Re: SMP VM race in 2.[0-4]

2000-10-04 Thread Eric Lowe
Hello, > I found a possible problem on SMP. In vmscan.c / try_to_swap_out you do > not use atomic operations for manipulating with ptes. You read the pte, > modify it and write it nonatomically. When the second CPU is running > process that turns on 'D' bit of pte while the first CPU is in > try_

SMP VM race in 2.[0-4]

2000-10-04 Thread Mikulas Patocka
Hi. I found a possible problem on SMP. In vmscan.c / try_to_swap_out you do not use atomic operations for manipulating with ptes. You read the pte, modify it and write it nonatomically. When the second CPU is running process that turns on 'D' bit of pte while the first CPU is in try_to_swap_out,