On 06/02/2017 18:32, Dr. David Alan Gilbert (git) wrote:
> From: "Dr. David Alan Gilbert" <dgilb...@redhat.com>
>
> Create ram_block_discard_range in exec.c to replace
> postcopy_ram_discard_range and most of ram_discard_range.
>
> Those two routines are a bit of a weird combination, and
> ram_discard_range is about to get more complex for hugepages.
> It's OS dependent code (so shouldn't be in migration/ram.c) but
> it needs quite a bit of the innards of RAMBlock so doesn't belong in
> the os*.c.
>
> Signed-off-by: Dr. David Alan Gilbert <dgilb...@redhat.com>
> ---
> exec.c | 59
> +++++++++++++++++++++++++++++++++++++++++++++++
> include/exec/cpu-common.h | 1 +
> 2 files changed, 60 insertions(+)
>
> diff --git a/exec.c b/exec.c
> index 8b9ed73..e040cdf 100644
> --- a/exec.c
> +++ b/exec.c
> @@ -45,6 +45,12 @@
> #include "exec/address-spaces.h"
> #include "sysemu/xen-mapcache.h"
> #include "trace-root.h"
> +
> +#ifdef CONFIG_FALLOCATE_PUNCH_HOLE
> +#include <fcntl.h>
> +#include <linux/falloc.h>
> +#endif
> +
> #endif
> #include "exec/cpu-all.h"
> #include "qemu/rcu_queue.h"
> @@ -3286,4 +3292,57 @@ int qemu_ram_foreach_block(RAMBlockIterFunc func, void
> *opaque)
> rcu_read_unlock();
> return ret;
> }
> +
> +/*
> + * Unmap pages of memory from start to start+length such that
> + * they a) read as 0, b) Trigger whatever fault mechanism
> + * the OS provides for postcopy.
> + * The pages must be unmapped by the end of the function.
> + * Returns: 0 on success, none-0 on failure
> + *
> + */
> +int ram_block_discard_range(RAMBlock *rb, uint64_t start, size_t length)
> +{
> + int ret = -1;
> +
> + rcu_read_lock();
> + uint8_t *host_startaddr = rb->host + start;
> +
> + if ((uintptr_t)host_startaddr & (rb->page_size - 1)) {
> + error_report("ram_block_discard_range: Unaligned start address: %p",
> + host_startaddr);
> + goto err;
> + }
> +
> + if ((start + length) <= rb->used_length) {
> + uint8_t *host_endaddr = host_startaddr + length;
> + if ((uintptr_t)host_endaddr & (rb->page_size - 1)) {
> + error_report("ram_block_discard_range: Unaligned end address:
> %p",
> + host_endaddr);
> + goto err;
> + }
> +
> + errno = ENOTSUP; /* If we are missing MADVISE etc */
> +
> +#if defined(CONFIG_MADVISE)
> + ret = qemu_madvise(host_startaddr, length, QEMU_MADV_DONTNEED);
> +#endif
> + if (ret) {
> + ret = -errno;
> + error_report("ram_block_discard_range: Failed to discard range "
> + "%s:%" PRIx64 " +%zx (%d)",
> + rb->idstr, start, length, ret);
> + }
> + } else {
> + error_report("ram_block_discard_range: Overrun block '%s' (%" PRIu64
> + "/%zx/" RAM_ADDR_FMT")",
> + rb->idstr, start, length, rb->used_length);
> + }
> +
> +err:
> + rcu_read_unlock();
> +
> + return ret;
> +}
I really looks like a copy'n'paste from ram_discard_range(). It could be
clearer if you remove the code from ram_discard_range() and call this
function instead.
I think you don't need the "#if defined(CONFIG_MADVISE)" as you use
qemu_madvise() (or you should use madvise() directly if you want to
avoid the posix_madvise()).
[perhaps qemu_madvise() should set errno to ENOTSUP instead of EINVAL]
Laurent
