Revision 9a6e7c39810e4a8bc7fc95056cefb40583fe07ef authored by Wanpeng Li on 14 September 2017, 10:54:16 UTC, committed by Radim Krčmář on 14 September 2017, 16:43:43 UTC
qemu-system-x86-8600  [004] d..1  7205.687530: kvm_entry: vcpu 2
qemu-system-x86-8600  [004] ....  7205.687532: kvm_exit: reason EXCEPTION_NMI rip 0xffffffffa921297d info ffffeb2c0e44e018 80000b0e
qemu-system-x86-8600  [004] ....  7205.687532: kvm_page_fault: address ffffeb2c0e44e018 error_code 0
qemu-system-x86-8600  [004] ....  7205.687620: kvm_try_async_get_page: gva = 0xffffeb2c0e44e018, gfn = 0x427e4e
qemu-system-x86-8600  [004] .N..  7205.687628: kvm_async_pf_not_present: token 0x8b002 gva 0xffffeb2c0e44e018
    kworker/4:2-7814  [004] ....  7205.687655: kvm_async_pf_completed: gva 0xffffeb2c0e44e018 address 0x7fcc30c4e000
qemu-system-x86-8600  [004] ....  7205.687703: kvm_async_pf_ready: token 0x8b002 gva 0xffffeb2c0e44e018
qemu-system-x86-8600  [004] d..1  7205.687711: kvm_entry: vcpu 2

After running some memory intensive workload in guest, I catch the kworker
which completes the GUP too quickly, and queues an "Page Ready" #PF exception
after the "Page not Present" exception before the next vmentry as the above
trace which will result in #DF injected to guest.

This patch fixes it by clearing the queue for "Page not Present" if "Page Ready"
occurs before the next vmentry since the GUP has already got the required page
and shadow page table has already been fixed by "Page Ready" handler.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Fixes: 7c90705bf2a3 ("KVM: Inject asynchronous page fault into a PV guest if page is swapped out.")
[Changed indentation and added clearing of injected. - Radim]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
1 parent 648d453
Raw File
syscall.c
/*
 * sys_ipc() is the old de-multiplexer for the SysV IPC calls.
 *
 * This is really horribly ugly, and new architectures should just wire up
 * the individual syscalls instead.
 */
#include <linux/unistd.h>

#ifdef __ARCH_WANT_SYS_IPC
#include <linux/errno.h>
#include <linux/ipc.h>
#include <linux/shm.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>

SYSCALL_DEFINE6(ipc, unsigned int, call, int, first, unsigned long, second,
		unsigned long, third, void __user *, ptr, long, fifth)
{
	int version, ret;

	version = call >> 16; /* hack for backward compatibility */
	call &= 0xffff;

	switch (call) {
	case SEMOP:
		return sys_semtimedop(first, (struct sembuf __user *)ptr,
				      second, NULL);
	case SEMTIMEDOP:
		return sys_semtimedop(first, (struct sembuf __user *)ptr,
				      second,
				      (const struct timespec __user *)fifth);

	case SEMGET:
		return sys_semget(first, second, third);
	case SEMCTL: {
		unsigned long arg;
		if (!ptr)
			return -EINVAL;
		if (get_user(arg, (unsigned long __user *) ptr))
			return -EFAULT;
		return sys_semctl(first, second, third, arg);
	}

	case MSGSND:
		return sys_msgsnd(first, (struct msgbuf __user *) ptr,
				  second, third);
	case MSGRCV:
		switch (version) {
		case 0: {
			struct ipc_kludge tmp;
			if (!ptr)
				return -EINVAL;

			if (copy_from_user(&tmp,
					   (struct ipc_kludge __user *) ptr,
					   sizeof(tmp)))
				return -EFAULT;
			return sys_msgrcv(first, tmp.msgp, second,
					   tmp.msgtyp, third);
		}
		default:
			return sys_msgrcv(first,
					   (struct msgbuf __user *) ptr,
					   second, fifth, third);
		}
	case MSGGET:
		return sys_msgget((key_t) first, second);
	case MSGCTL:
		return sys_msgctl(first, second, (struct msqid_ds __user *)ptr);

	case SHMAT:
		switch (version) {
		default: {
			unsigned long raddr;
			ret = do_shmat(first, (char __user *)ptr,
				       second, &raddr, SHMLBA);
			if (ret)
				return ret;
			return put_user(raddr, (unsigned long __user *) third);
		}
		case 1:
			/*
			 * This was the entry point for kernel-originating calls
			 * from iBCS2 in 2.2 days.
			 */
			return -EINVAL;
		}
	case SHMDT:
		return sys_shmdt((char __user *)ptr);
	case SHMGET:
		return sys_shmget(first, second, third);
	case SHMCTL:
		return sys_shmctl(first, second,
				   (struct shmid_ds __user *) ptr);
	default:
		return -ENOSYS;
	}
}
#endif
back to top