From: Ruslan Babayev ruslan@babayev.com

[ Upstream commit 60f2208699ec08ff9fdf1f97639a661a92a18f1c ]

The ds4424_get_value function takes channel number as it's 3rd argument and translates it internally into I2C address using DS4424_DAC_ADDR macro. The caller ds4424_verify_chip was passing an already translated I2C address as its last argument.

Signed-off-by: Ruslan Babayev ruslan@babayev.com Cc: xe-linux-external@cisco.com Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/dac/ds4424.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/dac/ds4424.c b/drivers/iio/dac/ds4424.c index 883a47562055..714a97f91319 100644 --- a/drivers/iio/dac/ds4424.c +++ b/drivers/iio/dac/ds4424.c @@ -166,7 +166,7 @@ static int ds4424_verify_chip(struct iio_dev *indio_dev) { int ret, val;

- ret = ds4424_get_value(indio_dev, &val, DS4424_DAC_ADDR(0)); + ret = ds4424_get_value(indio_dev, &val, 0); if (ret < 0) dev_err(&indio_dev->dev, "%s failed. ret: %d\n", __func__, ret);

From: Chengguang Xu cgxu519@gmail.com

[ Upstream commit f2dcb8841e6b155da098edae09125859ef7e853d ]

Set sb->s_root to NULL when failing from __getname(), so that we can avoid double dput and unnecessary operations in generic_shutdown_super().

Signed-off-by: Chengguang Xu cgxu519@gmail.com Reviewed-by: Chao Yu yuchao0@huawei.com Reviewed-by: Gao Xiang gaoxiang25@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/erofs/super.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/staging/erofs/super.c b/drivers/staging/erofs/super.c index 15c784fba879..c8981662a49b 100644 --- a/drivers/staging/erofs/super.c +++ b/drivers/staging/erofs/super.c @@ -459,6 +459,7 @@ static int erofs_read_super(struct super_block *sb, */ err_devname: dput(sb->s_root); + sb->s_root = NULL; err_iget: #ifdef EROFS_FS_HAS_MANAGED_CACHE iput(sbi->managed_cache);

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit fea69916360468e364a4988db25a5afa835f3406 ]

If ->hif_read_reg() or ->hif_write_reg() fail then the code unlocks and keeps executing. It should just return.

Fixes: c5c77ba18ea6 ("staging: wilc1000: Add SDIO/SPI 802.11 driver") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/staging/wilc1000/wilc_wlan.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/wilc1000/wilc_wlan.c b/drivers/staging/wilc1000/wilc_wlan.c index c2389695fe20..70b1ab21f8a3 100644 --- a/drivers/staging/wilc1000/wilc_wlan.c +++ b/drivers/staging/wilc1000/wilc_wlan.c @@ -1076,13 +1076,17 @@ void wilc_wlan_cleanup(struct net_device *dev) acquire_bus(wilc, WILC_BUS_ACQUIRE_AND_WAKEUP);

ret = wilc->hif_func->hif_read_reg(wilc, WILC_GP_REG_0, &reg); - if (!ret) + if (!ret) { release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP); + return; + }

ret = wilc->hif_func->hif_write_reg(wilc, WILC_GP_REG_0, (reg | ABORT_INT)); - if (!ret) + if (!ret) { release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP); + return; + }

release_bus(wilc, WILC_BUS_RELEASE_ALLOW_SLEEP); wilc->hif_func->hif_deinit(NULL);

From: Florian Westphal fw@strlen.de

[ Upstream commit 2c82c7e724ff51cab78e1afd5c2aaa31994fe41e ]

We can oops in nf_tables_fill_rule_info().

Its not possible to fetch previous element in rcu-protected lists when deletions are not prevented somehow: list_del_rcu poisons the ->prev pointer value.

Before rcu-conversion this was safe as dump operations did hold nfnetlink mutex.

Pass previous rule as argument, obtained by keeping a pointer to the previous rule during traversal.

Fixes: d9adf22a291883 ("netfilter: nf_tables: use call_rcu in netlink dumps") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1606eaa5ae0d..041a81185c6a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2256,13 +2256,13 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct nft_rule *rule) + const struct nft_rule *rule, + const struct nft_rule *prule) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; const struct nft_expr *expr, *next; struct nlattr *list; - const struct nft_rule *prule; u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);

nlh = nlmsg_put(skb, portid, seq, type, sizeof(struct nfgenmsg), flags); @@ -2282,8 +2282,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, NFTA_RULE_PAD)) goto nla_put_failure;

- if ((event != NFT_MSG_DELRULE) && (rule->list.prev != &chain->rules)) { - prule = list_prev_entry(rule, list); + if (event != NFT_MSG_DELRULE && prule) { if (nla_put_be64(skb, NFTA_RULE_POSITION, cpu_to_be64(prule->handle), NFTA_RULE_PAD)) @@ -2330,7 +2329,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx,

err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, event, 0, ctx->family, ctx->table, - ctx->chain, rule); + ctx->chain, rule, NULL); if (err < 0) { kfree_skb(skb); goto err; @@ -2355,12 +2354,13 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, const struct nft_chain *chain) { struct net *net = sock_net(skb->sk); + const struct nft_rule *rule, *prule; unsigned int s_idx = cb->args[0]; - const struct nft_rule *rule;

+ prule = NULL; list_for_each_entry_rcu(rule, &chain->rules, list) { if (!nft_is_active(net, rule)) - goto cont; + goto cont_skip; if (*idx < s_idx) goto cont; if (*idx > s_idx) { @@ -2372,11 +2372,13 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule) < 0) + table, chain, rule, prule) < 0) return 1;

nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: + prule = rule; +cont_skip: (*idx)++; } return 0; @@ -2532,7 +2534,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,

err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, - family, table, chain, rule); + family, table, chain, rule, NULL); if (err < 0) goto err;

From: Jagdish Motwani jagdish.motwani@sophos.com

[ Upstream commit 946c0d8e6ed43dae6527e878d0077c1e11015db0 ]

This patch fixes netfilter hook traversal when there are more than 1 hooks returning NF_QUEUE verdict. When the first queue reinjects the packet, 'nf_reinject' starts traversing hooks with a proper hook_index. However, if it again receives a NF_QUEUE verdict (by some other netfilter hook), it queues the packet with a wrong hook_index. So, when the second queue reinjects the packet, it re-executes hooks in between.

Fixes: 960632ece694 ("netfilter: convert hook list to an array") Signed-off-by: Jagdish Motwani jagdish.motwani@sophos.com Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_queue.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index a36a77bae1d6..5b86574e7b89 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -254,6 +254,7 @@ static unsigned int nf_iterate(struct sk_buff *skb, repeat: verdict = nf_hook_entry_hookfn(hook, skb, state); if (verdict != NF_ACCEPT) { + *index = i; if (verdict != NF_REPEAT) return verdict; goto repeat;

From: YueHaibing yuehaibing@huawei.com

[ Upstream commit 719c7d563c17b150877cee03a4b812a424989dfa ]

BUG: KASAN: use-after-free in ip_vs_in.part.29+0xe8/0xd20 [ip_vs] Read of size 4 at addr ffff8881e9b26e2c by task sshd/5603

CPU: 0 PID: 5603 Comm: sshd Not tainted 4.19.39+ #30 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 Call Trace: dump_stack+0x71/0xab print_address_description+0x6a/0x270 kasan_report+0x179/0x2c0 ip_vs_in.part.29+0xe8/0xd20 [ip_vs] ip_vs_in+0xd8/0x170 [ip_vs] nf_hook_slow+0x5f/0xe0 __ip_local_out+0x1d5/0x250 ip_local_out+0x19/0x60 __tcp_transmit_skb+0xba1/0x14f0 tcp_write_xmit+0x41f/0x1ed0 ? _copy_from_iter_full+0xca/0x340 __tcp_push_pending_frames+0x52/0x140 tcp_sendmsg_locked+0x787/0x1600 ? tcp_sendpage+0x60/0x60 ? inet_sk_set_state+0xb0/0xb0 tcp_sendmsg+0x27/0x40 sock_sendmsg+0x6d/0x80 sock_write_iter+0x121/0x1c0 ? sock_sendmsg+0x80/0x80 __vfs_write+0x23e/0x370 vfs_write+0xe7/0x230 ksys_write+0xa1/0x120 ? __ia32_sys_read+0x50/0x50 ? __audit_syscall_exit+0x3ce/0x450 do_syscall_64+0x73/0x200 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7ff6f6147c60 Code: 73 01 c3 48 8b 0d 28 12 2d 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 5d 73 2d 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 RSP: 002b:00007ffd772ead18 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 0000000000000034 RCX: 00007ff6f6147c60 RDX: 0000000000000034 RSI: 000055df30a31270 RDI: 0000000000000003 RBP: 000055df30a31270 R08: 0000000000000000 R09: 0000000000000000 R10: 00007ffd772ead70 R11: 0000000000000246 R12: 00007ffd772ead74 R13: 00007ffd772eae20 R14: 00007ffd772eae24 R15: 000055df2f12ddc0

Allocated by task 6052: kasan_kmalloc+0xa0/0xd0 __kmalloc+0x10a/0x220 ops_init+0x97/0x190 register_pernet_operations+0x1ac/0x360 register_pernet_subsys+0x24/0x40 0xffffffffc0ea016d do_one_initcall+0x8b/0x253 do_init_module+0xe3/0x335 load_module+0x2fc0/0x3890 __do_sys_finit_module+0x192/0x1c0 do_syscall_64+0x73/0x200 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 6067: __kasan_slab_free+0x130/0x180 kfree+0x90/0x1a0 ops_free_list.part.7+0xa6/0xc0 unregister_pernet_operations+0x18b/0x1f0 unregister_pernet_subsys+0x1d/0x30 ip_vs_cleanup+0x1d/0xd2f [ip_vs] __x64_sys_delete_module+0x20c/0x300 do_syscall_64+0x73/0x200 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The buggy address belongs to the object at ffff8881e9b26600 which belongs to the cache kmalloc-4096 of size 4096 The buggy address is located 2092 bytes inside of 4096-byte region [ffff8881e9b26600, ffff8881e9b27600) The buggy address belongs to the page: page:ffffea0007a6c800 count:1 mapcount:0 mapping:ffff888107c0e600 index:0x0 compound_mapcount: 0 flags: 0x17ffffc0008100(slab|head) raw: 0017ffffc0008100 dead000000000100 dead000000000200 ffff888107c0e600 raw: 0000000000000000 0000000080070007 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected

while unregistering ipvs module, ops_free_list calls __ip_vs_cleanup, then nf_unregister_net_hooks be called to do remove nf hook entries. It need a RCU period to finish, however net->ipvs is set to NULL immediately, which will trigger NULL pointer dereference when a packet is hooked and handled by ip_vs_in where net->ipvs is dereferenced.

Another scene is ops_free_list call ops_free to free the net_generic directly while __ip_vs_cleanup finished, then calling ip_vs_in will triggers use-after-free.

This patch moves nf_unregister_net_hooks from __ip_vs_cleanup() to __ip_vs_dev_cleanup(), where rcu_barrier() is called by unregister_pernet_device -> unregister_pernet_operations, that will do the needed grace period.

Reported-by: Hulk Robot hulkci@huawei.com Fixes: efe41606184e ("ipvs: convert to use pernet nf_hook api") Suggested-by: Julian Anastasov ja@ssi.bg Signed-off-by: YueHaibing yuehaibing@huawei.com Acked-by: Julian Anastasov ja@ssi.bg Signed-off-by: Simon Horman horms@verge.net.au Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/ipvs/ip_vs_core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 14457551bcb4..8ebf21149ec3 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -2312,7 +2312,6 @@ static void __net_exit __ip_vs_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net);

- nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */ ip_vs_conn_net_cleanup(ipvs); ip_vs_app_net_cleanup(ipvs); @@ -2327,6 +2326,7 @@ static void __net_exit __ip_vs_dev_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); EnterFunction(2); + nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); ip_vs_sync_net_cleanup(ipvs);

From: Florian Westphal fw@strlen.de

[ Upstream commit 6bac76db1da3cb162c425d58ae421486f8e43955 ]

Due to copy&paste error nf_nat_mangle_udp_packet passes IPPROTO_TCP, resulting in incorrect udp checksum when payload had to be mangled.

Fixes: dac3fe72596f9 ("netfilter: nat: remove csum_recalc hook") Reported-by: Marc Haber mh+netdev@zugschlus.de Tested-by: Marc Haber mh+netdev@zugschlus.de Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_nat_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index ccc06f7539d7..53aeb12b70fb 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -170,7 +170,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) return true;

- nf_nat_csum_recalc(skb, nf_ct_l3num(ct), IPPROTO_TCP, + nf_nat_csum_recalc(skb, nf_ct_l3num(ct), IPPROTO_UDP, udph, &udph->check, datalen, oldlen);

return true;

From: Anju T Sudhakar anju@linux.vnet.ibm.com

[ Upstream commit b59bd3527fe3c1939340df558d7f9d568fc9f882 ]

Currently init_imc_pmu() can fail either because we try to register an IMC unit with an invalid domain (i.e an IMC node not supported by the kernel) or something went wrong while registering a valid IMC unit. In both the cases kernel provides a 'Register failed' error message.

For example when trace-imc node is not supported by the kernel, but skiboot advertises a trace-imc node we print:

IMC Unknown Device type IMC PMU (null) Register failed

To avoid confusion just print the unknown device type message, before attempting PMU registration, so the second message isn't printed.

Fixes: 8f95faaac56c ("powerpc/powernv: Detect and create IMC device") Reported-by: Pavaman Subramaniyam pavsubra@in.ibm.com Signed-off-by: Anju T Sudhakar anju@linux.vnet.ibm.com Reviewed-by: Madhavan Srinivasan maddy@linux.vnet.ibm.com [mpe: Reword change log a bit] Signed-off-by: Michael Ellerman mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/platforms/powernv/opal-imc.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c index 3d27f02695e4..828f6656f8f7 100644 --- a/arch/powerpc/platforms/powernv/opal-imc.c +++ b/arch/powerpc/platforms/powernv/opal-imc.c @@ -161,6 +161,10 @@ static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain) struct imc_pmu *pmu_ptr; u32 offset;

+ /* Return for unknown domain */ + if (domain < 0) + return -EINVAL; + /* memory for pmu */ pmu_ptr = kzalloc(sizeof(*pmu_ptr), GFP_KERNEL); if (!pmu_ptr)

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit ccfb62f27beb295103e9392462b20a6ed807d0ea ]

The user can change the device_name with the IMSETDEVNAME ioctl, but we need to ensure that the user's name is NUL terminated. Otherwise it could result in a buffer overflow when we copy the name back to the user with IMGETDEVINFO ioctl.

I also changed two strcpy() calls which handle the name to strscpy(). Hopefully, there aren't any other ways to create a too long name, but it's nice to do this as a kernel hardening measure.

Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/isdn/mISDN/socket.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index a14e35d40538..84e1d4c2db66 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -393,7 +393,7 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) memcpy(di.channelmap, dev->channelmap, sizeof(di.channelmap)); di.nrbchan = dev->nrbchan; - strcpy(di.name, dev_name(&dev->dev)); + strscpy(di.name, dev_name(&dev->dev), sizeof(di.name)); if (copy_to_user((void __user *)arg, &di, sizeof(di))) err = -EFAULT; } else @@ -676,7 +676,7 @@ base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) memcpy(di.channelmap, dev->channelmap, sizeof(di.channelmap)); di.nrbchan = dev->nrbchan; - strcpy(di.name, dev_name(&dev->dev)); + strscpy(di.name, dev_name(&dev->dev), sizeof(di.name)); if (copy_to_user((void __user *)arg, &di, sizeof(di))) err = -EFAULT; } else @@ -690,6 +690,7 @@ base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) err = -EFAULT; break; } + dn.name[sizeof(dn.name) - 1] = '\0'; dev = get_mdevice(dn.id); if (dev) err = device_rename(&dev->dev, dn.name);

From: Yabin Cui yabinc@google.com

[ Upstream commit 1b038c6e05ff70a1e66e3e571c2e6106bdb75f53 ]

In perf_output_put_handle(), an IRQ/NMI can happen in below location and write records to the same ring buffer:

... local_dec_and_test(&rb->nest) ... <-- an IRQ/NMI can happen here rb->user_page->data_head = head; ...

In this case, a value A is written to data_head in the IRQ, then a value B is written to data_head after the IRQ. And A > B. As a result, data_head is temporarily decreased from A to B. And a reader may see data_head < data_tail if it read the buffer frequently enough, which creates unexpected behaviors.

This can be fixed by moving dec(&rb->nest) to after updating data_head, which prevents the IRQ/NMI above from updating data_head.

[ Split up by peterz. ]

Signed-off-by: Yabin Cui yabinc@google.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@kernel.org Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Cc: mark.rutland@arm.com Fixes: ef60777c9abd ("perf: Optimize the perf_output() path by removing IRQ-disables") Link: http://lkml.kernel.org/r/20190517115418.224478157@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/ring_buffer.c | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 674b35383491..009467a60578 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -51,11 +51,18 @@ again: head = local_read(&rb->head);

/* - * IRQ/NMI can happen here, which means we can miss a head update. + * IRQ/NMI can happen here and advance @rb->head, causing our + * load above to be stale. */

- if (!local_dec_and_test(&rb->nest)) + /* + * If this isn't the outermost nesting, we don't have to update + * @rb->user_page->data_head. + */ + if (local_read(&rb->nest) > 1) { + local_dec(&rb->nest); goto out; + }

/* * Since the mmap() consumer (userspace) can run on a different CPU: @@ -87,9 +94,18 @@ again: rb->user_page->data_head = head;

/* - * Now check if we missed an update -- rely on previous implied - * compiler barriers to force a re-read. + * We must publish the head before decrementing the nest count, + * otherwise an IRQ/NMI can publish a more recent head value and our + * write will (temporarily) publish a stale value. + */ + barrier(); + local_set(&rb->nest, 0); + + /* + * Ensure we decrement @rb->nest before we validate the @rb->head. + * Otherwise we cannot be sure we caught the 'last' nested update. */ + barrier(); if (unlikely(head != local_read(&rb->head))) { local_inc(&rb->nest); goto again;

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 4d839dd9e4356bbacf3eb0ab13a549b83b008c21 ]

We must use {READ,WRITE}_ONCE() on rb->user_page data such that concurrent usage will see whole values. A few key sites were missing this.

Suggested-by: Yabin Cui yabinc@google.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Arnaldo Carvalho de Melo acme@redhat.com Cc: Jiri Olsa jolsa@redhat.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Stephane Eranian eranian@google.com Cc: Thomas Gleixner tglx@linutronix.de Cc: Vince Weaver vincent.weaver@maine.edu Cc: acme@kernel.org Cc: mark.rutland@arm.com Cc: namhyung@kernel.org Fixes: 7b732a750477 ("perf_counter: new output ABI - part 1") Link: http://lkml.kernel.org/r/20190517115418.394192145@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/ring_buffer.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 4b5f8d932400..7a0c73e4b3eb 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -100,7 +100,7 @@ again: * See perf_output_begin(). */ smp_wmb(); /* B, matches C */ - rb->user_page->data_head = head; + WRITE_ONCE(rb->user_page->data_head, head);

/* * We must publish the head before decrementing the nest count, @@ -496,7 +496,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) perf_event_aux_event(handle->event, aux_head, size, handle->aux_flags);

- rb->user_page->aux_head = rb->aux_head; + WRITE_ONCE(rb->user_page->aux_head, rb->aux_head); if (rb_need_aux_wakeup(rb)) wakeup = true;

@@ -528,7 +528,7 @@ int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size)

rb->aux_head += size;

- rb->user_page->aux_head = rb->aux_head; + WRITE_ONCE(rb->user_page->aux_head, rb->aux_head); if (rb_need_aux_wakeup(rb)) { perf_output_wakeup(handle); handle->wakeup = rb->aux_wakeup + rb->aux_watermark;

From: Gen Zhang blackgod016574@gmail.com

[ Upstream commit 4e78921ba4dd0aca1cc89168f45039add4183f8e ]

The old_memmap flow in efi_call_phys_prolog() performs numerous memory allocations, and either does not check for failure at all, or it does but fails to propagate it back to the caller, which may end up calling into the firmware with an incomplete 1:1 mapping.

So let's fix this by returning NULL from efi_call_phys_prolog() on memory allocation failures only, and by handling this condition in the caller. Also, clean up any half baked sets of page tables that we may have created before returning with a NULL return value.

Note that any failure at this level will trigger a panic() two levels up, so none of this makes a huge difference, but it is a nice cleanup nonetheless.

[ardb: update commit log, add efi_call_phys_epilog() call on error path]

Signed-off-by: Gen Zhang blackgod016574@gmail.com Signed-off-by: Ard Biesheuvel ard.biesheuvel@linaro.org Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Cc: Rob Bradford robert.bradford@intel.com Cc: Thomas Gleixner tglx@linutronix.de Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20190525112559.7917-2-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/platform/efi/efi.c | 2 ++ arch/x86/platform/efi/efi_64.c | 9 ++++++--- 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index e1cb01a22fa8..a7189a3b4d70 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -85,6 +85,8 @@ static efi_status_t __init phys_efi_set_virtual_address_map( pgd_t *save_pgd;

save_pgd = efi_call_phys_prolog(); + if (!save_pgd) + return EFI_ABORTED;

/* Disable interrupts around EFI calls: */ local_irq_save(flags); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index cf0347f61b21..08ce8177c3af 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -84,13 +84,15 @@ pgd_t * __init efi_call_phys_prolog(void)

if (!efi_enabled(EFI_OLD_MEMMAP)) { efi_switch_mm(&efi_mm); - return NULL; + return efi_mm.pgd; }

early_code_mapping_set_exec(1);

n_pgds = DIV_ROUND_UP((max_pfn << PAGE_SHIFT), PGDIR_SIZE); save_pgd = kmalloc_array(n_pgds, sizeof(*save_pgd), GFP_KERNEL); + if (!save_pgd) + return NULL;

/* * Build 1:1 identity mapping for efi=old_map usage. Note that @@ -138,10 +140,11 @@ pgd_t * __init efi_call_phys_prolog(void) pgd_offset_k(pgd * PGDIR_SIZE)->pgd &= ~_PAGE_NX; }

-out: __flush_tlb_all(); - return save_pgd; +out: + efi_call_phys_epilog(save_pgd); + return NULL; }

void __init efi_call_phys_epilog(pgd_t *save_pgd)

From: Biao Huang biao.huang@mediatek.com

[ Upstream commit 5e7f7fc538d894b2d9aa41876b8dcf35f5fe11e6 ]

The specific clk_csr value can be zero, and stmmac_clk is necessary for MDC clock which can be set dynamically. So, change the condition from plat->clk_csr to plat->stmmac_clk to fix clk_csr can't be zero issue.

Fixes: cd7201f477b9 ("stmmac: MDC clock dynamically based on the csr clock input") Signed-off-by: Biao Huang biao.huang@mediatek.com Acked-by: Alexandre TORGUE alexandre.torgue@st.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++--- drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 5 ++++- 2 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8cebc44108b2..635d88d82610 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4380,10 +4380,10 @@ int stmmac_dvr_probe(struct device *device, * set the MDC clock dynamically according to the csr actual * clock input. */ - if (!priv->plat->clk_csr) - stmmac_clk_csr_set(priv); - else + if (priv->plat->clk_csr >= 0) priv->clk_csr = priv->plat->clk_csr; + else + stmmac_clk_csr_set(priv);

stmmac_check_pcs_mode(priv);

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3031f2bf15d6..f45bfbef97d0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -408,7 +408,10 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) /* Default to phy auto-detection */ plat->phy_addr = -1;

- /* Get clk_csr from device tree */ + /* Default to get clk_csr from stmmac_clk_crs_set(), + * or get clk_csr from device tree. + */ + plat->clk_csr = -1; of_property_read_u32(np, "clk_csr", &plat->clk_csr);

/* "snps,phy-addr" is not a standard property. Mark it as deprecated

From: Pavel Begunkov asml.silence@gmail.com

[ Upstream commit a278682dad37fd2f8d2f30d8e84e376a856ab472 ]

If io_copy_iov() fails, it will break the loop and report success, albeit partially completed operation.

Signed-off-by: Pavel Begunkov asml.silence@gmail.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/io_uring.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c index 30a5687a17b6..69ff94558758 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -2505,7 +2505,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,

ret = io_copy_iov(ctx, &iov, arg, i); if (ret) - break; + goto err;

/* * Don't impose further limits on the size and buffer

From: Ioana Radulescu ruxandra.radulescu@nxp.com

[ Upstream commit bd8460fa4de46e9d6177af4fe33bf0763a7af4b7 ]

Use PTR_ERR_OR_ZERO instead of PTR_ERR in cases where zero is a valid input. Reported by smatch.

Signed-off-by: Ioana Radulescu ruxandra.radulescu@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 57cbaa38d247..df371c81a706 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1966,7 +1966,7 @@ alloc_channel(struct dpaa2_eth_priv *priv)

channel->dpcon = setup_dpcon(priv); if (IS_ERR_OR_NULL(channel->dpcon)) { - err = PTR_ERR(channel->dpcon); + err = PTR_ERR_OR_ZERO(channel->dpcon); goto err_setup; }

@@ -2022,7 +2022,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv) /* Try to allocate a channel */ channel = alloc_channel(priv); if (IS_ERR_OR_NULL(channel)) { - err = PTR_ERR(channel); + err = PTR_ERR_OR_ZERO(channel); if (err != -EPROBE_DEFER) dev_info(dev, "No affine channel for cpu %d and above\n", i);

From: "Rafael J. Wysocki" rafael.j.wysocki@intel.com

[ Upstream commit 9a51c6b1f9e0239a9435db036b212498a2a3b75c ]

Both acpi_pci_need_resume() and acpi_dev_needs_resume() check if the current ACPI wakeup configuration of the device matches what is expected as far as system wakeup from sleep states is concerned, as reflected by the device_may_wakeup() return value for the device.

However, they only should do that if wakeup.flags.valid is set for the device's ACPI companion, because otherwise the wakeup.prepare_count value for it is meaningless.

Add the missing wakeup.flags.valid checks to these functions.

Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/acpi/device_pm.c | 4 ++-- drivers/pci/pci-acpi.c | 3 ++- 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index 824ae985ad93..ccb59768b1f3 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -949,8 +949,8 @@ static bool acpi_dev_needs_resume(struct device *dev, struct acpi_device *adev) u32 sys_target = acpi_target_system_state(); int ret, state;

- if (!pm_runtime_suspended(dev) || !adev || - device_may_wakeup(dev) != !!adev->wakeup.prepare_count) + if (!pm_runtime_suspended(dev) || !adev || (adev->wakeup.flags.valid && + device_may_wakeup(dev) != !!adev->wakeup.prepare_count)) return true;

if (sys_target == ACPI_STATE_S0) diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index e1949f7efd9c..bf32fde328c2 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -666,7 +666,8 @@ static bool acpi_pci_need_resume(struct pci_dev *dev) if (!adev || !acpi_device_power_manageable(adev)) return false;

- if (device_may_wakeup(&dev->dev) != !!adev->wakeup.prepare_count) + if (adev->wakeup.flags.valid && + device_may_wakeup(&dev->dev) != !!adev->wakeup.prepare_count) return true;

if (acpi_target_system_state() == ACPI_STATE_S0)

From: Jan Kara jack@suse.cz

[ Upstream commit 33ec3e53e7b1869d7851e59e126bdb0fe0bd1982 ]

Loop module allows calling LOOP_SET_FD while there are other openers of the loop device. Even exclusive ones. This can lead to weird consequences such as kernel deadlocks like:

mount_bdev() lo_ioctl() udf_fill_super() udf_load_vrs() sb_set_blocksize() - sets desired block size B udf_tread() sb_bread() __bread_gfp(bdev, block, B) loop_set_fd() set_blocksize() - now __getblk_slow() indefinitely loops because B != bdev block size

Fix the problem by disallowing LOOP_SET_FD ioctl when there are exclusive openers of a loop device.

[Deliberately chosen not to CC stable as a user with priviledges to trigger this race has other means of taking the system down and this has a potential of breaking some weird userspace setup]

Reported-and-tested-by: syzbot+10007d66ca02b08f0e60@syzkaller.appspotmail.com Signed-off-by: Jan Kara jack@suse.cz Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/block/loop.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bf1c61cab8eb..21349a17f7f5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -919,9 +919,20 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!file) goto out;

+ /* + * If we don't hold exclusive handle for the device, upgrade to it + * here to avoid changing device under exclusive owner. + */ + if (!(mode & FMODE_EXCL)) { + bdgrab(bdev); + error = blkdev_get(bdev, mode | FMODE_EXCL, loop_set_fd); + if (error) + goto out_putf; + } + error = mutex_lock_killable(&loop_ctl_mutex); if (error) - goto out_putf; + goto out_bdev;

error = -EBUSY; if (lo->lo_state != Lo_unbound) @@ -985,10 +996,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, mutex_unlock(&loop_ctl_mutex); if (partscan) loop_reread_partitions(lo, bdev); + if (!(mode & FMODE_EXCL)) + blkdev_put(bdev, mode | FMODE_EXCL); return 0;

out_unlock: mutex_unlock(&loop_ctl_mutex); +out_bdev: + if (!(mode & FMODE_EXCL)) + blkdev_put(bdev, mode | FMODE_EXCL); out_putf: fput(file); out:

From: Lucas Stach l.stach@pengutronix.de

[ Upstream commit 1396500d673bd027683a0609ff84dca7eb6ea2e7 ]

The devcoredump needs to operate on a stable state of the MMU while it is writing the MMU state to the coredump. The missing lock allowed both the userspace submit, as well as the GPU job finish paths to mutate the MMU state while a coredump is under way.

Fixes: a8c21a5451d8 (drm/etnaviv: add initial etnaviv DRM driver) Reported-by: David Jander david@protonic.nl Signed-off-by: Lucas Stach l.stach@pengutronix.de Tested-by: David Jander david@protonic.nl Reviewed-by: Philipp Zabel p.zabel@pengutronix.de Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/etnaviv/etnaviv_dump.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c index 33854c94cb85..515515ef24f9 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c @@ -125,6 +125,8 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) return; etnaviv_dump_core = false;

+ mutex_lock(&gpu->mmu->lock); + mmu_size = etnaviv_iommu_dump_size(gpu->mmu);

/* We always dump registers, mmu, ring and end marker */ @@ -167,6 +169,7 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) iter.start = __vmalloc(file_size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY, PAGE_KERNEL); if (!iter.start) { + mutex_unlock(&gpu->mmu->lock); dev_warn(gpu->dev, "failed to allocate devcoredump file\n"); return; } @@ -234,6 +237,8 @@ void etnaviv_core_dump(struct etnaviv_gpu *gpu) obj->base.size); }

+ mutex_unlock(&gpu->mmu->lock); + etnaviv_core_dump_header(&iter, ETDUMP_BUF_END, iter.data);

dev_coredumpv(gpu->dev, iter.start, iter.data - iter.start, GFP_KERNEL);

From: Dmitry Bogdanov dmitry.bogdanov@aquantia.com

[ Upstream commit eaeb3b7494ba9159323814a8ce8af06a9277d99b ]

Driver stops producing skbs on ring if a packet with FCS error was coalesced into LRO session. Ring gets hang forever.

Thats a logical error in driver processing descriptors: When rx_stat indicates MAC Error, next pointer and eop flags are not filled. This confuses driver so it waits for descriptor 0 to be filled by HW.

Solution is fill next pointer and eop flag even for packets with FCS error.

Fixes: bab6de8fd180b ("net: ethernet: aquantia: Atlantic A0 and B0 specific functions.") Signed-off-by: Igor Russkikh igor.russkikh@aquantia.com Signed-off-by: Dmitry Bogdanov dmitry.bogdanov@aquantia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- .../aquantia/atlantic/hw_atl/hw_atl_b0.c | 61 ++++++++++--------- 1 file changed, 32 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index b31dba1b1a55..ec302fdfec63 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -702,38 +702,41 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, if ((rx_stat & BIT(0)) || rxd_wb->type & 0x1000U) { /* MAC error or DMA error */ buff->is_error = 1U; - } else { - if (self->aq_nic_cfg->is_rss) { - /* last 4 byte */ - u16 rss_type = rxd_wb->type & 0xFU; - - if (rss_type && rss_type < 0x8U) { - buff->is_hash_l4 = (rss_type == 0x4 || - rss_type == 0x5); - buff->rss_hash = rxd_wb->rss_hash; - } + } + if (self->aq_nic_cfg->is_rss) { + /* last 4 byte */ + u16 rss_type = rxd_wb->type & 0xFU; + + if (rss_type && rss_type < 0x8U) { + buff->is_hash_l4 = (rss_type == 0x4 || + rss_type == 0x5); + buff->rss_hash = rxd_wb->rss_hash; } + }

- if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) { - buff->len = rxd_wb->pkt_len % - AQ_CFG_RX_FRAME_MAX; - buff->len = buff->len ? - buff->len : AQ_CFG_RX_FRAME_MAX; - buff->next = 0U; - buff->is_eop = 1U; + if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) { + buff->len = rxd_wb->pkt_len % + AQ_CFG_RX_FRAME_MAX; + buff->len = buff->len ? + buff->len : AQ_CFG_RX_FRAME_MAX; + buff->next = 0U; + buff->is_eop = 1U; + } else { + buff->len = + rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ? + AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len; + + if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT & + rxd_wb->status) { + /* LRO */ + buff->next = rxd_wb->next_desc_ptr; + ++ring->stats.rx.lro_packets; } else { - if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT & - rxd_wb->status) { - /* LRO */ - buff->next = rxd_wb->next_desc_ptr; - ++ring->stats.rx.lro_packets; - } else { - /* jumbo */ - buff->next = - aq_ring_next_dx(ring, - ring->hw_head); - ++ring->stats.rx.jumbo_packets; - } + /* jumbo */ + buff->next = + aq_ring_next_dx(ring, + ring->hw_head); + ++ring->stats.rx.jumbo_packets; } } }

From: Vadim Pasternak vadimp@mellanox.com

[ Upstream commit 13067ef73f337336e3149f5bb9f3fd05fe7f87a0 ]

Fix wrong order in probing routine initialization - field `base_addr' is used before it's initialized. Move assignment of 'priv->base_addr` to the beginning, prior the call to mlxcpld_i2c_read_comm(). Wrong order caused the first read of capability register to be executed at wrong offset 0x0 instead of 0x2000. By chance it was a "good garbage" at 0x0 offset.

Fixes: 313ce648b5a4 ("i2c: mlxcpld: Add support for extended transaction length for i2c-mlxcpld") Signed-off-by: Vadim Pasternak vadimp@mellanox.com Signed-off-by: Wolfram Sang wsa@the-dreams.de Cc: stable@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i2c/busses/i2c-mlxcpld.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-mlxcpld.c b/drivers/i2c/busses/i2c-mlxcpld.c index 745ed43a22d6..2fd717d8dd30 100644 --- a/drivers/i2c/busses/i2c-mlxcpld.c +++ b/drivers/i2c/busses/i2c-mlxcpld.c @@ -503,6 +503,7 @@ static int mlxcpld_i2c_probe(struct platform_device *pdev) platform_set_drvdata(pdev, priv);

priv->dev = &pdev->dev; + priv->base_addr = MLXPLAT_CPLD_LPC_I2C_BASE_ADDR;

/* Register with i2c layer */ mlxcpld_i2c_adapter.timeout = usecs_to_jiffies(MLXCPLD_I2C_XFER_TO); @@ -518,7 +519,6 @@ static int mlxcpld_i2c_probe(struct platform_device *pdev) mlxcpld_i2c_adapter.nr = pdev->id; priv->adap = mlxcpld_i2c_adapter; priv->adap.dev.parent = &pdev->dev; - priv->base_addr = MLXPLAT_CPLD_LPC_I2C_BASE_ADDR; i2c_set_adapdata(&priv->adap, priv);

err = i2c_add_numbered_adapter(&priv->adap);

From: Sahitya Tummala stummala@codeaurora.org

[ Upstream commit f6122ed2a4f9c9c1c073ddf6308d1b2ac10e0781 ]

In the vfs_statx() context, during path lookup, the dentry gets added to sd->s_dentry via configfs_attach_attr(). In the end, vfs_statx() kills the dentry by calling path_put(), which invokes configfs_d_iput(). Ideally, this dentry must be removed from sd->s_dentry but it doesn't if the sd->s_count >= 3. As a result, sd->s_dentry is holding reference to a stale dentry pointer whose memory is already freed up. This results in use-after-free issue, when this stale sd->s_dentry is accessed later in configfs_readdir() path.

This issue can be easily reproduced, by running the LTP test case - sh fs_racer_file_list.sh /config (https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/fs/ra...)

Fixes: 76ae281f6307 ('configfs: fix race between dentry put and lookup') Signed-off-by: Sahitya Tummala stummala@codeaurora.org Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org --- fs/configfs/dir.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 39843fa7e11b..073e788f7810 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -58,15 +58,13 @@ static void configfs_d_iput(struct dentry * dentry, if (sd) { /* Coordinate with configfs_readdir */ spin_lock(&configfs_dirent_lock); - /* Coordinate with configfs_attach_attr where will increase - * sd->s_count and update sd->s_dentry to new allocated one. - * Only set sd->dentry to null when this dentry is the only - * sd owner. - * If not do so, configfs_d_iput may run just after - * configfs_attach_attr and set sd->s_dentry to null - * even it's still in use. + /* + * Set sd->s_dentry to null only when this dentry is the one + * that is going to be killed. Otherwise configfs_d_iput may + * run just after configfs_attach_attr and set sd->s_dentry to + * NULL even it's still in use. */ - if (atomic_read(&sd->s_count) <= 2) + if (sd->s_dentry == dentry) sd->s_dentry = NULL;

spin_unlock(&configfs_dirent_lock);

From: Harald Freudenberger freude@linux.ibm.com

[ Upstream commit 7379e652797c0b9b5f6caea1576f2dff9ce6a708 ]

The zcrypt device driver does not handle CPRBs which address a control domain correctly. This fix introduces a workaround: The domain field of the request CPRB is checked if there is a valid domain value in there. If this is true and the value is a control only domain (a domain which is enabled in the crypto config ADM mask but disabled in the AQM mask) the CPRB is forwarded to the default usage domain. If there is no default domain, the request is rejected with an ENODEV.

This fix is important for maintaining crypto adapters. For example one LPAR can use a crypto adapter domain ('Control and Usage') but another LPAR needs to be able to maintain this adapter domain ('Control'). Scenarios like this did not work properly and the patch enables this.

Signed-off-by: Harald Freudenberger freude@linux.ibm.com Signed-off-by: Heiko Carstens heiko.carstens@de.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/include/asm/ap.h | 4 ++-- drivers/s390/crypto/ap_bus.c | 26 ++++++++++++++++++++++---- drivers/s390/crypto/ap_bus.h | 3 +++ drivers/s390/crypto/zcrypt_api.c | 17 ++++++++++++++--- 4 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h index e94a0a28b5eb..aea32dda3d14 100644 --- a/arch/s390/include/asm/ap.h +++ b/arch/s390/include/asm/ap.h @@ -160,8 +160,8 @@ struct ap_config_info { unsigned char Nd; /* max # of Domains - 1 */ unsigned char _reserved3[10]; unsigned int apm[8]; /* AP ID mask */ - unsigned int aqm[8]; /* AP queue mask */ - unsigned int adm[8]; /* AP domain mask */ + unsigned int aqm[8]; /* AP (usage) queue mask */ + unsigned int adm[8]; /* AP (control) domain mask */ unsigned char _reserved4[16]; } __aligned(8);

diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 1546389d71db..6717536a633c 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -254,19 +254,37 @@ static inline int ap_test_config_card_id(unsigned int id) }

/* - * ap_test_config_domain(): Test, whether an AP usage domain is configured. + * ap_test_config_usage_domain(): Test, whether an AP usage domain + * is configured. * @domain AP usage domain ID * * Returns 0 if the usage domain is not configured * 1 if the usage domain is configured or * if the configuration information is not available */ -static inline int ap_test_config_domain(unsigned int domain) +int ap_test_config_usage_domain(unsigned int domain) { if (!ap_configuration) /* QCI not supported */ return domain < 16; return ap_test_config(ap_configuration->aqm, domain); } +EXPORT_SYMBOL(ap_test_config_usage_domain); + +/* + * ap_test_config_ctrl_domain(): Test, whether an AP control domain + * is configured. + * @domain AP control domain ID + * + * Returns 1 if the control domain is configured + * 0 in all other cases + */ +int ap_test_config_ctrl_domain(unsigned int domain) +{ + if (!ap_configuration) /* QCI not supported */ + return 0; + return ap_test_config(ap_configuration->adm, domain); +} +EXPORT_SYMBOL(ap_test_config_ctrl_domain);

/** * ap_query_queue(): Check if an AP queue is available. @@ -1267,7 +1285,7 @@ static void ap_select_domain(void) best_domain = -1; max_count = 0; for (i = 0; i < AP_DOMAINS; i++) { - if (!ap_test_config_domain(i) || + if (!ap_test_config_usage_domain(i) || !test_bit_inv(i, ap_perms.aqm)) continue; count = 0; @@ -1442,7 +1460,7 @@ static void _ap_scan_bus_adapter(int id) (void *)(long) qid, __match_queue_device_with_qid); aq = dev ? to_ap_queue(dev) : NULL; - if (!ap_test_config_domain(dom)) { + if (!ap_test_config_usage_domain(dom)) { if (dev) { /* Queue device exists but has been * removed from configuration. diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h index 15a98a673c5c..6f3cf37776ca 100644 --- a/drivers/s390/crypto/ap_bus.h +++ b/drivers/s390/crypto/ap_bus.h @@ -251,6 +251,9 @@ void ap_wait(enum ap_wait wait); void ap_request_timeout(struct timer_list *t); void ap_bus_force_rescan(void);

+int ap_test_config_usage_domain(unsigned int domain); +int ap_test_config_ctrl_domain(unsigned int domain); + void ap_queue_init_reply(struct ap_queue *aq, struct ap_message *ap_msg); struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type); void ap_queue_prepare_remove(struct ap_queue *aq); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index c31b2d31cd83..03b1853464db 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -822,7 +822,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, struct ap_message ap_msg; unsigned int weight, pref_weight; unsigned int func_code; - unsigned short *domain; + unsigned short *domain, tdom; int qid = 0, rc = -ENODEV; struct module *mod;

@@ -834,6 +834,17 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, if (rc) goto out;

+ /* + * If a valid target domain is set and this domain is NOT a usage + * domain but a control only domain, use the default domain as target. + */ + tdom = *domain; + if (tdom >= 0 && tdom < AP_DOMAINS && + !ap_test_config_usage_domain(tdom) && + ap_test_config_ctrl_domain(tdom) && + ap_domain_index >= 0) + tdom = ap_domain_index; + pref_zc = NULL; pref_zq = NULL; spin_lock(&zcrypt_list_lock); @@ -856,8 +867,8 @@ static long _zcrypt_send_cprb(struct ap_perms *perms, /* check if device is online and eligible */ if (!zq->online || !zq->ops->send_cprb || - ((*domain != (unsigned short) AUTOSELECT) && - (*domain != AP_QID_QUEUE(zq->queue->qid)))) + (tdom != (unsigned short) AUTOSELECT && + tdom != AP_QID_QUEUE(zq->queue->qid))) continue; /* check if device node has admission for this queue */ if (!zcrypt_check_queue(perms,

From: Thomas Richter tmricht@linux.ibm.com

[ Upstream commit 6738028dd57df064b969d8392c943ef3b3ae705d ]

Command 'perf record' and 'perf report' on a system without kernel debuginfo packages uses /proc/kallsyms and /proc/modules to find addresses for kernel and module symbols. On x86 this works for root and non-root users.

On s390, when invoked as non-root user, many of the following warnings are shown and module symbols are missing:

proc/{kallsyms,modules} inconsistency while looking for "[sha1_s390]" module!

Command 'perf record' creates a list of module start addresses by parsing the output of /proc/modules and creates a PERF_RECORD_MMAP record for the kernel and each module. The following function call sequence is executed:

machine__create_kernel_maps machine__create_module modules__parse machine__create_module --> for each line in /proc/modules arch__fix_module_text_start

Function arch__fix_module_text_start() is s390 specific. It opens file /sys/module/<name>/sections/.text to extract the module's .text section start address. On s390 the module loader prepends a header before the first section, whereas on x86 the module's text section address is identical the the module's load address.

However module section files are root readable only. For non-root the read operation fails and machine__create_module() returns an error. Command perf record does not generate any PERF_RECORD_MMAP record for loaded modules. Later command perf report complains about missing module maps.

To fix this function arch__fix_module_text_start() always returns success. For root users there is no change, for non-root users the module's load address is used as module's text start address (the prepended header then counts as part of the text section).

This enable non-root users to use module symbols and avoid the warning when perf report is executed.

Output before:

[tmricht@m83lp54 perf]$ ./perf report -D | fgrep MMAP 0 0x168 [0x50]: PERF_RECORD_MMAP ... x [kernel.kallsyms]_text

Output after:

[tmricht@m83lp54 perf]$ ./perf report -D | fgrep MMAP 0 0x168 [0x50]: PERF_RECORD_MMAP ... x [kernel.kallsyms]_text 0 0x1b8 [0x98]: PERF_RECORD_MMAP ... x /lib/modules/.../autofs4.ko.xz 0 0x250 [0xa8]: PERF_RECORD_MMAP ... x /lib/modules/.../sha_common.ko.xz 0 0x2f8 [0x98]: PERF_RECORD_MMAP ... x /lib/modules/.../des_generic.ko.xz

Signed-off-by: Thomas Richter tmricht@linux.ibm.com Reviewed-by: Hendrik Brueckner brueckner@linux.ibm.com Cc: Heiko Carstens heiko.carstens@de.ibm.com Link: http://lkml.kernel.org/r/20190522144601.50763-4-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/arch/s390/util/machine.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 0b2054007314..a19690a17291 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -5,16 +5,19 @@ #include "util.h" #include "machine.h" #include "api/fs/fs.h" +#include "debug.h"

int arch__fix_module_text_start(u64 *start, const char *name) { + u64 m_start = *start; char path[PATH_MAX];

snprintf(path, PATH_MAX, "module/%.*s/sections/.text", (int)strlen(name) - 2, name + 1); - - if (sysfs__read_ull(path, (unsigned long long *)start) < 0) - return -1; + if (sysfs__read_ull(path, (unsigned long long *)start) < 0) { + pr_debug2("Using module %s start:%#lx\n", path, m_start); + *start = m_start; + }

return 0; }

From: Madalin Bucur madalin.bucur@nxp.com

[ Upstream commit 7aae703f8096d21e34ce5f34f16715587bc30902 ]

Make sure only the portals for the online CPUs are used. Without this change, there are issues when someone boots with maxcpus=n, with n < actual number of cores available as frames either received or corresponding to the transmit confirmation path would be offered for dequeue to the offline CPU portals, getting lost.

Signed-off-by: Madalin Bucur madalin.bucur@nxp.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 9 ++++----- drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 4 ++-- 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index d3f2408dc9e8..f38c3fa7d705 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -780,7 +780,7 @@ static void dpaa_eth_add_channel(u16 channel) struct qman_portal *portal; int cpu;

- for_each_cpu(cpu, cpus) { + for_each_cpu_and(cpu, cpus, cpu_online_mask) { portal = qman_get_affine_portal(cpu); qman_p_static_dequeue_add(portal, pool); } @@ -896,7 +896,7 @@ static void dpaa_fq_setup(struct dpaa_priv *priv, u16 channels[NR_CPUS]; struct dpaa_fq *fq;

- for_each_cpu(cpu, affine_cpus) + for_each_cpu_and(cpu, affine_cpus, cpu_online_mask) channels[num_portals++] = qman_affine_channel(cpu);

if (num_portals == 0) @@ -2174,7 +2174,6 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget) if (cleaned < budget) { napi_complete_done(napi, cleaned); qman_p_irqsource_add(np->p, QM_PIRQ_DQRI); - } else if (np->down) { qman_p_irqsource_add(np->p, QM_PIRQ_DQRI); } @@ -2448,7 +2447,7 @@ static void dpaa_eth_napi_enable(struct dpaa_priv *priv) struct dpaa_percpu_priv *percpu_priv; int i;

- for_each_possible_cpu(i) { + for_each_online_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i);

percpu_priv->np.down = 0; @@ -2461,7 +2460,7 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv) struct dpaa_percpu_priv *percpu_priv; int i;

- for_each_possible_cpu(i) { + for_each_online_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i);

percpu_priv->np.down = 1; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index bdee441bc3b7..7ce2e99b594d 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -569,7 +569,7 @@ static int dpaa_set_coalesce(struct net_device *dev, qman_dqrr_get_ithresh(portal, &prev_thresh);

/* set new values */ - for_each_cpu(cpu, cpus) { + for_each_cpu_and(cpu, cpus, cpu_online_mask) { portal = qman_get_affine_portal(cpu); res = qman_portal_set_iperiod(portal, period); if (res) @@ -586,7 +586,7 @@ static int dpaa_set_coalesce(struct net_device *dev,

revert_values: /* restore previous values */ - for_each_cpu(cpu, cpus) { + for_each_cpu_and(cpu, cpus, cpu_online_mask) { if (!needs_revert[cpu]) continue; portal = qman_get_affine_portal(cpu);

From: Ross Lagerwall ross.lagerwall@citrix.com

[ Upstream commit d10e0cc113c9e1b64b5c6e3db37b5c839794f3df ]

During a suspend/resume, the xenwatch thread waits for all outstanding xenstore requests and transactions to complete. This does not work correctly for transactions started by userspace because it waits for them to complete after freezing userspace threads which means the transactions have no way of completing, resulting in a deadlock. This is trivial to reproduce by running this script and then suspending the VM:

import pyxs, time c = pyxs.client.Client(xen_bus_path="/dev/xen/xenbus") c.connect() c.transaction() time.sleep(3600)

Even if this deadlock were resolved, misbehaving userspace should not prevent a VM from being migrated. So, instead of waiting for these transactions to complete before suspending, store the current generation id for each transaction when it is started. The global generation id is incremented during resume. If the caller commits the transaction and the generation id does not match the current generation id, return EAGAIN so that they try again. If the transaction was instead discarded, return OK since no changes were made anyway.

This only affects users of the xenbus file interface. In-kernel users of xenbus are assumed to be well-behaved and complete all transactions before freezing.

Signed-off-by: Ross Lagerwall ross.lagerwall@citrix.com Reviewed-by: Juergen Gross jgross@suse.com Signed-off-by: Boris Ostrovsky boris.ostrovsky@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/xen/xenbus/xenbus.h | 3 +++ drivers/xen/xenbus/xenbus_dev_frontend.c | 18 ++++++++++++++++++ drivers/xen/xenbus/xenbus_xs.c | 7 +++++-- 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 092981171df1..d75a2385b37c 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -83,6 +83,7 @@ struct xb_req_data { int num_vecs; int err; enum xb_req_state state; + bool user_req; void (*cb)(struct xb_req_data *); void *par; }; @@ -133,4 +134,6 @@ void xenbus_ring_ops_init(void); int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par); void xenbus_dev_queue_reply(struct xb_req_data *req);

+extern unsigned int xb_dev_generation_id; + #endif diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 0782ff3c2273..39c63152a358 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -62,6 +62,8 @@

#include "xenbus.h"

+unsigned int xb_dev_generation_id; + /* * An element of a list of outstanding transactions, for which we're * still waiting a reply. @@ -69,6 +71,7 @@ struct xenbus_transaction_holder { struct list_head list; struct xenbus_transaction handle; + unsigned int generation_id; };

/* @@ -441,6 +444,7 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } + trans->generation_id = xb_dev_generation_id; list_add(&trans->list, &u->transactions); } else if (msg->hdr.tx_id != 0 && !xenbus_get_transaction(u, msg->hdr.tx_id)) @@ -449,6 +453,20 @@ static int xenbus_write_transaction(unsigned msg_type, !(msg->hdr.len == 2 && (!strcmp(msg->body, "T") || !strcmp(msg->body, "F")))) return xenbus_command_reply(u, XS_ERROR, "EINVAL"); + else if (msg_type == XS_TRANSACTION_END) { + trans = xenbus_get_transaction(u, msg->hdr.tx_id); + if (trans && trans->generation_id != xb_dev_generation_id) { + list_del(&trans->list); + kfree(trans); + if (!strcmp(msg->body, "T")) + return xenbus_command_reply(u, XS_ERROR, + "EAGAIN"); + else + return xenbus_command_reply(u, + XS_TRANSACTION_END, + "OK"); + } + }

rc = xenbus_dev_request_and_reply(&msg->hdr, u); if (rc && trans) { diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 49a3874ae6bb..ddc18da61834 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -105,6 +105,7 @@ static void xs_suspend_enter(void)

static void xs_suspend_exit(void) { + xb_dev_generation_id++; spin_lock(&xs_state_lock); xs_suspend_active--; spin_unlock(&xs_state_lock); @@ -125,7 +126,7 @@ static uint32_t xs_request_enter(struct xb_req_data *req) spin_lock(&xs_state_lock); }

- if (req->type == XS_TRANSACTION_START) + if (req->type == XS_TRANSACTION_START && !req->user_req) xs_state_users++; xs_state_users++; rq_id = xs_request_id++; @@ -140,7 +141,7 @@ void xs_request_exit(struct xb_req_data *req) spin_lock(&xs_state_lock); xs_state_users--; if ((req->type == XS_TRANSACTION_START && req->msg.type == XS_ERROR) || - (req->type == XS_TRANSACTION_END && + (req->type == XS_TRANSACTION_END && !req->user_req && !WARN_ON_ONCE(req->msg.type == XS_ERROR && !strcmp(req->body, "ENOENT")))) xs_state_users--; @@ -286,6 +287,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par) req->num_vecs = 1; req->cb = xenbus_dev_queue_reply; req->par = par; + req->user_req = true;

xs_send(req, msg);

@@ -313,6 +315,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->vec = iovec; req->num_vecs = num_vecs; req->cb = xs_wake_up; + req->user_req = false;

msg.req_id = 0; msg.tx_id = t.id;

From: Paul Mackerras paulus@ozlabs.org

[ Upstream commit 0d4ee88d92884c661fcafd5576da243aa943dc24 ]

Currently the HV KVM code uses kvm->lock in conjunction with a flag, kvm->arch.mmu_ready, to synchronize MMU setup and hold off vcpu execution until the MMU-related data structures are ready. However, this means that kvm->lock is being taken inside vcpu->mutex, which is contrary to Documentation/virtual/kvm/locking.txt and results in lockdep warnings.

To fix this, we add a new mutex, kvm->arch.mmu_setup_lock, which nests inside the vcpu mutexes, and is taken in the places where kvm->lock was taken that are related to MMU setup.

Additionally we take the new mutex in the vcpu creation code at the point where we are creating a new vcore, in order to provide mutual exclusion with kvmppc_update_lpcr() and ensure that an update to kvm->arch.lpcr doesn't get missed, which could otherwise lead to a stale vcore->lpcr value.

Signed-off-by: Paul Mackerras paulus@ozlabs.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/include/asm/kvm_host.h | 1 + arch/powerpc/kvm/book3s_64_mmu_hv.c | 36 ++++++++++++++--------------- arch/powerpc/kvm/book3s_hv.c | 31 ++++++++++++++++++------- 3 files changed, 42 insertions(+), 26 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index e6b5bb012ccb..8d3658275a34 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -317,6 +317,7 @@ struct kvm_arch { #endif struct kvmppc_ops *kvm_ops; #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE + struct mutex mmu_setup_lock; /* nests inside vcpu mutexes */ u64 l1_ptcr; int max_nested_lpid; struct kvm_nested_guest *nested_guests[KVM_MAX_NESTED_GUESTS]; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index be7bc070eae5..c1ced22455f9 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -63,7 +63,7 @@ struct kvm_resize_hpt { struct work_struct work; u32 order;

- /* These fields protected by kvm->lock */ + /* These fields protected by kvm->arch.mmu_setup_lock */

/* Possible values and their usage: * <0 an error occurred during allocation, @@ -73,7 +73,7 @@ struct kvm_resize_hpt { int error;

/* Private to the work thread, until error != -EBUSY, - * then protected by kvm->lock. + * then protected by kvm->arch.mmu_setup_lock. */ struct kvm_hpt_info hpt; }; @@ -139,7 +139,7 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order) long err = -EBUSY; struct kvm_hpt_info info;

- mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock); if (kvm->arch.mmu_ready) { kvm->arch.mmu_ready = 0; /* order mmu_ready vs. vcpus_running */ @@ -183,7 +183,7 @@ out: /* Ensure that each vcpu will flush its TLB on next entry. */ cpumask_setall(&kvm->arch.need_tlb_flush);

- mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock); return err; }

@@ -1447,7 +1447,7 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize)

static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize) { - if (WARN_ON(!mutex_is_locked(&kvm->lock))) + if (WARN_ON(!mutex_is_locked(&kvm->arch.mmu_setup_lock))) return;

if (!resize) @@ -1474,14 +1474,14 @@ static void resize_hpt_prepare_work(struct work_struct *work) if (WARN_ON(resize->error != -EBUSY)) return;

- mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock);

/* Request is still current? */ if (kvm->arch.resize_hpt == resize) { /* We may request large allocations here: - * do not sleep with kvm->lock held for a while. + * do not sleep with kvm->arch.mmu_setup_lock held for a while. */ - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock);

resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n", resize->order); @@ -1494,9 +1494,9 @@ static void resize_hpt_prepare_work(struct work_struct *work) if (WARN_ON(err == -EBUSY)) err = -EINPROGRESS;

- mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock); /* It is possible that kvm->arch.resize_hpt != resize - * after we grab kvm->lock again. + * after we grab kvm->arch.mmu_setup_lock again. */ }

@@ -1505,7 +1505,7 @@ static void resize_hpt_prepare_work(struct work_struct *work) if (kvm->arch.resize_hpt != resize) resize_hpt_release(kvm, resize);

- mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock); }

long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, @@ -1522,7 +1522,7 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, if (shift && ((shift < 18) || (shift > 46))) return -EINVAL;

- mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock);

resize = kvm->arch.resize_hpt;

@@ -1565,7 +1565,7 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm, ret = 100; /* estimated time in ms */

out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock); return ret; }

@@ -1588,7 +1588,7 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm, if (shift && ((shift < 18) || (shift > 46))) return -EINVAL;

- mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock);

resize = kvm->arch.resize_hpt;

@@ -1625,7 +1625,7 @@ out: smp_mb(); out_no_hpt: resize_hpt_release(kvm, resize); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock); return ret; }

@@ -1868,7 +1868,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, return -EINVAL;

/* lock out vcpus from running while we're doing this */ - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock); mmu_ready = kvm->arch.mmu_ready; if (mmu_ready) { kvm->arch.mmu_ready = 0; /* temporarily */ @@ -1876,7 +1876,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, smp_mb(); if (atomic_read(&kvm->arch.vcpus_running)) { kvm->arch.mmu_ready = 1; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock); return -EBUSY; } } @@ -1963,7 +1963,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf, /* Order HPTE updates vs. mmu_ready */ smp_wmb(); kvm->arch.mmu_ready = mmu_ready; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock);

if (err) return err; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index b2b29d4f9842..4519c55ba19d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -2257,11 +2257,17 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm, pr_devel("KVM: collision on id %u", id); vcore = NULL; } else if (!vcore) { + /* + * Take mmu_setup_lock for mutual exclusion + * with kvmppc_update_lpcr(). + */ err = -ENOMEM; vcore = kvmppc_vcore_create(kvm, id & ~(kvm->arch.smt_mode - 1)); + mutex_lock(&kvm->arch.mmu_setup_lock); kvm->arch.vcores[core] = vcore; kvm->arch.online_vcores++; + mutex_unlock(&kvm->arch.mmu_setup_lock); } } mutex_unlock(&kvm->lock); @@ -3820,7 +3826,7 @@ static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu) int r = 0; struct kvm *kvm = vcpu->kvm;

- mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock); if (!kvm->arch.mmu_ready) { if (!kvm_is_radix(kvm)) r = kvmppc_hv_setup_htab_rma(vcpu); @@ -3830,7 +3836,7 @@ static int kvmhv_setup_mmu(struct kvm_vcpu *vcpu) kvm->arch.mmu_ready = 1; } } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock); return r; }

@@ -4435,7 +4441,8 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,

/* * Update LPCR values in kvm->arch and in vcores. - * Caller must hold kvm->lock. + * Caller must hold kvm->arch.mmu_setup_lock (for mutual exclusion + * of kvm->arch.lpcr update). */ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask) { @@ -4487,7 +4494,7 @@ void kvmppc_setup_partition_table(struct kvm *kvm)

/* * Set up HPT (hashed page table) and RMA (real-mode area). - * Must be called with kvm->lock held. + * Must be called with kvm->arch.mmu_setup_lock held. */ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) { @@ -4575,7 +4582,10 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) goto out_srcu; }

-/* Must be called with kvm->lock held and mmu_ready = 0 and no vcpus running */ +/* + * Must be called with kvm->arch.mmu_setup_lock held and + * mmu_ready = 0 and no vcpus running. + */ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) { if (nesting_enabled(kvm)) @@ -4592,7 +4602,10 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm) return 0; }

-/* Must be called with kvm->lock held and mmu_ready = 0 and no vcpus running */ +/* + * Must be called with kvm->arch.mmu_setup_lock held and + * mmu_ready = 0 and no vcpus running. + */ int kvmppc_switch_mmu_to_radix(struct kvm *kvm) { int err; @@ -4697,6 +4710,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm) char buf[32]; int ret;

+ mutex_init(&kvm->arch.mmu_setup_lock); + /* Allocate the guest's logical partition ID */

lpid = kvmppc_alloc_lpid(); @@ -5222,7 +5237,7 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg) if (kvmhv_on_pseries() && !radix) return -EINVAL;

- mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.mmu_setup_lock); if (radix != kvm_is_radix(kvm)) { if (kvm->arch.mmu_ready) { kvm->arch.mmu_ready = 0; @@ -5250,7 +5265,7 @@ static int kvmhv_configure_mmu(struct kvm *kvm, struct kvm_ppc_mmuv3_cfg *cfg) err = 0;

out_unlock: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.mmu_setup_lock); return err; }

From: Paul Mackerras paulus@ozlabs.org

[ Upstream commit 5a3f49364c3ffa1107bd88f8292406e98c5d206c ]

Currently the HV KVM code takes the kvm->lock around calls to kvm_for_each_vcpu() and kvm_get_vcpu_by_id() (which can call kvm_for_each_vcpu() internally). However, that leads to a lock order inversion problem, because these are called in contexts where the vcpu mutex is held, but the vcpu mutexes nest within kvm->lock according to Documentation/virtual/kvm/locking.txt. Hence there is a possibility of deadlock.

To fix this, we simply don't take the kvm->lock mutex around these calls. This is safe because the implementations of kvm_for_each_vcpu() and kvm_get_vcpu_by_id() have been designed to be able to be called locklessly.

Signed-off-by: Paul Mackerras paulus@ozlabs.org Reviewed-by: Cédric Le Goater clg@kaod.org Signed-off-by: Paul Mackerras paulus@ozlabs.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/kvm/book3s_hv.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 4519c55ba19d..bea595c94cfc 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -445,12 +445,7 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu)

static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id) { - struct kvm_vcpu *ret; - - mutex_lock(&kvm->lock); - ret = kvm_get_vcpu_by_id(kvm, id); - mutex_unlock(&kvm->lock); - return ret; + return kvm_get_vcpu_by_id(kvm, id); }

static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa) @@ -1502,7 +1497,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, struct kvmppc_vcore *vc = vcpu->arch.vcore; u64 mask;

- mutex_lock(&kvm->lock); spin_lock(&vc->lock); /* * If ILE (interrupt little-endian) has changed, update the @@ -1542,7 +1536,6 @@ static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr, mask &= 0xFFFFFFFF; vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask); spin_unlock(&vc->lock); - mutex_unlock(&kvm->lock); }

static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,

From: Sami Tolvanen samitolvanen@google.com

[ Upstream commit 8ef8f368ce72b5e17f7c1f1ef15c38dcfd0fef64 ]

Syscall wrappers in <asm/syscall_wrapper.h> use const struct pt_regs * as the argument type. Use const in syscall_fn_t as well to fix indirect call type mismatches with Control-Flow Integrity checking.

Signed-off-by: Sami Tolvanen samitolvanen@google.com Reviewed-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/include/asm/syscall.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h index a179df3674a1..6206ab9bfcfc 100644 --- a/arch/arm64/include/asm/syscall.h +++ b/arch/arm64/include/asm/syscall.h @@ -20,7 +20,7 @@ #include <linux/compat.h> #include <linux/err.h>

-typedef long (*syscall_fn_t)(struct pt_regs *regs); +typedef long (*syscall_fn_t)(const struct pt_regs *regs);

extern const syscall_fn_t sys_call_table[];

From: Sami Tolvanen samitolvanen@google.com

[ Upstream commit 1e29ab3186e33c77dbb2d7566172a205b59fa390 ]

Calling sys_ni_syscall through a syscall_fn_t pointer trips indirect call Control-Flow Integrity checking due to a function type mismatch. Use SYSCALL_DEFINE0 for __arm64_sys_ni_syscall instead and remove the now unnecessary casts.

Signed-off-by: Sami Tolvanen samitolvanen@google.com Signed-off-by: Will Deacon will.deacon@arm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/sys.c | 14 +++++++++----- arch/arm64/kernel/sys32.c | 7 ++----- 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c index 6f91e8116514..d8b35cfe5e94 100644 --- a/arch/arm64/kernel/sys.c +++ b/arch/arm64/kernel/sys.c @@ -47,22 +47,26 @@ SYSCALL_DEFINE1(arm64_personality, unsigned int, personality) return ksys_personality(personality); }

+asmlinkage long sys_ni_syscall(void); + +asmlinkage long __arm64_sys_ni_syscall(const struct pt_regs *__unused) +{ + return sys_ni_syscall(); +} + /* * Wrappers to pass the pt_regs argument. */ #define sys_personality sys_arm64_personality

-asmlinkage long sys_ni_syscall(const struct pt_regs *); -#define __arm64_sys_ni_syscall sys_ni_syscall - #undef __SYSCALL #define __SYSCALL(nr, sym) asmlinkage long __arm64_##sym(const struct pt_regs *); #include <asm/unistd.h>

#undef __SYSCALL -#define __SYSCALL(nr, sym) [nr] = (syscall_fn_t)__arm64_##sym, +#define __SYSCALL(nr, sym) [nr] = __arm64_##sym,

const syscall_fn_t sys_call_table[__NR_syscalls] = { - [0 ... __NR_syscalls - 1] = (syscall_fn_t)sys_ni_syscall, + [0 ... __NR_syscalls - 1] = __arm64_sys_ni_syscall, #include <asm/unistd.h> }; diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c index 0f8bcb7de700..3c80a40c1c9d 100644 --- a/arch/arm64/kernel/sys32.c +++ b/arch/arm64/kernel/sys32.c @@ -133,17 +133,14 @@ COMPAT_SYSCALL_DEFINE6(aarch32_fallocate, int, fd, int, mode, return ksys_fallocate(fd, mode, arg_u64(offset), arg_u64(len)); }

-asmlinkage long sys_ni_syscall(const struct pt_regs *); -#define __arm64_sys_ni_syscall sys_ni_syscall - #undef __SYSCALL #define __SYSCALL(nr, sym) asmlinkage long __arm64_##sym(const struct pt_regs *); #include <asm/unistd32.h>

#undef __SYSCALL -#define __SYSCALL(nr, sym) [nr] = (syscall_fn_t)__arm64_##sym, +#define __SYSCALL(nr, sym) [nr] = __arm64_##sym,

const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] = { - [0 ... __NR_compat_syscalls - 1] = (syscall_fn_t)sys_ni_syscall, + [0 ... __NR_compat_syscalls - 1] = __arm64_sys_ni_syscall, #include <asm/unistd32.h> };

From: Jes Sorensen jsorensen@fb.com

[ Upstream commit 41de54c64811bf087c8464fdeb43c6ad8be2686b ]

If blk_mq_init_allocated_queue() fails, make sure to free the poll stat callback struct allocated.

Signed-off-by: Jes Sorensen jsorensen@fb.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-mq.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c index 8a41cc5974fe..95e8005982cd 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2844,7 +2844,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, goto err_exit;

if (blk_mq_alloc_ctxs(q)) - goto err_exit; + goto err_poll;

/* init q->mq_kobj and sw queues' kobjects */ blk_mq_sysfs_init(q); @@ -2905,6 +2905,9 @@ err_hctxs: kfree(q->queue_hw_ctx); err_sys_init: blk_mq_sysfs_deinit(q); +err_poll: + blk_stat_free_callback(q->poll_cb); + q->poll_cb = NULL; err_exit: q->mq_ops = NULL; return ERR_PTR(-ENOMEM);

From: Max Uvarov muvarov@gmail.com

[ Upstream commit 333061b924539c0de081339643f45514f5f1c1e6 ]

For supporting 10Mps speed in SGMII mode DP83867_10M_SGMII_RATE_ADAPT bit of DP83867_10M_SGMII_CFG register has to be cleared by software. That does not affect speeds 100 and 1000 so can be done on init.

Signed-off-by: Max Uvarov muvarov@gmail.com Cc: Heiner Kallweit hkallweit1@gmail.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/dp83867.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)

diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 8448d01819ef..29cae4de9a4f 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -30,6 +30,8 @@ #define DP83867_STRAP_STS1 0x006E #define DP83867_RGMIIDCTL 0x0086 #define DP83867_IO_MUX_CFG 0x0170 +#define DP83867_10M_SGMII_CFG 0x016F +#define DP83867_10M_SGMII_RATE_ADAPT_MASK BIT(7)

#define DP83867_SW_RESET BIT(15) #define DP83867_SW_RESTART BIT(14) @@ -277,6 +279,21 @@ static int dp83867_config_init(struct phy_device *phydev) DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL); }

+ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { + /* For support SPEED_10 in SGMII mode + * DP83867_10M_SGMII_RATE_ADAPT bit + * has to be cleared by software. That + * does not affect SPEED_100 and + * SPEED_1000. + */ + ret = phy_modify_mmd(phydev, DP83867_DEVADDR, + DP83867_10M_SGMII_CFG, + DP83867_10M_SGMII_RATE_ADAPT_MASK, + 0); + if (ret) + return ret; + } + /* Enable Interrupt output INT_OE in CFG3 register */ if (phy_interrupt_is_valid(phydev)) { val = phy_read(phydev, DP83867_CFG3);

From: Max Uvarov muvarov@gmail.com

[ Upstream commit 2b892649254fec01678c64f16427622b41fa27f4 ]

PHY_INTERFACE_MODE_RGMII_RXID is less then TXID so code to set tx delay is never called.

Fixes: 2a10154abcb75 ("net: phy: dp83867: Add TI dp83867 phy") Signed-off-by: Max Uvarov muvarov@gmail.com Cc: Florian Fainelli f.fainelli@gmail.com Reviewed-by: Florian Fainelli f.fainelli@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/phy/dp83867.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index ffaf67bdb140..2995a1788ceb 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -255,10 +255,8 @@ static int dp83867_config_init(struct phy_device *phydev) ret = phy_write(phydev, MII_DP83867_PHYCTRL, val); if (ret) return ret; - }

- if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) && - (phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) { + /* Set up RGMII delays */ val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIICTL);

if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID)

From: Lianbo Jiang lijiang@redhat.com

[ Upstream commit 1d94f06e7f5df4064ef336b7b710f50143b64a53 ]

When SME is enabled, the smartpqi driver won't work on the HP DL385 G10 machine, which causes the failure of kernel boot because it fails to allocate pqi error buffer. Please refer to the kernel log: .... [ 9.431749] usbcore: registered new interface driver uas [ 9.441524] Microsemi PQI Driver (v1.1.4-130) [ 9.442956] i40e 0000:04:00.0: fw 6.70.48768 api 1.7 nvm 10.2.5 [ 9.447237] smartpqi 0000:23:00.0: Microsemi Smart Family Controller found Starting dracut initqueue hook... [ OK ] Started Show Plymouth Boot Scre[ 9.471654] Broadcom NetXtreme-C/E driver bnxt_en v1.9.1 en. [ OK ] Started Forward Password Requests to Plymouth Directory Watch. [[0;[ 9.487108] smartpqi 0000:23:00.0: failed to allocate PQI error buffer .... [ 139.050544] dracut-initqueue[949]: Warning: dracut-initqueue timeout - starting timeout scripts [ 139.589779] dracut-initqueue[949]: Warning: dracut-initqueue timeout - starting timeout scripts

Basically, the fact that the coherent DMA mask value wasn't set caused the driver to fall back to SWIOTLB when SME is active.

For correct operation, lets call the dma_set_mask_and_coherent() to properly set the mask for both streaming and coherent, in order to inform the kernel about the devices DMA addressing capabilities.

Signed-off-by: Lianbo Jiang lijiang@redhat.com Acked-by: Don Brace don.brace@microsemi.com Tested-by: Don Brace don.brace@microsemi.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/smartpqi/smartpqi_init.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c index 75ec43aa8df3..531824afba5f 100644 --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@ -7285,7 +7285,7 @@ static int pqi_pci_init(struct pqi_ctrl_info *ctrl_info) else mask = DMA_BIT_MASK(32);

- rc = dma_set_mask(&ctrl_info->pci_dev->dev, mask); + rc = dma_set_mask_and_coherent(&ctrl_info->pci_dev->dev, mask); if (rc) { dev_err(&ctrl_info->pci_dev->dev, "failed to set DMA mask\n"); goto disable_device;

From: Jason Yan yanaijie@huawei.com

[ Upstream commit 3b0541791453fbe7f42867e310e0c9eb6295364d ]

The sas_port(phy->port) allocated in sas_ex_discover_expander() will not be deleted when the expander failed to discover. This will cause resource leak and a further issue of kernel BUG like below:

[159785.843156] port-2:17:29: trying to add phy phy-2:17:29 fails: it's already part of another port [159785.852144] ------------[ cut here ]------------ [159785.856833] kernel BUG at drivers/scsi/scsi_transport_sas.c:1086! [159785.863000] Internal error: Oops - BUG: 0 [#1] SMP [159785.867866] CPU: 39 PID: 16993 Comm: kworker/u96:2 Tainted: G W OE 4.19.25-vhulk1901.1.0.h111.aarch64 #1 [159785.878458] Hardware name: Huawei Technologies Co., Ltd. Hi1620EVBCS/Hi1620EVBCS, BIOS Hi1620 CS B070 1P TA 03/21/2019 [159785.889231] Workqueue: 0000:74:02.0_disco_q sas_discover_domain [159785.895224] pstate: 40c00009 (nZcv daif +PAN +UAO) [159785.900094] pc : sas_port_add_phy+0x188/0x1b8 [159785.904524] lr : sas_port_add_phy+0x188/0x1b8 [159785.908952] sp : ffff0001120e3b80 [159785.912341] x29: ffff0001120e3b80 x28: 0000000000000000 [159785.917727] x27: ffff802ade8f5400 x26: ffff0000681b7560 [159785.923111] x25: ffff802adf11a800 x24: ffff0000680e8000 [159785.928496] x23: ffff802ade8f5728 x22: ffff802ade8f5708 [159785.933880] x21: ffff802adea2db40 x20: ffff802ade8f5400 [159785.939264] x19: ffff802adea2d800 x18: 0000000000000010 [159785.944649] x17: 00000000821bf734 x16: ffff00006714faa0 [159785.950033] x15: ffff0000e8ab4ecf x14: 7261702079646165 [159785.955417] x13: 726c612073277469 x12: ffff00006887b830 [159785.960802] x11: ffff00006773eaa0 x10: 7968702079687020 [159785.966186] x9 : 0000000000002453 x8 : 726f702072656874 [159785.971570] x7 : 6f6e6120666f2074 x6 : ffff802bcfb21290 [159785.976955] x5 : ffff802bcfb21290 x4 : 0000000000000000 [159785.982339] x3 : ffff802bcfb298c8 x2 : 337752b234c2ab00 [159785.987723] x1 : 337752b234c2ab00 x0 : 0000000000000000 [159785.993108] Process kworker/u96:2 (pid: 16993, stack limit = 0x0000000072dae094) [159786.000576] Call trace: [159786.003097] sas_port_add_phy+0x188/0x1b8 [159786.007179] sas_ex_get_linkrate.isra.5+0x134/0x140 [159786.012130] sas_ex_discover_expander+0x128/0x408 [159786.016906] sas_ex_discover_dev+0x218/0x4c8 [159786.021249] sas_ex_discover_devices+0x9c/0x1a8 [159786.025852] sas_discover_root_expander+0x134/0x160 [159786.030802] sas_discover_domain+0x1b8/0x1e8 [159786.035148] process_one_work+0x1b4/0x3f8 [159786.039230] worker_thread+0x54/0x470 [159786.042967] kthread+0x134/0x138 [159786.046269] ret_from_fork+0x10/0x18 [159786.049918] Code: 91322300 f0004402 91178042 97fe4c9b (d4210000) [159786.056083] Modules linked in: hns3_enet_ut(OE) hclge(OE) hnae3(OE) hisi_sas_test_hw(OE) hisi_sas_test_main(OE) serdes(OE) [159786.067202] ---[ end trace 03622b9e2d99e196 ]--- [159786.071893] Kernel panic - not syncing: Fatal exception [159786.077190] SMP: stopping secondary CPUs [159786.081192] Kernel Offset: disabled [159786.084753] CPU features: 0x2,a2a00a38

Fixes: 2908d778ab3e ("[SCSI] aic94xx: new driver") Reported-by: Jian Luo luojian5@huawei.com Signed-off-by: Jason Yan yanaijie@huawei.com CC: John Garry john.garry@huawei.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/libsas/sas_expander.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c index 3611a4ef0d15..7c2d78d189e4 100644 --- a/drivers/scsi/libsas/sas_expander.c +++ b/drivers/scsi/libsas/sas_expander.c @@ -1014,6 +1014,8 @@ static struct domain_device *sas_ex_discover_expander( list_del(&child->dev_list_node); spin_unlock_irq(&parent->port->dev_list_lock); sas_put_device(child); + sas_port_delete(phy->port); + phy->port = NULL; return NULL; } list_add_tail(&child->siblings, &parent->ex_dev.children);

From: "Tobin C. Harding" tobin@kernel.org

[ Upstream commit b9fba67b3806e21b98bd5a98dc3921a8e9b42d61 ]

If a call to kobject_init_and_add() fails we should call kobject_put() otherwise we leak memory.

Add call to kobject_put() in the error path of call to kobject_init_and_add(). Please note, this has the side effect that the release method is called if kobject_init_and_add() fails.

Link: http://lkml.kernel.org/r/20190513033458.2824-1-tobin@kernel.org Signed-off-by: Tobin C. Harding tobin@kernel.org Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Reviewed-by: Joseph Qi joseph.qi@linux.alibaba.com Cc: Mark Fasheh mark@fasheh.com Cc: Joel Becker jlbec@evilplan.org Cc: Junxiao Bi junxiao.bi@oracle.com Cc: Changwei Ge gechangwei@live.cn Cc: Gang He ghe@suse.com Cc: Jun Piao piaojun@huawei.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ocfs2/filecheck.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/ocfs2/filecheck.c b/fs/ocfs2/filecheck.c index f65f2b2f594d..1906cc962c4d 100644 --- a/fs/ocfs2/filecheck.c +++ b/fs/ocfs2/filecheck.c @@ -193,6 +193,7 @@ int ocfs2_filecheck_create_sysfs(struct ocfs2_super *osb) ret = kobject_init_and_add(&entry->fs_kobj, &ocfs2_ktype_filecheck, NULL, "filecheck"); if (ret) { + kobject_put(&entry->fs_kobj); kfree(fcheck); return ret; }