From: "Gustavo A. R. Silva" <[email protected]>
[ Upstream commit bfabdd6997323adbedccb13a3fed1967fb8cf8f5 ]
Notice that *rc* can evaluate to up to 5, include/linux/netdevice.h:
enum gro_result {
GRO_MERGED,
GRO_MERGED_FREE,
GRO_HELD,
GRO_NORMAL,
GRO_DROP,
GRO_CONSUMED,
};
typedef enum gro_result gro_result_t;
In case *rc* evaluates to 5, we end up having an out-of-bounds read
at drivers/net/wireless/ath/wil6210/txrx.c:821:
wil_dbg_txrx(wil, "Rx complete %d bytes => %s\n",
len, gro_res_str[rc]);
Fix this by adding element "GRO_CONSUMED" to array gro_res_str.
Addresses-Coverity-ID: 1444666 ("Out-of-bounds read")
Fixes: 194b482b5055 ("wil6210: Debug print GRO Rx result")
Signed-off-by: Gustavo A. R. Silva <[email protected]>
Reviewed-by: Maya Erez <[email protected]>
Signed-off-by: Kalle Valo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/wireless/ath/wil6210/txrx.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 75c8aa297107..1b1b58e0129a 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -736,6 +736,7 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
[GRO_HELD] = "GRO_HELD",
[GRO_NORMAL] = "GRO_NORMAL",
[GRO_DROP] = "GRO_DROP",
+ [GRO_CONSUMED] = "GRO_CONSUMED",
};
wil->txrx_ops.get_netif_rx_params(skb, &cid, &security);
--
2.20.1
From: Hans Verkuil <[email protected]>
[ Upstream commit 518fa4e0e0da97ea2e17c95ab57647ce748a96e2 ]
You can't memset the contents of a __user pointer. Instead, call copy_to_user to
copy links.reserved (which is zeroed) to the user memory.
This fixes this sparse warning:
SPARSE:drivers/media/mc/mc-device.c drivers/media/mc/mc-device.c:521:16: warning: incorrect type in argument 1 (different address spaces)
Fixes: f49308878d720 ("media: media_device_enum_links32: clean a reserved field")
Signed-off-by: Hans Verkuil <[email protected]>
Reviewed-by: Sakari Ailus <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/media-device.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index ba344e6f0139..ed518b1f82e4 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -503,8 +503,9 @@ static long media_device_enum_links32(struct media_device *mdev,
if (ret)
return ret;
- memset(ulinks->reserved, 0, sizeof(ulinks->reserved));
-
+ if (copy_to_user(ulinks->reserved, links.reserved,
+ sizeof(ulinks->reserved)))
+ return -EFAULT;
return 0;
}
--
2.20.1
From: Kefeng Wang <[email protected]>
[ Upstream commit 50710eeefbc1ed25375942aad0c4d1eb4af0f330 ]
if saa7164_proc_create() fails, saa7164_fini() will trigger a warning,
name 'saa7164'
WARNING: CPU: 1 PID: 6311 at fs/proc/generic.c:672 remove_proc_entry+0x1e8/0x3a0
? remove_proc_entry+0x1e8/0x3a0
? try_stop_module+0x7b/0x240
? proc_readdir+0x70/0x70
? rcu_read_lock_sched_held+0xd7/0x100
saa7164_fini+0x13/0x1f [saa7164]
__x64_sys_delete_module+0x30c/0x480
? __ia32_sys_delete_module+0x480/0x480
? __x64_sys_clock_gettime+0x11e/0x1c0
? __x64_sys_timer_create+0x1a0/0x1a0
? trace_hardirqs_off_caller+0x40/0x180
? do_syscall_64+0x18/0x450
do_syscall_64+0x9f/0x450
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Fix it by checking the return of proc_create_single() before
calling remove_proc_entry().
Signed-off-by: Kefeng Wang <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
[[email protected]: use 0444 instead of S_IRUGO]
[[email protected]: use pr_info instead of KERN_INFO]
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/pci/saa7164/saa7164-core.c | 33 ++++++++++++++++--------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/drivers/media/pci/saa7164/saa7164-core.c b/drivers/media/pci/saa7164/saa7164-core.c
index d697e1ad929c..5102519df108 100644
--- a/drivers/media/pci/saa7164/saa7164-core.c
+++ b/drivers/media/pci/saa7164/saa7164-core.c
@@ -1122,16 +1122,25 @@ static int saa7164_proc_show(struct seq_file *m, void *v)
return 0;
}
+static struct proc_dir_entry *saa7164_pe;
+
static int saa7164_proc_create(void)
{
- struct proc_dir_entry *pe;
-
- pe = proc_create_single("saa7164", S_IRUGO, NULL, saa7164_proc_show);
- if (!pe)
+ saa7164_pe = proc_create_single("saa7164", 0444, NULL, saa7164_proc_show);
+ if (!saa7164_pe)
return -ENOMEM;
return 0;
}
+
+static void saa7164_proc_destroy(void)
+{
+ if (saa7164_pe)
+ remove_proc_entry("saa7164", NULL);
+}
+#else
+static int saa7164_proc_create(void) { return 0; }
+static void saa7164_proc_destroy(void) {}
#endif
static int saa7164_thread_function(void *data)
@@ -1503,19 +1512,21 @@ static struct pci_driver saa7164_pci_driver = {
static int __init saa7164_init(void)
{
- printk(KERN_INFO "saa7164 driver loaded\n");
+ int ret = pci_register_driver(&saa7164_pci_driver);
+
+ if (ret)
+ return ret;
-#ifdef CONFIG_PROC_FS
saa7164_proc_create();
-#endif
- return pci_register_driver(&saa7164_pci_driver);
+
+ pr_info("saa7164 driver loaded\n");
+
+ return 0;
}
static void __exit saa7164_fini(void)
{
-#ifdef CONFIG_PROC_FS
- remove_proc_entry("saa7164", NULL);
-#endif
+ saa7164_proc_destroy();
pci_unregister_driver(&saa7164_pci_driver);
}
--
2.20.1
From: Daniel Baluta <[email protected]>
[ Upstream commit 2899872b627e99b7586fe3b6c9f861da1b4d5072 ]
As detected by kmemleak running on i.MX6ULL board:
nreferenced object 0xd8366600 (size 64):
comm "swapper/0", pid 1, jiffies 4294937370 (age 933.220s)
hex dump (first 32 bytes):
64 75 6d 6d 79 2d 69 6f 6d 75 78 63 2d 67 70 72 dummy-iomuxc-gpr
40 32 30 65 34 30 30 30 00 e3 f3 ab fe d1 1b dd @20e4000........
backtrace:
[<b0402aec>] kasprintf+0x2c/0x54
[<a6fbad2c>] regmap_debugfs_init+0x7c/0x31c
[<9c8d91fa>] __regmap_init+0xb5c/0xcf4
[<5b1c3d2a>] of_syscon_register+0x164/0x2c4
[<596a5d80>] syscon_node_to_regmap+0x64/0x90
[<49bd597b>] imx6ul_init_machine+0x34/0xa0
[<250a4dac>] customize_machine+0x1c/0x30
[<2d19fdaf>] do_one_initcall+0x7c/0x398
[<e6084469>] kernel_init_freeable+0x328/0x448
[<168c9101>] kernel_init+0x8/0x114
[<913268aa>] ret_from_fork+0x14/0x20
[<ce7b131a>] 0x0
Root cause is that map->debugfs_name is allocated using kasprintf
and then the pointer is lost by assigning it other memory address.
Reported-by: Stefan Wahren <[email protected]>
Signed-off-by: Daniel Baluta <[email protected]>
Signed-off-by: Mark Brown <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/base/regmap/regmap-debugfs.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 87b562e49a43..c9687c8b2347 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -575,6 +575,8 @@ void regmap_debugfs_init(struct regmap *map, const char *name)
}
if (!strcmp(name, "dummy")) {
+ kfree(map->debugfs_name);
+
map->debugfs_name = kasprintf(GFP_KERNEL, "dummy%d",
dummy_index);
name = map->debugfs_name;
--
2.20.1
From: Daniel Gomez <[email protected]>
[ Upstream commit 24e4cf770371df6ad49ed873f21618d9878f64c8 ]
MODULE_DEVICE_TABLE(of, <of_match_table> should be called to complete DT
OF mathing mechanism and register it.
Before this patch:
modinfo drivers/media/rc/ir-spi.ko | grep alias
After this patch:
modinfo drivers/media/rc/ir-spi.ko | grep alias
alias: of:N*T*Cir-spi-ledC*
alias: of:N*T*Cir-spi-led
Reported-by: Javier Martinez Canillas <[email protected]>
Signed-off-by: Daniel Gomez <[email protected]>
Signed-off-by: Sean Young <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/rc/ir-spi.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/media/rc/ir-spi.c b/drivers/media/rc/ir-spi.c
index 66334e8d63ba..c58f2d38a458 100644
--- a/drivers/media/rc/ir-spi.c
+++ b/drivers/media/rc/ir-spi.c
@@ -161,6 +161,7 @@ static const struct of_device_id ir_spi_of_match[] = {
{ .compatible = "ir-spi-led" },
{},
};
+MODULE_DEVICE_TABLE(of, ir_spi_of_match);
static struct spi_driver ir_spi_driver = {
.probe = ir_spi_probe,
--
2.20.1
From: Jungo Lin <[email protected]>
[ Upstream commit f49308878d7202e07d8761238e01bd0e5fce2750 ]
In v4l2-compliance utility, test MEDIA_IOC_ENUM_ENTITIES
will check whether reserved field of media_links_enum filled
with zero.
However, for 32 bit program, the reserved field is missing
copy from kernel space to user space in media_device_enum_links32
function.
This patch adds the cleaning a reserved field logic in
media_device_enum_links32 function.
Signed-off-by: Jungo Lin <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/media-device.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 3bae24b15eaa..ba344e6f0139 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -487,6 +487,7 @@ static long media_device_enum_links32(struct media_device *mdev,
{
struct media_links_enum links;
compat_uptr_t pads_ptr, links_ptr;
+ int ret;
memset(&links, 0, sizeof(links));
@@ -498,7 +499,13 @@ static long media_device_enum_links32(struct media_device *mdev,
links.pads = compat_ptr(pads_ptr);
links.links = compat_ptr(links_ptr);
- return media_device_enum_links(mdev, &links);
+ ret = media_device_enum_links(mdev, &links);
+ if (ret)
+ return ret;
+
+ memset(ulinks->reserved, 0, sizeof(ulinks->reserved));
+
+ return 0;
}
#define MEDIA_IOC_ENUM_LINKS32 _IOWR('|', 0x02, struct media_links_enum32)
--
2.20.1
From: Jeremy Sowden <[email protected]>
[ Upstream commit 7c80eb1c7e2b8420477fbc998971d62a648035d9 ]
In both functions, if pfkey_xfrm_policy2msg failed we leaked the newly
allocated sk_buff. Free it on error.
Fixes: 55569ce256ce ("Fix conversion between IPSEC_MODE_xxx and XFRM_MODE_xxx.")
Reported-by: [email protected]
Signed-off-by: Jeremy Sowden <[email protected]>
Signed-off-by: Steffen Klassert <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/key/af_key.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 0b79c9aa8eb1..1982f9f31deb 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2442,8 +2442,10 @@ static int key_pol_get_resp(struct sock *sk, struct xfrm_policy *xp, const struc
goto out;
}
err = pfkey_xfrm_policy2msg(out_skb, xp, dir);
- if (err < 0)
+ if (err < 0) {
+ kfree_skb(out_skb);
goto out;
+ }
out_hdr = (struct sadb_msg *) out_skb->data;
out_hdr->sadb_msg_version = hdr->sadb_msg_version;
@@ -2694,8 +2696,10 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr)
return PTR_ERR(out_skb);
err = pfkey_xfrm_policy2msg(out_skb, xp, dir);
- if (err < 0)
+ if (err < 0) {
+ kfree_skb(out_skb);
return err;
+ }
out_hdr = (struct sadb_msg *) out_skb->data;
out_hdr->sadb_msg_version = pfk->dump.msg_version;
--
2.20.1
From: Kangjie Lu <[email protected]>
[ Upstream commit e08f0761234def47961d3252eac09ccedfe4c6a0 ]
In case ioremap fails, the fix returns -ENOMEM to avoid NULL
pointer dereference.
Signed-off-by: Kangjie Lu <[email protected]>
Reviewed-by: Mukesh Ojha <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/davinci/vpss.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/media/platform/davinci/vpss.c b/drivers/media/platform/davinci/vpss.c
index 19cf6853411e..89a86c19579b 100644
--- a/drivers/media/platform/davinci/vpss.c
+++ b/drivers/media/platform/davinci/vpss.c
@@ -518,6 +518,11 @@ static int __init vpss_init(void)
return -EBUSY;
oper_cfg.vpss_regs_base2 = ioremap(VPSS_CLK_CTRL, 4);
+ if (unlikely(!oper_cfg.vpss_regs_base2)) {
+ release_mem_region(VPSS_CLK_CTRL, 4);
+ return -ENOMEM;
+ }
+
writel(VPSS_CLK_CTRL_VENCCLKEN |
VPSS_CLK_CTRL_DACCLKEN, oper_cfg.vpss_regs_base2);
--
2.20.1
From: Sven Eckelmann <[email protected]>
[ Upstream commit 9e6b5648bbc4cd48fab62cecbb81e9cc3c6e7e88 ]
The state of slave interfaces are handled differently depending on whether
the interface is up or not. All active interfaces (IFF_UP) will transmit
OGMs. But for B.A.T.M.A.N. IV, also non-active interfaces are scheduling
(low TTL) OGMs on active interfaces. The code which setups and schedules
the OGMs must therefore already be called when the interfaces gets added as
slave interface and the transmit function must then check whether it has to
send out the OGM or not on the specific slave interface.
But the commit f0d97253fb5f ("batman-adv: remove ogm_emit and ogm_schedule
API calls") moved the setup code from the enable function to the activate
function. The latter is called either when the added slave was already up
when batadv_hardif_enable_interface processed the new interface or when a
NETDEV_UP event was received for this slave interfac. As result, each
NETDEV_UP would schedule a new OGM worker for the interface and thus OGMs
would be send a lot more than expected.
Fixes: f0d97253fb5f ("batman-adv: remove ogm_emit and ogm_schedule API calls")
Reported-by: Linus Lüssing <[email protected]>
Tested-by: Linus Lüssing <[email protected]>
Acked-by: Marek Lindner <[email protected]>
Signed-off-by: Sven Eckelmann <[email protected]>
Signed-off-by: Simon Wunderlich <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/batman-adv/bat_iv_ogm.c | 4 ++--
net/batman-adv/hard-interface.c | 3 +++
net/batman-adv/types.h | 3 +++
3 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 73bf6a93a3cf..0b7b36fa0d5c 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -2485,7 +2485,7 @@ batadv_iv_ogm_neigh_is_sob(struct batadv_neigh_node *neigh1,
return ret;
}
-static void batadv_iv_iface_activate(struct batadv_hard_iface *hard_iface)
+static void batadv_iv_iface_enabled(struct batadv_hard_iface *hard_iface)
{
/* begin scheduling originator messages on that interface */
batadv_iv_ogm_schedule(hard_iface);
@@ -2825,8 +2825,8 @@ static void batadv_iv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb,
static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
.name = "BATMAN_IV",
.iface = {
- .activate = batadv_iv_iface_activate,
.enable = batadv_iv_ogm_iface_enable,
+ .enabled = batadv_iv_iface_enabled,
.disable = batadv_iv_ogm_iface_disable,
.update_mac = batadv_iv_ogm_iface_update_mac,
.primary_set = batadv_iv_ogm_primary_iface_set,
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 08690d06b7be..36f0962040d1 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -821,6 +821,9 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
batadv_hardif_recalc_extra_skbroom(soft_iface);
+ if (bat_priv->algo_ops->iface.enabled)
+ bat_priv->algo_ops->iface.enabled(hard_iface);
+
out:
return 0;
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index eeee3e61c625..fdba8a144d73 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -2130,6 +2130,9 @@ struct batadv_algo_iface_ops {
/** @enable: init routing info when hard-interface is enabled */
int (*enable)(struct batadv_hard_iface *hard_iface);
+ /** @enabled: notification when hard-interface was enabled (optional) */
+ void (*enabled)(struct batadv_hard_iface *hard_iface);
+
/** @disable: de-init routing info when hard-interface is disabled */
void (*disable)(struct batadv_hard_iface *hard_iface);
--
2.20.1
From: Robert Hancock <[email protected]>
[ Upstream commit 7de44285c1f69ccfbe8be1d6a16fcd956681fee6 ]
It is possible that the interrupt handler fires and frees up space in
the TX ring in between checking for sufficient TX ring space and
stopping the TX queue in axienet_start_xmit. If this happens, the
queue wake from the interrupt handler will occur before the queue is
stopped, causing a lost wakeup and the adapter's transmit hanging.
To avoid this, after stopping the queue, check again whether there is
sufficient space in the TX ring. If so, wake up the queue again.
Signed-off-by: Robert Hancock <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
.../net/ethernet/xilinx/xilinx_axienet_main.c | 20 ++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 7cfd7ff38e86..66b30ebd45ee 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -614,6 +614,10 @@ static void axienet_start_xmit_done(struct net_device *ndev)
ndev->stats.tx_packets += packets;
ndev->stats.tx_bytes += size;
+
+ /* Matches barrier in axienet_start_xmit */
+ smp_mb();
+
netif_wake_queue(ndev);
}
@@ -668,9 +672,19 @@ static int axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
if (axienet_check_tx_bd_space(lp, num_frag)) {
- if (!netif_queue_stopped(ndev))
- netif_stop_queue(ndev);
- return NETDEV_TX_BUSY;
+ if (netif_queue_stopped(ndev))
+ return NETDEV_TX_BUSY;
+
+ netif_stop_queue(ndev);
+
+ /* Matches barrier in axienet_start_xmit_done */
+ smp_mb();
+
+ /* Space might have just been freed - check again */
+ if (axienet_check_tx_bd_space(lp, num_frag))
+ return NETDEV_TX_BUSY;
+
+ netif_wake_queue(ndev);
}
if (skb->ip_summed == CHECKSUM_PARTIAL) {
--
2.20.1
From: Robert Hancock <[email protected]>
[ Upstream commit 2158e856f56bb762ef90f3ec244d41a519826f75 ]
sfp_check_state can potentially be called by both a threaded IRQ handler
and delayed work. If it is concurrently called, it could result in
incorrect state management. Add a st_mutex to protect the state - this
lock gets taken outside of code that checks and handle state changes, and
the existing sm_mutex nests inside of it.
Suggested-by: Russell King <[email protected]>
Signed-off-by: Robert Hancock <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/phy/sfp.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 8807a806cc47..418522aa2f71 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -185,10 +185,11 @@ struct sfp {
struct gpio_desc *gpio[GPIO_MAX];
bool attached;
+ struct mutex st_mutex; /* Protects state */
unsigned int state;
struct delayed_work poll;
struct delayed_work timeout;
- struct mutex sm_mutex;
+ struct mutex sm_mutex; /* Protects state machine */
unsigned char sm_mod_state;
unsigned char sm_dev_state;
unsigned short sm_state;
@@ -1718,6 +1719,7 @@ static void sfp_check_state(struct sfp *sfp)
{
unsigned int state, i, changed;
+ mutex_lock(&sfp->st_mutex);
state = sfp_get_state(sfp);
changed = state ^ sfp->state;
changed &= SFP_F_PRESENT | SFP_F_LOS | SFP_F_TX_FAULT;
@@ -1743,6 +1745,7 @@ static void sfp_check_state(struct sfp *sfp)
sfp_sm_event(sfp, state & SFP_F_LOS ?
SFP_E_LOS_HIGH : SFP_E_LOS_LOW);
rtnl_unlock();
+ mutex_unlock(&sfp->st_mutex);
}
static irqreturn_t sfp_irq(int irq, void *data)
@@ -1773,6 +1776,7 @@ static struct sfp *sfp_alloc(struct device *dev)
sfp->dev = dev;
mutex_init(&sfp->sm_mutex);
+ mutex_init(&sfp->st_mutex);
INIT_DELAYED_WORK(&sfp->poll, sfp_poll);
INIT_DELAYED_WORK(&sfp->timeout, sfp_timeout);
--
2.20.1
From: Stefano Brivio <[email protected]>
[ Upstream commit 11921796f4799ca9c61c4b22cc54d84aa69f8a35 ]
If a fresh array block is allocated during resize, the current in-memory
set size should be increased by the size of the block, not replaced by it.
Before the fix, adding entries to a hash set type, leading to a table
resize, caused an inconsistent memory size to be reported. This becomes
more obvious when swapping sets with similar sizes:
# cat hash_ip_size.sh
#!/bin/sh
FAIL_RETRIES=10
tries=0
while [ ${tries} -lt ${FAIL_RETRIES} ]; do
ipset create t1 hash:ip
for i in `seq 1 4345`; do
ipset add t1 1.2.$((i / 255)).$((i % 255))
done
t1_init="$(ipset list t1|sed -n 's/Size in memory: \(.*\)/\1/p')"
ipset create t2 hash:ip
for i in `seq 1 4360`; do
ipset add t2 1.2.$((i / 255)).$((i % 255))
done
t2_init="$(ipset list t2|sed -n 's/Size in memory: \(.*\)/\1/p')"
ipset swap t1 t2
t1_swap="$(ipset list t1|sed -n 's/Size in memory: \(.*\)/\1/p')"
t2_swap="$(ipset list t2|sed -n 's/Size in memory: \(.*\)/\1/p')"
ipset destroy t1
ipset destroy t2
tries=$((tries + 1))
if [ ${t1_init} -lt 10000 ] || [ ${t2_init} -lt 10000 ]; then
echo "FAIL after ${tries} tries:"
echo "T1 size ${t1_init}, after swap ${t1_swap}"
echo "T2 size ${t2_init}, after swap ${t2_swap}"
exit 1
fi
done
echo "PASS"
# echo -n 'func hash_ip4_resize +p' > /sys/kernel/debug/dynamic_debug/control
# ./hash_ip_size.sh
[ 2035.018673] attempt to resize set t1 from 10 to 11, t 00000000fe6551fa
[ 2035.078583] set t1 resized from 10 (00000000fe6551fa) to 11 (00000000172a0163)
[ 2035.080353] Table destroy by resize 00000000fe6551fa
FAIL after 4 tries:
T1 size 9064, after swap 71128
T2 size 71128, after swap 9064
Reported-by: NOYB <[email protected]>
Fixes: 9e41f26a505c ("netfilter: ipset: Count non-static extension memory for userspace")
Signed-off-by: Stefano Brivio <[email protected]>
Signed-off-by: Jozsef Kadlecsik <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/netfilter/ipset/ip_set_hash_gen.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 8a33dac4e805..ddfe06d7530b 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -625,7 +625,7 @@ mtype_resize(struct ip_set *set, bool retried)
goto cleanup;
}
m->size = AHASH_INIT_SIZE;
- extsize = ext_size(AHASH_INIT_SIZE, dsize);
+ extsize += ext_size(AHASH_INIT_SIZE, dsize);
RCU_INIT_POINTER(hbucket(t, key), m);
} else if (m->pos >= m->size) {
struct hbucket *ht;
--
2.20.1
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit da2019633f0b5c105ce658aada333422d8cb28fe ]
Some compilers will complain when using a member of a struct to
initialize another member, in the same struct initialization.
For instance:
debian:8 Debian clang version 3.5.0-10 (tags/RELEASE_350/final) (based on LLVM 3.5.0)
oraclelinux:7 clang version 3.4.2 (tags/RELEASE_34/dot2-final)
Produce:
ui/browsers/annotate.c:104:12: error: variable 'ops' is uninitialized when used within its own initialization [-Werror,-Wuninitialized]
(!ops.current_entry ||
^~~
1 error generated.
So use an extra variable, initialized just before that struct, to have
the value used in the expressions used to init two of the struct
members.
Cc: Adrian Hunter <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Namhyung Kim <[email protected]>
Fixes: c298304bd747 ("perf annotate: Use a ops table for annotation_line__write()")
Link: https://lkml.kernel.org/n/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/ui/browsers/annotate.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 1d00e5ec7906..a3c255228d62 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -96,11 +96,12 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
struct annotation *notes = browser__annotation(browser);
struct annotation_line *al = list_entry(entry, struct annotation_line, node);
+ const bool is_current_entry = ui_browser__is_current_entry(browser, row);
struct annotation_write_ops ops = {
.first_line = row == 0,
- .current_entry = ui_browser__is_current_entry(browser, row),
+ .current_entry = is_current_entry,
.change_color = (!notes->options->hide_src_code &&
- (!ops.current_entry ||
+ (!is_current_entry ||
(browser->use_navkeypressed &&
!browser->navkeypressed))),
.width = browser->width,
--
2.20.1
From: Shailendra Verma <[email protected]>
[ Upstream commit 6995a659101bd4effa41cebb067f9dc18d77520d ]
Fix to avoid possible memory leak if the decoder initialization
got failed.Free the allocated memory for file handle object
before return in case decoder initialization fails.
Signed-off-by: Shailendra Verma <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/staging/media/davinci_vpfe/vpfe_video.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c
index 1269a983455e..13b890b9ef18 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c
@@ -422,6 +422,9 @@ static int vpfe_open(struct file *file)
/* If decoder is not initialized. initialize it */
if (!video->initialized && vpfe_update_pipe_state(video)) {
mutex_unlock(&video->lock);
+ v4l2_fh_del(&handle->vfh);
+ v4l2_fh_exit(&handle->vfh);
+ kfree(handle);
return -ENODEV;
}
/* Increment device users counter */
--
2.20.1
From: "David S. Miller" <[email protected]>
[ Upstream commit 621ccc6cc5f8d6730b740d31d4818227866c93c9 ]
Rename _P to _P_VAL and _R to _R_VAL to avoid global
namespace conflicts:
drivers/media/dvb-frontends/tua6100.c: In function ‘tua6100_set_params’:
drivers/media/dvb-frontends/tua6100.c:79: warning: "_P" redefined
#define _P 32
In file included from ./include/acpi/platform/aclinux.h:54,
from ./include/acpi/platform/acenv.h:152,
from ./include/acpi/acpi.h:22,
from ./include/linux/acpi.h:34,
from ./include/linux/i2c.h:17,
from drivers/media/dvb-frontends/tua6100.h:30,
from drivers/media/dvb-frontends/tua6100.c:32:
./include/linux/ctype.h:14: note: this is the location of the previous definition
#define _P 0x10 /* punct */
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/dvb-frontends/tua6100.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/drivers/media/dvb-frontends/tua6100.c b/drivers/media/dvb-frontends/tua6100.c
index b233b7be0b84..e6aaf4973aef 100644
--- a/drivers/media/dvb-frontends/tua6100.c
+++ b/drivers/media/dvb-frontends/tua6100.c
@@ -75,8 +75,8 @@ static int tua6100_set_params(struct dvb_frontend *fe)
struct i2c_msg msg1 = { .addr = priv->i2c_address, .flags = 0, .buf = reg1, .len = 4 };
struct i2c_msg msg2 = { .addr = priv->i2c_address, .flags = 0, .buf = reg2, .len = 3 };
-#define _R 4
-#define _P 32
+#define _R_VAL 4
+#define _P_VAL 32
#define _ri 4000000
// setup register 0
@@ -91,14 +91,14 @@ static int tua6100_set_params(struct dvb_frontend *fe)
else
reg1[1] = 0x0c;
- if (_P == 64)
+ if (_P_VAL == 64)
reg1[1] |= 0x40;
if (c->frequency >= 1525000)
reg1[1] |= 0x80;
// register 2
- reg2[1] = (_R >> 8) & 0x03;
- reg2[2] = _R;
+ reg2[1] = (_R_VAL >> 8) & 0x03;
+ reg2[2] = _R_VAL;
if (c->frequency < 1455000)
reg2[1] |= 0x1c;
else if (c->frequency < 1630000)
@@ -110,18 +110,18 @@ static int tua6100_set_params(struct dvb_frontend *fe)
* The N divisor ratio (note: c->frequency is in kHz, but we
* need it in Hz)
*/
- prediv = (c->frequency * _R) / (_ri / 1000);
- div = prediv / _P;
+ prediv = (c->frequency * _R_VAL) / (_ri / 1000);
+ div = prediv / _P_VAL;
reg1[1] |= (div >> 9) & 0x03;
reg1[2] = div >> 1;
reg1[3] = (div << 7);
- priv->frequency = ((div * _P) * (_ri / 1000)) / _R;
+ priv->frequency = ((div * _P_VAL) * (_ri / 1000)) / _R_VAL;
// Finally, calculate and store the value for A
- reg1[3] |= (prediv - (div*_P)) & 0x7f;
+ reg1[3] |= (prediv - (div*_P_VAL)) & 0x7f;
-#undef _R
-#undef _P
+#undef _R_VAL
+#undef _P_VAL
#undef _ri
if (fe->ops.i2c_gate_ctrl)
--
2.20.1
From: Eric Auger <[email protected]>
[ Upstream commit ad0834dedaa15c3a176f783c0373f836e44b4700 ]
In case we expand an existing region, we unlink
this latter and insert the larger one. In
that case we should free the original region after
the insertion. Also we can immediately return.
Fixes: 6c65fb318e8b ("iommu: iommu_get_group_resv_regions")
Signed-off-by: Eric Auger <[email protected]>
Signed-off-by: Joerg Roedel <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/iommu/iommu.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8c15c5980299..bc14825edc9c 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -211,18 +211,21 @@ static int iommu_insert_resv_region(struct iommu_resv_region *new,
pos = pos->next;
} else if ((start >= a) && (end <= b)) {
if (new->type == type)
- goto done;
+ return 0;
else
pos = pos->next;
} else {
if (new->type == type) {
phys_addr_t new_start = min(a, start);
phys_addr_t new_end = max(b, end);
+ int ret;
list_del(&entry->list);
entry->start = new_start;
entry->length = new_end - new_start + 1;
- iommu_insert_resv_region(entry, regions);
+ ret = iommu_insert_resv_region(entry, regions);
+ kfree(entry);
+ return ret;
} else {
pos = pos->next;
}
@@ -235,7 +238,6 @@ static int iommu_insert_resv_region(struct iommu_resv_region *new,
return -ENOMEM;
list_add_tail(®ion->list, pos);
-done:
return 0;
}
--
2.20.1
From: Xingyu Chen <[email protected]>
[ Upstream commit c64a9e804ccf86eb202bfd1c6a8c5233c75a0431 ]
The Meson-G12A SoC uses the same GPIO interrupt controller IP block as the
other Meson SoCs, A totle of 100 pins can be spied on, which is the sum of:
- 223:100 undefined (no interrupt)
- 99:97 3 pins on bank GPIOE
- 96:77 20 pins on bank GPIOX
- 76:61 16 pins on bank GPIOA
- 60:53 8 pins on bank GPIOC
- 52:37 16 pins on bank BOOT
- 36:28 9 pins on bank GPIOH
- 27:12 16 pins on bank GPIOZ
- 11:0 12 pins in the AO domain
Signed-off-by: Xingyu Chen <[email protected]>
Signed-off-by: Jianxin Pan <[email protected]>
Signed-off-by: Martin Blumenstingl <[email protected]>
Signed-off-by: Marc Zyngier <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/irqchip/irq-meson-gpio.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
index 7b531fd075b8..7599b10ecf09 100644
--- a/drivers/irqchip/irq-meson-gpio.c
+++ b/drivers/irqchip/irq-meson-gpio.c
@@ -73,6 +73,7 @@ static const struct of_device_id meson_irq_gpio_matches[] = {
{ .compatible = "amlogic,meson-gxbb-gpio-intc", .data = &gxbb_params },
{ .compatible = "amlogic,meson-gxl-gpio-intc", .data = &gxl_params },
{ .compatible = "amlogic,meson-axg-gpio-intc", .data = &axg_params },
+ { .compatible = "amlogic,meson-g12a-gpio-intc", .data = &axg_params },
{ }
};
--
2.20.1
From: Srinivas Kandagatla <[email protected]>
[ Upstream commit db057679de3e9e6a03c1bcd5aee09b0d25fd9f5b ]
On buses like SlimBus and SoundWire which does not support
gather_writes yet in regmap, A bulk write on paged register
would be silently ignored after programming page.
This is because local variable 'ret' value in regmap_raw_write_impl()
gets reset to 0 once page register is written successfully and the
code below checks for 'ret' value to be -ENOTSUPP before linearising
the write buffer to send to bus->write().
Fix this by resetting the 'ret' value to -ENOTSUPP in cases where
gather_writes() is not supported or single register write is
not possible.
Signed-off-by: Srinivas Kandagatla <[email protected]>
Signed-off-by: Mark Brown <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/base/regmap/regmap.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 0360a90ad6b6..6c9f6988bc09 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1618,6 +1618,8 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
map->format.reg_bytes +
map->format.pad_bytes,
val, val_len);
+ else
+ ret = -ENOTSUPP;
/* If that didn't work fall back on linearising by hand. */
if (ret == -ENOTSUPP) {
--
2.20.1
From: Thomas Richter <[email protected]>
[ Upstream commit 53fe307dfd309e425b171f6272d64296a54f4dff ]
Command
# perf test -Fv 6
fails with error
running test 100 'kvm-s390:kvm_s390_create_vm' failed to parse
event 'kvm-s390:kvm_s390_create_vm', err -1, str 'unknown tracepoint'
event syntax error: 'kvm-s390:kvm_s390_create_vm'
\___ unknown tracepoint
when the kvm module is not loaded or not built in.
Fix this by adding a valid function which tests if the module
is loaded. Loaded modules (or builtin KVM support) have a
directory named
/sys/kernel/debug/tracing/events/kvm-s390
for this tracepoint.
Check for existence of this directory.
Signed-off-by: Thomas Richter <[email protected]>
Reviewed-by: Christian Borntraeger <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Hendrik Brueckner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/tests/parse-events.c | 27 +++++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 3b97ac018d5a..532c95e8fa6b 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -18,6 +18,32 @@
#define PERF_TP_SAMPLE_TYPE (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | \
PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD)
+#if defined(__s390x__)
+/* Return true if kvm module is available and loaded. Test this
+ * and retun success when trace point kvm_s390_create_vm
+ * exists. Otherwise this test always fails.
+ */
+static bool kvm_s390_create_vm_valid(void)
+{
+ char *eventfile;
+ bool rc = false;
+
+ eventfile = get_events_file("kvm-s390");
+
+ if (eventfile) {
+ DIR *mydir = opendir(eventfile);
+
+ if (mydir) {
+ rc = true;
+ closedir(mydir);
+ }
+ put_events_file(eventfile);
+ }
+
+ return rc;
+}
+#endif
+
static int test__checkevent_tracepoint(struct perf_evlist *evlist)
{
struct perf_evsel *evsel = perf_evlist__first(evlist);
@@ -1622,6 +1648,7 @@ static struct evlist_test test__events[] = {
{
.name = "kvm-s390:kvm_s390_create_vm",
.check = test__checkevent_tracepoint,
+ .valid = kvm_s390_create_vm_valid,
.id = 100,
},
#endif
--
2.20.1
From: Waiman Long <[email protected]>
[ Upstream commit 6da9f775175e516fc7229ceaa9b54f8f56aa7924 ]
When debugging options are turned on, the rcu_read_lock() function
might not be inlined. This results in lockdep's print_lock() function
printing "rcu_read_lock+0x0/0x70" instead of rcu_read_lock()'s caller.
For example:
[ 10.579995] =============================
[ 10.584033] WARNING: suspicious RCU usage
[ 10.588074] 4.18.0.memcg_v2+ #1 Not tainted
[ 10.593162] -----------------------------
[ 10.597203] include/linux/rcupdate.h:281 Illegal context switch in
RCU read-side critical section!
[ 10.606220]
[ 10.606220] other info that might help us debug this:
[ 10.606220]
[ 10.614280]
[ 10.614280] rcu_scheduler_active = 2, debug_locks = 1
[ 10.620853] 3 locks held by systemd/1:
[ 10.624632] #0: (____ptrval____) (&type->i_mutex_dir_key#5){.+.+}, at: lookup_slow+0x42/0x70
[ 10.633232] #1: (____ptrval____) (rcu_read_lock){....}, at: rcu_read_lock+0x0/0x70
[ 10.640954] #2: (____ptrval____) (rcu_read_lock){....}, at: rcu_read_lock+0x0/0x70
These "rcu_read_lock+0x0/0x70" strings are not providing any useful
information. This commit therefore forces inlining of the rcu_read_lock()
function so that rcu_read_lock()'s caller is instead shown.
Signed-off-by: Waiman Long <[email protected]>
Signed-off-by: Paul E. McKenney <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
include/linux/rcupdate.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index e102c5bccbb9..68cbe111420b 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -620,7 +620,7 @@ static inline void rcu_preempt_sleep_check(void) { }
* read-side critical sections may be preempted and they may also block, but
* only when acquiring spinlocks that are subject to priority inheritance.
*/
-static inline void rcu_read_lock(void)
+static __always_inline void rcu_read_lock(void)
{
__rcu_read_lock();
__acquire(RCU);
--
2.20.1
From: Michal Kalderon <[email protected]>
[ Upstream commit cb94d52b93c74fe1f2595734fabeda9f8ae891ee ]
The driver needs to assign a lossless traffic class for the MPA ll2
connection to ensure no packets are dropped when returning from the
driver as they will never be re-transmitted by the peer.
Fixes: ae3488ff37dc ("qed: Add ll2 connection for processing unaligned MPA packets")
Signed-off-by: Ariel Elior <[email protected]>
Signed-off-by: Michal Kalderon <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index b7471e48db7b..7002a660b6b4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -2709,6 +2709,8 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
data.input.rx_num_desc = n_ooo_bufs * 2;
data.input.tx_num_desc = data.input.rx_num_desc;
data.input.tx_max_bds_per_packet = QED_IWARP_MAX_BDS_PER_FPDU;
+ data.input.tx_tc = PKT_LB_TC;
+ data.input.tx_dest = QED_LL2_TX_DEST_LB;
data.p_connection_handle = &iwarp_info->ll2_mpa_handle;
data.input.secondary_queue = true;
data.cbs = &cbs;
--
2.20.1
From: Ondrej Mosnacek <[email protected]>
[ Upstream commit 464c258aa45b09f16aa0f05847ed8895873262d9 ]
When sid == 0 (we are resetting keycreate_sid to the default value), we
should skip the KEY__CREATE check.
Before this patch, doing a zero-sized write to /proc/self/keycreate
would check if the current task can create unlabeled keys (which would
usually fail with -EACCESS and generate an AVC). Now it skips the check
and correctly sets the task's keycreate_sid to 0.
Bug report: https://bugzilla.redhat.com/show_bug.cgi?id=1719067
Tested using the reproducer from the report above.
Fixes: 4eb582cf1fbd ("[PATCH] keys: add a way to store the appropriate context for newly-created keys")
Reported-by: Kir Kolyshkin <[email protected]>
Signed-off-by: Ondrej Mosnacek <[email protected]>
Signed-off-by: Paul Moore <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
security/selinux/hooks.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 70bad15ed7a0..109ab510bdb1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -6550,11 +6550,12 @@ static int selinux_setprocattr(const char *name, void *value, size_t size)
} else if (!strcmp(name, "fscreate")) {
tsec->create_sid = sid;
} else if (!strcmp(name, "keycreate")) {
- error = avc_has_perm(&selinux_state,
- mysid, sid, SECCLASS_KEY, KEY__CREATE,
- NULL);
- if (error)
- goto abort_change;
+ if (sid) {
+ error = avc_has_perm(&selinux_state, mysid, sid,
+ SECCLASS_KEY, KEY__CREATE, NULL);
+ if (error)
+ goto abort_change;
+ }
tsec->keycreate_sid = sid;
} else if (!strcmp(name, "sockcreate")) {
tsec->sockcreate_sid = sid;
--
2.20.1
From: Aaron Lewis <[email protected]>
[ Upstream commit cbb99c0f588737ec98c333558922ce47e9a95827 ]
Add the CPUID enumeration for Intel's de-feature bits to accommodate
passing these de-features through to kvm guests.
These de-features are (from SDM vol 1, section 8.1.8):
- X86_FEATURE_FDP_EXCPTN_ONLY: If CPUID.(EAX=07H,ECX=0H):EBX[bit 6] = 1, the
data pointer (FDP) is updated only for the x87 non-control instructions that
incur unmasked x87 exceptions.
- X86_FEATURE_ZERO_FCS_FDS: If CPUID.(EAX=07H,ECX=0H):EBX[bit 13] = 1, the
processor deprecates FCS and FDS; it saves each as 0000H.
Signed-off-by: Aaron Lewis <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Jim Mattson <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: Frederic Weisbecker <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Konrad Rzeszutek Wilk <[email protected]>
Cc: [email protected]
Cc: Peter Feiner <[email protected]>
Cc: [email protected]
Cc: Robert Hoo <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Thomas Lendacky <[email protected]>
Cc: x86-ml <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/include/asm/cpufeatures.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 69037da75ea0..0cf704933f23 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -239,12 +239,14 @@
#define X86_FEATURE_BMI1 ( 9*32+ 3) /* 1st group bit manipulation extensions */
#define X86_FEATURE_HLE ( 9*32+ 4) /* Hardware Lock Elision */
#define X86_FEATURE_AVX2 ( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
#define X86_FEATURE_SMEP ( 9*32+ 7) /* Supervisor Mode Execution Protection */
#define X86_FEATURE_BMI2 ( 9*32+ 8) /* 2nd group bit manipulation extensions */
#define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
#define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */
#define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */
#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* "" Zero out FPU CS and FPU DS */
#define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */
#define X86_FEATURE_RDT_A ( 9*32+15) /* Resource Director Technology Allocation */
#define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */
--
2.20.1
From: Tejun Heo <[email protected]>
[ Upstream commit 6631142229005e1b1c311a09efe9fb3cfdac8559 ]
wbc_account_io() collects information on cgroup ownership of writeback
pages to determine which cgroup should own the inode. Pages can stay
associated with dead memcgs but we want to avoid attributing IOs to
dead blkcgs as much as possible as the association is likely to be
stale. However, currently, pages associated with dead memcgs
contribute to the accounting delaying and/or confusing the
arbitration.
Fix it by ignoring pages associated with dead memcgs.
Signed-off-by: Tejun Heo <[email protected]>
Cc: Jan Kara <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
fs/fs-writeback.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 9544e2f8b79f..7ee86d8f313d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -721,6 +721,7 @@ void wbc_detach_inode(struct writeback_control *wbc)
void wbc_account_io(struct writeback_control *wbc, struct page *page,
size_t bytes)
{
+ struct cgroup_subsys_state *css;
int id;
/*
@@ -732,7 +733,12 @@ void wbc_account_io(struct writeback_control *wbc, struct page *page,
if (!wbc->wb)
return;
- id = mem_cgroup_css_from_page(page)->id;
+ css = mem_cgroup_css_from_page(page);
+ /* dead cgroups shouldn't contribute to inode ownership arbitration */
+ if (!(css->flags & CSS_ONLINE))
+ return;
+
+ id = css->id;
if (id == wbc->wb_id) {
wbc->wb_bytes += bytes;
--
2.20.1
From: Russell King <[email protected]>
[ Upstream commit 64ea3e9094a1f13b96c33244a3fb3a0f45690bd2 ]
Commit 384ebe1c2849 ("gpio/omap: Add DT support to GPIO driver") added
the register definition tables to the gpio-omap driver. Subsequently to
that commit, commit 4e962e8998cc ("gpio/omap: remove cpu_is_omapxxxx()
checks from *_runtime_resume()") added definitions for irqstatus_raw*
registers to the legacy OMAP4 definitions, but missed the DT
definitions.
This causes an unintentional change of behaviour for the 1.101 errata
workaround on OMAP4 platforms. Fix this oversight.
Fixes: 4e962e8998cc ("gpio/omap: remove cpu_is_omapxxxx() checks from *_runtime_resume()")
Signed-off-by: Russell King <[email protected]>
Signed-off-by: Grygorii Strashko <[email protected]>
Tested-by: Tony Lindgren <[email protected]>
Signed-off-by: Linus Walleij <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/gpio/gpio-omap.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 6fa430d98517..9254bcf7f647 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1687,6 +1687,8 @@ static struct omap_gpio_reg_offs omap4_gpio_regs = {
.clr_dataout = OMAP4_GPIO_CLEARDATAOUT,
.irqstatus = OMAP4_GPIO_IRQSTATUS0,
.irqstatus2 = OMAP4_GPIO_IRQSTATUS1,
+ .irqstatus_raw0 = OMAP4_GPIO_IRQSTATUSRAW0,
+ .irqstatus_raw1 = OMAP4_GPIO_IRQSTATUSRAW1,
.irqenable = OMAP4_GPIO_IRQSTATUSSET0,
.irqenable2 = OMAP4_GPIO_IRQSTATUSSET1,
.set_irqenable = OMAP4_GPIO_IRQSTATUSSET0,
--
2.20.1
From: Jerome Brunet <[email protected]>
[ Upstream commit cb36ff785e868992e96e8b9e5a0c2822b680a9e2 ]
The content of SND_SOC_DAIFMT_FORMAT_MASK is a number, not a bitfield,
so the test to check if the format is i2s is wrong. Because of this the
clock setting may be wrong. For example, the sample clock gets inverted
in DSP B mode, when it should not.
Fix the lrclk invert helper function
Fixes: 1a11d88f499c ("ASoC: meson: add tdm formatter base driver")
Signed-off-by: Jerome Brunet <[email protected]>
Signed-off-by: Mark Brown <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
sound/soc/meson/axg-tdm.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/sound/soc/meson/axg-tdm.h b/sound/soc/meson/axg-tdm.h
index e578b6f40a07..5774ce0916d4 100644
--- a/sound/soc/meson/axg-tdm.h
+++ b/sound/soc/meson/axg-tdm.h
@@ -40,7 +40,7 @@ struct axg_tdm_iface {
static inline bool axg_tdm_lrclk_invert(unsigned int fmt)
{
- return (fmt & SND_SOC_DAIFMT_I2S) ^
+ return ((fmt & SND_SOC_DAIFMT_FORMAT_MASK) == SND_SOC_DAIFMT_I2S) ^
!!(fmt & (SND_SOC_DAIFMT_IB_IF | SND_SOC_DAIFMT_NB_IF));
}
--
2.20.1
From: Kieran Bingham <[email protected]>
[ Upstream commit 4e8c120de9268fc26f583268b9d22e7d37c4595f ]
New Gen3 R-Car platforms incorporate the FDP1 with an updated version
register. No code change is required to support these targets, but they
will currently report an error stating that the device can not be
identified.
Update the driver to match against the new device types.
Signed-off-by: Kieran Bingham <[email protected]>
Signed-off-by: Laurent Pinchart <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/rcar_fdp1.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c
index 2a15b7cca338..0d1467028811 100644
--- a/drivers/media/platform/rcar_fdp1.c
+++ b/drivers/media/platform/rcar_fdp1.c
@@ -257,6 +257,8 @@ MODULE_PARM_DESC(debug, "activate debug info");
#define FD1_IP_H3_ES1 0x02010101
#define FD1_IP_M3W 0x02010202
#define FD1_IP_H3 0x02010203
+#define FD1_IP_M3N 0x02010204
+#define FD1_IP_E3 0x02010205
/* LUTs */
#define FD1_LUT_DIF_ADJ 0x1000
@@ -2365,6 +2367,12 @@ static int fdp1_probe(struct platform_device *pdev)
case FD1_IP_H3:
dprintk(fdp1, "FDP1 Version R-Car H3\n");
break;
+ case FD1_IP_M3N:
+ dprintk(fdp1, "FDP1 Version R-Car M3N\n");
+ break;
+ case FD1_IP_E3:
+ dprintk(fdp1, "FDP1 Version R-Car E3\n");
+ break;
default:
dev_err(fdp1->dev, "FDP1 Unidentifiable (0x%08x)\n",
hw_version);
--
2.20.1
From: Gao Xiang <[email protected]>
[ Upstream commit e3b929b0a184edb35531153c5afcaebb09014f9d ]
Non-inline io_schedule() was introduced in:
commit 10ab56434f2f ("sched/core: Separate out io_schedule_prepare() and io_schedule_finish()")
Keep in line with io_schedule_timeout(), otherwise "/proc/<pid>/wchan" will
report io_schedule() rather than its callers when waiting for IO.
Reported-by: Jilong Kou <[email protected]>
Signed-off-by: Gao Xiang <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Tejun Heo <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Miao Xie <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Fixes: 10ab56434f2f ("sched/core: Separate out io_schedule_prepare() and io_schedule_finish()")
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
kernel/sched/core.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6859ea1d5c04..795c63ca44a9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5133,7 +5133,7 @@ long __sched io_schedule_timeout(long timeout)
}
EXPORT_SYMBOL(io_schedule_timeout);
-void io_schedule(void)
+void __sched io_schedule(void)
{
int token;
--
2.20.1
From: Peter Zijlstra <[email protected]>
[ Upstream commit 69d927bba39517d0980462efc051875b7f4db185 ]
Recent probing at the Linux Kernel Memory Model uncovered a
'surprise'. Strongly ordered architectures where the atomic RmW
primitive implies full memory ordering and
smp_mb__{before,after}_atomic() are a simple barrier() (such as x86)
fail for:
*x = 1;
atomic_inc(u);
smp_mb__after_atomic();
r0 = *y;
Because, while the atomic_inc() implies memory order, it
(surprisingly) does not provide a compiler barrier. This then allows
the compiler to re-order like so:
atomic_inc(u);
*x = 1;
smp_mb__after_atomic();
r0 = *y;
Which the CPU is then allowed to re-order (under TSO rules) like:
atomic_inc(u);
r0 = *y;
*x = 1;
And this very much was not intended. Therefore strengthen the atomic
RmW ops to include a compiler barrier.
NOTE: atomic_{or,and,xor} and the bitops already had the compiler
barrier.
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
Documentation/atomic_t.txt | 3 +++
arch/x86/include/asm/atomic.h | 8 ++++----
arch/x86/include/asm/atomic64_64.h | 8 ++++----
arch/x86/include/asm/barrier.h | 4 ++--
4 files changed, 13 insertions(+), 10 deletions(-)
diff --git a/Documentation/atomic_t.txt b/Documentation/atomic_t.txt
index 913396ac5824..ed0d814df7e0 100644
--- a/Documentation/atomic_t.txt
+++ b/Documentation/atomic_t.txt
@@ -177,6 +177,9 @@ These helper barriers exist because architectures have varying implicit
ordering on their SMP atomic primitives. For example our TSO architectures
provide full ordered atomics and these barriers are no-ops.
+NOTE: when the atomic RmW ops are fully ordered, they should also imply a
+compiler barrier.
+
Thus:
atomic_fetch_add();
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ce84388e540c..d266a4066289 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -54,7 +54,7 @@ static __always_inline void arch_atomic_add(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "addl %1,%0"
: "+m" (v->counter)
- : "ir" (i));
+ : "ir" (i) : "memory");
}
/**
@@ -68,7 +68,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
{
asm volatile(LOCK_PREFIX "subl %1,%0"
: "+m" (v->counter)
- : "ir" (i));
+ : "ir" (i) : "memory");
}
/**
@@ -95,7 +95,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
static __always_inline void arch_atomic_inc(atomic_t *v)
{
asm volatile(LOCK_PREFIX "incl %0"
- : "+m" (v->counter));
+ : "+m" (v->counter) :: "memory");
}
#define arch_atomic_inc arch_atomic_inc
@@ -108,7 +108,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
static __always_inline void arch_atomic_dec(atomic_t *v)
{
asm volatile(LOCK_PREFIX "decl %0"
- : "+m" (v->counter));
+ : "+m" (v->counter) :: "memory");
}
#define arch_atomic_dec arch_atomic_dec
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 5f851d92eecd..55ca027f8c1c 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -45,7 +45,7 @@ static __always_inline void arch_atomic64_add(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "addq %1,%0"
: "=m" (v->counter)
- : "er" (i), "m" (v->counter));
+ : "er" (i), "m" (v->counter) : "memory");
}
/**
@@ -59,7 +59,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
{
asm volatile(LOCK_PREFIX "subq %1,%0"
: "=m" (v->counter)
- : "er" (i), "m" (v->counter));
+ : "er" (i), "m" (v->counter) : "memory");
}
/**
@@ -87,7 +87,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "incq %0"
: "=m" (v->counter)
- : "m" (v->counter));
+ : "m" (v->counter) : "memory");
}
#define arch_atomic64_inc arch_atomic64_inc
@@ -101,7 +101,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
{
asm volatile(LOCK_PREFIX "decq %0"
: "=m" (v->counter)
- : "m" (v->counter));
+ : "m" (v->counter) : "memory");
}
#define arch_atomic64_dec arch_atomic64_dec
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 14de0432d288..84f848c2541a 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -80,8 +80,8 @@ do { \
})
/* Atomic operations are already serializing on x86 */
-#define __smp_mb__before_atomic() barrier()
-#define __smp_mb__after_atomic() barrier()
+#define __smp_mb__before_atomic() do { } while (0)
+#define __smp_mb__after_atomic() do { } while (0)
#include <asm-generic/barrier.h>
--
2.20.1
From: Qian Cai <[email protected]>
[ Upstream commit 509466b7d480bc5d22e90b9fbe6122ae0e2fbe39 ]
runnable_avg_yN_inv[] is only used in kernel/sched/pelt.c but was
included in several other places because they need other macros all
came from kernel/sched/sched-pelt.h which was generated by
Documentation/scheduler/sched-pelt. As the result, it causes compilation
a lot of warnings,
kernel/sched/sched-pelt.h:4:18: warning: 'runnable_avg_yN_inv' defined but not used [-Wunused-const-variable=]
kernel/sched/sched-pelt.h:4:18: warning: 'runnable_avg_yN_inv' defined but not used [-Wunused-const-variable=]
kernel/sched/sched-pelt.h:4:18: warning: 'runnable_avg_yN_inv' defined but not used [-Wunused-const-variable=]
...
Silence it by appending the __maybe_unused attribute for it, so all
generated variables and macros can still be kept in the same file.
Signed-off-by: Qian Cai <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
Documentation/scheduler/sched-pelt.c | 3 ++-
kernel/sched/sched-pelt.h | 2 +-
2 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/Documentation/scheduler/sched-pelt.c b/Documentation/scheduler/sched-pelt.c
index e4219139386a..7238b355919c 100644
--- a/Documentation/scheduler/sched-pelt.c
+++ b/Documentation/scheduler/sched-pelt.c
@@ -20,7 +20,8 @@ void calc_runnable_avg_yN_inv(void)
int i;
unsigned int x;
- printf("static const u32 runnable_avg_yN_inv[] = {");
+ /* To silence -Wunused-but-set-variable warnings. */
+ printf("static const u32 runnable_avg_yN_inv[] __maybe_unused = {");
for (i = 0; i < HALFLIFE; i++) {
x = ((1UL<<32)-1)*pow(y, i);
diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h
index a26473674fb7..c529706bed11 100644
--- a/kernel/sched/sched-pelt.h
+++ b/kernel/sched/sched-pelt.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Generated by Documentation/scheduler/sched-pelt; do not modify. */
-static const u32 runnable_avg_yN_inv[] = {
+static const u32 runnable_avg_yN_inv[] __maybe_unused = {
0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,
--
2.20.1
From: Arnaldo Carvalho de Melo <[email protected]>
[ Upstream commit fdbdd7e8580eac9bdafa532746c865644d125e34 ]
In which case it simply returns "unknown", like when it can't figure out
the evsel->name value.
This makes this code more robust and fixes a problem in 'perf trace'
where a NULL evsel was being passed to a routine that only used the
evsel for printing its name when a invalid syscall id was passed.
Reported-by: Leo Yan <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Namhyung Kim <[email protected]>
Link: https://lkml.kernel.org/n/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/util/evsel.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b65ad5a273eb..4fad92213609 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -590,6 +590,9 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
{
char bf[128];
+ if (!evsel)
+ goto out_unknown;
+
if (evsel->name)
return evsel->name;
@@ -626,7 +629,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
evsel->name = strdup(bf);
- return evsel->name ?: "unknown";
+ if (evsel->name)
+ return evsel->name;
+out_unknown:
+ return "unknown";
}
const char *perf_evsel__group_name(struct perf_evsel *evsel)
--
2.20.1
From: Denis Kirjanov <[email protected]>
[ Upstream commit 64d701c608fea362881e823b666327f5d28d7ffd ]
in the case of IPoIB with SRIOV enabled hardware
ip link show command incorrecly prints
0 instead of a VF hardware address.
Before:
11: ib1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 2044 qdisc pfifo_fast
state UP mode DEFAULT group default qlen 256
link/infiniband
80:00:00:66:fe:80:00:00:00:00:00:00:24:8a:07:03:00:a4:3e:7c brd
00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff
vf 0 MAC 00:00:00:00:00:00, spoof checking off, link-state disable,
trust off, query_rss off
...
After:
11: ib1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 2044 qdisc pfifo_fast
state UP mode DEFAULT group default qlen 256
link/infiniband
80:00:00:66:fe:80:00:00:00:00:00:00:24:8a:07:03:00:a4:3e:7c brd
00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff
vf 0 link/infiniband
80:00:00:66:fe:80:00:00:00:00:00:00:24:8a:07:03:00:a4:3e:7c brd
00:ff:ff:ff:ff:12:40:1b:ff:ff:00:00:00:00:00:00:ff:ff:ff:ff, spoof
checking off, link-state disable, trust off, query_rss off
v1->v2: just copy an address without modifing ifla_vf_mac
v2->v3: update the changelog
Signed-off-by: Denis Kirjanov <[email protected]>
Acked-by: Doug Ledford <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/infiniband/ulp/ipoib/ipoib_main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 30f840f874b3..009615499b37 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1997,6 +1997,7 @@ static int ipoib_get_vf_config(struct net_device *dev, int vf,
return err;
ivf->vf = vf;
+ memcpy(ivf->mac, dev->dev_addr, dev->addr_len);
return 0;
}
--
2.20.1
From: Jason Wang <[email protected]>
[ Upstream commit 098eadce3c622c07b328d0a43dda379b38cf7c5e ]
Vhost_net was known to suffer from HOL[1] issues which is not easy to
fix. Several downstream disable the feature by default. What's more,
the datapath was split and datacopy path got the support of batching
and XDP support recently which makes it faster than zerocopy part for
small packets transmission.
It looks to me that disable zerocopy by default is more
appropriate. It cold be enabled by default again in the future if we
fix the above issues.
[1] https://patchwork.kernel.org/patch/3787671/
Signed-off-by: Jason Wang <[email protected]>
Acked-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/vhost/net.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 39155d7cc894..ae704658b528 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -36,7 +36,7 @@
#include "vhost.h"
-static int experimental_zcopytx = 1;
+static int experimental_zcopytx = 0;
module_param(experimental_zcopytx, int, 0444);
MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;"
" 1 -Enable; 0 - Disable");
--
2.20.1
From: Russell King <[email protected]>
[ Upstream commit c859e0d479b3b4f6132fc12637c51e01492f31f6 ]
Documentation states:
NOTE: There must be a correlation between the wake-up enable and
interrupt-enable registers. If a GPIO pin has a wake-up configured
on it, it must also have the corresponding interrupt enabled (on
one of the two interrupt lines).
Ensure that this condition is always satisfied by enabling the detection
events after enabling the interrupt, and disabling the detection before
disabling the interrupt. This ensures interrupt/wakeup events can not
happen until both the wakeup and interrupt enables correlate.
If we do any clearing, clear between the interrupt enable/disable and
trigger setting.
Signed-off-by: Russell King <[email protected]>
Signed-off-by: Grygorii Strashko <[email protected]>
Tested-by: Tony Lindgren <[email protected]>
Signed-off-by: Linus Walleij <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/gpio/gpio-omap.c | 15 ++++++++-------
1 file changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 9254bcf7f647..feabac40743e 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -837,9 +837,9 @@ static void omap_gpio_irq_shutdown(struct irq_data *d)
raw_spin_lock_irqsave(&bank->lock, flags);
bank->irq_usage &= ~(BIT(offset));
- omap_set_gpio_irqenable(bank, offset, 0);
- omap_clear_gpio_irqstatus(bank, offset);
omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
+ omap_clear_gpio_irqstatus(bank, offset);
+ omap_set_gpio_irqenable(bank, offset, 0);
if (!LINE_USED(bank->mod_usage, offset))
omap_clear_gpio_debounce(bank, offset);
omap_disable_gpio_module(bank, offset);
@@ -881,8 +881,8 @@ static void omap_gpio_mask_irq(struct irq_data *d)
unsigned long flags;
raw_spin_lock_irqsave(&bank->lock, flags);
- omap_set_gpio_irqenable(bank, offset, 0);
omap_set_gpio_triggering(bank, offset, IRQ_TYPE_NONE);
+ omap_set_gpio_irqenable(bank, offset, 0);
raw_spin_unlock_irqrestore(&bank->lock, flags);
}
@@ -894,9 +894,6 @@ static void omap_gpio_unmask_irq(struct irq_data *d)
unsigned long flags;
raw_spin_lock_irqsave(&bank->lock, flags);
- if (trigger)
- omap_set_gpio_triggering(bank, offset, trigger);
-
omap_set_gpio_irqenable(bank, offset, 1);
/*
@@ -904,9 +901,13 @@ static void omap_gpio_unmask_irq(struct irq_data *d)
* is cleared, thus after the handler has run. OMAP4 needs this done
* after enabing the interrupt to clear the wakeup status.
*/
- if (bank->level_mask & BIT(offset))
+ if (bank->regs->leveldetect0 && bank->regs->wkup_en &&
+ trigger & (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW))
omap_clear_gpio_irqstatus(bank, offset);
+ if (trigger)
+ omap_set_gpio_triggering(bank, offset, trigger);
+
raw_spin_unlock_irqrestore(&bank->lock, flags);
}
--
2.20.1
From: Marek Szyprowski <[email protected]>
[ Upstream commit be22203aec440c1761ce8542c2636ac6c8951e3a ]
MFC v6 and v7 has no register to read min scratch buffer size, so it has
to be read conditionally only if hardware supports it. This fixes following
NULL pointer exception on SoCs with MFC v6/v7:
8<--- cut here ---
Unable to handle kernel NULL pointer dereference at virtual address 00000000
pgd = f25837f9
[00000000] *pgd=bd93d835
Internal error: Oops: 17 [#1] PREEMPT SMP ARM
Modules linked in: btmrvl_sdio btmrvl bluetooth mwifiex_sdio mwifiex ecdh_generic ecc
Hardware name: SAMSUNG EXYNOS (Flattened Device Tree)
PC is at s5p_mfc_get_min_scratch_buf_size+0x30/0x3c
LR is at s5p_mfc_get_min_scratch_buf_size+0x28/0x3c
...
[<c074f998>] (s5p_mfc_get_min_scratch_buf_size) from [<c0745bc0>] (s5p_mfc_irq+0x814/0xa5c)
[<c0745bc0>] (s5p_mfc_irq) from [<c019a218>] (__handle_irq_event_percpu+0x64/0x3f8)
[<c019a218>] (__handle_irq_event_percpu) from [<c019a5d8>] (handle_irq_event_percpu+0x2c/0x7c)
[<c019a5d8>] (handle_irq_event_percpu) from [<c019a660>] (handle_irq_event+0x38/0x5c)
[<c019a660>] (handle_irq_event) from [<c019ebc4>] (handle_fasteoi_irq+0xc4/0x180)
[<c019ebc4>] (handle_fasteoi_irq) from [<c0199270>] (generic_handle_irq+0x24/0x34)
[<c0199270>] (generic_handle_irq) from [<c0199888>] (__handle_domain_irq+0x7c/0xec)
[<c0199888>] (__handle_domain_irq) from [<c04ac298>] (gic_handle_irq+0x58/0x9c)
[<c04ac298>] (gic_handle_irq) from [<c0101ab0>] (__irq_svc+0x70/0xb0)
Exception stack(0xe73ddc60 to 0xe73ddca8)
...
[<c0101ab0>] (__irq_svc) from [<c01967d8>] (console_unlock+0x5a8/0x6a8)
[<c01967d8>] (console_unlock) from [<c01981d0>] (vprintk_emit+0x118/0x2d8)
[<c01981d0>] (vprintk_emit) from [<c01983b0>] (vprintk_default+0x20/0x28)
[<c01983b0>] (vprintk_default) from [<c01989b4>] (printk+0x30/0x54)
[<c01989b4>] (printk) from [<c07500b8>] (s5p_mfc_init_decode_v6+0x1d4/0x284)
[<c07500b8>] (s5p_mfc_init_decode_v6) from [<c07230d0>] (vb2_start_streaming+0x24/0x150)
[<c07230d0>] (vb2_start_streaming) from [<c0724e4c>] (vb2_core_streamon+0x11c/0x15c)
[<c0724e4c>] (vb2_core_streamon) from [<c07478b8>] (vidioc_streamon+0x64/0xa0)
[<c07478b8>] (vidioc_streamon) from [<c0709640>] (__video_do_ioctl+0x28c/0x45c)
[<c0709640>] (__video_do_ioctl) from [<c0709bc8>] (video_usercopy+0x260/0x8a4)
[<c0709bc8>] (video_usercopy) from [<c02b3820>] (do_vfs_ioctl+0xb0/0x9fc)
[<c02b3820>] (do_vfs_ioctl) from [<c02b41a0>] (ksys_ioctl+0x34/0x58)
[<c02b41a0>] (ksys_ioctl) from [<c0101000>] (ret_fast_syscall+0x0/0x28)
Exception stack(0xe73ddfa8 to 0xe73ddff0)
...
---[ end trace 376cf5ba6e0bee93 ]---
Signed-off-by: Marek Szyprowski <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/s5p-mfc/s5p_mfc.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index ca11f8a7569d..4b8516c35bc2 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -527,7 +527,8 @@ static void s5p_mfc_handle_seq_done(struct s5p_mfc_ctx *ctx,
dev);
ctx->mv_count = s5p_mfc_hw_call(dev->mfc_ops, get_mv_count,
dev);
- ctx->scratch_buf_size = s5p_mfc_hw_call(dev->mfc_ops,
+ if (FW_HAS_E_MIN_SCRATCH_BUF(dev))
+ ctx->scratch_buf_size = s5p_mfc_hw_call(dev->mfc_ops,
get_min_scratch_buf_size, dev);
if (ctx->img_width == 0 || ctx->img_height == 0)
ctx->state = MFCINST_ERROR;
--
2.20.1
From: Qian Cai <[email protected]>
[ Upstream commit 1b7aebf0487613033aff26420e32fa2076d52846 ]
cpuinfo_x86.x86_model is an unsigned type, so comparing against zero
will generate a compilation warning:
arch/x86/kernel/cpu/cacheinfo.c: In function 'cacheinfo_amd_init_llc_id':
arch/x86/kernel/cpu/cacheinfo.c:662:19: warning: comparison is always true \
due to limited range of data type [-Wtype-limits]
Remove the unnecessary lower bound check.
[ bp: Massage. ]
Fixes: 68091ee7ac3c ("x86/CPU/AMD: Calculate last level cache ID from number of sharing threads")
Signed-off-by: Qian Cai <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Sean Christopherson <[email protected]>
Cc: "Gustavo A. R. Silva" <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Masami Hiramatsu <[email protected]>
Cc: Pu Wen <[email protected]>
Cc: Suravee Suthikulpanit <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: x86-ml <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/kernel/cpu/cacheinfo.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 0c5fcbd998cf..9d863e8f9b3f 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -651,8 +651,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
if (c->x86 < 0x17) {
/* LLC is at the node level. */
per_cpu(cpu_llc_id, cpu) = node_id;
- } else if (c->x86 == 0x17 &&
- c->x86_model >= 0 && c->x86_model <= 0x1F) {
+ } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
/*
* LLC is at the core complex level.
* Core complex ID is ApicId[3] for these processors.
--
2.20.1
From: "Rafael J. Wysocki" <[email protected]>
[ Upstream commit 44758bafa53602f2581a6857bb20b55d4d8ad5b2 ]
ACPI GPEs (other than the EC one) can be enabled in two situations.
First, the GPEs with existing _Lxx and _Exx methods are enabled
implicitly by ACPICA during system initialization. Second, the
GPEs without these methods (like GPEs listed by _PRW objects for
wakeup devices) need to be enabled directly by the code that is
going to use them (e.g. ACPI power management or device drivers).
In the former case, if the status of a given GPE is set to start
with, its handler method (either _Lxx or _Exx) needs to be invoked
to take care of the events (possibly) signaled before the GPE was
enabled. In the latter case, however, the first caller of
acpi_enable_gpe() for a given GPE should not be expected to care
about any events that might be signaled through it earlier. In
that case, it is better to clear the status of the GPE before
enabling it, to prevent stale events from triggering unwanted
actions (like spurious system resume, for example).
For this reason, modify acpi_ev_add_gpe_reference() to take an
additional boolean argument indicating whether or not the GPE
status needs to be cleared when its reference counter changes from
zero to one and make acpi_enable_gpe() pass TRUE to it through
that new argument.
Fixes: 18996f2db918 ("ACPICA: Events: Stop unconditionally clearing ACPI IRQs during suspend/resume")
Reported-by: Furquan Shaikh <[email protected]>
Tested-by: Furquan Shaikh <[email protected]>
Tested-by: Mika Westerberg <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/acpi/acpica/acevents.h | 3 ++-
drivers/acpi/acpica/evgpe.c | 8 +++++++-
drivers/acpi/acpica/evgpeblk.c | 2 +-
drivers/acpi/acpica/evxface.c | 2 +-
drivers/acpi/acpica/evxfgpe.c | 2 +-
5 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
index 704bebbd35b0..298180bf7e3c 100644
--- a/drivers/acpi/acpica/acevents.h
+++ b/drivers/acpi/acpica/acevents.h
@@ -69,7 +69,8 @@ acpi_status
acpi_ev_mask_gpe(struct acpi_gpe_event_info *gpe_event_info, u8 is_masked);
acpi_status
-acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info);
+acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info,
+ u8 clear_on_enable);
acpi_status
acpi_ev_remove_gpe_reference(struct acpi_gpe_event_info *gpe_event_info);
diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index e10fec99a182..4b5d3b4c627a 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -146,6 +146,7 @@ acpi_ev_mask_gpe(struct acpi_gpe_event_info *gpe_event_info, u8 is_masked)
* FUNCTION: acpi_ev_add_gpe_reference
*
* PARAMETERS: gpe_event_info - Add a reference to this GPE
+ * clear_on_enable - Clear GPE status before enabling it
*
* RETURN: Status
*
@@ -155,7 +156,8 @@ acpi_ev_mask_gpe(struct acpi_gpe_event_info *gpe_event_info, u8 is_masked)
******************************************************************************/
acpi_status
-acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info)
+acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info,
+ u8 clear_on_enable)
{
acpi_status status = AE_OK;
@@ -170,6 +172,10 @@ acpi_ev_add_gpe_reference(struct acpi_gpe_event_info *gpe_event_info)
/* Enable on first reference */
+ if (clear_on_enable) {
+ (void)acpi_hw_clear_gpe(gpe_event_info);
+ }
+
status = acpi_ev_update_gpe_enable_mask(gpe_event_info);
if (ACPI_SUCCESS(status)) {
status = acpi_ev_enable_gpe(gpe_event_info);
diff --git a/drivers/acpi/acpica/evgpeblk.c b/drivers/acpi/acpica/evgpeblk.c
index b253063b09d3..8d96270ed8c7 100644
--- a/drivers/acpi/acpica/evgpeblk.c
+++ b/drivers/acpi/acpica/evgpeblk.c
@@ -453,7 +453,7 @@ acpi_ev_initialize_gpe_block(struct acpi_gpe_xrupt_info *gpe_xrupt_info,
continue;
}
- status = acpi_ev_add_gpe_reference(gpe_event_info);
+ status = acpi_ev_add_gpe_reference(gpe_event_info, FALSE);
if (ACPI_FAILURE(status)) {
ACPI_EXCEPTION((AE_INFO, status,
"Could not enable GPE 0x%02X",
diff --git a/drivers/acpi/acpica/evxface.c b/drivers/acpi/acpica/evxface.c
index febc332b00ac..841557bda641 100644
--- a/drivers/acpi/acpica/evxface.c
+++ b/drivers/acpi/acpica/evxface.c
@@ -971,7 +971,7 @@ acpi_remove_gpe_handler(acpi_handle gpe_device,
ACPI_GPE_DISPATCH_METHOD) ||
(ACPI_GPE_DISPATCH_TYPE(handler->original_flags) ==
ACPI_GPE_DISPATCH_NOTIFY)) && handler->originally_enabled) {
- (void)acpi_ev_add_gpe_reference(gpe_event_info);
+ (void)acpi_ev_add_gpe_reference(gpe_event_info, FALSE);
if (ACPI_GPE_IS_POLLING_NEEDED(gpe_event_info)) {
/* Poll edge triggered GPEs to handle existing events */
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index b2d5f66cc1b0..4188731e7c40 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -108,7 +108,7 @@ acpi_status acpi_enable_gpe(acpi_handle gpe_device, u32 gpe_number)
if (gpe_event_info) {
if (ACPI_GPE_DISPATCH_TYPE(gpe_event_info->flags) !=
ACPI_GPE_DISPATCH_NONE) {
- status = acpi_ev_add_gpe_reference(gpe_event_info);
+ status = acpi_ev_add_gpe_reference(gpe_event_info, TRUE);
if (ACPI_SUCCESS(status) &&
ACPI_GPE_IS_POLLING_NEEDED(gpe_event_info)) {
--
2.20.1
From: Valdis Klētnieks <[email protected]>
[ Upstream commit aee450cbe482a8c2f6fa5b05b178ef8b8ff107ca ]
Compiling kernel/bpf/core.c with W=1 causes a flood of warnings:
kernel/bpf/core.c:1198:65: warning: initialized field overwritten [-Woverride-init]
1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
| ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
1087 | INSN_3(ALU, ADD, X), \
| ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
1202 | BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
| ^~~~~~~~~~~~
kernel/bpf/core.c:1198:65: note: (near initialization for 'public_insntable[12]')
1198 | #define BPF_INSN_3_TBL(x, y, z) [BPF_##x | BPF_##y | BPF_##z] = true
| ^~~~
kernel/bpf/core.c:1087:2: note: in expansion of macro 'BPF_INSN_3_TBL'
1087 | INSN_3(ALU, ADD, X), \
| ^~~~~~
kernel/bpf/core.c:1202:3: note: in expansion of macro 'BPF_INSN_MAP'
1202 | BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL),
| ^~~~~~~~~~~~
98 copies of the above.
The attached patch silences the warnings, because we *know* we're overwriting
the default initializer. That leaves bpf/core.c with only 6 other warnings,
which become more visible in comparison.
Signed-off-by: Valdis Kletnieks <[email protected]>
Acked-by: Andrii Nakryiko <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
kernel/bpf/Makefile | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 0488b8258321..ffc39a7e028d 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
obj-y := core.o
+CFLAGS_core.o += $(call cc-disable-warning, override-init)
obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
--
2.20.1
From: Anton Eidelman <[email protected]>
[ Upstream commit 2181e455612a8db2761eabbf126640552a451e96 ]
When a shared namespace is removed, we call blk_cleanup_queue()
when the device can still be accessed as the current path and this can
result in submission to a dying queue. Hence, direct_make_request()
called by our mpath device may fail (propagating the failure to userspace).
Instead, we want to failover this I/O to a different path if one exists.
Thus, before we cleanup the request queue, we make sure that the device is
cleared from the current path nor it can be selected again as such.
Fix this by:
- clear the ns from the head->list and synchronize rcu to make sure there is
no concurrent path search that restores it as the current path
- clear the mpath current path in order to trigger a subsequent path search
and sync srcu to wait for any ongoing request submissions
- safely continue to namespace removal and blk_cleanup_queue
Signed-off-by: Anton Eidelman <[email protected]>
Signed-off-by: Sagi Grimberg <[email protected]>
Signed-off-by: Christoph Hellwig <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/nvme/host/core.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d8869d978c34..e26d1191c5ad 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3168,6 +3168,14 @@ static void nvme_ns_remove(struct nvme_ns *ns)
return;
nvme_fault_inject_fini(ns);
+
+ mutex_lock(&ns->ctrl->subsys->lock);
+ list_del_rcu(&ns->siblings);
+ mutex_unlock(&ns->ctrl->subsys->lock);
+ synchronize_rcu(); /* guarantee not available in head->list */
+ nvme_mpath_clear_current_path(ns);
+ synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
+
if (ns->disk && ns->disk->flags & GENHD_FL_UP) {
sysfs_remove_group(&disk_to_dev(ns->disk)->kobj,
&nvme_ns_id_attr_group);
@@ -3179,16 +3187,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
blk_integrity_unregister(ns->disk);
}
- mutex_lock(&ns->ctrl->subsys->lock);
- list_del_rcu(&ns->siblings);
- nvme_mpath_clear_current_path(ns);
- mutex_unlock(&ns->ctrl->subsys->lock);
-
down_write(&ns->ctrl->namespaces_rwsem);
list_del_init(&ns->list);
up_write(&ns->ctrl->namespaces_rwsem);
- synchronize_srcu(&ns->head->srcu);
nvme_mpath_check_last_path(ns);
nvme_put_ns(ns);
}
--
2.20.1
From: Heiner Litz <[email protected]>
[ Upstream commit 510fd8ea98fcb586c01aef93d87c060a159ac30a ]
bio_add_pc_page() may merge pages when a bio is padded due to a flush.
Fix iteration over the bio to free the correct pages in case of a merge.
Signed-off-by: Heiner Litz <[email protected]>
Reviewed-by: Javier González <[email protected]>
Signed-off-by: Matias Bjørling <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/lightnvm/pblk-core.c | 18 ++++++++++--------
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 95be6e36c7dd..80710c62ac29 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -288,14 +288,16 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
int nr_pages)
{
- struct bio_vec bv;
- int i;
-
- WARN_ON(off + nr_pages != bio->bi_vcnt);
-
- for (i = off; i < nr_pages + off; i++) {
- bv = bio->bi_io_vec[i];
- mempool_free(bv.bv_page, &pblk->page_bio_pool);
+ struct bio_vec *bv;
+ struct page *page;
+ int i, e, nbv = 0;
+
+ for (i = 0; i < bio->bi_vcnt; i++) {
+ bv = &bio->bi_io_vec[i];
+ page = bv->bv_page;
+ for (e = 0; e < bv->bv_len; e += PBLK_EXPOSED_PAGE_SIZE, nbv++)
+ if (nbv >= off)
+ mempool_free(page++, &pblk->page_bio_pool);
}
}
--
2.20.1
From: Rajneesh Bhardwaj <[email protected]>
[ Upstream commit e32d045cd4ba06b59878323e434bad010e78e658 ]
Add the CPUID model number of Ice Lake Neural Network Processor for Deep
Learning Inference (ICL-NNPI) to the Intel family list. Ice Lake NNPI uses
model number 0x9D and this will be documented in a future version of Intel
Software Development Manual.
Signed-off-by: Rajneesh Bhardwaj <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Andy Shevchenko <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Kan Liang <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Cc: Qiuxu Zhuo <[email protected]>
Cc: Srinivas Pandruvada <[email protected]>
Cc: Len Brown <[email protected]>
Cc: Linux PM <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/include/asm/intel-family.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 2e38fb82b91d..aebedbaf5260 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -56,6 +56,7 @@
#define INTEL_FAM6_ICELAKE_XEON_D 0x6C
#define INTEL_FAM6_ICELAKE_DESKTOP 0x7D
#define INTEL_FAM6_ICELAKE_MOBILE 0x7E
+#define INTEL_FAM6_ICELAKE_NNPI 0x9D
/* "Small Core" Processors (Atom) */
--
2.20.1
From: Julien Thierry <[email protected]>
[ Upstream commit 9034f6251572a4744597c51dea5ab73a55f2b938 ]
For el0_dbg and el0_error, DAIF bits get explicitly cleared before
calling ct_user_exit.
When context tracking is disabled, DAIF gets set (almost) immediately
after. When context tracking is enabled, among the first things done
is disabling IRQs.
What is actually needed is:
- PSR.D = 0 so the system can be debugged (should be already the case)
- PSR.A = 0 so async error can be handled during context tracking
Do not clear PSR.I in those two locations.
Reviewed-by: Marc Zyngier <[email protected]>
Acked-by: Mark Rutland <[email protected]>
Reviewed-by: James Morse <[email protected]>
Cc: Will Deacon <[email protected]>
Signed-off-by: Julien Thierry <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/arm64/kernel/entry.S | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 8556876c9109..5f800384cb9a 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -824,7 +824,7 @@ el0_dbg:
mov x1, x25
mov x2, sp
bl do_debug_exception
- enable_daif
+ enable_da_f
ct_user_exit
b ret_to_user
el0_inv:
@@ -876,7 +876,7 @@ el0_error_naked:
enable_dbg
mov x0, sp
bl do_serror
- enable_daif
+ enable_da_f
ct_user_exit
b ret_to_user
ENDPROC(el0_error)
--
2.20.1
From: Anders Roxell <[email protected]>
[ Upstream commit b2ce5617dad254230551feda3599f2cc68e53ad8 ]
When building with CONFIG_VIDEO_ADV7511 and CONFIG_DRM_I2C_ADV7511
enabled as loadable modules, we see the following warning:
drivers/gpu/drm/bridge/adv7511/adv7511.ko
drivers/media/i2c/adv7511.ko
Rework so that the file is named adv7511-v4l2.c.
Signed-off-by: Anders Roxell <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/i2c/Makefile | 2 +-
drivers/media/i2c/{adv7511.c => adv7511-v4l2.c} | 5 +++++
2 files changed, 6 insertions(+), 1 deletion(-)
rename drivers/media/i2c/{adv7511.c => adv7511-v4l2.c} (99%)
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index a94eb03d10d4..520b3c3bf48c 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -36,7 +36,7 @@ obj-$(CONFIG_VIDEO_ADV748X) += adv748x/
obj-$(CONFIG_VIDEO_ADV7604) += adv7604.o
obj-$(CONFIG_VIDEO_ADV7842) += adv7842.o
obj-$(CONFIG_VIDEO_AD9389B) += ad9389b.o
-obj-$(CONFIG_VIDEO_ADV7511) += adv7511.o
+obj-$(CONFIG_VIDEO_ADV7511) += adv7511-v4l2.o
obj-$(CONFIG_VIDEO_VPX3220) += vpx3220.o
obj-$(CONFIG_VIDEO_VS6624) += vs6624.o
obj-$(CONFIG_VIDEO_BT819) += bt819.o
diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511-v4l2.c
similarity index 99%
rename from drivers/media/i2c/adv7511.c
rename to drivers/media/i2c/adv7511-v4l2.c
index 88349b5053cc..6869bb593a68 100644
--- a/drivers/media/i2c/adv7511.c
+++ b/drivers/media/i2c/adv7511-v4l2.c
@@ -5,6 +5,11 @@
* Copyright 2013 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
*/
+/*
+ * This file is named adv7511-v4l2.c so it doesn't conflict with the Analog
+ * Device ADV7511 (config fragment CONFIG_DRM_I2C_ADV7511).
+ */
+
#include <linux/kernel.h>
#include <linux/module.h>
--
2.20.1
From: Miroslav Lichvar <[email protected]>
[ Upstream commit d897a4ab11dc8a9fda50d2eccc081a96a6385998 ]
Don't allow the TAI-UTC offset of the system clock to be set by adjtimex()
to a value larger than 100000 seconds.
This prevents an overflow in the conversion to int, prevents the CLOCK_TAI
clock from getting too far ahead of the CLOCK_REALTIME clock, and it is
still large enough to allow leap seconds to be inserted at the maximum rate
currently supported by the kernel (once per day) for the next ~270 years,
however unlikely it is that someone can survive a catastrophic event which
slowed down the rotation of the Earth so much.
Reported-by: Weikang shi <[email protected]>
Signed-off-by: Miroslav Lichvar <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: John Stultz <[email protected]>
Cc: Prarit Bhargava <[email protected]>
Cc: Richard Cochran <[email protected]>
Cc: Stephen Boyd <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
kernel/time/ntp.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 6b23cd584295..e1110a7bd3e6 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -43,6 +43,7 @@ static u64 tick_length_base;
#define MAX_TICKADJ 500LL /* usecs */
#define MAX_TICKADJ_SCALED \
(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
+#define MAX_TAI_OFFSET 100000
/*
* phase-lock loop variables
@@ -698,7 +699,8 @@ static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai
time_constant = max(time_constant, 0l);
}
- if (txc->modes & ADJ_TAI && txc->constant >= 0)
+ if (txc->modes & ADJ_TAI &&
+ txc->constant >= 0 && txc->constant <= MAX_TAI_OFFSET)
*time_tai = txc->constant;
if (txc->modes & ADJ_OFFSET)
--
2.20.1
From: Nicolas Dichtel <[email protected]>
[ Upstream commit b8d6d0079757cbd1b69724cfd1c08e2171c68cee ]
After commit b38ff4075a80, the following command does not work anymore:
$ ip xfrm state add src 10.125.0.2 dst 10.125.0.1 proto esp spi 34 reqid 1 \
mode tunnel enc 'cbc(aes)' 0xb0abdba8b782ad9d364ec81e3a7d82a1 auth-trunc \
'hmac(sha1)' 0xe26609ebd00acb6a4d51fca13e49ea78a72c73e6 96 flag align4
In fact, the selector is not mandatory, allow the user to provide an empty
selector.
Fixes: b38ff4075a80 ("xfrm: Fix xfrm sel prefix length validation")
CC: Anirudh Gupta <[email protected]>
Signed-off-by: Nicolas Dichtel <[email protected]>
Acked-by: Herbert Xu <[email protected]>
Signed-off-by: Steffen Klassert <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/xfrm/xfrm_user.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d80d54e663c0..1484bc99a537 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -166,6 +166,9 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
}
switch (p->sel.family) {
+ case AF_UNSPEC:
+ break;
+
case AF_INET:
if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
goto out;
--
2.20.1
From: Marco Felsch <[email protected]>
[ Upstream commit f3775f89852d167990b0d718587774cf00d22ac2 ]
coda_encoder_cmd() is racy, as the last scheduled picture run worker can
still be in-flight while the ENC_CMD_STOP command is issued. Depending
on the exact timing the sequence numbers might already be changed, but
the last buffer might not have been put on the destination queue yet.
In this case the current implementation would prematurely wake the
destination queue with last_buffer_dequeued=true, causing userspace to
call streamoff before the last buffer is handled.
Close this race window by synchronizing with the pic_run_worker before
doing the sequence check.
Signed-off-by: Marco Felsch <[email protected]>
[[email protected]: switch to flush_work, reword commit message]
Signed-off-by: Lucas Stach <[email protected]>
Signed-off-by: Philipp Zabel <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/coda/coda-common.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 19d92edcc981..4b0220f40b42 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -997,6 +997,8 @@ static int coda_encoder_cmd(struct file *file, void *fh,
/* Set the stream-end flag on this context */
ctx->bit_stream_param |= CODA_BIT_STREAM_END_FLAG;
+ flush_work(&ctx->pic_run_work);
+
/* If there is no buffer in flight, wake up */
if (!ctx->streamon_out || ctx->qsequence == ctx->osequence) {
dst_vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx,
--
2.20.1
From: Kan Liang <[email protected]>
[ Upstream commit 543ac280b3576c0009e8c0fcd4d6bfc9978d7bd0 ]
Counting with invalid event coding for free-running counter may cause
OOPs, e.g. uncore_iio_free_running_0/event=1/.
Current code only validate the event with free-running event format,
event=0xff,umask=0xXY. Non-free-running event format never be checked
for the PMU with free-running counters.
Add generic hw_config() to check and reject the invalid event coding
for free-running PMU.
Signed-off-by: Kan Liang <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: [email protected]
Cc: [email protected]
Fixes: 0f519f0352e3 ("perf/x86/intel/uncore: Support IIO free-running counters on SKX")
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/events/intel/uncore.h | 10 ++++++++++
arch/x86/events/intel/uncore_snbep.c | 1 +
2 files changed, 11 insertions(+)
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index cc6dd4f78158..42fa3974c421 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -402,6 +402,16 @@ static inline bool is_freerunning_event(struct perf_event *event)
(((cfg >> 8) & 0xff) >= UNCORE_FREERUNNING_UMASK_START);
}
+/* Check and reject invalid config */
+static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
+ struct perf_event *event)
+{
+ if (is_freerunning_event(event))
+ return 0;
+
+ return -EINVAL;
+}
+
static inline void uncore_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->type->ops->disable_box)
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index b10e04387f38..8e4e8e423839 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -3585,6 +3585,7 @@ static struct uncore_event_desc skx_uncore_iio_freerunning_events[] = {
static struct intel_uncore_ops skx_uncore_iio_freerunning_ops = {
.read_counter = uncore_msr_read_counter,
+ .hw_config = uncore_freerunning_hw_config,
};
static struct attribute *skx_uncore_iio_freerunning_formats_attr[] = {
--
2.20.1
From: Philipp Zabel <[email protected]>
[ Upstream commit b3b7d96817cdb8b6fc353867705275dce8f41ccc ]
If no more frames are decoded in bitstream end mode, and a previously
decoded frame has been returned, the firmware still increments the frame
number. To avoid a sequence number mismatch after decoder restart,
increment the sequence_offset correction parameter.
Signed-off-by: Philipp Zabel <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/coda/coda-bit.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 25ef0c928a81..925581d65ad8 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -2143,6 +2143,9 @@ static void coda_finish_decode(struct coda_ctx *ctx)
else if (ctx->display_idx < 0)
ctx->hold = true;
} else if (decoded_idx == -2) {
+ if (ctx->display_idx >= 0 &&
+ ctx->display_idx < ctx->num_internal_frames)
+ ctx->sequence_offset++;
/* no frame was decoded, we still return remaining buffers */
} else if (decoded_idx < 0 || decoded_idx >= ctx->num_internal_frames) {
v4l2_err(&dev->v4l2_dev,
--
2.20.1
From: Icenowy Zheng <[email protected]>
[ Upstream commit 0fec7e72ae1391bb2d7527efb54fe6ae88acabce ]
The PHY selection bit also exists on SoCs without an internal PHY; if it's
set to 1 (internal PHY, default value) then the MAC will not make use of
any PHY on such SoCs.
This problem appears when adapting for H6, which has no real internal PHY
(the "internal PHY" on H6 is not on-die, but on a co-packaged AC200 chip,
connected via RMII interface at GPIO bank A).
Force the PHY selection bit to 0 when the SOC doesn't have an internal PHY,
to address the problem of a wrong default value.
Signed-off-by: Icenowy Zheng <[email protected]>
Signed-off-by: Ondrej Jirman <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 49a896a16391..79c91526f3ec 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -893,6 +893,11 @@ static int sun8i_dwmac_set_syscon(struct stmmac_priv *priv)
* address. No need to mask it again.
*/
reg |= 1 << H3_EPHY_ADDR_SHIFT;
+ } else {
+ /* For SoCs without internal PHY the PHY selection bit should be
+ * set to 0 (external PHY).
+ */
+ reg &= ~H3_EPHY_SELECT;
}
if (!of_property_read_u32(node, "allwinner,tx-delay-ps", &val)) {
--
2.20.1
From: Kyle Meyer <[email protected]>
[ Upstream commit 9f94c7f947e919c343b30f080285af53d0fa9902 ]
Attempting to profile 1024 or more CPUs with perf causes two errors:
perf record -a
[ perf record: Woken up X times to write data ]
way too many cpu caches..
[ perf record: Captured and wrote X MB perf.data (X samples) ]
perf report -C 1024
Error: failed to set cpu bitmap
Requested CPU 1024 too large. Consider raising MAX_NR_CPUS
Increasing MAX_NR_CPUS from 1024 to 2048 and redefining MAX_CACHES as
MAX_NR_CPUS * 4 returns normal functionality to perf:
perf record -a
[ perf record: Woken up X times to write data ]
[ perf record: Captured and wrote X MB perf.data (X samples) ]
perf report -C 1024
...
Signed-off-by: Kyle Meyer <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/perf.h | 2 +-
tools/perf/util/header.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 21bf7f5a3cf5..19d435a9623b 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -26,7 +26,7 @@ static inline unsigned long long rdclock(void)
}
#ifndef MAX_NR_CPUS
-#define MAX_NR_CPUS 1024
+#define MAX_NR_CPUS 2048
#endif
extern const char *input_name;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b9a82598e2ac..7f2e3b1c746c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1173,7 +1173,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 size, u32 *cntp)
return 0;
}
-#define MAX_CACHES 2000
+#define MAX_CACHES (MAX_NR_CPUS * 4)
static int write_cache(struct feat_fd *ff,
struct perf_evlist *evlist __maybe_unused)
--
2.20.1
From: Julian Anastasov <[email protected]>
[ Upstream commit cf47a0b882a4e5f6b34c7949d7b293e9287f1972 ]
syzkaller reports for memory leak when registering hooks [1]
As we moved the nf_unregister_net_hooks() call into
__ip_vs_dev_cleanup(), defer the nf_register_net_hooks()
call, so that hooks are allocated and freed from same
pernet_operations (ipvs_core_dev_ops).
[1]
BUG: memory leak
unreferenced object 0xffff88810acd8a80 (size 96):
comm "syz-executor073", pid 7254, jiffies 4294950560 (age 22.250s)
hex dump (first 32 bytes):
02 00 00 00 00 00 00 00 50 8b bb 82 ff ff ff ff ........P.......
00 00 00 00 00 00 00 00 00 77 bb 82 ff ff ff ff .........w......
backtrace:
[<0000000013db61f1>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline]
[<0000000013db61f1>] slab_post_alloc_hook mm/slab.h:439 [inline]
[<0000000013db61f1>] slab_alloc_node mm/slab.c:3269 [inline]
[<0000000013db61f1>] kmem_cache_alloc_node_trace+0x15b/0x2a0 mm/slab.c:3597
[<000000001a27307d>] __do_kmalloc_node mm/slab.c:3619 [inline]
[<000000001a27307d>] __kmalloc_node+0x38/0x50 mm/slab.c:3627
[<0000000025054add>] kmalloc_node include/linux/slab.h:590 [inline]
[<0000000025054add>] kvmalloc_node+0x4a/0xd0 mm/util.c:431
[<0000000050d1bc00>] kvmalloc include/linux/mm.h:637 [inline]
[<0000000050d1bc00>] kvzalloc include/linux/mm.h:645 [inline]
[<0000000050d1bc00>] allocate_hook_entries_size+0x3b/0x60 net/netfilter/core.c:61
[<00000000e8abe142>] nf_hook_entries_grow+0xae/0x270 net/netfilter/core.c:128
[<000000004b94797c>] __nf_register_net_hook+0x9a/0x170 net/netfilter/core.c:337
[<00000000d1545cbc>] nf_register_net_hook+0x34/0xc0 net/netfilter/core.c:464
[<00000000876c9b55>] nf_register_net_hooks+0x53/0xc0 net/netfilter/core.c:480
[<000000002ea868e0>] __ip_vs_init+0xe8/0x170 net/netfilter/ipvs/ip_vs_core.c:2280
[<000000002eb2d451>] ops_init+0x4c/0x140 net/core/net_namespace.c:130
[<000000000284ec48>] setup_net+0xde/0x230 net/core/net_namespace.c:316
[<00000000a70600fa>] copy_net_ns+0xf0/0x1e0 net/core/net_namespace.c:439
[<00000000ff26c15e>] create_new_namespaces+0x141/0x2a0 kernel/nsproxy.c:107
[<00000000b103dc79>] copy_namespaces+0xa1/0xe0 kernel/nsproxy.c:165
[<000000007cc008a2>] copy_process.part.0+0x11fd/0x2150 kernel/fork.c:2035
[<00000000c344af7c>] copy_process kernel/fork.c:1800 [inline]
[<00000000c344af7c>] _do_fork+0x121/0x4f0 kernel/fork.c:2369
Reported-by: [email protected]
Fixes: 719c7d563c17 ("ipvs: Fix use-after-free in ip_vs_in")
Signed-off-by: Julian Anastasov <[email protected]>
Acked-by: Simon Horman <[email protected]>
Signed-off-by: Pablo Neira Ayuso <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/netfilter/ipvs/ip_vs_core.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 62c0e80dcd71..a71f777d1353 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2218,7 +2218,6 @@ static const struct nf_hook_ops ip_vs_ops[] = {
static int __net_init __ip_vs_init(struct net *net)
{
struct netns_ipvs *ipvs;
- int ret;
ipvs = net_generic(net, ip_vs_net_id);
if (ipvs == NULL)
@@ -2250,17 +2249,11 @@ static int __net_init __ip_vs_init(struct net *net)
if (ip_vs_sync_net_init(ipvs) < 0)
goto sync_fail;
- ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
- if (ret < 0)
- goto hook_fail;
-
return 0;
/*
* Error handling
*/
-hook_fail:
- ip_vs_sync_net_cleanup(ipvs);
sync_fail:
ip_vs_conn_net_cleanup(ipvs);
conn_fail:
@@ -2290,6 +2283,19 @@ static void __net_exit __ip_vs_cleanup(struct net *net)
net->ipvs = NULL;
}
+static int __net_init __ip_vs_dev_init(struct net *net)
+{
+ int ret;
+
+ ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+ if (ret < 0)
+ goto hook_fail;
+ return 0;
+
+hook_fail:
+ return ret;
+}
+
static void __net_exit __ip_vs_dev_cleanup(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -2309,6 +2315,7 @@ static struct pernet_operations ipvs_core_ops = {
};
static struct pernet_operations ipvs_core_dev_ops = {
+ .init = __ip_vs_dev_init,
.exit = __ip_vs_dev_cleanup,
};
--
2.20.1
From: Minwoo Im <[email protected]>
[ Upstream commit cee6c269b016ba89c62e34d6bccb103ee2c7de4f ]
If the state change to NVME_CTRL_CONNECTING fails, the dmesg is going to
be like:
[ 293.689160] nvme nvme0: failed to mark controller CONNECTING
[ 293.689160] nvme nvme0: Removing after probe failure status: 0
Even it prints the first line to indicate the situation, the second line
is not proper because the status is 0 which means normally success of
the previous operation.
This patch makes it indicate the proper error value when it fails.
[ 25.932367] nvme nvme0: failed to mark controller CONNECTING
[ 25.932369] nvme nvme0: Removing after probe failure status: -16
This situation is able to be easily reproduced by:
root@target:~# rmmod nvme && modprobe nvme && rmmod nvme
Signed-off-by: Minwoo Im <[email protected]>
Reviewed-by: Chaitanya Kulkarni <[email protected]>
Signed-off-by: Christoph Hellwig <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/nvme/host/pci.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index c8eeecc58115..03e72e2f57f5 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2294,6 +2294,7 @@ static void nvme_reset_work(struct work_struct *work)
if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) {
dev_warn(dev->ctrl.device,
"failed to mark controller CONNECTING\n");
+ result = -EBUSY;
goto out;
}
--
2.20.1
From: Arnd Bergmann <[email protected]>
[ Upstream commit 597179b0ba550bd83fab1a9d57c42a9343c58514 ]
kernelci.org reports failed builds on arc because of what looks
like an old missed 'select' statement:
net/xfrm/xfrm_algo.o: In function `xfrm_probe_algs':
xfrm_algo.c:(.text+0x1e8): undefined reference to `crypto_has_ahash'
I don't see this in randconfig builds on other architectures, but
it's fairly clear we want to select the hash code for it, like we
do for all its other users. As Herbert points out, CRYPTO_BLKCIPHER
is also required even though it has not popped up in build tests.
Fixes: 17bc19702221 ("ipsec: Use skcipher and ahash when probing algorithms")
Signed-off-by: Arnd Bergmann <[email protected]>
Acked-by: Herbert Xu <[email protected]>
Signed-off-by: Steffen Klassert <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/xfrm/Kconfig | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 4a9ee2d83158..372c91faa283 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -14,6 +14,8 @@ config XFRM_ALGO
tristate
select XFRM
select CRYPTO
+ select CRYPTO_HASH
+ select CRYPTO_BLKCIPHER
config XFRM_USER
tristate "Transformation user configuration interface"
--
2.20.1
From: Amadeusz Sławiński <[email protected]>
[ Upstream commit 0f6ff78540bd1b4df1e0f17806b0ce2e1dff0d78 ]
When we unload Skylake driver we may end up calling
hdac_component_master_unbind(), it uses acomp->audio_ops, which we set
in hdmi_codec_probe(), so we need to set it to NULL in hdmi_codec_remove(),
otherwise we will dereference no longer existing pointer.
Signed-off-by: Amadeusz Sławiński <[email protected]>
Reviewed-by: Pierre-Louis Bossart <[email protected]>
Signed-off-by: Mark Brown <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
sound/soc/codecs/hdac_hdmi.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 63487240b61e..098196610542 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1854,6 +1854,12 @@ static void hdmi_codec_remove(struct snd_soc_component *component)
{
struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
struct hdac_device *hdev = hdmi->hdev;
+ int ret;
+
+ ret = snd_hdac_acomp_register_notifier(hdev->bus, NULL);
+ if (ret < 0)
+ dev_err(&hdev->dev, "notifier unregister failed: err: %d\n",
+ ret);
pm_runtime_disable(&hdev->dev);
}
--
2.20.1
From: Nathan Huckleberry <[email protected]>
[ Upstream commit a9314773a91a1d3b36270085246a6715a326ff00 ]
With CONFIG_PROC_FS=n the following warning is emitted:
kernel/time/timer_list.c:361:36: warning: unused variable
'timer_list_sops' [-Wunused-const-variable]
static const struct seq_operations timer_list_sops = {
Add #ifdef guard around procfs specific code.
Signed-off-by: Nathan Huckleberry <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Nick Desaulniers <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: https://github.com/ClangBuiltLinux/linux/issues/534
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
kernel/time/timer_list.c | 36 +++++++++++++++++++-----------------
1 file changed, 19 insertions(+), 17 deletions(-)
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index d647dabdac97..07afcfe2a61b 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -287,23 +287,6 @@ static inline void timer_list_header(struct seq_file *m, u64 now)
SEQ_printf(m, "\n");
}
-static int timer_list_show(struct seq_file *m, void *v)
-{
- struct timer_list_iter *iter = v;
-
- if (iter->cpu == -1 && !iter->second_pass)
- timer_list_header(m, iter->now);
- else if (!iter->second_pass)
- print_cpu(m, iter->cpu, iter->now);
-#ifdef CONFIG_GENERIC_CLOCKEVENTS
- else if (iter->cpu == -1 && iter->second_pass)
- timer_list_show_tickdevices_header(m);
- else
- print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
-#endif
- return 0;
-}
-
void sysrq_timer_list_show(void)
{
u64 now = ktime_to_ns(ktime_get());
@@ -322,6 +305,24 @@ void sysrq_timer_list_show(void)
return;
}
+#ifdef CONFIG_PROC_FS
+static int timer_list_show(struct seq_file *m, void *v)
+{
+ struct timer_list_iter *iter = v;
+
+ if (iter->cpu == -1 && !iter->second_pass)
+ timer_list_header(m, iter->now);
+ else if (!iter->second_pass)
+ print_cpu(m, iter->cpu, iter->now);
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+ else if (iter->cpu == -1 && iter->second_pass)
+ timer_list_show_tickdevices_header(m);
+ else
+ print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
+#endif
+ return 0;
+}
+
static void *move_iter(struct timer_list_iter *iter, loff_t offset)
{
for (; offset; offset--) {
@@ -381,3 +382,4 @@ static int __init init_timer_list_procfs(void)
return 0;
}
__initcall(init_timer_list_procfs);
+#endif
--
2.20.1
From: Tejun Heo <[email protected]>
[ Upstream commit ca156e006add67e4beea7896be395160735e09b0 ]
ZAC support added sense data requesting on error for both ZAC and ATA
devices. This seems to cause erratic error handling behaviors on some
SSDs where the device reports sense data availability and then
delivers the wrong content making EH take the wrong actions. The
failure mode was sporadic on a LITE-ON ssd and couldn't be reliably
reproduced.
There is no value in requesting sense data from non-ZAC ATA devices
while there's a significant risk of introducing EH misbehaviors which
are difficult to reproduce and fix. Let's do the sense data dancing
only for ZAC devices.
Reviewed-by: Hannes Reinecke <[email protected]>
Tested-by: Masato Suzuki <[email protected]>
Reviewed-by: Damien Le Moal <[email protected]>
Signed-off-by: Tejun Heo <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/ata/libata-eh.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 01306c018398..ccc80ff57eb2 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1490,7 +1490,7 @@ static int ata_eh_read_log_10h(struct ata_device *dev,
tf->hob_lbah = buf[10];
tf->nsect = buf[12];
tf->hob_nsect = buf[13];
- if (ata_id_has_ncq_autosense(dev->id))
+ if (dev->class == ATA_DEV_ZAC && ata_id_has_ncq_autosense(dev->id))
tf->auxiliary = buf[14] << 16 | buf[15] << 8 | buf[16];
return 0;
@@ -1737,7 +1737,8 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
memcpy(&qc->result_tf, &tf, sizeof(tf));
qc->result_tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
qc->err_mask |= AC_ERR_DEV | AC_ERR_NCQ;
- if ((qc->result_tf.command & ATA_SENSE) || qc->result_tf.auxiliary) {
+ if (dev->class == ATA_DEV_ZAC &&
+ ((qc->result_tf.command & ATA_SENSE) || qc->result_tf.auxiliary)) {
char sense_key, asc, ascq;
sense_key = (qc->result_tf.auxiliary >> 16) & 0xff;
@@ -1791,10 +1792,11 @@ static unsigned int ata_eh_analyze_tf(struct ata_queued_cmd *qc,
}
switch (qc->dev->class) {
- case ATA_DEV_ATA:
case ATA_DEV_ZAC:
if (stat & ATA_SENSE)
ata_eh_request_sense(qc, qc->scsicmd);
+ /* fall through */
+ case ATA_DEV_ATA:
if (err & ATA_ICRC)
qc->err_mask |= AC_ERR_ATA_BUS;
if (err & (ATA_UNC | ATA_AMNF))
--
2.20.1
From: Philipp Zabel <[email protected]>
[ Upstream commit 56d159a4ec6d8da7313aac6fcbb95d8fffe689ba ]
Sequence number handling assumed that the BIT processor frame number
starts counting at 1, but this is not true for the MPEG-2 decoder,
which starts at 0. Fix the sequence counter offset detection to handle
this.
Signed-off-by: Philipp Zabel <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/coda/coda-bit.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index a3cfefdbee12..25ef0c928a81 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1728,6 +1728,7 @@ static int __coda_start_decoding(struct coda_ctx *ctx)
v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
return ret;
}
+ ctx->sequence_offset = ~0U;
ctx->initialized = 1;
/* Update kfifo out pointer from coda bitstream read pointer */
@@ -2147,7 +2148,9 @@ static void coda_finish_decode(struct coda_ctx *ctx)
v4l2_err(&dev->v4l2_dev,
"decoded frame index out of range: %d\n", decoded_idx);
} else {
- val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM) - 1;
+ val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM);
+ if (ctx->sequence_offset == -1)
+ ctx->sequence_offset = val;
val -= ctx->sequence_offset;
spin_lock_irqsave(&ctx->buffer_meta_lock, flags);
if (!list_empty(&ctx->buffer_meta_list)) {
--
2.20.1
From: Masahiro Yamada <[email protected]>
[ Upstream commit bc53d3d777f81385c1bb08b07bd1c06450ecc2c1 ]
Without 'set -e', shell scripts continue running even after any
error occurs. The missed 'set -e' is a typical bug in shell scripting.
For example, when a disk space shortage occurs while this script is
running, it actually ends up with generating a truncated capflags.c.
Yet, mkcapflags.sh continues running and exits with 0. So, the build
system assumes it has succeeded.
It will not be re-generated in the next invocation of Make since its
timestamp is newer than that of any of the source files.
Add 'set -e' so that any error in this script is caught and propagated
to the build system.
Since 9c2af1c7377a ("kbuild: add .DELETE_ON_ERROR special target"),
make automatically deletes the target on any failure. So, the broken
capflags.c will be deleted automatically.
Signed-off-by: Masahiro Yamada <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Borislav Petkov <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/kernel/cpu/mkcapflags.sh | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index d0dfb892c72f..aed45b8895d5 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -4,6 +4,8 @@
# Generate the x86_cap/bug_flags[] arrays from include/asm/cpufeatures.h
#
+set -e
+
IN=$1
OUT=$2
--
2.20.1
From: Ferdinand Blomqvist <[email protected]>
[ Upstream commit 2034a42d1747fc1e1eeef2c6f1789c4d0762cb9c ]
The decoding of shortenend codes is broken. It only works as expected if
there are no erasures.
When decoding with erasures, Lambda (the error and erasure locator
polynomial) is initialized from the given erasure positions. The pad
parameter is not accounted for by the initialisation code, and hence
Lambda is initialized from incorrect erasure positions.
The fix is to adjust the erasure positions by the supplied pad.
Signed-off-by: Ferdinand Blomqvist <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
lib/reed_solomon/decode_rs.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c
index 1db74eb098d0..3313bf944ff1 100644
--- a/lib/reed_solomon/decode_rs.c
+++ b/lib/reed_solomon/decode_rs.c
@@ -99,9 +99,9 @@
if (no_eras > 0) {
/* Init lambda to be the erasure locator polynomial */
lambda[1] = alpha_to[rs_modnn(rs,
- prim * (nn - 1 - eras_pos[0]))];
+ prim * (nn - 1 - (eras_pos[0] + pad)))];
for (i = 1; i < no_eras; i++) {
- u = rs_modnn(rs, prim * (nn - 1 - eras_pos[i]));
+ u = rs_modnn(rs, prim * (nn - 1 - (eras_pos[i] + pad)));
for (j = i + 1; j > 0; j--) {
tmp = index_of[lambda[j - 1]];
if (tmp != nn) {
--
2.20.1
From: Mika Westerberg <[email protected]>
[ Upstream commit 83a16e3f6d70da99896c7a2639c0b60fff13afb8 ]
The ACPI power state returned by acpi_device_get_power() may depend on
the configuration of ACPI power resources in the system which may change
any time after acpi_device_get_power() has returned, unless the
reference counters of the ACPI power resources in question are set to
prevent that from happening. Thus it is invalid to use acpi_device_get_power()
in acpi_pci_get_power_state() the way it is done now and the value of
the ->power.state field in the corresponding struct acpi_device objects
(which reflects the ACPI power resources reference counting, among other
things) should be used instead.
As an example where this becomes an issue is Intel Ice Lake where the
Thunderbolt controller (NHI), two PCIe root ports (RP0 and RP1) and xHCI
all share the same power resources. The following picture with power
resources marked with [] shows the topology:
Host bridge
|
+- RP0 ---\
+- RP1 ---|--+--> [TBT]
+- NHI --/ |
| |
| v
+- xHCI --> [D3C]
Here TBT and D3C are the shared ACPI power resources. ACPI _PR3() method
of the devices in question returns either TBT or D3C or both.
Say we runtime suspend first the root ports RP0 and RP1, then NHI. Now
since the TBT power resource is still on when the root ports are runtime
suspended their dev->current_state is set to D3hot. When NHI is runtime
suspended TBT is finally turned off but state of the root ports remain
to be D3hot. Now when the xHCI is runtime suspended D3C gets also turned
off. PCI core thus has power states of these devices cached in their
dev->current_state as follows:
RP0 -> D3hot
RP1 -> D3hot
NHI -> D3cold
xHCI -> D3cold
If the user now runs lspci for instance, the result is all 1's like in
the below output (00:07.0 is the first root port, RP0):
00:07.0 PCI bridge: Intel Corporation Device 8a1d (rev ff) (prog-if ff)
!!! Unknown header type 7f
Kernel driver in use: pcieport
In short the hardware state is not in sync with the software state
anymore. The exact same thing happens with the PME polling thread which
ends up bringing the root ports back into D0 after they are runtime
suspended.
For this reason, modify acpi_pci_get_power_state() so that it uses the
ACPI device power state that was cached by the ACPI core. This makes the
PCI device power state match the ACPI device power state regardless of
state of the shared power resources which may still be on at this point.
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Mika Westerberg <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/pci/pci-acpi.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index f7218c1673ce..bfe6ba33e25c 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -577,7 +577,8 @@ static pci_power_t acpi_pci_get_power_state(struct pci_dev *dev)
if (!adev || !acpi_device_power_manageable(adev))
return PCI_UNKNOWN;
- if (acpi_device_get_power(adev, &state) || state == ACPI_STATE_UNKNOWN)
+ state = adev->power.state;
+ if (state == ACPI_STATE_UNKNOWN)
return PCI_UNKNOWN;
return state_conv[state];
--
2.20.1
From: Hans Verkuil <[email protected]>
[ Upstream commit 6bc5a4a1927556ff9adce1aa95ea408c95453225 ]
This driver has three locking issues:
- The wait_event_interruptible() condition calls hdpvr_get_next_buffer(dev)
which uses a mutex, which is not allowed. Rewrite with list_empty_careful()
that doesn't need locking.
- In hdpvr_read() the call to hdpvr_stop_streaming() didn't lock io_mutex,
but it should have since stop_streaming expects that.
- In hdpvr_device_release() io_mutex was locked when calling flush_work(),
but there it shouldn't take that mutex since the work done by flush_work()
also wants to lock that mutex.
There are also two other changes (suggested by Keith):
- msecs_to_jiffies(4000); (a NOP) should have been msleep(4000).
- Change v4l2_dbg to v4l2_info to always log if streaming had to be restarted.
Reported-by: Keith Pyle <[email protected]>
Suggested-by: Keith Pyle <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/usb/hdpvr/hdpvr-video.c | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/drivers/media/usb/hdpvr/hdpvr-video.c b/drivers/media/usb/hdpvr/hdpvr-video.c
index 1b89c77bad66..0615996572e4 100644
--- a/drivers/media/usb/hdpvr/hdpvr-video.c
+++ b/drivers/media/usb/hdpvr/hdpvr-video.c
@@ -439,7 +439,7 @@ static ssize_t hdpvr_read(struct file *file, char __user *buffer, size_t count,
/* wait for the first buffer */
if (!(file->f_flags & O_NONBLOCK)) {
if (wait_event_interruptible(dev->wait_data,
- hdpvr_get_next_buffer(dev)))
+ !list_empty_careful(&dev->rec_buff_list)))
return -ERESTARTSYS;
}
@@ -465,10 +465,17 @@ static ssize_t hdpvr_read(struct file *file, char __user *buffer, size_t count,
goto err;
}
if (!err) {
- v4l2_dbg(MSG_INFO, hdpvr_debug, &dev->v4l2_dev,
- "timeout: restart streaming\n");
+ v4l2_info(&dev->v4l2_dev,
+ "timeout: restart streaming\n");
+ mutex_lock(&dev->io_mutex);
hdpvr_stop_streaming(dev);
- msecs_to_jiffies(4000);
+ mutex_unlock(&dev->io_mutex);
+ /*
+ * The FW needs about 4 seconds after streaming
+ * stopped before it is ready to restart
+ * streaming.
+ */
+ msleep(4000);
err = hdpvr_start_streaming(dev);
if (err) {
ret = err;
@@ -1133,9 +1140,7 @@ static void hdpvr_device_release(struct video_device *vdev)
struct hdpvr_device *dev = video_get_drvdata(vdev);
hdpvr_delete(dev);
- mutex_lock(&dev->io_mutex);
flush_work(&dev->worker);
- mutex_unlock(&dev->io_mutex);
v4l2_device_unregister(&dev->v4l2_dev);
v4l2_ctrl_handler_free(&dev->hdl);
--
2.20.1
From: Eiichi Tsukata <[email protected]>
[ Upstream commit d8655e7630dafa88bc37f101640e39c736399771 ]
Commit 9da21b1509d8 ("EDAC: Poll timeout cannot be zero, p2") assumes
edac_mc_poll_msec to be unsigned long, but the type of the variable still
remained as int. Setting edac_mc_poll_msec can trigger out-of-bounds
write.
Reproducer:
# echo 1001 > /sys/module/edac_core/parameters/edac_mc_poll_msec
KASAN report:
BUG: KASAN: global-out-of-bounds in edac_set_poll_msec+0x140/0x150
Write of size 8 at addr ffffffffb91b2d00 by task bash/1996
CPU: 1 PID: 1996 Comm: bash Not tainted 5.2.0-rc6+ #23
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014
Call Trace:
dump_stack+0xca/0x13e
print_address_description.cold+0x5/0x246
__kasan_report.cold+0x75/0x9a
? edac_set_poll_msec+0x140/0x150
kasan_report+0xe/0x20
edac_set_poll_msec+0x140/0x150
? dimmdev_location_show+0x30/0x30
? vfs_lock_file+0xe0/0xe0
? _raw_spin_lock+0x87/0xe0
param_attr_store+0x1b5/0x310
? param_array_set+0x4f0/0x4f0
module_attr_store+0x58/0x80
? module_attr_show+0x80/0x80
sysfs_kf_write+0x13d/0x1a0
kernfs_fop_write+0x2bc/0x460
? sysfs_kf_bin_read+0x270/0x270
? kernfs_notify+0x1f0/0x1f0
__vfs_write+0x81/0x100
vfs_write+0x1e1/0x560
ksys_write+0x126/0x250
? __ia32_sys_read+0xb0/0xb0
? do_syscall_64+0x1f/0x390
do_syscall_64+0xc1/0x390
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7fa7caa5e970
Code: 73 01 c3 48 8b 0d 28 d5 2b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 99 2d 2c 00 00 75 10 b8 01 00 00 00 04
RSP: 002b:00007fff6acfdfe8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00007fa7caa5e970
RDX: 0000000000000005 RSI: 0000000000e95c08 RDI: 0000000000000001
RBP: 0000000000e95c08 R08: 00007fa7cad1e760 R09: 00007fa7cb36a700
R10: 0000000000000073 R11: 0000000000000246 R12: 0000000000000005
R13: 0000000000000001 R14: 00007fa7cad1d600 R15: 0000000000000005
The buggy address belongs to the variable:
edac_mc_poll_msec+0x0/0x40
Memory state around the buggy address:
ffffffffb91b2c00: 00 00 00 00 fa fa fa fa 00 00 00 00 fa fa fa fa
ffffffffb91b2c80: 00 00 00 00 fa fa fa fa 00 00 00 00 fa fa fa fa
>ffffffffb91b2d00: 04 fa fa fa fa fa fa fa 04 fa fa fa fa fa fa fa
^
ffffffffb91b2d80: 04 fa fa fa fa fa fa fa 00 00 00 00 00 00 00 00
ffffffffb91b2e00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
Fix it by changing the type of edac_mc_poll_msec to unsigned int.
The reason why this patch adopts unsigned int rather than unsigned long
is msecs_to_jiffies() assumes arg to be unsigned int. We can avoid
integer conversion bugs and unsigned int will be large enough for
edac_mc_poll_msec.
Reviewed-by: James Morse <[email protected]>
Fixes: 9da21b1509d8 ("EDAC: Poll timeout cannot be zero, p2")
Signed-off-by: Eiichi Tsukata <[email protected]>
Signed-off-by: Tony Luck <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/edac/edac_mc_sysfs.c | 16 ++++++++--------
drivers/edac/edac_module.h | 2 +-
2 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index e50610b5bd06..d4545a9222a0 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -26,7 +26,7 @@
static int edac_mc_log_ue = 1;
static int edac_mc_log_ce = 1;
static int edac_mc_panic_on_ue;
-static int edac_mc_poll_msec = 1000;
+static unsigned int edac_mc_poll_msec = 1000;
/* Getter functions for above */
int edac_mc_get_log_ue(void)
@@ -45,30 +45,30 @@ int edac_mc_get_panic_on_ue(void)
}
/* this is temporary */
-int edac_mc_get_poll_msec(void)
+unsigned int edac_mc_get_poll_msec(void)
{
return edac_mc_poll_msec;
}
static int edac_set_poll_msec(const char *val, const struct kernel_param *kp)
{
- unsigned long l;
+ unsigned int i;
int ret;
if (!val)
return -EINVAL;
- ret = kstrtoul(val, 0, &l);
+ ret = kstrtouint(val, 0, &i);
if (ret)
return ret;
- if (l < 1000)
+ if (i < 1000)
return -EINVAL;
- *((unsigned long *)kp->arg) = l;
+ *((unsigned int *)kp->arg) = i;
/* notify edac_mc engine to reset the poll period */
- edac_mc_reset_delay_period(l);
+ edac_mc_reset_delay_period(i);
return 0;
}
@@ -82,7 +82,7 @@ MODULE_PARM_DESC(edac_mc_log_ue,
module_param(edac_mc_log_ce, int, 0644);
MODULE_PARM_DESC(edac_mc_log_ce,
"Log correctable error to console: 0=off 1=on");
-module_param_call(edac_mc_poll_msec, edac_set_poll_msec, param_get_int,
+module_param_call(edac_mc_poll_msec, edac_set_poll_msec, param_get_uint,
&edac_mc_poll_msec, 0644);
MODULE_PARM_DESC(edac_mc_poll_msec, "Polling period in milliseconds");
diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
index dec88dcea036..c9f0e73872a6 100644
--- a/drivers/edac/edac_module.h
+++ b/drivers/edac/edac_module.h
@@ -36,7 +36,7 @@ extern int edac_mc_get_log_ue(void);
extern int edac_mc_get_log_ce(void);
extern int edac_mc_get_panic_on_ue(void);
extern int edac_get_poll_msec(void);
-extern int edac_mc_get_poll_msec(void);
+extern unsigned int edac_mc_get_poll_msec(void);
unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
unsigned len);
--
2.20.1
From: "Mauro S. M. Rodrigues" <[email protected]>
[ Upstream commit 655c91414579d7bb115a4f7898ee726fc18e0984 ]
Some transceivers may comply with SFF-8472 but not implement the Digital
Diagnostic Monitoring (DDM) interface described in it. The existence of
such area is specified by bit 6 of byte 92, set to 1 if implemented.
Currently, due to not checking this bit ixgbe fails trying to read SFP
module's eeprom with the follow message:
ethtool -m enP51p1s0f0
Cannot get Module EEPROM data: Input/output error
Because it fails to read the additional 256 bytes in which it was assumed
to exist the DDM data.
This issue was noticed using a Mellanox Passive DAC PN 01FT738. The eeprom
data was confirmed by Mellanox as correct and present in other Passive
DACs in from other manufacturers.
Signed-off-by: "Mauro S. M. Rodrigues" <[email protected]>
Reviewed-by: Jesse Brandeburg <[email protected]>
Tested-by: Andrew Bowers <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 3 ++-
drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h | 1 +
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index e5a8461fe6a9..8829bd95d0d3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -3223,7 +3223,8 @@ static int ixgbe_get_module_info(struct net_device *dev,
page_swap = true;
}
- if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap) {
+ if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap ||
+ !(addr_mode & IXGBE_SFF_DDM_IMPLEMENTED)) {
/* We have a SFP, but it does not support SFF-8472 */
modinfo->type = ETH_MODULE_SFF_8079;
modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 64e44e01c973..c56baad04ee6 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -45,6 +45,7 @@
#define IXGBE_SFF_SOFT_RS_SELECT_10G 0x8
#define IXGBE_SFF_SOFT_RS_SELECT_1G 0x0
#define IXGBE_SFF_ADDRESSING_MODE 0x4
+#define IXGBE_SFF_DDM_IMPLEMENTED 0x40
#define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1
#define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8
#define IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE 0x23
--
2.20.1
From: Marek Szyprowski <[email protected]>
[ Upstream commit 6282edb72bed5324352522d732080d4c1b9dfed6 ]
Exynos SoCs based on CA7/CA15 have 2 timer interfaces: custom Exynos MCT
(Multi Core Timer) and standard ARM Architected Timers.
There are use cases, where both timer interfaces are used simultanously.
One of such examples is using Exynos MCT for the main system timer and
ARM Architected Timers for the KVM and virtualized guests (KVM requires
arch timers).
Exynos Multi-Core Timer driver (exynos_mct) must be however started
before ARM Architected Timers (arch_timer), because they both share some
common hardware blocks (global system counter) and turning on MCT is
needed to get ARM Architected Timer working properly.
To ensure selecting Exynos MCT as the main system timer, increase MCT
timer rating. To ensure proper starting order of both timers during
suspend/resume cycle, increase MCT hotplug priority over ARM Archictected
Timers.
Signed-off-by: Marek Szyprowski <[email protected]>
Reviewed-by: Krzysztof Kozlowski <[email protected]>
Reviewed-by: Chanwoo Choi <[email protected]>
Signed-off-by: Daniel Lezcano <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/clocksource/exynos_mct.c | 4 ++--
include/linux/cpuhotplug.h | 2 +-
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/clocksource/exynos_mct.c b/drivers/clocksource/exynos_mct.c
index d55c30f6981d..aaf5bfa9bd9c 100644
--- a/drivers/clocksource/exynos_mct.c
+++ b/drivers/clocksource/exynos_mct.c
@@ -211,7 +211,7 @@ static void exynos4_frc_resume(struct clocksource *cs)
static struct clocksource mct_frc = {
.name = "mct-frc",
- .rating = 400,
+ .rating = 450, /* use value higher than ARM arch timer */
.read = exynos4_frc_read,
.mask = CLOCKSOURCE_MASK(32),
.flags = CLOCK_SOURCE_IS_CONTINUOUS,
@@ -466,7 +466,7 @@ static int exynos4_mct_starting_cpu(unsigned int cpu)
evt->set_state_oneshot_stopped = set_state_shutdown;
evt->tick_resume = set_state_shutdown;
evt->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
- evt->rating = 450;
+ evt->rating = 500; /* use value higher than ARM arch timer */
exynos4_mct_write(TICK_BASE_CNT, mevt->base + MCT_L_TCNTB_OFFSET);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index d64d8c2bbdab..6df31106115d 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -116,10 +116,10 @@ enum cpuhp_state {
CPUHP_AP_PERF_ARM_ACPI_STARTING,
CPUHP_AP_PERF_ARM_STARTING,
CPUHP_AP_ARM_L2X0_STARTING,
+ CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
CPUHP_AP_ARM_ARCH_TIMER_STARTING,
CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
CPUHP_AP_JCORE_TIMER_STARTING,
- CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
CPUHP_AP_ARM_TWD_STARTING,
CPUHP_AP_QCOM_TIMER_STARTING,
CPUHP_AP_ARMADA_TIMER_STARTING,
--
2.20.1
From: Ferdinand Blomqvist <[email protected]>
[ Upstream commit ef4d6a8556b637ad27c8c2a2cff1dda3da38e9a9 ]
Check if the syndrome provided by the caller is zero, and act
accordingly.
Signed-off-by: Ferdinand Blomqvist <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
lib/reed_solomon/decode_rs.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/lib/reed_solomon/decode_rs.c b/lib/reed_solomon/decode_rs.c
index 3313bf944ff1..121beb2f0930 100644
--- a/lib/reed_solomon/decode_rs.c
+++ b/lib/reed_solomon/decode_rs.c
@@ -42,8 +42,18 @@
BUG_ON(pad < 0 || pad >= nn);
/* Does the caller provide the syndrome ? */
- if (s != NULL)
- goto decode;
+ if (s != NULL) {
+ for (i = 0; i < nroots; i++) {
+ /* The syndrome is in index form,
+ * so nn represents zero
+ */
+ if (s[i] != nn)
+ goto decode;
+ }
+
+ /* syndrome is zero, no errors to correct */
+ return 0;
+ }
/* form the syndromes; i.e., evaluate data(x) at roots of
* g(x) */
--
2.20.1
From: Wen Gong <[email protected]>
[ Upstream commit 3ed39f8e747a7aafeec07bb244f2c3a1bdca5730 ]
The workqueue need to flush and destory while remove sdio module,
otherwise it will have thread which is not destory after remove
sdio modules.
Tested with QCA6174 SDIO with firmware
WLAN.RMH.4.4.1-00007-QCARMSWP-1.
Signed-off-by: Wen Gong <[email protected]>
Signed-off-by: Kalle Valo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/wireless/ath/ath10k/sdio.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index cb527a21f1ac..686759b5613f 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -2073,6 +2073,9 @@ static void ath10k_sdio_remove(struct sdio_func *func)
cancel_work_sync(&ar_sdio->wr_async_work);
ath10k_core_unregister(ar);
ath10k_core_destroy(ar);
+
+ flush_workqueue(ar_sdio->workqueue);
+ destroy_workqueue(ar_sdio->workqueue);
}
static const struct sdio_device_id ath10k_sdio_devices[] = {
--
2.20.1
From: Maxime Chevallier <[email protected]>
[ Upstream commit 8ec3ede559956f8ad58db7b57d25ac724bab69e9 ]
The Header Parser allows identifying various fields in the packet
headers, used for various kind of filtering and classification
steps.
This is a re-entrant process, where the offset in the packet header
depends on the previous lookup results. This offset is represented in
the SRAM results of the TCAM, as a shift to be operated.
This shift can be negative in some cases, such as in IPv6 parsing.
This commit prevents overriding the sign bit when setting the shift
value, which could cause instabilities when parsing IPv6 flows.
Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Suggested-by: Alan Winkowski <[email protected]>
Signed-off-by: Maxime Chevallier <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index ae2240074d8e..5692c6087bbb 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -312,7 +312,8 @@ static void mvpp2_prs_sram_shift_set(struct mvpp2_prs_entry *pe, int shift,
}
/* Set value */
- pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] = shift & MVPP2_PRS_SRAM_SHIFT_MASK;
+ pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] |=
+ shift & MVPP2_PRS_SRAM_SHIFT_MASK;
/* Reset and set operation */
mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_SHIFT_OFFS,
--
2.20.1
From: Andrei Otcheretianski <[email protected]>
[ Upstream commit ac70499ee97231a418dc1a4d6c9dc102e8f64631 ]
In some buggy scenarios we could possible attempt to transmit frames larger
than maximum MSDU size. Since our devices don't know how to handle this,
it may result in asserts, hangs etc.
This can happen, for example, when we receive a large multicast frame
and try to transmit it back to the air in AP mode.
Since in a legal scenario this should never happen, drop such frames and
warn about it.
Signed-off-by: Andrei Otcheretianski <[email protected]>
Signed-off-by: Luca Coelho <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/wireless/intel/iwlwifi/mvm/tx.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 2d21f0a1fa00..ffae299c3492 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -641,6 +641,9 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb)
memcpy(&info, skb->cb, sizeof(info));
+ if (WARN_ON_ONCE(skb->len > IEEE80211_MAX_DATA_LEN + hdrlen))
+ return -1;
+
if (WARN_ON_ONCE(info.flags & IEEE80211_TX_CTL_AMPDU))
return -1;
--
2.20.1
From: Coly Li <[email protected]>
[ Upstream commit e775339e1ae1205b47d94881db124c11385e597c ]
If CACHE_SET_IO_DISABLE of a cache set flag is set by too many I/O
errors, currently allocator routines can still continue allocate
space which may introduce inconsistent metadata state.
This patch checkes CACHE_SET_IO_DISABLE bit in following allocator
routines,
- bch_bucket_alloc()
- __bch_bucket_alloc_set()
Once CACHE_SET_IO_DISABLE is set on cache set, the allocator routines
may reject allocation request earlier to avoid potential inconsistent
metadata.
Signed-off-by: Coly Li <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/md/bcache/alloc.c | 9 +++++++++
1 file changed, 9 insertions(+)
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index de85b3af3b39..9c3beb1e382b 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -393,6 +393,11 @@ long bch_bucket_alloc(struct cache *ca, unsigned int reserve, bool wait)
struct bucket *b;
long r;
+
+ /* No allocation if CACHE_SET_IO_DISABLE bit is set */
+ if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &ca->set->flags)))
+ return -1;
+
/* fastpath */
if (fifo_pop(&ca->free[RESERVE_NONE], r) ||
fifo_pop(&ca->free[reserve], r))
@@ -484,6 +489,10 @@ int __bch_bucket_alloc_set(struct cache_set *c, unsigned int reserve,
{
int i;
+ /* No allocation if CACHE_SET_IO_DISABLE bit is set */
+ if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
+ return -1;
+
lockdep_assert_held(&c->bucket_lock);
BUG_ON(!n || n > c->caches_loaded || n > 8);
--
2.20.1
From: Yunsheng Lin <[email protected]>
[ Upstream commit 04f25edb48c441fc278ecc154c270f16966cbb90 ]
When hdev->tx_sch_mode is HCLGE_FLAG_VNET_BASE_SCH_MODE, the
hclge_tm_schd_mode_vnet_base_cfg calls hclge_tm_pri_schd_mode_cfg
with vport->vport_id as pri_id, which is used as index for
hdev->tm_info.tc_info, it will cause out of bound access issue
if vport_id is equal to or larger than HNAE3_MAX_TC.
Also hardware only support maximum speed of HCLGE_ETHER_MAX_RATE.
So this patch adds two checks for above cases.
Fixes: 848440544b41 ("net: hns3: Add support of TX Scheduler & Shaper to HNS3 driver")
Signed-off-by: Yunsheng Lin <[email protected]>
Signed-off-by: Peng Li <[email protected]>
Signed-off-by: Huazhong Tan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 48235dc2dd56..11e9259ca040 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -54,7 +54,8 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level,
u32 tick;
/* Calc tick */
- if (shaper_level >= HCLGE_SHAPER_LVL_CNT)
+ if (shaper_level >= HCLGE_SHAPER_LVL_CNT ||
+ ir > HCLGE_ETHER_MAX_RATE)
return -EINVAL;
tick = tick_array[shaper_level];
@@ -1057,6 +1058,9 @@ static int hclge_tm_schd_mode_vnet_base_cfg(struct hclge_vport *vport)
int ret;
u8 i;
+ if (vport->vport_id >= HNAE3_MAX_TC)
+ return -EINVAL;
+
ret = hclge_tm_pri_schd_mode_cfg(hdev, vport->vport_id);
if (ret)
return ret;
--
2.20.1
From: Nathan Chancellor <[email protected]>
[ Upstream commit f7019b7b0ad14bde732b8953161994edfc384953 ]
Clang warns:
In file included from net/xdp/xsk_queue.c:10:
net/xdp/xsk_queue.h:292:2: warning: expression result unused
[-Wunused-value]
WRITE_ONCE(q->ring->producer, q->prod_tail);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
include/linux/compiler.h:284:6: note: expanded from macro 'WRITE_ONCE'
__u.__val; \
~~~ ^~~~~
1 warning generated.
The q->prod_tail assignment has a comma at the end, not a semi-colon.
Fix that so clang no longer warns and everything works as expected.
Fixes: c497176cb2e4 ("xsk: add Rx receive functions and poll support")
Link: https://github.com/ClangBuiltLinux/linux/issues/544
Signed-off-by: Nathan Chancellor <[email protected]>
Acked-by: Nick Desaulniers <[email protected]>
Acked-by: Jonathan Lemon <[email protected]>
Acked-by: Björn Töpel <[email protected]>
Acked-by: Song Liu <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/xdp/xsk_queue.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index 8a64b150be54..fe96c0d039f2 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -239,7 +239,7 @@ static inline void xskq_produce_flush_desc(struct xsk_queue *q)
/* Order producer and data */
smp_wmb();
- q->prod_tail = q->prod_head,
+ q->prod_tail = q->prod_head;
WRITE_ONCE(q->ring->producer, q->prod_tail);
}
--
2.20.1
From: Viresh Kumar <[email protected]>
[ Upstream commit 9801522840cc1073f8064b4c979b7b6995c74bca ]
CPUFREQ_CONST_LOOPS was introduced in a very old commit from pre-2.6
kernel release by commit 6a4a93f9c0d5 ("[CPUFREQ] Fix 'out of sync'
issue").
Basically, that commit does two things:
- It adds the frequency verification code (which is quite similar to
what we have today as well).
- And it sets the CPUFREQ_CONST_LOOPS flag only for setpolicy drivers,
rightly so based on the code we had then. The idea was to avoid
frequency validation for setpolicy drivers as the cpufreq core doesn't
know what frequency the hardware is running at and so no point in
doing frequency verification.
The problem happened when we started to use the same CPUFREQ_CONST_LOOPS
flag for constant loops-per-jiffy thing as well and many has_target()
drivers started using the same flag and unknowingly skipped the
verification of frequency. There is no logical reason behind skipping
frequency validation because of the presence of CPUFREQ_CONST_LOOPS
flag otherwise.
Fix this issue by skipping frequency validation only for setpolicy
drivers and always doing it for has_target() drivers irrespective of
the presence or absence of CPUFREQ_CONST_LOOPS flag.
cpufreq_notify_transition() is only called for has_target() type driver
and not for set_policy type, and the check is simply redundant. Remove
it as well.
Also remove () around freq comparison statement as they aren't required
and checkpatch also warns for them.
Signed-off-by: Viresh Kumar <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/cpufreq/cpufreq.c | 13 +++++--------
1 file changed, 5 insertions(+), 8 deletions(-)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index d3213594d1a7..80942ec34efd 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -321,12 +321,10 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy,
* which is not equal to what the cpufreq core thinks is
* "old frequency".
*/
- if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
- if (policy->cur && (policy->cur != freqs->old)) {
- pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
- freqs->old, policy->cur);
- freqs->old = policy->cur;
- }
+ if (policy->cur && policy->cur != freqs->old) {
+ pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
+ freqs->old, policy->cur);
+ freqs->old = policy->cur;
}
for_each_cpu(freqs->cpu, policy->cpus) {
@@ -1543,8 +1541,7 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
if (policy->fast_switch_enabled)
return ret_freq;
- if (ret_freq && policy->cur &&
- !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
+ if (has_target() && ret_freq && policy->cur) {
/* verify no discrepancy between actual and
saved value exists */
if (unlikely(ret_freq != policy->cur)) {
--
2.20.1
From: "Guilherme G. Piccoli" <[email protected]>
[ Upstream commit 3c91f25c2f72ba6001775a5932857c1d2131c531 ]
Currently bnx2x ptp worker tries to read a register with timestamp
information in case of TX packet timestamping and in case it fails,
the routine reschedules itself indefinitely. This was reported as a
kworker always at 100% of CPU usage, which was narrowed down to be
bnx2x ptp_task.
By following the ioctl handler, we could narrow down the problem to
an NTP tool (chrony) requesting HW timestamping from bnx2x NIC with
RX filter zeroed; this isn't reproducible for example with ptp4l
(from linuxptp) since this tool requests a supported RX filter.
It seems NIC FW timestamp mechanism cannot work well with
RX_FILTER_NONE - driver's PTP filter init routine skips a register
write to the adapter if there's not a supported filter request.
This patch addresses the problem of bnx2x ptp thread's everlasting
reschedule by retrying the register read 10 times; between the read
attempts the thread sleeps for an increasing amount of time starting
in 1ms to give FW some time to perform the timestamping. If it still
fails after all retries, we bail out in order to prevent an unbound
resource consumption from bnx2x.
The patch also adds an ethtool statistic for accounting the skipped
TX timestamp packets and it reduces the priority of timestamping
error messages to prevent log flooding. The code was tested using
both linuxptp and chrony.
Reported-and-tested-by: Przemyslaw Hausman <[email protected]>
Suggested-by: Sudarsana Reddy Kalluru <[email protected]>
Signed-off-by: Guilherme G. Piccoli <[email protected]>
Acked-by: Sudarsana Reddy Kalluru <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
.../net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 5 ++-
.../ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 4 ++-
.../net/ethernet/broadcom/bnx2x/bnx2x_main.c | 33 ++++++++++++++-----
.../net/ethernet/broadcom/bnx2x/bnx2x_stats.h | 3 ++
4 files changed, 34 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 5a727d4729da..e3ce29951c5e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -3858,9 +3858,12 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
if (!(bp->flags & TX_TIMESTAMPING_EN)) {
+ bp->eth_stats.ptp_skip_tx_ts++;
BNX2X_ERR("Tx timestamping was not enabled, this packet will not be timestamped\n");
} else if (bp->ptp_tx_skb) {
- BNX2X_ERR("The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n");
+ bp->eth_stats.ptp_skip_tx_ts++;
+ netdev_err_once(bp->dev,
+ "Device supports only a single outstanding packet to timestamp, this packet won't be timestamped\n");
} else {
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
/* schedule check for Tx timestamp */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index c428b0655c26..00f9ed93360c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -182,7 +182,9 @@ static const struct {
{ STATS_OFFSET32(driver_filtered_tx_pkt),
4, false, "driver_filtered_tx_pkt" },
{ STATS_OFFSET32(eee_tx_lpi),
- 4, true, "Tx LPI entry count"}
+ 4, true, "Tx LPI entry count"},
+ { STATS_OFFSET32(ptp_skip_tx_ts),
+ 4, false, "ptp_skipped_tx_tstamp" },
};
#define BNX2X_NUM_STATS ARRAY_SIZE(bnx2x_stats_arr)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index a585f1025a58..2c9af0f420e5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -15244,11 +15244,24 @@ static void bnx2x_ptp_task(struct work_struct *work)
u32 val_seq;
u64 timestamp, ns;
struct skb_shared_hwtstamps shhwtstamps;
+ bool bail = true;
+ int i;
+
+ /* FW may take a while to complete timestamping; try a bit and if it's
+ * still not complete, may indicate an error state - bail out then.
+ */
+ for (i = 0; i < 10; i++) {
+ /* Read Tx timestamp registers */
+ val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
+ NIG_REG_P0_TLLH_PTP_BUF_SEQID);
+ if (val_seq & 0x10000) {
+ bail = false;
+ break;
+ }
+ msleep(1 << i);
+ }
- /* Read Tx timestamp registers */
- val_seq = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_SEQID :
- NIG_REG_P0_TLLH_PTP_BUF_SEQID);
- if (val_seq & 0x10000) {
+ if (!bail) {
/* There is a valid timestamp value */
timestamp = REG_RD(bp, port ? NIG_REG_P1_TLLH_PTP_BUF_TS_MSB :
NIG_REG_P0_TLLH_PTP_BUF_TS_MSB);
@@ -15263,16 +15276,18 @@ static void bnx2x_ptp_task(struct work_struct *work)
memset(&shhwtstamps, 0, sizeof(shhwtstamps));
shhwtstamps.hwtstamp = ns_to_ktime(ns);
skb_tstamp_tx(bp->ptp_tx_skb, &shhwtstamps);
- dev_kfree_skb_any(bp->ptp_tx_skb);
- bp->ptp_tx_skb = NULL;
DP(BNX2X_MSG_PTP, "Tx timestamp, timestamp cycles = %llu, ns = %llu\n",
timestamp, ns);
} else {
- DP(BNX2X_MSG_PTP, "There is no valid Tx timestamp yet\n");
- /* Reschedule to keep checking for a valid timestamp value */
- schedule_work(&bp->ptp_task);
+ DP(BNX2X_MSG_PTP,
+ "Tx timestamp is not recorded (register read=%u)\n",
+ val_seq);
+ bp->eth_stats.ptp_skip_tx_ts++;
}
+
+ dev_kfree_skb_any(bp->ptp_tx_skb);
+ bp->ptp_tx_skb = NULL;
}
void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
index b2644ed13d06..d55e63692cf3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
@@ -207,6 +207,9 @@ struct bnx2x_eth_stats {
u32 driver_filtered_tx_pkt;
/* src: Clear-on-Read register; Will not survive PMF Migration */
u32 eee_tx_lpi;
+
+ /* PTP */
+ u32 ptp_skip_tx_ts;
};
struct bnx2x_eth_q_stats {
--
2.20.1
From: Cong Wang <[email protected]>
[ Upstream commit 9d1bc24b52fb8c5d859f9a47084bf1179470e04c ]
bond_xmit_roundrobin() checks for IGMP packets but it parses
the IP header even before checking skb->protocol.
We should validate the IP header with pskb_may_pull() before
using iph->protocol.
Reported-and-tested-by: [email protected]
Fixes: a2fd940f4cff ("bonding: fix broken multicast with round-robin mode")
Cc: Jay Vosburgh <[email protected]>
Cc: Veaceslav Falico <[email protected]>
Cc: Andy Gospodarek <[email protected]>
Signed-off-by: Cong Wang <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/bonding/bond_main.c | 37 ++++++++++++++++++++-------------
1 file changed, 23 insertions(+), 14 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7e162fff01ab..be0b785becd0 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3852,8 +3852,8 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
struct net_device *bond_dev)
{
struct bonding *bond = netdev_priv(bond_dev);
- struct iphdr *iph = ip_hdr(skb);
struct slave *slave;
+ int slave_cnt;
u32 slave_id;
/* Start with the curr_active_slave that joined the bond as the
@@ -3862,23 +3862,32 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
* send the join/membership reports. The curr_active_slave found
* will send all of this type of traffic.
*/
- if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) {
- slave = rcu_dereference(bond->curr_active_slave);
- if (slave)
- bond_dev_queue_xmit(bond, skb, slave->dev);
- else
- bond_xmit_slave_id(bond, skb, 0);
- } else {
- int slave_cnt = READ_ONCE(bond->slave_cnt);
+ if (skb->protocol == htons(ETH_P_IP)) {
+ int noff = skb_network_offset(skb);
+ struct iphdr *iph;
- if (likely(slave_cnt)) {
- slave_id = bond_rr_gen_slave_id(bond);
- bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
- } else {
- bond_tx_drop(bond_dev, skb);
+ if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph))))
+ goto non_igmp;
+
+ iph = ip_hdr(skb);
+ if (iph->protocol == IPPROTO_IGMP) {
+ slave = rcu_dereference(bond->curr_active_slave);
+ if (slave)
+ bond_dev_queue_xmit(bond, skb, slave->dev);
+ else
+ bond_xmit_slave_id(bond, skb, 0);
+ return NETDEV_TX_OK;
}
}
+non_igmp:
+ slave_cnt = READ_ONCE(bond->slave_cnt);
+ if (likely(slave_cnt)) {
+ slave_id = bond_rr_gen_slave_id(bond);
+ bond_xmit_slave_id(bond, skb, slave_id % slave_cnt);
+ } else {
+ bond_tx_drop(bond_dev, skb);
+ }
return NETDEV_TX_OK;
}
--
2.20.1
From: Coly Li <[email protected]>
[ Upstream commit b387e9b58679c60f5b1e4313939bd4878204fc37 ]
When system memory is in heavy pressure, bch_gc_thread_start() from
run_cache_set() may fail due to out of memory. In such condition,
c->gc_thread is assigned to -ENOMEM, not NULL pointer. Then in following
failure code path bch_cache_set_error(), when cache_set_flush() gets
called, the code piece to stop c->gc_thread is broken,
if (!IS_ERR_OR_NULL(c->gc_thread))
kthread_stop(c->gc_thread);
And KASAN catches such NULL pointer deference problem, with the warning
information:
[ 561.207881] ==================================================================
[ 561.207900] BUG: KASAN: null-ptr-deref in kthread_stop+0x3b/0x440
[ 561.207904] Write of size 4 at addr 000000000000001c by task kworker/15:1/313
[ 561.207913] CPU: 15 PID: 313 Comm: kworker/15:1 Tainted: G W 5.0.0-vanilla+ #3
[ 561.207916] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE136T-2.10]- 03/22/2019
[ 561.207935] Workqueue: events cache_set_flush [bcache]
[ 561.207940] Call Trace:
[ 561.207948] dump_stack+0x9a/0xeb
[ 561.207955] ? kthread_stop+0x3b/0x440
[ 561.207960] ? kthread_stop+0x3b/0x440
[ 561.207965] kasan_report+0x176/0x192
[ 561.207973] ? kthread_stop+0x3b/0x440
[ 561.207981] kthread_stop+0x3b/0x440
[ 561.207995] cache_set_flush+0xd4/0x6d0 [bcache]
[ 561.208008] process_one_work+0x856/0x1620
[ 561.208015] ? find_held_lock+0x39/0x1d0
[ 561.208028] ? drain_workqueue+0x380/0x380
[ 561.208048] worker_thread+0x87/0xb80
[ 561.208058] ? __kthread_parkme+0xb6/0x180
[ 561.208067] ? process_one_work+0x1620/0x1620
[ 561.208072] kthread+0x326/0x3e0
[ 561.208079] ? kthread_create_worker_on_cpu+0xc0/0xc0
[ 561.208090] ret_from_fork+0x3a/0x50
[ 561.208110] ==================================================================
[ 561.208113] Disabling lock debugging due to kernel taint
[ 561.208115] irq event stamp: 11800231
[ 561.208126] hardirqs last enabled at (11800231): [<ffffffff83008538>] do_syscall_64+0x18/0x410
[ 561.208127] BUG: unable to handle kernel NULL pointer dereference at 000000000000001c
[ 561.208129] #PF error: [WRITE]
[ 561.312253] hardirqs last disabled at (11800230): [<ffffffff830052ff>] trace_hardirqs_off_thunk+0x1a/0x1c
[ 561.312259] softirqs last enabled at (11799832): [<ffffffff850005c7>] __do_softirq+0x5c7/0x8c3
[ 561.405975] PGD 0 P4D 0
[ 561.442494] softirqs last disabled at (11799821): [<ffffffff831add2c>] irq_exit+0x1ac/0x1e0
[ 561.791359] Oops: 0002 [#1] SMP KASAN NOPTI
[ 561.791362] CPU: 15 PID: 313 Comm: kworker/15:1 Tainted: G B W 5.0.0-vanilla+ #3
[ 561.791363] Hardware name: Lenovo ThinkSystem SR650 -[7X05CTO1WW]-/-[7X05CTO1WW]-, BIOS -[IVE136T-2.10]- 03/22/2019
[ 561.791371] Workqueue: events cache_set_flush [bcache]
[ 561.791374] RIP: 0010:kthread_stop+0x3b/0x440
[ 561.791376] Code: 00 00 65 8b 05 26 d5 e0 7c 89 c0 48 0f a3 05 ec aa df 02 0f 82 dc 02 00 00 4c 8d 63 20 be 04 00 00 00 4c 89 e7 e8 65 c5 53 00 <f0> ff 43 20 48 8d 7b 24 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48
[ 561.791377] RSP: 0018:ffff88872fc8fd10 EFLAGS: 00010286
[ 561.838895] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 561.838916] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 561.838934] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 561.838948] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 561.838966] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 561.838979] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 561.838996] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 563.067028] RAX: 0000000000000000 RBX: fffffffffffffffc RCX: ffffffff832dd314
[ 563.067030] RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000297
[ 563.067032] RBP: ffff88872fc8fe88 R08: fffffbfff0b8213d R09: fffffbfff0b8213d
[ 563.067034] R10: 0000000000000001 R11: fffffbfff0b8213c R12: 000000000000001c
[ 563.408618] R13: ffff88dc61cc0f68 R14: ffff888102b94900 R15: ffff88dc61cc0f68
[ 563.408620] FS: 0000000000000000(0000) GS:ffff888f7dc00000(0000) knlGS:0000000000000000
[ 563.408622] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 563.408623] CR2: 000000000000001c CR3: 0000000f48a1a004 CR4: 00000000007606e0
[ 563.408625] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 563.408627] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 563.904795] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 563.915796] PKRU: 55555554
[ 563.915797] Call Trace:
[ 563.915807] cache_set_flush+0xd4/0x6d0 [bcache]
[ 563.915812] process_one_work+0x856/0x1620
[ 564.001226] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 564.033563] ? find_held_lock+0x39/0x1d0
[ 564.033567] ? drain_workqueue+0x380/0x380
[ 564.033574] worker_thread+0x87/0xb80
[ 564.062823] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 564.118042] ? __kthread_parkme+0xb6/0x180
[ 564.118046] ? process_one_work+0x1620/0x1620
[ 564.118048] kthread+0x326/0x3e0
[ 564.118050] ? kthread_create_worker_on_cpu+0xc0/0xc0
[ 564.167066] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 564.252441] ret_from_fork+0x3a/0x50
[ 564.252447] Modules linked in: msr rpcrdma sunrpc rdma_ucm ib_iser ib_umad rdma_cm ib_ipoib i40iw configfs iw_cm ib_cm libiscsi scsi_transport_iscsi mlx4_ib ib_uverbs mlx4_en ib_core nls_iso8859_1 nls_cp437 vfat fat intel_rapl skx_edac x86_pkg_temp_thermal coretemp iTCO_wdt iTCO_vendor_support crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ses raid0 aesni_intel cdc_ether enclosure usbnet ipmi_ssif joydev aes_x86_64 i40e scsi_transport_sas mii bcache md_mod crypto_simd mei_me ioatdma crc64 ptp cryptd pcspkr i2c_i801 mlx4_core glue_helper pps_core mei lpc_ich dca wmi ipmi_si ipmi_devintf nd_pmem dax_pmem nd_btt ipmi_msghandler device_dax pcc_cpufreq button hid_generic usbhid mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect xhci_pci sysimgblt fb_sys_fops xhci_hcd ttm megaraid_sas drm usbcore nfit libnvdimm sg dm_multipath dm_mod scsi_dh_rdac scsi_dh_emc scsi_dh_alua efivarfs
[ 564.299390] bcache: bch_count_io_errors() nvme0n1: IO error on writing btree.
[ 564.348360] CR2: 000000000000001c
[ 564.348362] ---[ end trace b7f0e5cc7b2103b0 ]---
Therefore, it is not enough to only check whether c->gc_thread is NULL,
we should use IS_ERR_OR_NULL() to check both NULL pointer and error
value.
This patch changes the above buggy code piece in this way,
if (!IS_ERR_OR_NULL(c->gc_thread))
kthread_stop(c->gc_thread);
Signed-off-by: Coly Li <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/md/bcache/super.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index ca39cf20aa96..be8054c04eb7 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1552,7 +1552,7 @@ static void cache_set_flush(struct closure *cl)
kobject_put(&c->internal);
kobject_del(&c->kobj);
- if (c->gc_thread)
+ if (!IS_ERR_OR_NULL(c->gc_thread))
kthread_stop(c->gc_thread);
if (!IS_ERR_OR_NULL(c->root))
--
2.20.1
From: Coly Li <[email protected]>
[ Upstream commit 80265d8dfd77792e133793cef44a21323aac2908 ]
When enable lockdep engine, a lockdep warning can be observed when
reboot or shutdown system,
[ 3142.764557][ T1] bcache: bcache_reboot() Stopping all devices:
[ 3142.776265][ T2649]
[ 3142.777159][ T2649] ======================================================
[ 3142.780039][ T2649] WARNING: possible circular locking dependency detected
[ 3142.782869][ T2649] 5.2.0-rc4-lp151.20-default+ #1 Tainted: G W
[ 3142.785684][ T2649] ------------------------------------------------------
[ 3142.788479][ T2649] kworker/3:67/2649 is trying to acquire lock:
[ 3142.790738][ T2649] 00000000aaf02291 ((wq_completion)bcache_writeback_wq){+.+.}, at: flush_workqueue+0x87/0x4c0
[ 3142.794678][ T2649]
[ 3142.794678][ T2649] but task is already holding lock:
[ 3142.797402][ T2649] 000000004fcf89c5 (&bch_register_lock){+.+.}, at: cached_dev_free+0x17/0x120 [bcache]
[ 3142.801462][ T2649]
[ 3142.801462][ T2649] which lock already depends on the new lock.
[ 3142.801462][ T2649]
[ 3142.805277][ T2649]
[ 3142.805277][ T2649] the existing dependency chain (in reverse order) is:
[ 3142.808902][ T2649]
[ 3142.808902][ T2649] -> #2 (&bch_register_lock){+.+.}:
[ 3142.812396][ T2649] __mutex_lock+0x7a/0x9d0
[ 3142.814184][ T2649] cached_dev_free+0x17/0x120 [bcache]
[ 3142.816415][ T2649] process_one_work+0x2a4/0x640
[ 3142.818413][ T2649] worker_thread+0x39/0x3f0
[ 3142.820276][ T2649] kthread+0x125/0x140
[ 3142.822061][ T2649] ret_from_fork+0x3a/0x50
[ 3142.823965][ T2649]
[ 3142.823965][ T2649] -> #1 ((work_completion)(&cl->work)#2){+.+.}:
[ 3142.827244][ T2649] process_one_work+0x277/0x640
[ 3142.829160][ T2649] worker_thread+0x39/0x3f0
[ 3142.830958][ T2649] kthread+0x125/0x140
[ 3142.832674][ T2649] ret_from_fork+0x3a/0x50
[ 3142.834915][ T2649]
[ 3142.834915][ T2649] -> #0 ((wq_completion)bcache_writeback_wq){+.+.}:
[ 3142.838121][ T2649] lock_acquire+0xb4/0x1c0
[ 3142.840025][ T2649] flush_workqueue+0xae/0x4c0
[ 3142.842035][ T2649] drain_workqueue+0xa9/0x180
[ 3142.844042][ T2649] destroy_workqueue+0x17/0x250
[ 3142.846142][ T2649] cached_dev_free+0x52/0x120 [bcache]
[ 3142.848530][ T2649] process_one_work+0x2a4/0x640
[ 3142.850663][ T2649] worker_thread+0x39/0x3f0
[ 3142.852464][ T2649] kthread+0x125/0x140
[ 3142.854106][ T2649] ret_from_fork+0x3a/0x50
[ 3142.855880][ T2649]
[ 3142.855880][ T2649] other info that might help us debug this:
[ 3142.855880][ T2649]
[ 3142.859663][ T2649] Chain exists of:
[ 3142.859663][ T2649] (wq_completion)bcache_writeback_wq --> (work_completion)(&cl->work)#2 --> &bch_register_lock
[ 3142.859663][ T2649]
[ 3142.865424][ T2649] Possible unsafe locking scenario:
[ 3142.865424][ T2649]
[ 3142.868022][ T2649] CPU0 CPU1
[ 3142.869885][ T2649] ---- ----
[ 3142.871751][ T2649] lock(&bch_register_lock);
[ 3142.873379][ T2649] lock((work_completion)(&cl->work)#2);
[ 3142.876399][ T2649] lock(&bch_register_lock);
[ 3142.879727][ T2649] lock((wq_completion)bcache_writeback_wq);
[ 3142.882064][ T2649]
[ 3142.882064][ T2649] *** DEADLOCK ***
[ 3142.882064][ T2649]
[ 3142.885060][ T2649] 3 locks held by kworker/3:67/2649:
[ 3142.887245][ T2649] #0: 00000000e774cdd0 ((wq_completion)events){+.+.}, at: process_one_work+0x21e/0x640
[ 3142.890815][ T2649] #1: 00000000f7df89da ((work_completion)(&cl->work)#2){+.+.}, at: process_one_work+0x21e/0x640
[ 3142.894884][ T2649] #2: 000000004fcf89c5 (&bch_register_lock){+.+.}, at: cached_dev_free+0x17/0x120 [bcache]
[ 3142.898797][ T2649]
[ 3142.898797][ T2649] stack backtrace:
[ 3142.900961][ T2649] CPU: 3 PID: 2649 Comm: kworker/3:67 Tainted: G W 5.2.0-rc4-lp151.20-default+ #1
[ 3142.904789][ T2649] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/13/2018
[ 3142.909168][ T2649] Workqueue: events cached_dev_free [bcache]
[ 3142.911422][ T2649] Call Trace:
[ 3142.912656][ T2649] dump_stack+0x85/0xcb
[ 3142.914181][ T2649] print_circular_bug+0x19a/0x1f0
[ 3142.916193][ T2649] __lock_acquire+0x16cd/0x1850
[ 3142.917936][ T2649] ? __lock_acquire+0x6a8/0x1850
[ 3142.919704][ T2649] ? lock_acquire+0xb4/0x1c0
[ 3142.921335][ T2649] ? find_held_lock+0x34/0xa0
[ 3142.923052][ T2649] lock_acquire+0xb4/0x1c0
[ 3142.924635][ T2649] ? flush_workqueue+0x87/0x4c0
[ 3142.926375][ T2649] flush_workqueue+0xae/0x4c0
[ 3142.928047][ T2649] ? flush_workqueue+0x87/0x4c0
[ 3142.929824][ T2649] ? drain_workqueue+0xa9/0x180
[ 3142.931686][ T2649] drain_workqueue+0xa9/0x180
[ 3142.933534][ T2649] destroy_workqueue+0x17/0x250
[ 3142.935787][ T2649] cached_dev_free+0x52/0x120 [bcache]
[ 3142.937795][ T2649] process_one_work+0x2a4/0x640
[ 3142.939803][ T2649] worker_thread+0x39/0x3f0
[ 3142.941487][ T2649] ? process_one_work+0x640/0x640
[ 3142.943389][ T2649] kthread+0x125/0x140
[ 3142.944894][ T2649] ? kthread_create_worker_on_cpu+0x70/0x70
[ 3142.947744][ T2649] ret_from_fork+0x3a/0x50
[ 3142.970358][ T2649] bcache: bcache_device_free() bcache0 stopped
Here is how the deadlock happens.
1) bcache_reboot() calls bcache_device_stop(), then inside
bcache_device_stop() BCACHE_DEV_CLOSING bit is set on d->flags.
Then closure_queue(&d->cl) is called to invoke cached_dev_flush().
2) In cached_dev_flush(), cached_dev_free() is called by continu_at().
3) In cached_dev_free(), when stopping the writeback kthread of the
cached device by kthread_stop(), dc->writeback_thread will be waken
up to quite the kthread while-loop, then cached_dev_put() is called
in bch_writeback_thread().
4) Calling cached_dev_put() in writeback kthread may drop dc->count to
0, then dc->detach kworker is scheduled, which is initialized as
cached_dev_detach_finish().
5) Inside cached_dev_detach_finish(), the last line of code is to call
closure_put(&dc->disk.cl), which drops the last reference counter of
closrure dc->disk.cl, then the callback cached_dev_flush() gets
called.
Now cached_dev_flush() is called for second time in the code path, the
first time is in step 2). And again bch_register_lock will be acquired
again, and a A-A lock (lockdep terminology) is happening.
The root cause of the above A-A lock is in cached_dev_free(), mutex
bch_register_lock is held before stopping writeback kthread and other
kworkers. Fortunately now we have variable 'bcache_is_reboot', which may
prevent device registration or unregistration during reboot/shutdown
time, so it is unncessary to hold bch_register_lock such early now.
This is how this patch fixes the reboot/shutdown time A-A lock issue:
After moving mutex_lock(&bch_register_lock) to a later location where
before atomic_read(&dc->running) in cached_dev_free(), such A-A lock
problem can be solved without any reboot time registration race.
Signed-off-by: Coly Li <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/md/bcache/super.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 2409507d7bff..ca39cf20aa96 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1180,8 +1180,6 @@ static void cached_dev_free(struct closure *cl)
{
struct cached_dev *dc = container_of(cl, struct cached_dev, disk.cl);
- mutex_lock(&bch_register_lock);
-
if (test_and_clear_bit(BCACHE_DEV_WB_RUNNING, &dc->disk.flags))
cancel_writeback_rate_update_dwork(dc);
@@ -1192,6 +1190,8 @@ static void cached_dev_free(struct closure *cl)
if (!IS_ERR_OR_NULL(dc->status_update_thread))
kthread_stop(dc->status_update_thread);
+ mutex_lock(&bch_register_lock);
+
if (atomic_read(&dc->running))
bd_unlink_disk_holder(dc->bdev, dc->disk.disk);
bcache_device_free(&dc->disk);
--
2.20.1
From: Jiri Olsa <[email protected]>
[ Upstream commit aa52bcbe0e72fac36b1862db08b9c09c4caefae3 ]
Michael reported crash with by bpf program in json mode on powerpc:
# bpftool prog -p dump jited id 14
[{
"name": "0xd00000000a9aa760",
"insns": [{
"pc": "0x0",
"operation": "nop",
"operands": [null
]
},{
"pc": "0x4",
"operation": "nop",
"operands": [null
]
},{
"pc": "0x8",
"operation": "mflr",
Segmentation fault (core dumped)
The code is assuming char pointers in format, which is not always
true at least for powerpc. Fixing this by dumping the whole string
into buffer based on its format.
Please note that libopcodes code does not check return values from
fprintf callback, but as per Jakub suggestion returning -1 on allocation
failure so we do the best effort to propagate the error.
Fixes: 107f041212c1 ("tools: bpftool: add JSON output for `bpftool prog dump jited *` command")
Reported-by: Michael Petlan <[email protected]>
Signed-off-by: Jiri Olsa <[email protected]>
Reviewed-by: Quentin Monnet <[email protected]>
Reviewed-by: Jakub Kicinski <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/bpf/bpftool/jit_disasm.c | 11 +++++++----
1 file changed, 7 insertions(+), 4 deletions(-)
diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index 87439320ef70..73d7252729fa 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -10,6 +10,8 @@
* Licensed under the GNU General Public License, version 2.0 (GPLv2)
*/
+#define _GNU_SOURCE
+#include <stdio.h>
#include <stdarg.h>
#include <stdint.h>
#include <stdio.h>
@@ -51,11 +53,13 @@ static int fprintf_json(void *out, const char *fmt, ...)
char *s;
va_start(ap, fmt);
+ if (vasprintf(&s, fmt, ap) < 0)
+ return -1;
+ va_end(ap);
+
if (!oper_count) {
int i;
- s = va_arg(ap, char *);
-
/* Strip trailing spaces */
i = strlen(s) - 1;
while (s[i] == ' ')
@@ -68,11 +72,10 @@ static int fprintf_json(void *out, const char *fmt, ...)
} else if (!strcmp(fmt, ",")) {
/* Skip */
} else {
- s = va_arg(ap, char *);
jsonw_string(json_wtr, s);
oper_count++;
}
- va_end(ap);
+ free(s);
return 0;
}
--
2.20.1
From: Coly Li <[email protected]>
[ Upstream commit 7e865eba00a3df2dc8c4746173a8ca1c1c7f042e ]
When enable lockdep and reboot system with a writeback mode bcache
device, the following potential deadlock warning is reported by lockdep
engine.
[ 101.536569][ T401] kworker/2:2/401 is trying to acquire lock:
[ 101.538575][ T401] 00000000bbf6e6c7 ((wq_completion)bcache_writeback_wq){+.+.}, at: flush_workqueue+0x87/0x4c0
[ 101.542054][ T401]
[ 101.542054][ T401] but task is already holding lock:
[ 101.544587][ T401] 00000000f5f305b3 ((work_completion)(&cl->work)#2){+.+.}, at: process_one_work+0x21e/0x640
[ 101.548386][ T401]
[ 101.548386][ T401] which lock already depends on the new lock.
[ 101.548386][ T401]
[ 101.551874][ T401]
[ 101.551874][ T401] the existing dependency chain (in reverse order) is:
[ 101.555000][ T401]
[ 101.555000][ T401] -> #1 ((work_completion)(&cl->work)#2){+.+.}:
[ 101.557860][ T401] process_one_work+0x277/0x640
[ 101.559661][ T401] worker_thread+0x39/0x3f0
[ 101.561340][ T401] kthread+0x125/0x140
[ 101.562963][ T401] ret_from_fork+0x3a/0x50
[ 101.564718][ T401]
[ 101.564718][ T401] -> #0 ((wq_completion)bcache_writeback_wq){+.+.}:
[ 101.567701][ T401] lock_acquire+0xb4/0x1c0
[ 101.569651][ T401] flush_workqueue+0xae/0x4c0
[ 101.571494][ T401] drain_workqueue+0xa9/0x180
[ 101.573234][ T401] destroy_workqueue+0x17/0x250
[ 101.575109][ T401] cached_dev_free+0x44/0x120 [bcache]
[ 101.577304][ T401] process_one_work+0x2a4/0x640
[ 101.579357][ T401] worker_thread+0x39/0x3f0
[ 101.581055][ T401] kthread+0x125/0x140
[ 101.582709][ T401] ret_from_fork+0x3a/0x50
[ 101.584592][ T401]
[ 101.584592][ T401] other info that might help us debug this:
[ 101.584592][ T401]
[ 101.588355][ T401] Possible unsafe locking scenario:
[ 101.588355][ T401]
[ 101.590974][ T401] CPU0 CPU1
[ 101.592889][ T401] ---- ----
[ 101.594743][ T401] lock((work_completion)(&cl->work)#2);
[ 101.596785][ T401] lock((wq_completion)bcache_writeback_wq);
[ 101.600072][ T401] lock((work_completion)(&cl->work)#2);
[ 101.602971][ T401] lock((wq_completion)bcache_writeback_wq);
[ 101.605255][ T401]
[ 101.605255][ T401] *** DEADLOCK ***
[ 101.605255][ T401]
[ 101.608310][ T401] 2 locks held by kworker/2:2/401:
[ 101.610208][ T401] #0: 00000000cf2c7d17 ((wq_completion)events){+.+.}, at: process_one_work+0x21e/0x640
[ 101.613709][ T401] #1: 00000000f5f305b3 ((work_completion)(&cl->work)#2){+.+.}, at: process_one_work+0x21e/0x640
[ 101.617480][ T401]
[ 101.617480][ T401] stack backtrace:
[ 101.619539][ T401] CPU: 2 PID: 401 Comm: kworker/2:2 Tainted: G W 5.2.0-rc4-lp151.20-default+ #1
[ 101.623225][ T401] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 04/13/2018
[ 101.627210][ T401] Workqueue: events cached_dev_free [bcache]
[ 101.629239][ T401] Call Trace:
[ 101.630360][ T401] dump_stack+0x85/0xcb
[ 101.631777][ T401] print_circular_bug+0x19a/0x1f0
[ 101.633485][ T401] __lock_acquire+0x16cd/0x1850
[ 101.635184][ T401] ? __lock_acquire+0x6a8/0x1850
[ 101.636863][ T401] ? lock_acquire+0xb4/0x1c0
[ 101.638421][ T401] ? find_held_lock+0x34/0xa0
[ 101.640015][ T401] lock_acquire+0xb4/0x1c0
[ 101.641513][ T401] ? flush_workqueue+0x87/0x4c0
[ 101.643248][ T401] flush_workqueue+0xae/0x4c0
[ 101.644832][ T401] ? flush_workqueue+0x87/0x4c0
[ 101.646476][ T401] ? drain_workqueue+0xa9/0x180
[ 101.648303][ T401] drain_workqueue+0xa9/0x180
[ 101.649867][ T401] destroy_workqueue+0x17/0x250
[ 101.651503][ T401] cached_dev_free+0x44/0x120 [bcache]
[ 101.653328][ T401] process_one_work+0x2a4/0x640
[ 101.655029][ T401] worker_thread+0x39/0x3f0
[ 101.656693][ T401] ? process_one_work+0x640/0x640
[ 101.658501][ T401] kthread+0x125/0x140
[ 101.660012][ T401] ? kthread_create_worker_on_cpu+0x70/0x70
[ 101.661985][ T401] ret_from_fork+0x3a/0x50
[ 101.691318][ T401] bcache: bcache_device_free() bcache0 stopped
Here is how the above potential deadlock may happen in reboot/shutdown
code path,
1) bcache_reboot() is called firstly in the reboot/shutdown code path,
then in bcache_reboot(), bcache_device_stop() is called.
2) bcache_device_stop() sets BCACHE_DEV_CLOSING on d->falgs, then call
closure_queue(&d->cl) to invoke cached_dev_flush(). And in turn
cached_dev_flush() calls cached_dev_free() via closure_at()
3) In cached_dev_free(), after stopped writebach kthread
dc->writeback_thread, the kwork dc->writeback_write_wq is stopping by
destroy_workqueue().
4) Inside destroy_workqueue(), drain_workqueue() is called. Inside
drain_workqueue(), flush_workqueue() is called. Then wq->lockdep_map
is acquired by lock_map_acquire() in flush_workqueue(). After the
lock acquired the rest part of flush_workqueue() just wait for the
workqueue to complete.
5) Now we look back at writeback thread routine bch_writeback_thread(),
in the main while-loop, write_dirty() is called via continue_at() in
read_dirty_submit(), which is called via continue_at() in while-loop
level called function read_dirty(). Inside write_dirty() it may be
re-called on workqueeu dc->writeback_write_wq via continue_at().
It means when the writeback kthread is stopped in cached_dev_free()
there might be still one kworker queued on dc->writeback_write_wq
to execute write_dirty() again.
6) Now this kworker is scheduled on dc->writeback_write_wq to run by
process_one_work() (which is called by worker_thread()). Before
calling the kwork routine, wq->lockdep_map is acquired.
7) But wq->lockdep_map is acquired already in step 4), so a A-A lock
(lockdep terminology) scenario happens.
Indeed on multiple cores syatem, the above deadlock is very rare to
happen, just as the code comments in process_one_work() says,
2263 * AFAICT there is no possible deadlock scenario between the
2264 * flush_work() and complete() primitives (except for
single-threaded
2265 * workqueues), so hiding them isn't a problem.
But it is still good to fix such lockdep warning, even no one running
bcache on single core system.
The fix is simple. This patch solves the above potential deadlock by,
- Do not destroy workqueue dc->writeback_write_wq in cached_dev_free().
- Flush and destroy dc->writeback_write_wq in writebach kthread routine
bch_writeback_thread(), where after quit the thread main while-loop
and before cached_dev_put() is called.
By this fix, dc->writeback_write_wq will be stopped and destroy before
the writeback kthread stopped, so the chance for a A-A locking on
wq->lockdep_map is disappeared, such A-A deadlock won't happen
any more.
Signed-off-by: Coly Li <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/md/bcache/super.c | 2 --
drivers/md/bcache/writeback.c | 4 ++++
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index be8054c04eb7..173a2be72eeb 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1185,8 +1185,6 @@ static void cached_dev_free(struct closure *cl)
if (!IS_ERR_OR_NULL(dc->writeback_thread))
kthread_stop(dc->writeback_thread);
- if (dc->writeback_write_wq)
- destroy_workqueue(dc->writeback_write_wq);
if (!IS_ERR_OR_NULL(dc->status_update_thread))
kthread_stop(dc->status_update_thread);
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 08c3a9f9676c..6e72bb6c00f2 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -708,6 +708,10 @@ static int bch_writeback_thread(void *arg)
}
}
+ if (dc->writeback_write_wq) {
+ flush_workqueue(dc->writeback_write_wq);
+ destroy_workqueue(dc->writeback_write_wq);
+ }
cached_dev_put(dc);
wait_for_kthread_stop();
--
2.20.1
From: Yonglong Liu <[email protected]>
[ Upstream commit 18d219b783da61a6cc77581f55fc4af2fa16bc36 ]
When setting -Wformat=2, there is a compiler warning like this:
hclge_main.c:xxx:x: warning: format not a string literal and no
format arguments [-Wformat-nonliteral]
strs[i].desc);
^~~~
This patch adds missing format parameter "%s" to snprintf() to
fix it.
Fixes: 46a3df9f9718 ("Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Yonglong Liu <[email protected]>
Signed-off-by: Peng Li <[email protected]>
Signed-off-by: Huazhong Tan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 4648c6a9d9e8..89ca69fa2b97 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -663,8 +663,7 @@ static u8 *hclge_comm_get_strings(u32 stringset,
return buff;
for (i = 0; i < size; i++) {
- snprintf(buff, ETH_GSTRING_LEN,
- strs[i].desc);
+ snprintf(buff, ETH_GSTRING_LEN, "%s", strs[i].desc);
buff = buff + ETH_GSTRING_LEN;
}
--
2.20.1
From: Matias Karhumaa <[email protected]>
[ Upstream commit 28261da8a26f4915aa257d12d506c6ba179d961f ]
Because of both sides doing L2CAP disconnection at the same time, it
was possible to receive L2CAP Disconnection Response with CID that was
already freed. That caused problems if CID was already reused and L2CAP
Connection Request with same CID was sent out. Before this patch kernel
deleted channel context regardless of the state of the channel.
Example where leftover Disconnection Response (frame #402) causes local
device to delete L2CAP channel which was not yet connected. This in
turn confuses remote device's stack because same CID is re-used without
properly disconnecting.
Btmon capture before patch:
** snip **
> ACL Data RX: Handle 43 flags 0x02 dlen 8 #394 [hci1] 10.748949
Channel: 65 len 4 [PSM 3 mode 0] {chan 2}
RFCOMM: Disconnect (DISC) (0x43)
Address: 0x03 cr 1 dlci 0x00
Control: 0x53 poll/final 1
Length: 0
FCS: 0xfd
< ACL Data TX: Handle 43 flags 0x00 dlen 8 #395 [hci1] 10.749062
Channel: 65 len 4 [PSM 3 mode 0] {chan 2}
RFCOMM: Unnumbered Ack (UA) (0x63)
Address: 0x03 cr 1 dlci 0x00
Control: 0x73 poll/final 1
Length: 0
FCS: 0xd7
< ACL Data TX: Handle 43 flags 0x00 dlen 12 #396 [hci1] 10.749073
L2CAP: Disconnection Request (0x06) ident 17 len 4
Destination CID: 65
Source CID: 65
> HCI Event: Number of Completed Packets (0x13) plen 5 #397 [hci1] 10.752391
Num handles: 1
Handle: 43
Count: 1
> HCI Event: Number of Completed Packets (0x13) plen 5 #398 [hci1] 10.753394
Num handles: 1
Handle: 43
Count: 1
> ACL Data RX: Handle 43 flags 0x02 dlen 12 #399 [hci1] 10.756499
L2CAP: Disconnection Request (0x06) ident 26 len 4
Destination CID: 65
Source CID: 65
< ACL Data TX: Handle 43 flags 0x00 dlen 12 #400 [hci1] 10.756548
L2CAP: Disconnection Response (0x07) ident 26 len 4
Destination CID: 65
Source CID: 65
< ACL Data TX: Handle 43 flags 0x00 dlen 12 #401 [hci1] 10.757459
L2CAP: Connection Request (0x02) ident 18 len 4
PSM: 1 (0x0001)
Source CID: 65
> ACL Data RX: Handle 43 flags 0x02 dlen 12 #402 [hci1] 10.759148
L2CAP: Disconnection Response (0x07) ident 17 len 4
Destination CID: 65
Source CID: 65
= bluetoothd: 00:1E:AB:4C:56:54: error updating services: Input/o.. 10.759447
> HCI Event: Number of Completed Packets (0x13) plen 5 #403 [hci1] 10.759386
Num handles: 1
Handle: 43
Count: 1
> ACL Data RX: Handle 43 flags 0x02 dlen 12 #404 [hci1] 10.760397
L2CAP: Connection Request (0x02) ident 27 len 4
PSM: 3 (0x0003)
Source CID: 65
< ACL Data TX: Handle 43 flags 0x00 dlen 16 #405 [hci1] 10.760441
L2CAP: Connection Response (0x03) ident 27 len 8
Destination CID: 65
Source CID: 65
Result: Connection successful (0x0000)
Status: No further information available (0x0000)
< ACL Data TX: Handle 43 flags 0x00 dlen 27 #406 [hci1] 10.760449
L2CAP: Configure Request (0x04) ident 19 len 19
Destination CID: 65
Flags: 0x0000
Option: Maximum Transmission Unit (0x01) [mandatory]
MTU: 1013
Option: Retransmission and Flow Control (0x04) [mandatory]
Mode: Basic (0x00)
TX window size: 0
Max transmit: 0
Retransmission timeout: 0
Monitor timeout: 0
Maximum PDU size: 0
> HCI Event: Number of Completed Packets (0x13) plen 5 #407 [hci1] 10.761399
Num handles: 1
Handle: 43
Count: 1
> ACL Data RX: Handle 43 flags 0x02 dlen 16 #408 [hci1] 10.762942
L2CAP: Connection Response (0x03) ident 18 len 8
Destination CID: 66
Source CID: 65
Result: Connection successful (0x0000)
Status: No further information available (0x0000)
*snip*
Similar case after the patch:
*snip*
> ACL Data RX: Handle 43 flags 0x02 dlen 8 #22702 [hci0] 1664.411056
Channel: 65 len 4 [PSM 3 mode 0] {chan 3}
RFCOMM: Disconnect (DISC) (0x43)
Address: 0x03 cr 1 dlci 0x00
Control: 0x53 poll/final 1
Length: 0
FCS: 0xfd
< ACL Data TX: Handle 43 flags 0x00 dlen 8 #22703 [hci0] 1664.411136
Channel: 65 len 4 [PSM 3 mode 0] {chan 3}
RFCOMM: Unnumbered Ack (UA) (0x63)
Address: 0x03 cr 1 dlci 0x00
Control: 0x73 poll/final 1
Length: 0
FCS: 0xd7
< ACL Data TX: Handle 43 flags 0x00 dlen 12 #22704 [hci0] 1664.411143
L2CAP: Disconnection Request (0x06) ident 11 len 4
Destination CID: 65
Source CID: 65
> HCI Event: Number of Completed Pac.. (0x13) plen 5 #22705 [hci0] 1664.414009
Num handles: 1
Handle: 43
Count: 1
> HCI Event: Number of Completed Pac.. (0x13) plen 5 #22706 [hci0] 1664.415007
Num handles: 1
Handle: 43
Count: 1
> ACL Data RX: Handle 43 flags 0x02 dlen 12 #22707 [hci0] 1664.418674
L2CAP: Disconnection Request (0x06) ident 17 len 4
Destination CID: 65
Source CID: 65
< ACL Data TX: Handle 43 flags 0x00 dlen 12 #22708 [hci0] 1664.418762
L2CAP: Disconnection Response (0x07) ident 17 len 4
Destination CID: 65
Source CID: 65
< ACL Data TX: Handle 43 flags 0x00 dlen 12 #22709 [hci0] 1664.421073
L2CAP: Connection Request (0x02) ident 12 len 4
PSM: 1 (0x0001)
Source CID: 65
> ACL Data RX: Handle 43 flags 0x02 dlen 12 #22710 [hci0] 1664.421371
L2CAP: Disconnection Response (0x07) ident 11 len 4
Destination CID: 65
Source CID: 65
> HCI Event: Number of Completed Pac.. (0x13) plen 5 #22711 [hci0] 1664.424082
Num handles: 1
Handle: 43
Count: 1
> HCI Event: Number of Completed Pac.. (0x13) plen 5 #22712 [hci0] 1664.425040
Num handles: 1
Handle: 43
Count: 1
> ACL Data RX: Handle 43 flags 0x02 dlen 12 #22713 [hci0] 1664.426103
L2CAP: Connection Request (0x02) ident 18 len 4
PSM: 3 (0x0003)
Source CID: 65
< ACL Data TX: Handle 43 flags 0x00 dlen 16 #22714 [hci0] 1664.426186
L2CAP: Connection Response (0x03) ident 18 len 8
Destination CID: 66
Source CID: 65
Result: Connection successful (0x0000)
Status: No further information available (0x0000)
< ACL Data TX: Handle 43 flags 0x00 dlen 27 #22715 [hci0] 1664.426196
L2CAP: Configure Request (0x04) ident 13 len 19
Destination CID: 65
Flags: 0x0000
Option: Maximum Transmission Unit (0x01) [mandatory]
MTU: 1013
Option: Retransmission and Flow Control (0x04) [mandatory]
Mode: Basic (0x00)
TX window size: 0
Max transmit: 0
Retransmission timeout: 0
Monitor timeout: 0
Maximum PDU size: 0
> ACL Data RX: Handle 43 flags 0x02 dlen 16 #22716 [hci0] 1664.428804
L2CAP: Connection Response (0x03) ident 12 len 8
Destination CID: 66
Source CID: 65
Result: Connection successful (0x0000)
Status: No further information available (0x0000)
*snip*
Fix is to check that channel is in state BT_DISCONN before deleting the
channel.
This bug was found while fuzzing Bluez's OBEX implementation using
Synopsys Defensics.
Reported-by: Matti Kamunen <[email protected]>
Reported-by: Ari Timonen <[email protected]>
Signed-off-by: Matias Karhumaa <[email protected]>
Signed-off-by: Marcel Holtmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/bluetooth/l2cap_core.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 879d5432bf77..260ef5426e0c 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4384,6 +4384,12 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn,
l2cap_chan_lock(chan);
+ if (chan->state != BT_DISCONN) {
+ l2cap_chan_unlock(chan);
+ mutex_unlock(&conn->chan_lock);
+ return 0;
+ }
+
l2cap_chan_hold(chan);
l2cap_chan_del(chan, 0);
--
2.20.1
From: João Paulo Rechi Vita <[email protected]>
[ Upstream commit 44d34af2e4cfd0c5357182f8b43f3e0a1fe30a2e ]
Without the QCA ROME setup routine this adapter fails to establish a SCO
connection.
T: Bus=01 Lev=01 Prnt=01 Port=08 Cnt=01 Dev#= 2 Spd=12 MxCh= 0
D: Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs= 1
P: Vendor=13d3 ProdID=3491 Rev=00.01
C: #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA
I: If#=0x0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
I: If#=0x1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
Signed-off-by: João Paulo Rechi Vita <[email protected]>
Signed-off-by: Marcel Holtmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/bluetooth/btusb.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 40a4f95f6178..f494fa30a912 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -277,6 +277,7 @@ static const struct usb_device_id blacklist_table[] = {
{ USB_DEVICE(0x04ca, 0x3015), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x04ca, 0x3016), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x04ca, 0x301a), .driver_info = BTUSB_QCA_ROME },
+ { USB_DEVICE(0x13d3, 0x3491), .driver_info = BTUSB_QCA_ROME },
{ USB_DEVICE(0x13d3, 0x3496), .driver_info = BTUSB_QCA_ROME },
/* Broadcom BCM2035 */
--
2.20.1
From: Taehee Yoo <[email protected]>
[ Upstream commit a2bed90704c68d3763bf24decb1b781a45395de8 ]
Current gtp_newlink() could be called after unregister_pernet_subsys().
gtp_newlink() uses gtp_net but it can be destroyed by
unregister_pernet_subsys().
So unregister_pernet_subsys() should be called after
rtnl_link_unregister().
Test commands:
#SHELL 1
while :
do
for i in {1..5}
do
./gtp-link add gtp$i &
done
killall gtp-link
done
#SHELL 2
while :
do
modprobe -rv gtp
done
Splat looks like:
[ 753.176631] BUG: KASAN: use-after-free in gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.177722] Read of size 8 at addr ffff8880d48f2458 by task gtp-link/7126
[ 753.179082] CPU: 0 PID: 7126 Comm: gtp-link Tainted: G W 5.2.0-rc6+ #50
[ 753.185801] Call Trace:
[ 753.186264] dump_stack+0x7c/0xbb
[ 753.186863] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.187583] print_address_description+0xc7/0x240
[ 753.188382] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.189097] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.189846] __kasan_report+0x12a/0x16f
[ 753.190542] ? gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.191298] kasan_report+0xe/0x20
[ 753.191893] gtp_newlink+0x9b4/0xa5c [gtp]
[ 753.192580] ? __netlink_ns_capable+0xc3/0xf0
[ 753.193370] __rtnl_newlink+0xb9f/0x11b0
[ ... ]
[ 753.241201] Allocated by task 7186:
[ 753.241844] save_stack+0x19/0x80
[ 753.242399] __kasan_kmalloc.constprop.3+0xa0/0xd0
[ 753.243192] __kmalloc+0x13e/0x300
[ 753.243764] ops_init+0xd6/0x350
[ 753.244314] register_pernet_operations+0x249/0x6f0
[ ... ]
[ 753.251770] Freed by task 7178:
[ 753.252288] save_stack+0x19/0x80
[ 753.252833] __kasan_slab_free+0x111/0x150
[ 753.253962] kfree+0xc7/0x280
[ 753.254509] ops_free_list.part.11+0x1c4/0x2d0
[ 753.255241] unregister_pernet_operations+0x262/0x390
[ ... ]
[ 753.285883] list_add corruption. next->prev should be prev (ffff8880d48f2458), but was ffff8880d497d878. (next.
[ 753.287241] ------------[ cut here ]------------
[ 753.287794] kernel BUG at lib/list_debug.c:25!
[ 753.288364] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 753.289099] CPU: 0 PID: 7126 Comm: gtp-link Tainted: G B W 5.2.0-rc6+ #50
[ 753.291036] RIP: 0010:__list_add_valid+0x74/0xd0
[ 753.291589] Code: 48 39 da 75 27 48 39 f5 74 36 48 39 dd 74 31 48 83 c4 08 b8 01 00 00 00 5b 5d c3 48 89 d9 48b
[ 753.293779] RSP: 0018:ffff8880cae8f398 EFLAGS: 00010286
[ 753.294401] RAX: 0000000000000075 RBX: ffff8880d497d878 RCX: 0000000000000000
[ 753.296260] RDX: 0000000000000075 RSI: 0000000000000008 RDI: ffffed10195d1e69
[ 753.297070] RBP: ffff8880cd250ae0 R08: ffffed101b4bff21 R09: ffffed101b4bff21
[ 753.297899] R10: 0000000000000001 R11: ffffed101b4bff20 R12: ffff8880d497d878
[ 753.298703] R13: 0000000000000000 R14: ffff8880cd250ae0 R15: ffff8880d48f2458
[ 753.299564] FS: 00007f5f79805740(0000) GS:ffff8880da400000(0000) knlGS:0000000000000000
[ 753.300533] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 753.301231] CR2: 00007fe8c7ef4f10 CR3: 00000000b71a6006 CR4: 00000000000606f0
[ 753.302183] Call Trace:
[ 753.302530] gtp_newlink+0x5f6/0xa5c [gtp]
[ 753.303037] ? __netlink_ns_capable+0xc3/0xf0
[ 753.303576] __rtnl_newlink+0xb9f/0x11b0
[ 753.304092] ? rtnl_link_unregister+0x230/0x230
Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/gtp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 61e9b288d2dc..d178d5bad7e4 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1385,9 +1385,9 @@ late_initcall(gtp_init);
static void __exit gtp_fini(void)
{
- unregister_pernet_subsys(>p_net_ops);
genl_unregister_family(>p_genl_family);
rtnl_link_unregister(>p_link_ops);
+ unregister_pernet_subsys(>p_net_ops);
pr_info("GTP module unloaded\n");
}
--
2.20.1
From: Phong Tran <[email protected]>
[ Upstream commit 78226f6eaac80bf30256a33a4926c194ceefdf36 ]
This is for fixing bug KMSAN: uninit-value in ax88772_bind
Tested by
https://groups.google.com/d/msg/syzkaller-bugs/aFQurGotng4/eB_HlNhhCwAJ
Reported-by: [email protected]
syzbot found the following crash on:
HEAD commit: f75e4cfe kmsan: use kmsan_handle_urb() in urb.c
git tree: kmsan
console output: https://syzkaller.appspot.com/x/log.txt?x=136d720ea00000
kernel config:
https://syzkaller.appspot.com/x/.config?x=602468164ccdc30a
dashboard link:
https://syzkaller.appspot.com/bug?extid=8a3fc6674bbc3978ed4e
compiler: clang version 9.0.0 (/home/glider/llvm/clang
06d00afa61eef8f7f501ebdb4e8612ea43ec2d78)
syz repro:
https://syzkaller.appspot.com/x/repro.syz?x=12788316a00000
C reproducer: https://syzkaller.appspot.com/x/repro.c?x=120359aaa00000
==================================================================
BUG: KMSAN: uninit-value in is_valid_ether_addr
include/linux/etherdevice.h:200 [inline]
BUG: KMSAN: uninit-value in asix_set_netdev_dev_addr
drivers/net/usb/asix_devices.c:73 [inline]
BUG: KMSAN: uninit-value in ax88772_bind+0x93d/0x11e0
drivers/net/usb/asix_devices.c:724
CPU: 0 PID: 3348 Comm: kworker/0:2 Not tainted 5.1.0+ #1
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
Google 01/01/2011
Workqueue: usb_hub_wq hub_event
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0x191/0x1f0 lib/dump_stack.c:113
kmsan_report+0x130/0x2a0 mm/kmsan/kmsan.c:622
__msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:310
is_valid_ether_addr include/linux/etherdevice.h:200 [inline]
asix_set_netdev_dev_addr drivers/net/usb/asix_devices.c:73 [inline]
ax88772_bind+0x93d/0x11e0 drivers/net/usb/asix_devices.c:724
usbnet_probe+0x10f5/0x3940 drivers/net/usb/usbnet.c:1728
usb_probe_interface+0xd66/0x1320 drivers/usb/core/driver.c:361
really_probe+0xdae/0x1d80 drivers/base/dd.c:513
driver_probe_device+0x1b3/0x4f0 drivers/base/dd.c:671
__device_attach_driver+0x5b8/0x790 drivers/base/dd.c:778
bus_for_each_drv+0x28e/0x3b0 drivers/base/bus.c:454
__device_attach+0x454/0x730 drivers/base/dd.c:844
device_initial_probe+0x4a/0x60 drivers/base/dd.c:891
bus_probe_device+0x137/0x390 drivers/base/bus.c:514
device_add+0x288d/0x30e0 drivers/base/core.c:2106
usb_set_configuration+0x30dc/0x3750 drivers/usb/core/message.c:2027
generic_probe+0xe7/0x280 drivers/usb/core/generic.c:210
usb_probe_device+0x14c/0x200 drivers/usb/core/driver.c:266
really_probe+0xdae/0x1d80 drivers/base/dd.c:513
driver_probe_device+0x1b3/0x4f0 drivers/base/dd.c:671
__device_attach_driver+0x5b8/0x790 drivers/base/dd.c:778
bus_for_each_drv+0x28e/0x3b0 drivers/base/bus.c:454
__device_attach+0x454/0x730 drivers/base/dd.c:844
device_initial_probe+0x4a/0x60 drivers/base/dd.c:891
bus_probe_device+0x137/0x390 drivers/base/bus.c:514
device_add+0x288d/0x30e0 drivers/base/core.c:2106
usb_new_device+0x23e5/0x2ff0 drivers/usb/core/hub.c:2534
hub_port_connect drivers/usb/core/hub.c:5089 [inline]
hub_port_connect_change drivers/usb/core/hub.c:5204 [inline]
port_event drivers/usb/core/hub.c:5350 [inline]
hub_event+0x48d1/0x7290 drivers/usb/core/hub.c:5432
process_one_work+0x1572/0x1f00 kernel/workqueue.c:2269
process_scheduled_works kernel/workqueue.c:2331 [inline]
worker_thread+0x189c/0x2460 kernel/workqueue.c:2417
kthread+0x4b5/0x4f0 kernel/kthread.c:254
ret_from_fork+0x35/0x40 arch/x86/entry/entry_64.S:355
Signed-off-by: Phong Tran <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/usb/asix_devices.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 3d93993e74da..2eca4168af2f 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -238,7 +238,7 @@ static void asix_phy_reset(struct usbnet *dev, unsigned int reset_bits)
static int ax88172_bind(struct usbnet *dev, struct usb_interface *intf)
{
int ret = 0;
- u8 buf[ETH_ALEN];
+ u8 buf[ETH_ALEN] = {0};
int i;
unsigned long gpio_bits = dev->driver_info->data;
@@ -689,7 +689,7 @@ static int asix_resume(struct usb_interface *intf)
static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
{
int ret, i;
- u8 buf[ETH_ALEN], chipcode = 0;
+ u8 buf[ETH_ALEN] = {0}, chipcode = 0;
u32 phyid;
struct asix_common_private *priv;
@@ -1073,7 +1073,7 @@ static const struct net_device_ops ax88178_netdev_ops = {
static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf)
{
int ret;
- u8 buf[ETH_ALEN];
+ u8 buf[ETH_ALEN] = {0};
usbnet_get_endpoints(dev,intf);
--
2.20.1
From: Josua Mayer <[email protected]>
[ Upstream commit 433a06d7d74e677c40b1148c70c48677ff62fb6b ]
Defer probing of the orion-mdio interface when getting a clock returns
EPROBE_DEFER. This avoids locking up the Armada 8k SoC when mdio is used
before all clocks have been enabled.
Signed-off-by: Josua Mayer <[email protected]>
Reviewed-by: Andrew Lunn <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/marvell/mvmdio.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index c5dac6bd2be4..903836e334d8 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -321,6 +321,10 @@ static int orion_mdio_probe(struct platform_device *pdev)
for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
dev->clk[i] = of_clk_get(pdev->dev.of_node, i);
+ if (PTR_ERR(dev->clk[i]) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto out_clk;
+ }
if (IS_ERR(dev->clk[i]))
break;
clk_prepare_enable(dev->clk[i]);
@@ -362,6 +366,7 @@ static int orion_mdio_probe(struct platform_device *pdev)
if (dev->err_interrupt > 0)
writel(0, dev->regs + MVMDIO_ERR_INT_MASK);
+out_clk:
for (i = 0; i < ARRAY_SIZE(dev->clk); i++) {
if (IS_ERR(dev->clk[i]))
break;
--
2.20.1
From: Andi Kleen <[email protected]>
[ Upstream commit 145c407c808352acd625be793396fd4f33c794f8 ]
After setting up metric groups through the event parser, the metricgroup
code looks them up again in the event list.
Make sure we only look up events that haven't been used by some other
metric. The data structures currently cannot handle more than one metric
per event. This avoids problems with multiple events partially
overlapping.
Signed-off-by: Andi Kleen <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Kan Liang <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/util/stat-shadow.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 99990f5f2512..bbb0e042d8e5 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -303,7 +303,7 @@ static struct perf_evsel *perf_stat__find_event(struct perf_evlist *evsel_list,
struct perf_evsel *c2;
evlist__for_each_entry (evsel_list, c2) {
- if (!strcasecmp(c2->name, name))
+ if (!strcasecmp(c2->name, name) && !c2->collect_stat)
return c2;
}
return NULL;
@@ -342,7 +342,8 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
if (leader) {
/* Search in group */
for_each_group_member (oc, leader) {
- if (!strcasecmp(oc->name, metric_names[i])) {
+ if (!strcasecmp(oc->name, metric_names[i]) &&
+ !oc->collect_stat) {
found = true;
break;
}
--
2.20.1
From: Jiri Benc <[email protected]>
[ Upstream commit 11aca65ec4db09527d3e9b6b41a0615b7da4386b ]
Selftests are reporting this failure in test_lwt_seg6local.sh:
+ ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2
Error fetching program/map!
Failed to parse eBPF program: Operation not permitted
The problem is __attribute__((always_inline)) alone is not enough to prevent
clang from inserting those functions in .text. In that case, .text is not
marked as relocateable.
See the output of objdump -h test_lwt_seg6local.o:
Idx Name Size VMA LMA File off Algn
0 .text 00003530 0000000000000000 0000000000000000 00000040 2**3
CONTENTS, ALLOC, LOAD, READONLY, CODE
This causes the iproute bpf loader to fail in bpf_fetch_prog_sec:
bpf_has_call_data returns true but bpf_fetch_prog_relo fails as there's no
relocateable .text section in the file.
To fix this, convert to 'static __always_inline'.
v2: Use 'static __always_inline' instead of 'static inline
__attribute__((always_inline))'
Fixes: c99a84eac026 ("selftests/bpf: test for seg6local End.BPF action")
Signed-off-by: Jiri Benc <[email protected]>
Acked-by: Yonghong Song <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/testing/selftests/bpf/test_lwt_seg6local.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.c b/tools/testing/selftests/bpf/test_lwt_seg6local.c
index 0575751bc1bc..e2f6ed0a583d 100644
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.c
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.c
@@ -61,7 +61,7 @@ struct sr6_tlv_t {
unsigned char value[0];
} BPF_PACKET_HEADER;
-__attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
+static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb)
{
void *cursor, *data_end;
struct ip6_srh_t *srh;
@@ -95,7 +95,7 @@ __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
return srh;
}
-__attribute__((always_inline))
+static __always_inline
int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
uint32_t old_pad, uint32_t pad_off)
{
@@ -125,7 +125,7 @@ int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
return 0;
}
-__attribute__((always_inline))
+static __always_inline
int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
uint32_t *tlv_off, uint32_t *pad_size,
uint32_t *pad_off)
@@ -184,7 +184,7 @@ int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
return 0;
}
-__attribute__((always_inline))
+static __always_inline
int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
struct sr6_tlv_t *itlv, uint8_t tlv_size)
{
@@ -228,7 +228,7 @@ int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
return update_tlv_pad(skb, new_pad, pad_size, pad_off);
}
-__attribute__((always_inline))
+static __always_inline
int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
uint32_t tlv_off)
{
@@ -266,7 +266,7 @@ int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
return update_tlv_pad(skb, new_pad, pad_size, pad_off);
}
-__attribute__((always_inline))
+static __always_inline
int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh)
{
int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) +
--
2.20.1
From: Leo Yan <[email protected]>
[ Upstream commit 33bae185f74d49a0d7b1bfaafb8e959efce0f243 ]
Based on the following report from Smatch, fix the potential NULL
pointer dereference check:
tools/lib/bpf/libbpf.c:3493
bpf_prog_load_xattr() warn: variable dereferenced before check 'attr'
(see line 3483)
3479 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
3480 struct bpf_object **pobj, int *prog_fd)
3481 {
3482 struct bpf_object_open_attr open_attr = {
3483 .file = attr->file,
3484 .prog_type = attr->prog_type,
^^^^^^
3485 };
At the head of function, it directly access 'attr' without checking
if it's NULL pointer. This patch moves the values assignment after
validating 'attr' and 'attr->file'.
Signed-off-by: Leo Yan <[email protected]>
Acked-by: Yonghong Song <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/lib/bpf/libbpf.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index bdb94939fd60..a350f97e3a1a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2293,10 +2293,7 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
struct bpf_object **pobj, int *prog_fd)
{
- struct bpf_object_open_attr open_attr = {
- .file = attr->file,
- .prog_type = attr->prog_type,
- };
+ struct bpf_object_open_attr open_attr = {};
struct bpf_program *prog, *first_prog = NULL;
enum bpf_attach_type expected_attach_type;
enum bpf_prog_type prog_type;
@@ -2309,6 +2306,9 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
if (!attr->file)
return -EINVAL;
+ open_attr.file = attr->file;
+ open_attr.prog_type = attr->prog_type;
+
obj = bpf_object__open_xattr(&open_attr);
if (IS_ERR_OR_NULL(obj))
return -ENOENT;
--
2.20.1
From: Geert Uytterhoeven <[email protected]>
[ Upstream commit 3285170f28a850638794cdfe712eb6d93e51e706 ]
Commit 372e722ea4dd4ca1 ("gpiolib: use descriptors internally") renamed
the functions to use a "gpiod" prefix, and commit 79a9becda8940deb
("gpiolib: export descriptor-based GPIO interface") introduced the "raw"
variants, but both changes forgot to update the comments.
Readd a similar reference to gpiod_set_value(), which was accidentally
removed by commit 1e77fc82110ac36f ("gpio: Add missing open drain/source
handling to gpiod_set_value_cansleep()").
Signed-off-by: Geert Uytterhoeven <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Linus Walleij <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/gpio/gpiolib.c | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index fd713326dcfc..4a48c7c47709 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2877,7 +2877,7 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep,
int gpiod_get_raw_value(const struct gpio_desc *desc)
{
VALIDATE_DESC(desc);
- /* Should be using gpio_get_value_cansleep() */
+ /* Should be using gpiod_get_raw_value_cansleep() */
WARN_ON(desc->gdev->chip->can_sleep);
return gpiod_get_raw_value_commit(desc);
}
@@ -2898,7 +2898,7 @@ int gpiod_get_value(const struct gpio_desc *desc)
int value;
VALIDATE_DESC(desc);
- /* Should be using gpio_get_value_cansleep() */
+ /* Should be using gpiod_get_value_cansleep() */
WARN_ON(desc->gdev->chip->can_sleep);
value = gpiod_get_raw_value_commit(desc);
@@ -3123,7 +3123,7 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep,
void gpiod_set_raw_value(struct gpio_desc *desc, int value)
{
VALIDATE_DESC_VOID(desc);
- /* Should be using gpiod_set_value_cansleep() */
+ /* Should be using gpiod_set_raw_value_cansleep() */
WARN_ON(desc->gdev->chip->can_sleep);
gpiod_set_raw_value_commit(desc, value);
}
@@ -3164,6 +3164,7 @@ static void gpiod_set_value_nocheck(struct gpio_desc *desc, int value)
void gpiod_set_value(struct gpio_desc *desc, int value)
{
VALIDATE_DESC_VOID(desc);
+ /* Should be using gpiod_set_value_cansleep() */
WARN_ON(desc->gdev->chip->can_sleep);
gpiod_set_value_nocheck(desc, value);
}
--
2.20.1
From: Taehee Yoo <[email protected]>
[ Upstream commit 3f167e1921865b379a9becf03828e7202c7b4917 ]
ipv4_pdp_add() is called in RCU read-side critical section.
So GFP_KERNEL should not be used in the function.
This patch make ipv4_pdp_add() to use GFP_ATOMIC instead of GFP_KERNEL.
Test commands:
gtp-link add gtp1 &
gtp-tunnel add gtp1 v1 100 200 1.1.1.1 2.2.2.2
Splat looks like:
[ 130.618881] =============================
[ 130.626382] WARNING: suspicious RCU usage
[ 130.626994] 5.2.0-rc6+ #50 Not tainted
[ 130.627622] -----------------------------
[ 130.628223] ./include/linux/rcupdate.h:266 Illegal context switch in RCU read-side critical section!
[ 130.629684]
[ 130.629684] other info that might help us debug this:
[ 130.629684]
[ 130.631022]
[ 130.631022] rcu_scheduler_active = 2, debug_locks = 1
[ 130.632136] 4 locks held by gtp-tunnel/1025:
[ 130.632925] #0: 000000002b93c8b7 (cb_lock){++++}, at: genl_rcv+0x15/0x40
[ 130.634159] #1: 00000000f17bc999 (genl_mutex){+.+.}, at: genl_rcv_msg+0xfb/0x130
[ 130.635487] #2: 00000000c644ed8e (rtnl_mutex){+.+.}, at: gtp_genl_new_pdp+0x18c/0x1150 [gtp]
[ 130.636936] #3: 0000000007a1cde7 (rcu_read_lock){....}, at: gtp_genl_new_pdp+0x187/0x1150 [gtp]
[ 130.638348]
[ 130.638348] stack backtrace:
[ 130.639062] CPU: 1 PID: 1025 Comm: gtp-tunnel Not tainted 5.2.0-rc6+ #50
[ 130.641318] Call Trace:
[ 130.641707] dump_stack+0x7c/0xbb
[ 130.642252] ___might_sleep+0x2c0/0x3b0
[ 130.642862] kmem_cache_alloc_trace+0x1cd/0x2b0
[ 130.643591] gtp_genl_new_pdp+0x6c5/0x1150 [gtp]
[ 130.644371] genl_family_rcv_msg+0x63a/0x1030
[ 130.645074] ? mutex_lock_io_nested+0x1090/0x1090
[ 130.645845] ? genl_unregister_family+0x630/0x630
[ 130.646592] ? debug_show_all_locks+0x2d0/0x2d0
[ 130.647293] ? check_flags.part.40+0x440/0x440
[ 130.648099] genl_rcv_msg+0xa3/0x130
[ ... ]
Fixes: 459aa660eb1d ("gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)")
Signed-off-by: Taehee Yoo <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/gtp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index f45a806b6c06..6f1ad7ccaea6 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -958,7 +958,7 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
}
- pctx = kmalloc(sizeof(struct pdp_ctx), GFP_KERNEL);
+ pctx = kmalloc(sizeof(*pctx), GFP_ATOMIC);
if (pctx == NULL)
return -ENOMEM;
--
2.20.1
From: Taehee Yoo <[email protected]>
[ Upstream commit e198987e7dd7d3645a53875151cd6f8fc425b706 ]
gtp_encap_enable_socket() and gtp_encap_destroy() are not protected
by rcu_read_lock(). and it's not safe to write sk->sk_user_data.
This patch make these functions to use lock_sock() instead of
rcu_dereference_sk_user_data().
Test commands:
gtp-link add gtp1
Splat looks like:
[ 83.238315] =============================
[ 83.239127] WARNING: suspicious RCU usage
[ 83.239702] 5.2.0-rc6+ #49 Not tainted
[ 83.240268] -----------------------------
[ 83.241205] drivers/net/gtp.c:799 suspicious rcu_dereference_check() usage!
[ 83.243828]
[ 83.243828] other info that might help us debug this:
[ 83.243828]
[ 83.246325]
[ 83.246325] rcu_scheduler_active = 2, debug_locks = 1
[ 83.247314] 1 lock held by gtp-link/1008:
[ 83.248523] #0: 0000000017772c7f (rtnl_mutex){+.+.}, at: __rtnl_newlink+0x5f5/0x11b0
[ 83.251503]
[ 83.251503] stack backtrace:
[ 83.252173] CPU: 0 PID: 1008 Comm: gtp-link Not tainted 5.2.0-rc6+ #49
[ 83.253271] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 83.254562] Call Trace:
[ 83.254995] dump_stack+0x7c/0xbb
[ 83.255567] gtp_encap_enable_socket+0x2df/0x360 [gtp]
[ 83.256415] ? gtp_find_dev+0x1a0/0x1a0 [gtp]
[ 83.257161] ? memset+0x1f/0x40
[ 83.257843] gtp_newlink+0x90/0xa21 [gtp]
[ 83.258497] ? __netlink_ns_capable+0xc3/0xf0
[ 83.259260] __rtnl_newlink+0xb9f/0x11b0
[ 83.260022] ? rtnl_link_unregister+0x230/0x230
[ ... ]
Fixes: 1e3a3abd8b28 ("gtp: make GTP sockets in gtp_newlink optional")
Signed-off-by: Taehee Yoo <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/gtp.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 83488f2bf7a0..f45a806b6c06 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -293,12 +293,14 @@ static void gtp_encap_destroy(struct sock *sk)
{
struct gtp_dev *gtp;
- gtp = rcu_dereference_sk_user_data(sk);
+ lock_sock(sk);
+ gtp = sk->sk_user_data;
if (gtp) {
udp_sk(sk)->encap_type = 0;
rcu_assign_sk_user_data(sk, NULL);
sock_put(sk);
}
+ release_sock(sk);
}
static void gtp_encap_disable_sock(struct sock *sk)
@@ -800,7 +802,8 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
goto out_sock;
}
- if (rcu_dereference_sk_user_data(sock->sk)) {
+ lock_sock(sock->sk);
+ if (sock->sk->sk_user_data) {
sk = ERR_PTR(-EBUSY);
goto out_sock;
}
@@ -816,6 +819,7 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
setup_udp_tunnel_sock(sock_net(sock->sk), sock, &tuncfg);
out_sock:
+ release_sock(sock->sk);
sockfd_put(sock);
return sk;
}
--
2.20.1
From: Taehee Yoo <[email protected]>
[ Upstream commit 1788b8569f5de27da09087fa3f6580d2aa04cc75 ]
gtp_encap_destroy() is called twice.
1. When interface is deleted.
2. When udp socket is destroyed.
either gtp->sk0 or gtp->sk1u could be freed by sock_put() in
gtp_encap_destroy(). so, when gtp_encap_destroy() is called again,
it would uses freed sk pointer.
patch makes gtp_encap_destroy() to set either gtp->sk0 or gtp->sk1u to
null. in addition, both gtp->sk0 and gtp->sk1u pointer are protected
by rtnl_lock. so, rtnl_lock() is added.
Test command:
gtp-link add gtp1 &
killall gtp-link
ip link del gtp1
Splat looks like:
[ 83.182767] BUG: KASAN: use-after-free in __lock_acquire+0x3a20/0x46a0
[ 83.184128] Read of size 8 at addr ffff8880cc7d5360 by task ip/1008
[ 83.185567] CPU: 1 PID: 1008 Comm: ip Not tainted 5.2.0-rc6+ #50
[ 83.188469] Call Trace:
[ ... ]
[ 83.200126] lock_acquire+0x141/0x380
[ 83.200575] ? lock_sock_nested+0x3a/0xf0
[ 83.201069] _raw_spin_lock_bh+0x38/0x70
[ 83.201551] ? lock_sock_nested+0x3a/0xf0
[ 83.202044] lock_sock_nested+0x3a/0xf0
[ 83.202520] gtp_encap_destroy+0x18/0xe0 [gtp]
[ 83.203065] gtp_encap_disable.isra.14+0x13/0x50 [gtp]
[ 83.203687] gtp_dellink+0x56/0x170 [gtp]
[ 83.204190] rtnl_delete_link+0xb4/0x100
[ ... ]
[ 83.236513] Allocated by task 976:
[ 83.236925] save_stack+0x19/0x80
[ 83.237332] __kasan_kmalloc.constprop.3+0xa0/0xd0
[ 83.237894] kmem_cache_alloc+0xd8/0x280
[ 83.238360] sk_prot_alloc.isra.42+0x50/0x200
[ 83.238874] sk_alloc+0x32/0x940
[ 83.239264] inet_create+0x283/0xc20
[ 83.239684] __sock_create+0x2dd/0x540
[ 83.240136] __sys_socket+0xca/0x1a0
[ 83.240550] __x64_sys_socket+0x6f/0xb0
[ 83.240998] do_syscall_64+0x9c/0x450
[ 83.241466] entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 83.242061]
[ 83.242249] Freed by task 0:
[ 83.242616] save_stack+0x19/0x80
[ 83.243013] __kasan_slab_free+0x111/0x150
[ 83.243498] kmem_cache_free+0x89/0x250
[ 83.244444] __sk_destruct+0x38f/0x5a0
[ 83.245366] rcu_core+0x7e9/0x1c20
[ 83.245766] __do_softirq+0x213/0x8fa
Fixes: 1e3a3abd8b28 ("gtp: make GTP sockets in gtp_newlink optional")
Signed-off-by: Taehee Yoo <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/gtp.c | 17 +++++++++++++++--
1 file changed, 15 insertions(+), 2 deletions(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 6f1ad7ccaea6..61e9b288d2dc 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -289,13 +289,17 @@ static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb)
return gtp_rx(pctx, skb, hdrlen, gtp->role);
}
-static void gtp_encap_destroy(struct sock *sk)
+static void __gtp_encap_destroy(struct sock *sk)
{
struct gtp_dev *gtp;
lock_sock(sk);
gtp = sk->sk_user_data;
if (gtp) {
+ if (gtp->sk0 == sk)
+ gtp->sk0 = NULL;
+ else
+ gtp->sk1u = NULL;
udp_sk(sk)->encap_type = 0;
rcu_assign_sk_user_data(sk, NULL);
sock_put(sk);
@@ -303,12 +307,19 @@ static void gtp_encap_destroy(struct sock *sk)
release_sock(sk);
}
+static void gtp_encap_destroy(struct sock *sk)
+{
+ rtnl_lock();
+ __gtp_encap_destroy(sk);
+ rtnl_unlock();
+}
+
static void gtp_encap_disable_sock(struct sock *sk)
{
if (!sk)
return;
- gtp_encap_destroy(sk);
+ __gtp_encap_destroy(sk);
}
static void gtp_encap_disable(struct gtp_dev *gtp)
@@ -1047,6 +1058,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
return -EINVAL;
}
+ rtnl_lock();
rcu_read_lock();
gtp = gtp_find_dev(sock_net(skb->sk), info->attrs);
@@ -1071,6 +1083,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
out_unlock:
rcu_read_unlock();
+ rtnl_unlock();
return err;
}
--
2.20.1
From: Taehee Yoo <[email protected]>
[ Upstream commit e30155fd23c9c141cbe7d99b786e10a83a328837 ]
If an invalid role is sent from user space, gtp_encap_enable() will fail.
Then, it should call gtp_encap_disable_sock() but current code doesn't.
It makes memory leak.
Fixes: 91ed81f9abc7 ("gtp: support SGSN-side tunnels")
Signed-off-by: Taehee Yoo <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/gtp.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 7a145172d503..83488f2bf7a0 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -847,8 +847,13 @@ static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[])
if (data[IFLA_GTP_ROLE]) {
role = nla_get_u32(data[IFLA_GTP_ROLE]);
- if (role > GTP_ROLE_SGSN)
+ if (role > GTP_ROLE_SGSN) {
+ if (sk0)
+ gtp_encap_disable_sock(sk0);
+ if (sk1u)
+ gtp_encap_disable_sock(sk1u);
return -EINVAL;
+ }
}
gtp->sk0 = sk0;
--
2.20.1
From: David Howells <[email protected]>
[ Upstream commit 99f0eae653b2db64917d0b58099eb51e300b311d ]
If the rxrpc_eproto tracepoint is enabled, an oops will be cause by the
trace line that rxrpc_extract_header() tries to emit when a protocol error
occurs (typically because the packet is short) because the call argument is
NULL.
Fix this by using ?: to assume 0 as the debug_id if call is NULL.
This can then be induced by:
echo -e '\0\0\0\0\0\0\0\0' | ncat -4u --send-only <addr> 20001
where addr has the following program running on it:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/socket.h>
#include <arpa/inet.h>
#include <linux/rxrpc.h>
int main(void)
{
struct sockaddr_rxrpc srx;
int fd;
memset(&srx, 0, sizeof(srx));
srx.srx_family = AF_RXRPC;
srx.srx_service = 0;
srx.transport_type = AF_INET;
srx.transport_len = sizeof(srx.transport.sin);
srx.transport.sin.sin_family = AF_INET;
srx.transport.sin.sin_port = htons(0x4e21);
fd = socket(AF_RXRPC, SOCK_DGRAM, AF_INET6);
bind(fd, (struct sockaddr *)&srx, sizeof(srx));
sleep(20);
return 0;
}
It results in the following oops.
BUG: kernel NULL pointer dereference, address: 0000000000000340
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
...
RIP: 0010:trace_event_raw_event_rxrpc_rx_eproto+0x47/0xac
...
Call Trace:
<IRQ>
rxrpc_extract_header+0x86/0x171
? rcu_read_lock_sched_held+0x5d/0x63
? rxrpc_new_skb+0xd4/0x109
rxrpc_input_packet+0xef/0x14fc
? rxrpc_input_data+0x986/0x986
udp_queue_rcv_one_skb+0xbf/0x3d0
udp_unicast_rcv_skb.isra.8+0x64/0x71
ip_protocol_deliver_rcu+0xe4/0x1b4
ip_local_deliver+0xf0/0x154
__netif_receive_skb_one_core+0x50/0x6c
netif_receive_skb_internal+0x26b/0x2e9
napi_gro_receive+0xf8/0x1da
rtl8169_poll+0x303/0x4c4
net_rx_action+0x10e/0x333
__do_softirq+0x1a5/0x38f
irq_exit+0x54/0xc4
do_IRQ+0xda/0xf8
common_interrupt+0xf/0xf
</IRQ>
...
? cpuidle_enter_state+0x23c/0x34d
cpuidle_enter+0x2a/0x36
do_idle+0x163/0x1ea
cpu_startup_entry+0x1d/0x1f
start_secondary+0x157/0x172
secondary_startup_64+0xa4/0xb0
Fixes: a25e21f0bcd2 ("rxrpc, afs: Use debug_ids rather than pointers in traces")
Signed-off-by: David Howells <[email protected]>
Reviewed-by: Marc Dionne <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
include/trace/events/rxrpc.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 6d182746afab..147546e0c11b 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1381,7 +1381,7 @@ TRACE_EVENT(rxrpc_rx_eproto,
),
TP_fast_assign(
- __entry->call = call->debug_id;
+ __entry->call = call ? call->debug_id : 0;
__entry->serial = serial;
__entry->why = why;
),
--
2.20.1
From: Seeteena Thoufeek <[email protected]>
[ Upstream commit bff5a556c149804de29347a88a884d25e4e4e3a2 ]
'probe libc's inet_pton & backtrace it with ping' testcase sometimes
fails on powerpc because distro ping binary does not have symbol
information and thus it prints "[unknown]" function name in the
backtrace.
Accept "[unknown]" as valid function name for powerpc as well.
# perf test -v "probe libc's inet_pton & backtrace it with ping"
Before:
59: probe libc's inet_pton & backtrace it with ping :
--- start ---
test child forked, pid 79695
ping 79718 [077] 96483.787025: probe_libc:inet_pton: (7fff83a754c8)
7fff83a754c8 __GI___inet_pton+0x8 (/usr/lib64/power9/libc-2.28.so)
7fff83a2b7a0 gaih_inet.constprop.7+0x1020
(/usr/lib64/power9/libc-2.28.so)
7fff83a2c170 getaddrinfo+0x160 (/usr/lib64/power9/libc-2.28.so)
1171830f4 [unknown] (/usr/bin/ping)
FAIL: expected backtrace entry
".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
got "1171830f4 [unknown] (/usr/bin/ping)"
test child finished with -1
---- end ----
probe libc's inet_pton & backtrace it with ping: FAILED!
After:
59: probe libc's inet_pton & backtrace it with ping :
--- start ---
test child forked, pid 79085
ping 79108 [045] 96400.214177: probe_libc:inet_pton: (7fffbb9654c8)
7fffbb9654c8 __GI___inet_pton+0x8 (/usr/lib64/power9/libc-2.28.so)
7fffbb91b7a0 gaih_inet.constprop.7+0x1020
(/usr/lib64/power9/libc-2.28.so)
7fffbb91c170 getaddrinfo+0x160 (/usr/lib64/power9/libc-2.28.so)
132e830f4 [unknown] (/usr/bin/ping)
test child finished with 0
---- end ----
probe libc's inet_pton & backtrace it with ping: Ok
Signed-off-by: Seeteena Thoufeek <[email protected]>
Reviewed-by: Kim Phillips <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Hendrik Brueckner <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Michael Petlan <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Sandipan Das <[email protected]>
Fixes: 1632936480a5 ("perf tests: Fix record+probe_libc_inet_pton.sh without ping's debuginfo")
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index cab7b0aea6ea..f5837f28f3af 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -43,7 +43,7 @@ trace_libc_inet_pton_backtrace() {
eventattr='max-stack=4'
echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
- echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+ echo ".*(\+0x[[:xdigit:]]+|\[unknown\])[[:space:]]\(.*/bin/ping.*\)$" >> $expected
;;
*)
eventattr='max-stack=3'
--
2.20.1
From: Julian Anastasov <[email protected]>
[ Upstream commit 5db7c8b9f9fc2aeec671ae3ca6375752c162e0e7 ]
syzkaller reports for memory leak in start_sync_thread [1]
As Eric points out, kthread may start and stop before the
threadfn function is called, so there is no chance the
data (tinfo in our case) to be released in thread.
Fix this by releasing tinfo in the controlling code instead.
[1]
BUG: memory leak
unreferenced object 0xffff8881206bf700 (size 32):
comm "syz-executor761", pid 7268, jiffies 4294943441 (age 20.470s)
hex dump (first 32 bytes):
00 40 7c 09 81 88 ff ff 80 45 b8 21 81 88 ff ff .@|......E.!....
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace:
[<0000000057619e23>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline]
[<0000000057619e23>] slab_post_alloc_hook mm/slab.h:439 [inline]
[<0000000057619e23>] slab_alloc mm/slab.c:3326 [inline]
[<0000000057619e23>] kmem_cache_alloc_trace+0x13d/0x280 mm/slab.c:3553
[<0000000086ce5479>] kmalloc include/linux/slab.h:547 [inline]
[<0000000086ce5479>] start_sync_thread+0x5d2/0xe10 net/netfilter/ipvs/ip_vs_sync.c:1862
[<000000001a9229cc>] do_ip_vs_set_ctl+0x4c5/0x780 net/netfilter/ipvs/ip_vs_ctl.c:2402
[<00000000ece457c8>] nf_sockopt net/netfilter/nf_sockopt.c:106 [inline]
[<00000000ece457c8>] nf_setsockopt+0x4c/0x80 net/netfilter/nf_sockopt.c:115
[<00000000942f62d4>] ip_setsockopt net/ipv4/ip_sockglue.c:1258 [inline]
[<00000000942f62d4>] ip_setsockopt+0x9b/0xb0 net/ipv4/ip_sockglue.c:1238
[<00000000a56a8ffd>] udp_setsockopt+0x4e/0x90 net/ipv4/udp.c:2616
[<00000000fa895401>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3130
[<0000000095eef4cf>] __sys_setsockopt+0x98/0x120 net/socket.c:2078
[<000000009747cf88>] __do_sys_setsockopt net/socket.c:2089 [inline]
[<000000009747cf88>] __se_sys_setsockopt net/socket.c:2086 [inline]
[<000000009747cf88>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2086
[<00000000ded8ba80>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301
[<00000000893b4ac8>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
Reported-by: [email protected]
Suggested-by: Eric Biggers <[email protected]>
Fixes: 998e7a76804b ("ipvs: Use kthread_run() instead of doing a double-fork via kernel_thread()")
Signed-off-by: Julian Anastasov <[email protected]>
Acked-by: Simon Horman <[email protected]>
Signed-off-by: Pablo Neira Ayuso <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
include/net/ip_vs.h | 6 +-
net/netfilter/ipvs/ip_vs_ctl.c | 4 -
net/netfilter/ipvs/ip_vs_sync.c | 134 +++++++++++++++++---------------
3 files changed, 76 insertions(+), 68 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a0d2e0bb9a94..0e3c0d83bd99 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -806,11 +806,12 @@ struct ipvs_master_sync_state {
struct ip_vs_sync_buff *sync_buff;
unsigned long sync_queue_len;
unsigned int sync_queue_delay;
- struct task_struct *master_thread;
struct delayed_work master_wakeup_work;
struct netns_ipvs *ipvs;
};
+struct ip_vs_sync_thread_data;
+
/* How much time to keep dests in trash */
#define IP_VS_DEST_TRASH_PERIOD (120 * HZ)
@@ -941,7 +942,8 @@ struct netns_ipvs {
spinlock_t sync_lock;
struct ipvs_master_sync_state *ms;
spinlock_t sync_buff_lock;
- struct task_struct **backup_threads;
+ struct ip_vs_sync_thread_data *master_tinfo;
+ struct ip_vs_sync_thread_data *backup_tinfo;
int threads_mask;
volatile int sync_state;
struct mutex sync_mutex;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 2d4e048762f6..3df94a499126 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2382,9 +2382,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
cfg.syncid = dm->syncid;
ret = start_sync_thread(ipvs, &cfg, dm->state);
} else {
- mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
}
goto out_dec;
}
@@ -3492,10 +3490,8 @@ static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
if (!attrs[IPVS_DAEMON_ATTR_STATE])
return -EINVAL;
- mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
return ret;
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index d4020c5e831d..ecb71062fcb3 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -195,6 +195,7 @@ union ip_vs_sync_conn {
#define IPVS_OPT_F_PARAM (1 << (IPVS_OPT_PARAM-1))
struct ip_vs_sync_thread_data {
+ struct task_struct *task;
struct netns_ipvs *ipvs;
struct socket *sock;
char *buf;
@@ -374,8 +375,11 @@ static inline void sb_queue_tail(struct netns_ipvs *ipvs,
max(IPVS_SYNC_SEND_DELAY, 1));
ms->sync_queue_len++;
list_add_tail(&sb->list, &ms->sync_queue);
- if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
- wake_up_process(ms->master_thread);
+ if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE) {
+ int id = (int)(ms - ipvs->ms);
+
+ wake_up_process(ipvs->master_tinfo[id].task);
+ }
} else
ip_vs_sync_buff_release(sb);
spin_unlock(&ipvs->sync_lock);
@@ -1636,8 +1640,10 @@ static void master_wakeup_work_handler(struct work_struct *work)
spin_lock_bh(&ipvs->sync_lock);
if (ms->sync_queue_len &&
ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
+ int id = (int)(ms - ipvs->ms);
+
ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
- wake_up_process(ms->master_thread);
+ wake_up_process(ipvs->master_tinfo[id].task);
}
spin_unlock_bh(&ipvs->sync_lock);
}
@@ -1703,10 +1709,6 @@ static int sync_thread_master(void *data)
if (sb)
ip_vs_sync_buff_release(sb);
- /* release the sending multicast socket */
- sock_release(tinfo->sock);
- kfree(tinfo);
-
return 0;
}
@@ -1740,11 +1742,6 @@ static int sync_thread_backup(void *data)
}
}
- /* release the sending multicast socket */
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
-
return 0;
}
@@ -1752,8 +1749,8 @@ static int sync_thread_backup(void *data)
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo = NULL;
- struct task_struct **array = NULL, *task;
+ struct ip_vs_sync_thread_data *ti = NULL, *tinfo;
+ struct task_struct *task;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
@@ -1822,7 +1819,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
result = -EEXIST;
- if (ipvs->backup_threads)
+ if (ipvs->backup_tinfo)
goto out_early;
ipvs->bcfg = *c;
@@ -1849,28 +1846,22 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
master_wakeup_work_handler);
ms->ipvs = ipvs;
}
- } else {
- array = kcalloc(count, sizeof(struct task_struct *),
- GFP_KERNEL);
- result = -ENOMEM;
- if (!array)
- goto out;
}
+ result = -ENOMEM;
+ ti = kcalloc(count, sizeof(struct ip_vs_sync_thread_data),
+ GFP_KERNEL);
+ if (!ti)
+ goto out;
for (id = 0; id < count; id++) {
- result = -ENOMEM;
- tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
- if (!tinfo)
- goto out;
+ tinfo = &ti[id];
tinfo->ipvs = ipvs;
- tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
+ result = -ENOMEM;
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
goto out;
- } else {
- tinfo->buf = NULL;
}
tinfo->id = id;
if (state == IP_VS_STATE_MASTER)
@@ -1885,17 +1876,15 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
result = PTR_ERR(task);
goto out;
}
- tinfo = NULL;
- if (state == IP_VS_STATE_MASTER)
- ipvs->ms[id].master_thread = task;
- else
- array[id] = task;
+ tinfo->task = task;
}
/* mark as active */
- if (state == IP_VS_STATE_BACKUP)
- ipvs->backup_threads = array;
+ if (state == IP_VS_STATE_MASTER)
+ ipvs->master_tinfo = ti;
+ else
+ ipvs->backup_tinfo = ti;
spin_lock_bh(&ipvs->sync_buff_lock);
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);
@@ -1910,29 +1899,31 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
out:
/* We do not need RTNL lock anymore, release it here so that
- * sock_release below and in the kthreads can use rtnl_lock
- * to leave the mcast group.
+ * sock_release below can use rtnl_lock to leave the mcast group.
*/
rtnl_unlock();
- count = id;
- while (count-- > 0) {
- if (state == IP_VS_STATE_MASTER)
- kthread_stop(ipvs->ms[count].master_thread);
- else
- kthread_stop(array[count]);
+ id = min(id, count - 1);
+ if (ti) {
+ for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+ if (tinfo->task)
+ kthread_stop(tinfo->task);
+ }
}
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
mutex_unlock(&ipvs->sync_mutex);
- if (tinfo) {
- if (tinfo->sock)
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
+
+ /* No more mutexes, release socks */
+ if (ti) {
+ for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ }
+ kfree(ti);
}
- kfree(array);
return result;
out_early:
@@ -1944,15 +1935,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int stop_sync_thread(struct netns_ipvs *ipvs, int state)
{
- struct task_struct **array;
+ struct ip_vs_sync_thread_data *ti, *tinfo;
int id;
int retc = -EINVAL;
IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
+ mutex_lock(&ipvs->sync_mutex);
if (state == IP_VS_STATE_MASTER) {
+ retc = -ESRCH;
if (!ipvs->ms)
- return -ESRCH;
+ goto err;
+ ti = ipvs->master_tinfo;
/*
* The lock synchronizes with sb_queue_tail(), so that we don't
@@ -1971,38 +1965,56 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state)
struct ipvs_master_sync_state *ms = &ipvs->ms[id];
int ret;
+ tinfo = &ti[id];
pr_info("stopping master sync thread %d ...\n",
- task_pid_nr(ms->master_thread));
+ task_pid_nr(tinfo->task));
cancel_delayed_work_sync(&ms->master_wakeup_work);
- ret = kthread_stop(ms->master_thread);
+ ret = kthread_stop(tinfo->task);
if (retc >= 0)
retc = ret;
}
kfree(ipvs->ms);
ipvs->ms = NULL;
+ ipvs->master_tinfo = NULL;
} else if (state == IP_VS_STATE_BACKUP) {
- if (!ipvs->backup_threads)
- return -ESRCH;
+ retc = -ESRCH;
+ if (!ipvs->backup_tinfo)
+ goto err;
+ ti = ipvs->backup_tinfo;
ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
- array = ipvs->backup_threads;
retc = 0;
for (id = ipvs->threads_mask; id >= 0; id--) {
int ret;
+ tinfo = &ti[id];
pr_info("stopping backup sync thread %d ...\n",
- task_pid_nr(array[id]));
- ret = kthread_stop(array[id]);
+ task_pid_nr(tinfo->task));
+ ret = kthread_stop(tinfo->task);
if (retc >= 0)
retc = ret;
}
- kfree(array);
- ipvs->backup_threads = NULL;
+ ipvs->backup_tinfo = NULL;
+ } else {
+ goto err;
}
+ id = ipvs->threads_mask;
+ mutex_unlock(&ipvs->sync_mutex);
+
+ /* No more mutexes, release socks */
+ for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ }
+ kfree(ti);
/* decrease the module use count */
ip_vs_use_count_dec();
+ return retc;
+err:
+ mutex_unlock(&ipvs->sync_mutex);
return retc;
}
@@ -2021,7 +2033,6 @@ void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs)
{
int retc;
- mutex_lock(&ipvs->sync_mutex);
retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER);
if (retc && retc != -ESRCH)
pr_err("Failed to stop Master Daemon\n");
@@ -2029,5 +2040,4 @@ void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs)
retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP);
if (retc && retc != -ESRCH)
pr_err("Failed to stop Backup Daemon\n");
- mutex_unlock(&ipvs->sync_mutex);
}
--
2.20.1
From: Baruch Siach <[email protected]>
[ Upstream commit 0472301a28f6cf53a6bc5783e48a2d0bbff4682f ]
Merge commit 1c8c5a9d38f60 ("Merge
git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next") undid the
fix from commit 36f9814a494 ("bpf: fix uapi hole for 32 bit compat
applications") by taking the gpl_compatible 1-bit field definition from
commit b85fab0e67b162 ("bpf: Add gpl_compatible flag to struct
bpf_prog_info") as is. That breaks architectures with 16-bit alignment
like m68k. Add 31-bit pad after gpl_compatible to restore alignment of
following fields.
Thanks to Dmitry V. Levin his analysis of this bug history.
Signed-off-by: Baruch Siach <[email protected]>
Acked-by: Song Liu <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Daniel Borkmann <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: Linus Torvalds <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
include/uapi/linux/bpf.h | 1 +
tools/include/uapi/linux/bpf.h | 1 +
2 files changed, 2 insertions(+)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2932600ce271..d143e277cdaf 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2486,6 +2486,7 @@ struct bpf_prog_info {
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
__u32 gpl_compatible:1;
+ __u32 :31; /* alignment pad */
__u64 netns_dev;
__u64 netns_ino;
__u32 nr_jited_ksyms;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 66917a4eba27..bf4cd924aed5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2484,6 +2484,7 @@ struct bpf_prog_info {
char name[BPF_OBJ_NAME_LEN];
__u32 ifindex;
__u32 gpl_compatible:1;
+ __u32 :31; /* alignment pad */
__u64 netns_dev;
__u64 netns_ino;
__u32 nr_jited_ksyms;
--
2.20.1
From: Coly Li <[email protected]>
[ Upstream commit 383ff2183ad16a8842d1fbd9dd3e1cbd66813e64 ]
When too many I/O errors happen on cache set and CACHE_SET_IO_DISABLE
bit is set, bch_journal() may continue to work because the journaling
bkey might be still in write set yet. The caller of bch_journal() may
believe the journal still work but the truth is in-memory journal write
set won't be written into cache device any more. This behavior may
introduce potential inconsistent metadata status.
This patch checks CACHE_SET_IO_DISABLE bit at the head of bch_journal(),
if the bit is set, bch_journal() returns NULL immediately to notice
caller to know journal does not work.
Signed-off-by: Coly Li <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/md/bcache/journal.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index f880e5eba8dd..8d4d63b51553 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -810,6 +810,10 @@ atomic_t *bch_journal(struct cache_set *c,
struct journal_write *w;
atomic_t *ret;
+ /* No journaling if CACHE_SET_IO_DISABLE set already */
+ if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
+ return NULL;
+
if (!CACHE_SYNC(&c->sb))
return NULL;
--
2.20.1
From: André Almeida <[email protected]>
[ Upstream commit 77ae46e11df5c96bb4582633851f838f5d954df4 ]
v4l2_fill_pixfmt() returns -EINVAL if the pixelformat used as parameter is
invalid or if the user is trying to use a multiplanar format with the
singleplanar API. Currently, the vimc_cap_try_fmt_vid_cap() returns such
value, but vimc_cap_s_fmt_vid_cap() is ignoring it. Fix that and returns
an error value if vimc_cap_try_fmt_vid_cap() has failed.
Signed-off-by: André Almeida <[email protected]>
Suggested-by: Helen Koike <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/vimc/vimc-capture.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/drivers/media/platform/vimc/vimc-capture.c b/drivers/media/platform/vimc/vimc-capture.c
index 65d657daf66f..8e014cc485f0 100644
--- a/drivers/media/platform/vimc/vimc-capture.c
+++ b/drivers/media/platform/vimc/vimc-capture.c
@@ -132,12 +132,15 @@ static int vimc_cap_s_fmt_vid_cap(struct file *file, void *priv,
struct v4l2_format *f)
{
struct vimc_cap_device *vcap = video_drvdata(file);
+ int ret;
/* Do not change the format while stream is on */
if (vb2_is_busy(&vcap->queue))
return -EBUSY;
- vimc_cap_try_fmt_vid_cap(file, priv, f);
+ ret = vimc_cap_try_fmt_vid_cap(file, priv, f);
+ if (ret)
+ return ret;
dev_dbg(vcap->dev, "%s: format update: "
"old:%dx%d (0x%x, %d, %d, %d, %d) "
--
2.20.1
From: Ard Biesheuvel <[email protected]>
[ Upstream commit 2af22f3ec3ca452f1e79b967f634708ff01ced8a ]
Some Qualcomm Snapdragon based laptops built to run Microsoft Windows
are clearly ACPI 5.1 based, given that that is the first ACPI revision
that supports ARM, and introduced the FADT 'arm_boot_flags' field,
which has a non-zero field on those systems.
So in these cases, infer from the ARM boot flags that the FADT must be
5.1 or later, and treat it as 5.1.
Acked-by: Sudeep Holla <[email protected]>
Tested-by: Lee Jones <[email protected]>
Reviewed-by: Graeme Gregory <[email protected]>
Acked-by: Lorenzo Pieralisi <[email protected]>
Acked-by: Hanjun Guo <[email protected]>
Signed-off-by: Ard Biesheuvel <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/arm64/kernel/acpi.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index ed46dc188b22..970f15c76bac 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -154,10 +154,14 @@ static int __init acpi_fadt_sanity_check(void)
*/
if (table->revision < 5 ||
(table->revision == 5 && fadt->minor_revision < 1)) {
- pr_err("Unsupported FADT revision %d.%d, should be 5.1+\n",
+ pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 5.1+\n",
table->revision, fadt->minor_revision);
- ret = -EINVAL;
- goto out;
+
+ if (!fadt->arm_boot_flags) {
+ ret = -EINVAL;
+ goto out;
+ }
+ pr_err("FADT has ARM boot flags set, assuming 5.1\n");
}
if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) {
--
2.20.1
From: Vedang Patel <[email protected]>
[ Upstream commit 1e08511d5d01884a3c9070afd52a47799312074a ]
If a packet which is utilizing the launchtime feature (via SO_TXTIME socket
option) also requests the hardware transmit timestamp, the hardware
timestamp is not delivered to the userspace. This is because the value in
skb->tstamp is mistaken as the software timestamp.
Applications, like ptp4l, request a hardware timestamp by setting the
SOF_TIMESTAMPING_TX_HARDWARE socket option. Whenever a new timestamp is
detected by the driver (this work is done in igb_ptp_tx_work() which calls
igb_ptp_tx_hwtstamps() in igb_ptp.c[1]), it will queue the timestamp in the
ERR_QUEUE for the userspace to read. When the userspace is ready, it will
issue a recvmsg() call to collect this timestamp. The problem is in this
recvmsg() call. If the skb->tstamp is not cleared out, it will be
interpreted as a software timestamp and the hardware tx timestamp will not
be successfully sent to the userspace. Look at skb_is_swtx_tstamp() and the
callee function __sock_recv_timestamp() in net/socket.c for more details.
Signed-off-by: Vedang Patel <[email protected]>
Tested-by: Aaron Brown <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/intel/igb/igb_main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 5aa083d9a6c9..ab76a5f77cd0 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5703,6 +5703,7 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
*/
if (tx_ring->launchtime_enable) {
ts = ns_to_timespec64(first->skb->tstamp);
+ first->skb->tstamp = 0;
context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
} else {
context_desc->seqnum_seed = 0;
--
2.20.1
From: Marek Szyprowski <[email protected]>
[ Upstream commit e08efef8fe7db87206314c19b341612c719f891a ]
Since the beginning the second clock ('special', 'sclk') was optional and
it is not available on some variants of Exynos SoCs (i.e. Exynos5420 with
v7 of MFC hardware).
However commit 1bce6fb3edf1 ("[media] s5p-mfc: Rework clock handling")
made handling of all specified clocks mandatory. This patch restores
original behavior of the driver and fixes its operation on
Exynos5420 SoCs.
Fixes: 1bce6fb3edf1 ("[media] s5p-mfc: Rework clock handling")
Signed-off-by: Marek Szyprowski <[email protected]>
Signed-off-by: Hans Verkuil <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/platform/s5p-mfc/s5p_mfc_pm.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
index eb85cedc5ef3..5e080f32b0e8 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_pm.c
@@ -38,6 +38,11 @@ int s5p_mfc_init_pm(struct s5p_mfc_dev *dev)
for (i = 0; i < pm->num_clocks; i++) {
pm->clocks[i] = devm_clk_get(pm->device, pm->clk_names[i]);
if (IS_ERR(pm->clocks[i])) {
+ /* additional clocks are optional */
+ if (i && PTR_ERR(pm->clocks[i]) == -ENOENT) {
+ pm->clocks[i] = NULL;
+ continue;
+ }
mfc_err("Failed to get clock: %s\n",
pm->clk_names[i]);
return PTR_ERR(pm->clocks[i]);
--
2.20.1
From: Chaitanya Kulkarni <[email protected]>
[ Upstream commit e71afda49335620e3d9adf56015676db33a3bd86 ]
This patch removes the confusing assignment of the variable result at
the time of declaration and sets the value in error cases next to the
places where the actual error is happening.
Here we also set the result value to -ENODEV when we fail at the final
ctrl state transition in nvme_reset_work(). Without this assignment
result will hold 0 from nvme_setup_io_queue() and on failure 0 will be
passed to he nvme_remove_dead_ctrl() from final state transition.
Signed-off-by: Chaitanya Kulkarni <[email protected]>
Signed-off-by: Christoph Hellwig <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/nvme/host/pci.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 03e72e2f57f5..0a5d064f82ca 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2253,11 +2253,13 @@ static void nvme_reset_work(struct work_struct *work)
struct nvme_dev *dev =
container_of(work, struct nvme_dev, ctrl.reset_work);
bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
- int result = -ENODEV;
+ int result;
enum nvme_ctrl_state new_state = NVME_CTRL_LIVE;
- if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING))
+ if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
+ result = -ENODEV;
goto out;
+ }
/*
* If we're called to reset a live controller first shut it down before
@@ -2355,6 +2357,7 @@ static void nvme_reset_work(struct work_struct *work)
if (!nvme_change_ctrl_state(&dev->ctrl, new_state)) {
dev_warn(dev->ctrl.device,
"failed to mark controller state %d\n", new_state);
+ result = -ENODEV;
goto out;
}
--
2.20.1
From: Andi Kleen <[email protected]>
[ Upstream commit 2f87f33f4226523df9c9cc28f9874ea02fcc3d3f ]
The metric group code tries to find a group it added earlier in the
evlist. Fix the lookup to handle groups with partially overlaps
correctly. When a sub string match fails and we reset the match, we have
to compare the first element again.
I also renamed the find_evsel function to find_evsel_group to make its
purpose clearer.
With the earlier changes this fixes:
Before:
% perf stat -M UPI,IPC sleep 1
...
1,032,922 uops_retired.retire_slots # 1.1 UPI
1,896,096 inst_retired.any
1,896,096 inst_retired.any
1,177,254 cpu_clk_unhalted.thread
After:
% perf stat -M UPI,IPC sleep 1
...
1,013,193 uops_retired.retire_slots # 1.1 UPI
932,033 inst_retired.any
932,033 inst_retired.any # 0.9 IPC
1,091,245 cpu_clk_unhalted.thread
Signed-off-by: Andi Kleen <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Cc: Kan Liang <[email protected]>
Fixes: b18f3e365019 ("perf stat: Support JSON metrics in perf stat")
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/util/metricgroup.c | 47 ++++++++++++++++++++++++++---------
1 file changed, 35 insertions(+), 12 deletions(-)
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index a28f9b5cc4ff..8b3dafe3fac3 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -94,26 +94,49 @@ struct egroup {
const char *metric_expr;
};
-static struct perf_evsel *find_evsel(struct perf_evlist *perf_evlist,
- const char **ids,
- int idnum,
- struct perf_evsel **metric_events)
+static bool record_evsel(int *ind, struct perf_evsel **start,
+ int idnum,
+ struct perf_evsel **metric_events,
+ struct perf_evsel *ev)
+{
+ metric_events[*ind] = ev;
+ if (*ind == 0)
+ *start = ev;
+ if (++*ind == idnum) {
+ metric_events[*ind] = NULL;
+ return true;
+ }
+ return false;
+}
+
+static struct perf_evsel *find_evsel_group(struct perf_evlist *perf_evlist,
+ const char **ids,
+ int idnum,
+ struct perf_evsel **metric_events)
{
struct perf_evsel *ev, *start = NULL;
int ind = 0;
evlist__for_each_entry (perf_evlist, ev) {
+ if (ev->collect_stat)
+ continue;
if (!strcmp(ev->name, ids[ind])) {
- metric_events[ind] = ev;
- if (ind == 0)
- start = ev;
- if (++ind == idnum) {
- metric_events[ind] = NULL;
+ if (record_evsel(&ind, &start, idnum,
+ metric_events, ev))
return start;
- }
} else {
+ /*
+ * We saw some other event that is not
+ * in our list of events. Discard
+ * the whole match and start again.
+ */
ind = 0;
start = NULL;
+ if (!strcmp(ev->name, ids[ind])) {
+ if (record_evsel(&ind, &start, idnum,
+ metric_events, ev))
+ return start;
+ }
}
}
/*
@@ -143,8 +166,8 @@ static int metricgroup__setup_events(struct list_head *groups,
ret = -ENOMEM;
break;
}
- evsel = find_evsel(perf_evlist, eg->ids, eg->idnum,
- metric_events);
+ evsel = find_evsel_group(perf_evlist, eg->ids, eg->idnum,
+ metric_events);
if (!evsel) {
pr_debug("Cannot resolve %s: %s\n",
eg->metric_name, eg->metric_expr);
--
2.20.1
From: Pan Bian <[email protected]>
[ Upstream commit 585fb3d93d32dbe89e718b85009f9c322cc554cd ]
In edac_create_csrow_object(), the reference to the object is not
released when adding the device to the device hierarchy fails
(device_add()). This may result in a memory leak.
Signed-off-by: Pan Bian <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Greg Kroah-Hartman <[email protected]>
Cc: James Morse <[email protected]>
Cc: Mauro Carvalho Chehab <[email protected]>
Cc: linux-edac <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/edac/edac_mc_sysfs.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 20374b8248f0..e50610b5bd06 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -404,6 +404,8 @@ static inline int nr_pages_per_csrow(struct csrow_info *csrow)
static int edac_create_csrow_object(struct mem_ctl_info *mci,
struct csrow_info *csrow, int index)
{
+ int err;
+
csrow->dev.type = &csrow_attr_type;
csrow->dev.bus = mci->bus;
csrow->dev.groups = csrow_dev_groups;
@@ -416,7 +418,11 @@ static int edac_create_csrow_object(struct mem_ctl_info *mci,
edac_dbg(0, "creating (virtual) csrow node %s\n",
dev_name(&csrow->dev));
- return device_add(&csrow->dev);
+ err = device_add(&csrow->dev);
+ if (err)
+ put_device(&csrow->dev);
+
+ return err;
}
/* Create a CSROW object under specifed edac_mc_device */
--
2.20.1
From: Yunsheng Lin <[email protected]>
[ Upstream commit 8f9eed1a8791b83eb1c54c261d68424717e4111e ]
If hns3_nic_net_xmit does not return NETDEV_TX_BUSY when doing
a loopback selftest, the skb is not freed in hns3_clean_tx_ring
or hns3_nic_net_xmit, which causes skb not freed problem.
This patch fixes it by freeing skb when hns3_nic_net_xmit does
not return NETDEV_TX_OK.
Fixes: c39c4d98dc65 ("net: hns3: Add mac loopback selftest support in hns3 driver")
Signed-off-by: Yunsheng Lin <[email protected]>
Signed-off-by: Peng Li <[email protected]>
Signed-off-by: Huazhong Tan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 9684ad015c42..6a3c6b02a77c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -245,11 +245,13 @@ static int hns3_lp_run_test(struct net_device *ndev, enum hnae3_loop mode)
skb_get(skb);
tx_ret = hns3_nic_net_xmit(skb, ndev);
- if (tx_ret == NETDEV_TX_OK)
+ if (tx_ret == NETDEV_TX_OK) {
good_cnt++;
- else
+ } else {
+ kfree_skb(skb);
netdev_err(ndev, "hns3_lb_run_test xmit failed: %d\n",
tx_ret);
+ }
}
if (good_cnt != HNS3_NIC_LB_TEST_PKT_NUM) {
ret_val = HNS3_NIC_LB_TEST_TX_CNT_ERR;
--
2.20.1
From: Dennis Zhou <[email protected]>
[ Upstream commit a3fb01ba5af066521f3f3421839e501bb2c71805 ]
As is, iolatency recognizes done_bio and cleanup as ending paths. If a
request is marked REQ_NOWAIT and fails to get a request, the bio is
cleaned up via rq_qos_cleanup() and ended in bio_wouldblock_error().
This results in underflowing the inflight counter. Fix this by only
accounting bios that were actually submitted.
Signed-off-by: Dennis Zhou <[email protected]>
Cc: Josef Bacik <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
block/blk-iolatency.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 6b8396ccb5c4..75df47ad2e79 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -565,6 +565,10 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
if (!blkg)
return;
+ /* We didn't actually submit this bio, don't account it. */
+ if (bio->bi_status == BLK_STS_AGAIN)
+ return;
+
iolat = blkg_to_lat(bio->bi_blkg);
if (!iolat)
return;
--
2.20.1
From: Oliver Neukum <[email protected]>
[ Upstream commit 11a087f484bf15ff65f0a9f277aa5a61fd07ed2a ]
We need to check whether this work we are canceling actually is
initialized.
Signed-off-by: Oliver Neukum <[email protected]>
Reported-by: [email protected]
Signed-off-by: Laurent Pinchart <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/usb/uvc/uvc_ctrl.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index 467b1ddaf4e7..f2854337cdca 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -2350,7 +2350,9 @@ void uvc_ctrl_cleanup_device(struct uvc_device *dev)
struct uvc_entity *entity;
unsigned int i;
- cancel_work_sync(&dev->async_ctrl.work);
+ /* Can be uninitialized if we are aborting on probe error. */
+ if (dev->async_ctrl.work.func)
+ cancel_work_sync(&dev->async_ctrl.work);
/* Free controls and control mappings for all entities. */
list_for_each_entry(entity, &dev->entities, list) {
--
2.20.1
From: Imre Deak <[email protected]>
[ Upstream commit d9349850e188b8b59e5322fda17ff389a1c0cd7d ]
The sequence
static DEFINE_WW_CLASS(test_ww_class);
struct ww_acquire_ctx ww_ctx;
struct ww_mutex ww_lock_a;
struct ww_mutex ww_lock_b;
struct ww_mutex ww_lock_c;
struct mutex lock_c;
ww_acquire_init(&ww_ctx, &test_ww_class);
ww_mutex_init(&ww_lock_a, &test_ww_class);
ww_mutex_init(&ww_lock_b, &test_ww_class);
ww_mutex_init(&ww_lock_c, &test_ww_class);
mutex_init(&lock_c);
ww_mutex_lock(&ww_lock_a, &ww_ctx);
mutex_lock(&lock_c);
ww_mutex_lock(&ww_lock_b, &ww_ctx);
ww_mutex_lock(&ww_lock_c, &ww_ctx);
mutex_unlock(&lock_c); (*)
ww_mutex_unlock(&ww_lock_c);
ww_mutex_unlock(&ww_lock_b);
ww_mutex_unlock(&ww_lock_a);
ww_acquire_fini(&ww_ctx); (**)
will trigger the following error in __lock_release() when calling
mutex_release() at **:
DEBUG_LOCKS_WARN_ON(depth <= 0)
The problem is that the hlock merging happening at * updates the
references for test_ww_class incorrectly to 3 whereas it should've
updated it to 4 (representing all the instances for ww_ctx and
ww_lock_[abc]).
Fix this by updating the references during merging correctly taking into
account that we can have non-zero references (both for the hlock that we
merge into another hlock or for the hlock we are merging into).
Signed-off-by: Imre Deak <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Cc: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Will Deacon <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
kernel/locking/lockdep.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 26b57e24476f..e810e8cb17e1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3326,17 +3326,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
if (depth) {
hlock = curr->held_locks + depth - 1;
if (hlock->class_idx == class_idx && nest_lock) {
- if (hlock->references) {
- /*
- * Check: unsigned int references:12, overflow.
- */
- if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
- return 0;
+ if (!references)
+ references++;
+ if (!hlock->references)
hlock->references++;
- } else {
- hlock->references = 2;
- }
+
+ hlock->references += references;
+
+ /* Overflow */
+ if (DEBUG_LOCKS_WARN_ON(hlock->references < references))
+ return 0;
return 1;
}
--
2.20.1
From: Fabio Estevam <[email protected]>
[ Upstream commit a19a0582363b9a5f8ba812f34f1b8df394898780 ]
When a valid MAC address is not found the current messages
are shown:
fec 2188000.ethernet (unnamed net_device) (uninitialized): Invalid MAC address: 00:00:00:00:00:00
fec 2188000.ethernet (unnamed net_device) (uninitialized): Using random MAC address: aa:9f:25:eb:7e:aa
Since the network device has not been registered at this point, it is better
to use dev_err()/dev_info() instead, which will provide cleaner log
messages like these:
fec 2188000.ethernet: Invalid MAC address: 00:00:00:00:00:00
fec 2188000.ethernet: Using random MAC address: aa:9f:25:eb:7e:aa
Tested on a imx6dl-pico-pi board.
Signed-off-by: Fabio Estevam <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/freescale/fec_main.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index bf715a367273..4cf80de4c471 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1689,10 +1689,10 @@ static void fec_get_mac(struct net_device *ndev)
*/
if (!is_valid_ether_addr(iap)) {
/* Report it and use a random ethernet address instead */
- netdev_err(ndev, "Invalid MAC address: %pM\n", iap);
+ dev_err(&fep->pdev->dev, "Invalid MAC address: %pM\n", iap);
eth_hw_addr_random(ndev);
- netdev_info(ndev, "Using random MAC address: %pM\n",
- ndev->dev_addr);
+ dev_info(&fep->pdev->dev, "Using random MAC address: %pM\n",
+ ndev->dev_addr);
return;
}
--
2.20.1
From: Borislav Petkov <[email protected]>
[ Upstream commit 6d8e294bf5f0e85c34e8b14b064e2965f53f38b0 ]
When inserting random PFNs for debugging the CEC through
(debugfs)/ras/cec/pfn, depending on the return value of pfn_set(),
multiple values get inserted per a single write.
That is because simple_attr_write() interprets a retval of 0 as
success and claims the whole input. However, pfn_set() returns the
cec_add_elem() value, which, if > 0 and smaller than the whole input
length, makes glibc continue issuing the write syscall until there's
input left:
pfn_set
simple_attr_write
debugfs_attr_write
full_proxy_write
vfs_write
ksys_write
do_syscall_64
entry_SYSCALL_64_after_hwframe
leading to those repeated calls.
Return 0 to fix that.
Signed-off-by: Borislav Petkov <[email protected]>
Cc: Tony Luck <[email protected]>
Cc: linux-edac <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/ras/cec.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index f85d6b7a1984..5d2b2c02cbbe 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -369,7 +369,9 @@ static int pfn_set(void *data, u64 val)
{
*(u64 *)data = val;
- return cec_add_elem(val);
+ cec_add_elem(val);
+
+ return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(pfn_ops, u64_get, pfn_set, "0x%llx\n");
--
2.20.1
From: Bob Liu <[email protected]>
[ Upstream commit 7602843fd873cae43a444b83b14dfdd114a9659c ]
Dulicate call of null_del_dev() will trigger null pointer error like below.
The reason is a race condition between nullb_device_power_store() and
nullb_group_drop_item().
CPU#0 CPU#1
---------------- -----------------
do_rmdir()
>configfs_rmdir()
>client_drop_item()
>nullb_group_drop_item()
nullb_device_power_store()
>null_del_dev()
>test_and_clear_bit(NULLB_DEV_FL_UP
>null_del_dev()
^^^^^
Duplicated null_dev_dev() triger null pointer error
>clear_bit(NULLB_DEV_FL_UP
The fix could be keep the sequnce of clear NULLB_DEV_FL_UP and null_del_dev().
[ 698.613600] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018
[ 698.613608] #PF error: [normal kernel read fault]
[ 698.613611] PGD 0 P4D 0
[ 698.613619] Oops: 0000 [#1] SMP PTI
[ 698.613627] CPU: 3 PID: 6382 Comm: rmdir Not tainted 5.0.0+ #35
[ 698.613631] Hardware name: LENOVO 20LJS2EV08/20LJS2EV08, BIOS R0SET33W (1.17 ) 07/18/2018
[ 698.613644] RIP: 0010:null_del_dev+0xc/0x110 [null_blk]
[ 698.613649] Code: 00 00 00 5b 41 5c 41 5d 41 5e 41 5f 5d c3 0f 0b eb 97 e8 47 bb 2a e8 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 48 89 e5 41 54 53 <8b> 77 18 48 89 fb 4c 8b 27 48 c7 c7 40 57 1e c1 e8 bf c7 cb e8 48
[ 698.613654] RSP: 0018:ffffb887888bfde0 EFLAGS: 00010286
[ 698.613659] RAX: 0000000000000000 RBX: ffff9d436d92bc00 RCX: ffff9d43a9184681
[ 698.613663] RDX: ffffffffc11e5c30 RSI: 0000000068be6540 RDI: 0000000000000000
[ 698.613667] RBP: ffffb887888bfdf0 R08: 0000000000000001 R09: 0000000000000000
[ 698.613671] R10: ffffb887888bfdd8 R11: 0000000000000f16 R12: ffff9d436d92bc08
[ 698.613675] R13: ffff9d436d94e630 R14: ffffffffc11e5088 R15: ffffffffc11e5000
[ 698.613680] FS: 00007faa68be6540(0000) GS:ffff9d43d14c0000(0000) knlGS:0000000000000000
[ 698.613685] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 698.613689] CR2: 0000000000000018 CR3: 000000042f70c002 CR4: 00000000003606e0
[ 698.613693] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 698.613697] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 698.613700] Call Trace:
[ 698.613712] nullb_group_drop_item+0x50/0x70 [null_blk]
[ 698.613722] client_drop_item+0x29/0x40
[ 698.613728] configfs_rmdir+0x1ed/0x300
[ 698.613738] vfs_rmdir+0xb2/0x130
[ 698.613743] do_rmdir+0x1c7/0x1e0
[ 698.613750] __x64_sys_rmdir+0x17/0x20
[ 698.613759] do_syscall_64+0x5a/0x110
[ 698.613768] entry_SYSCALL_64_after_hwframe+0x44/0xa9
Signed-off-by: Bob Liu <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/block/null_blk_main.c | 11 ++++++-----
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 093b614d6524..c5c0b7c89481 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -321,11 +321,12 @@ static ssize_t nullb_device_power_store(struct config_item *item,
set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
dev->power = newp;
} else if (dev->power && !newp) {
- mutex_lock(&lock);
- dev->power = newp;
- null_del_dev(dev->nullb);
- mutex_unlock(&lock);
- clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+ if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
+ mutex_lock(&lock);
+ dev->power = newp;
+ null_del_dev(dev->nullb);
+ mutex_unlock(&lock);
+ }
clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
}
--
2.20.1
From: Julian Wiedmann <[email protected]>
[ Upstream commit 04310324c6f482921c071444833e70fe861b73d9 ]
When a CQ-enabled device uses QEBSM for SBAL state inspection,
get_buf_states() can return the PENDING state for an Output Queue.
get_outbound_buffer_frontier() isn't prepared for this, and any PENDING
buffer will permanently stall all further completion processing on this
Queue.
This isn't a concern for non-QEBSM devices, as get_buf_states() for such
devices will manually turn PENDING buffers into EMPTY ones.
Fixes: 104ea556ee7f ("qdio: support asynchronous delivery of storage blocks")
Signed-off-by: Julian Wiedmann <[email protected]>
Signed-off-by: Heiko Carstens <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/s390/cio/qdio_main.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 9c7d9da42ba0..4ac4a73037f5 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -749,6 +749,7 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
switch (state) {
case SLSB_P_OUTPUT_EMPTY:
+ case SLSB_P_OUTPUT_PENDING:
/* the adapter got it */
DBF_DEV_EVENT(DBF_INFO, q->irq_ptr,
"out empty:%1d %02x", q->nr, count);
--
2.20.1
From: Jiri Olsa <[email protected]>
[ Upstream commit 279ab04dbea1370d2eac0f854270369ccaef8a44 ]
We are getting false positive gcc warning when we compile with gcc9 (9.1.1):
CC jvmti/libjvmti.o
In file included from /usr/include/string.h:494,
from jvmti/libjvmti.c:5:
In function ‘strncpy’,
inlined from ‘copy_class_filename.constprop’ at jvmti/libjvmti.c:166:3:
/usr/include/bits/string_fortified.h:106:10: error: ‘__builtin_strncpy’ specified bound depends on the length of the source argument [-Werror=stringop-overflow=]
106 | return __builtin___strncpy_chk (__dest, __src, __len, __bos (__dest));
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
jvmti/libjvmti.c: In function ‘copy_class_filename.constprop’:
jvmti/libjvmti.c:165:26: note: length computed here
165 | size_t file_name_len = strlen(file_name);
| ^~~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
As per Arnaldo's suggestion use strlcpy(), which does the same thing and keeps
gcc silent.
Suggested-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Jiri Olsa <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Ben Gainey <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Stephane Eranian <[email protected]>
Link: http://lkml.kernel.org/r/20190531131321.GB1281@krava
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/jvmti/libjvmti.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/tools/perf/jvmti/libjvmti.c b/tools/perf/jvmti/libjvmti.c
index 6add3e982614..3361d98a4edd 100644
--- a/tools/perf/jvmti/libjvmti.c
+++ b/tools/perf/jvmti/libjvmti.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/compiler.h>
+#include <linux/string.h>
#include <sys/types.h>
#include <stdio.h>
#include <string.h>
@@ -150,8 +151,7 @@ copy_class_filename(const char * class_sign, const char * file_name, char * resu
result[i] = '\0';
} else {
/* fallback case */
- size_t file_name_len = strlen(file_name);
- strncpy(result, file_name, file_name_len < max_length ? file_name_len : max_length);
+ strlcpy(result, file_name, max_length);
}
}
--
2.20.1
From: Biao Huang <[email protected]>
[ Upstream commit ee326fd01e79dfa42014d55931260b68b9fa3273 ]
Current dwmac4_flow_ctrl will not clear
GMAC_RX_FLOW_CTRL_RFE/GMAC_RX_FLOW_CTRL_RFE bits,
so MAC hw will keep flow control on although expecting
flow control off by ethtool. Add codes to fix it.
Fixes: 477286b53f55 ("stmmac: add GMAC4 core support")
Signed-off-by: Biao Huang <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index a2f3db39221e..d0e6e1503581 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -475,8 +475,9 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
if (fc & FLOW_RX) {
pr_debug("\tReceive Flow-Control ON\n");
flow |= GMAC_RX_FLOW_CTRL_RFE;
- writel(flow, ioaddr + GMAC_RX_FLOW_CTRL);
}
+ writel(flow, ioaddr + GMAC_RX_FLOW_CTRL);
+
if (fc & FLOW_TX) {
pr_debug("\tTransmit Flow-Control ON\n");
@@ -484,7 +485,7 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
pr_debug("\tduplex mode: PAUSE %d\n", pause_time);
for (queue = 0; queue < tx_cnt; queue++) {
- flow |= GMAC_TX_FLOW_CTRL_TFE;
+ flow = GMAC_TX_FLOW_CTRL_TFE;
if (duplex)
flow |=
@@ -492,6 +493,9 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
}
+ } else {
+ for (queue = 0; queue < tx_cnt; queue++)
+ writel(0, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
}
}
--
2.20.1
From: Abhishek Goel <[email protected]>
[ Upstream commit 04507c0a9385cc8280f794a36bfff567c8cc1042 ]
To set frequency on specific cpus using cpupower, following syntax can
be used :
cpupower -c #i frequency-set -f #f -r
While setting frequency using cpupower frequency-set command, if we use
'-r' option, it is expected to set frequency for all cpus related to
cpu #i. But it is observed to be missing the last cpu in related cpu
list. This patch fixes the problem.
Signed-off-by: Abhishek Goel <[email protected]>
Reviewed-by: Thomas Renninger <[email protected]>
Signed-off-by: Shuah Khan <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/power/cpupower/utils/cpufreq-set.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c
index 1eef0aed6423..08a405593a79 100644
--- a/tools/power/cpupower/utils/cpufreq-set.c
+++ b/tools/power/cpupower/utils/cpufreq-set.c
@@ -306,6 +306,8 @@ int cmd_freq_set(int argc, char **argv)
bitmask_setbit(cpus_chosen, cpus->cpu);
cpus = cpus->next;
}
+ /* Set the last cpu in related cpus list */
+ bitmask_setbit(cpus_chosen, cpus->cpu);
cpufreq_put_related_cpus(cpus);
}
}
--
2.20.1
From: Kefeng Wang <[email protected]>
[ Upstream commit 69fbb3f47327d959830c94bf31893972b8c8f700 ]
X-Originating-IP: [10.175.113.25]
X-CFilter-Loop: Reflected
The fm_v4l2_init_video_device() forget to unregister v4l2/video device
in the error path, it could lead to UAF issue, eg,
BUG: KASAN: use-after-free in atomic64_read include/asm-generic/atomic-instrumented.h:836 [inline]
BUG: KASAN: use-after-free in atomic_long_read include/asm-generic/atomic-long.h:28 [inline]
BUG: KASAN: use-after-free in __mutex_unlock_slowpath+0x92/0x690 kernel/locking/mutex.c:1206
Read of size 8 at addr ffff8881e84a7c70 by task v4l_id/3659
CPU: 1 PID: 3659 Comm: v4l_id Not tainted 5.1.0 #8
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
Call Trace:
__dump_stack lib/dump_stack.c:77 [inline]
dump_stack+0xa9/0x10e lib/dump_stack.c:113
print_address_description+0x65/0x270 mm/kasan/report.c:187
kasan_report+0x149/0x18d mm/kasan/report.c:317
atomic64_read include/asm-generic/atomic-instrumented.h:836 [inline]
atomic_long_read include/asm-generic/atomic-long.h:28 [inline]
__mutex_unlock_slowpath+0x92/0x690 kernel/locking/mutex.c:1206
fm_v4l2_fops_open+0xac/0x120 [fm_drv]
v4l2_open+0x191/0x390 [videodev]
chrdev_open+0x20d/0x570 fs/char_dev.c:417
do_dentry_open+0x700/0xf30 fs/open.c:777
do_last fs/namei.c:3416 [inline]
path_openat+0x7c4/0x2a90 fs/namei.c:3532
do_filp_open+0x1a5/0x2b0 fs/namei.c:3563
do_sys_open+0x302/0x490 fs/open.c:1069
do_syscall_64+0x9f/0x450 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7f8180c17c8e
...
Allocated by task 3642:
set_track mm/kasan/common.c:87 [inline]
__kasan_kmalloc.constprop.3+0xa0/0xd0 mm/kasan/common.c:497
fm_drv_init+0x13/0x1000 [fm_drv]
do_one_initcall+0xbc/0x47d init/main.c:901
do_init_module+0x1b5/0x547 kernel/module.c:3456
load_module+0x6405/0x8c10 kernel/module.c:3804
__do_sys_finit_module+0x162/0x190 kernel/module.c:3898
do_syscall_64+0x9f/0x450 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Freed by task 3642:
set_track mm/kasan/common.c:87 [inline]
__kasan_slab_free+0x130/0x180 mm/kasan/common.c:459
slab_free_hook mm/slub.c:1429 [inline]
slab_free_freelist_hook mm/slub.c:1456 [inline]
slab_free mm/slub.c:3003 [inline]
kfree+0xe1/0x270 mm/slub.c:3958
fm_drv_init+0x1e6/0x1000 [fm_drv]
do_one_initcall+0xbc/0x47d init/main.c:901
do_init_module+0x1b5/0x547 kernel/module.c:3456
load_module+0x6405/0x8c10 kernel/module.c:3804
__do_sys_finit_module+0x162/0x190 kernel/module.c:3898
do_syscall_64+0x9f/0x450 arch/x86/entry/common.c:290
entry_SYSCALL_64_after_hwframe+0x49/0xbe
Add relevant unregister functions to fix it.
Cc: Hans Verkuil <[email protected]>
Reported-by: Hulk Robot <[email protected]>
Signed-off-by: Kefeng Wang <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/radio/wl128x/fmdrv_v4l2.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/media/radio/wl128x/fmdrv_v4l2.c b/drivers/media/radio/wl128x/fmdrv_v4l2.c
index dccdf6558e6a..33abc8616ecb 100644
--- a/drivers/media/radio/wl128x/fmdrv_v4l2.c
+++ b/drivers/media/radio/wl128x/fmdrv_v4l2.c
@@ -549,6 +549,7 @@ int fm_v4l2_init_video_device(struct fmdev *fmdev, int radio_nr)
/* Register with V4L2 subsystem as RADIO device */
if (video_register_device(&gradio_dev, VFL_TYPE_RADIO, radio_nr)) {
+ v4l2_device_unregister(&fmdev->v4l2_dev);
fmerr("Could not register video device\n");
return -ENOMEM;
}
@@ -562,6 +563,8 @@ int fm_v4l2_init_video_device(struct fmdev *fmdev, int radio_nr)
if (ret < 0) {
fmerr("(fmdev): Can't init ctrl handler\n");
v4l2_ctrl_handler_free(&fmdev->ctrl_handler);
+ video_unregister_device(fmdev->radio_dev);
+ v4l2_device_unregister(&fmdev->v4l2_dev);
return -EBUSY;
}
--
2.20.1
From: Biao Huang <[email protected]>
[ Upstream commit d2facb4b3983425f6776c24dd678a82dbe673773 ]
the default value of tx-frames is 25, it's too late when
passing tstamp to stack, then the ptp4l will fail:
ptp4l -i eth0 -f gPTP.cfg -m
ptp4l: selected /dev/ptp0 as PTP clock
ptp4l: port 1: INITIALIZING to LISTENING on INITIALIZE
ptp4l: port 0: INITIALIZING to LISTENING on INITIALIZE
ptp4l: port 1: link up
ptp4l: timed out while polling for tx timestamp
ptp4l: increasing tx_timestamp_timeout may correct this issue,
but it is likely caused by a driver bug
ptp4l: port 1: send peer delay response failed
ptp4l: port 1: LISTENING to FAULTY on FAULT_DETECTED (FT_UNSPECIFIED)
ptp4l tests pass when changing the tx-frames from 25 to 1 with
ethtool -C option.
It should be fine to set tx-frames default value to 1, so ptp4l will pass
by default.
Signed-off-by: Biao Huang <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 272b9ca66314..b069b3a2453b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -261,7 +261,7 @@ struct stmmac_safety_stats {
#define STMMAC_COAL_TX_TIMER 1000
#define STMMAC_MAX_COAL_TX_TICK 100000
#define STMMAC_TX_MAX_FRAMES 256
-#define STMMAC_TX_FRAMES 25
+#define STMMAC_TX_FRAMES 1
/* Packets types */
enum packets_types {
--
2.20.1
From: Mathieu Poirier <[email protected]>
[ Upstream commit e45c48a9a4d20ebc7b639a62c3ef8f4b08007027 ]
This patch adds the necessary intelligence to properly compute the value
of 'old' and 'head' when operating in snapshot mode. That way we can
get the latest information in the AUX buffer and be compatible with the
generic AUX ring buffer mechanic.
Tester notes:
> Leo, have you had the chance to test/review this one? Suzuki?
Sure. I applied this patch on the perf/core branch (with latest
commit 3e4fbf36c1e3 'perf augmented_raw_syscalls: Move reading
filename to the loop') and passed testing with below steps:
# perf record -e cs_etm/@tmc_etr0/ -S -m,64 --per-thread ./sort &
[1] 19097
Bubble sorting array of 30000 elements
# kill -USR2 19097
# kill -USR2 19097
# kill -USR2 19097
[ perf record: Woken up 4 times to write data ]
[ perf record: Captured and wrote 0.753 MB perf.data ]
Signed-off-by: Mathieu Poirier <[email protected]>
Tested-by: Leo Yan <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Suzuki Poulouse <[email protected]>
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/arch/arm/util/cs-etm.c | 127 +++++++++++++++++++++++++++++-
1 file changed, 123 insertions(+), 4 deletions(-)
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 2f595cd73da6..16af6c3b1365 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -32,6 +32,8 @@ struct cs_etm_recording {
struct auxtrace_record itr;
struct perf_pmu *cs_etm_pmu;
struct perf_evlist *evlist;
+ int wrapped_cnt;
+ bool *wrapped;
bool snapshot_mode;
size_t snapshot_size;
};
@@ -495,16 +497,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
return 0;
}
-static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused,
+static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
+{
+ bool *wrapped;
+ int cnt = ptr->wrapped_cnt;
+
+ /* Make @ptr->wrapped as big as @idx */
+ while (cnt <= idx)
+ cnt++;
+
+ /*
+ * Free'ed in cs_etm_recording_free(). Using realloc() to avoid
+ * cross compilation problems where the host's system supports
+ * reallocarray() but not the target.
+ */
+ wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
+ if (!wrapped)
+ return -ENOMEM;
+
+ wrapped[cnt - 1] = false;
+ ptr->wrapped_cnt = cnt;
+ ptr->wrapped = wrapped;
+
+ return 0;
+}
+
+static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
+ size_t buffer_size, u64 head)
+{
+ u64 i, watermark;
+ u64 *buf = (u64 *)buffer;
+ size_t buf_size = buffer_size;
+
+ /*
+ * We want to look the very last 512 byte (chosen arbitrarily) in
+ * the ring buffer.
+ */
+ watermark = buf_size - 512;
+
+ /*
+ * @head is continuously increasing - if its value is equal or greater
+ * than the size of the ring buffer, it has wrapped around.
+ */
+ if (head >= buffer_size)
+ return true;
+
+ /*
+ * The value of @head is somewhere within the size of the ring buffer.
+ * This can be that there hasn't been enough data to fill the ring
+ * buffer yet or the trace time was so long that @head has numerically
+ * wrapped around. To find we need to check if we have data at the very
+ * end of the ring buffer. We can reliably do this because mmap'ed
+ * pages are zeroed out and there is a fresh mapping with every new
+ * session.
+ */
+
+ /* @head is less than 512 byte from the end of the ring buffer */
+ if (head > watermark)
+ watermark = head;
+
+ /*
+ * Speed things up by using 64 bit transactions (see "u64 *buf" above)
+ */
+ watermark >>= 3;
+ buf_size >>= 3;
+
+ /*
+ * If we find trace data at the end of the ring buffer, @head has
+ * been there and has numerically wrapped around at least once.
+ */
+ for (i = watermark; i < buf_size; i++)
+ if (buf[i])
+ return true;
+
+ return false;
+}
+
+static int cs_etm_find_snapshot(struct auxtrace_record *itr,
int idx, struct auxtrace_mmap *mm,
- unsigned char *data __maybe_unused,
+ unsigned char *data,
u64 *head, u64 *old)
{
+ int err;
+ bool wrapped;
+ struct cs_etm_recording *ptr =
+ container_of(itr, struct cs_etm_recording, itr);
+
+ /*
+ * Allocate memory to keep track of wrapping if this is the first
+ * time we deal with this *mm.
+ */
+ if (idx >= ptr->wrapped_cnt) {
+ err = cs_etm_alloc_wrapped_array(ptr, idx);
+ if (err)
+ return err;
+ }
+
+ /*
+ * Check to see if *head has wrapped around. If it hasn't only the
+ * amount of data between *head and *old is snapshot'ed to avoid
+ * bloating the perf.data file with zeros. But as soon as *head has
+ * wrapped around the entire size of the AUX ring buffer it taken.
+ */
+ wrapped = ptr->wrapped[idx];
+ if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
+ wrapped = true;
+ ptr->wrapped[idx] = true;
+ }
+
pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
__func__, idx, (size_t)*old, (size_t)*head, mm->len);
- *old = *head;
- *head += mm->len;
+ /* No wrap has occurred, we can just use *head and *old. */
+ if (!wrapped)
+ return 0;
+
+ /*
+ * *head has wrapped around - adjust *head and *old to pickup the
+ * entire content of the AUX buffer.
+ */
+ if (*head >= mm->len) {
+ *old = *head - mm->len;
+ } else {
+ *head += mm->len;
+ *old = *head - mm->len;
+ }
return 0;
}
@@ -545,6 +662,8 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
{
struct cs_etm_recording *ptr =
container_of(itr, struct cs_etm_recording, itr);
+
+ zfree(&ptr->wrapped);
free(ptr);
}
--
2.20.1
From: Thomas Richter <[email protected]>
[ Upstream commit 8a07aa4e9b7b0222129c07afff81634a884b2866 ]
Debugging a OOM error using the TUI interface revealed this issue
on s390:
[tmricht@m83lp54 perf]$ cat /proc/kallsyms |sort
....
00000001119b7158 B radix_tree_node_cachep
00000001119b8000 B __bss_stop
00000001119b8000 B _end
000003ff80002850 t autofs_mount [autofs4]
000003ff80002868 t autofs_show_options [autofs4]
000003ff80002a98 t autofs_evict_inode [autofs4]
....
There is a huge gap between the last kernel symbol
__bss_stop/_end and the first kernel module symbol
autofs_mount (from autofs4 module).
After reading the kernel symbol table via functions:
dso__load()
+--> dso__load_kernel_sym()
+--> dso__load_kallsyms()
+--> __dso_load_kallsyms()
+--> symbols__fixup_end()
the symbol __bss_stop has a start address of 1119b8000 and
an end address of 3ff80002850, as can be seen by this debug statement:
symbols__fixup_end __bss_stop start:0x1119b8000 end:0x3ff80002850
The size of symbol __bss_stop is 0x3fe6e64a850 bytes!
It is the last kernel symbol and fills up the space until
the first kernel module symbol.
This size kills the TUI interface when executing the following
code:
process_sample_event()
hist_entry_iter__add()
hist_iter__report_callback()
hist_entry__inc_addr_samples()
symbol__inc_addr_samples(symbol = __bss_stop)
symbol__cycles_hist()
annotated_source__alloc_histograms(...,
symbol__size(sym),
...)
This function allocates memory to save sample histograms.
The symbol_size() marco is defined as sym->end - sym->start, which
results in above value of 0x3fe6e64a850 bytes and
the call to calloc() in annotated_source__alloc_histograms() fails.
The histgram memory allocation might fail, make this failure
no-fatal and continue processing.
Output before:
[tmricht@m83lp54 perf]$ ./perf --debug stderr=1 report -vvvvv \
-i ~/slow.data 2>/tmp/2
[tmricht@m83lp54 perf]$ tail -5 /tmp/2
__symbol__inc_addr_samples(875): ENOMEM! sym->name=__bss_stop,
start=0x1119b8000, addr=0x2aa0005eb08, end=0x3ff80002850,
func: 0
problem adding hist entry, skipping event
0x938b8 [0x8]: failed to process type: 68 [Cannot allocate memory]
[tmricht@m83lp54 perf]$
Output after:
[tmricht@m83lp54 perf]$ ./perf --debug stderr=1 report -vvvvv \
-i ~/slow.data 2>/tmp/2
[tmricht@m83lp54 perf]$ tail -5 /tmp/2
symbol__inc_addr_samples map:0x1597830 start:0x110730000 end:0x3ff80002850
symbol__hists notes->src:0x2aa2a70 nr_hists:1
symbol__inc_addr_samples sym:unlink_anon_vmas src:0x2aa2a70
__symbol__inc_addr_samples: addr=0x11094c69e
0x11094c670 unlink_anon_vmas: period++ [addr: 0x11094c69e, 0x2e, evidx=0]
=> nr_samples: 1, period: 526008
[tmricht@m83lp54 perf]$
There is no error about failed memory allocation and the TUI interface
shows all entries.
Signed-off-by: Thomas Richter <[email protected]>
Reviewed-by: Hendrik Brueckner <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Hendrik Brueckner <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
tools/perf/util/annotate.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index dfee110b3a58..c357051dd2b6 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -911,9 +911,8 @@ static int symbol__inc_addr_samples(struct symbol *sym, struct map *map,
if (sym == NULL)
return 0;
src = symbol__hists(sym, evsel->evlist->nr_entries);
- if (src == NULL)
- return -ENOMEM;
- return __symbol__inc_addr_samples(sym, map, src, evsel->idx, addr, sample);
+ return (src) ? __symbol__inc_addr_samples(sym, map, src, evsel->idx,
+ addr, sample) : 0;
}
static int symbol__account_cycles(u64 addr, u64 start,
--
2.20.1
From: "Eric W. Biederman" <[email protected]>
[ Upstream commit 72abe3bcf0911d69b46c1e8bdb5612675e0ac42c ]
The locking in force_sig_info is not prepared to deal with a task that
exits or execs (as sighand may change). The is not a locking problem
in force_sig as force_sig is only built to handle synchronous
exceptions.
Further the function force_sig_info changes the signal state if the
signal is ignored, or blocked or if SIGNAL_UNKILLABLE will prevent the
delivery of the signal. The signal SIGKILL can not be ignored and can
not be blocked and SIGNAL_UNKILLABLE won't prevent it from being
delivered.
So using force_sig rather than send_sig for SIGKILL is confusing
and pointless.
Because it won't impact the sending of the signal and and because
using force_sig is wrong, replace force_sig with send_sig.
Cc: Namjae Jeon <[email protected]>
Cc: Jeff Layton <[email protected]>
Cc: Steve French <[email protected]>
Fixes: a5c3e1c725af ("Revert "cifs: No need to send SIGKILL to demux_thread during umount"")
Fixes: e7ddee9037e7 ("cifs: disable sharing session and tcon and add new TCP sharing code")
Signed-off-by: "Eric W. Biederman" <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
fs/cifs/connect.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index f31339db45fd..82b3af47bce3 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -2428,7 +2428,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
task = xchg(&server->tsk, NULL);
if (task)
- force_sig(SIGKILL, task);
+ send_sig(SIGKILL, task, 1);
}
static struct TCP_Server_Info *
--
2.20.1
From: Anirudh Gupta <[email protected]>
[ Upstream commit b38ff4075a80b4da5cb2202d7965332ca0efb213 ]
Family of src/dst can be different from family of selector src/dst.
Use xfrm selector family to validate address prefix length,
while verifying new sa from userspace.
Validated patch with this command:
ip xfrm state add src 1.1.6.1 dst 1.1.6.2 proto esp spi 4260196 \
reqid 20004 mode tunnel aead "rfc4106(gcm(aes))" \
0x1111016400000000000000000000000044440001 128 \
sel src 1011:1:4::2/128 sel dst 1021:1:4::2/128 dev Port5
Fixes: 07bf7908950a ("xfrm: Validate address prefix lengths in the xfrm selector.")
Signed-off-by: Anirudh Gupta <[email protected]>
Acked-by: Herbert Xu <[email protected]>
Signed-off-by: Steffen Klassert <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/xfrm/xfrm_user.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 2122f89f6155..d80d54e663c0 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -150,6 +150,22 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
err = -EINVAL;
switch (p->family) {
+ case AF_INET:
+ break;
+
+ case AF_INET6:
+#if IS_ENABLED(CONFIG_IPV6)
+ break;
+#else
+ err = -EAFNOSUPPORT;
+ goto out;
+#endif
+
+ default:
+ goto out;
+ }
+
+ switch (p->sel.family) {
case AF_INET:
if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
goto out;
--
2.20.1
From: "Eric W. Biederman" <[email protected]>
[ Upstream commit f9070dc94542093fd516ae4ccea17ef46a4362c5 ]
The locking in force_sig_info is not prepared to deal with a task that
exits or execs (as sighand may change). The is not a locking problem
in force_sig as force_sig is only built to handle synchronous
exceptions.
Further the function force_sig_info changes the signal state if the
signal is ignored, or blocked or if SIGNAL_UNKILLABLE will prevent the
delivery of the signal. The signal SIGKILL can not be ignored and can
not be blocked and SIGNAL_UNKILLABLE won't prevent it from being
delivered.
So using force_sig rather than send_sig for SIGKILL is confusing
and pointless.
Because it won't impact the sending of the signal and and because
using force_sig is wrong, replace force_sig with send_sig.
Cc: Daniel Lezcano <[email protected]>
Cc: Serge Hallyn <[email protected]>
Cc: Oleg Nesterov <[email protected]>
Fixes: cf3f89214ef6 ("pidns: add reboot_pid_ns() to handle the reboot syscall")
Signed-off-by: "Eric W. Biederman" <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
kernel/pid_namespace.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 2a2ac53d8b8b..95271f180687 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -325,7 +325,7 @@ int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
}
read_lock(&tasklist_lock);
- force_sig(SIGKILL, pid_ns->child_reaper);
+ send_sig(SIGKILL, pid_ns->child_reaper, 1);
read_unlock(&tasklist_lock);
do_exit(0);
--
2.20.1
From: Michal Kalderon <[email protected]>
[ Upstream commit 8366d520019f366fabd6c7a13032bdcd837e18d4 ]
In 100g mode the doorbell bar is united for both engines. Set
the correct offset in the hwfn so that the doorbell returned
for RoCE is in the affined hwfn.
Signed-off-by: Ariel Elior <[email protected]>
Signed-off-by: Denis Bolotin <[email protected]>
Signed-off-by: Michal Kalderon <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/qlogic/qed/qed_dev.c | 29 ++++++++++++++--------
drivers/net/ethernet/qlogic/qed/qed_rdma.c | 2 +-
2 files changed, 19 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 4dd82a1612aa..a6a9688db307 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -3096,6 +3096,7 @@ static void qed_nvm_info_free(struct qed_hwfn *p_hwfn)
static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
void __iomem *p_regview,
void __iomem *p_doorbells,
+ u64 db_phys_addr,
enum qed_pci_personality personality)
{
int rc = 0;
@@ -3103,6 +3104,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
/* Split PCI bars evenly between hwfns */
p_hwfn->regview = p_regview;
p_hwfn->doorbells = p_doorbells;
+ p_hwfn->db_phys_addr = db_phys_addr;
if (IS_VF(p_hwfn->cdev))
return qed_vf_hw_prepare(p_hwfn);
@@ -3198,7 +3200,9 @@ int qed_hw_prepare(struct qed_dev *cdev,
/* Initialize the first hwfn - will learn number of hwfns */
rc = qed_hw_prepare_single(p_hwfn,
cdev->regview,
- cdev->doorbells, personality);
+ cdev->doorbells,
+ cdev->db_phys_addr,
+ personality);
if (rc)
return rc;
@@ -3207,22 +3211,25 @@ int qed_hw_prepare(struct qed_dev *cdev,
/* Initialize the rest of the hwfns */
if (cdev->num_hwfns > 1) {
void __iomem *p_regview, *p_doorbell;
- u8 __iomem *addr;
+ u64 db_phys_addr;
+ u32 offset;
/* adjust bar offset for second engine */
- addr = cdev->regview +
- qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
- BAR_ID_0) / 2;
- p_regview = addr;
+ offset = qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+ BAR_ID_0) / 2;
+ p_regview = cdev->regview + offset;
- addr = cdev->doorbells +
- qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
- BAR_ID_1) / 2;
- p_doorbell = addr;
+ offset = qed_hw_bar_size(p_hwfn, p_hwfn->p_main_ptt,
+ BAR_ID_1) / 2;
+
+ p_doorbell = cdev->doorbells + offset;
+
+ db_phys_addr = cdev->db_phys_addr + offset;
/* prepare second hw function */
rc = qed_hw_prepare_single(&cdev->hwfns[1], p_regview,
- p_doorbell, personality);
+ p_doorbell, db_phys_addr,
+ personality);
/* in case of error, need to free the previously
* initiliazed hwfn 0.
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 7873d6dfd91f..13802b825d65 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -803,7 +803,7 @@ static int qed_rdma_add_user(void *rdma_cxt,
dpi_start_offset +
((out_params->dpi) * p_hwfn->dpi_size));
- out_params->dpi_phys_addr = p_hwfn->cdev->db_phys_addr +
+ out_params->dpi_phys_addr = p_hwfn->db_phys_addr +
dpi_start_offset +
((out_params->dpi) * p_hwfn->dpi_size);
--
2.20.1
From: Jose Abreu <[email protected]>
[ Upstream commit 0620ec6c62a5a07625b65f699adc5d1b90394ee6 ]
In case we don't use a given address entry we need to clear it because
it could contain previous values that are no longer valid.
Found out while running stmmac selftests.
Signed-off-by: Jose Abreu <[email protected]>
Cc: Joao Pinto <[email protected]>
Cc: David S. Miller <[email protected]>
Cc: Giuseppe Cavallaro <[email protected]>
Cc: Alexandre Torgue <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 7e5d5db0d516..a2f3db39221e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -444,14 +444,20 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
* are required
*/
value |= GMAC_PACKET_FILTER_PR;
- } else if (!netdev_uc_empty(dev)) {
- int reg = 1;
+ } else {
struct netdev_hw_addr *ha;
+ int reg = 1;
netdev_for_each_uc_addr(ha, dev) {
dwmac4_set_umac_addr(hw, ha->addr, reg);
reg++;
}
+
+ while (reg <= GMAC_MAX_PERFECT_ADDRESSES) {
+ writel(0, ioaddr + GMAC_ADDR_HIGH(reg));
+ writel(0, ioaddr + GMAC_ADDR_LOW(reg));
+ reg++;
+ }
}
writel(value, ioaddr + GMAC_PACKET_FILTER);
--
2.20.1
From: Miles Chen <[email protected]>
[ Upstream commit 0c1f14ed12262f45a3af1d588e4d7bd12438b8f5 ]
This change makes CONFIG_ZONE_DMA32 defuly y and allows users
to overwrite it only when CONFIG_EXPERT=y.
For the SoCs that do not need CONFIG_ZONE_DMA32, this is the
first step to manage all available memory by a single
zone(normal zone) to reduce the overhead of multiple zones.
The change also fixes a build error when CONFIG_NUMA=y and
CONFIG_ZONE_DMA32=n.
arch/arm64/mm/init.c:195:17: error: use of undeclared identifier 'ZONE_DMA32'
max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
Change since v1:
1. only expose CONFIG_ZONE_DMA32 when CONFIG_EXPERT=y
2. remove redundant IS_ENABLED(CONFIG_ZONE_DMA32)
Cc: Robin Murphy <[email protected]>
Signed-off-by: Miles Chen <[email protected]>
Signed-off-by: Catalin Marinas <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/arm64/Kconfig | 3 ++-
arch/arm64/mm/init.c | 5 +++--
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 8790a29d0af4..e3ebece79617 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -251,7 +251,8 @@ config GENERIC_CALIBRATE_DELAY
def_bool y
config ZONE_DMA32
- def_bool y
+ bool "Support DMA32 zone" if EXPERT
+ default y
config HAVE_GENERIC_GUP
def_bool y
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 774c3e17c798..29d2f425806e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -233,8 +233,9 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
- if (IS_ENABLED(CONFIG_ZONE_DMA32))
- max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+#ifdef CONFIG_ZONE_DMA32
+ max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+#endif
max_zone_pfns[ZONE_NORMAL] = max;
free_area_init_nodes(max_zone_pfns);
--
2.20.1
From: Daniel Drake <[email protected]>
[ Upstream commit 604dc9170f2435d27da5039a3efd757dceadc684 ]
native_calibrate_tsc() had a data mapping Intel CPU families
and crystal clock speed, but hardcoded tables are not ideal, and this
approach was already problematic at least in the Skylake X case, as
seen in commit:
b51120309348 ("x86/tsc: Fix erroneous TSC rate on Skylake Xeon")
By examining CPUID data from http://instlatx64.atw.hu/ and units
in the lab, we have found that 3 different scenarios need to be dealt
with, and we can eliminate most of the hardcoded data using an approach a
little more advanced than before:
1. ApolloLake, GeminiLake, CannonLake (and presumably all new chipsets
from this point) report the crystal frequency directly via CPUID.0x15.
That's definitive data that we can rely upon.
2. Skylake, Kabylake and all variants of those two chipsets report a
crystal frequency of zero, however we can calculate the crystal clock
speed by condidering data from CPUID.0x16.
This method correctly distinguishes between the two crystal clock
frequencies present on different Skylake X variants that caused
headaches before.
As the calculations do not quite match the previously-hardcoded values
in some cases (e.g. 23913043Hz instead of 24MHz), TSC refinement is
enabled on all platforms where we had to calculate the crystal
frequency in this way.
3. Denverton (GOLDMONT_X) reports a crystal frequency of zero and does
not support CPUID.0x16, so we leave this entry hardcoded.
Suggested-by: Thomas Gleixner <[email protected]>
Signed-off-by: Daniel Drake <[email protected]>
Reviewed-by: Thomas Gleixner <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: H. Peter Anvin <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
arch/x86/kernel/tsc.c | 47 +++++++++++++++++++++++++------------------
1 file changed, 27 insertions(+), 20 deletions(-)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 03b7529333a6..58a4ac0d20a8 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -628,31 +628,38 @@ unsigned long native_calibrate_tsc(void)
crystal_khz = ecx_hz / 1000;
- if (crystal_khz == 0) {
- switch (boot_cpu_data.x86_model) {
- case INTEL_FAM6_SKYLAKE_MOBILE:
- case INTEL_FAM6_SKYLAKE_DESKTOP:
- case INTEL_FAM6_KABYLAKE_MOBILE:
- case INTEL_FAM6_KABYLAKE_DESKTOP:
- crystal_khz = 24000; /* 24.0 MHz */
- break;
- case INTEL_FAM6_ATOM_GOLDMONT_X:
- crystal_khz = 25000; /* 25.0 MHz */
- break;
- case INTEL_FAM6_ATOM_GOLDMONT:
- crystal_khz = 19200; /* 19.2 MHz */
- break;
- }
- }
+ /*
+ * Denverton SoCs don't report crystal clock, and also don't support
+ * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal
+ * clock.
+ */
+ if (crystal_khz == 0 &&
+ boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_X)
+ crystal_khz = 25000;
- if (crystal_khz == 0)
- return 0;
/*
- * TSC frequency determined by CPUID is a "hardware reported"
+ * TSC frequency reported directly by CPUID is a "hardware reported"
* frequency and is the most accurate one so far we have. This
* is considered a known frequency.
*/
- setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+ if (crystal_khz != 0)
+ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+ /*
+ * Some Intel SoCs like Skylake and Kabylake don't report the crystal
+ * clock, but we can easily calculate it to a high degree of accuracy
+ * by considering the crystal ratio and the CPU speed.
+ */
+ if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) {
+ unsigned int eax_base_mhz, ebx, ecx, edx;
+
+ cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx);
+ crystal_khz = eax_base_mhz * 1000 *
+ eax_denominator / ebx_numerator;
+ }
+
+ if (crystal_khz == 0)
+ return 0;
/*
* For Atom SoCs TSC is the only reliable clocksource.
--
2.20.1
From: Konstantin Khlebnikov <[email protected]>
[ Upstream commit caff422ea81e144842bc44bab408d85ac449377b ]
This reverts commit 0f9e980bf5ee1a97e2e401c846b2af989eb21c61.
That change cased false-positive warning about hardware hang:
e1000e: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: Rx/Tx
IPv6: ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
e1000e 0000:00:1f.6 eth0: Detected Hardware Unit Hang:
TDH <0>
TDT <1>
next_to_use <1>
next_to_clean <0>
buffer_info[next_to_clean]:
time_stamp <fffba7a7>
next_to_watch <0>
jiffies <fffbb140>
next_to_watch.status <0>
MAC Status <40080080>
PHY Status <7949>
PHY 1000BASE-T Status <0>
PHY Extended Status <3000>
PCI Status <10>
e1000e: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: Rx/Tx
Besides warning everything works fine.
Original issue will be fixed property in following patch.
Signed-off-by: Konstantin Khlebnikov <[email protected]>
Reported-by: Joseph Yasi <[email protected]>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=203175
Tested-by: Joseph Yasi <[email protected]>
Tested-by: Aaron Brown <[email protected]>
Tested-by: Oleksandr Natalenko <[email protected]>
Signed-off-by: Jeff Kirsher <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/intel/e1000e/netdev.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 8cd339c92c1a..31ef42a031f2 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -5286,13 +5286,8 @@ static void e1000_watchdog_task(struct work_struct *work)
/* 8000ES2LAN requires a Rx packet buffer work-around
* on link down event; reset the controller to flush
* the Rx packet buffer.
- *
- * If the link is lost the controller stops DMA, but
- * if there is queued Tx work it cannot be done. So
- * reset the controller to flush the Tx packet buffers.
*/
- if ((adapter->flags & FLAG_RX_NEEDS_RESTART) ||
- e1000_desc_unused(tx_ring) + 1 < tx_ring->count)
+ if (adapter->flags & FLAG_RX_NEEDS_RESTART)
adapter->flags |= FLAG_RESTART_NOW;
else
pm_schedule_suspend(netdev->dev.parent,
@@ -5315,6 +5310,14 @@ static void e1000_watchdog_task(struct work_struct *work)
adapter->gotc_old = adapter->stats.gotc;
spin_unlock(&adapter->stats64_lock);
+ /* If the link is lost the controller stops DMA, but
+ * if there is queued Tx work it cannot be done. So
+ * reset the controller to flush the Tx packet buffers.
+ */
+ if (!netif_carrier_ok(netdev) &&
+ (e1000_desc_unused(tx_ring) + 1 < tx_ring->count))
+ adapter->flags |= FLAG_RESTART_NOW;
+
/* If reset is necessary, do it outside of interrupt context. */
if (adapter->flags & FLAG_RESTART_NOW) {
schedule_work(&adapter->reset_task);
--
2.20.1
From: Jeremy Sowden <[email protected]>
[ Upstream commit 17f78dd1bd624a4dd78ed5db3284a63ee807fcc3 ]
A handler for BATADV_TVLV_ROAM was being registered when the
translation-table was initialized, but not unregistered when the
translation-table was freed. Unregister it.
Fixes: 122edaa05940 ("batman-adv: tvlv - convert roaming adv packet to use tvlv unicast packets")
Reported-by: [email protected]
Signed-off-by: Jeremy Sowden <[email protected]>
Signed-off-by: Sven Eckelmann <[email protected]
Signed-off-by: Simon Wunderlich <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
net/batman-adv/translation-table.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 359ec1a6e822..9fa5389ea244 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -3821,6 +3821,8 @@ static void batadv_tt_purge(struct work_struct *work)
*/
void batadv_tt_free(struct batadv_priv *bat_priv)
{
+ batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_ROAM, 1);
+
batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_TT, 1);
batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_TT, 1);
--
2.20.1
From: Ioana Ciornei <[email protected]>
[ Upstream commit 82c76aca81187b3d28a6fb3062f6916450ce955e ]
In general, we don't want MAC drivers calling phy_attach_direct with the
net_device being NULL. Add checks against this in all the functions
calling it: phy_attach() and phy_connect_direct().
Signed-off-by: Ioana Ciornei <[email protected]>
Suggested-by: Andrew Lunn <[email protected]>
Reviewed-by: Andrew Lunn <[email protected]>
Reviewed-by: Florian Fainelli <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/phy/phy_device.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 8a96d985a52f..6144146aec29 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -757,6 +757,9 @@ int phy_connect_direct(struct net_device *dev, struct phy_device *phydev,
{
int rc;
+ if (!dev)
+ return -EINVAL;
+
rc = phy_attach_direct(dev, phydev, phydev->dev_flags, interface);
if (rc)
return rc;
@@ -1098,6 +1101,9 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id,
struct device *d;
int rc;
+ if (!dev)
+ return ERR_PTR(-EINVAL);
+
/* Search the list of PHY devices on the mdio bus for the
* PHY with the requested name
*/
--
2.20.1
From: Weihang Li <[email protected]>
[ Upstream commit 594a81b39525f0a17e92c2e0b167ae1400650380 ]
The hclge/hclgevf and hns3 module can be unloaded independently,
when hclge/hclgevf unloaded firstly, the ops of ae_dev should
be set to NULL, otherwise it will cause an use-after-free problem.
Fixes: 38caee9d3ee8 ("net: hns3: Add support of the HNAE3 framework")
Signed-off-by: Weihang Li <[email protected]>
Signed-off-by: Peng Li <[email protected]>
Signed-off-by: Huazhong Tan <[email protected]>
Signed-off-by: David S. Miller <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/net/ethernet/hisilicon/hns3/hnae3.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index fff5be8078ac..0594a6c3dccd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -229,6 +229,7 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+ ae_dev->ops = NULL;
}
list_del(&ae_algo->node);
@@ -316,6 +317,7 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
ae_algo->ops->uninit_ae_dev(ae_dev);
hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+ ae_dev->ops = NULL;
}
list_del(&ae_dev->node);
--
2.20.1
From: Eric Biggers <[email protected]>
[ Upstream commit eeacfdc68a104967162dfcba60f53f6f5b62a334 ]
Replace some BUG_ON()s with WARN_ON_ONCE() and returning an error code,
and move the check for len divisible by FS_CRYPTO_BLOCK_SIZE into
fscrypt_crypt_block() so that it's done for both encryption and
decryption, not just encryption.
Reviewed-by: Chandan Rajendra <[email protected]>
Signed-off-by: Eric Biggers <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
fs/crypto/crypto.c | 15 +++++++++------
1 file changed, 9 insertions(+), 6 deletions(-)
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 0f46cf550907..c83ddff3ff4a 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -149,7 +149,10 @@ int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
struct crypto_skcipher *tfm = ci->ci_ctfm;
int res = 0;
- BUG_ON(len == 0);
+ if (WARN_ON_ONCE(len <= 0))
+ return -EINVAL;
+ if (WARN_ON_ONCE(len % FS_CRYPTO_BLOCK_SIZE != 0))
+ return -EINVAL;
BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE);
BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE);
@@ -241,8 +244,6 @@ struct page *fscrypt_encrypt_page(const struct inode *inode,
struct page *ciphertext_page = page;
int err;
- BUG_ON(len % FS_CRYPTO_BLOCK_SIZE != 0);
-
if (inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES) {
/* with inplace-encryption we just encrypt the page */
err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num, page,
@@ -254,7 +255,8 @@ struct page *fscrypt_encrypt_page(const struct inode *inode,
return ciphertext_page;
}
- BUG_ON(!PageLocked(page));
+ if (WARN_ON_ONCE(!PageLocked(page)))
+ return ERR_PTR(-EINVAL);
ctx = fscrypt_get_ctx(inode, gfp_flags);
if (IS_ERR(ctx))
@@ -302,8 +304,9 @@ EXPORT_SYMBOL(fscrypt_encrypt_page);
int fscrypt_decrypt_page(const struct inode *inode, struct page *page,
unsigned int len, unsigned int offs, u64 lblk_num)
{
- if (!(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES))
- BUG_ON(!PageLocked(page));
+ if (WARN_ON_ONCE(!PageLocked(page) &&
+ !(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES)))
+ return -EINVAL;
return fscrypt_do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page,
len, offs, GFP_NOFS);
--
2.20.1
From: Akinobu Mita <[email protected]>
[ Upstream commit 6e4ab830ac6d6a0d7cd7f87dc5d6536369bf24a8 ]
If the requested framesize by VIDIOC_SUBDEV_S_FMT is larger than supported
framesizes, it causes an out of bounds array access and the resulting
framesize is unexpected.
Avoid out of bounds array access and select the default framesize.
Cc: Wenyou Yang <[email protected]>
Cc: Eugen Hristev <[email protected]>
Signed-off-by: Akinobu Mita <[email protected]>
Signed-off-by: Sakari Ailus <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
Signed-off-by: Sasha Levin <[email protected]>
---
drivers/media/i2c/ov7740.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/media/i2c/ov7740.c b/drivers/media/i2c/ov7740.c
index f5a1ee90a6c5..8a6a7a5929aa 100644
--- a/drivers/media/i2c/ov7740.c
+++ b/drivers/media/i2c/ov7740.c
@@ -761,7 +761,11 @@ static int ov7740_try_fmt_internal(struct v4l2_subdev *sd,
fsize++;
}
-
+ if (i >= ARRAY_SIZE(ov7740_framesizes)) {
+ fsize = &ov7740_framesizes[0];
+ fmt->width = fsize->width;
+ fmt->height = fsize->height;
+ }
if (ret_frmsize != NULL)
*ret_frmsize = fsize;
--
2.20.1
On 7/15/2019 4:17 PM, Sasha Levin wrote:
> From: Viresh Kumar <[email protected]>
>
> [ Upstream commit 9801522840cc1073f8064b4c979b7b6995c74bca ]
>
> CPUFREQ_CONST_LOOPS was introduced in a very old commit from pre-2.6
> kernel release by commit 6a4a93f9c0d5 ("[CPUFREQ] Fix 'out of sync'
> issue").
>
> Basically, that commit does two things:
>
> - It adds the frequency verification code (which is quite similar to
> what we have today as well).
>
> - And it sets the CPUFREQ_CONST_LOOPS flag only for setpolicy drivers,
> rightly so based on the code we had then. The idea was to avoid
> frequency validation for setpolicy drivers as the cpufreq core doesn't
> know what frequency the hardware is running at and so no point in
> doing frequency verification.
>
> The problem happened when we started to use the same CPUFREQ_CONST_LOOPS
> flag for constant loops-per-jiffy thing as well and many has_target()
> drivers started using the same flag and unknowingly skipped the
> verification of frequency. There is no logical reason behind skipping
> frequency validation because of the presence of CPUFREQ_CONST_LOOPS
> flag otherwise.
>
> Fix this issue by skipping frequency validation only for setpolicy
> drivers and always doing it for has_target() drivers irrespective of
> the presence or absence of CPUFREQ_CONST_LOOPS flag.
>
> cpufreq_notify_transition() is only called for has_target() type driver
> and not for set_policy type, and the check is simply redundant. Remove
> it as well.
>
> Also remove () around freq comparison statement as they aren't required
> and checkpatch also warns for them.
>
> Signed-off-by: Viresh Kumar <[email protected]>
> Signed-off-by: Rafael J. Wysocki <[email protected]>
> Signed-off-by: Sasha Levin <[email protected]>
> ---
> drivers/cpufreq/cpufreq.c | 13 +++++--------
> 1 file changed, 5 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
> index d3213594d1a7..80942ec34efd 100644
> --- a/drivers/cpufreq/cpufreq.c
> +++ b/drivers/cpufreq/cpufreq.c
> @@ -321,12 +321,10 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy,
> * which is not equal to what the cpufreq core thinks is
> * "old frequency".
> */
> - if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
> - if (policy->cur && (policy->cur != freqs->old)) {
> - pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
> - freqs->old, policy->cur);
> - freqs->old = policy->cur;
> - }
> + if (policy->cur && policy->cur != freqs->old) {
> + pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
> + freqs->old, policy->cur);
> + freqs->old = policy->cur;
> }
>
> for_each_cpu(freqs->cpu, policy->cpus) {
> @@ -1543,8 +1541,7 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
> if (policy->fast_switch_enabled)
> return ret_freq;
>
> - if (ret_freq && policy->cur &&
> - !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
> + if (has_target() && ret_freq && policy->cur) {
> /* verify no discrepancy between actual and
> saved value exists */
> if (unlikely(ret_freq != policy->cur)) {
This is not -stable material, please drop it.
On Tue, Jul 16, 2019 at 11:21:34AM +0200, Rafael J. Wysocki wrote:
>On 7/15/2019 4:17 PM, Sasha Levin wrote:
>>From: Viresh Kumar <[email protected]>
>>
>>[ Upstream commit 9801522840cc1073f8064b4c979b7b6995c74bca ]
>>
>>CPUFREQ_CONST_LOOPS was introduced in a very old commit from pre-2.6
>>kernel release by commit 6a4a93f9c0d5 ("[CPUFREQ] Fix 'out of sync'
>>issue").
>>
>>Basically, that commit does two things:
>>
>> - It adds the frequency verification code (which is quite similar to
>> what we have today as well).
>>
>> - And it sets the CPUFREQ_CONST_LOOPS flag only for setpolicy drivers,
>> rightly so based on the code we had then. The idea was to avoid
>> frequency validation for setpolicy drivers as the cpufreq core doesn't
>> know what frequency the hardware is running at and so no point in
>> doing frequency verification.
>>
>>The problem happened when we started to use the same CPUFREQ_CONST_LOOPS
>>flag for constant loops-per-jiffy thing as well and many has_target()
>>drivers started using the same flag and unknowingly skipped the
>>verification of frequency. There is no logical reason behind skipping
>>frequency validation because of the presence of CPUFREQ_CONST_LOOPS
>>flag otherwise.
>>
>>Fix this issue by skipping frequency validation only for setpolicy
>>drivers and always doing it for has_target() drivers irrespective of
>>the presence or absence of CPUFREQ_CONST_LOOPS flag.
>>
>>cpufreq_notify_transition() is only called for has_target() type driver
>>and not for set_policy type, and the check is simply redundant. Remove
>>it as well.
>>
>>Also remove () around freq comparison statement as they aren't required
>>and checkpatch also warns for them.
>>
>>Signed-off-by: Viresh Kumar <[email protected]>
>>Signed-off-by: Rafael J. Wysocki <[email protected]>
>>Signed-off-by: Sasha Levin <[email protected]>
>>---
>> drivers/cpufreq/cpufreq.c | 13 +++++--------
>> 1 file changed, 5 insertions(+), 8 deletions(-)
>>
>>diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
>>index d3213594d1a7..80942ec34efd 100644
>>--- a/drivers/cpufreq/cpufreq.c
>>+++ b/drivers/cpufreq/cpufreq.c
>>@@ -321,12 +321,10 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy,
>> * which is not equal to what the cpufreq core thinks is
>> * "old frequency".
>> */
>>- if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
>>- if (policy->cur && (policy->cur != freqs->old)) {
>>- pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
>>- freqs->old, policy->cur);
>>- freqs->old = policy->cur;
>>- }
>>+ if (policy->cur && policy->cur != freqs->old) {
>>+ pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
>>+ freqs->old, policy->cur);
>>+ freqs->old = policy->cur;
>> }
>> for_each_cpu(freqs->cpu, policy->cpus) {
>>@@ -1543,8 +1541,7 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
>> if (policy->fast_switch_enabled)
>> return ret_freq;
>>- if (ret_freq && policy->cur &&
>>- !(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
>>+ if (has_target() && ret_freq && policy->cur) {
>> /* verify no discrepancy between actual and
>> saved value exists */
>> if (unlikely(ret_freq != policy->cur)) {
>
>This is not -stable material, please drop it.
I've dropped it, thanks!
--
Thanks,
Sasha
Hi!
> From: Philipp Zabel <[email protected]>
>
> [ Upstream commit 56d159a4ec6d8da7313aac6fcbb95d8fffe689ba ]
>
> Sequence number handling assumed that the BIT processor frame number
> starts counting at 1, but this is not true for the MPEG-2 decoder,
> which starts at 0. Fix the sequence counter offset detection to handle
> this.
> +++ b/drivers/media/platform/coda/coda-bit.c
> @@ -1728,6 +1728,7 @@ static int __coda_start_decoding(struct coda_ctx *ctx)
> v4l2_err(&dev->v4l2_dev, "CODA_COMMAND_SEQ_INIT timeout\n");
> return ret;
> }
> + ctx->sequence_offset = ~0U;
> ctx->initialized = 1;
>
> /* Update kfifo out pointer from coda bitstream read pointer */
> @@ -2147,7 +2148,9 @@ static void coda_finish_decode(struct coda_ctx *ctx)
> v4l2_err(&dev->v4l2_dev,
> "decoded frame index out of range: %d\n", decoded_idx);
> } else {
> - val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM) - 1;
> + val = coda_read(dev, CODA_RET_DEC_PIC_FRAME_NUM);
> + if (ctx->sequence_offset == -1)
> + ctx->sequence_offset = val;
For consistency, would it be better to use == ~0U here, too? Variable is unsigned...
--
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html