From: Dan Robertson dan@dlrobertson.com

[ Upstream commit 9fdd04918a452980631ecc499317881c1d120b70 ]

Fix a logic error that could result in a null deref if the user sets the mode incorrectly for the given addr type.

Signed-off-by: Dan Robertson dan@dlrobertson.com Acked-by: Alexander Aring aahringo@redhat.com Link: https://lore.kernel.org/r/20210423040214.15438-2-dan@dlrobertson.com Signed-off-by: Stefan Schmidt stefan@datenfreihafen.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ieee802154/nl802154.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index cfc01314958f..936371340dc3 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -1330,19 +1330,20 @@ ieee802154_llsec_parse_dev_addr(struct nlattr *nla, nl802154_dev_addr_policy)) return -EINVAL;

- if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || - !attrs[NL802154_DEV_ADDR_ATTR_MODE] || - !(attrs[NL802154_DEV_ADDR_ATTR_SHORT] || - attrs[NL802154_DEV_ADDR_ATTR_EXTENDED])) + if (!attrs[NL802154_DEV_ADDR_ATTR_PAN_ID] || !attrs[NL802154_DEV_ADDR_ATTR_MODE]) return -EINVAL;

addr->pan_id = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_PAN_ID]); addr->mode = nla_get_u32(attrs[NL802154_DEV_ADDR_ATTR_MODE]); switch (addr->mode) { case NL802154_DEV_ADDR_SHORT: + if (!attrs[NL802154_DEV_ADDR_ATTR_SHORT]) + return -EINVAL; addr->short_addr = nla_get_le16(attrs[NL802154_DEV_ADDR_ATTR_SHORT]); break; case NL802154_DEV_ADDR_EXTENDED: + if (!attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]) + return -EINVAL; addr->extended_addr = nla_get_le64(attrs[NL802154_DEV_ADDR_ATTR_EXTENDED]); break; default:

From: Mark Bolhuis mark@bolhuis.dev

[ Upstream commit 48e33befe61a7d407753c53d1a06fc8d6b5dab80 ]

Add BUS_VIRTUAL to hid_connect logging since it's a valid hid bus type and it should not print <UNKNOWN>

Signed-off-by: Mark Bolhuis mark@bolhuis.dev Signed-off-by: Jiri Kosina jkosina@suse.cz Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/hid/hid-core.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 40b36e59a867..a056850328ef 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1804,6 +1804,9 @@ int hid_connect(struct hid_device *hdev, unsigned int connect_mask) case BUS_I2C: bus = "I2C"; break; + case BUS_VIRTUAL: + bus = "VIRTUAL"; + break; default: bus = "<UNKNOWN>"; }

From: Yongqiang Liu liuyongqiang13@huawei.com

[ Upstream commit 040ab72ee10ea88e1883ad143b3e2b77596abc31 ]

GCC reports the following warning with W=1:

arch/arm/mach-omap2/board-n8x0.c:325:19: warning: variable 'index' set but not used [-Wunused-but-set-variable] 325 | int bit, *openp, index; | ^~~~~

Fix this by moving CONFIG_MMC_OMAP to cover the rest codes in the n8x0_mmc_callback().

Signed-off-by: Yongqiang Liu liuyongqiang13@huawei.com Signed-off-by: Tony Lindgren tony@atomide.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-omap2/board-n8x0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index 6b6fda65fb3b..5eeecf83c9e6 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -327,6 +327,7 @@ static int n8x0_mmc_get_cover_state(struct device *dev, int slot)

static void n8x0_mmc_callback(void *data, u8 card_mask) { +#ifdef CONFIG_MMC_OMAP int bit, *openp, index;

if (board_is_n800()) { @@ -344,7 +345,6 @@ static void n8x0_mmc_callback(void *data, u8 card_mask) else *openp = 0;

-#ifdef CONFIG_MMC_OMAP omap_mmc_notify_cover_event(mmc_device, index, *openp); #else pr_warn("MMC: notify cover event not available\n");

From: Hillf Danton hdanton@sina.com

[ Upstream commit 1ab19c5de4c537ec0d9b21020395a5b5a6c059b2 ]

The GLF_LRU flag is checked under lru_lock in gfs2_glock_remove_from_lru() to remove the glock from the lru list in __gfs2_glock_put().

On the shrink scan path, the same flag is cleared under lru_lock but because of cond_resched_lock(&lru_lock) in gfs2_dispose_glock_lru(), progress on the put side can be made without deleting the glock from the lru list.

Keep GLF_LRU across the race window opened by cond_resched_lock(&lru_lock) to ensure correct behavior on both sides - clear GLF_LRU after list_del under lru_lock.

Reported-by: syzbot syzbot+34ba7ddbf3021981a228@syzkaller.appspotmail.com Signed-off-by: Hillf Danton hdanton@sina.com Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/gfs2/glock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index f19e49a5d032..3d4d35083438 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -1350,6 +1350,7 @@ __acquires(&lru_lock) while(!list_empty(list)) { gl = list_entry(list->next, struct gfs2_glock, gl_lru); list_del_init(&gl->gl_lru); + clear_bit(GLF_LRU, &gl->gl_flags); if (!spin_trylock(&gl->gl_lockref.lock)) { add_back_to_lru: list_add(&gl->gl_lru, &lru_list); @@ -1396,7 +1397,6 @@ static long gfs2_scan_glock_lru(int nr) if (!test_bit(GLF_LOCK, &gl->gl_flags)) { list_move(&gl->gl_lru, &dispose); atomic_dec(&lru_count); - clear_bit(GLF_LRU, &gl->gl_flags); freed++; continue; }

From: Jiapeng Chong jiapeng.chong@linux.alibaba.com

[ Upstream commit f336d0b93ae978f12c5e27199f828da89b91e56a ]

The error code is missing in this code scenario, add the error code '-EINVAL' to the return value 'status'.

Eliminate the follow smatch warning:

drivers/net/ethernet/myricom/myri10ge/myri10ge.c:3818 myri10ge_probe() warn: missing error code 'status'.

Reported-by: Abaci Robot abaci@linux.alibaba.com Signed-off-by: Jiapeng Chong jiapeng.chong@linux.alibaba.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 02ec326cb129..5eeba263b5f8 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -4050,6 +4050,7 @@ static int myri10ge_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_err(&pdev->dev, "invalid sram_size %dB or board span %ldB\n", mgp->sram_size, mgp->board_span); + status = -EINVAL; goto abort_with_ioremap; } memcpy_fromio(mgp->eeprom_strings,

From: Jiapeng Chong jiapeng.chong@linux.alibaba.com

[ Upstream commit a8db57c1d285c758adc7fb43d6e2bad2554106e1 ]

The error code is missing in this code scenario, add the error code '-EINVAL' to the return value 'err'.

Eliminate the follow smatch warning:

net/core/rtnetlink.c:4834 rtnl_bridge_notify() warn: missing error code 'err'.

Reported-by: Abaci Robot abaci@linux.alibaba.com Signed-off-by: Jiapeng Chong jiapeng.chong@linux.alibaba.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/rtnetlink.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e652e376fb30..93de31ca3d65 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3530,8 +3530,10 @@ static int rtnl_bridge_notify(struct net_device *dev) if (err < 0) goto errout;

- if (!skb->len) + if (!skb->len) { + err = -EINVAL; goto errout; + }

rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return 0;

From: Zheng Yongjun zhengyongjun3@huawei.com

[ Upstream commit 49251cd00228a3c983651f6bb2f33f6a0b8f152e ]

When kalloc or kmemdup failed, should return ENOMEM rather than ENOBUF.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/compat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/compat.c b/net/compat.c index ce851cf4d0f9..1f08f0e49e07 100644 --- a/net/compat.c +++ b/net/compat.c @@ -159,7 +159,7 @@ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, if (kcmlen > stackbuf_size) kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL); if (kcmsg == NULL) - return -ENOBUFS; + return -ENOMEM;

/* Now copy them over neatly. */ memset(kcmsg, 0, kcmlen);

From: Randy Dunlap rdunlap@infradead.org

[ Upstream commit 0cfbb589d67f16fa55b26ae02b69c31b52e344b1 ]

When CONFIG_HAS_IOMEM is not set/enabled, certain iomap() family functions [including ioremap(), devm_ioremap(), etc.] are not available. Drivers that use these functions should depend on HAS_IOMEM so that they do not cause build errors.

Rectifies these build errors: s390-linux-ld: drivers/dma/qcom/hidma_mgmt.o: in function `hidma_mgmt_probe': hidma_mgmt.c:(.text+0x780): undefined reference to `devm_ioremap_resource' s390-linux-ld: drivers/dma/qcom/hidma_mgmt.o: in function `hidma_mgmt_init': hidma_mgmt.c:(.init.text+0x126): undefined reference to `of_address_to_resource' s390-linux-ld: hidma_mgmt.c:(.init.text+0x16e): undefined reference to `of_address_to_resource'

Fixes: 67a2003e0607 ("dmaengine: add Qualcomm Technologies HIDMA channel driver") Signed-off-by: Randy Dunlap rdunlap@infradead.org Reported-by: kernel test robot lkp@intel.com Cc: Sinan Kaya okaya@codeaurora.org Cc: Vinod Koul vkoul@kernel.org Cc: dmaengine@vger.kernel.org Link: https://lore.kernel.org/r/20210522021313.16405-3-rdunlap@infradead.org Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/qcom/Kconfig | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig index a7761c4025f4..a97c7123d913 100644 --- a/drivers/dma/qcom/Kconfig +++ b/drivers/dma/qcom/Kconfig @@ -9,6 +9,7 @@ config QCOM_BAM_DMA

config QCOM_HIDMA_MGMT tristate "Qualcomm Technologies HIDMA Management support" + depends on HAS_IOMEM select DMA_ENGINE help Enable support for the Qualcomm Technologies HIDMA Management.

From: Naoya Horiguchi n-horiguchi@ah.jp.nec.com

[ Upstream commit b37ff71cc626a0c1b5e098ff9a0b723815f6aaeb ]

We'd like to narrow down the error region in memory error on hugetlb pages. However, currently we set PageHWPoison flags on all subpages in the error hugepage and add # of subpages to num_hwpoison_pages, which doesn't fit our purpose.

So this patch changes the behavior and we only set PageHWPoison on the head page then increase num_hwpoison_pages only by 1. This is a preparation for narrow-down part which comes in later patches.

Link: http://lkml.kernel.org/r/1496305019-5493-4-git-send-email-n-horiguchi@ah.jp.... Signed-off-by: Naoya Horiguchi n-horiguchi@ah.jp.nec.com Cc: Michal Hocko mhocko@kernel.org Cc: "Aneesh Kumar K.V" aneesh.kumar@linux.vnet.ibm.com Cc: Anshuman Khandual khandual@linux.vnet.ibm.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/swapops.h | 9 ----- mm/memory-failure.c | 87 ++++++++++++----------------------------- 2 files changed, 24 insertions(+), 72 deletions(-)

diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 5c3a5f3e7eec..c5ff7b217ee6 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -196,15 +196,6 @@ static inline void num_poisoned_pages_dec(void) atomic_long_dec(&num_poisoned_pages); }

-static inline void num_poisoned_pages_add(long num) -{ - atomic_long_add(num, &num_poisoned_pages); -} - -static inline void num_poisoned_pages_sub(long num) -{ - atomic_long_sub(num, &num_poisoned_pages); -} #else

static inline swp_entry_t make_hwpoison_entry(struct page *page) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index d6524dce43b2..ad156b42d2ad 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1010,22 +1010,6 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, return ret; }

-static void set_page_hwpoison_huge_page(struct page *hpage) -{ - int i; - int nr_pages = 1 << compound_order(hpage); - for (i = 0; i < nr_pages; i++) - SetPageHWPoison(hpage + i); -} - -static void clear_page_hwpoison_huge_page(struct page *hpage) -{ - int i; - int nr_pages = 1 << compound_order(hpage); - for (i = 0; i < nr_pages; i++) - ClearPageHWPoison(hpage + i); -} - /** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page @@ -1051,7 +1035,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags) struct page *hpage; struct page *orig_head; int res; - unsigned int nr_pages; unsigned long page_flags;

if (!sysctl_memory_failure_recovery) @@ -1065,24 +1048,23 @@ int memory_failure(unsigned long pfn, int trapno, int flags)

p = pfn_to_page(pfn); orig_head = hpage = compound_head(p); + + /* tmporary check code, to be updated in later patches */ + if (PageHuge(p)) { + if (TestSetPageHWPoison(hpage)) { + pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); + return 0; + } + goto tmp; + } if (TestSetPageHWPoison(p)) { pr_err("Memory failure: %#lx: already hardware poisoned\n", pfn); return 0; }

- /* - * Currently errors on hugetlbfs pages are measured in hugepage units, - * so nr_pages should be 1 << compound_order. OTOH when errors are on - * transparent hugepages, they are supposed to be split and error - * measurement is done in normal page units. So nr_pages should be one - * in this case. - */ - if (PageHuge(p)) - nr_pages = 1 << compound_order(hpage); - else /* normal page or thp */ - nr_pages = 1; - num_poisoned_pages_add(nr_pages); +tmp: + num_poisoned_pages_inc();

/* * We need/can do nothing about count=0 pages. @@ -1110,12 +1092,11 @@ int memory_failure(unsigned long pfn, int trapno, int flags) if (PageHWPoison(hpage)) { if ((hwpoison_filter(p) && TestClearPageHWPoison(p)) || (p != hpage && TestSetPageHWPoison(hpage))) { - num_poisoned_pages_sub(nr_pages); + num_poisoned_pages_dec(); unlock_page(hpage); return 0; } } - set_page_hwpoison_huge_page(hpage); res = dequeue_hwpoisoned_huge_page(hpage); action_result(pfn, MF_MSG_FREE_HUGE, res ? MF_IGNORED : MF_DELAYED); @@ -1138,7 +1119,7 @@ int memory_failure(unsigned long pfn, int trapno, int flags) pr_err("Memory failure: %#lx: thp split failed\n", pfn); if (TestClearPageHWPoison(p)) - num_poisoned_pages_sub(nr_pages); + num_poisoned_pages_dec(); put_hwpoison_page(p); return -EBUSY; } @@ -1202,14 +1183,14 @@ int memory_failure(unsigned long pfn, int trapno, int flags) */ if (!PageHWPoison(p)) { pr_err("Memory failure: %#lx: just unpoisoned\n", pfn); - num_poisoned_pages_sub(nr_pages); + num_poisoned_pages_dec(); unlock_page(hpage); put_hwpoison_page(hpage); return 0; } if (hwpoison_filter(p)) { if (TestClearPageHWPoison(p)) - num_poisoned_pages_sub(nr_pages); + num_poisoned_pages_dec(); unlock_page(hpage); put_hwpoison_page(hpage); return 0; @@ -1228,14 +1209,6 @@ int memory_failure(unsigned long pfn, int trapno, int flags) put_hwpoison_page(hpage); return 0; } - /* - * Set PG_hwpoison on all pages in an error hugepage, - * because containment is done in hugepage unit for now. - * Since we have done TestSetPageHWPoison() for the head page with - * page lock held, we can safely set PG_hwpoison bits on tail pages. - */ - if (PageHuge(p)) - set_page_hwpoison_huge_page(hpage);

/* * It's very difficult to mess with pages currently under IO @@ -1407,7 +1380,6 @@ int unpoison_memory(unsigned long pfn) struct page *page; struct page *p; int freeit = 0; - unsigned int nr_pages; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);

@@ -1452,8 +1424,6 @@ int unpoison_memory(unsigned long pfn) return 0; }

- nr_pages = 1 << compound_order(page); - if (!get_hwpoison_page(p)) { /* * Since HWPoisoned hugepage should have non-zero refcount, @@ -1483,10 +1453,8 @@ int unpoison_memory(unsigned long pfn) if (TestClearPageHWPoison(page)) { unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", pfn, &unpoison_rs); - num_poisoned_pages_sub(nr_pages); + num_poisoned_pages_dec(); freeit = 1; - if (PageHuge(page)) - clear_page_hwpoison_huge_page(page); } unlock_page(page);

@@ -1612,14 +1580,10 @@ static int soft_offline_huge_page(struct page *page, int flags) ret = -EIO; } else { /* overcommit hugetlb page will be freed to buddy */ - if (PageHuge(page)) { - set_page_hwpoison_huge_page(hpage); + SetPageHWPoison(page); + if (PageHuge(page)) dequeue_hwpoisoned_huge_page(hpage); - num_poisoned_pages_add(1 << compound_order(hpage)); - } else { - SetPageHWPoison(page); - num_poisoned_pages_inc(); - } + num_poisoned_pages_inc(); } return ret; } @@ -1728,15 +1692,12 @@ static int soft_offline_in_use_page(struct page *page, int flags)

static void soft_offline_free_page(struct page *page) { - if (PageHuge(page)) { - struct page *hpage = compound_head(page); + struct page *head = compound_head(page);

- set_page_hwpoison_huge_page(hpage); - if (!dequeue_hwpoisoned_huge_page(hpage)) - num_poisoned_pages_add(1 << compound_order(hpage)); - } else { - if (!TestSetPageHWPoison(page)) - num_poisoned_pages_inc(); + if (!TestSetPageHWPoison(head)) { + num_poisoned_pages_inc(); + if (PageHuge(head)) + dequeue_hwpoisoned_huge_page(head); } }

From: Nanyong Sun sunnanyong@huawei.com

[ Upstream commit d612c3f3fae221e7ea736d196581c2217304bbbc ]

Reported by syzkaller: BUG: memory leak unreferenced object 0xffff888105df7000 (size 64): comm "syz-executor842", pid 360, jiffies 4294824824 (age 22.546s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000e67ed558>] kmalloc include/linux/slab.h:590 [inline] [<00000000e67ed558>] kzalloc include/linux/slab.h:720 [inline] [<00000000e67ed558>] netlbl_cipsov4_add_std net/netlabel/netlabel_cipso_v4.c:145 [inline] [<00000000e67ed558>] netlbl_cipsov4_add+0x390/0x2340 net/netlabel/netlabel_cipso_v4.c:416 [<0000000006040154>] genl_family_rcv_msg_doit.isra.0+0x20e/0x320 net/netlink/genetlink.c:739 [<00000000204d7a1c>] genl_family_rcv_msg net/netlink/genetlink.c:783 [inline] [<00000000204d7a1c>] genl_rcv_msg+0x2bf/0x4f0 net/netlink/genetlink.c:800 [<00000000c0d6a995>] netlink_rcv_skb+0x134/0x3d0 net/netlink/af_netlink.c:2504 [<00000000d78b9d2c>] genl_rcv+0x24/0x40 net/netlink/genetlink.c:811 [<000000009733081b>] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] [<000000009733081b>] netlink_unicast+0x4a0/0x6a0 net/netlink/af_netlink.c:1340 [<00000000d5fd43b8>] netlink_sendmsg+0x789/0xc70 net/netlink/af_netlink.c:1929 [<000000000a2d1e40>] sock_sendmsg_nosec net/socket.c:654 [inline] [<000000000a2d1e40>] sock_sendmsg+0x139/0x170 net/socket.c:674 [<00000000321d1969>] ____sys_sendmsg+0x658/0x7d0 net/socket.c:2350 [<00000000964e16bc>] ___sys_sendmsg+0xf8/0x170 net/socket.c:2404 [<000000001615e288>] __sys_sendmsg+0xd3/0x190 net/socket.c:2433 [<000000004ee8b6a5>] do_syscall_64+0x37/0x90 arch/x86/entry/common.c:47 [<00000000171c7cee>] entry_SYSCALL_64_after_hwframe+0x44/0xae

The memory of doi_def->map.std pointing is allocated in netlbl_cipsov4_add_std, but no place has freed it. It should be freed in cipso_v4_doi_free which frees the cipso DOI resource.

Fixes: 96cb8e3313c7a ("[NetLabel]: CIPSOv4 and Unlabeled packet integration") Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: Nanyong Sun sunnanyong@huawei.com Acked-by: Paul Moore paul@paul-moore.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/cipso_ipv4.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 71409928763b..553cda6f887a 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -486,6 +486,7 @@ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) kfree(doi_def->map.std->lvl.local); kfree(doi_def->map.std->cat.cipso); kfree(doi_def->map.std->cat.local); + kfree(doi_def->map.std); break; } kfree(doi_def);

From: Paolo Abeni pabeni@redhat.com

[ Upstream commit a8b897c7bcd47f4147d066e22cc01d1026d7640e ]

Kaustubh reported and diagnosed a panic in udp_lib_lookup(). The root cause is udp_abort() racing with close(). Both racing functions acquire the socket lock, but udp{v6}_destroy_sock() release it before performing destructive actions.

We can't easily extend the socket lock scope to avoid the race, instead use the SOCK_DEAD flag to prevent udp_abort from doing any action when the critical race happens.

Diagnosed-and-tested-by: Kaustubh Pandey kapandey@codeaurora.org Fixes: 5d77dca82839 ("net: diag: support SOCK_DESTROY for UDP sockets") Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/udp.c | 10 ++++++++++ net/ipv6/udp.c | 3 +++ 2 files changed, 13 insertions(+)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 18a1a4890c5f..79249a44e4a3 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1998,6 +1998,9 @@ void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); if (static_key_false(&udp_encap_needed) && up->encap_type) { @@ -2228,10 +2231,17 @@ int udp_abort(struct sock *sk, int err) { lock_sock(sk);

+ /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing + * with close() + */ + if (sock_flag(sk, SOCK_DEAD)) + goto out; + sk->sk_err = err; sk->sk_error_report(sk); __udp_disconnect(sk, 0);

+out: release_sock(sk);

return 0; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1ad84e18c03b..3a876a2fdd82 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1325,6 +1325,9 @@ void udpv6_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); lock_sock(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_v6_flush_pending_frames(sk); release_sock(sk);

From: Maxim Mikityanskiy maximmi@nvidia.com

[ Upstream commit 5fc177ab759418c9537433e63301096e733fb915 ]

The TCP option parser in synproxy (synproxy_parse_options) could read one byte out of bounds. When the length is 1, the execution flow gets into the loop, reads one byte of the opcode, and if the opcode is neither TCPOPT_EOL nor TCPOPT_NOP, it reads one more byte, which exceeds the length of 1.

This fix is inspired by commit 9609dad263f8 ("ipv4: tcp_input: fix stack out of bounds when parsing TCP options.").

v2 changes:

Added an early return when length < 0 to avoid calling skb_header_pointer with negative length.

Cc: Young Xiao 92siuyang@gmail.com Fixes: 48b1de4c110a ("netfilter: add SYNPROXY core/target") Signed-off-by: Maxim Mikityanskiy maximmi@nvidia.com Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_synproxy_core.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index c8a4a48bced9..8be604eb6961 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -34,6 +34,9 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, int length = (th->doff * 4) - sizeof(*th); u8 buf[40], *ptr;

+ if (unlikely(length < 0)) + return false; + ptr = skb_header_pointer(skb, doff + sizeof(*th), length, buf); if (ptr == NULL) return false; @@ -50,6 +53,8 @@ synproxy_parse_options(const struct sk_buff *skb, unsigned int doff, length--; continue; default: + if (length < 2) + return true; opsize = *ptr++; if (opsize < 2) return true;

From: Jisheng Zhang Jisheng.Zhang@synaptics.com

[ Upstream commit 1adb20f0d496b2c61e9aa1f4761b8d71f93d258e ]

The register starts from 0x800 is the 16th MAC address register rather than the first one.

Fixes: cffb13f4d6fb ("stmmac: extend mac addr reg and fix perfect filering") Signed-off-by: Jisheng Zhang Jisheng.Zhang@synaptics.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index ff3e5ab39bd0..24fb7a2bba62 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -91,10 +91,10 @@ enum power_event { #define LPI_CTRL_STATUS_TLPIEN 0x00000001 /* Transmit LPI Entry */

/* GMAC HW ADDR regs */ -#define GMAC_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \ - (reg * 8)) -#define GMAC_ADDR_LOW(reg) (((reg > 15) ? 0x00000804 : 0x00000044) + \ - (reg * 8)) +#define GMAC_ADDR_HIGH(reg) ((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \ + 0x00000040 + (reg * 8)) +#define GMAC_ADDR_LOW(reg) ((reg > 15) ? 0x00000804 + (reg - 16) * 8 : \ + 0x00000044 + (reg * 8)) #define GMAC_MAX_PERFECT_ADDRESSES 1

#define GMAC_PCS_BASE 0x000000c0 /* PCS register base */

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 49a10c7b176295f8fafb338911cf028e97f65f4d ]

If an error occurs after a 'pci_enable_pcie_error_reporting()' call, it must be undone by a corresponding 'pci_disable_pcie_error_reporting()' call, as already done in the remove function.

Fixes: e87ad5539343 ("netxen: support pci error handlers") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index a5ee3d328f3d..75e25a3fe4a7 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1617,6 +1617,8 @@ netxen_nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) free_netdev(netdev);

err_out_free_res: + if (NX_IS_REVISION_P3(pdev->revision)) + pci_disable_pcie_error_reporting(pdev); pci_release_regions(pdev);

err_out_disable_pdev:

From: Dongliang Mu mudongliangabcd@gmail.com

[ Upstream commit 56b786d86694e079d8aad9b314e015cd4ac02a3d ]

The commit 46a8b29c6306 ("net: usb: fix memory leak in smsc75xx_bind") fails to clean up the work scheduled in smsc75xx_reset-> smsc75xx_set_multicast, which leads to use-after-free if the work is scheduled to start after the deallocation. In addition, this patch also removes a dangling pointer - dev->data[0].

This patch calls cancel_work_sync to cancel the scheduled work and set the dangling pointer to NULL.

Fixes: 46a8b29c6306 ("net: usb: fix memory leak in smsc75xx_bind") Signed-off-by: Dongliang Mu mudongliangabcd@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/smsc75xx.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index 3a391ae5c4e0..841d97491592 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -1497,7 +1497,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_wait_ready(dev, 0); if (ret < 0) { netdev_warn(dev->net, "device not ready in smsc75xx_bind\n"); - goto err; + goto free_pdata; }

smsc75xx_init_mac_address(dev); @@ -1506,7 +1506,7 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) ret = smsc75xx_reset(dev); if (ret < 0) { netdev_warn(dev->net, "smsc75xx_reset error %d\n", ret); - goto err; + goto cancel_work; }

dev->net->netdev_ops = &smsc75xx_netdev_ops; @@ -1516,8 +1516,11 @@ static int smsc75xx_bind(struct usbnet *dev, struct usb_interface *intf) dev->hard_mtu = dev->net->mtu + dev->net->hard_header_len; return 0;

-err: +cancel_work: + cancel_work_sync(&pdata->set_multicast); +free_pdata: kfree(pdata); + dev->data[0] = 0; return ret; }

@@ -1528,7 +1531,6 @@ static void smsc75xx_unbind(struct usbnet *dev, struct usb_interface *intf) cancel_work_sync(&pdata->set_multicast); netif_dbg(dev, ifdown, dev->net, "free pdata\n"); kfree(pdata); - pdata = NULL; dev->data[0] = 0; } }

From: Eric Dumazet edumazet@google.com

[ Upstream commit a494bd642d9120648b06bb7d28ce6d05f55a7819 ]

While unix_may_send(sk, osk) is called while osk is locked, it appears unix_release_sock() can overwrite unix_peer() after this lock has been released, making KCSAN unhappy.

Changing unix_release_sock() to access/change unix_peer() before lock is released should fix this issue.

BUG: KCSAN: data-race in unix_dgram_sendmsg / unix_release_sock

write to 0xffff88810465a338 of 8 bytes by task 20852 on cpu 1: unix_release_sock+0x4ed/0x6e0 net/unix/af_unix.c:558 unix_release+0x2f/0x50 net/unix/af_unix.c:859 __sock_release net/socket.c:599 [inline] sock_close+0x6c/0x150 net/socket.c:1258 __fput+0x25b/0x4e0 fs/file_table.c:280 ____fput+0x11/0x20 fs/file_table.c:313 task_work_run+0xae/0x130 kernel/task_work.c:164 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:175 [inline] exit_to_user_mode_prepare+0x156/0x190 kernel/entry/common.c:209 __syscall_exit_to_user_mode_work kernel/entry/common.c:291 [inline] syscall_exit_to_user_mode+0x20/0x40 kernel/entry/common.c:302 do_syscall_64+0x56/0x90 arch/x86/entry/common.c:57 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff88810465a338 of 8 bytes by task 20888 on cpu 0: unix_may_send net/unix/af_unix.c:189 [inline] unix_dgram_sendmsg+0x923/0x1610 net/unix/af_unix.c:1712 sock_sendmsg_nosec net/socket.c:654 [inline] sock_sendmsg net/socket.c:674 [inline] ____sys_sendmsg+0x360/0x4d0 net/socket.c:2350 ___sys_sendmsg net/socket.c:2404 [inline] __sys_sendmmsg+0x315/0x4b0 net/socket.c:2490 __do_sys_sendmmsg net/socket.c:2519 [inline] __se_sys_sendmmsg net/socket.c:2516 [inline] __x64_sys_sendmmsg+0x53/0x60 net/socket.c:2516 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0xffff888167905400 -> 0x0000000000000000

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 20888 Comm: syz-executor.0 Not tainted 5.13.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/unix/af_unix.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index bcd6ed6e7e25..8bbaa35937dd 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -534,12 +534,14 @@ static void unix_release_sock(struct sock *sk, int embrion) u->path.mnt = NULL; state = sk->sk_state; sk->sk_state = TCP_CLOSE; + + skpair = unix_peer(sk); + unix_peer(sk) = NULL; + unix_state_unlock(sk);

wake_up_interruptible_all(&u->peer_wait);

- skpair = unix_peer(sk); - if (skpair != NULL) { if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) { unix_state_lock(skpair); @@ -554,7 +556,6 @@ static void unix_release_sock(struct sock *sk, int embrion)

unix_dgram_peer_wake_disconnect(sk, skpair); sock_put(skpair); /* It may now die */ - unix_peer(sk) = NULL; }

/* Try to flush out this socket. Throw out buffers at least */

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 7edcc682301492380fbdd604b4516af5ae667a13 ]

My local syzbot instance hit memory leak in mkiss_open()[1]. The problem was in missing free_netdev() in mkiss_close().

In mkiss_open() netdevice is allocated and then registered, but in mkiss_close() netdevice was only unregistered, but not freed.

Fail log:

BUG: memory leak unreferenced object 0xffff8880281ba000 (size 4096): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): 61 78 30 00 00 00 00 00 00 00 00 00 00 00 00 00 ax0............. 00 27 fa 2a 80 88 ff ff 00 00 00 00 00 00 00 00 .'.*............ backtrace: [<ffffffff81a27201>] kvmalloc_node+0x61/0xf0 [<ffffffff8706e7e8>] alloc_netdev_mqs+0x98/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

BUG: memory leak unreferenced object 0xffff8880141a9a00 (size 96): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): e8 a2 1b 28 80 88 ff ff e8 a2 1b 28 80 88 ff ff ...(.......(.... 98 92 9c aa b0 40 02 00 00 00 00 00 00 00 00 00 .....@.......... backtrace: [<ffffffff8709f68b>] __hw_addr_create_ex+0x5b/0x310 [<ffffffff8709fb38>] __hw_addr_add_ex+0x1f8/0x2b0 [<ffffffff870a0c7b>] dev_addr_init+0x10b/0x1f0 [<ffffffff8706e88b>] alloc_netdev_mqs+0x13b/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

BUG: memory leak unreferenced object 0xffff8880219bfc00 (size 512): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): 00 a0 1b 28 80 88 ff ff 80 8f b1 8d ff ff ff ff ...(............ 80 8f b1 8d ff ff ff ff 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff81a27201>] kvmalloc_node+0x61/0xf0 [<ffffffff8706eec7>] alloc_netdev_mqs+0x777/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

BUG: memory leak unreferenced object 0xffff888029b2b200 (size 256): comm "syz-executor.1", pid 11443, jiffies 4295046091 (age 17.660s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<ffffffff81a27201>] kvmalloc_node+0x61/0xf0 [<ffffffff8706f062>] alloc_netdev_mqs+0x912/0xe80 [<ffffffff84e64192>] mkiss_open+0xb2/0x6f0 [1] [<ffffffff842355db>] tty_ldisc_open+0x9b/0x110 [<ffffffff84236488>] tty_set_ldisc+0x2e8/0x670 [<ffffffff8421f7f3>] tty_ioctl+0xda3/0x1440 [<ffffffff81c9f273>] __x64_sys_ioctl+0x193/0x200 [<ffffffff8911263a>] do_syscall_64+0x3a/0xb0 [<ffffffff89200068>] entry_SYSCALL_64_after_hwframe+0x44/0xae

Fixes: 815f62bf7427 ("[PATCH] SMP rewrite of mkiss") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/hamradio/mkiss.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index 088fe5d34f50..76340bc3cf44 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -810,6 +810,7 @@ static void mkiss_close(struct tty_struct *tty) ax->tty = NULL;

unregister_netdev(ax->dev); + free_netdev(ax->dev); }

/* Perform I/O control on an active ax25 channel. */

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 9cca0c2d70149160407bda9a9446ce0c29b6e6c6 ]

static void ec_bhf_remove(struct pci_dev *dev) { ... struct ec_bhf_priv *priv = netdev_priv(net_dev);

unregister_netdev(net_dev); free_netdev(net_dev);

pci_iounmap(dev, priv->dma_io); pci_iounmap(dev, priv->io); ... }

priv is netdev private data, but it is used after free_netdev(). It can cause use-after-free when accessing priv pointer. So, fix it by moving free_netdev() after pci_iounmap() calls.

Fixes: 6af55ff52b02 ("Driver for Beckhoff CX5020 EtherCAT master module.") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/ec_bhf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index f7b42483921c..0ade0c6d81ee 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -589,10 +589,12 @@ static void ec_bhf_remove(struct pci_dev *dev) struct ec_bhf_priv *priv = netdev_priv(net_dev);

unregister_netdev(net_dev); - free_netdev(net_dev);

pci_iounmap(dev, priv->dma_io); pci_iounmap(dev, priv->io); + + free_netdev(net_dev); + pci_release_regions(dev); pci_clear_master(dev); pci_disable_device(dev);

From: Chen Li chenli@uniontech.com

[ Upstream commit ab8363d3875a83f4901eb1cc00ce8afd24de6c85 ]

I met a gpu addr bug recently and the kernel log tells me the pc is memcpy/memset and link register is radeon_uvd_resume.

As we know, in some architectures, optimized memcpy/memset may not work well on device memory. Trival memcpy_toio/memset_io can fix this problem.

BTW, amdgpu has already done it in: commit ba0b2275a678 ("drm/amdgpu: use memcpy_to/fromio for UVD fw upload"), that's why it has no this issue on the same gpu and platform.

Signed-off-by: Chen Li chenli@uniontech.com Reviewed-by: Christian König christian.koenig@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/radeon/radeon_uvd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 16239b07ce45..2610919eb709 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -286,7 +286,7 @@ int radeon_uvd_resume(struct radeon_device *rdev) if (rdev->uvd.vcpu_bo == NULL) return -EINVAL;

- memcpy(rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size); + memcpy_toio((void __iomem *)rdev->uvd.cpu_addr, rdev->uvd_fw->data, rdev->uvd_fw->size);

size = radeon_bo_size(rdev->uvd.vcpu_bo); size -= rdev->uvd_fw->size; @@ -294,7 +294,7 @@ int radeon_uvd_resume(struct radeon_device *rdev) ptr = rdev->uvd.cpu_addr; ptr += rdev->uvd_fw->size;

- memset(ptr, 0, size); + memset_io((void __iomem *)ptr, 0, size);

return 0; }

From: "Steven Rostedt (VMware)" rostedt@goodmis.org

commit 89529d8b8f8daf92d9979382b8d2eb39966846ea upstream.

The trace_clock_global() tries to make sure the events between CPUs is somewhat in order. A global value is used and updated by the latest read of a clock. If one CPU is ahead by a little, and is read by another CPU, a lock is taken, and if the timestamp of the other CPU is behind, it will simply use the other CPUs timestamp.

The lock is also only taken with a "trylock" due to tracing, and strange recursions can happen. The lock is not taken at all in NMI context.

In the case where the lock is not able to be taken, the non synced timestamp is returned. But it will not be less than the saved global timestamp.

The problem arises because when the time goes "backwards" the time returned is the saved timestamp plus 1. If the lock is not taken, and the plus one to the timestamp is returned, there's a small race that can cause the time to go backwards!

CPU0 CPU1 ---- ---- trace_clock_global() { ts = clock() [ 1000 ] trylock(clock_lock) [ success ] global_ts = ts; [ 1000 ]

<interrupted by NMI> trace_clock_global() { ts = clock() [ 999 ] if (ts < global_ts) ts = global_ts + 1 [ 1001 ]

trylock(clock_lock) [ fail ]

return ts [ 1001] } unlock(clock_lock); return ts; [ 1000 ] }

trace_clock_global() { ts = clock() [ 1000 ] if (ts < global_ts) [ false 1000 == 1000 ]

trylock(clock_lock) [ success ] global_ts = ts; [ 1000 ] unlock(clock_lock)

return ts; [ 1000 ] }

The above case shows to reads of trace_clock_global() on the same CPU, but the second read returns one less than the first read. That is, time when backwards, and this is not what is allowed by trace_clock_global().

This was triggered by heavy tracing and the ring buffer checker that tests for the clock going backwards:

Ring buffer clock went backwards: 20613921464 -> 20613921463 ------------[ cut here ]------------ WARNING: CPU: 2 PID: 0 at kernel/trace/ring_buffer.c:3412 check_buffer+0x1b9/0x1c0 Modules linked in: [..] [CPU: 2]TIME DOES NOT MATCH expected:20620711698 actual:20620711697 delta:6790234 before:20613921463 after:20613921463 [20613915818] PAGE TIME STAMP [20613915818] delta:0 [20613915819] delta:1 [20613916035] delta:216 [20613916465] delta:430 [20613916575] delta:110 [20613916749] delta:174 [20613917248] delta:499 [20613917333] delta:85 [20613917775] delta:442 [20613917921] delta:146 [20613918321] delta:400 [20613918568] delta:247 [20613918768] delta:200 [20613919306] delta:538 [20613919353] delta:47 [20613919980] delta:627 [20613920296] delta:316 [20613920571] delta:275 [20613920862] delta:291 [20613921152] delta:290 [20613921464] delta:312 [20613921464] delta:0 TIME EXTEND [20613921464] delta:0

This happened more than once, and always for an off by one result. It also started happening after commit aafe104aa9096 was added.

Cc: stable@vger.kernel.org Fixes: aafe104aa9096 ("tracing: Restructure trace_clock_global() to never block") Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_clock.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c index b67ea5eed2a8..b70233a9563f 100644 --- a/kernel/trace/trace_clock.c +++ b/kernel/trace/trace_clock.c @@ -113,9 +113,9 @@ u64 notrace trace_clock_global(void) prev_time = READ_ONCE(trace_clock_struct.prev_time); now = sched_clock_cpu(this_cpu);

- /* Make sure that now is always greater than prev_time */ + /* Make sure that now is always greater than or equal to prev_time */ if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time;

/* * If in an NMI context then dont risk lockups and simply return @@ -129,7 +129,7 @@ u64 notrace trace_clock_global(void) /* Reread prev_time in case it was already updated */ prev_time = READ_ONCE(trace_clock_struct.prev_time); if ((s64)(now - prev_time) < 0) - now = prev_time + 1; + now = prev_time;

trace_clock_struct.prev_time = now;

From: Shanker Donthineni sdonthineni@nvidia.com

commit 4c207e7121fa92b66bf1896bf8ccb9edfb0f9731 upstream.

Some NVIDIA GPU devices do not work with SBR. Triggering SBR leaves the device inoperable for the current system boot. It requires a system hard-reboot to get the GPU device back to normal operating condition post-SBR. For the affected devices, enable NO_BUS_RESET quirk to avoid the issue.

This issue will be fixed in the next generation of hardware.

Link: https://lore.kernel.org/r/20210608054857.18963-8-ameynarkhede03@gmail.com Signed-off-by: Shanker Donthineni sdonthineni@nvidia.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: Sinan Kaya okaya@kernel.org Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/pci/quirks.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 77874187f5b3..096ba11ac105 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3345,6 +3345,18 @@ static void quirk_no_bus_reset(struct pci_dev *dev) dev->dev_flags |= PCI_DEV_FLAGS_NO_BUS_RESET; }

+/* + * Some NVIDIA GPU devices do not work with bus reset, SBR needs to be + * prevented for those affected devices. + */ +static void quirk_nvidia_no_bus_reset(struct pci_dev *dev) +{ + if ((dev->device & 0xffc0) == 0x2340) + quirk_no_bus_reset(dev); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, + quirk_nvidia_no_bus_reset); + /* * Some Atheros AR9xxx and QCA988x chips do not behave after a bus reset. * The device will throw a Link Down error on AER-capable systems and

From: Bumyong Lee bumyong.lee@samsung.com

commit 4ad5dd2d7876d79507a20f026507d1a93b8fff10 upstream.

flags varible which is the input parameter of pl330_prep_dma_cyclic() should not be used by spinlock_irq[save/restore] function.

Signed-off-by: Jongho Park jongho7.park@samsung.com Signed-off-by: Bumyong Lee bumyong.lee@samsung.com Signed-off-by: Chanho Park chanho61.park@samsung.com Link: https://lore.kernel.org/r/20210507063647.111209-1-chanho61.park@samsung.com Fixes: f6f2421c0a1c ("dmaengine: pl330: Merge dma_pl330_dmac and pl330_dmac structs") Cc: stable@vger.kernel.org Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/dma/pl330.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c index f5a9bb123188..d8997dafb876 100644 --- a/drivers/dma/pl330.c +++ b/drivers/dma/pl330.c @@ -2579,13 +2579,15 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic( for (i = 0; i < len / period_len; i++) { desc = pl330_get_desc(pch); if (!desc) { + unsigned long iflags; + dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n", __func__, __LINE__);

if (!first) return NULL;

- spin_lock_irqsave(&pl330->pool_lock, flags); + spin_lock_irqsave(&pl330->pool_lock, iflags);

while (!list_empty(&first->node)) { desc = list_entry(first->node.next, @@ -2595,7 +2597,7 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(

list_move_tail(&first->node, &pl330->desc_pool);

- spin_unlock_irqrestore(&pl330->pool_lock, flags); + spin_unlock_irqrestore(&pl330->pool_lock, iflags);

return NULL; }

From: Tetsuo Handa penguin-kernel@i-love.sakura.ne.jp

commit 8d0caedb759683041d9db82069937525999ada53 upstream.

syzbot is reporting hung task at register_netdevice_notifier() [1] and unregister_netdevice_notifier() [2], for cleanup_net() might perform time consuming operations while CAN driver's raw/bcm/isotp modules are calling {register,unregister}_netdevice_notifier() on each socket.

Change raw/bcm/isotp modules to call register_netdevice_notifier() from module's __init function and call unregister_netdevice_notifier() from module's __exit function, as with gw/j1939 modules are doing.

Link: https://syzkaller.appspot.com/bug?id=391b9498827788b3cc6830226d4ff5be87107c3... [1] Link: https://syzkaller.appspot.com/bug?id=1724d278c83ca6e6df100a2e320c10d991cf2bc... [2] Link: https://lore.kernel.org/r/54a5f451-05ed-f977-8534-79e7aa2bcc8f@i-love.sakura... Cc: linux-stable stable@vger.kernel.org Reported-by: syzbot syzbot+355f8edb2ff45d5f95fa@syzkaller.appspotmail.com Reported-by: syzbot syzbot+0f1827363a305f74996f@syzkaller.appspotmail.com Reviewed-by: Kirill Tkhai ktkhai@virtuozzo.com Tested-by: syzbot syzbot+355f8edb2ff45d5f95fa@syzkaller.appspotmail.com Tested-by: Oliver Hartkopp socketcan@hartkopp.net Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/can/bcm.c | 61 +++++++++++++++++++++++++++++++++++++++----------- net/can/raw.c | 62 +++++++++++++++++++++++++++++++++++++++------------ 2 files changed, 96 insertions(+), 27 deletions(-)

diff --git a/net/can/bcm.c b/net/can/bcm.c index 077606585ed9..65fa0ac2fb47 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -127,7 +127,7 @@ struct bcm_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; struct list_head rx_ops; struct list_head tx_ops; unsigned long dropped_usr_msgs; @@ -135,6 +135,10 @@ struct bcm_sock { char procname [32]; /* inode number in decimal with \0 */ };

+static LIST_HEAD(bcm_notifier_list); +static DEFINE_SPINLOCK(bcm_notifier_lock); +static struct bcm_sock *bcm_busy_notifier; + static inline struct bcm_sock *bcm_sk(const struct sock *sk) { return (struct bcm_sock *)sk; @@ -1439,20 +1443,15 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* * notification handler for netdevice status changes */ -static int bcm_notifier(struct notifier_block *nb, unsigned long msg, - void *ptr) +static void bcm_notify(struct bcm_sock *bo, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct bcm_sock *bo = container_of(nb, struct bcm_sock, notifier); struct sock *sk = &bo->sk; struct bcm_op *op; int notify_enodev = 0;

if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return;

switch (msg) {

@@ -1487,7 +1486,28 @@ static int bcm_notifier(struct notifier_block *nb, unsigned long msg, sk->sk_error_report(sk); } } +}

+static int bcm_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(bcm_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE; + + spin_lock(&bcm_notifier_lock); + list_for_each_entry(bcm_busy_notifier, &bcm_notifier_list, notifier) { + spin_unlock(&bcm_notifier_lock); + bcm_notify(bcm_busy_notifier, msg, dev); + spin_lock(&bcm_notifier_lock); + } + bcm_busy_notifier = NULL; + spin_unlock(&bcm_notifier_lock); return NOTIFY_DONE; }

@@ -1507,9 +1527,9 @@ static int bcm_init(struct sock *sk) INIT_LIST_HEAD(&bo->rx_ops);

/* set notifier */ - bo->notifier.notifier_call = bcm_notifier; - - register_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + list_add_tail(&bo->notifier, &bcm_notifier_list); + spin_unlock(&bcm_notifier_lock);

return 0; } @@ -1530,7 +1550,14 @@ static int bcm_release(struct socket *sock)

/* remove bcm_ops, timer, rx_unregister(), etc. */

- unregister_netdevice_notifier(&bo->notifier); + spin_lock(&bcm_notifier_lock); + while (bcm_busy_notifier == bo) { + spin_unlock(&bcm_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&bcm_notifier_lock); + } + list_del(&bo->notifier); + spin_unlock(&bcm_notifier_lock);

lock_sock(sk);

@@ -1716,6 +1743,10 @@ static const struct can_proto bcm_can_proto = { .prot = &bcm_proto, };

+static struct notifier_block canbcm_notifier = { + .notifier_call = bcm_notifier +}; + static int __init bcm_module_init(void) { int err; @@ -1730,6 +1761,8 @@ static int __init bcm_module_init(void)

/* create /proc/net/can-bcm directory */ proc_dir = proc_mkdir("can-bcm", init_net.proc_net); + register_netdevice_notifier(&canbcm_notifier); + return 0; }

@@ -1739,6 +1772,8 @@ static void __exit bcm_module_exit(void)

if (proc_dir) remove_proc_entry("can-bcm", init_net.proc_net); + + unregister_netdevice_notifier(&canbcm_notifier); }

module_init(bcm_module_init); diff --git a/net/can/raw.c b/net/can/raw.c index 6dc546a06673..2bb50b1535c2 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,7 +84,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; - struct notifier_block notifier; + struct list_head notifier; int loopback; int recv_own_msgs; int fd_frames; @@ -96,6 +96,10 @@ struct raw_sock { struct uniqframe __percpu *uniq; };

+static LIST_HEAD(raw_notifier_list); +static DEFINE_SPINLOCK(raw_notifier_lock); +static struct raw_sock *raw_busy_notifier; + /* * Return pointer to store the extra msg flags for raw_recvmsg(). * We use the space of one unsigned int beyond the 'struct sockaddr_can' @@ -260,21 +264,16 @@ static int raw_enable_allfilters(struct net_device *dev, struct sock *sk) return err; }

-static int raw_notifier(struct notifier_block *nb, - unsigned long msg, void *ptr) +static void raw_notify(struct raw_sock *ro, unsigned long msg, + struct net_device *dev) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); - struct raw_sock *ro = container_of(nb, struct raw_sock, notifier); struct sock *sk = &ro->sk;

if (!net_eq(dev_net(dev), &init_net)) - return NOTIFY_DONE; - - if (dev->type != ARPHRD_CAN) - return NOTIFY_DONE; + return;

if (ro->ifindex != dev->ifindex) - return NOTIFY_DONE; + return;

switch (msg) {

@@ -303,7 +302,28 @@ static int raw_notifier(struct notifier_block *nb, sk->sk_error_report(sk); break; } +} + +static int raw_notifier(struct notifier_block *nb, unsigned long msg, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (dev->type != ARPHRD_CAN) + return NOTIFY_DONE; + if (msg != NETDEV_UNREGISTER && msg != NETDEV_DOWN) + return NOTIFY_DONE; + if (unlikely(raw_busy_notifier)) /* Check for reentrant bug. */ + return NOTIFY_DONE;

+ spin_lock(&raw_notifier_lock); + list_for_each_entry(raw_busy_notifier, &raw_notifier_list, notifier) { + spin_unlock(&raw_notifier_lock); + raw_notify(raw_busy_notifier, msg, dev); + spin_lock(&raw_notifier_lock); + } + raw_busy_notifier = NULL; + spin_unlock(&raw_notifier_lock); return NOTIFY_DONE; }

@@ -332,9 +352,9 @@ static int raw_init(struct sock *sk) return -ENOMEM;

/* set notifier */ - ro->notifier.notifier_call = raw_notifier; - - register_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + list_add_tail(&ro->notifier, &raw_notifier_list); + spin_unlock(&raw_notifier_lock);

return 0; } @@ -349,7 +369,14 @@ static int raw_release(struct socket *sock)

ro = raw_sk(sk);

- unregister_netdevice_notifier(&ro->notifier); + spin_lock(&raw_notifier_lock); + while (raw_busy_notifier == ro) { + spin_unlock(&raw_notifier_lock); + schedule_timeout_uninterruptible(1); + spin_lock(&raw_notifier_lock); + } + list_del(&ro->notifier); + spin_unlock(&raw_notifier_lock);

lock_sock(sk);

@@ -857,6 +884,10 @@ static const struct can_proto raw_can_proto = { .prot = &raw_proto, };

+static struct notifier_block canraw_notifier = { + .notifier_call = raw_notifier +}; + static __init int raw_module_init(void) { int err; @@ -866,6 +897,8 @@ static __init int raw_module_init(void) err = can_proto_register(&raw_can_proto); if (err < 0) printk(KERN_ERR "can: registration of raw protocol failed\n"); + else + register_netdevice_notifier(&canraw_notifier);

return err; } @@ -873,6 +906,7 @@ static __init int raw_module_init(void) static __exit void raw_module_exit(void) { can_proto_unregister(&raw_can_proto); + unregister_netdevice_notifier(&canraw_notifier); }

module_init(raw_module_init);

From: "Steven Rostedt (VMware)" rostedt@goodmis.org

commit 85550c83da421fb12dc1816c45012e1e638d2b38 upstream.

The saved_cmdlines is used to map pids to the task name, such that the output of the tracing does not just show pids, but also gives a human readable name for the task.

If the name is not mapped, the output looks like this:

<...>-1316 [005] ...2 132.044039: ...

Instead of this:

gnome-shell-1316 [005] ...2 132.044039: ...

The names are updated when tracing is running, but are skipped if tracing is stopped. Unfortunately, this stops the recording of the names if the top level tracer is stopped, and not if there's other tracers active.

The recording of a name only happens when a new event is written into a ring buffer, so there is no need to test if tracing is on or not. If tracing is off, then no event is written and no need to test if tracing is off or not.

Remove the check, as it hides the names of tasks for events in the instance buffers.

Cc: stable@vger.kernel.org Fixes: 7ffbd48d5cab2 ("tracing: Cache comms only after an event occurred") Signed-off-by: Steven Rostedt (VMware) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace.c | 3 --- 1 file changed, 3 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index cdf614943aa3..74ec372a3286 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1882,9 +1882,6 @@ void trace_find_cmdline(int pid, char comm[])

void tracing_record_cmdline(struct task_struct *tsk) { - if (atomic_read(&trace_record_cmdline_disabled) || !tracing_is_on()) - return; - if (!__this_cpu_read(trace_cmdline_save)) return;

From: Thomas Gleixner tglx@linutronix.de

commit efa165504943f2128d50f63de0c02faf6dcceb0d upstream.

If access_ok() or fpregs_soft_set() fails in __fpu__restore_sig() then the function just returns but does not clear the FPU state as it does for all other fatal failures.

Clear the FPU state for these failures as well.

Fixes: 72a671ced66d ("x86, fpu: Unify signal handling code paths for x86 and x86_64 kernels") Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/87mtryyhhz.ffs@nanos.tec.linutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/fpu/signal.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 769831d9fd11..07b0ebd49576 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -276,15 +276,23 @@ static int __fpu__restore_sig(void __user *buf, void __user *buf_fx, int size) return 0; }

- if (!access_ok(VERIFY_READ, buf, size)) + if (!access_ok(VERIFY_READ, buf, size)) { + fpu__clear(fpu); return -EACCES; + }

fpu__activate_curr(fpu);

- if (!static_cpu_has(X86_FEATURE_FPU)) - return fpregs_soft_set(current, NULL, - 0, sizeof(struct user_i387_ia32_struct), - NULL, buf) != 0; + if (!static_cpu_has(X86_FEATURE_FPU)) { + int ret = fpregs_soft_set(current, NULL, 0, + sizeof(struct user_i387_ia32_struct), + NULL, buf); + + if (ret) + fpu__clear(fpu); + + return ret != 0; + }

if (use_xsave()) { struct _fpx_sw_bytes fx_sw_user;

From: Alexander Duyck alexander.h.duyck@intel.com

commit f114dca2533ca770aebebffb5ed56e5e7d1fb3fb upstream.

This change makes it so that we are much more robust about defining what we can and cannot offload. Previously we were just checking for the L4 tunnel header length, however there are other fields we should be verifying as there are multiple scenarios in which we cannot perform hardware offloads.

In addition the device only supports GSO as long as the MSS is 64 or greater. We were not checking this so an MSS less than that was resulting in Tx hangs.

Change-ID: I5e2fd5f3075c73601b4b36327b771c64fcb6c31b Signed-off-by: Alexander Duyck alexander.h.duyck@intel.com Tested-by: Andrew Bowers andrewx.bowers@intel.com Cc: Philipp Hahn hahn@univention.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/i40e/i40e_main.c | 52 +++++++++++++++++---- 1 file changed, 44 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 40644657b1b7..0b1ee353f415 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9059,10 +9059,6 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, 0, 0, nlflags, filter_mask, NULL); }

-/* Hardware supports L4 tunnel length of 128B (=2^7) which includes - * inner mac plus all inner ethertypes. - */ -#define I40E_MAX_TUNNEL_HDR_LEN 128 /** * i40e_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff @@ -9073,12 +9069,52 @@ static netdev_features_t i40e_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { - if (skb->encapsulation && - ((skb_inner_network_header(skb) - skb_transport_header(skb)) > - I40E_MAX_TUNNEL_HDR_LEN)) - return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + size_t len; + + /* No point in doing any of this if neither checksum nor GSO are + * being requested for this frame. We can rule out both by just + * checking for CHECKSUM_PARTIAL + */ + if (skb->ip_summed != CHECKSUM_PARTIAL) + return features; + + /* We cannot support GSO if the MSS is going to be less than + * 64 bytes. If it is then we need to drop support for GSO. + */ + if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64)) + features &= ~NETIF_F_GSO_MASK; + + /* MACLEN can support at most 63 words */ + len = skb_network_header(skb) - skb->data; + if (len & ~(63 * 2)) + goto out_err; + + /* IPLEN and EIPLEN can support at most 127 dwords */ + len = skb_transport_header(skb) - skb_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + + if (skb->encapsulation) { + /* L4TUNLEN can support 127 words */ + len = skb_inner_network_header(skb) - skb_transport_header(skb); + if (len & ~(127 * 2)) + goto out_err; + + /* IPLEN can support at most 127 dwords */ + len = skb_inner_transport_header(skb) - + skb_inner_network_header(skb); + if (len & ~(127 * 4)) + goto out_err; + } + + /* No need to validate L4LEN as TCP is the only protocol with a + * a flexible value and we support all possible values supported + * by TCP, which is at most 15 dwords + */

return features; +out_err: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); }

static const struct net_device_ops i40e_netdev_ops = {

From: Nathan Chancellor nathan@kernel.org

commit 885480b084696331bea61a4f7eba10652999a9c1 upstream.

Currently, -Wunused-but-set-variable is only supported by GCC so it is disabled unconditionally in a GCC only block (it is enabled with W=1). clang currently has its implementation for this warning in review so preemptively move this statement out of the GCC only block and wrap it with cc-disable-warning so that both compilers function the same.

Cc: stable@vger.kernel.org Link: https://reviews.llvm.org/D100581 Signed-off-by: Nathan Chancellor nathan@kernel.org Reviewed-by: Nick Desaulniers ndesaulniers@google.com Tested-by: Nick Desaulniers ndesaulniers@google.com Signed-off-by: Masahiro Yamada masahiroy@kernel.org [nc: Backport, workaround lack of e2079e93f562 in older branches] Signed-off-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Makefile | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/Makefile b/Makefile index e43823c3337f..651d4fbf56aa 100644 --- a/Makefile +++ b/Makefile @@ -718,12 +718,11 @@ KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare) # See modpost pattern 2 KBUILD_CFLAGS += $(call cc-option, -mno-global-merge,) KBUILD_CFLAGS += $(call cc-option, -fcatch-undefined-behavior) -else +endif

# These warnings generated too much noise in a regular build. # Use make W=1 to enable them (see scripts/Makefile.extrawarn) KBUILD_CFLAGS += $(call cc-disable-warning, unused-but-set-variable) -endif

KBUILD_CFLAGS += $(call cc-disable-warning, unused-const-variable) ifdef CONFIG_FRAME_POINTER

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

[ Upstream commit 4d6035f9bf4ea12776322746a216e856dfe46698 ]

Revert commit 4514d991d992 ("PCI: PM: Do not read power state in pci_enable_device_flags()") that is reported to cause PCI device initialization issues on some systems.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=213481 Link: https://lore.kernel.org/linux-acpi/YNDoGICcg0V8HhpQ@eldamar.lan Reported-by: Michael phyre@rogers.com Reported-by: Salvatore Bonaccorso carnil@debian.org Fixes: 4514d991d992 ("PCI: PM: Do not read power state in pci_enable_device_flags()") Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/pci.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index acd89fa9820c..e09653c73ab4 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1378,11 +1378,21 @@ static int pci_enable_device_flags(struct pci_dev *dev, unsigned long flags) int err; int i, bars = 0;

- if (atomic_inc_return(&dev->enable_cnt) > 1) { - pci_update_current_state(dev, dev->current_state); - return 0; /* already enabled */ + /* + * Power state could be unknown at this point, either due to a fresh + * boot or a device removal call. So get the current power state + * so that things like MSI message writing will behave as expected + * (e.g. if the device really is in D0 at enable time). + */ + if (dev->pm_cap) { + u16 pmcsr; + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); + dev->current_state = (pmcsr & PCI_PM_CTRL_STATE_MASK); }

+ if (atomic_inc_return(&dev->enable_cnt) > 1) + return 0; /* already enabled */ + bridge = pci_upstream_bridge(dev); if (bridge) pci_enable_bridge(bridge);

From: Du Cheng ducheng2@gmail.com

[ Upstream commit a64b6a25dd9f984ed05fade603a00e2eae787d2f ]

If the userland switches back-and-forth between NL80211_IFTYPE_OCB and NL80211_IFTYPE_ADHOC via send_msg(NL80211_CMD_SET_INTERFACE), there is a chance where the cleanup cfg80211_leave_ocb() is not called. This leads to initialization of in-use memory (e.g. init u.ibss while in-use by u.ocb) due to a shared struct/union within ieee80211_sub_if_data:

struct ieee80211_sub_if_data { ... union { struct ieee80211_if_ap ap; struct ieee80211_if_vlan vlan; struct ieee80211_if_managed mgd; struct ieee80211_if_ibss ibss; // <- shares address struct ieee80211_if_mesh mesh; struct ieee80211_if_ocb ocb; // <- shares address struct ieee80211_if_mntr mntr; struct ieee80211_if_nan nan; } u; ... }

Therefore add handling of otype == NL80211_IFTYPE_OCB, during cfg80211_change_iface() to perform cleanup when leaving OCB mode.

link to syzkaller bug: https://syzkaller.appspot.com/bug?id=0612dbfa595bf4b9b680ff7b4948257b8e3732d...

Reported-by: syzbot+105896fac213f26056f9@syzkaller.appspotmail.com Signed-off-by: Du Cheng ducheng2@gmail.com Link: https://lore.kernel.org/r/20210428063941.105161-1-ducheng2@gmail.com Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/util.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/net/wireless/util.c b/net/wireless/util.c index 939320571d71..a16e805c4857 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1050,6 +1050,9 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev, case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; + case NL80211_IFTYPE_OCB: + cfg80211_leave_ocb(rdev, dev); + break; default: break; }

From: Zheng Yongjun zhengyongjun3@huawei.com

[ Upstream commit 9d44fa3e50cc91691896934d106c86e4027e61ca ]

Function 'ping_queue_rcv_skb' not always return success, which will also return fail. If not check the wrong return value of it, lead to function `ping_rcv` return success.

Signed-off-by: Zheng Yongjun zhengyongjun3@huawei.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/ping.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 4fda9abf38ee..dd4e46af1e53 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -976,6 +976,7 @@ bool ping_rcv(struct sk_buff *skb) struct sock *sk; struct net *net = dev_net(skb->dev); struct icmphdr *icmph = icmp_hdr(skb); + bool rc = false;

/* We assume the packet has already been checked by icmp_rcv */

@@ -990,14 +991,15 @@ bool ping_rcv(struct sk_buff *skb) struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);

pr_debug("rcv on socket %p\n", sk); - if (skb2) - ping_queue_rcv_skb(sk, skb2); + if (skb2 && !ping_queue_rcv_skb(sk, skb2)) + rc = true; sock_put(sk); - return true; } - pr_debug("no socket, dropping\n");

- return false; + if (!rc) + pr_debug("no socket, dropping\n"); + + return rc; } EXPORT_SYMBOL_GPL(ping_rcv);

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 58af3d3d54e87bfc1f936e16c04ade3369d34011 ]

Syzbot reported memory leak in tty_init_dev(). The problem was in unputted tty in ldisc_open()

static int ldisc_open(struct tty_struct *tty) { ... ser->tty = tty_kref_get(tty); ... result = register_netdevice(dev); if (result) { rtnl_unlock(); free_netdev(dev); return -ENODEV; } ... }

Ser pointer is netdev private_data, so after free_netdev() this pointer goes away with unputted tty reference. So, fix it by adding tty_kref_put() before freeing netdev.

Reported-and-tested-by: syzbot+f303e045423e617d2cad@syzkaller.appspotmail.com Signed-off-by: Pavel Skripkin paskripkin@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/caif/caif_serial.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index 32834dad0b83..1243c2e5a86a 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -362,6 +362,7 @@ static int ldisc_open(struct tty_struct *tty) rtnl_lock(); result = register_netdevice(dev); if (result) { + tty_kref_put(tty); rtnl_unlock(); free_netdev(dev); return -ENODEV;

From: Eric Dumazet edumazet@google.com

[ Upstream commit e032f7c9c7cefffcfb79b9fc16c53011d2d9d11f ]

Like prior patch, we need to annotate lockless accesses to po->ifindex For instance, packet_getname() is reading po->ifindex (twice) while another thread is able to change po->ifindex.

KCSAN reported:

BUG: KCSAN: data-race in packet_do_bind / packet_getname

write to 0xffff888143ce3cbc of 4 bytes by task 25573 on cpu 1: packet_do_bind+0x420/0x7e0 net/packet/af_packet.c:3191 packet_bind+0xc3/0xd0 net/packet/af_packet.c:3255 __sys_bind+0x200/0x290 net/socket.c:1637 __do_sys_bind net/socket.c:1648 [inline] __se_sys_bind net/socket.c:1646 [inline] __x64_sys_bind+0x3d/0x50 net/socket.c:1646 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff888143ce3cbc of 4 bytes by task 25578 on cpu 0: packet_getname+0x5b/0x1a0 net/packet/af_packet.c:3525 __sys_getsockname+0x10e/0x1a0 net/socket.c:1887 __do_sys_getsockname net/socket.c:1902 [inline] __se_sys_getsockname net/socket.c:1899 [inline] __x64_sys_getsockname+0x3e/0x50 net/socket.c:1899 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x00000000 -> 0x00000001

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 25578 Comm: syz-executor.5 Not tainted 5.13.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/packet/af_packet.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5f9007e7c28d..370d0a4af1f9 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3173,11 +3173,11 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, if (unlikely(unlisted)) { dev_put(dev); po->prot_hook.dev = NULL; - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { po->prot_hook.dev = dev; - po->ifindex = dev ? dev->ifindex : 0; + WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } } @@ -3492,7 +3492,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), pkt_sk(sk)->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); @@ -3508,16 +3508,18 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); + int ifindex;

if (peer) return -EOPNOTSUPP;

+ ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; - sll->sll_ifindex = po->ifindex; + sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); - dev = dev_get_by_index_rcu(sock_net(sk), po->ifindex); + dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -4097,7 +4099,7 @@ static int packet_notifier(struct notifier_block *this, } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); - po->ifindex = -1; + WRITE_ONCE(po->ifindex, -1); if (po->prot_hook.dev) dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; @@ -4603,7 +4605,7 @@ static int packet_seq_show(struct seq_file *seq, void *v) atomic_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), - po->ifindex, + READ_ONCE(po->ifindex), po->running, atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)),

From: Kees Cook keescook@chromium.org

[ Upstream commit 224004fbb033600715dbd626bceec10bfd9c58bc ]

In preparation for FORTIFY_SOURCE performing compile-time and run-time field bounds checking for memcpy(), memmove(), and memset(), avoid intentionally reading across neighboring array fields.

The memcpy() is copying the entire structure, not just the first array. Adjust the source argument so the compiler can do appropriate bounds checking.

Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/renesas/sh_eth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 0e5b1935af50..468f02beccee 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2117,7 +2117,7 @@ static void sh_eth_get_strings(struct net_device *ndev, u32 stringset, u8 *data) { switch (stringset) { case ETH_SS_STATS: - memcpy(data, *sh_eth_gstrings_stats, + memcpy(data, sh_eth_gstrings_stats, sizeof(sh_eth_gstrings_stats)); break; }

From: Kees Cook keescook@chromium.org

[ Upstream commit 1c200f832e14420fa770193f9871f4ce2df00d07 ]

The source (&dcbx_info->operational.params) and dest (&p_hwfn->p_dcbx_info->set.config.params) are both struct qed_dcbx_params (560 bytes), not struct qed_dcbx_admin_params (564 bytes), which is used as the memcpy() size.

However it seems that struct qed_dcbx_operational_params (dcbx_info->operational)'s layout matches struct qed_dcbx_admin_params (p_hwfn->p_dcbx_info->set.config)'s 4 byte difference (3 padding, 1 byte for "valid").

On the assumption that the size is wrong (rather than the source structure type), adjust the memcpy() size argument to be 4 bytes smaller and add a BUILD_BUG_ON() to validate any changes to the structure sizes.

Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 7b6824e560d2..59e59878a3a7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -1205,9 +1205,11 @@ int qed_dcbx_get_config_params(struct qed_hwfn *p_hwfn, p_hwfn->p_dcbx_info->set.ver_num |= DCBX_CONFIG_VERSION_IEEE;

p_hwfn->p_dcbx_info->set.enabled = dcbx_info->operational.enabled; + BUILD_BUG_ON(sizeof(dcbx_info->operational.params) != + sizeof(p_hwfn->p_dcbx_info->set.config.params)); memcpy(&p_hwfn->p_dcbx_info->set.config.params, &dcbx_info->operational.params, - sizeof(struct qed_dcbx_admin_params)); + sizeof(p_hwfn->p_dcbx_info->set.config.params)); p_hwfn->p_dcbx_info->set.config.valid = true;

memcpy(params, &p_hwfn->p_dcbx_info->set, sizeof(struct qed_dcbx_set));

From: Pavel Skripkin paskripkin@gmail.com

[ Upstream commit 8fd0c1b0647a6bda4067ee0cd61e8395954b6f28 ]

My local syzbot instance hit memory leak in nilfs2. The problem was in missing kobject_put() in nilfs_sysfs_delete_device_group().

kobject_del() does not call kobject_cleanup() for passed kobject and it leads to leaking duped kobject name if kobject_put() was not called.

Fail log:

BUG: memory leak unreferenced object 0xffff8880596171e0 (size 8): comm "syz-executor379", pid 8381, jiffies 4294980258 (age 21.100s) hex dump (first 8 bytes): 6c 6f 6f 70 30 00 00 00 loop0... backtrace: kstrdup+0x36/0x70 mm/util.c:60 kstrdup_const+0x53/0x80 mm/util.c:83 kvasprintf_const+0x108/0x190 lib/kasprintf.c:48 kobject_set_name_vargs+0x56/0x150 lib/kobject.c:289 kobject_add_varg lib/kobject.c:384 [inline] kobject_init_and_add+0xc9/0x160 lib/kobject.c:473 nilfs_sysfs_create_device_group+0x150/0x800 fs/nilfs2/sysfs.c:999 init_nilfs+0xe26/0x12b0 fs/nilfs2/the_nilfs.c:637

Link: https://lkml.kernel.org/r/20210612140559.20022-1-paskripkin@gmail.com Fixes: da7141fb78db ("nilfs2: add /sys/fs/nilfs2/<device> group") Signed-off-by: Pavel Skripkin paskripkin@gmail.com Acked-by: Ryusuke Konishi konishi.ryusuke@gmail.com Cc: Michael L. Semon mlsemon35@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nilfs2/sysfs.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 490303e3d517..e9903bceb2bf 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1064,6 +1064,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs) nilfs_sysfs_delete_superblock_group(nilfs); nilfs_sysfs_delete_segctor_group(nilfs); kobject_del(&nilfs->ns_dev_kobj); + kobject_put(&nilfs->ns_dev_kobj); kfree(nilfs->ns_dev_subgroups); }

Signed-off-by: Sasha Levin sashal@kernel.org --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile index 651d4fbf56aa..8891b5dd49e1 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 273 -EXTRAVERSION = +SUBLEVEL = 274 +EXTRAVERSION = -rc1 NAME = Roaring Lionus

# *DOCUMENTATION*