From: Venkata Narendra Kumar Gutta vnkgutta@codeaurora.org

[ Upstream commit edb16da34b084c66763f29bee42b4e6bb33c3d66 ]

Platform core is using pdev->name as the platform device name to do the binding of the devices with the drivers. But, when the platform driver overrides the platform device name with dev_set_name(), the pdev->name is pointing to a location which is freed and becomes an invalid parameter to do the binding match.

use-after-free instance:

[ 33.325013] BUG: KASAN: use-after-free in strcmp+0x8c/0xb0 [ 33.330646] Read of size 1 at addr ffffffc10beae600 by task modprobe [ 33.339068] CPU: 5 PID: 518 Comm: modprobe Tainted: G S W O 4.19.30+ #3 [ 33.346835] Hardware name: MTP (DT) [ 33.350419] Call trace: [ 33.352941] dump_backtrace+0x0/0x3b8 [ 33.356713] show_stack+0x24/0x30 [ 33.360119] dump_stack+0x160/0x1d8 [ 33.363709] print_address_description+0x84/0x2e0 [ 33.368549] kasan_report+0x26c/0x2d0 [ 33.372322] __asan_report_load1_noabort+0x2c/0x38 [ 33.377248] strcmp+0x8c/0xb0 [ 33.380306] platform_match+0x70/0x1f8 [ 33.384168] __driver_attach+0x78/0x3a0 [ 33.388111] bus_for_each_dev+0x13c/0x1b8 [ 33.392237] driver_attach+0x4c/0x58 [ 33.395910] bus_add_driver+0x350/0x560 [ 33.399854] driver_register+0x23c/0x328 [ 33.403886] __platform_driver_register+0xd0/0xe0

So, use dev_name(&pdev->dev), which fetches the platform device name from the kobject(dev->kobj->name) of the device instead of the pdev->name.

Signed-off-by: Venkata Narendra Kumar Gutta vnkgutta@codeaurora.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/platform.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 065fcc4be263..071dd053a917 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -796,7 +796,7 @@ static ssize_t modalias_show(struct device *dev, struct device_attribute *a, if (len != -ENODEV) return len;

- len = snprintf(buf, PAGE_SIZE, "platform:%s\n", pdev->name); + len = snprintf(buf, PAGE_SIZE, "platform:%s\n", dev_name(&pdev->dev));

return (len >= PAGE_SIZE) ? (PAGE_SIZE - 1) : len; } @@ -872,7 +872,7 @@ static int platform_uevent(struct device *dev, struct kobj_uevent_env *env) return rc;

add_uevent_var(env, "MODALIAS=%s%s", PLATFORM_MODULE_PREFIX, - pdev->name); + dev_name(&pdev->dev)); return 0; }

@@ -881,7 +881,7 @@ static const struct platform_device_id *platform_match_id( struct platform_device *pdev) { while (id->name[0]) { - if (strcmp(pdev->name, id->name) == 0) { + if (strcmp(dev_name(&pdev->dev), id->name) == 0) { pdev->id_entry = id; return id; } @@ -925,7 +925,7 @@ static int platform_match(struct device *dev, struct device_driver *drv) return platform_match_id(pdrv->id_table, pdev) != NULL;

/* fall-back to driver name match */ - return (strcmp(pdev->name, drv->name) == 0); + return (strcmp(dev_name(&pdev->dev), drv->name) == 0); }

#ifdef CONFIG_PM_SLEEP

From: Li Rongqing lirongqing@baidu.com

[ Upstream commit d6a2946a88f524a47cc9b79279667137899db807 ]

msgctl10 of ltp triggers the following lockup When CONFIG_KASAN is enabled on large memory SMP systems, the pages initialization can take a long time, if msgctl10 requests a huge block memory, and it will block rcu scheduler, so release cpu actively.

After adding schedule() in free_msg, free_msg can not be called when holding spinlock, so adding msg to a tmp list, and free it out of spinlock

rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: rcu: Tasks blocked on level-1 rcu_node (CPUs 16-31): P32505 rcu: Tasks blocked on level-1 rcu_node (CPUs 48-63): P34978 rcu: (detected by 11, t=35024 jiffies, g=44237529, q=16542267) msgctl10 R running task 21608 32505 2794 0x00000082 Call Trace: preempt_schedule_irq+0x4c/0xb0 retint_kernel+0x1b/0x2d RIP: 0010:__is_insn_slot_addr+0xfb/0x250 Code: 82 1d 00 48 8b 9b 90 00 00 00 4c 89 f7 49 c1 ee 03 e8 59 83 1d 00 48 b8 00 00 00 00 00 fc ff df 4c 39 eb 48 89 9d 58 ff ff ff <41> c6 04 06 f8 74 66 4c 8d 75 98 4c 89 f1 48 c1 e9 03 48 01 c8 48 RSP: 0018:ffff88bce041f758 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: dffffc0000000000 RBX: ffffffff8471bc50 RCX: ffffffff828a2a57 RDX: dffffc0000000000 RSI: dffffc0000000000 RDI: ffff88bce041f780 RBP: ffff88bce041f828 R08: ffffed15f3f4c5b3 R09: ffffed15f3f4c5b3 R10: 0000000000000001 R11: ffffed15f3f4c5b2 R12: 000000318aee9b73 R13: ffffffff8471bc50 R14: 1ffff1179c083ef0 R15: 1ffff1179c083eec kernel_text_address+0xc1/0x100 __kernel_text_address+0xe/0x30 unwind_get_return_address+0x2f/0x50 __save_stack_trace+0x92/0x100 create_object+0x380/0x650 __kmalloc+0x14c/0x2b0 load_msg+0x38/0x1a0 do_msgsnd+0x19e/0xcf0 do_syscall_64+0x117/0x400 entry_SYSCALL_64_after_hwframe+0x49/0xbe

rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: rcu: Tasks blocked on level-1 rcu_node (CPUs 0-15): P32170 rcu: (detected by 14, t=35016 jiffies, g=44237525, q=12423063) msgctl10 R running task 21608 32170 32155 0x00000082 Call Trace: preempt_schedule_irq+0x4c/0xb0 retint_kernel+0x1b/0x2d RIP: 0010:lock_acquire+0x4d/0x340 Code: 48 81 ec c0 00 00 00 45 89 c6 4d 89 cf 48 8d 6c 24 20 48 89 3c 24 48 8d bb e4 0c 00 00 89 74 24 0c 48 c7 44 24 20 b3 8a b5 41 <48> c1 ed 03 48 c7 44 24 28 b4 25 18 84 48 c7 44 24 30 d0 54 7a 82 RSP: 0018:ffff88af83417738 EFLAGS: 00000282 ORIG_RAX: ffffffffffffff13 RAX: dffffc0000000000 RBX: ffff88bd335f3080 RCX: 0000000000000002 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff88bd335f3d64 RBP: ffff88af83417758 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000001 R11: ffffed13f3f745b2 R12: 0000000000000000 R13: 0000000000000002 R14: 0000000000000000 R15: 0000000000000000 is_bpf_text_address+0x32/0xe0 kernel_text_address+0xec/0x100 __kernel_text_address+0xe/0x30 unwind_get_return_address+0x2f/0x50 __save_stack_trace+0x92/0x100 save_stack+0x32/0xb0 __kasan_slab_free+0x130/0x180 kfree+0xfa/0x2d0 free_msg+0x24/0x50 do_msgrcv+0x508/0xe60 do_syscall_64+0x117/0x400 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Davidlohr said: "So after releasing the lock, the msg rbtree/list is empty and new calls will not see those in the newly populated tmp_msg list, and therefore they cannot access the delayed msg freeing pointers, which is good. Also the fact that the node_cache is now freed before the actual messages seems to be harmless as this is wanted for msg_insert() avoiding GFP_ATOMIC allocations, and after releasing the info->lock the thing is freed anyway so it should not change things"

Link: http://lkml.kernel.org/r/1552029161-4957-1-git-send-email-lirongqing@baidu.c... Signed-off-by: Li RongQing lirongqing@baidu.com Signed-off-by: Zhang Yu zhangyu31@baidu.com Reviewed-by: Davidlohr Bueso dbueso@suse.de Cc: Manfred Spraul manfred@colorfullife.com Cc: Arnd Bergmann arnd@arndb.de 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 --- ipc/mqueue.c | 10 ++++++++-- ipc/msgutil.c | 6 ++++++ 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 5e24eb0ab5dd..6ed74825ab54 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -373,7 +373,8 @@ static void mqueue_evict_inode(struct inode *inode) struct user_struct *user; unsigned long mq_bytes, mq_treesize; struct ipc_namespace *ipc_ns; - struct msg_msg *msg; + struct msg_msg *msg, *nmsg; + LIST_HEAD(tmp_msg);

clear_inode(inode);

@@ -384,10 +385,15 @@ static void mqueue_evict_inode(struct inode *inode) info = MQUEUE_I(inode); spin_lock(&info->lock); while ((msg = msg_get(info)) != NULL) - free_msg(msg); + list_add_tail(&msg->m_list, &tmp_msg); kfree(info->node_cache); spin_unlock(&info->lock);

+ list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) { + list_del(&msg->m_list); + free_msg(msg); + } + /* Total amount of bytes accounted for the mqueue */ mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) + min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) * diff --git a/ipc/msgutil.c b/ipc/msgutil.c index ed81aafd2392..9467307487f7 100644 --- a/ipc/msgutil.c +++ b/ipc/msgutil.c @@ -18,6 +18,7 @@ #include <linux/utsname.h> #include <linux/proc_ns.h> #include <linux/uaccess.h> +#include <linux/sched.h>

#include "util.h"

@@ -66,6 +67,9 @@ static struct msg_msg *alloc_msg(size_t len) pseg = &msg->next; while (len > 0) { struct msg_msgseg *seg; + + cond_resched(); + alen = min(len, DATALEN_SEG); seg = kmalloc(sizeof(*seg) + alen, GFP_KERNEL); if (seg == NULL) @@ -178,6 +182,8 @@ void free_msg(struct msg_msg *msg) kfree(msg); while (seg != NULL) { struct msg_msgseg *tmp = seg->next; + + cond_resched(); kfree(seg); seg = tmp; }

From: Colin Ian King colin.king@canonical.com

[ Upstream commit d0c0d902339249c75da85fd9257a86cbb98dfaa5 ]

Currently an int is being shifted and the result is being cast to a u64 which leads to undefined behaviour if the shift is more than 31 bits. Fix this by casting the integer value 1 to u64 before the shift operation.

Addresses-Coverity: ("Bad shift operation") Fixes: 7b594769120b ("[SCSI] bnx2fc: Handle REC_TOV error code from firmware") Signed-off-by: Colin Ian King colin.king@canonical.com Acked-by: Saurav Kashyap skashyap@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/bnx2fc/bnx2fc_hwi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 28c671b609b2..0c71b69b9f88 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -829,7 +829,7 @@ static void bnx2fc_process_unsol_compl(struct bnx2fc_rport *tgt, u16 wqe) ((u64)err_entry->data.err_warn_bitmap_hi << 32) | (u64)err_entry->data.err_warn_bitmap_lo; for (i = 0; i < BNX2FC_NUM_ERR_BITS; i++) { - if (err_warn_bit_map & (u64) (1 << i)) { + if (err_warn_bit_map & ((u64)1 << i)) { err_warn = i; break; }

From: Kloetzke Jan Jan.Kloetzke@preh.de

[ Upstream commit ad70411a978d1e6e97b1e341a7bde9a79af0c93d ]

When disconnecting cdc_ncm the kernel sporadically crashes shortly after the disconnect:

[ 57.868812] Unable to handle kernel NULL pointer dereference at virtual address 00000000 ... [ 58.006653] PC is at 0x0 [ 58.009202] LR is at call_timer_fn+0xec/0x1b4 [ 58.013567] pc : [<0000000000000000>] lr : [<ffffff80080f5130>] pstate: 00000145 [ 58.020976] sp : ffffff8008003da0 [ 58.024295] x29: ffffff8008003da0 x28: 0000000000000001 [ 58.029618] x27: 000000000000000a x26: 0000000000000100 [ 58.034941] x25: 0000000000000000 x24: ffffff8008003e68 [ 58.040263] x23: 0000000000000000 x22: 0000000000000000 [ 58.045587] x21: 0000000000000000 x20: ffffffc68fac1808 [ 58.050910] x19: 0000000000000100 x18: 0000000000000000 [ 58.056232] x17: 0000007f885aff8c x16: 0000007f883a9f10 [ 58.061556] x15: 0000000000000001 x14: 000000000000006e [ 58.066878] x13: 0000000000000000 x12: 00000000000000ba [ 58.072201] x11: ffffffc69ff1db30 x10: 0000000000000020 [ 58.077524] x9 : 8000100008001000 x8 : 0000000000000001 [ 58.082847] x7 : 0000000000000800 x6 : ffffff8008003e70 [ 58.088169] x5 : ffffffc69ff17a28 x4 : 00000000ffff138b [ 58.093492] x3 : 0000000000000000 x2 : 0000000000000000 [ 58.098814] x1 : 0000000000000000 x0 : 0000000000000000 ... [ 58.205800] [< (null)>] (null) [ 58.210521] [<ffffff80080f5298>] expire_timers+0xa0/0x14c [ 58.215937] [<ffffff80080f542c>] run_timer_softirq+0xe8/0x128 [ 58.221702] [<ffffff8008081120>] __do_softirq+0x298/0x348 [ 58.227118] [<ffffff80080a6304>] irq_exit+0x74/0xbc [ 58.232009] [<ffffff80080e17dc>] __handle_domain_irq+0x78/0xac [ 58.237857] [<ffffff8008080cf4>] gic_handle_irq+0x80/0xac ...

The crash happens roughly 125..130ms after the disconnect. This correlates with the 'delay' timer that is started on certain USB tx/rx errors in the URB completion handler.

The problem is a race of usbnet_stop() with usbnet_start_xmit(). In usbnet_stop() we call usbnet_terminate_urbs() to cancel all URBs in flight. This only makes sense if no new URBs are submitted concurrently, though. But the usbnet_start_xmit() can run at the same time on another CPU which almost unconditionally submits an URB. The error callback of the new URB will then schedule the timer after it was already stopped.

The fix adds a check if the tx queue is stopped after the tx list lock has been taken. This should reliably prevent the submission of new URBs while usbnet_terminate_urbs() does its job. The same thing is done on the rx side even though it might be safe due to other flags that are checked there.

Signed-off-by: Jan Klötzke Jan.Kloetzke@preh.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/usb/usbnet.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 9710cf71054a..2502681369cd 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -499,6 +499,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)

if (netif_running (dev->net) && netif_device_present (dev->net) && + test_bit(EVENT_DEV_OPEN, &dev->flags) && !test_bit (EVENT_RX_HALT, &dev->flags) && !test_bit (EVENT_DEV_ASLEEP, &dev->flags)) { switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { @@ -1385,6 +1386,11 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, spin_unlock_irqrestore(&dev->txq.lock, flags); goto drop; } + if (netif_queue_stopped(net)) { + usb_autopm_put_interface_async(dev->intf); + spin_unlock_irqrestore(&dev->txq.lock, flags); + goto drop; + }

#ifdef CONFIG_PM /* if this triggers the device is still a sleep */

From: Christian Borntraeger borntraeger@de.ibm.com

[ Upstream commit 19ec166c3f39fe1d3789888a74cc95544ac266d4 ]

kselftests exposed a problem in the s390 handling for memory slots. Right now we only do proper memory slot handling for creation of new memory slots. Neither MOVE, nor DELETION are handled properly. Let us implement those.

Signed-off-by: Christian Borntraeger borntraeger@de.ibm.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kvm/kvm-s390.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5ddb1debba95..23911ecfbad6 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2721,21 +2721,28 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, const struct kvm_memory_slot *new, enum kvm_mr_change change) { - int rc; - - /* If the basics of the memslot do not change, we do not want - * to update the gmap. Every update causes several unnecessary - * segment translation exceptions. This is usually handled just - * fine by the normal fault handler + gmap, but it will also - * cause faults on the prefix page of running guest CPUs. - */ - if (old->userspace_addr == mem->userspace_addr && - old->base_gfn * PAGE_SIZE == mem->guest_phys_addr && - old->npages * PAGE_SIZE == mem->memory_size) - return; + int rc = 0;

- rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, - mem->guest_phys_addr, mem->memory_size); + switch (change) { + case KVM_MR_DELETE: + rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, + old->npages * PAGE_SIZE); + break; + case KVM_MR_MOVE: + rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE, + old->npages * PAGE_SIZE); + if (rc) + break; + /* FALLTHROUGH */ + case KVM_MR_CREATE: + rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr, + mem->guest_phys_addr, mem->memory_size); + break; + case KVM_MR_FLAGS_ONLY: + break; + default: + WARN(1, "Unknown KVM MR CHANGE: %d\n", change); + } if (rc) pr_warn("failed to commit memory region\n"); return;