Skip to main content

Browse the archive

Revision 471f0aa7fa64e23766a1473b32d9ec3f0718895a authored by Chang S. Bae on 21 October 2022, 18:58:44 UTC, committed by Dave Hansen on 21 October 2022, 22:22:09 UTC 
x86/fpu: Fix copy_xstate_to_uabi() to copy init states correctly
 
When an extended state component is not present in fpstate, but in init
state, the function copies from init_fpstate via copy_feature().

But, dynamic states are not present in init_fpstate because of all-zeros
init states. Then retrieving them from init_fpstate will explode like this:

 BUG: kernel NULL pointer dereference, address: 0000000000000000
 ...
 RIP: 0010:memcpy_erms+0x6/0x10
  ? __copy_xstate_to_uabi_buf+0x381/0x870
  fpu_copy_guest_fpstate_to_uabi+0x28/0x80
  kvm_arch_vcpu_ioctl+0x14c/0x1460 [kvm]
  ? __this_cpu_preempt_check+0x13/0x20
  ? vmx_vcpu_put+0x2e/0x260 [kvm_intel]
  kvm_vcpu_ioctl+0xea/0x6b0 [kvm]
  ? kvm_vcpu_ioctl+0xea/0x6b0 [kvm]
  ? __fget_light+0xd4/0x130
  __x64_sys_ioctl+0xe3/0x910
  ? debug_smp_processor_id+0x17/0x20
  ? fpregs_assert_state_consistent+0x27/0x50
  do_syscall_64+0x3f/0x90
  entry_SYSCALL_64_after_hwframe+0x63/0xcd

Adjust the 'mask' to zero out the userspace buffer for the features that
are not available both from fpstate and from init_fpstate.

The dynamic features depend on the compacted XSAVE format. Ensure it is
enabled before reading XCOMP_BV in init_fpstate.

Fixes: 2308ee57d93d ("x86/fpu/amx: Enable the AMX feature in 64-bit mode")
Reported-by: Yuan Yao <yuan.yao@intel.com>
Suggested-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Tested-by: Yuan Yao <yuan.yao@intel.com>
Link: https://lore.kernel.org/lkml/BYAPR11MB3717EDEF2351C958F2C86EED95259@BYAPR11MB3717.namprd11.prod.outlook.com/
Link: https://lkml.kernel.org/r/20221021185844.13472-1-chang.seok.bae@intel.com
1 parent b329f5d
Raw File
epoll.c 
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/uaccess.h>
#include <linux/io_uring.h>
#include <linux/eventpoll.h>

#include <uapi/linux/io_uring.h>

#include "io_uring.h"
#include "epoll.h"

#if defined(CONFIG_EPOLL)
struct io_epoll {
	struct file			*file;
	int				epfd;
	int				op;
	int				fd;
	struct epoll_event		event;
};

int io_epoll_ctl_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_epoll *epoll = io_kiocb_to_cmd(req, struct io_epoll);

	pr_warn_once("%s: epoll_ctl support in io_uring is deprecated and will "
		     "be removed in a future Linux kernel version.\n",
		     current->comm);

	if (sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;

	epoll->epfd = READ_ONCE(sqe->fd);
	epoll->op = READ_ONCE(sqe->len);
	epoll->fd = READ_ONCE(sqe->off);

	if (ep_op_has_event(epoll->op)) {
		struct epoll_event __user *ev;

		ev = u64_to_user_ptr(READ_ONCE(sqe->addr));
		if (copy_from_user(&epoll->event, ev, sizeof(*ev)))
			return -EFAULT;
	}

	return 0;
}

int io_epoll_ctl(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_epoll *ie = io_kiocb_to_cmd(req, struct io_epoll);
	int ret;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;

	ret = do_epoll_ctl(ie->epfd, ie->op, ie->fd, &ie->event, force_nonblock);
	if (force_nonblock && ret == -EAGAIN)
		return -EAGAIN;

	if (ret < 0)
		req_set_fail(req);
	io_req_set_res(req, ret, 0);
	return IOU_OK;
}
#endif
back to top