -242,8 +242,7 @@ static inline int pgd_write(pgd_t pgd)
#ifndef pud_write
static inline int pud_write(pud_t pud)
{
- BUG();
- return 0;
+ return pud_access_permitted(pud, WRITE);
}
#endif
Aleksa Sarai <asarai(a)suse.de> writes:
> On 11/05/2017 01:56 PM, Aleksa Sarai wrote:
>> Previously, the only capability effectively required to operate on the
>> /proc/scsi interface was CAP_DAC_OVERRIDE (or for some other files,
>> having an fsuid of GLOBAL_ROOT_UID was enough). This means that
>> semi-privileged processes could interfere with core components of a
>> system (such as causing a DoS by removing the underlying SCSI device of
>> the host's / mount).
>
> An alternative to this patch would be to make the open(2) call fail, if you try
> to open it write-only or read-write. Not sure which would be preferred (should
> it be possible to pass /proc/scsi/scsi to a semi-privileged process to write
> to?).
Making open fail is very much the preferred solution.
Testing for permission on write can be avoided by finding a suid root
application whose error output acts like a suid cat.
The best current practice for adding this kind of permission check is to
add the check in open. For some older use cases where we made this
mistake we had to maintian a check during write to avoid breaking
userspace. But as this check is new there is no reason to add a check
anywhere except in open.
Eric
On Thu, Nov 09, 2017 at 04:59:58PM +0000, Ben Hutchings wrote:
> On Thu, 2017-11-09 at 08:03 -0800, Guenter Roeck wrote:
> > On Thu, Nov 09, 2017 at 12:40:36PM +0000, Ben Hutchings wrote:
> > > On Thu, 2017-11-09 at 13:21 +0100, Arnd Bergmann wrote:
> > > > On Thu, Nov 9, 2017 at 1:08 PM, Greg KH <greg(a)kroah.com> wrote:
> > > > > On Thu, Nov 09, 2017 at 12:55:30PM +0100, Arnd Bergmann wrote:
> > >
> > > [...]
> > > > > > I think if you upload the branch to the stable-rc git, that should produce
> > > > > > the automated build and boot results via email or via the
> > > > > > https://kernelci.org/job/ interface. Once there are some results
> > > > > > there, I'll go through the list once more to see what warnings
> > > > > > and failures remain.
> > > > >
> > > > > I don't know of a way to have others push to that tree/branch at the
> > > > > moment :(
> > > > >
> > > > > I'll go update that branch now...
> > > >
> > > > Thanks!
> > > >
> > > > With the arm-soc tree, we simply have a shared group-id on
> > > > gitolite.kernel.org and everyone in that group can push to it.
> > > >
> > > > If that is the only thing you need, it should be trivial to let Ben
> > > > and Sasha push to /pub/scm/linux/kernel/git/stable/*.git as well,
> > > > I'm sure helpdesk(a)kernel.org can arrange that. Of course if you are
> > > > worried about having multiple accounts with write access to all the
> > > > branches, then that wouldn't be enough.
> > >
> > > I think I'd rather send a pull request to Greg at the start of the
> > > review period.
> > >
> >
> > If you change the trees I am supposed to pull from for my builders,
> > please let me know.
>
> If you're happy to keep supporting quilt-in-git then there's no change.
> I check your builders page and try to fix up build failures before even
> making a release candidate.
>
Ah yes, kernelci won't pick that up. No problem to keep kerneltests going
as long as it adds value.
Guenter
Hi Simon,
On 08.11.17 18:17, Simon Guinot wrote:
> Hi Sven and Andreas,
>
> Please, can you try with this patch ?
Today we, my son and I, repeated the failing scenario and we were able
to show that our scenario behaves stable after you patch being applied.
Thanks for taking care of this issue. If you need further testing let me
know.
Regards,
Andreas
> On Wed, Nov 08, 2017 at 05:58:35PM +0100, Simon Guinot wrote:
>> The mvneta controller provides a 8-bit register to update the pending
>> Tx descriptor counter. Then, a maximum of 255 Tx descriptors can be
>> added at once. In the current code the mvneta_txq_pend_desc_add function
>> assumes the caller takes care of this limit. But it is not the case. In
>> some situations (xmit_more flag), more than 255 descriptors are added.
>> When this happens, the Tx descriptor counter register is updated with a
>> wrong value, which breaks the whole Tx queue management.
>>
>> This patch fixes the issue by allowing the mvneta_txq_pend_desc_add
>> function to process more than 255 Tx descriptors.
>>
>> Fixes: 2a90f7e1d5d0 ("net: mvneta: add xmit_more support")
>> Cc: stable(a)vger.kernel.org # 4.11+
>> Signed-off-by: Simon Guinot <simon.guinot(a)sequanux.org>
>> ---
>> drivers/net/ethernet/marvell/mvneta.c | 16 +++++++++-------
>> 1 file changed, 9 insertions(+), 7 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
>> index 64a04975bcf8..027c08ce4e5d 100644
>> --- a/drivers/net/ethernet/marvell/mvneta.c
>> +++ b/drivers/net/ethernet/marvell/mvneta.c
>> @@ -816,11 +816,14 @@ static void mvneta_txq_pend_desc_add(struct mvneta_port *pp,
>> {
>> u32 val;
>>
>> - /* Only 255 descriptors can be added at once ; Assume caller
>> - * process TX desriptors in quanta less than 256
>> - */
>> - val = pend_desc + txq->pending;
>> - mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
>> + pend_desc += txq->pending;
>> +
>> + /* Only 255 Tx descriptors can be added at once */
>> + while (pend_desc > 0) {
>> + val = min(pend_desc, 255);
>> + mvreg_write(pp, MVNETA_TXQ_UPDATE_REG(txq->id), val);
>> + pend_desc -= val;
>> + }
>> txq->pending = 0;
>> }
>>
>> @@ -2413,8 +2416,7 @@ static int mvneta_tx(struct sk_buff *skb, struct net_device *dev)
>> if (txq->count >= txq->tx_stop_threshold)
>> netif_tx_stop_queue(nq);
>>
>> - if (!skb->xmit_more || netif_xmit_stopped(nq) ||
>> - txq->pending + frags > MVNETA_TXQ_DEC_SENT_MASK)
>> + if (!skb->xmit_more || netif_xmit_stopped(nq))
>> mvneta_txq_pend_desc_add(pp, txq, frags);
>> else
>> txq->pending += frags;
>> --
>> 2.9.3
On Mon, 2017-10-16 at 18:11 +0200, gregkh(a)linuxfoundation.org wrote:
> 4.4-stable review patch. If anyone has any objections, please let me know.
>
> ------------------
>
> From: Paul E. McKenney <paulmck(a)linux.vnet.ibm.com>
>
> commit 28585a832602747cbfa88ad8934013177a3aae38 upstream.
>
> A number of architecture invoke rcu_irq_enter() on exception entry in
> order to allow RCU read-side critical sections in the exception handler
> when the exception is from an idle or nohz_full CPU. This works, at
> least unless the exception happens in an NMI handler. In that case,
> rcu_nmi_enter() would already have exited the extended quiescent state,
> which would mean that rcu_irq_enter() would (incorrectly) cause RCU
> to think that it is again in an extended quiescent state. This will
> in turn result in lockdep splats in response to later RCU read-side
> critical sections.
>
> This commit therefore causes rcu_irq_enter() and rcu_irq_exit() to
> take no action if there is an rcu_nmi_enter() in effect, thus avoiding
> the unscheduled return to RCU quiescent state. This in turn should
> make the kernel safe for on-demand RCU voyeurism.
>
> Link: http://lkml.kernel.org/r/20170922211022.GA18084@linux.vnet.ibm.com
>
> Cc: stable(a)vger.kernel.org
> Fixes: 0be964be0 ("module: Sanitize RCU usage and locking")
> > Reported-by: Steven Rostedt <rostedt(a)goodmis.org>
> > Signed-off-by: Paul E. McKenney <paulmck(a)linux.vnet.ibm.com>
> > Signed-off-by: Steven Rostedt (VMware) <rostedt(a)goodmis.org>
> > Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
> ---
> kernel/rcu/tree.c | 12 ++++++++++++
> 1 file changed, 12 insertions(+)
>
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -759,6 +759,12 @@ void rcu_irq_exit(void)
>
> local_irq_save(flags);
> rdtp = this_cpu_ptr(&rcu_dynticks);
> +
> + /* Page faults can happen in NMI handlers, so check... */
> + if (READ_ONCE(rdtp->dynticks_nmi_nesting))
> + return;
Shouldn't there be a local_irq_restore() on this return path? Or does
this condition imply that IRQs were already disabled?
> + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_exit() invoked with irqs enabled!!!");
I don't see why you added RCU_LOCKDEP_WARN() here. Prior to 4.5 it's
not an error to call this function with IRQs disabled. And after
calling local_irq_save(), it's redundant to assert that IRQs are
disabled.
> oldval = rdtp->dynticks_nesting;
> rdtp->dynticks_nesting--;
> WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
> @@ -887,6 +893,12 @@ void rcu_irq_enter(void)
>
> local_irq_save(flags);
> rdtp = this_cpu_ptr(&rcu_dynticks);
> +
> + /* Page faults can happen in NMI handlers, so check... */
> + if (READ_ONCE(rdtp->dynticks_nmi_nesting))
> + return;
> +
> + RCU_LOCKDEP_WARN(!irqs_disabled(), "rcu_irq_enter() invoked with irqs enabled!!!");
Same problems here.
Ben.
> oldval = rdtp->dynticks_nesting;
> rdtp->dynticks_nesting++;
> WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
--
Ben Hutchings
Software Developer, Codethink Ltd.
This is a note to let you know that I've just added the patch titled
xen/netback: set default upper limit of tx/rx queues to 8
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
xen-netback-set-default-upper-limit-of-tx-rx-queues-to-8.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: Juergen Gross <jgross(a)suse.com>
Date: Tue, 10 Jan 2017 14:32:52 +0100
Subject: xen/netback: set default upper limit of tx/rx queues to 8
From: Juergen Gross <jgross(a)suse.com>
[ Upstream commit 56dd5af9bc23d0d5d23bb207c477715b4c2216c5 ]
The default for the maximum number of tx/rx queues of one interface is
the number of cpus of the system today. As each queue pair reserves 512
grant pages this default consumes a ridiculous number of grants for
large guests.
Limit the queue number to 8 as default. This value can be modified
via a module parameter if required.
Signed-off-by: Juergen Gross <jgross(a)suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky(a)oracle.com>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/net/xen-netback/netback.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -67,6 +67,7 @@ module_param(rx_drain_timeout_msecs, uin
unsigned int rx_stall_timeout_msecs = 60000;
module_param(rx_stall_timeout_msecs, uint, 0444);
+#define MAX_QUEUES_DEFAULT 8
unsigned int xenvif_max_queues;
module_param_named(max_queues, xenvif_max_queues, uint, 0644);
MODULE_PARM_DESC(max_queues,
@@ -2157,11 +2158,12 @@ static int __init netback_init(void)
if (!xen_domain())
return -ENODEV;
- /* Allow as many queues as there are CPUs if user has not
+ /* Allow as many queues as there are CPUs but max. 8 if user has not
* specified a value.
*/
if (xenvif_max_queues == 0)
- xenvif_max_queues = num_online_cpus();
+ xenvif_max_queues = min_t(unsigned int, MAX_QUEUES_DEFAULT,
+ num_online_cpus());
if (fatal_skb_slots < XEN_NETBK_LEGACY_SLOTS_MAX) {
pr_info("fatal_skb_slots too small (%d), bump it to XEN_NETBK_LEGACY_SLOTS_MAX (%d)\n",
Patches currently in stable-queue which might be from jgross(a)suse.com are
queue-4.4/xen-netback-set-default-upper-limit-of-tx-rx-queues-to-8.patch
This is a note to let you know that I've just added the patch titled
video: fbdev: pmag-ba-fb: Remove bad `__init' annotation
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
video-fbdev-pmag-ba-fb-remove-bad-__init-annotation.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: "Maciej W. Rozycki" <macro(a)linux-mips.org>
Date: Mon, 30 Jan 2017 17:39:48 +0100
Subject: video: fbdev: pmag-ba-fb: Remove bad `__init' annotation
From: "Maciej W. Rozycki" <macro(a)linux-mips.org>
[ Upstream commit 879e5a0df626f39cbb3c61bb90373e56d67012c4 ]
Fix:
WARNING: drivers/video/fbdev/pmag-ba-fb.o(.text+0x308): Section mismatch in reference from the function pmagbafb_probe() to the function .init.text:pmagbafb_erase_cursor()
The function pmagbafb_probe()
references the function __init pmagbafb_erase_cursor().
This is often because pmagbafb_probe lacks a __init
annotation or the annotation of pmagbafb_erase_cursor is wrong.
-- a fallout from a missed update from commit 9625b51350cc ("VIDEO:
PMAG-BA: Fix section mismatch") and then commit 48c68c4f1b54 ("Drivers:
video: remove __dev* attributes.")
Signed-off-by: Maciej W. Rozycki <macro(a)linux-mips.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie(a)samsung.com>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/video/fbdev/pmag-ba-fb.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/drivers/video/fbdev/pmag-ba-fb.c
+++ b/drivers/video/fbdev/pmag-ba-fb.c
@@ -129,7 +129,7 @@ static struct fb_ops pmagbafb_ops = {
/*
* Turn the hardware cursor off.
*/
-static void __init pmagbafb_erase_cursor(struct fb_info *info)
+static void pmagbafb_erase_cursor(struct fb_info *info)
{
struct pmagbafb_par *par = info->par;
Patches currently in stable-queue which might be from macro(a)linux-mips.org are
queue-4.4/video-fbdev-pmag-ba-fb-remove-bad-__init-annotation.patch
This is a note to let you know that I've just added the patch titled
usb: hcd: initialize hcd->flags to 0 when rm hcd
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
usb-hcd-initialize-hcd-flags-to-0-when-rm-hcd.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: William wu <wulf(a)rock-chips.com>
Date: Fri, 13 Jan 2017 11:04:22 +0800
Subject: usb: hcd: initialize hcd->flags to 0 when rm hcd
From: William wu <wulf(a)rock-chips.com>
[ Upstream commit 76b8db0d480e8045e1a1902fc9ab143b3b9ef115 ]
On some platforms(e.g. rk3399 board), we can call hcd_add/remove
consecutively without calling usb_put_hcd/usb_create_hcd in between,
so hcd->flags can be stale.
If the HC dies due to whatever reason then without this patch we get
the below error on next hcd_add.
[173.296154] xhci-hcd xhci-hcd.2.auto: HC died; cleaning up
[173.296209] xhci-hcd xhci-hcd.2.auto: xHCI Host Controller
[173.296762] xhci-hcd xhci-hcd.2.auto: new USB bus registered, assigned bus number 6
[173.296931] usb usb6: We don't know the algorithms for LPM for this host, disabling LPM.
[173.297179] usb usb6: New USB device found, idVendor=1d6b, idProduct=0003
[173.297203] usb usb6: New USB device strings: Mfr=3, Product=2, SerialNumber=1
[173.297222] usb usb6: Product: xHCI Host Controller
[173.297240] usb usb6: Manufacturer: Linux 4.4.21 xhci-hcd
[173.297257] usb usb6: SerialNumber: xhci-hcd.2.auto
[173.298680] hub 6-0:1.0: USB hub found
[173.298749] hub 6-0:1.0: 1 port detected
[173.299382] rockchip-dwc3 usb@fe800000: USB HOST connected
[173.395418] hub 5-0:1.0: activate --> -19
[173.603447] irq 228: nobody cared (try booting with the "irqpoll" option)
[173.603493] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.4.21 #9
[173.603513] Hardware name: Google Kevin (DT)
[173.603531] Call trace:
[173.603568] [<ffffffc0002087dc>] dump_backtrace+0x0/0x160
[173.603596] [<ffffffc00020895c>] show_stack+0x20/0x28
[173.603623] [<ffffffc0004b28a8>] dump_stack+0x90/0xb0
[173.603650] [<ffffffc00027347c>] __report_bad_irq+0x48/0xe8
[173.603674] [<ffffffc0002737cc>] note_interrupt+0x1e8/0x28c
[173.603698] [<ffffffc000270a38>] handle_irq_event_percpu+0x1d4/0x25c
[173.603722] [<ffffffc000270b0c>] handle_irq_event+0x4c/0x7c
[173.603748] [<ffffffc00027456c>] handle_fasteoi_irq+0xb4/0x124
[173.603777] [<ffffffc00026fe3c>] generic_handle_irq+0x30/0x44
[173.603804] [<ffffffc0002701a8>] __handle_domain_irq+0x90/0xbc
[173.603827] [<ffffffc0002006f4>] gic_handle_irq+0xcc/0x188
...
[173.604500] [<ffffffc000203700>] el1_irq+0x80/0xf8
[173.604530] [<ffffffc000261388>] cpu_startup_entry+0x38/0x3cc
[173.604558] [<ffffffc00090f7d8>] rest_init+0x8c/0x94
[173.604585] [<ffffffc000e009ac>] start_kernel+0x3d0/0x3fc
[173.604607] [<0000000000b16000>] 0xb16000
[173.604622] handlers:
[173.604648] [<ffffffc000642084>] usb_hcd_irq
[173.604673] Disabling IRQ #228
Signed-off-by: William wu <wulf(a)rock-chips.com>
Acked-by: Roger Quadros <rogerq(a)ti.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/usb/core/hcd.c | 1 +
1 file changed, 1 insertion(+)
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2997,6 +2997,7 @@ void usb_remove_hcd(struct usb_hcd *hcd)
}
usb_put_invalidate_rhdev(hcd);
+ hcd->flags = 0;
}
EXPORT_SYMBOL_GPL(usb_remove_hcd);
Patches currently in stable-queue which might be from wulf(a)rock-chips.com are
queue-4.4/usb-hcd-initialize-hcd-flags-to-0-when-rm-hcd.patch
This is a note to let you know that I've just added the patch titled
serial: sh-sci: Fix register offsets for the IRDA serial port
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
serial-sh-sci-fix-register-offsets-for-the-irda-serial-port.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com>
Date: Wed, 11 Jan 2017 16:43:32 +0200
Subject: serial: sh-sci: Fix register offsets for the IRDA serial port
From: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com>
[ Upstream commit a752ba18af8285e3eeda572f40dddaebff0c3621 ]
Even though most of its registers are 8-bit wide, the IRDA has two
16-bit registers that make it a 16-bit peripheral and not a 8-bit
peripheral with addresses shifted by one. Fix the registers offset in
the driver and the platform data regshift value.
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas(a)ideasonboard.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas(a)glider.be>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/sh/kernel/cpu/sh3/setup-sh770x.c | 1 -
drivers/tty/serial/sh-sci.c | 17 ++++++++---------
2 files changed, 8 insertions(+), 10 deletions(-)
--- a/arch/sh/kernel/cpu/sh3/setup-sh770x.c
+++ b/arch/sh/kernel/cpu/sh3/setup-sh770x.c
@@ -165,7 +165,6 @@ static struct plat_sci_port scif2_platfo
.scscr = SCSCR_TE | SCSCR_RE,
.type = PORT_IRDA,
.ops = &sh770x_sci_port_ops,
- .regshift = 1,
};
static struct resource scif2_resources[] = {
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -163,18 +163,17 @@ static const struct plat_sci_reg sci_reg
},
/*
- * Common definitions for legacy IrDA ports, dependent on
- * regshift value.
+ * Common definitions for legacy IrDA ports.
*/
[SCIx_IRDA_REGTYPE] = {
[SCSMR] = { 0x00, 8 },
- [SCBRR] = { 0x01, 8 },
- [SCSCR] = { 0x02, 8 },
- [SCxTDR] = { 0x03, 8 },
- [SCxSR] = { 0x04, 8 },
- [SCxRDR] = { 0x05, 8 },
- [SCFCR] = { 0x06, 8 },
- [SCFDR] = { 0x07, 16 },
+ [SCBRR] = { 0x02, 8 },
+ [SCSCR] = { 0x04, 8 },
+ [SCxTDR] = { 0x06, 8 },
+ [SCxSR] = { 0x08, 16 },
+ [SCxRDR] = { 0x0a, 8 },
+ [SCFCR] = { 0x0c, 8 },
+ [SCFDR] = { 0x0e, 16 },
[SCTFDR] = sci_reg_invalid,
[SCRFDR] = sci_reg_invalid,
[SCSPTR] = sci_reg_invalid,
Patches currently in stable-queue which might be from laurent.pinchart+renesas(a)ideasonboard.com are
queue-4.4/serial-sh-sci-fix-register-offsets-for-the-irda-serial-port.patch
This is a note to let you know that I've just added the patch titled
powerpc/corenet: explicitly disable the SDHC controller on kmcoge4
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
powerpc-corenet-explicitly-disable-the-sdhc-controller-on-kmcoge4.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: Valentin Longchamp <valentin.longchamp(a)keymile.com>
Date: Thu, 15 Dec 2016 14:22:26 +0100
Subject: powerpc/corenet: explicitly disable the SDHC controller on kmcoge4
From: Valentin Longchamp <valentin.longchamp(a)keymile.com>
[ Upstream commit a674c7d470bb47e82f4eb1fa944eadeac2f6bbaf ]
It is not implemented on the kmcoge4 hardware and if not disabled it
leads to error messages with the corenet32_smp_defconfig.
Signed-off-by: Valentin Longchamp <valentin.longchamp(a)keymile.com>
Signed-off-by: Scott Wood <oss(a)buserror.net>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
arch/powerpc/boot/dts/fsl/kmcoge4.dts | 4 ++++
1 file changed, 4 insertions(+)
--- a/arch/powerpc/boot/dts/fsl/kmcoge4.dts
+++ b/arch/powerpc/boot/dts/fsl/kmcoge4.dts
@@ -83,6 +83,10 @@
};
};
+ sdhc@114000 {
+ status = "disabled";
+ };
+
i2c@119000 {
status = "disabled";
};
Patches currently in stable-queue which might be from valentin.longchamp(a)keymile.com are
queue-4.4/powerpc-corenet-explicitly-disable-the-sdhc-controller-on-kmcoge4.patch
This is a note to let you know that I've just added the patch titled
phy: increase size of MII_BUS_ID_SIZE and bus_id
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
phy-increase-size-of-mii_bus_id_size-and-bus_id.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: Volodymyr Bendiuga <volodymyr.bendiuga(a)gmail.com>
Date: Thu, 19 Jan 2017 17:05:04 +0100
Subject: phy: increase size of MII_BUS_ID_SIZE and bus_id
From: Volodymyr Bendiuga <volodymyr.bendiuga(a)gmail.com>
[ Upstream commit 4567d686f5c6d955e57a3afa1741944c1e7f4033 ]
Some bus names are pretty long and do not fit into
17 chars. Increase therefore MII_BUS_ID_SIZE and
phy_fixup.bus_id to larger number. Now mii_bus.id
can host larger name.
Signed-off-by: Volodymyr Bendiuga <volodymyr.bendiuga(a)gmail.com>
Signed-off-by: Magnus Öberg <magnus.oberg(a)westermo.se>
Reviewed-by: Andrew Lunn <andrew(a)lunn.ch>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
include/linux/phy.h | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -136,11 +136,7 @@ static inline const char *phy_modes(phy_
/* Used when trying to connect to a specific phy (mii bus id:phy device id) */
#define PHY_ID_FMT "%s:%02x"
-/*
- * Need to be a little smaller than phydev->dev.bus_id to leave room
- * for the ":%02x"
- */
-#define MII_BUS_ID_SIZE (20 - 3)
+#define MII_BUS_ID_SIZE 61
/* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit
IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */
@@ -599,7 +595,7 @@ struct phy_driver {
/* A Structure for boards to register fixups with the PHY Lib */
struct phy_fixup {
struct list_head list;
- char bus_id[20];
+ char bus_id[MII_BUS_ID_SIZE + 3];
u32 phy_uid;
u32 phy_uid_mask;
int (*run)(struct phy_device *phydev);
Patches currently in stable-queue which might be from volodymyr.bendiuga(a)gmail.com are
queue-4.4/phy-increase-size-of-mii_bus_id_size-and-bus_id.patch
This is a note to let you know that I've just added the patch titled
PCI: mvebu: Handle changes to the bridge windows while enabled
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
pci-mvebu-handle-changes-to-the-bridge-windows-while-enabled.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: Jason Gunthorpe <jgunthorpe(a)obsidianresearch.com>
Date: Mon, 12 Dec 2016 11:30:20 -0700
Subject: PCI: mvebu: Handle changes to the bridge windows while enabled
From: Jason Gunthorpe <jgunthorpe(a)obsidianresearch.com>
[ Upstream commit d9bf28e2650fe3eeefed7e34841aea07d10c6543 ]
The PCI core will write to the bridge window config multiple times while
they are enabled. This can lead to mbus failures like this:
mvebu_mbus: cannot add window '4:e8', conflicts with another window
mvebu-pcie mbus:pex@e0000000: Could not create MBus window at [mem 0xe0000000-0xe00fffff]: -22
For me this is happening during a hotplug cycle. The PCI core is not
changing the values, just writing them twice while active.
The patch addresses the general case of any change to an active window, but
not atomically. The code is slightly refactored so io and mem can share
more of the window logic.
Signed-off-by: Jason Gunthorpe <jgunthorpe(a)obsidianresearch.com>
Signed-off-by: Bjorn Helgaas <bhelgaas(a)google.com>
Acked-by: Jason Cooper <jason(a)lakedaemon.net>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/pci/host/pci-mvebu.c | 101 +++++++++++++++++++++++++------------------
1 file changed, 60 insertions(+), 41 deletions(-)
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -131,6 +131,12 @@ struct mvebu_pcie {
int nports;
};
+struct mvebu_pcie_window {
+ phys_addr_t base;
+ phys_addr_t remap;
+ size_t size;
+};
+
/* Structure representing one PCIe interface */
struct mvebu_pcie_port {
char *name;
@@ -148,10 +154,8 @@ struct mvebu_pcie_port {
struct mvebu_sw_pci_bridge bridge;
struct device_node *dn;
struct mvebu_pcie *pcie;
- phys_addr_t memwin_base;
- size_t memwin_size;
- phys_addr_t iowin_base;
- size_t iowin_size;
+ struct mvebu_pcie_window memwin;
+ struct mvebu_pcie_window iowin;
u32 saved_pcie_stat;
};
@@ -377,23 +381,45 @@ static void mvebu_pcie_add_windows(struc
}
}
+static void mvebu_pcie_set_window(struct mvebu_pcie_port *port,
+ unsigned int target, unsigned int attribute,
+ const struct mvebu_pcie_window *desired,
+ struct mvebu_pcie_window *cur)
+{
+ if (desired->base == cur->base && desired->remap == cur->remap &&
+ desired->size == cur->size)
+ return;
+
+ if (cur->size != 0) {
+ mvebu_pcie_del_windows(port, cur->base, cur->size);
+ cur->size = 0;
+ cur->base = 0;
+
+ /*
+ * If something tries to change the window while it is enabled
+ * the change will not be done atomically. That would be
+ * difficult to do in the general case.
+ */
+ }
+
+ if (desired->size == 0)
+ return;
+
+ mvebu_pcie_add_windows(port, target, attribute, desired->base,
+ desired->size, desired->remap);
+ *cur = *desired;
+}
+
static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
{
- phys_addr_t iobase;
+ struct mvebu_pcie_window desired = {};
/* Are the new iobase/iolimit values invalid? */
if (port->bridge.iolimit < port->bridge.iobase ||
port->bridge.iolimitupper < port->bridge.iobaseupper ||
!(port->bridge.command & PCI_COMMAND_IO)) {
-
- /* If a window was configured, remove it */
- if (port->iowin_base) {
- mvebu_pcie_del_windows(port, port->iowin_base,
- port->iowin_size);
- port->iowin_base = 0;
- port->iowin_size = 0;
- }
-
+ mvebu_pcie_set_window(port, port->io_target, port->io_attr,
+ &desired, &port->iowin);
return;
}
@@ -410,32 +436,27 @@ static void mvebu_pcie_handle_iobase_cha
* specifications. iobase is the bus address, port->iowin_base
* is the CPU address.
*/
- iobase = ((port->bridge.iobase & 0xF0) << 8) |
- (port->bridge.iobaseupper << 16);
- port->iowin_base = port->pcie->io.start + iobase;
- port->iowin_size = ((0xFFF | ((port->bridge.iolimit & 0xF0) << 8) |
- (port->bridge.iolimitupper << 16)) -
- iobase) + 1;
-
- mvebu_pcie_add_windows(port, port->io_target, port->io_attr,
- port->iowin_base, port->iowin_size,
- iobase);
+ desired.remap = ((port->bridge.iobase & 0xF0) << 8) |
+ (port->bridge.iobaseupper << 16);
+ desired.base = port->pcie->io.start + desired.remap;
+ desired.size = ((0xFFF | ((port->bridge.iolimit & 0xF0) << 8) |
+ (port->bridge.iolimitupper << 16)) -
+ desired.remap) +
+ 1;
+
+ mvebu_pcie_set_window(port, port->io_target, port->io_attr, &desired,
+ &port->iowin);
}
static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
{
+ struct mvebu_pcie_window desired = {.remap = MVEBU_MBUS_NO_REMAP};
+
/* Are the new membase/memlimit values invalid? */
if (port->bridge.memlimit < port->bridge.membase ||
!(port->bridge.command & PCI_COMMAND_MEMORY)) {
-
- /* If a window was configured, remove it */
- if (port->memwin_base) {
- mvebu_pcie_del_windows(port, port->memwin_base,
- port->memwin_size);
- port->memwin_base = 0;
- port->memwin_size = 0;
- }
-
+ mvebu_pcie_set_window(port, port->mem_target, port->mem_attr,
+ &desired, &port->memwin);
return;
}
@@ -445,14 +466,12 @@ static void mvebu_pcie_handle_membase_ch
* window to setup, according to the PCI-to-PCI bridge
* specifications.
*/
- port->memwin_base = ((port->bridge.membase & 0xFFF0) << 16);
- port->memwin_size =
- (((port->bridge.memlimit & 0xFFF0) << 16) | 0xFFFFF) -
- port->memwin_base + 1;
-
- mvebu_pcie_add_windows(port, port->mem_target, port->mem_attr,
- port->memwin_base, port->memwin_size,
- MVEBU_MBUS_NO_REMAP);
+ desired.base = ((port->bridge.membase & 0xFFF0) << 16);
+ desired.size = (((port->bridge.memlimit & 0xFFF0) << 16) | 0xFFFFF) -
+ desired.base + 1;
+
+ mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, &desired,
+ &port->memwin);
}
/*
Patches currently in stable-queue which might be from jgunthorpe(a)obsidianresearch.com are
queue-4.4/pci-mvebu-handle-changes-to-the-bridge-windows-while-enabled.patch
This is a note to let you know that I've just added the patch titled
net: dsa: select NET_SWITCHDEV
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
net-dsa-select-net_switchdev.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: Vivien Didelot <vivien.didelot(a)savoirfairelinux.com>
Date: Mon, 9 Jan 2017 16:49:26 -0500
Subject: net: dsa: select NET_SWITCHDEV
From: Vivien Didelot <vivien.didelot(a)savoirfairelinux.com>
[ Upstream commit 3a89eaa65db68bf53bf92dedc60084f810e1779a ]
The support for DSA Ethernet switch chips depends on TCP/IP networking,
thus explicit that HAVE_NET_DSA depends on INET.
DSA uses SWITCHDEV, thus select it instead of depending on it.
Signed-off-by: Vivien Didelot <vivien.didelot(a)savoirfairelinux.com>
Reviewed-by: Andrew Lunn <andrew(a)lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli(a)gmail.com>
Tested-by: Randy Dunlap <rdunlap(a)infradead.org>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
net/dsa/Kconfig | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -1,12 +1,13 @@
config HAVE_NET_DSA
def_bool y
- depends on NETDEVICES && !S390
+ depends on INET && NETDEVICES && !S390
# Drivers must select NET_DSA and the appropriate tagging format
config NET_DSA
tristate "Distributed Switch Architecture"
- depends on HAVE_NET_DSA && NET_SWITCHDEV
+ depends on HAVE_NET_DSA
+ select NET_SWITCHDEV
select PHYLIB
---help---
Say Y if you want to enable support for the hardware switches supported
Patches currently in stable-queue which might be from vivien.didelot(a)savoirfairelinux.com are
queue-4.4/net-dsa-select-net_switchdev.patch
This is a note to let you know that I've just added the patch titled
netfilter: nft_meta: deal with PACKET_LOOPBACK in netdev family
to the 4.4-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=sum…
The filename of the patch is:
netfilter-nft_meta-deal-with-packet_loopback-in-netdev-family.patch
and it can be found in the queue-4.4 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable(a)vger.kernel.org> know about it.
>From foo@baz Thu Nov 9 18:22:51 CET 2017
From: Liping Zhang <zlpnobody(a)gmail.com>
Date: Sat, 7 Jan 2017 21:33:55 +0800
Subject: netfilter: nft_meta: deal with PACKET_LOOPBACK in netdev family
From: Liping Zhang <zlpnobody(a)gmail.com>
[ Upstream commit f169fd695b192dd7b23aff8e69d25a1bc881bbfa ]
After adding the following nft rule, then ping 224.0.0.1:
# nft add rule netdev t c pkttype host counter
The warning complain message will be printed out again and again:
WARNING: CPU: 0 PID: 10182 at net/netfilter/nft_meta.c:163 \
nft_meta_get_eval+0x3fe/0x460 [nft_meta]
[...]
Call Trace:
<IRQ>
dump_stack+0x85/0xc2
__warn+0xcb/0xf0
warn_slowpath_null+0x1d/0x20
nft_meta_get_eval+0x3fe/0x460 [nft_meta]
nft_do_chain+0xff/0x5e0 [nf_tables]
So we should deal with PACKET_LOOPBACK in netdev family too. For ipv4,
convert it to PACKET_BROADCAST/MULTICAST according to the destination
address's type; For ipv6, convert it to PACKET_MULTICAST directly.
Signed-off-by: Liping Zhang <zlpnobody(a)gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org>
Signed-off-by: Sasha Levin <alexander.levin(a)verizon.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
net/netfilter/nft_meta.c | 28 +++++++++++++++++++++++++++-
1 file changed, 27 insertions(+), 1 deletion(-)
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -151,8 +151,34 @@ void nft_meta_get_eval(const struct nft_
else
*dest = PACKET_BROADCAST;
break;
+ case NFPROTO_NETDEV:
+ switch (skb->protocol) {
+ case htons(ETH_P_IP): {
+ int noff = skb_network_offset(skb);
+ struct iphdr *iph, _iph;
+
+ iph = skb_header_pointer(skb, noff,
+ sizeof(_iph), &_iph);
+ if (!iph)
+ goto err;
+
+ if (ipv4_is_multicast(iph->daddr))
+ *dest = PACKET_MULTICAST;
+ else
+ *dest = PACKET_BROADCAST;
+
+ break;
+ }
+ case htons(ETH_P_IPV6):
+ *dest = PACKET_MULTICAST;
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ goto err;
+ }
+ break;
default:
- WARN_ON(1);
+ WARN_ON_ONCE(1);
goto err;
}
break;
Patches currently in stable-queue which might be from zlpnobody(a)gmail.com are
queue-4.4/netfilter-nft_meta-deal-with-packet_loopback-in-netdev-family.patch