qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [PATCH v3 10/13] migration/ram: Handle RAM block resizes during post


From: Dr. David Alan Gilbert
Subject: Re: [PATCH v3 10/13] migration/ram: Handle RAM block resizes during postcopy
Date: Fri, 6 Mar 2020 16:56:15 +0000
User-agent: Mutt/1.13.3 (2020-01-12)

* David Hildenbrand (address@hidden) wrote:
> Resizing while migrating is dangerous and does not work as expected.
> The whole migration code works on the usable_length of ram blocks and does
> not expect this to change at random points in time.
> 
> In the case of postcopy, relying on used_length is racy as soon as the
> guest is running. Also, when used_length changes we might leave the
> uffd handler registered for some memory regions, reject valid pages
> when migrating and fail when sending the recv bitmap to the source.
> 
> Resizing can be trigger *after* (but not during) a reset in
> ACPI code by the guest
> - hw/arm/virt-acpi-build.c:acpi_ram_update()
> - hw/i386/acpi-build.c:acpi_ram_update()
> 
> Let's remember the original used_length in a separate variable and
> use it in relevant postcopy code. Make sure to update it when we resize
> during precopy, when synchronizing the RAM block sizes with the source.
> 
> Reviewed-by: Peter Xu <address@hidden>
> Cc: "Dr. David Alan Gilbert" <address@hidden>
> Cc: Juan Quintela <address@hidden>
> Cc: Eduardo Habkost <address@hidden>
> Cc: Paolo Bonzini <address@hidden>
> Cc: Igor Mammedov <address@hidden>
> Cc: "Michael S. Tsirkin" <address@hidden>
> Cc: Richard Henderson <address@hidden>
> Cc: Shannon Zhao <address@hidden>
> Cc: Alex Bennée <address@hidden>
> Cc: Peter Xu <address@hidden>
> Signed-off-by: David Hildenbrand <address@hidden>
> ---
>  include/exec/ramblock.h  | 10 ++++++++++
>  migration/postcopy-ram.c | 15 ++++++++++++---
>  migration/ram.c          | 11 +++++++++--
>  3 files changed, 31 insertions(+), 5 deletions(-)
> 
> diff --git a/include/exec/ramblock.h b/include/exec/ramblock.h
> index 07d50864d8..664701b759 100644
> --- a/include/exec/ramblock.h
> +++ b/include/exec/ramblock.h
> @@ -59,6 +59,16 @@ struct RAMBlock {
>       */
>      unsigned long *clear_bmap;
>      uint8_t clear_bmap_shift;
> +
> +    /*
> +     * RAM block length that corresponds to the used_length on the migration
> +     * source (after RAM block sizes were synchronized). Especially, after
> +     * starting to run the guest, used_length and postcopy_length can differ.
> +     * Used to register/unregister uffd handlers and as the size of the 
> received
> +     * bitmap. Receiving any page beyond this length will bail out, as it
> +     * could not have been valid on the source.
> +     */
> +    ram_addr_t postcopy_length;
>  };
>  #endif
>  #endif
> diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
> index a36402722b..c68caf4e42 100644
> --- a/migration/postcopy-ram.c
> +++ b/migration/postcopy-ram.c
> @@ -17,6 +17,7 @@
>   */
>  
>  #include "qemu/osdep.h"
> +#include "qemu/rcu.h"
>  #include "exec/target_page.h"
>  #include "migration.h"
>  #include "qemu-file.h"
> @@ -31,6 +32,7 @@
>  #include "qemu/error-report.h"
>  #include "trace.h"
>  #include "hw/boards.h"
> +#include "exec/ramblock.h"
>  
>  /* Arbitrary limit on size of each discard command,
>   * keeps them around ~200 bytes
> @@ -456,6 +458,13 @@ static int init_range(RAMBlock *rb, void *opaque)
>      ram_addr_t length = qemu_ram_get_used_length(rb);
>      trace_postcopy_init_range(block_name, host_addr, offset, length);
>  
> +    /*
> +     * Save the used_length before running the guest. In case we have to
> +     * resize RAM blocks when syncing RAM block sizes from the source during
> +     * precopy, we'll update it manually via the ram block notifier.
> +     */
> +    rb->postcopy_length = length;
> +
>      /*
>       * We need the whole of RAM to be truly empty for postcopy, so things
>       * like ROMs and any data tables built during init must be zero'd
> @@ -478,7 +487,7 @@ static int cleanup_range(RAMBlock *rb, void *opaque)
>      const char *block_name = qemu_ram_get_idstr(rb);
>      void *host_addr = qemu_ram_get_host_addr(rb);
>      ram_addr_t offset = qemu_ram_get_offset(rb);
> -    ram_addr_t length = qemu_ram_get_used_length(rb);
> +    ram_addr_t length = rb->postcopy_length;
>      MigrationIncomingState *mis = opaque;
>      struct uffdio_range range_struct;
>      trace_postcopy_cleanup_range(block_name, host_addr, offset, length);
> @@ -600,7 +609,7 @@ static int nhp_range(RAMBlock *rb, void *opaque)
>      const char *block_name = qemu_ram_get_idstr(rb);
>      void *host_addr = qemu_ram_get_host_addr(rb);
>      ram_addr_t offset = qemu_ram_get_offset(rb);
> -    ram_addr_t length = qemu_ram_get_used_length(rb);
> +    ram_addr_t length = rb->postcopy_length;
>      trace_postcopy_nhp_range(block_name, host_addr, offset, length);
>  
>      /*
> @@ -644,7 +653,7 @@ static int ram_block_enable_notify(RAMBlock *rb, void 
> *opaque)
>      struct uffdio_register reg_struct;
>  
>      reg_struct.range.start = (uintptr_t)qemu_ram_get_host_addr(rb);
> -    reg_struct.range.len = qemu_ram_get_used_length(rb);
> +    reg_struct.range.len = rb->postcopy_length;
>      reg_struct.mode = UFFDIO_REGISTER_MODE_MISSING;
>  
>      /* Now tell our userfault_fd that it's responsible for this area */
> diff --git a/migration/ram.c b/migration/ram.c
> index 1a5ff07997..ee5c3d5784 100644
> --- a/migration/ram.c
> +++ b/migration/ram.c
> @@ -244,7 +244,7 @@ int64_t ramblock_recv_bitmap_send(QEMUFile *file,
>          return -1;
>      }
>  
> -    nbits = block->used_length >> TARGET_PAGE_BITS;
> +    nbits = block->postcopy_length >> TARGET_PAGE_BITS;
>  
>      /*
>       * Make sure the tmp bitmap buffer is big enough, e.g., on 32bit
> @@ -3160,7 +3160,13 @@ static int ram_load_postcopy(QEMUFile *f)
>                  break;
>              }
>  
> -            if (!offset_in_ramblock(block, addr)) {
> +            /*
> +             * Relying on used_length is racy and can result in false 
> positives.
> +             * We might place pages beyond used_length in case RAM was shrunk
> +             * while in postcopy, which is fine - trying to place via
> +             * UFFDIO_COPY/UFFDIO_ZEROPAGE will never segfault.
> +             */

Is this actually safe? Imagine that the region had got shrunk, would it
still be mmap'd in there - or could there now be a space where something
else might have landed in?

> +            if (!block->host || addr >= block->postcopy_length) {
>                  error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
>                  ret = -EINVAL;
>                  break;
> @@ -3757,6 +3763,7 @@ static void ram_mig_ram_block_resized(RAMBlockNotifier 
> *n, void *host,
>                               rb->idstr);
>              }
>          }
> +        rb->postcopy_length = new_size;
>          break;
>      case POSTCOPY_INCOMING_NONE:
>      case POSTCOPY_INCOMING_RUNNING:
> -- 
> 2.24.1
> 
--
Dr. David Alan Gilbert / address@hidden / Manchester, UK




reply via email to

[Prev in Thread] Current Thread [Next in Thread]