Re: [PATCH 09/10] x86 rwsem: down_read_critical implementation

[David Howells]

Michel Lespinasse <walken@xxxxxxxxxx> wrote:

> The basic properties that have been true so far still hold:
> - RWSEM_ACTIVE_READ_BIAS  & RWSEM_ACTIVE_MASK == 1
> - RWSEM_ACTIVE_WRITE_BIAS & RWSEM_ACTIVE_MASK == 1
> - RWSEM_WAITING_BIAS      & RWSEM_ACTIVE_MASK == 0
> - RWSEM_ACTIVE_WRITE_BIAS < 0 and RWSEM_WAITING_BIAS < 0
> 
> A new property is introduced: RWSEM_ACTIVE_WRITE_BIAS is set to be
> 'more negative' than RWSEM_WAITING_BIAS. This way, even the first writer
> will set the rwsem count to be < RWSEM_WAITING_BIAS and down_read_critical()
> can make use of this to determine if there are any active writers.
> 
> Signed-off-by: Michel Lespinasse <walken@xxxxxxxxxx>

Acked-by: David Howells <dhowells@xxxxxxxxxx>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/