4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Siddh Raman Pant code@siddh.me

[ Upstream commit c95f919567d6f1914f13350af61a1b044ac85014 ]

llcp_sock_sendmsg() calls nfc_llcp_send_ui_frame() which in turn calls nfc_alloc_send_skb(), which accesses the nfc_dev from the llcp_sock for getting the headroom and tailroom needed for skb allocation.

Parallelly the nfc_dev can be freed, as the refcount is decreased via nfc_free_device(), leading to a UAF reported by Syzkaller, which can be summarized as follows:

(1) llcp_sock_sendmsg() -> nfc_llcp_send_ui_frame() -> nfc_alloc_send_skb() -> Dereference *nfc_dev (2) virtual_ncidev_close() -> nci_free_device() -> nfc_free_device() -> put_device() -> nfc_release() -> Free *nfc_dev

When a reference to llcp_local is acquired, we do not acquire the same for the nfc_dev. This leads to freeing even when the llcp_local is in use, and this is the case with the UAF described above too.

Thus, when we acquire a reference to llcp_local, we should acquire a reference to nfc_dev, and release the references appropriately later.

References for llcp_local is initialized in nfc_llcp_register_device() (which is called by nfc_register_device()). Thus, we should acquire a reference to nfc_dev there.

nfc_unregister_device() calls nfc_llcp_unregister_device() which in turn calls nfc_llcp_local_put(). Thus, the reference to nfc_dev is appropriately released later.

Reported-and-tested-by: syzbot+bbe84a4010eeea00982d@syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=bbe84a4010eeea00982d Fixes: c7aa12252f51 ("NFC: Take a reference on the LLCP local pointer when creating a socket") Reviewed-by: Suman Ghosh sumang@marvell.com Signed-off-by: Siddh Raman Pant code@siddh.me Reviewed-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/nfc/llcp_core.c | 39 ++++++++++++++++++++++++++++++++++++--- 1 file changed, 36 insertions(+), 3 deletions(-)

diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index c30b28465e644..a217830f0f34c 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -157,6 +157,13 @@ static void nfc_llcp_socket_release(struct nfc_llcp_local *local, bool device,

struct nfc_llcp_local *nfc_llcp_local_get(struct nfc_llcp_local *local) { + /* Since using nfc_llcp_local may result in usage of nfc_dev, whenever + * we hold a reference to local, we also need to hold a reference to + * the device to avoid UAF. + */ + if (!nfc_get_device(local->dev->idx)) + return NULL; + kref_get(&local->ref);

return local; @@ -190,10 +197,18 @@ static void local_release(struct kref *ref)

int nfc_llcp_local_put(struct nfc_llcp_local *local) { + struct nfc_dev *dev; + int ret; + if (local == NULL) return 0;

- return kref_put(&local->ref, local_release); + dev = local->dev; + + ret = kref_put(&local->ref, local_release); + nfc_put_device(dev); + + return ret; }

static struct nfc_llcp_sock *nfc_llcp_sock_get(struct nfc_llcp_local *local, @@ -951,8 +966,17 @@ static void nfc_llcp_recv_connect(struct nfc_llcp_local *local, }

new_sock = nfc_llcp_sock(new_sk); - new_sock->dev = local->dev; + new_sock->local = nfc_llcp_local_get(local); + if (!new_sock->local) { + reason = LLCP_DM_REJ; + sock_put(&new_sock->sk); + release_sock(&sock->sk); + sock_put(&sock->sk); + goto fail; + } + + new_sock->dev = local->dev; new_sock->rw = sock->rw; new_sock->miux = sock->miux; new_sock->nfc_protocol = sock->nfc_protocol; @@ -1584,7 +1608,16 @@ int nfc_llcp_register_device(struct nfc_dev *ndev) if (local == NULL) return -ENOMEM;

- local->dev = ndev; + /* As we are going to initialize local's refcount, we need to get the + * nfc_dev to avoid UAF, otherwise there is no point in continuing. + * See nfc_llcp_local_get(). + */ + local->dev = nfc_get_device(ndev->idx); + if (!local->dev) { + kfree(local); + return -ENODEV; + } + INIT_LIST_HEAD(&local->list); kref_init(&local->ref); mutex_init(&local->sdp_lock);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hangyu Hua hbh25y@gmail.com

[ Upstream commit 8fcb0382af6f1ef50936f1be05b8149eb2f88496 ]

m->data needs to be freed when em_text_destroy is called.

Fixes: d675c989ed2d ("[PKT_SCHED]: Packet classification based on textsearch (ematch)") Acked-by: Jamal Hadi Salim jhs@mojatatu.com Signed-off-by: Hangyu Hua hbh25y@gmail.com Reviewed-by: Simon Horman horms@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/sched/em_text.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/em_text.c b/net/sched/em_text.c index 73e2ed576ceb3..cbf44783024f3 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -101,8 +101,10 @@ static int em_text_change(struct net *net, void *data, int len,

static void em_text_destroy(struct tcf_ematch *m) { - if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) + if (EM_TEXT_PRIV(m) && EM_TEXT_PRIV(m)->config) { textsearch_destroy(EM_TEXT_PRIV(m)->config); + kfree(EM_TEXT_PRIV(m)); + } }

static int em_text_dump(struct sk_buff *skb, struct tcf_ematch *m)

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Adrian Cinal adriancinal@gmail.com

[ Upstream commit e584f2ff1e6cc9b1d99e8a6b0f3415940d1b3eb3 ]

The flag DMA_TX_APPEND_CRC was only written to the first DMA descriptor in the TX path, where each descriptor corresponds to a single skbuff fragment (or the skbuff head). This led to packets with no FCS appearing on the wire if the kernel allocated the packet in fragments, which would always happen when using PACKET_MMAP/TPACKET (cf. tpacket_fill_skb() in net/af_packet.c).

Fixes: 1c1008c793fa ("net: bcmgenet: add main driver file") Signed-off-by: Adrian Cinal adriancinal1@gmail.com Acked-by: Doug Berger opendmb@gmail.com Acked-by: Florian Fainelli florian.fainelli@broadcom.com Link: https://lore.kernel.org/r/20231228135638.1339245-1-adriancinal1@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index d518577313145..8bbc5dcf8cb43 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -1650,8 +1650,10 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev) /* Note: if we ever change from DMA_TX_APPEND_CRC below we * will need to restore software padding of "runt" packets */ + len_stat |= DMA_TX_APPEND_CRC; + if (!i) { - len_stat |= DMA_TX_APPEND_CRC | DMA_SOP; + len_stat |= DMA_SOP; if (skb->ip_summed == CHECKSUM_PARTIAL) len_stat |= DMA_TX_DO_CSUM; }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ke Xiao xiaoke@sangfor.com.cn

[ Upstream commit 6a15584e99db8918b60e507539c7446375dcf366 ]

Commit 3116f59c12bd ("i40e: fix use-after-free in i40e_sync_filters_subtask()") avoided use-after-free issues, by increasing refcount during update the VSI filter list to the HW. However, it missed the unicast situation.

When deleting an unicast FDB entry, the i40e driver will release the mac_filter, and i40e_service_task will concurrently request firmware to add the mac_filter, which will lead to the following use-after-free issue.

Fix again for both netdev->uc and netdev->mc.

BUG: KASAN: use-after-free in i40e_aqc_add_filters+0x55c/0x5b0 [i40e] Read of size 2 at addr ffff888eb3452d60 by task kworker/8:7/6379

CPU: 8 PID: 6379 Comm: kworker/8:7 Kdump: loaded Tainted: G Workqueue: i40e i40e_service_task [i40e] Call Trace: dump_stack+0x71/0xab print_address_description+0x6b/0x290 kasan_report+0x14a/0x2b0 i40e_aqc_add_filters+0x55c/0x5b0 [i40e] i40e_sync_vsi_filters+0x1676/0x39c0 [i40e] i40e_service_task+0x1397/0x2bb0 [i40e] process_one_work+0x56a/0x11f0 worker_thread+0x8f/0xf40 kthread+0x2a0/0x390 ret_from_fork+0x1f/0x40

Allocated by task 21948: kasan_kmalloc+0xa6/0xd0 kmem_cache_alloc_trace+0xdb/0x1c0 i40e_add_filter+0x11e/0x520 [i40e] i40e_addr_sync+0x37/0x60 [i40e] __hw_addr_sync_dev+0x1f5/0x2f0 i40e_set_rx_mode+0x61/0x1e0 [i40e] dev_uc_add_excl+0x137/0x190 i40e_ndo_fdb_add+0x161/0x260 [i40e] rtnl_fdb_add+0x567/0x950 rtnetlink_rcv_msg+0x5db/0x880 netlink_rcv_skb+0x254/0x380 netlink_unicast+0x454/0x610 netlink_sendmsg+0x747/0xb00 sock_sendmsg+0xe2/0x120 __sys_sendto+0x1ae/0x290 __x64_sys_sendto+0xdd/0x1b0 do_syscall_64+0xa0/0x370 entry_SYSCALL_64_after_hwframe+0x65/0xca

Freed by task 21948: __kasan_slab_free+0x137/0x190 kfree+0x8b/0x1b0 __i40e_del_filter+0x116/0x1e0 [i40e] i40e_del_mac_filter+0x16c/0x300 [i40e] i40e_addr_unsync+0x134/0x1b0 [i40e] __hw_addr_sync_dev+0xff/0x2f0 i40e_set_rx_mode+0x61/0x1e0 [i40e] dev_uc_del+0x77/0x90 rtnl_fdb_del+0x6a5/0x860 rtnetlink_rcv_msg+0x5db/0x880 netlink_rcv_skb+0x254/0x380 netlink_unicast+0x454/0x610 netlink_sendmsg+0x747/0xb00 sock_sendmsg+0xe2/0x120 __sys_sendto+0x1ae/0x290 __x64_sys_sendto+0xdd/0x1b0 do_syscall_64+0xa0/0x370 entry_SYSCALL_64_after_hwframe+0x65/0xca

Fixes: 3116f59c12bd ("i40e: fix use-after-free in i40e_sync_filters_subtask()") Fixes: 41c445ff0f48 ("i40e: main driver core") Signed-off-by: Ke Xiao xiaoke@sangfor.com.cn Signed-off-by: Ding Hui dinghui@sangfor.com.cn Cc: Di Zhu zhudi2@huawei.com Reviewed-by: Jan Sokolowski jan.sokolowski@intel.com Reviewed-by: Simon Horman horms@kernel.org Reviewed-by: Jacob Keller jacob.e.keller@intel.com Tested-by: Pucha Himasekhar Reddy himasekharx.reddy.pucha@intel.com (A Contingent worker at Intel) Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 75a553f4e26f6..552f5025d265b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -99,12 +99,18 @@ static struct workqueue_struct *i40e_wq; static void netdev_hw_addr_refcnt(struct i40e_mac_filter *f, struct net_device *netdev, int delta) { + struct netdev_hw_addr_list *ha_list; struct netdev_hw_addr *ha;

if (!f || !netdev) return;

- netdev_for_each_mc_addr(ha, netdev) { + if (is_unicast_ether_addr(f->macaddr) || is_link_local_ether_addr(f->macaddr)) + ha_list = &netdev->uc; + else + ha_list = &netdev->mc; + + netdev_hw_addr_list_for_each(ha, ha_list) { if (ether_addr_equal(ha->addr, f->macaddr)) { ha->refcount += delta; if (ha->refcount <= 0)

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 41fb4c1ba7478fe34c7e094e124e4ee4513b9763 ]

The wrappers in include/linux/pci-dma-compat.h should go away.

The patch has been generated with the coccinelle script below and has been hand modified to replace GFP_ with a correct flag. It has been compile tested.

When memory is allocated in 'ql_alloc_net_req_rsp_queues()' GFP_KERNEL can be used because it is only called from 'ql_alloc_mem_resources()' which already calls 'ql_alloc_buffer_queues()' which uses GFP_KERNEL. (see below)

When memory is allocated in 'ql_alloc_buffer_queues()' GFP_KERNEL can be used because this flag is already used just a few line above.

When memory is allocated in 'ql_alloc_small_buffers()' GFP_KERNEL can be used because it is only called from 'ql_alloc_mem_resources()' which already calls 'ql_alloc_buffer_queues()' which uses GFP_KERNEL. (see above)

When memory is allocated in 'ql_alloc_mem_resources()' GFP_KERNEL can be used because this function already calls 'ql_alloc_buffer_queues()' which uses GFP_KERNEL. (see above)

While at it, use 'dma_set_mask_and_coherent()' instead of 'dma_set_mask()/ dma_set_coherent_mask()' in order to slightly simplify code.

@@ @@ - PCI_DMA_BIDIRECTIONAL + DMA_BIDIRECTIONAL

@@ @@ - PCI_DMA_TODEVICE + DMA_TO_DEVICE

@@ @@ - PCI_DMA_FROMDEVICE + DMA_FROM_DEVICE

@@ @@ - PCI_DMA_NONE + DMA_NONE

@@ expression e1, e2, e3; @@ - pci_alloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_)

@@ expression e1, e2, e3; @@ - pci_zalloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_)

@@ expression e1, e2, e3, e4; @@ - pci_free_consistent(e1, e2, e3, e4) + dma_free_coherent(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_map_single(e1, e2, e3, e4) + dma_map_single(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_unmap_single(e1, e2, e3, e4) + dma_unmap_single(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4, e5; @@ - pci_map_page(e1, e2, e3, e4, e5) + dma_map_page(&e1->dev, e2, e3, e4, e5)

@@ expression e1, e2, e3, e4; @@ - pci_unmap_page(e1, e2, e3, e4) + dma_unmap_page(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_map_sg(e1, e2, e3, e4) + dma_map_sg(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_unmap_sg(e1, e2, e3, e4) + dma_unmap_sg(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_cpu(e1, e2, e3, e4) + dma_sync_single_for_cpu(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_device(e1, e2, e3, e4) + dma_sync_single_for_device(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_cpu(e1, e2, e3, e4) + dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4)

@@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_device(e1, e2, e3, e4) + dma_sync_sg_for_device(&e1->dev, e2, e3, e4)

@@ expression e1, e2; @@ - pci_dma_mapping_error(e1, e2) + dma_mapping_error(&e1->dev, e2)

@@ expression e1, e2; @@ - pci_set_dma_mask(e1, e2) + dma_set_mask(&e1->dev, e2)

@@ expression e1, e2; @@ - pci_set_consistent_dma_mask(e1, e2) + dma_set_coherent_mask(&e1->dev, e2)

Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Link: https://lore.kernel.org/r/20210117081542.560021-1-christophe.jaillet@wanadoo... Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: 89f45c30172c ("net/qla3xxx: fix potential memleak in ql_alloc_buffer_queues") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qla3xxx.c | 196 ++++++++++++-------------- 1 file changed, 87 insertions(+), 109 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index d545593354c63..6350872fd5a52 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -316,12 +316,11 @@ static void ql_release_to_lrg_buf_free_list(struct ql3_adapter *qdev, * buffer */ skb_reserve(lrg_buf_cb->skb, QL_HEADER_SPACE); - map = pci_map_single(qdev->pdev, + map = dma_map_single(&qdev->pdev->dev, lrg_buf_cb->skb->data, - qdev->lrg_buffer_len - - QL_HEADER_SPACE, - PCI_DMA_FROMDEVICE); - err = pci_dma_mapping_error(qdev->pdev, map); + qdev->lrg_buffer_len - QL_HEADER_SPACE, + DMA_FROM_DEVICE); + err = dma_mapping_error(&qdev->pdev->dev, map); if (err) { netdev_err(qdev->ndev, "PCI mapping failed with error: %d\n", @@ -1803,13 +1802,12 @@ static int ql_populate_free_queue(struct ql3_adapter *qdev) * first buffer */ skb_reserve(lrg_buf_cb->skb, QL_HEADER_SPACE); - map = pci_map_single(qdev->pdev, + map = dma_map_single(&qdev->pdev->dev, lrg_buf_cb->skb->data, - qdev->lrg_buffer_len - - QL_HEADER_SPACE, - PCI_DMA_FROMDEVICE); + qdev->lrg_buffer_len - QL_HEADER_SPACE, + DMA_FROM_DEVICE);

- err = pci_dma_mapping_error(qdev->pdev, map); + err = dma_mapping_error(&qdev->pdev->dev, map); if (err) { netdev_err(qdev->ndev, "PCI mapping failed with error: %d\n", @@ -1945,18 +1943,16 @@ static void ql_process_mac_tx_intr(struct ql3_adapter *qdev, goto invalid_seg_count; }

- pci_unmap_single(qdev->pdev, + dma_unmap_single(&qdev->pdev->dev, dma_unmap_addr(&tx_cb->map[0], mapaddr), - dma_unmap_len(&tx_cb->map[0], maplen), - PCI_DMA_TODEVICE); + dma_unmap_len(&tx_cb->map[0], maplen), DMA_TO_DEVICE); tx_cb->seg_count--; if (tx_cb->seg_count) { for (i = 1; i < tx_cb->seg_count; i++) { - pci_unmap_page(qdev->pdev, - dma_unmap_addr(&tx_cb->map[i], - mapaddr), + dma_unmap_page(&qdev->pdev->dev, + dma_unmap_addr(&tx_cb->map[i], mapaddr), dma_unmap_len(&tx_cb->map[i], maplen), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); } } qdev->ndev->stats.tx_packets++; @@ -2023,10 +2019,9 @@ static void ql_process_mac_rx_intr(struct ql3_adapter *qdev, qdev->ndev->stats.rx_bytes += length;

skb_put(skb, length); - pci_unmap_single(qdev->pdev, + dma_unmap_single(&qdev->pdev->dev, dma_unmap_addr(lrg_buf_cb2, mapaddr), - dma_unmap_len(lrg_buf_cb2, maplen), - PCI_DMA_FROMDEVICE); + dma_unmap_len(lrg_buf_cb2, maplen), DMA_FROM_DEVICE); prefetch(skb->data); skb_checksum_none_assert(skb); skb->protocol = eth_type_trans(skb, qdev->ndev); @@ -2069,10 +2064,9 @@ static void ql_process_macip_rx_intr(struct ql3_adapter *qdev, skb2 = lrg_buf_cb2->skb;

skb_put(skb2, length); /* Just the second buffer length here. */ - pci_unmap_single(qdev->pdev, + dma_unmap_single(&qdev->pdev->dev, dma_unmap_addr(lrg_buf_cb2, mapaddr), - dma_unmap_len(lrg_buf_cb2, maplen), - PCI_DMA_FROMDEVICE); + dma_unmap_len(lrg_buf_cb2, maplen), DMA_FROM_DEVICE); prefetch(skb2->data);

skb_checksum_none_assert(skb2); @@ -2321,9 +2315,9 @@ static int ql_send_map(struct ql3_adapter *qdev, /* * Map the skb buffer first. */ - map = pci_map_single(qdev->pdev, skb->data, len, PCI_DMA_TODEVICE); + map = dma_map_single(&qdev->pdev->dev, skb->data, len, DMA_TO_DEVICE);

- err = pci_dma_mapping_error(qdev->pdev, map); + err = dma_mapping_error(&qdev->pdev->dev, map); if (err) { netdev_err(qdev->ndev, "PCI mapping failed with error: %d\n", err); @@ -2359,11 +2353,11 @@ static int ql_send_map(struct ql3_adapter *qdev, (seg == 7 && seg_cnt > 8) || (seg == 12 && seg_cnt > 13) || (seg == 17 && seg_cnt > 18)) { - map = pci_map_single(qdev->pdev, oal, + map = dma_map_single(&qdev->pdev->dev, oal, sizeof(struct oal), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE);

- err = pci_dma_mapping_error(qdev->pdev, map); + err = dma_mapping_error(&qdev->pdev->dev, map); if (err) { netdev_err(qdev->ndev, "PCI mapping outbound address list with error: %d\n", @@ -2425,24 +2419,24 @@ static int ql_send_map(struct ql3_adapter *qdev, (seg == 7 && seg_cnt > 8) || (seg == 12 && seg_cnt > 13) || (seg == 17 && seg_cnt > 18)) { - pci_unmap_single(qdev->pdev, - dma_unmap_addr(&tx_cb->map[seg], mapaddr), - dma_unmap_len(&tx_cb->map[seg], maplen), - PCI_DMA_TODEVICE); + dma_unmap_single(&qdev->pdev->dev, + dma_unmap_addr(&tx_cb->map[seg], mapaddr), + dma_unmap_len(&tx_cb->map[seg], maplen), + DMA_TO_DEVICE); oal++; seg++; }

- pci_unmap_page(qdev->pdev, + dma_unmap_page(&qdev->pdev->dev, dma_unmap_addr(&tx_cb->map[seg], mapaddr), dma_unmap_len(&tx_cb->map[seg], maplen), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE); }

- pci_unmap_single(qdev->pdev, + dma_unmap_single(&qdev->pdev->dev, dma_unmap_addr(&tx_cb->map[0], mapaddr), dma_unmap_addr(&tx_cb->map[0], maplen), - PCI_DMA_TODEVICE); + DMA_TO_DEVICE);

return NETDEV_TX_BUSY;

@@ -2528,9 +2522,8 @@ static int ql_alloc_net_req_rsp_queues(struct ql3_adapter *qdev) wmb();

qdev->req_q_virt_addr = - pci_alloc_consistent(qdev->pdev, - (size_t) qdev->req_q_size, - &qdev->req_q_phy_addr); + dma_alloc_coherent(&qdev->pdev->dev, (size_t)qdev->req_q_size, + &qdev->req_q_phy_addr, GFP_KERNEL);

if ((qdev->req_q_virt_addr == NULL) || LS_64BITS(qdev->req_q_phy_addr) & (qdev->req_q_size - 1)) { @@ -2539,16 +2532,14 @@ static int ql_alloc_net_req_rsp_queues(struct ql3_adapter *qdev) }

qdev->rsp_q_virt_addr = - pci_alloc_consistent(qdev->pdev, - (size_t) qdev->rsp_q_size, - &qdev->rsp_q_phy_addr); + dma_alloc_coherent(&qdev->pdev->dev, (size_t)qdev->rsp_q_size, + &qdev->rsp_q_phy_addr, GFP_KERNEL);

if ((qdev->rsp_q_virt_addr == NULL) || LS_64BITS(qdev->rsp_q_phy_addr) & (qdev->rsp_q_size - 1)) { netdev_err(qdev->ndev, "rspQ allocation failed\n"); - pci_free_consistent(qdev->pdev, (size_t) qdev->req_q_size, - qdev->req_q_virt_addr, - qdev->req_q_phy_addr); + dma_free_coherent(&qdev->pdev->dev, (size_t)qdev->req_q_size, + qdev->req_q_virt_addr, qdev->req_q_phy_addr); return -ENOMEM; }

@@ -2564,15 +2555,13 @@ static void ql_free_net_req_rsp_queues(struct ql3_adapter *qdev) return; }

- pci_free_consistent(qdev->pdev, - qdev->req_q_size, - qdev->req_q_virt_addr, qdev->req_q_phy_addr); + dma_free_coherent(&qdev->pdev->dev, qdev->req_q_size, + qdev->req_q_virt_addr, qdev->req_q_phy_addr);

qdev->req_q_virt_addr = NULL;

- pci_free_consistent(qdev->pdev, - qdev->rsp_q_size, - qdev->rsp_q_virt_addr, qdev->rsp_q_phy_addr); + dma_free_coherent(&qdev->pdev->dev, qdev->rsp_q_size, + qdev->rsp_q_virt_addr, qdev->rsp_q_phy_addr);

qdev->rsp_q_virt_addr = NULL;

@@ -2596,9 +2585,9 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) return -ENOMEM;

qdev->lrg_buf_q_alloc_virt_addr = - pci_alloc_consistent(qdev->pdev, - qdev->lrg_buf_q_alloc_size, - &qdev->lrg_buf_q_alloc_phy_addr); + dma_alloc_coherent(&qdev->pdev->dev, + qdev->lrg_buf_q_alloc_size, + &qdev->lrg_buf_q_alloc_phy_addr, GFP_KERNEL);

if (qdev->lrg_buf_q_alloc_virt_addr == NULL) { netdev_err(qdev->ndev, "lBufQ failed\n"); @@ -2616,15 +2605,16 @@ static int ql_alloc_buffer_queues(struct ql3_adapter *qdev) qdev->small_buf_q_alloc_size = qdev->small_buf_q_size * 2;

qdev->small_buf_q_alloc_virt_addr = - pci_alloc_consistent(qdev->pdev, - qdev->small_buf_q_alloc_size, - &qdev->small_buf_q_alloc_phy_addr); + dma_alloc_coherent(&qdev->pdev->dev, + qdev->small_buf_q_alloc_size, + &qdev->small_buf_q_alloc_phy_addr, GFP_KERNEL);

if (qdev->small_buf_q_alloc_virt_addr == NULL) { netdev_err(qdev->ndev, "Small Buffer Queue allocation failed\n"); - pci_free_consistent(qdev->pdev, qdev->lrg_buf_q_alloc_size, - qdev->lrg_buf_q_alloc_virt_addr, - qdev->lrg_buf_q_alloc_phy_addr); + dma_free_coherent(&qdev->pdev->dev, + qdev->lrg_buf_q_alloc_size, + qdev->lrg_buf_q_alloc_virt_addr, + qdev->lrg_buf_q_alloc_phy_addr); return -ENOMEM; }

@@ -2641,17 +2631,15 @@ static void ql_free_buffer_queues(struct ql3_adapter *qdev) return; } kfree(qdev->lrg_buf); - pci_free_consistent(qdev->pdev, - qdev->lrg_buf_q_alloc_size, - qdev->lrg_buf_q_alloc_virt_addr, - qdev->lrg_buf_q_alloc_phy_addr); + dma_free_coherent(&qdev->pdev->dev, qdev->lrg_buf_q_alloc_size, + qdev->lrg_buf_q_alloc_virt_addr, + qdev->lrg_buf_q_alloc_phy_addr);

qdev->lrg_buf_q_virt_addr = NULL;

- pci_free_consistent(qdev->pdev, - qdev->small_buf_q_alloc_size, - qdev->small_buf_q_alloc_virt_addr, - qdev->small_buf_q_alloc_phy_addr); + dma_free_coherent(&qdev->pdev->dev, qdev->small_buf_q_alloc_size, + qdev->small_buf_q_alloc_virt_addr, + qdev->small_buf_q_alloc_phy_addr);

qdev->small_buf_q_virt_addr = NULL;

@@ -2669,9 +2657,9 @@ static int ql_alloc_small_buffers(struct ql3_adapter *qdev) QL_SMALL_BUFFER_SIZE);

qdev->small_buf_virt_addr = - pci_alloc_consistent(qdev->pdev, - qdev->small_buf_total_size, - &qdev->small_buf_phy_addr); + dma_alloc_coherent(&qdev->pdev->dev, + qdev->small_buf_total_size, + &qdev->small_buf_phy_addr, GFP_KERNEL);

if (qdev->small_buf_virt_addr == NULL) { netdev_err(qdev->ndev, "Failed to get small buffer memory\n"); @@ -2704,10 +2692,10 @@ static void ql_free_small_buffers(struct ql3_adapter *qdev) return; } if (qdev->small_buf_virt_addr != NULL) { - pci_free_consistent(qdev->pdev, - qdev->small_buf_total_size, - qdev->small_buf_virt_addr, - qdev->small_buf_phy_addr); + dma_free_coherent(&qdev->pdev->dev, + qdev->small_buf_total_size, + qdev->small_buf_virt_addr, + qdev->small_buf_phy_addr);

qdev->small_buf_virt_addr = NULL; } @@ -2722,10 +2710,10 @@ static void ql_free_large_buffers(struct ql3_adapter *qdev) lrg_buf_cb = &qdev->lrg_buf[i]; if (lrg_buf_cb->skb) { dev_kfree_skb(lrg_buf_cb->skb); - pci_unmap_single(qdev->pdev, + dma_unmap_single(&qdev->pdev->dev, dma_unmap_addr(lrg_buf_cb, mapaddr), dma_unmap_len(lrg_buf_cb, maplen), - PCI_DMA_FROMDEVICE); + DMA_FROM_DEVICE); memset(lrg_buf_cb, 0, sizeof(struct ql_rcv_buf_cb)); } else { break; @@ -2777,13 +2765,11 @@ static int ql_alloc_large_buffers(struct ql3_adapter *qdev) * buffer */ skb_reserve(skb, QL_HEADER_SPACE); - map = pci_map_single(qdev->pdev, - skb->data, - qdev->lrg_buffer_len - - QL_HEADER_SPACE, - PCI_DMA_FROMDEVICE); + map = dma_map_single(&qdev->pdev->dev, skb->data, + qdev->lrg_buffer_len - QL_HEADER_SPACE, + DMA_FROM_DEVICE);

- err = pci_dma_mapping_error(qdev->pdev, map); + err = dma_mapping_error(&qdev->pdev->dev, map); if (err) { netdev_err(qdev->ndev, "PCI mapping failed with error: %d\n", @@ -2868,8 +2854,8 @@ static int ql_alloc_mem_resources(struct ql3_adapter *qdev) * Network Completion Queue Producer Index Register */ qdev->shadow_reg_virt_addr = - pci_alloc_consistent(qdev->pdev, - PAGE_SIZE, &qdev->shadow_reg_phy_addr); + dma_alloc_coherent(&qdev->pdev->dev, PAGE_SIZE, + &qdev->shadow_reg_phy_addr, GFP_KERNEL);

if (qdev->shadow_reg_virt_addr != NULL) { qdev->preq_consumer_index = qdev->shadow_reg_virt_addr; @@ -2924,10 +2910,9 @@ static int ql_alloc_mem_resources(struct ql3_adapter *qdev) err_buffer_queues: ql_free_net_req_rsp_queues(qdev); err_req_rsp: - pci_free_consistent(qdev->pdev, - PAGE_SIZE, - qdev->shadow_reg_virt_addr, - qdev->shadow_reg_phy_addr); + dma_free_coherent(&qdev->pdev->dev, PAGE_SIZE, + qdev->shadow_reg_virt_addr, + qdev->shadow_reg_phy_addr);

return -ENOMEM; } @@ -2940,10 +2925,9 @@ static void ql_free_mem_resources(struct ql3_adapter *qdev) ql_free_buffer_queues(qdev); ql_free_net_req_rsp_queues(qdev); if (qdev->shadow_reg_virt_addr != NULL) { - pci_free_consistent(qdev->pdev, - PAGE_SIZE, - qdev->shadow_reg_virt_addr, - qdev->shadow_reg_phy_addr); + dma_free_coherent(&qdev->pdev->dev, PAGE_SIZE, + qdev->shadow_reg_virt_addr, + qdev->shadow_reg_phy_addr); qdev->shadow_reg_virt_addr = NULL; } } @@ -3644,18 +3628,15 @@ static void ql_reset_work(struct work_struct *work) if (tx_cb->skb) { netdev_printk(KERN_DEBUG, ndev, "Freeing lost SKB\n"); - pci_unmap_single(qdev->pdev, - dma_unmap_addr(&tx_cb->map[0], - mapaddr), - dma_unmap_len(&tx_cb->map[0], maplen), - PCI_DMA_TODEVICE); + dma_unmap_single(&qdev->pdev->dev, + dma_unmap_addr(&tx_cb->map[0], mapaddr), + dma_unmap_len(&tx_cb->map[0], maplen), + DMA_TO_DEVICE); for (j = 1; j < tx_cb->seg_count; j++) { - pci_unmap_page(qdev->pdev, - dma_unmap_addr(&tx_cb->map[j], - mapaddr), - dma_unmap_len(&tx_cb->map[j], - maplen), - PCI_DMA_TODEVICE); + dma_unmap_page(&qdev->pdev->dev, + dma_unmap_addr(&tx_cb->map[j], mapaddr), + dma_unmap_len(&tx_cb->map[j], maplen), + DMA_TO_DEVICE); } dev_kfree_skb(tx_cb->skb); tx_cb->skb = NULL; @@ -3787,13 +3768,10 @@ static int ql3xxx_probe(struct pci_dev *pdev,

pci_set_master(pdev);

- if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) pci_using_dac = 1; - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - } else if (!(err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)))) { + else if (!(err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)))) pci_using_dac = 0; - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - }

if (err) { pr_err("%s no usable DMA configuration\n", pci_name(pdev));

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chen Ni nichen@iscas.ac.cn

[ Upstream commit eaac6a2d26b65511e164772bec6918fcbc61938e ]

Add check for usbnet_get_endpoints() and return the error if it fails in order to transfer the error.

Fixes: 16626b0cc3d5 ("asix: Add a new driver for the AX88172A") Signed-off-by: Chen Ni nichen@iscas.ac.cn Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/ax88172a.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c index 909755ef71ac3..5881620e44365 100644 --- a/drivers/net/usb/ax88172a.c +++ b/drivers/net/usb/ax88172a.c @@ -198,7 +198,9 @@ static int ax88172a_bind(struct usbnet *dev, struct usb_interface *intf) u8 buf[ETH_ALEN]; struct ax88172a_private *priv;

- usbnet_get_endpoints(dev, intf); + ret = usbnet_get_endpoints(dev, intf); + if (ret) + return ret;

priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv)

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Matthew Wilcox (Oracle) willy@infradead.org

[ Upstream commit c79c5a0a00a9457718056b588f312baadf44e471 ]

A process may map only some of the pages in a folio, and might be missed if it maps the poisoned page but not the head page. Or it might be unnecessarily hit if it maps the head page, but not the poisoned page.

Link: https://lkml.kernel.org/r/20231218135837.3310403-3-willy@infradead.org Fixes: 7af446a841a2 ("HWPOISON, hugetlb: enable error handling path for hugepage") Signed-off-by: Matthew Wilcox (Oracle) willy@infradead.org Cc: Dan Williams dan.j.williams@intel.com Cc: Naoya Horiguchi n-horiguchi@ah.jp.nec.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- mm/memory-failure.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3da3c63dccd1a..c971d5e11f932 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -989,7 +989,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ - if (!page_mapped(hpage)) + if (!page_mapped(p)) return true;

if (PageKsm(p)) { @@ -1033,10 +1033,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (kill) collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED);

- unmap_success = try_to_unmap(hpage, ttu); + unmap_success = try_to_unmap(p, ttu); if (!unmap_success) pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(p));

/* * try_to_unmap() might put mlocked page in lru cache, so call

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jiajun Xie jiajun.xie.sh@gmail.com

commit 9eab0421fa94a3dde0d1f7e36ab3294fc306c99d upstream.

The bug happens when highest bit of holebegin is 1, suppose holebegin is 0x8000000111111000, after shift, hba would be 0xfff8000000111111, then vma_interval_tree_foreach would look it up fail or leads to the wrong result.

error call seq e.g.: - mmap(..., offset=0x8000000111111000) |- syscall(mmap, ... unsigned long, off): |- ksys_mmap_pgoff( ... , off >> PAGE_SHIFT);

here pgoff is correctly shifted to 0x8000000111111, but pass 0x8000000111111000 as holebegin to unmap would then cause terrible result, as shown below:

- unmap_mapping_range(..., loff_t const holebegin) |- pgoff_t hba = holebegin >> PAGE_SHIFT; /* hba = 0xfff8000000111111 unexpectedly */

The issue happens in Heterogeneous computing, where the device(e.g. gpu) and host share the same virtual address space.

A simple workflow pattern which hit the issue is: /* host */ 1. userspace first mmap a file backed VA range with specified offset. e.g. (offset=0x800..., mmap return: va_a) 2. write some data to the corresponding sys page e.g. (va_a = 0xAABB) /* device */ 3. gpu workload touches VA, triggers gpu fault and notify the host. /* host */ 4. reviced gpu fault notification, then it will: 4.1 unmap host pages and also takes care of cpu tlb (use unmap_mapping_range with offset=0x800...) 4.2 migrate sys page to device 4.3 setup device page table and resolve device fault. /* device */ 5. gpu workload continued, it accessed va_a and got 0xAABB. 6. gpu workload continued, it wrote 0xBBCC to va_a. /* host */ 7. userspace access va_a, as expected, it will: 7.1 trigger cpu vm fault. 7.2 driver handling fault to migrate gpu local page to host. 8. userspace then could correctly get 0xBBCC from va_a 9. done

But in step 4.1, if we hit the bug this patch mentioned, then userspace would never trigger cpu fault, and still get the old value: 0xAABB.

Making holebegin unsigned first fixes the bug.

Link: https://lkml.kernel.org/r/20231220052839.26970-1-jiajun.xie.sh@gmail.com Signed-off-by: Jiajun Xie jiajun.xie.sh@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memory.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/mm/memory.c +++ b/mm/memory.c @@ -3042,8 +3042,8 @@ void unmap_mapping_pages(struct address_ void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { - pgoff_t hba = holebegin >> PAGE_SHIFT; - pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT;

/* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) {

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Geert Uytterhoeven geert+renesas@glider.be

commit 1036f69e251380573e256568cf814506e3fb9988 upstream.

On RZ/Five SMARC EVK, where probing of SDHI is deferred due to probe deferral of the vqmmc-supply regulator:

------------[ cut here ]------------ WARNING: CPU: 0 PID: 0 at kernel/time/timer.c:1738 __run_timers.part.0+0x1d0/0x1e8 Modules linked in: CPU: 0 PID: 0 Comm: swapper Not tainted 6.7.0-rc4 #101 Hardware name: Renesas SMARC EVK based on r9a07g043f01 (DT) epc : __run_timers.part.0+0x1d0/0x1e8 ra : __run_timers.part.0+0x134/0x1e8 epc : ffffffff800771a4 ra : ffffffff80077108 sp : ffffffc800003e60 gp : ffffffff814f5028 tp : ffffffff8140c5c0 t0 : ffffffc800000000 t1 : 0000000000000001 t2 : ffffffff81201300 s0 : ffffffc800003f20 s1 : ffffffd8023bc4a0 a0 : 00000000fffee6b0 a1 : 0004010000400000 a2 : ffffffffc0000016 a3 : ffffffff81488640 a4 : ffffffc800003e60 a5 : 0000000000000000 a6 : 0000000004000000 a7 : ffffffc800003e68 s2 : 0000000000000122 s3 : 0000000000200000 s4 : 0000000000000000 s5 : ffffffffffffffff s6 : ffffffff81488678 s7 : ffffffff814886c0 s8 : ffffffff814f49c0 s9 : ffffffff81488640 s10: 0000000000000000 s11: ffffffc800003e60 t3 : 0000000000000240 t4 : 0000000000000a52 t5 : ffffffd8024ae018 t6 : ffffffd8024ae038 status: 0000000200000100 badaddr: 0000000000000000 cause: 0000000000000003 [<ffffffff800771a4>] __run_timers.part.0+0x1d0/0x1e8 [<ffffffff800771e0>] run_timer_softirq+0x24/0x4a [<ffffffff80809092>] __do_softirq+0xc6/0x1fa [<ffffffff80028e4c>] irq_exit_rcu+0x66/0x84 [<ffffffff80800f7a>] handle_riscv_irq+0x40/0x4e [<ffffffff80808f48>] call_on_irq_stack+0x1c/0x28 ---[ end trace 0000000000000000 ]---

What happens?

renesas_sdhi_probe() { tmio_mmc_host_alloc() mmc_alloc_host() INIT_DELAYED_WORK(&host->detect, mmc_rescan);

devm_request_irq(tmio_mmc_irq);

/* * After this, the interrupt handler may be invoked at any time * * tmio_mmc_irq() * { * __tmio_mmc_card_detect_irq() * mmc_detect_change() * _mmc_detect_change() * mmc_schedule_delayed_work(&host->detect, delay); * } */

tmio_mmc_host_probe() tmio_mmc_init_ocr() -EPROBE_DEFER

tmio_mmc_host_free() mmc_free_host() }

When expire_timers() runs later, it warns because the MMC host structure containing the delayed work was freed, and now contains an invalid work function pointer.

Fix this by cancelling any pending delayed work before releasing the MMC host structure.

Signed-off-by: Geert Uytterhoeven geert+renesas@glider.be Tested-by: Lad Prabhakar prabhakar.mahadev-lad.rj@bp.renesas.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/205dc4c91b47e31b64392fe2498c7a449e717b4b.170168933... Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/core/host.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -489,6 +489,7 @@ EXPORT_SYMBOL(mmc_remove_host); */ void mmc_free_host(struct mmc_host *host) { + cancel_delayed_work_sync(&host->detect); mmc_pwrseq_free(host); put_device(&host->class_dev); }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Phil Sutter phil@nwl.cc

commit f1082dd31fe461d482d69da2a8eccfeb7bf07ac2 upstream.

An nftables family is merely a hollow container, its family just a number and such not reliant on compile-time options other than nftables support itself. Add an artificial check so attempts at using a family the kernel can't support fail as early as possible. This helps user space detect kernels which lack e.g. NFPROTO_INET.

Signed-off-by: Phil Sutter phil@nwl.cc Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/nf_tables_api.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+)

--- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -893,6 +893,30 @@ static int nft_chain_hash_cmp(struct rha return strcmp(chain->name, name); }

+static bool nft_supported_family(u8 family) +{ + return false +#ifdef CONFIG_NF_TABLES_INET + || family == NFPROTO_INET +#endif +#ifdef CONFIG_NF_TABLES_IPV4 + || family == NFPROTO_IPV4 +#endif +#ifdef CONFIG_NF_TABLES_ARP + || family == NFPROTO_ARP +#endif +#ifdef CONFIG_NF_TABLES_NETDEV + || family == NFPROTO_NETDEV +#endif +#if IS_ENABLED(CONFIG_NF_TABLES_BRIDGE) + || family == NFPROTO_BRIDGE +#endif +#ifdef CONFIG_NF_TABLES_IPV6 + || family == NFPROTO_IPV6 +#endif + ; +} + static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -908,6 +932,9 @@ static int nf_tables_newtable(struct net struct nft_ctx ctx; int err;

+ if (!nft_supported_family(family)) + return -EOPNOTSUPP; + lockdep_assert_held(&nft_net->commit_mutex); attr = nla[NFTA_TABLE_NAME]; table = nft_table_lookup(net, attr, family, genmask);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bartosz Pawlowski bartosz.pawlowski@intel.com

commit a18615b1cfc04f00548c60eb9a77e0ce56e848fd upstream.

Due to a hardware issue in A and B steppings of Intel IPU E2000, it expects wrong endianness in ATS invalidation message body. This problem can lead to outdated translations being returned as valid and finally cause system instability.

To prevent such issues, add quirk_intel_e2000_no_ats() to disable ATS for vulnerable IPU E2000 devices.

Link: https://lore.kernel.org/r/20230908143606.685930-3-bartosz.pawlowski@intel.co... Signed-off-by: Bartosz Pawlowski bartosz.pawlowski@intel.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Reviewed-by: Alexander Lobakin aleksander.lobakin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/quirks.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+)

--- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5212,6 +5212,25 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AT /* AMD Navi14 dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats); + +/* + * Intel IPU E2000 revisions before C0 implement incorrect endianness + * in ATS Invalidate Request message body. Disable ATS for those devices. + */ +static void quirk_intel_e2000_no_ats(struct pci_dev *pdev) +{ + if (pdev->revision < 0x20) + quirk_no_ats(pdev); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1451, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1452, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1453, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1454, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1455, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1457, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1459, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x145a, quirk_intel_e2000_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x145c, quirk_intel_e2000_no_ats); #endif /* CONFIG_PCI_ATS */

/* Freescale PCIe doesn't support MSI in RC mode */

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit cf86a086a18095e33e0637cb78cda1fcf5280852 upstream.

percpu_counter_add() uses a default batch size which is quite big on platforms with 256 cpus. (2*256 -> 512)

This means dst_entries_get_fast() can be off by +/- 2*(nr_cpus^2) (131072 on servers with 256 cpus)

Reduce the batch size to something more reasonable, and add logic to ip6_dst_gc() to call dst_entries_get_slow() before calling the _very_ expensive fib6_run_gc() function.

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Suraj Jitindar Singh surajjs@amazon.com Cc: stable@vger.kernel.org # 4.19.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/dst_ops.h | 4 +++- net/core/dst.c | 8 ++++---- net/ipv6/route.c | 3 +++ 3 files changed, 10 insertions(+), 5 deletions(-)

--- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -53,9 +53,11 @@ static inline int dst_entries_get_slow(s return percpu_counter_sum_positive(&dst->pcpuc_entries); }

+#define DST_PERCPU_COUNTER_BATCH 32 static inline void dst_entries_add(struct dst_ops *dst, int val) { - percpu_counter_add(&dst->pcpuc_entries, val); + percpu_counter_add_batch(&dst->pcpuc_entries, val, + DST_PERCPU_COUNTER_BATCH); }

static inline int dst_entries_init(struct dst_ops *dst) --- a/net/core/dst.c +++ b/net/core/dst.c @@ -97,11 +97,11 @@ void *dst_alloc(struct dst_ops *ops, str { struct dst_entry *dst;

- if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { + if (ops->gc && + !(flags & DST_NOCOUNT) && + dst_entries_get_fast(ops) > ops->gc_thresh) { if (ops->gc(ops)) { - printk_ratelimited(KERN_NOTICE "Route cache is full: " - "consider increasing sysctl " - "net.ipv[4|6].route.max_size.\n"); + pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); return NULL; } } --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2778,6 +2778,9 @@ static int ip6_dst_gc(struct dst_ops *op int entries;

entries = dst_entries_get_fast(ops); + if (entries > rt_max_size) + entries = dst_entries_get_slow(ops); + if (time_after(rt_last_gc + rt_min_interval, jiffies) && entries <= rt_max_size) goto out;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jon Maxwell jmaxwell37@gmail.com

commit af6d10345ca76670c1b7c37799f0d5576ccef277 upstream.

In ip6_dst_gc() replace:

if (entries > gc_thresh)

With:

if (entries > ops->gc_thresh)

Sending Ipv6 packets in a loop via a raw socket triggers an issue where a route is cloned by ip6_rt_cache_alloc() for each packet sent. This quickly consumes the Ipv6 max_size threshold which defaults to 4096 resulting in these warnings:

[1] 99.187805] dst_alloc: 7728 callbacks suppressed [2] Route cache is full: consider increasing sysctl net.ipv6.route.max_size. . . [300] Route cache is full: consider increasing sysctl net.ipv6.route.max_size.

When this happens the packet is dropped and sendto() gets a network is unreachable error:

remaining pkt 200557 errno 101 remaining pkt 196462 errno 101 . . remaining pkt 126821 errno 101

Implement David Aherns suggestion to remove max_size check seeing that Ipv6 has a GC to manage memory usage. Ipv4 already does not check max_size.

Here are some memory comparisons for Ipv4 vs Ipv6 with the patch:

Test by running 5 instances of a program that sends UDP packets to a raw socket 5000000 times. Compare Ipv4 and Ipv6 performance with a similar program.

Ipv4:

Before test:

MemFree: 29427108 kB Slab: 237612 kB

ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0 xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0 ip_dst_cache 2881 3990 192 42 2 : tunables 0 0 0

During test:

MemFree: 29417608 kB Slab: 247712 kB

ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0 xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0 ip_dst_cache 44394 44394 192 42 2 : tunables 0 0 0

After test:

MemFree: 29422308 kB Slab: 238104 kB

ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0 xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0 ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0

Ipv6 with patch:

Errno 101 errors are not observed anymore with the patch.

Before test:

MemFree: 29422308 kB Slab: 238104 kB

ip6_dst_cache 1912 2528 256 32 2 : tunables 0 0 0 xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0 ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0

During Test:

MemFree: 29431516 kB Slab: 240940 kB

ip6_dst_cache 11980 12064 256 32 2 : tunables 0 0 0 xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0 ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0

After Test:

MemFree: 29441816 kB Slab: 238132 kB

ip6_dst_cache 1902 2432 256 32 2 : tunables 0 0 0 xfrm_dst_cache 0 0 320 25 2 : tunables 0 0 0 ip_dst_cache 3048 4116 192 42 2 : tunables 0 0 0

Tested-by: Andrea Mayer andrea.mayer@uniroma2.it Signed-off-by: Jon Maxwell jmaxwell37@gmail.com Reviewed-by: David Ahern dsahern@kernel.org Link: https://lore.kernel.org/r/20230112012532.311021-1-jmaxwell37@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Suraj Jitindar Singh surajjs@amazon.com Cc: stable@vger.kernel.org # 4.19.x Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/dst_ops.h | 2 +- net/core/dst.c | 8 ++------ net/ipv6/route.c | 13 +++++-------- 3 files changed, 8 insertions(+), 15 deletions(-)

--- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -16,7 +16,7 @@ struct dst_ops { unsigned short family; unsigned int gc_thresh;

- int (*gc)(struct dst_ops *ops); + void (*gc)(struct dst_ops *ops); struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*mtu)(const struct dst_entry *); --- a/net/core/dst.c +++ b/net/core/dst.c @@ -99,12 +99,8 @@ void *dst_alloc(struct dst_ops *ops, str

if (ops->gc && !(flags & DST_NOCOUNT) && - dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) { - pr_notice_ratelimited("Route cache is full: consider increasing sysctl net.ipv6.route.max_size.\n"); - return NULL; - } - } + dst_entries_get_fast(ops) > ops->gc_thresh) + ops->gc(ops);

dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -92,7 +92,7 @@ static struct dst_entry *ip6_negative_ad static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); -static int ip6_dst_gc(struct dst_ops *ops); +static void ip6_dst_gc(struct dst_ops *ops);

static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); @@ -2767,11 +2767,10 @@ out: return dst; }

-static int ip6_dst_gc(struct dst_ops *ops) +static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; - int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; @@ -2779,11 +2778,10 @@ static int ip6_dst_gc(struct dst_ops *op int entries;

entries = dst_entries_get_fast(ops); - if (entries > rt_max_size) + if (entries > ops->gc_thresh) entries = dst_entries_get_slow(ops);

- if (time_after(rt_last_gc + rt_min_interval, jiffies) && - entries <= rt_max_size) + if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out;

fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); @@ -2793,7 +2791,6 @@ static int ip6_dst_gc(struct dst_ops *op out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); - return entries > rt_max_size; }

static int ip6_convert_metrics(struct net *net, struct fib6_info *rt, @@ -5336,7 +5333,7 @@ static int __net_init ip6_route_net_init #endif

net->ipv6.sysctl.flush_delay = 0; - net->ipv6.sysctl.ip6_rt_max_size = 4096; + net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;