net: tundra: tsi108: use spin_lock_irqsave instead of spin_lock_irq in IRQ context
Subsystems (18)
Sasha Levin
maintainerPATCH 1/45 net: tundra: tsi108: use spin_lock_irqsave instead of spin_lock_irq in IRQ context
From: Fuqian Huang <[email protected]>
[ Upstream commit 8c25d0887a8bd0e1ca2074ac0c6dff173787a83b ]
As spin_unlock_irq will enable interrupts.
Function tsi108_stat_carry is called from interrupt handler tsi108_irq. Interrupts are enabled in interrupt handler.
Use spin_lock_irqsave/spin_unlock_irqrestore instead of spin_(un)lock_irq in IRQ context to avoid this.
--- drivers/net/ethernet/tundra/tsi108_eth.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/net/ethernet/tundra/tsi108_eth.c +3 -2
@@ -383,9 +383,10 @@ tsi108_stat_carry_one(int carry, int carry_bit, int carry_shift,static void tsi108_stat_carry (struct net_device *dev) {struct tsi108_prv_data *data =netdev_priv (dev); +unsigned long flags;u32 carry1, carry2; -spin_lock_irq (&data->misclock); +spin_lock_irqsave (&data->misclock, flags); carry1 =TSI_READ (TSI108_STAT_CARRY1 ); carry2 =TSI_READ (TSI108_STAT_CARRY2 );
@@ -453,7 +454,7 @@ static void tsi108_stat_carry(struct net_device *dev)TSI108_STAT_TXPAUSEDROP_CARRY , &data->tx_pause_drop); -spin_unlock_irq (&data->misclock); +spin_unlock_irqrestore (&data->misclock, flags); }/* Read a stat counter atomically with respect to carries.
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 2/45 netfilter: nf_tables: use-after-free in failing rule with bound set
From: Pablo Neira Ayuso <[email protected]>
[ Upstream commit 6a0a8d10a3661a036b55af695542a714c429ab7c ]
If a rule that has already a bound anonymous set fails to be added, the preparation phase releases the rule and the bound set. However, the transaction object from the abort path still has a reference to the set object that is stale, leading to a use-after-free when checking for the set->bound field. Add a new field to the transaction that specifies if the set is bound, so the abort path can skip releasing it since the rule command owns it and it takes care of releasing it. After this update, the set->bound field is removed.
[ 24.649883] Unable to handle kernel paging request at virtual address 0000000000040434 [ 24.657858] Mem abort info: [ 24.660686] ESR = 0x96000004 [ 24.663769] Exception class = DABT (current EL), IL = 32 bits [ 24.669725] SET = 0, FnV = 0 [ 24.672804] EA = 0, S1PTW = 0 [ 24.675975] Data abort info: [ 24.678880] ISV = 0, ISS = 0x00000004 [ 24.682743] CM = 0, WnR = 0 [ 24.685723] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000428952000 [ 24.692207] [0000000000040434] pgd=0000000000000000 [ 24.697119] Internal error: Oops: 96000004 [#1] SMP [...] [ 24.889414] Call trace: [ 24.891870] __nf_tables_abort+0x3f0/0x7a0 [ 24.895984] nf_tables_abort+0x20/0x40 [ 24.899750] nfnetlink_rcv_batch+0x17c/0x588 [ 24.904037] nfnetlink_rcv+0x13c/0x190 [ 24.907803] netlink_unicast+0x18c/0x208 [ 24.911742] netlink_sendmsg+0x1b0/0x350 [ 24.915682] sock_sendmsg+0x4c/0x68 [ 24.919185] ___sys_sendmsg+0x288/0x2c8 [ 24.923037] __sys_sendmsg+0x7c/0xd0 [ 24.926628] __arm64_sys_sendmsg+0x2c/0x38 [ 24.930744] el0_svc_common.constprop.0+0x94/0x158 [ 24.935556] el0_svc_handler+0x34/0x90 [ 24.939322] el0_svc+0x8/0xc [ 24.942216] Code: 37280300 f9404023 91014262 aa1703e0 (f9401863) [ 24.948336] ---[ end trace cebbb9dcbed3b56f ]---
--- include/net/netfilter/nf_tables.h | 9 +++++++-- net/netfilter/nf_tables_api.c | 15 ++++++++++----- 2 files changed, 17 insertions(+), 7 deletions(-)
include/net/netfilter/nf_tables.h +7 -2
@@ -418,8 +418,7 @@ struct nft_set {unsigned char *udata;/* runtime data below here */ const struct nft_set_ops *ops____cacheline_aligned ; - u16 flags:13, - bound:1, + u16 flags:14, genmask:2;u8 klen;u8 dlen;
@@ -1337,12 +1336,15 @@ struct nft_trans_rule {struct nft_trans_set {struct nft_set *set;u32 set_id; +bool bound; };#define nft_trans_set (trans) \ (((struct nft_trans_set *)trans->data)->set)#define nft_trans_set_id (trans) \ (((struct nft_trans_set *)trans->data)->set_id) +#define nft_trans_set_bound (trans) \ + (((struct nft_trans_set *)trans->data)->bound)struct nft_trans_chain {bool update;
@@ -1373,12 +1375,15 @@ struct nft_trans_table {struct nft_trans_elem {struct nft_set *set;struct nft_set_elem elem; +bool bound; };#define nft_trans_elem_set (trans) \ (((struct nft_trans_elem *)trans->data)->set)#define nft_trans_elem (trans) \ (((struct nft_trans_elem *)trans->data)->elem) +#define nft_trans_elem_set_bound (trans) \ + (((struct nft_trans_elem *)trans->data)->bound)struct nft_trans_obj {struct nft_object *obj;
net/netfilter/nf_tables_api.c +10 -5
@@ -121,9 +121,14 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)return ;list_for_each_entry_reverse (trans, &net->nft.commit_list, list) { -if (trans->msg_type ==NFT_MSG_NEWSET && -nft_trans_set (trans) == set) { - set->bound = true; +switch (trans->msg_type) { +case NFT_MSG_NEWSET : +if (nft_trans_set (trans) == set) +nft_trans_set_bound (trans) = true; +break ; +case NFT_MSG_NEWSETELEM : +if (nft_trans_elem_set (trans) == set) +nft_trans_elem_set_bound (trans) = true;break ; } }
@@ -6656,7 +6661,7 @@ static int __nf_tables_abort(struct net *net)break ;case NFT_MSG_NEWSET : trans->ctx.table->use--; -if (nft_trans_set (trans)->bound) { +if (nft_trans_set_bound (trans)) {nft_trans_destroy (trans);break ; }
@@ -6668,7 +6673,7 @@ static int __nf_tables_abort(struct net *net)nft_trans_destroy (trans);break ;case NFT_MSG_NEWSETELEM : -if (nft_trans_elem_set (trans)->bound) { +if (nft_trans_elem_set_bound (trans)) {nft_trans_destroy (trans);break ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 3/45 rxrpc: Fix local endpoint refcounting
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit 730c5fd42c1e3652a065448fd235cb9fafb2bd10 ]
The object lifetime management on the rxrpc_local struct is broken in that the rxrpc_local_processor() function is expected to clean up and remove an object - but it may get requeued by packets coming in on the backing UDP socket once it starts running.
This may result in the assertion in rxrpc_local_rcu() firing because the memory has been scheduled for RCU destruction whilst still queued:
rxrpc: Assertion failed ------------[ cut here ]------------ kernel BUG at net/rxrpc/local_object.c:468!
Note that if the processor comes around before the RCU free function, it will just do nothing because ->dead is true.
Fix this by adding a separate refcount to count active users of the endpoint that causes the endpoint to be destroyed when it reaches 0.
The original refcount can then be used to refcount objects through the work processor and cause the memory to be rcu freed when that reaches 0.
--- net/rxrpc/af_rxrpc.c | 4 +- net/rxrpc/ar-internal.h | 5 ++- net/rxrpc/input.c | 16 ++++++-- net/rxrpc/local_object.c | 86 +++++++++++++++++++++++++--------------- 4 files changed, 72 insertions(+), 39 deletions(-)
net/rxrpc/af_rxrpc.c +2 -2
@@ -195,7 +195,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) service_in_use:write_unlock (&local->services_lock); -rxrpc_put_local (local); +rxrpc_unuse_local (local); ret = -EADDRINUSE ; error_unlock:release_sock (&rx->sk);
@@ -908,7 +908,7 @@ static int rxrpc_release_sock(struct sock *sk)rxrpc_queue_work (&rxnet->service_conn_reaper);rxrpc_queue_work (&rxnet->client_conn_reaper); -rxrpc_put_local (rx->local); +rxrpc_unuse_local (rx->local); rx->local =NULL ;key_put (rx->key); rx->key =NULL ;
net/rxrpc/ar-internal.h +4 -1
@@ -258,7 +258,8 @@ struct rxrpc_security {*/ struct rxrpc_local {struct rcu_head rcu; -atomic_t usage; +atomic_t active_users;/* Number of users of the local endpoint */ +atomic_t usage;/* Number of references to the structure */ struct rxrpc_net *rxnet;/* The network ns in which this resides */ struct list_head link;struct socket *socket;/* my UDP socket */
@@ -998,6 +999,8 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpcstruct rxrpc_local *rxrpc_get_local (struct rxrpc_local *);struct rxrpc_local *rxrpc_get_local_maybe (struct rxrpc_local *);void rxrpc_put_local (struct rxrpc_local *); +struct rxrpc_local *rxrpc_use_local (struct rxrpc_local *); +void rxrpc_unuse_local (struct rxrpc_local *);void rxrpc_queue_local (struct rxrpc_local *);void rxrpc_destroy_all_locals (struct rxrpc_net *);
net/rxrpc/input.c +12 -4
@@ -1106,8 +1106,12 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, {_enter ("%p,%p" , local, skb); -skb_queue_tail (&local->event_queue, skb); -rxrpc_queue_local (local); +if (rxrpc_get_local_maybe (local)) { +skb_queue_tail (&local->event_queue, skb); +rxrpc_queue_local (local); + }else { +rxrpc_free_skb (skb, rxrpc_skb_rx_freed); + } }/*
@@ -1117,8 +1121,12 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) {CHECK_SLAB_OKAY (&local->usage); -skb_queue_tail (&local->reject_queue, skb); -rxrpc_queue_local (local); +if (rxrpc_get_local_maybe (local)) { +skb_queue_tail (&local->reject_queue, skb); +rxrpc_queue_local (local); + }else { +rxrpc_free_skb (skb, rxrpc_skb_rx_freed); + } }/*
net/rxrpc/local_object.c +54 -32
153 lines not on this page · raw message
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 4/45 tools: bpftool: fix error message (prog -> object)
In reply to Sasha LevinFrom: Jakub Kicinski <[email protected]>
[ Upstream commit b3e78adcbf991a4e8b2ebb23c9889e968ec76c5f ]
Change an error message to work for any object being pinned not just programs.
--- tools/bpf/bpftool/common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/bpf/bpftool/common.c +1 -1
@@ -238,7 +238,7 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32)) fd =get_fd_by_id (id);if (fd <0 ) { -p_err ("can't get prog by id (%u): %s" , id,strerror (errno)); +p_err ("can't open object by id (%u): %s" , id,strerror (errno));return -1 ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 5/45 hv_netvsc: Fix a warning of suspicious RCU usage
In reply to Sasha LevinFrom: Dexuan Cui <[email protected]>
[ Upstream commit 6d0d779dca73cd5acb649c54f81401f93098b298 ]
This fixes a warning of "suspicious rcu_dereference_check() usage" when nload runs.
--- drivers/net/hyperv/netvsc_drv.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/net/hyperv/netvsc_drv.c +7 -2
@@ -1248,12 +1248,15 @@ static void netvsc_get_stats64(struct net_device *net, struct rtnl_link_stats64 *t) {struct net_device_context *ndev_ctx =netdev_priv (net); -struct netvsc_device *nvdev =rcu_dereference_rtnl (ndev_ctx->nvdev); +struct netvsc_device *nvdev;struct netvsc_vf_pcpu_stats vf_tot;int i; +rcu_read_lock (); + + nvdev =rcu_dereference (ndev_ctx->nvdev);if (!nvdev) -return ; + goto out;netdev_stats_to_stats64 (t, &net->stats);
@@ -1292,6 +1295,8 @@ static void netvsc_get_stats64(struct net_device *net, t->rx_packets += packets; t->multicast += multicast; } +out: +rcu_read_unlock (); }static int netvsc_set_mac_addr (struct net_device *ndev,void *p)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 6/45 net: tc35815: Explicitly check NET_IP_ALIGN is not zero in tc35815_rx
In reply to Sasha LevinFrom: Nathan Chancellor <[email protected]>
[ Upstream commit 125b7e0949d4e72b15c2b1a1590f8cece985a918 ]
clang warns:
drivers/net/ethernet/toshiba/tc35815.c:1507:30: warning: use of logical '&&' with constant operand [-Wconstant-logical-operand]
if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN)
^ ~~~~~~~~~~~~
drivers/net/ethernet/toshiba/tc35815.c:1507:30: note: use '&' for a
bitwise operation
if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN)
^~
&
drivers/net/ethernet/toshiba/tc35815.c:1507:30: note: remove constant to
silence this warning
if (!HAVE_DMA_RXALIGN(lp) && NET_IP_ALIGN)
~^~~~~~~~~~~~~~~1 warning generated.
Explicitly check that NET_IP_ALIGN is not zero, which matches how this is checked in other parts of the tree. Because NET_IP_ALIGN is a build time constant, this check will be constant folded away during optimization.
--- drivers/net/ethernet/toshiba/tc35815.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/toshiba/tc35815.c +1 -1
@@ -1497,7 +1497,7 @@ tc35815_rx(struct net_device *dev, int limit)pci_unmap_single (lp->pci_dev, lp->rx_skbs[cur_bd].skb_dma,RX_BUF_SIZE ,PCI_DMA_FROMDEVICE ); -if (!HAVE_DMA_RXALIGN (lp) &&NET_IP_ALIGN ) +if (!HAVE_DMA_RXALIGN (lp) &&NET_IP_ALIGN !=0 )memmove (skb->data, skb->data -NET_IP_ALIGN , pkt_len); data =skb_put (skb, pkt_len);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 7/45 Bluetooth: btqca: Add a short delay before downloading the NVM
In reply to Sasha LevinFrom: Matthias Kaehlcke <[email protected]>
[ Upstream commit 8059ba0bd0e4694e51c2ee6438a77b325f06c0d5 ]
On WCN3990 downloading the NVM sometimes fails with a "TLV response size mismatch" error:
[ 174.949955] Bluetooth: btqca.c:qca_download_firmware() hci0: QCA Downloading qca/crnv21.bin [ 174.958718] Bluetooth: btqca.c:qca_tlv_send_segment() hci0: QCA TLV response size mismatch
It seems the controller needs a short time after downloading the firmware before it is ready for the NVM. A delay as short as 1 ms seems sufficient, make it 10 ms just in case. No event is received during the delay, hence we don't just silently drop an extra event.
--- drivers/bluetooth/btqca.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/bluetooth/btqca.c +3 -0
@@ -363,6 +363,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,return err; } +/* Give the controller some time to get ready to receive the NVM */ +msleep (10 ); +/* Download NVM configuration */ config.type =TLV_TYPE_NVM ;if (soc_type ==QCA_WCN3990 )
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 8/45 Bluetooth: hidp: Let hidp_send_message return number of queued bytes
In reply to Sasha LevinFrom: Fabian Henneke <[email protected]>
[ Upstream commit 48d9cc9d85dde37c87abb7ac9bbec6598ba44b56 ]
Let hidp_send_message return the number of successfully queued bytes instead of an unconditional 0.
With the return value fixed to 0, other drivers relying on hidp, such as hidraw, can not return meaningful values from their respective implementations of write(). In particular, with the current behavior, a hidraw device's write() will have different return values depending on whether the device is connected via USB or Bluetooth, which makes it harder to abstract away the transport layer.
--- net/bluetooth/hidp/core.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
net/bluetooth/hidp/core.c +7 -2
@@ -101,6 +101,7 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock, {struct sk_buff *skb;struct sock *sk = sock->sk; +int ret;BT_DBG ("session %p data %p size %d" , session, data, size);
@@ -114,13 +115,17 @@ static int hidp_send_message(struct hidp_session *session, struct socket *sock, }skb_put_u8 (skb, hdr); -if (data && size >0 ) +if (data && size >0 ) {skb_put_data (skb, data, size); + ret = size; + }else { + ret =0 ; + }skb_queue_tail (transmit, skb);wake_up_interruptible (sk_sleep (sk)); -return 0 ; +return ret; } static int hidp_send_ctrl_message(struct hidp_session *session,
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 9/45 ibmveth: Convert multicast list size for little-endian system
In reply to Sasha LevinFrom: Thomas Falcon <[email protected]>
[ Upstream commit 66cf4710b23ab2adda11155684a2c8826f4fe732 ]
The ibm,mac-address-filters property defines the maximum number of addresses the hypervisor's multicast filter list can support. It is encoded as a big-endian integer in the OF device tree, but the virtual ethernet driver does not convert it for use by little-endian systems. As a result, the driver is not behaving as it should on affected systems when a large number of multicast addresses are assigned to the device.
--- drivers/net/ethernet/ibm/ibmveth.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/net/ethernet/ibm/ibmveth.c +5 -4
@@ -1618,7 +1618,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)struct net_device *netdev;struct ibmveth_adapter *adapter;unsigned char *mac_addr_p; -unsigned int *mcastFilterSize_p; +__be32 *mcastFilterSize_p;long ret;unsigned long ret_attr;
@@ -1640,8 +1640,9 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id)return -EINVAL ; } - mcastFilterSize_p = (unsigned int *)vio_get_attribute (dev, -VETH_MCAST_FILTER_SIZE ,NULL ); + mcastFilterSize_p = (__be32 *)vio_get_attribute (dev, +VETH_MCAST_FILTER_SIZE , +NULL );if (!mcastFilterSize_p) {dev_err (&dev->dev,"Can't find VETH_MCAST_FILTER_SIZE " "attribute\n" );
@@ -1658,7 +1659,7 @@ static int ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->vdev = dev; adapter->netdev = netdev; - adapter->mcastFilterSize = *mcastFilterSize_p; + adapter->mcastFilterSize =be32_to_cpu (*mcastFilterSize_p); adapter->pool_config =0 ;netif_napi_add (netdev, &adapter->napi, ibmveth_poll,16 );
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 10/45 gpio: Fix build error of function redefinition
In reply to Sasha LevinFrom: YueHaibing <[email protected]>
[ Upstream commit 68e03b85474a51ec1921b4d13204782594ef7223 ]
when do randbuilding, I got this error:
In file included from drivers/hwmon/pmbus/ucd9000.c:19:0:./include/linux/gpio/driver.h:576:1: error: redefinition of gpiochip_add_pin_range
gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, ^~~~~~~~~~~~~~~~~~~~~~
In file included from drivers/hwmon/pmbus/ucd9000.c:18:0:./include/linux/gpio.h:245:1: note: previous definition of gpiochip_add_pin_range was here
gpiochip_add_pin_range(struct gpio_chip *chip, const char *pinctl_name, ^~~~~~~~~~~~~~~~~~~~~~
--- include/linux/gpio.h | 24 ------------------------ 1 file changed, 24 deletions(-)
include/linux/gpio.h +0 -24
@@ -240,30 +240,6 @@ static inline int irq_to_gpio(unsigned irq)return -EINVAL ; } -static inline int -gpiochip_add_pin_range (struct gpio_chip *chip,const char *pinctl_name, -unsigned int gpio_offset,unsigned int pin_offset, -unsigned int npins) -{ -WARN_ON (1 ); -return -EINVAL ; -} - -static inline int -gpiochip_add_pingroup_range (struct gpio_chip *chip, -struct pinctrl_dev *pctldev, -unsigned int gpio_offset,const char *pin_group) -{ -WARN_ON (1 ); -return -EINVAL ; -} - -static inline void -gpiochip_remove_pin_ranges (struct gpio_chip *chip) -{ -WARN_ON (1 ); -} -static inline int devm_gpio_request (struct device *dev,unsigned gpio,const char *label) {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 11/45 netfilter: nft_flow_offload: skip tcp rst and fin packets
In reply to Sasha LevinFrom: Pablo Neira Ayuso <[email protected]>
[ Upstream commit dfe42be15fde16232340b8b2a57c359f51cc10d9 ]
TCP rst and fin packets do not qualify to place a flow into the flowtable. Most likely there will be no more packets after connection closure. Without this patch, this flow entry expires and connection tracking picks up the entry in ESTABLISHED state using the fixup timeout, which makes this look inconsistent to the user for a connection that is actually already closed.
--- net/netfilter/nft_flow_offload.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
net/netfilter/nft_flow_offload.c +6 -3
@@ -71,11 +71,11 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, {struct nft_flow_offload *priv =nft_expr_priv (expr);struct nf_flowtable *flowtable = &priv->flowtable->data; +struct tcphdr _tcph, *tcph =NULL ;enum ip_conntrack_info ctinfo;struct nf_flow_route route;struct flow_offload *flow;enum ip_conntrack_dir dir; -bool is_tcp = false;struct nf_conn *ct;int ret;
@@ -88,7 +88,10 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,switch (ct->tuplehash[IP_CT_DIR_ORIGINAL ].tuple.dst.protonum) {case IPPROTO_TCP : - is_tcp = true; + tcph =skb_header_pointer (pkt->skb, pkt->xt.thoff, +sizeof (_tcph), &_tcph); +if (unlikely (!tcph || tcph->fin || tcph->rst)) + goto out;break ;case IPPROTO_UDP :break ;
@@ -115,7 +118,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,if (!flow) goto err_flow_alloc; -if (is_tcp) { +if (tcph) { ct->proto.tcp.seen[0 ].flags |=IP_CT_TCP_FLAG_BE_LIBERAL ; ct->proto.tcp.seen[1 ].flags |=IP_CT_TCP_FLAG_BE_LIBERAL ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 12/45 rxrpc: Fix local endpoint replacement
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit b00df840fb4004b7087940ac5f68801562d0d2de ]
When a local endpoint (struct rxrpc_local) ceases to be in use by any AF_RXRPC sockets, it starts the process of being destroyed, but this doesn't cause it to be removed from the namespace endpoint list immediately as tearing it down isn't trivial and can't be done in softirq context, so it gets deferred.
If a new socket comes along that wants to bind to the same endpoint, a new rxrpc_local object will be allocated and rxrpc_lookup_local() will use list_replace() to substitute the new one for the old.
Then, when the dying object gets to rxrpc_local_destroyer(), it is removed unconditionally from whatever list it is on by calling list_del_init().
However, list_replace() doesn't reset the pointers in the replaced list_head and so the list_del_init() will likely corrupt the local endpoints list.
Fix this by using list_replace_init() instead.
--- net/rxrpc/local_object.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/rxrpc/local_object.c +1 -1
@@ -287,7 +287,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, goto sock_error;if (cursor != &rxnet->local_endpoints) -list_replace (cursor, &local->link); +list_replace_init (cursor, &local->link);else list_add_tail (&local->link, cursor); age ="new" ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 13/45 rxrpc: Fix read-after-free in rxrpc_queue_local()
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit 06d9532fa6b34f12a6d75711162d47c17c1add72 ]
rxrpc_queue_local() attempts to queue the local endpoint it is given and then, if successful, prints a trace line. The trace line includes the current usage count - but we're not allowed to look at the local endpoint at this point as we passed our ref on it to the workqueue.
Fix this by reading the usage count before queuing the work item.
Also fix the reading of local->debug_id for trace lines, which must be done with the same consideration as reading the usage count.
--- include/trace/events/rxrpc.h | 6 +++--- net/rxrpc/local_object.c | 19 ++++++++++--------- 2 files changed, 13 insertions(+), 12 deletions(-)
include/trace/events/rxrpc.h +3 -3
@@ -500,10 +500,10 @@ rxrpc_tx_points;#define E_ (a, b) { a, b } TRACE_EVENT(rxrpc_local, - TP_PROTO(struct rxrpc_local *local, enum rxrpc_local_trace op, + TP_PROTO(unsigned int local_debug_id, enum rxrpc_local_trace op, int usage, const void *where), - TP_ARGS(local, op, usage, where), + TP_ARGS(local_debug_id, op, usage, where), TP_STRUCT__entry( __field(unsigned int, local )
@@ -513,7 +513,7 @@ TRACE_EVENT(rxrpc_local, ), TP_fast_assign( - __entry->local = local->debug_id; + __entry->local = local_debug_id; __entry->op = op; __entry->usage = usage; __entry->where = where;
net/rxrpc/local_object.c +10 -9
@@ -97,7 +97,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->debug_id =atomic_inc_return (&rxrpc_debug_id);memcpy (&local->srx, srx,sizeof (*srx)); local->srx.srx_service =0 ; -trace_rxrpc_local (local, rxrpc_local_new,1 ,NULL ); +trace_rxrpc_local (local->debug_id, rxrpc_local_new,1 ,NULL ); }_leave (" = %p" , local);
@@ -325,7 +325,7 @@ struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local)int n; n =atomic_inc_return (&local->usage); -trace_rxrpc_local (local, rxrpc_local_got, n, here); +trace_rxrpc_local (local->debug_id, rxrpc_local_got, n, here);return local; }
@@ -339,7 +339,8 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)if (local) {int n =atomic_fetch_add_unless (&local->usage,1 ,0 );if (n >0 ) -trace_rxrpc_local (local, rxrpc_local_got, n +1 , here); +trace_rxrpc_local (local->debug_id, rxrpc_local_got, + n +1 , here);else local =NULL ; }
@@ -347,16 +348,16 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) }/* -* Queue a local endpoint unless it has become unreferenced and pass the -* caller's reference to the work item. +* Queue a local endpoint and pass the caller's reference to the work item. */ void rxrpc_queue_local (struct rxrpc_local *local) {const void *here =__builtin_return_address (0 ); +unsigned int debug_id = local->debug_id; +int n =atomic_read (&local->usage);if (rxrpc_queue_work (&local->processor)) -trace_rxrpc_local (local, rxrpc_local_queued, -atomic_read (&local->usage), here); +trace_rxrpc_local (debug_id, rxrpc_local_queued, n, here);else rxrpc_put_local (local); }
@@ -371,7 +372,7 @@ void rxrpc_put_local(struct rxrpc_local *local)if (local) { n =atomic_dec_return (&local->usage); -trace_rxrpc_local (local, rxrpc_local_put, n, here); +trace_rxrpc_local (local->debug_id, rxrpc_local_put, n, here);if (n ==0 )call_rcu (&local->rcu, rxrpc_local_rcu);
@@ -458,7 +459,7 @@ static void rxrpc_local_processor(struct work_struct *work) container_of(work, struct rxrpc_local, processor);bool again; -trace_rxrpc_local (local, rxrpc_local_processing, +trace_rxrpc_local (local->debug_id, rxrpc_local_processing,atomic_read (&local->usage),NULL ); do {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 14/45 drm/mediatek: use correct device to import PRIME buffers
In reply to Sasha LevinFrom: Alexandre Courbot <[email protected]>
[ Upstream commit 4c6f3196e6ea111c456c6086dc3f57d4706b0b2d ]
PRIME buffers should be imported using the DMA device. To this end, use a custom import function that mimics drm_gem_prime_import_dev(), but passes the correct device.
--- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)
drivers/gpu/drm/mediatek/mtk_drm_drv.c +13 -1
@@ -327,6 +327,18 @@ static const struct file_operations mtk_drm_fops = { .compat_ioctl = drm_compat_ioctl, }; +/* +* We need to override this because the device used to import the memory is +* not dev->dev, as drm_gem_prime_import() expects. +*/ +struct drm_gem_object *mtk_drm_gem_prime_import (struct drm_device *dev, +struct dma_buf *dma_buf) +{ +struct mtk_drm_private *private = dev->dev_private; + +return drm_gem_prime_import_dev (dev, dma_buf, private->dma_dev); +} +static struct drm_driver mtk_drm_driver = { .driver_features =DRIVER_MODESET |DRIVER_GEM |DRIVER_PRIME |DRIVER_ATOMIC ,
@@ -338,7 +350,7 @@ static struct drm_driver mtk_drm_driver = { .prime_handle_to_fd = drm_gem_prime_handle_to_fd, .prime_fd_to_handle = drm_gem_prime_fd_to_handle, .gem_prime_export = drm_gem_prime_export, - .gem_prime_import = drm_gem_prime_import, + .gem_prime_import = mtk_drm_gem_prime_import, .gem_prime_get_sg_table = mtk_gem_prime_get_sg_table, .gem_prime_import_sg_table = mtk_gem_prime_import_sg_table, .gem_prime_mmap = mtk_drm_gem_mmap_buf,
Signature · 6 lines
2.20.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 15/45 drm/mediatek: set DMA max segment size
In reply to Sasha LevinFrom: Alexandre Courbot <[email protected]>
[ Upstream commit 070955558e820b9a89c570b91b1f21762f62b288 ]
This driver requires imported PRIME buffers to appear contiguously in its IO address space. Make sure this is the case by setting the maximum DMA segment size to a more suitable value than the default 64KB.
--- drivers/gpu/drm/mediatek/mtk_drm_drv.c | 35 ++++++++++++++++++++++++-- drivers/gpu/drm/mediatek/mtk_drm_drv.h | 2 ++ 2 files changed, 35 insertions(+), 2 deletions(-)
drivers/gpu/drm/mediatek/mtk_drm_drv.c +33 -2
@@ -220,6 +220,7 @@ static int mtk_drm_kms_init(struct drm_device *drm)struct mtk_drm_private *private = drm->dev_private;struct platform_device *pdev;struct device_node *np; +struct device *dma_dev;int ret;if (!iommu_present (&platform_bus_type))
@@ -282,7 +283,29 @@ static int mtk_drm_kms_init(struct drm_device *drm) goto err_component_unbind; } - private->dma_dev = &pdev->dev; + dma_dev = &pdev->dev; + private->dma_dev = dma_dev; + +/* +* Configure the DMA segment size to make sure we get contiguous IOVA +* when importing PRIME buffers. +*/ +if (!dma_dev->dma_parms) { + private->dma_parms_allocated = true; + dma_dev->dma_parms = +devm_kzalloc (drm->dev,sizeof (*dma_dev->dma_parms), +GFP_KERNEL ); + } +if (!dma_dev->dma_parms) { + ret = -ENOMEM ; + goto err_component_unbind; + } + + ret =dma_set_max_seg_size (dma_dev, (unsigned int )DMA_BIT_MASK (32 )); +if (ret) { +dev_err (dma_dev,"Failed to set DMA segment size\n" ); + goto err_unset_dma_parms; + }/* * We don't use the drm_irq_install() helpers provided by the DRM
@@ -292,13 +315,16 @@ static int mtk_drm_kms_init(struct drm_device *drm) drm->irq_enabled = true; ret =drm_vblank_init (drm,MAX_CRTC );if (ret <0 ) - goto err_component_unbind; + goto err_unset_dma_parms;drm_kms_helper_poll_init (drm);drm_mode_config_reset (drm);return 0 ; +err_unset_dma_parms: +if (private->dma_parms_allocated) + dma_dev->dma_parms =NULL ; err_component_unbind:component_unbind_all (drm->dev, drm); err_config_cleanup:
@@ -309,9 +335,14 @@ static int mtk_drm_kms_init(struct drm_device *drm)static void mtk_drm_kms_deinit (struct drm_device *drm) { +struct mtk_drm_private *private = drm->dev_private; +drm_kms_helper_poll_fini (drm);drm_atomic_helper_shutdown (drm); +if (private->dma_parms_allocated) + private->dma_dev->dma_parms =NULL ; +component_unbind_all (drm->dev, drm);drm_mode_config_cleanup (drm); }
drivers/gpu/drm/mediatek/mtk_drm_drv.h +2 -0
@@ -59,6 +59,8 @@ struct mtk_drm_private { } commit;struct drm_atomic_state *suspend_state; + +bool dma_parms_allocated; };extern struct platform_driver mtk_ddp_driver;
Signature · 6 lines
2.20.1 _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Sasha Levin
maintainerPATCH 16/45 scsi: qla2xxx: Fix gnl.l memory leak on adapter init failure
In reply to Sasha LevinFrom: Bill Kuzeja <[email protected]>
[ Upstream commit 26fa656e9a0cbccddf7db132ea020d2169dbe46e ]
If HBA initialization fails unexpectedly (exiting via probe_failed:), we may fail to free vha->gnl.l. So that we don't attempt to double free, set this pointer to NULL after a free and check for NULL at probe_failed: so we know whether or not to call dma_free_coherent.
--- drivers/scsi/qla2xxx/qla_attr.c | 2 ++ drivers/scsi/qla2xxx/qla_os.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-)
drivers/scsi/qla2xxx/qla_attr.c +2 -0
@@ -2191,6 +2191,8 @@ qla24xx_vport_delete(struct fc_vport *fc_vport)dma_free_coherent (&ha->pdev->dev, vha->gnl.size, vha->gnl.l, vha->gnl.ldma); + vha->gnl.l =NULL ; +vfree (vha->scan.l);if (vha->qpair && vha->qpair->vp_idx == vha->vp_idx) {
drivers/scsi/qla2xxx/qla_os.c +10 -1
@@ -3395,6 +3395,12 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)return 0 ; probe_failed: +if (base_vha->gnl.l) { +dma_free_coherent (&ha->pdev->dev, base_vha->gnl.size, + base_vha->gnl.l, base_vha->gnl.ldma); + base_vha->gnl.l =NULL ; + } +if (base_vha->timer_active)qla2x00_stop_timer (base_vha); base_vha->flags.online =0 ;
@@ -3624,7 +3630,7 @@ qla2x00_remove_one(struct pci_dev *pdev)if (!atomic_read (&pdev->enable_cnt)) {dma_free_coherent (&ha->pdev->dev, base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); - + base_vha->gnl.l =NULL ;scsi_host_put (base_vha->host);kfree (ha);pci_set_drvdata (pdev,NULL );
@@ -3663,6 +3669,8 @@ qla2x00_remove_one(struct pci_dev *pdev)dma_free_coherent (&ha->pdev->dev, base_vha->gnl.size, base_vha->gnl.l, base_vha->gnl.ldma); + base_vha->gnl.l =NULL ; +vfree (base_vha->scan.l);if (IS_QLAFX00 (ha))
@@ -4602,6 +4610,7 @@ struct scsi_qla_host *qla2x00_create_host(struct scsi_host_template *sht, "Alloc failed for scan database.\n");dma_free_coherent (&ha->pdev->dev, vha->gnl.size, vha->gnl.l, vha->gnl.ldma); + vha->gnl.l =NULL ;scsi_remove_host (vha->host);return NULL ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 17/45 scsi: target: tcmu: avoid use-after-free after command timeout
In reply to Sasha LevinFrom: Dmitry Fomichev <[email protected]>
[ Upstream commit a86a75865ff4d8c05f355d1750a5250aec89ab15 ]
In tcmu_handle_completion() function, the variable called read_len is always initialized with a value taken from se_cmd structure. If this function is called to complete an expired (timed out) out command, the session command pointed by se_cmd is likely to be already deallocated by the target core at that moment. As the result, this access triggers a use-after-free warning from KASAN.
This patch fixes the code not to touch se_cmd when completing timed out TCMU commands. It also resets the pointer to se_cmd at the time when the TCMU_CMD_BIT_EXPIRED flag is set because it is going to become invalid after calling target_complete_cmd() later in the same function, tcmu_check_expired_cmd().
--- drivers/target/target_core_user.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/target/target_core_user.c +7 -2
@@ -1143,14 +1143,16 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry *struct se_cmd *se_cmd = cmd->se_cmd;struct tcmu_dev *udev = cmd->tcmu_dev;bool read_len_valid = false; -uint32_t read_len = se_cmd->data_length; +uint32_t read_len;/* * cmd has been completed already from timeout, just reclaim * data area space and free cmd */ -if (test_bit (TCMU_CMD_BIT_EXPIRED , &cmd->flags)) +if (test_bit (TCMU_CMD_BIT_EXPIRED , &cmd->flags)) { +WARN_ON_ONCE (se_cmd); goto out; + }list_del_init (&cmd->queue_entry);
@@ -1163,6 +1165,7 @@ static void tcmu_handle_completion(struct tcmu_cmd *cmd, struct tcmu_cmd_entry * goto done; } + read_len = se_cmd->data_length;if (se_cmd->data_direction =DMA_FROM_DEVICE && (entry->hdr.uflags &TCMU_UFLAG_READ_LEN ) && entry->rsp.read_len) { read_len_valid = true;
@@ -1318,6 +1321,7 @@ static int tcmu_check_expired_cmd(int id, void *p, void *data)*/ scsi_status =SAM_STAT_CHECK_CONDITION ;list_del_init (&cmd->queue_entry); + cmd->se_cmd =NULL ; }else {list_del_init (&cmd->queue_entry);idr_remove (&udev->commands, id);
@@ -2036,6 +2040,7 @@ static void tcmu_reset_ring(struct tcmu_dev *udev, u8 err_level)idr_remove (&udev->commands, i);if (!test_bit (TCMU_CMD_BIT_EXPIRED , &cmd->flags)) { +WARN_ON (!cmd->se_cmd);list_del_init (&cmd->queue_entry);if (err_level =1 ) {/*
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 18/45 cxgb4: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit c554336efa9bbc28d6ec14efbee3c7d63c61a34f ]
In blocked_fl_write(), 't' is not deallocated if bitmap_parse_user() fails, leading to a memory leak bug. To fix this issue, free t before returning the error.
--- drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +3 -1
@@ -3276,8 +3276,10 @@ static ssize_t blocked_fl_write(struct file *filp, const char __user *ubuf,return -ENOMEM ; err =bitmap_parse_user (ubuf, count, t, adap->sge.egr_sz); -if (err) +if (err) { +kvfree (t);return err; + }bitmap_copy (adap->sge.blocked_fl, t, adap->sge.egr_sz);kvfree (t);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 19/45 liquidio: add cleanup in octeon_setup_iq()
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 6f967f8b1be7001b31c46429f2ee7d275af2190f ]
If oct->fn_list.enable_io_queues() fails, no cleanup is executed, leading to memory/resource leaks. To fix this issue, invoke octeon_delete_instr_queue() before returning from the function.
--- drivers/net/ethernet/cavium/liquidio/request_manager.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/cavium/liquidio/request_manager.c +3 -1
@@ -238,8 +238,10 @@ int octeon_setup_iq(struct octeon_device *oct, } oct->num_iqs++; -if (oct->fn_list.enable_io_queues (oct)) +if (oct->fn_list.enable_io_queues (oct)) { +octeon_delete_instr_queue (oct, iq_no);return 1 ; + }return 0 ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 20/45 net: myri10ge: fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 20fb7c7a39b5c719e2e619673b5f5729ee7d2306 ]
In myri10ge_probe(), myri10ge_alloc_slices() is invoked to allocate slices related structures. Later on, myri10ge_request_irq() is used to get an irq. However, if this process fails, the allocated slices related structures are not deallocated, leading to memory leaks. To fix this issue, revise the target label of the goto statement to 'abort_with_slices'.
--- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/myricom/myri10ge/myri10ge.c +1 -1
@@ -3922,7 +3922,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent)* setup (if available). */ status =myri10ge_request_irq (mgp);if (status !=0 ) - goto abort_with_firmware; + goto abort_with_slices;myri10ge_free_irq (mgp);/* Save configuration space to be restored if the
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 21/45 lan78xx: Fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit b9cbf8a64865b50fd0f4a3915fa00ac7365cdf8f ]
In lan78xx_probe(), a new urb is allocated through usb_alloc_urb() and saved to 'dev->urb_intr'. However, in the following execution, if an error occurs, 'dev->urb_intr' is not deallocated, leading to memory leaks. To fix this issue, invoke usb_free_urb() to free the allocated urb before returning from the function.
--- drivers/net/usb/lan78xx.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/net/usb/lan78xx.c +5 -3
@@ -3799,7 +3799,7 @@ static int lan78xx_probe(struct usb_interface *intf, ret =register_netdev (netdev);if (ret !=0 ) {netif_err (dev, probe, netdev,"couldn't register the device\n" ); - goto out3; + goto out4; }usb_set_intfdata (intf, dev);
@@ -3814,12 +3814,14 @@ static int lan78xx_probe(struct usb_interface *intf, ret =lan78xx_phy_init (dev);if (ret <0 ) - goto out4; + goto out5;return 0 ; -out4: +out5:unregister_netdev (netdev); +out4: +usb_free_urb (dev->urb_intr); out3:lan78xx_unbind (dev, intf); out2:
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 22/45 vfs: fix page locking deadlocks when deduping files
In reply to Sasha LevinFrom: "Darrick J. Wong" <[email protected]>
[ Upstream commit edc58dd0123b552453a74369bd0c8d890b497b4b ]
When dedupe wants to use the page cache to compare parts of two files for dedupe, we must be very careful to handle locking correctly. The current code doesn't do this. It must lock and unlock the page only once if the two pages are the same, since the overlapping range check doesn't catch this when blocksize < pagesize. If the pages are distinct but from the same file, we must observe page locking order and lock them in order of increasing offset to avoid clashing with writeback locking.
--- fs/read_write.c | 49 +++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 41 insertions(+), 8 deletions(-)
fs/read_write.c +41 -8
@@ -1888,10 +1888,7 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, }EXPORT_SYMBOL (vfs_clone_file_range); -/* -* Read a page's worth of file data into the page cache. Return the page -* locked. -*/ +/* Read a page's worth of file data into the page cache. */ static struct page *vfs_dedupe_get_page (struct inode *inode,loff_t offset) {struct address_space *mapping;
@@ -1907,10 +1904,32 @@ static struct page *vfs_dedupe_get_page(struct inode *inode, loff_t offset)put_page (page);return ERR_PTR (-EIO ); } -lock_page (page);return page; } +/* +* Lock two pages, ensuring that we lock in offset order if the pages are from +* the same file. +*/ +static void vfs_lock_two_pages (struct page *page1,struct page *page2) +{ +/* Always lock in order of increasing index. */ +if (page1->index > page2->index) +swap (page1, page2); + +lock_page (page1); +if (page1 != page2) +lock_page (page2); +} + +/* Unlock two pages, being careful not to unlock the same page twice. */ +static void vfs_unlock_two_pages (struct page *page1,struct page *page2) +{ +unlock_page (page1); +if (page1 != page2) +unlock_page (page2); +} +/* * Compare extents of two files to see if they are the same. * Caller must have locked both inodes to prevent write races.
@@ -1948,10 +1967,24 @@ int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, dest_page =vfs_dedupe_get_page (dest, destoff);if (IS_ERR (dest_page)) { error =PTR_ERR (dest_page); -unlock_page (src_page);put_page (src_page); goto out_error; } + +vfs_lock_two_pages (src_page, dest_page); + +/* +* Now that we've locked both pages, make sure they're still +* mapped to the file data we're interested in. If not, +* someone is invalidating pages on us and we lose. +*/ +if (!PageUptodate (src_page) || !PageUptodate (dest_page) || + src_page->mapping != src->i_mapping || + dest_page->mapping != dest->i_mapping) { + same = false; + goto unlock; + } + src_addr =kmap_atomic (src_page); dest_addr =kmap_atomic (dest_page);
@@ -1963,8 +1996,8 @@ int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,kunmap_atomic (dest_addr);kunmap_atomic (src_addr); -unlock_page (dest_page); -unlock_page (src_page); +unlock: +vfs_unlock_two_pages (src_page, dest_page);put_page (dest_page);put_page (src_page);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 23/45 cx82310_eth: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 1eca92eef18719027d394bf1a2d276f43e7cf886 ]
In cx82310_bind(), 'dev->partial_data' is allocated through kmalloc(). Then, the execution waits for the firmware to become ready. If the firmware is not ready in time, the execution is terminated. However, the allocated 'dev->partial_data' is not deallocated on this path, leading to a memory leak bug. To fix this issue, free 'dev->partial_data' before returning the error.
--- drivers/net/usb/cx82310_eth.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/usb/cx82310_eth.c +2 -1
@@ -175,7 +175,8 @@ static int cx82310_bind(struct usbnet *dev, struct usb_interface *intf) }if (!timeout) {dev_err (&udev->dev,"firmware not ready in time\n" ); -return -ETIMEDOUT ; + ret = -ETIMEDOUT ; + goto err; }/* enable ethernet mode (?) */
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 24/45 net: kalmia: fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit f1472cb09f11ddb41d4be84f0650835cb65a9073 ]
In kalmia_init_and_get_ethernet_addr(), 'usb_buf' is allocated through kmalloc(). In the following execution, if the 'status' returned by kalmia_send_init_packet() is not 0, 'usb_buf' is not deallocated, leading to memory leaks. To fix this issue, add the 'out' label to free 'usb_buf'.
--- drivers/net/usb/kalmia.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/net/usb/kalmia.c +3 -3
@@ -117,16 +117,16 @@ kalmia_init_and_get_ethernet_addr(struct usbnet *dev, u8 *ethernet_addr) status =kalmia_send_init_packet (dev, usb_buf,ARRAY_SIZE (init_msg_1), usb_buf,24 );if (status !=0 ) -return status; + goto out;memcpy (usb_buf, init_msg_2,12 ); status =kalmia_send_init_packet (dev, usb_buf,ARRAY_SIZE (init_msg_2), usb_buf,28 );if (status !=0 ) -return status; + goto out;memcpy (ethernet_addr, usb_buf +10 ,ETH_ALEN ); - +out:kfree (usb_buf);return status; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 25/45 ibmvnic: Unmap DMA address of TX descriptor buffers after use
In reply to Sasha LevinFrom: Thomas Falcon <[email protected]>
[ Upstream commit 80f0fe0934cd3daa13a5e4d48a103f469115b160 ]
There's no need to wait until a completion is received to unmap TX descriptor buffers that have been passed to the hypervisor. Instead unmap it when the hypervisor call has completed. This patch avoids the possibility that a buffer will not be unmapped because a TX completion is lost or mishandled.
--- drivers/net/ethernet/ibm/ibmvnic.c | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-)
drivers/net/ethernet/ibm/ibmvnic.c +2 -9
@@ -1586,6 +1586,8 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) lpar_rc =send_subcrq_indirect (adapter, handle_array[queue_num], (u64 )tx_buff->indir_dma, (u64 )num_entries); +dma_unmap_single (dev, tx_buff->indir_dma, +sizeof (tx_buff->indir_arr),DMA_TO_DEVICE ); }else { tx_buff->num_entries = num_entries; lpar_rc = send_subcrq(adapter, handle_array[queue_num],
@@ -2747,7 +2749,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter,union sub_crq *next;int index;int i, j; -u8 *first; restart_loop:while (pending_scrq (adapter, scrq)) {
@@ -2777,14 +2778,6 @@ static int ibmvnic_complete_tx(struct ibmvnic_adapter *adapter, txbuff->data_dma[j] =0 ; } -/* if sub_crq was sent indirectly */ - first = &txbuff->indir_arr[0 ].generic.first; -if (*first ==IBMVNIC_CRQ_CMD ) { -dma_unmap_single (dev, txbuff->indir_dma, -sizeof (txbuff->indir_arr), -DMA_TO_DEVICE ); - *first =0 ; - }if (txbuff->last_frag) {dev_kfree_skb_any (txbuff->skb);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 26/45 net: cavium: fix driver name
In reply to Sasha LevinFrom: Stephen Hemminger <[email protected]>
[ Upstream commit 3434341004a380f4e47c3a03d4320d43982162a0 ]
The driver name gets exposed in sysfs under /sys/bus/pci/drivers so it should look like other devices. Change it to be common format (instead of "Cavium PTP").
This is a trivial fix that was observed by accident because Debian kernels were building this driver into kernel (bug).
--- drivers/net/ethernet/cavium/common/cavium_ptp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/cavium/common/cavium_ptp.c +1 -1
@@ -10,7 +10,7 @@#include "cavium_ptp.h" -#define DRV_NAME "Cavium PTP Driver" +#define DRV_NAME "cavium_ptp"#define PCI_DEVICE_ID_CAVIUM_PTP 0xA00C#define PCI_DEVICE_ID_CAVIUM_RST 0xA00E
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 27/45 wimax/i2400m: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 44ef3a03252844a8753479b0cea7f29e4a804bdc ]
In i2400m_barker_db_init(), 'options_orig' is allocated through kstrdup() to hold the original command line options. Then, the options are parsed. However, if an error occurs during the parsing process, 'options_orig' is not deallocated, leading to a memory leak bug. To fix this issue, free 'options_orig' before returning the error.
--- drivers/net/wimax/i2400m/fw.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/wimax/i2400m/fw.c +3 -1
@@ -351,13 +351,15 @@ int i2400m_barker_db_init(const char *_options) } result =i2400m_barker_db_add (barker);if (result <0 ) - goto error_add; + goto error_parse_add; }kfree (options_orig); }return 0 ; +error_parse_add: error_parse: +kfree (options_orig); error_add:kfree (i2400m_barker_db);return result;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 28/45 ravb: Fix use-after-free ravb_tstamp_skb
In reply to Sasha LevinFrom: Tho Vu <[email protected]>
[ Upstream commit cfef46d692efd852a0da6803f920cc756eea2855 ]
When a Tx timestamp is requested, a pointer to the skb is stored in the ravb_tstamp_skb struct. This was done without an skb_get. There exists the possibility that the skb could be freed by ravb_tx_free (when ravb_tx_free is called from ravb_start_xmit) before the timestamp was processed, leading to a use-after-free bug.
Use skb_get when filling a ravb_tstamp_skb struct, and add appropriate frees/consumes when a ravb_tstamp_skb struct is freed.
--- drivers/net/ethernet/renesas/ravb_main.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/net/ethernet/renesas/ravb_main.c +6 -2
@@ -1,7 +1,7 @@// SPDX-License-Identifier: GPL-2.0 /* Renesas Ethernet AVB device driver * -* Copyright (C) 2014-2015 Renesas Electronics Corporation +* Copyright (C) 2014-2019 Renesas Electronics Corporation * Copyright (C) 2015 Renesas Solutions Corp. * Copyright (C) 2015-2016 Cogent Embedded, Inc. <[email protected]> *
@@ -514,7 +514,10 @@ static void ravb_get_tx_tstamp(struct net_device *ndev)kfree (ts_skb);if (tag == tfa_tag) {skb_tstamp_tx (skb, &shhwtstamps); +dev_consume_skb_any (skb);break ; + }else { +dev_kfree_skb_any (skb); } }ravb_modify (ndev,TCCR ,TCCR_TFR ,TCCR_TFR );
@@ -1556,7 +1559,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) DMA_TO_DEVICE); goto unmap; } - ts_skb->skb = skb; + ts_skb->skb =skb_get (skb); ts_skb->tag = priv->ts_skb_tag++; priv->ts_skb_tag &=0x3ff ;list_add_tail (&ts_skb->list, &priv->ts_skb_list);
@@ -1685,6 +1688,7 @@ static int ravb_close(struct net_device *ndev)/* Clear the timestamp list */ list_for_each_entry_safe (ts_skb, ts_skb2, &priv->ts_skb_list, list) {list_del (&ts_skb->list); +kfree_skb (ts_skb->skb);kfree (ts_skb); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 29/45 kprobes: Fix potential deadlock in kprobe_optimizer()
In reply to Sasha LevinFrom: Andrea Righi <[email protected]>
[ Upstream commit f1c6ece23729257fb46562ff9224cf5f61b818da ]
lockdep reports the following deadlock scenario:
WARNING: possible circular locking dependency detected
kworker/1:1/48 is trying to acquire lock:
000000008d7a62b2 (text_mutex){+.+.}, at: kprobe_optimizer+0x163/0x290
but task is already holding lock:
00000000850b5e2d (module_mutex){+.+.}, at: kprobe_optimizer+0x31/0x290
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (module_mutex){+.+.}:
__mutex_lock+0xac/0x9f0
mutex_lock_nested+0x1b/0x20
set_all_modules_text_rw+0x22/0x90
ftrace_arch_code_modify_prepare+0x1c/0x20
ftrace_run_update_code+0xe/0x30
ftrace_startup_enable+0x2e/0x50
ftrace_startup+0xa7/0x100
register_ftrace_function+0x27/0x70
arm_kprobe+0xb3/0x130
enable_kprobe+0x83/0xa0
enable_trace_kprobe.part.0+0x2e/0x80
kprobe_register+0x6f/0xc0
perf_trace_event_init+0x16b/0x270
perf_kprobe_init+0xa7/0xe0
perf_kprobe_event_init+0x3e/0x70
perf_try_init_event+0x4a/0x140
perf_event_alloc+0x93a/0xde0
__do_sys_perf_event_open+0x19f/0xf30
__x64_sys_perf_event_open+0x20/0x30
do_syscall_64+0x65/0x1d0
entry_SYSCALL_64_after_hwframe+0x49/0xbe-> #0 (text_mutex){+.+.}:
__lock_acquire+0xfcb/0x1b60
lock_acquire+0xca/0x1d0
__mutex_lock+0xac/0x9f0
mutex_lock_nested+0x1b/0x20
kprobe_optimizer+0x163/0x290
process_one_work+0x22b/0x560
worker_thread+0x50/0x3c0
kthread+0x112/0x150
ret_from_fork+0x3a/0x50other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(module_mutex);
lock(text_mutex);
lock(module_mutex); lock(text_mutex);
*** DEADLOCK ***
As a reproducer I've been using bcc's funccount.py
(https://github.com/iovisor/bcc/blob/master/tools/funccount.py),
for example:
# ./funccount.py '*interrupt*'
That immediately triggers the lockdep splat.
Fix by acquiring text_mutex before module_mutex in kprobe_optimizer().
--- kernel/kprobes.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
kernel/kprobes.c +4 -4
@@ -483,6 +483,7 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);*/ static void do_optimize_kprobes (void ) { +lockdep_assert_held (&text_mutex);/* * The optimization/unoptimization refers online_cpus via * stop_machine() and cpu-hotplug modifies online_cpus.
@@ -500,9 +501,7 @@ static void do_optimize_kprobes(void) list_empty(&optimizing_list))return ; -mutex_lock (&text_mutex);arch_optimize_kprobes (&optimizing_list); -mutex_unlock (&text_mutex); }/*
@@ -513,6 +512,7 @@ static void do_unoptimize_kprobes(void) {struct optimized_kprobe *op, *tmp; +lockdep_assert_held (&text_mutex);/* See comment in do_optimize_kprobes() */ lockdep_assert_cpus_held ();
@@ -520,7 +520,6 @@ static void do_unoptimize_kprobes(void)if (list_empty (&unoptimizing_list))return ; -mutex_lock (&text_mutex);arch_unoptimize_kprobes (&unoptimizing_list, &freeing_list);/* Loop free_list for disarming */ list_for_each_entry_safe (op, tmp, &freeing_list, list) {
@@ -537,7 +536,6 @@ static void do_unoptimize_kprobes(void) }else list_del_init (&op->list); } -mutex_unlock (&text_mutex); }/* Reclaim all kprobes on the free_list */
@@ -563,6 +561,7 @@ static void kprobe_optimizer(struct work_struct *work) {mutex_lock (&kprobe_mutex);cpus_read_lock (); +mutex_lock (&text_mutex);/* Lock modules while optimizing kprobes */ mutex_lock (&module_mutex);
@@ -590,6 +589,7 @@ static void kprobe_optimizer(struct work_struct *work)do_free_cleaned_kprobes ();mutex_unlock (&module_mutex); +mutex_unlock (&text_mutex);cpus_read_unlock ();mutex_unlock (&kprobe_mutex);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 30/45 HID: cp2112: prevent sleeping function called from invalid context
In reply to Sasha LevinFrom: Benjamin Tissoires <[email protected]>
[ Upstream commit 2d05dba2b25ecb0f8fc3a0b4eb2232da6454a47b ]
When calling request_threaded_irq() with a CP2112, the function cp2112_gpio_irq_startup() is called in a IRQ context.
Therefore we can not sleep, and we can not callcp2112_gpio_direction_input() there.
Move the call to cp2112_gpio_direction_input() earlier to have a working driver.
--- drivers/hid/hid-cp2112.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/hid/hid-cp2112.c +6 -2
@@ -1160,8 +1160,6 @@ static unsigned int cp2112_gpio_irq_startup(struct irq_data *d)INIT_DELAYED_WORK (&dev->gpio_poll_worker, cp2112_gpio_poll_callback); -cp2112_gpio_direction_input (gc, d->hwirq); -if (!dev->gpio_poll) { dev->gpio_poll = true;schedule_delayed_work (&dev->gpio_poll_worker,0 );
@@ -1209,6 +1207,12 @@ static int __maybe_unused cp2112_allocate_irq(struct cp2112_device *dev,return PTR_ERR (dev->desc[pin]); } + ret =cp2112_gpio_direction_input (&dev->gc, pin); +if (ret <0 ) { +dev_err (dev->gc.parent,"Failed to set GPIO to input dir\n" ); + goto err_desc; + } + ret =gpiochip_lock_as_irq (&dev->gc, pin);if (ret) {dev_err (dev->gc.parent,"Failed to lock GPIO as interrupt\n" );
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 31/45 x86/boot/compressed/64: Fix boot on machines with broken E820 table
In reply to Sasha LevinFrom: "Kirill A. Shutemov" <[email protected]>
[ Upstream commit 0a46fff2f9108c2c44218380a43a736cf4612541 ]
BIOS on Samsung 500C Chromebook reports very rudimentary E820 table that consists of 2 entries:
BIOS-e820: [mem 0x0000000000000000-0x0000000000000fff] usable
BIOS-e820: [mem 0x00000000fffff000-0x00000000ffffffff] reserved
It breaks logic in find_trampoline_placement(): bios_start lands on the end of the first 4k page and trampoline start gets placed below 0.
Detect underflow and don't touch bios_start for such cases. It makes kernel ignore E820 table on machines that doesn't have two usable pages below BIOS_START_MAX.
--- arch/x86/boot/compressed/pgtable_64.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
arch/x86/boot/compressed/pgtable_64.c +10 -3
@@ -73,6 +73,8 @@ static unsigned long find_trampoline_placement(void)/* Find the first usable memory region under bios_start. */ for (i = boot_params->e820_entries -1 ; i >=0 ; i--) { +unsigned long new; + entry = &boot_params->e820_table[i];/* Skip all entries above bios_start. */
@@ -85,15 +87,20 @@ static unsigned long find_trampoline_placement(void)/* Adjust bios_start to the end of the entry if needed. */ if (bios_start > entry->addr + entry->size) - bios_start = entry->addr + entry->size; + new = entry->addr + entry->size;/* Keep bios_start page-aligned. */ - bios_start =round_down (bios_start,PAGE_SIZE ); + new =round_down (new,PAGE_SIZE );/* Skip the entry if it's too small. */ -if (bios_start -TRAMPOLINE_32BIT_SIZE < entry->addr) +if (new -TRAMPOLINE_32BIT_SIZE < entry->addr)continue ; +/* Protect against underflow. */ +if (new -TRAMPOLINE_32BIT_SIZE > bios_start) +break ; + + bios_start = new;break ; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 32/45 Input: hyperv-keyboard: Use in-place iterator API in the channel callback
In reply to Sasha LevinFrom: Dexuan Cui <[email protected]>
[ Upstream commit d09bc83640d524b8467a660db7b1d15e6562a1de ]
Simplify the ring buffer handling with the in-place API.
Also avoid the dynamic allocation and the memory leak in the channel callback function.
--- drivers/input/serio/hyperv-keyboard.c | 35 +++++---------------------- 1 file changed, 6 insertions(+), 29 deletions(-)
drivers/input/serio/hyperv-keyboard.c +6 -29
@@ -245,40 +245,17 @@ static void hv_kbd_handle_received_packet(struct hv_device *hv_dev,static void hv_kbd_on_channel_callback (void *context) { +struct vmpacket_descriptor *desc;struct hv_device *hv_dev = context; -void *buffer; -int bufferlen =0x100 ;/* Start with sensible size */ u32 bytes_recvd;u64 req_id; -int error; - buffer =kmalloc (bufferlen,GFP_ATOMIC ); -if (!buffer) -return ; - -while (1 ) { - error =vmbus_recvpacket_raw (hv_dev->channel, buffer, bufferlen, - &bytes_recvd, &req_id); -switch (error) { -case 0 : -if (bytes_recvd ==0 ) { -kfree (buffer); -return ; - } - -hv_kbd_handle_received_packet (hv_dev, buffer, - bytes_recvd, req_id); -break ; + foreach_vmbus_pkt(desc, hv_dev->channel) { + bytes_recvd = desc->len8 *8 ; + req_id = desc->trans_id; -case -ENOBUFS : -kfree (buffer); -/* Handle large packet */ - bufferlen = bytes_recvd; - buffer =kmalloc (bytes_recvd,GFP_ATOMIC ); -if (!buffer) -return ; -break ; - } +hv_kbd_handle_received_packet (hv_dev, desc, bytes_recvd, + req_id); } }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 33/45 Tools: hv: kvp: eliminate 'may be used uninitialized' warning
In reply to Sasha LevinFrom: Vitaly Kuznetsov <[email protected]>
[ Upstream commit 89eb4d8d25722a0a0194cf7fa47ba602e32a6da7 ]
When building hv_kvp_daemon GCC-8.3 complains:
hv_kvp_daemon.c: In function ‘kvp_get_ip_info.constprop’:
hv_kvp_daemon.c:812:30: warning: ‘ip_buffer’ may be used uninitialized in this function [-Wmaybe-uninitialized]
struct hv_kvp_ipaddr_value *ip_buffer;
this seems to be a false positive: we only use ip_buffer when op == KVP_OP_GET_IP_INFO and it is only unset when op == KVP_OP_ENUMERATE.
Silence the warning by initializing ip_buffer to NULL.
--- tools/hv/hv_kvp_daemon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/hv/hv_kvp_daemon.c +1 -1
@@ -809,7 +809,7 @@ kvp_get_ip_info(int family, char *if_name, int op,int sn_offset =0 ;int error =0 ;char *buffer; -struct hv_kvp_ipaddr_value *ip_buffer; +struct hv_kvp_ipaddr_value *ip_buffer =NULL ;char cidr_mask[5 ];/* /xyz */ int weight;int i;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 34/45 nvme-multipath: fix possible I/O hang when paths are updated
In reply to Sasha LevinFrom: Anton Eidelman <[email protected]>
[ Upstream commit 504db087aaccdb32af61539916409f7dca31ceb5 ]
nvme_state_set_live() making a path available triggers requeue_work in order to resubmit requests that ended up on requeue_list when no paths were available.
This requeue_work may race with concurrent nvme_ns_head_make_request() that do not observe the live path yet.
Such concurrent requests may by made by either:
- New IO submission.
- Requeue_work triggered by nvme_failover_req() or another ana_work.
A race may cause requeue_work capture the state of requeue_list before more requests get onto the list. These requests will stay on the list forever unless requeue_work is triggered again.
In order to prevent such race, nvme_state_set_live() should synchronize_srcu(&head->srcu) before triggering the requeue_work and prevent nvme_ns_head_make_request referencing an old snapshot of the path list.
--- drivers/nvme/host/multipath.c | 1 + 1 file changed, 1 insertion(+)
drivers/nvme/host/multipath.c +1 -0
@@ -293,6 +293,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns) "failed to create id group.\n"); } +synchronize_srcu (&ns->head->srcu);kblockd_schedule_work (&ns->head->requeue_work); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 35/45 IB/mlx4: Fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 5c1baaa82cea2c815a5180ded402a7cd455d1810 ]
In mlx4_ib_alloc_pv_bufs(), 'tun_qp->tx_ring' is allocated through kcalloc(). However, it is not always deallocated in the following execution if an error occurs, leading to memory leaks. To fix this issue, free 'tun_qp->tx_ring' whenever an error occurs.
--- drivers/infiniband/hw/mlx4/mad.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/infiniband/hw/mlx4/mad.c +2 -2
@@ -1668,8 +1668,6 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, tx_buf_size, DMA_TO_DEVICE);kfree (tun_qp->tx_ring[i].buf.addr); } -kfree (tun_qp->tx_ring); - tun_qp->tx_ring =NULL ; i =MLX4_NUM_TUNNEL_BUFS ; err:while (i >0 ) {
@@ -1678,6 +1676,8 @@ static int mlx4_ib_alloc_pv_bufs(struct mlx4_ib_demux_pv_ctx *ctx, rx_buf_size, DMA_FROM_DEVICE);kfree (tun_qp->ring[i].addr); } +kfree (tun_qp->tx_ring); + tun_qp->tx_ring =NULL ;kfree (tun_qp->ring); tun_qp->ring =NULL ;return -ENOMEM ;
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 36/45 infiniband: hfi1: fix a memory leak bug
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit b08afa064c320e5d85cdc27228426b696c4c8dae ]
In fault_opcodes_read(), 'data' is not deallocated if debugfs_file_get() fails, leading to a memory leak. To fix this bug, introduce the 'free_data' label to free 'data' before returning the error.
--- drivers/infiniband/hw/hfi1/fault.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/infiniband/hw/hfi1/fault.c +2 -1
@@ -214,7 +214,7 @@ static ssize_t fault_opcodes_read(struct file *file, char __user *buf,return -ENOMEM ; ret =debugfs_file_get (file->f_path.dentry);if (unlikely (ret)) -return ret; + goto free_data; bit =find_first_bit (fault->opcodes, bitsize);while (bit < bitsize) { zero =find_next_zero_bit (fault->opcodes, bitsize, bit);
@@ -232,6 +232,7 @@ static ssize_t fault_opcodes_read(struct file *file, char __user *buf, data[size -1 ] ='\n' ; data[size] ='\0' ; ret =simple_read_from_buffer (buf, len, pos, data, size); +free_data:kfree (data);return ret; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 37/45 infiniband: hfi1: fix memory leaks
In reply to Sasha LevinFrom: Wenwen Wang <[email protected]>
[ Upstream commit 2323d7baab2b18d87d9bc267452e387aa9f0060a ]
In fault_opcodes_write(), 'data' is allocated through kcalloc(). However, it is not deallocated in the following execution if an error occurs, leading to memory leaks. To fix this issue, introduce the 'free_data' label to free 'data' before returning the error.
--- drivers/infiniband/hw/hfi1/fault.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/infiniband/hw/hfi1/fault.c +6 -3
@@ -141,12 +141,14 @@ static ssize_t fault_opcodes_write(struct file *file, const char __user *buf,if (!data)return -ENOMEM ; copy =min (len, datalen -1 ); -if (copy_from_user (data, buf, copy)) -return -EFAULT ; +if (copy_from_user (data, buf, copy)) { + ret = -EFAULT ; + goto free_data; + } ret =debugfs_file_get (file->f_path.dentry);if (unlikely (ret)) -return ret; + goto free_data; ptr = data; token = ptr;for (ptr = data; *ptr; ptr = end +1 , token = ptr) {
@@ -195,6 +197,7 @@ static ssize_t fault_opcodes_write(struct file *file, const char __user *buf, ret = len;debugfs_file_put (file->f_path.dentry); +free_data:kfree (data);return ret; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 38/45 selftests: kvm: fix state save/load on processors without XSAVE
In reply to Sasha LevinFrom: Paolo Bonzini <[email protected]>
[ Upstream commit 54577e5018a8c0cb79c9a0fa118a55c68715d398 ]
state_test and smm_test are failing on older processors that do not have xcr0. This is because on those processor KVM does provide support for KVM_GET/SET_XSAVE (to avoid having to rely on the older KVM_GET/SET_FPU) but not for KVM_GET/SET_XCRS.
--- tools/testing/selftests/kvm/lib/x86.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-)
tools/testing/selftests/kvm/lib/x86.c +10 -6
@@ -809,9 +809,11 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)TEST_ASSERT (r ==0 ,"Unexpected result from KVM_GET_XSAVE, r: %i" , r); - r =ioctl (vcpu->fd,KVM_GET_XCRS , &state->xcrs); -TEST_ASSERT (r ==0 ,"Unexpected result from KVM_GET_XCRS, r: %i" , - r); +if (kvm_check_cap (KVM_CAP_XCRS )) { + r =ioctl (vcpu->fd,KVM_GET_XCRS , &state->xcrs); +TEST_ASSERT (r ==0 ,"Unexpected result from KVM_GET_XCRS, r: %i" , + r); + } r =ioctl (vcpu->fd,KVM_GET_SREGS , &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_GET_SREGS, r: %i",
@@ -858,9 +860,11 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *sTEST_ASSERT (r ==0 ,"Unexpected result from KVM_SET_XSAVE, r: %i" , r); - r =ioctl (vcpu->fd,KVM_SET_XCRS , &state->xcrs); -TEST_ASSERT (r ==0 ,"Unexpected result from KVM_SET_XCRS, r: %i" , - r); +if (kvm_check_cap (KVM_CAP_XCRS )) { + r =ioctl (vcpu->fd,KVM_SET_XCRS , &state->xcrs); +TEST_ASSERT (r ==0 ,"Unexpected result from KVM_SET_XCRS, r: %i" , + r); + } r =ioctl (vcpu->fd,KVM_SET_SREGS , &state->sregs); TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_SREGS, r: %i",
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 39/45 selftests/kvm: make platform_info_test pass on AMD
In reply to Sasha LevinFrom: Vitaly Kuznetsov <[email protected]>
[ Upstream commit e4427372398c31f57450565de277f861a4db5b3b ]
test_msr_platform_info_disabled() generates EXIT_SHUTDOWN but VMCB state is undefined after that so an attempt to launch this guest again from test_msr_platform_info_enabled() fails. Reorder the tests to make test pass.
--- tools/testing/selftests/kvm/platform_info_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/kvm/platform_info_test.c +1 -1
@@ -100,8 +100,8 @@ int main(int argc, char *argv[]) msr_platform_info =vcpu_get_msr (vm,VCPU_ID ,MSR_PLATFORM_INFO );vcpu_set_msr (vm,VCPU_ID ,MSR_PLATFORM_INFO , msr_platform_info |MSR_PLATFORM_INFO_MAX_TURBO_RATIO ); -test_msr_platform_info_disabled (vm);test_msr_platform_info_enabled (vm); +test_msr_platform_info_disabled (vm);vcpu_set_msr (vm,VCPU_ID ,MSR_PLATFORM_INFO , msr_platform_info);kvm_vm_free (vm);
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 40/45 ceph: fix buffer free while holding i_ceph_lock in __ceph_setxattr()
In reply to Sasha LevinFrom: Luis Henriques <[email protected]>
[ Upstream commit 86968ef21596515958d5f0a40233d02be78ecec0 ]
Calling ceph_buffer_put() in __ceph_setxattr() may end up freeing the i_xattrs.prealloc_blob buffer while holding the i_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.
The following backtrace was triggered by fstests generic/117.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
in_atomic(): 1, irqs_disabled(): 0, pid: 650, name: fsstress
3 locks held by fsstress/650:
#0: 00000000870a0fe8 (sb_writers#8){.+.+}, at: mnt_want_write+0x20/0x50
#1: 00000000ba0c4c74 (&type->i_mutex_dir_key#6){++++}, at: vfs_setxattr+0x55/0xa0
#2: 000000008dfbb3f2 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: __ceph_setxattr+0x297/0x810
CPU: 1 PID: 650 Comm: fsstress Not tainted 5.2.0+ #437
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
Call Trace:
dump_stack+0x67/0x90
___might_sleep.cold+0x9f/0xb1
vfree+0x4b/0x60
ceph_buffer_release+0x1b/0x60
__ceph_setxattr+0x2b4/0x810
__vfs_setxattr+0x66/0x80
__vfs_setxattr_noperm+0x59/0xf0
vfs_setxattr+0x81/0xa0
setxattr+0x115/0x230
? filename_lookup+0xc9/0x140
? rcu_read_lock_sched_held+0x74/0x80
? rcu_sync_lockdep_assert+0x2e/0x60
? __sb_start_write+0x142/0x1a0
? mnt_want_write+0x20/0x50
path_setxattr+0xba/0xd0
__x64_sys_lsetxattr+0x24/0x30
do_syscall_64+0x50/0x1c0
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7ff23514359a--- fs/ceph/xattr.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)
fs/ceph/xattr.c +6 -2
@@ -1011,6 +1011,7 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_inode_info *ci =ceph_inode (inode);struct ceph_mds_client *mdsc =ceph_sb_to_client (inode->i_sb)->mdsc;struct ceph_cap_flush *prealloc_cf =NULL ; +struct ceph_buffer *old_blob =NULL ;int issued;int err;int dirty =0 ;
@@ -1084,13 +1085,15 @@ int __ceph_setxattr(struct inode *inode, const char *name,struct ceph_buffer *blob;spin_unlock (&ci->i_ceph_lock); -dout (" preaallocating new blob size=%d\n" , required_blob_size); +ceph_buffer_put (old_blob);/* Shouldn't be required */ +dout (" pre-allocating new blob size=%d\n" , required_blob_size); blob =ceph_buffer_new (required_blob_size,GFP_NOFS );if (!blob) goto do_sync_unlocked;spin_lock (&ci->i_ceph_lock); +/* prealloc_blob can't be released while holding i_ceph_lock */ if (ci->i_xattrs.prealloc_blob) -ceph_buffer_put (ci->i_xattrs.prealloc_blob); + old_blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob = blob; goto retry; }
@@ -1106,6 +1109,7 @@ int __ceph_setxattr(struct inode *inode, const char *name, }spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob);if (lock_snap_rwsem)up_read (&mdsc->snap_rwsem);if (dirty)
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 41/45 ceph: fix buffer free while holding i_ceph_lock in __ceph_build_xattrs_blob()
In reply to Sasha LevinFrom: Luis Henriques <[email protected]>
[ Upstream commit 12fe3dda7ed89c95cc0ef7abc001ad1ad3e092f8 ]
Calling ceph_buffer_put() in __ceph_build_xattrs_blob() may result in freeing the i_xattrs.blob buffer while holding the i_ceph_lock. This can be fixed by having this function returning the old blob buffer and have the callers of this function freeing it when the lock is released.
The following backtrace was triggered by fstests generic/117.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
in_atomic(): 1, irqs_disabled(): 0, pid: 649, name: fsstress
4 locks held by fsstress/649:
#0: 00000000a7478e7e (&type->s_umount_key#19){++++}, at: iterate_supers+0x77/0xf0
#1: 00000000f8de1423 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: ceph_check_caps+0x7b/0xc60
#2: 00000000562f2b27 (&s->s_mutex){+.+.}, at: ceph_check_caps+0x3bd/0xc60
#3: 00000000f83ce16a (&mdsc->snap_rwsem){++++}, at: ceph_check_caps+0x3ed/0xc60
CPU: 1 PID: 649 Comm: fsstress Not tainted 5.2.0+ #439
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
Call Trace:
dump_stack+0x67/0x90
___might_sleep.cold+0x9f/0xb1
vfree+0x4b/0x60
ceph_buffer_release+0x1b/0x60
__ceph_build_xattrs_blob+0x12b/0x170
__send_cap+0x302/0x540
? __lock_acquire+0x23c/0x1e40
? __mark_caps_flushing+0x15c/0x280
? _raw_spin_unlock+0x24/0x30
ceph_check_caps+0x5f0/0xc60
ceph_flush_dirty_caps+0x7c/0x150
? __ia32_sys_fdatasync+0x20/0x20
ceph_sync_fs+0x5a/0x130
iterate_supers+0x8f/0xf0
ksys_sync+0x4f/0xb0
__ia32_sys_sync+0xa/0x10
do_syscall_64+0x50/0x1c0
entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x7fc6409ab617--- fs/ceph/caps.c | 5 ++++- fs/ceph/snap.c | 4 +++- fs/ceph/super.h | 2 +- fs/ceph/xattr.c | 11 ++++++++--- 4 files changed, 16 insertions(+), 6 deletions(-)
fs/ceph/caps.c +4 -1
@@ -1280,6 +1280,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, {struct ceph_inode_info *ci = cap->ci;struct inode *inode = &ci->vfs_inode; +struct ceph_buffer *old_blob =NULL ;struct cap_msg_args arg;int held, revoking;int wake =0 ;
@@ -1344,7 +1345,7 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, ci->i_requested_max_size = arg.max_size;if (flushing &CEPH_CAP_XATTR_EXCL ) { -__ceph_build_xattrs_blob (ci); + old_blob =__ceph_build_xattrs_blob (ci); arg.xattr_version = ci->i_xattrs.version; arg.xattr_buf = ci->i_xattrs.blob; }else {
@@ -1379,6 +1380,8 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob); + ret =send_cap_msg (&arg);if (ret <0 ) {dout ("error sending cap msg, must requeue %p\n" , inode);
fs/ceph/snap.c +3 -1
@@ -460,6 +460,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)struct inode *inode = &ci->vfs_inode;struct ceph_cap_snap *capsnap;struct ceph_snap_context *old_snapc, *new_snapc; +struct ceph_buffer *old_blob =NULL ;int used, dirty; capsnap =kzalloc (sizeof (*capsnap),GFP_NOFS );
@@ -536,7 +537,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) capsnap->gid = inode->i_gid;if (dirty &CEPH_CAP_XATTR_EXCL ) { -__ceph_build_xattrs_blob (ci); + old_blob =__ceph_build_xattrs_blob (ci); capsnap->xattr_blob =ceph_buffer_get (ci->i_xattrs.blob); capsnap->xattr_version = ci->i_xattrs.version;
@@ -579,6 +580,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci) }spin_unlock (&ci->i_ceph_lock); +ceph_buffer_put (old_blob);kfree (capsnap);ceph_put_snap_context (old_snapc); }
fs/ceph/super.h +1 -1
@@ -896,7 +896,7 @@ extern int ceph_getattr(const struct path *path, struct kstat *stat,int __ceph_setxattr (struct inode *,const char *,const void *,size_t ,int );ssize_t __ceph_getxattr (struct inode *,const char *,void *,size_t );extern ssize_t ceph_listxattr (struct dentry *,char *,size_t ); -extern void __ceph_build_xattrs_blob (struct ceph_inode_info *ci); +extern struct ceph_buffer *__ceph_build_xattrs_blob (struct ceph_inode_info *ci);extern void __ceph_destroy_xattrs (struct ceph_inode_info *ci);extern void __init ceph_xattr_init (void );extern void ceph_xattr_exit (void );
fs/ceph/xattr.c +8 -3
@@ -734,12 +734,15 @@ static int __get_required_blob_size(struct ceph_inode_info *ci, int name_size,/* * If there are dirty xattrs, reencode xattrs into the prealloc_blob -* and swap into place. +* and swap into place. It returns the old i_xattrs.blob (or NULL) so +* that it can be freed by the caller as the i_ceph_lock is likely to be +* held. */ -void __ceph_build_xattrs_blob (struct ceph_inode_info *ci) +struct ceph_buffer *__ceph_build_xattrs_blob (struct ceph_inode_info *ci) {struct rb_node *p;struct ceph_inode_xattr *xattr =NULL ; +struct ceph_buffer *old_blob =NULL ;void *dest;dout ("__build_xattrs_blob %p\n" , &ci->vfs_inode);
@@ -770,12 +773,14 @@ void __ceph_build_xattrs_blob(struct ceph_inode_info *ci) dest - ci->i_xattrs.prealloc_blob->vec.iov_base;if (ci->i_xattrs.blob) -ceph_buffer_put (ci->i_xattrs.blob); + old_blob = ci->i_xattrs.blob; ci->i_xattrs.blob = ci->i_xattrs.prealloc_blob; ci->i_xattrs.prealloc_blob =NULL ; ci->i_xattrs.dirty = false; ci->i_xattrs.version++; } + +return old_blob; }static inline int __get_request_mask (struct inode *in) {
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 42/45 ceph: fix buffer free while holding i_ceph_lock in fill_inode()
In reply to Sasha LevinFrom: Luis Henriques <[email protected]>
[ Upstream commit af8a85a41734f37b67ba8ce69d56b685bee4ac48 ]
Calling ceph_buffer_put() in fill_inode() may result in freeing the i_xattrs.blob buffer while holding the i_ceph_lock. This can be fixed by postponing the call until later, when the lock is released.
The following backtrace was triggered by fstests generic/070.
BUG: sleeping function called from invalid context at mm/vmalloc.c:2283
in_atomic(): 1, irqs_disabled(): 0, pid: 3852, name: kworker/0:4
6 locks held by kworker/0:4/3852:
#0: 000000004270f6bb ((wq_completion)ceph-msgr){+.+.}, at: process_one_work+0x1b8/0x5f0
#1: 00000000eb420803 ((work_completion)(&(&con->work)->work)){+.+.}, at: process_one_work+0x1b8/0x5f0
#2: 00000000be1c53a4 (&s->s_mutex){+.+.}, at: dispatch+0x288/0x1476
#3: 00000000559cb958 (&mdsc->snap_rwsem){++++}, at: dispatch+0x2eb/0x1476
#4: 000000000d5ebbae (&req->r_fill_mutex){+.+.}, at: dispatch+0x2fc/0x1476
#5: 00000000a83d0514 (&(&ci->i_ceph_lock)->rlock){+.+.}, at: fill_inode.isra.0+0xf8/0xf70
CPU: 0 PID: 3852 Comm: kworker/0:4 Not tainted 5.2.0+ #441
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58-prebuilt.qemu.org 04/01/2014
Workqueue: ceph-msgr ceph_con_workfn
Call Trace:
dump_stack+0x67/0x90
___might_sleep.cold+0x9f/0xb1
vfree+0x4b/0x60
ceph_buffer_release+0x1b/0x60
fill_inode.isra.0+0xa9b/0xf70
ceph_fill_trace+0x13b/0xc70
? dispatch+0x2eb/0x1476
dispatch+0x320/0x1476
? __mutex_unlock_slowpath+0x4d/0x2a0
ceph_con_workfn+0xc97/0x2ec0
? process_one_work+0x1b8/0x5f0
process_one_work+0x244/0x5f0
worker_thread+0x4d/0x3e0
kthread+0x105/0x140
? process_one_work+0x5f0/0x5f0
? kthread_park+0x90/0x90
ret_from_fork+0x3a/0x50--- fs/ceph/inode.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
fs/ceph/inode.c +4 -3
@@ -742,6 +742,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,int issued, new_issued, info_caps;struct timespec64 mtime, atime, ctime;struct ceph_buffer *xattr_blob =NULL ; +struct ceph_buffer *old_blob =NULL ;struct ceph_string *pool_ns =NULL ;struct ceph_cap *new_cap =NULL ;int err =0 ;
@@ -878,7 +879,7 @@ static int fill_inode(struct inode *inode, struct page *locked_page,if ((ci->i_xattrs.version ==0 || !(issued &CEPH_CAP_XATTR_EXCL )) &&le64_to_cpu (info->xattr_version) > ci->i_xattrs.version) {if (ci->i_xattrs.blob) -ceph_buffer_put (ci->i_xattrs.blob); + old_blob = ci->i_xattrs.blob; ci->i_xattrs.blob = xattr_blob;if (xattr_blob) memcpy(ci->i_xattrs.blob->vec.iov_base,
@@ -1017,8 +1018,8 @@ static int fill_inode(struct inode *inode, struct page *locked_page, out:if (new_cap)ceph_put_cap (mdsc, new_cap); -if (xattr_blob) -ceph_buffer_put (xattr_blob); +ceph_buffer_put (old_blob); +ceph_buffer_put (xattr_blob);ceph_put_string (pool_ns);return err; }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 43/45 KVM: arm/arm64: Only skip MMIO insn once
In reply to Sasha LevinFrom: Andrew Jones <[email protected]>
[ Upstream commit 2113c5f62b7423e4a72b890bd479704aa85c81ba ]
If after an MMIO exit to userspace a VCPU is immediately run with an immediate_exit request, such as when a signal is delivered or an MMIO emulation completion is needed, then the VCPU completes the MMIO emulation and immediately returns to userspace. As the exit_reason does not get changed from KVM_EXIT_MMIO in these cases we have to be careful not to complete the MMIO emulation again, when the VCPU is eventually run again, because the emulation does an instruction skip (and doing too many skips would be a waste of guest code :-) We need to use additional VCPU state to track if the emulation is complete. As luck would have it, we already have 'mmio_needed', which even appears to be used in this way by other architectures already.
--- virt/kvm/arm/mmio.c | 7 +++++++ 1 file changed, 7 insertions(+)
virt/kvm/arm/mmio.c +7 -0
@@ -98,6 +98,12 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run)unsigned int len;int mask; +/* Detect an already handled MMIO return */ +if (unlikely (!vcpu->mmio_needed)) +return 0 ; + + vcpu->mmio_needed =0 ; +if (!run->mmio.is_write) { len = run->mmio.len;if (len >sizeof (unsigned long ))
@@ -200,6 +206,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, run->mmio.is_write = is_write; run->mmio.phys_addr = fault_ipa; run->mmio.len = len; + vcpu->mmio_needed =1 ;if (!ret) {/* We handled the access successfully in the kernel. */
Signature · 6 lines
2.20.1 _______________________________________________ kvmarm mailing list [email protected] https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
Sasha Levin
maintainerPATCH 44/45 afs: Fix leak in afs_lookup_cell_rcu()
In reply to Sasha LevinFrom: David Howells <[email protected]>
[ Upstream commit a5fb8e6c02d6a518fb2b1a2b8c2471fa77b69436 ]
Fix a leak on the cell refcount in afs_lookup_cell_rcu() due to non-clearance of the default error in the case a NULL cell name is passed and the workstation default cell is used.
Also put a bit at the end to make sure we don't leak a cell ref if we're going to be returning an error.
This leak results in an assertion like the following when the kafs module is unloaded:
AFS: Assertion failed 2 == 1 is false 0x2 == 0x1 is false ------------[ cut here ]------------ kernel BUG at fs/afs/cell.c:770! ... RIP: 0010:afs_manage_cells+0x220/0x42f [kafs] ... process_one_work+0x4c2/0x82c ? pool_mayday_timeout+0x1e1/0x1e1 ? do_raw_spin_lock+0x134/0x175 worker_thread+0x336/0x4a6 ? rescuer_thread+0x4af/0x4af kthread+0x1de/0x1ee ? kthread_park+0xd4/0xd4 ret_from_fork+0x24/0x30
--- fs/afs/cell.c | 4 ++++ 1 file changed, 4 insertions(+)
fs/afs/cell.c +4 -0
@@ -76,6 +76,7 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net, cell =rcu_dereference_raw (net->ws_cell);if (cell) {afs_get_cell (cell); + ret =0 ;break ; } ret = -EDESTADDRREQ ;
@@ -110,6 +111,9 @@ struct afs_cell *afs_lookup_cell_rcu(struct afs_net *net,done_seqretry (&net->cells_lock, seq); +if (ret !=0 && cell) +afs_put_cell (net, cell); +return ret ==0 ? cell :ERR_PTR (ret); }
Signature · 1 line
2.20.1
Sasha Levin
maintainerPATCH 45/45 KVM: arm/arm64: VGIC: Properly initialise private IRQ affinity
In reply to Sasha LevinFrom: Andre Przywara <[email protected]>
[ Upstream commit 2e16f3e926ed48373c98edea85c6ad0ef69425d1 ]
At the moment we initialise the target *mask* of a virtual IRQ to the VCPU it belongs to, even though this mask is only defined for GICv2 and quickly runs out of bits for many GICv3 guests.
This behaviour triggers an UBSAN complaint for more than 32 VCPUs:
------
[ 5659.462377] UBSAN: Undefined behaviour in virt/kvm/arm/vgic/vgic-init.c:223:21 [ 5659.471689] shift exponent 32 is too large for 32-bit type 'unsigned int'
------
Also for GICv3 guests the reporting of TARGET in the "vgic-state" debugfs dump is wrong, due to this very same problem.
Because there is no requirement to create the VGIC device before the VCPUs (and QEMU actually does it the other way round), we can't safely initialise mpidr or targets in kvm_vgic_vcpu_init(). But since we touch every private IRQ for each VCPU anyway later (in vgic_init()), we can just move the initialisation of those fields into there, where we definitely know the VGIC type.
On the way make sure we really have either a VGICv2 or a VGICv3 device, since the existing code is just checking for "VGICv3 or not", silently ignoring the uninitialised case.
--- virt/kvm/arm/vgic/vgic-init.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-)
virt/kvm/arm/vgic/vgic-init.c +20 -10
@@ -19,6 +19,7 @@#include <linux/cpu.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> +#include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include "vgic.h"
@@ -175,12 +176,18 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) irq->vcpu =NULL ; irq->target_vcpu = vcpu0;kref_init (&irq->refcount); -if (dist->vgic_model ==KVM_DEV_TYPE_ARM_VGIC_V2 ) { +switch (dist->vgic_model) { +case KVM_DEV_TYPE_ARM_VGIC_V2 : irq->targets =0 ; irq->group =0 ; - }else { +break ; +case KVM_DEV_TYPE_ARM_VGIC_V3 : irq->mpidr =0 ; irq->group =1 ; +break ; +default : +kfree (dist->spis); +return -EINVAL ; } }return 0 ;
@@ -220,7 +227,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) irq->intid = i; irq->vcpu =NULL ; irq->target_vcpu = vcpu; - irq->targets =1U << vcpu->vcpu_id;kref_init (&irq->refcount);if (vgic_irq_is_sgi (i)) {/* SGIs */
@@ -230,11 +236,6 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)/* PPIs */ irq->config =VGIC_CONFIG_LEVEL ; } - -if (dist->vgic_model ==KVM_DEV_TYPE_ARM_VGIC_V3 ) - irq->group =1 ; -else - irq->group =0 ; }if (!irqchip_in_kernel (vcpu->kvm))
@@ -297,10 +298,19 @@ int vgic_init(struct kvm *kvm)for (i =0 ; i <VGIC_NR_PRIVATE_IRQS ; i++) {struct vgic_irq *irq = &vgic_cpu->private_irqs[i]; -if (dist->vgic_model ==KVM_DEV_TYPE_ARM_VGIC_V3 ) +switch (dist->vgic_model) { +case KVM_DEV_TYPE_ARM_VGIC_V3 : irq->group =1 ; -else + irq->mpidr =kvm_vcpu_get_mpidr_aff (vcpu); +break ; +case KVM_DEV_TYPE_ARM_VGIC_V2 : irq->group =0 ; + irq->targets =1U << idx; +break ; +default : + ret = -EINVAL ; + goto out; + } } }
Signature · 1 line
2.20.1