softmmu/memory_mapping: optimize dump/tpm for virtio-mem
cover softmmu/memory_mapping: optimize dump/tpm for virtio-mem
Minor fixes and cleanups, followed by an optimization for virtio-mem regarding guest dumps and tpm.
virtio-mem logically plugs/unplugs memory within a sparse memory region and notifies via the RamDiscardMgr interface when parts become plugged (populated) or unplugged (discarded).
Currently, guest_phys_blocks_append() appends the whole (sparse) virtio-mem managed region and therefore tpm code might zero the hole region and dump code will dump the whole region. Let's only add logically plugged (populated) parts of that region, skipping over logically unplugged (discarded) parts by reusing the RamDiscardMgr infrastructure introduced to handle virtio-mem + VFIO properly.
Based-on: https://lkml.kernel.org/r/[email protected]
David Hildenbrand (5):
tpm: mark correct memory region range dirty when clearing RAM softmmu/memory_mapping: reuse qemu_get_guest_simple_memory_mapping() softmmu/memory_mapping: never merge ranges accross memory regions softmmu/memory_mapping: factor out adding physical memory ranges softmmu/memory_mapping: optimize for RamDiscardMgr sections
hw/tpm/tpm_ppi.c | 4 +- softmmu/memory_mapping.c | 118 +++++++++++++++++++++++++++------------ 2 files changed, 84 insertions(+), 38 deletions(-)
Signature · 1 line
2.29.2
PATCH 1/5 tpm: mark correct memory region range dirty when clearing RAM
We might not start at the beginning of the memory region. We could also calculate via the difference in the host address; however, memory_region_set_dirty() also relies on memory_region_get_ram_addr() internally, so let's just use that.
--- hw/tpm/tpm_ppi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
hw/tpm/tpm_ppi.c +3 -1
@@ -30,11 +30,13 @@ void tpm_ppi_reset(TPMPPI *tpmppi)guest_phys_blocks_init (&guest_phys_blocks);guest_phys_blocks_append (&guest_phys_blocks); QTAILQ_FOREACH(block, &guest_phys_blocks.head, next) { +ram_addr_t mr_start =memory_region_get_ram_addr (block->mr); +trace_tpm_ppi_memset (block->host_addr, block->target_end - block->target_start);memset (block->host_addr,0 , block->target_end - block->target_start); -memory_region_set_dirty (block->mr,0 , +memory_region_set_dirty (block->mr, block->target_start - mr_start, block->target_end - block->target_start); }guest_phys_blocks_free (&guest_phys_blocks);
Signature · 1 line
2.29.2
Re: [PATCH v1 1/5] tpm: mark correct memory region range dirty when clearing RAM
Quoted 32 lines · David Hildenbrand
We might not start at the beginning of the memory region. We could also calculate via the difference in the host address; however,
memory_region_set_dirty()also relies onmemory_region_get_ram_addr()internally, so let's just use that.Fixes ffab1be70692 ("tpm: clear RAM when "memory overwrite" requested")Cc Marc-André Lureau <[email protected]>Cc Paolo Bonzini <[email protected]>Cc "Michael S. Tsirkin" <[email protected]>Cc Alex Williamson <[email protected]>Cc Dr. David Alan Gilbert <[email protected]>Cc Igor Mammedov <[email protected]>Cc Claudio Fontana <[email protected]>Cc Thomas Huth <[email protected]>Cc "Alex Bennée" <[email protected]>Cc Peter Xu <[email protected]>Cc Laurent Vivier <[email protected]>Cc Stefan Berger <[email protected]>Signed-off-by David Hildenbrand <[email protected]>--- hw/tpm/tpm_ppi.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)hw/tpm/tpm_ppi.c +1
-0@@ -30,11 +30,13 @@ void tpm_ppi_reset(TPMPPI *tpmppi)guest_phys_blocks_init (&guest_phys_blocks);guest_phys_blocks_append (&guest_phys_blocks); QTAILQ_FOREACH(block, &guest_phys_blocks.head, next) { +ram_addr_t mr_start =memory_region_get_ram_addr (block->mr);
hw/tpm/tpm_ppi.c void tpm_ppi_reset(TPMPPI *tpmppi) · line 42
Quoted 10 lines
hw/tpm/tpm_ppi.c +2
-1+trace_tpm_ppi_memset (block->host_addr, block->target_end - block->target_start);memset (block->host_addr,0 , block->target_end - block->target_start); -memory_region_set_dirty (block->mr,0 , +memory_region_set_dirty (block->mr, block->target_start - mr_start, block->target_end - block->target_start); }guest_phys_blocks_free (&guest_phys_blocks);
PATCH 2/5 softmmu/memory_mapping: reuse qemu_get_guest_simple_memory_mapping()
In reply to David HildenbrandLet's reuse qemu_get_guest_simple_memory_mapping(), which does exactly what we want.
--- softmmu/memory_mapping.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-)
softmmu/memory_mapping.c +1 -7
@@ -289,8 +289,6 @@ void qemu_get_guest_memory_mapping(MemoryMappingList *list, Error **errp) {CPUState *cpu, *first_paging_enabled_cpu; -GuestPhysBlock *block; -ram_addr_t offset, length; first_paging_enabled_cpu =find_paging_enabled_cpu (first_cpu);if (first_paging_enabled_cpu) {
@@ -310,11 +308,7 @@ void qemu_get_guest_memory_mapping(MemoryMappingList *list,* If the guest doesn't use paging, the virtual address is equal to physical * address. */ - QTAILQ_FOREACH(block, &guest_phys_blocks->head, next) { - offset = block->target_start; - length = block->target_end - block->target_start; -create_new_memory_mapping (list, offset, offset, length); - } +qemu_get_guest_simple_memory_mapping (list, guest_phys_blocks); } void qemu_get_guest_simple_memory_mapping(MemoryMappingList *list,
Signature · 1 line
2.29.2
PATCH 3/5 softmmu/memory_mapping: never merge ranges accross memory regions
In reply to David HildenbrandLet's make sure to not merge when different memory regions are involved. Unlikely, but theoretically possible.
--- softmmu/memory_mapping.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
softmmu/memory_mapping.c +2 -1
@@ -230,7 +230,8 @@ static void guest_phys_blocks_region_add(MemoryListener *listener,/* we want continuity in both guest-physical and host-virtual memory */ if (predecessor->target_end < target_start || - predecessor->host_addr + predecessor_size != host_addr) { + predecessor->host_addr + predecessor_size != host_addr || + predecessor->mr != section->mr) { predecessor =NULL ; } }
Signature · 1 line
2.29.2
PATCH 4/5 softmmu/memory_mapping: factor out adding physical memory ranges
In reply to David HildenbrandLet's factor out adding an item to the list, to be reused in RamDiscardMgr context next.
--- softmmu/memory_mapping.c | 64 +++++++++++++++++++++------------------- 1 file changed, 34 insertions(+), 30 deletions(-)
softmmu/memory_mapping.c +34 -30
@@ -194,35 +194,17 @@ typedef struct GuestPhysListener {MemoryListener listener; } GuestPhysListener; -static void guest_phys_blocks_region_add (MemoryListener *listener, -MemoryRegionSection *section) +static void guest_phys_block_add (GuestPhysBlockList *list,MemoryRegion *mr, +hwaddr target_start,hwaddr target_end, +uint8_t *host_addr) { -GuestPhysListener *g; -uint64_t section_size; -hwaddr target_start, target_end; -uint8_t *host_addr; -GuestPhysBlock *predecessor; - -/* we only care about RAM */ -if (!memory_region_is_ram (section->mr) || -memory_region_is_ram_device (section->mr) || -memory_region_is_nonvolatile (section->mr)) { -return ; - } - - g =container_of (listener, GuestPhysListener, listener); - section_size =int128_get64 (section->size); - target_start = section->offset_within_address_space; - target_end = target_start + section_size; - host_addr =memory_region_get_ram_ptr (section->mr) + - section->offset_within_region; - predecessor =NULL ; +GuestPhysBlock *predecessor =NULL ;/* find continuity in guest physical address space */ -if (!QTAILQ_EMPTY (&g->list->head)) { +if (!QTAILQ_EMPTY (&list->head)) {hwaddr predecessor_size; - predecessor =QTAILQ_LAST (&g->list->head); + predecessor =QTAILQ_LAST (&list->head); predecessor_size = predecessor->target_end - predecessor->target_start;/* the memory API guarantees monotonically increasing traversal */
@@ -231,7 +213,7 @@ static void guest_phys_blocks_region_add(MemoryListener *listener,/* we want continuity in both guest-physical and host-virtual memory */ if (predecessor->target_end < target_start || predecessor->host_addr + predecessor_size != host_addr || - predecessor->mr != section->mr) { + predecessor->mr != mr) { predecessor =NULL ; } }
@@ -243,11 +225,11 @@ static void guest_phys_blocks_region_add(MemoryListener *listener, block->target_start = target_start; block->target_end = target_end; block->host_addr = host_addr; - block->mr = section->mr; -memory_region_ref (section->mr); + block->mr = mr; +memory_region_ref (mr); -QTAILQ_INSERT_TAIL (&g->list->head, block, next); - ++g->list->num; +QTAILQ_INSERT_TAIL (&list->head, block, next); + ++list->num; }else {/* expand predecessor until @target_end; predecessor's start doesn't * change
@@ -258,10 +240,32 @@ static void guest_phys_blocks_region_add(MemoryListener *listener,#ifdef DEBUG_GUEST_PHYS_REGION_ADD fprintf (stderr,"%s: target_start=" TARGET_FMT_plx" target_end=" TARGET_FMT_plx": %s (count: %u)\n" , __func__, target_start, - target_end, predecessor ?"joined" :"added" , g->list->num); + target_end, predecessor ?"joined" :"added" , list->num);#endif } +static void guest_phys_blocks_region_add (MemoryListener *listener, +MemoryRegionSection *section) +{ +GuestPhysListener *g =container_of (listener, GuestPhysListener, listener); +hwaddr target_start, target_end; +uint8_t *host_addr; + +/* we only care about RAM */ +if (!memory_region_is_ram (section->mr) || +memory_region_is_ram_device (section->mr) || +memory_region_is_nonvolatile (section->mr)) { +return ; + } + + target_start = section->offset_within_address_space; + target_end = target_start +int128_get64 (section->size); + host_addr =memory_region_get_ram_ptr (section->mr) + + section->offset_within_region; +guest_phys_block_add (g->list, section->mr, target_start, target_end, + host_addr); +} +void guest_phys_blocks_append (GuestPhysBlockList *list) {GuestPhysListener g = {0 };
Signature · 1 line
2.29.2
PATCH 5/5 softmmu/memory_mapping: optimize for RamDiscardMgr sections
In reply to David Hildenbrandvirtio-mem logically plugs/unplugs memory within a sparse memory region and notifies via the RamDiscardMgr interface when parts become plugged (populated) or unplugged (discarded).
Currently, we end up (via the two users)
1) zeroing all logically unplugged/discarded memory during TPM resets.
2) reading all logically unplugged/discarded memory when dumping, to figure out the content is zero.
1) is always bad, because we assume unplugged memory stays discarded (and is already implicitly zero).
2) isn't that bad with anonymous memory, we end up reading the zero page (slow and unnecessary, though). However, once we use some file-backed memory (future use case), even reading will populate memory.
Let's cut out all parts marked as not-populated (discarded) via the RamDiscardMgr. As virtio-mem is the single user, this now means that logically unplugged memory ranges will no longer be included in the dump, which results in smaller dump files and faster dumping.
virtio-mem has a minimum granularity of 1 MiB (and the default is usually 2 MiB). Theoretically, we can see quite some fragmentation, in practice we won't have it completely fragmented in 1 MiB pieces. Still, we might end up with many physical ranges.
Both, the ELF format and kdump seem to be ready to support many individual ranges (e.g., for ELF it seems to be UINT32_MAX, kdump has a linear bitmap).
--- softmmu/memory_mapping.c | 45 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+)
softmmu/memory_mapping.c +45 -0
@@ -244,6 +244,35 @@ static void guest_phys_block_add(GuestPhysBlockList *list, MemoryRegion *mr,#endif } +typedef struct GuestPhysRDL { +GuestPhysBlockList *list; +RamDiscardListener listener; +MemoryRegionSection *section; +}GuestPhysRDL ; + +static int guest_phys_ram_discard_notify_populate (RamDiscardListener *listener, +const MemoryRegion *const_mr, +ram_addr_t offset, +ram_addr_t size) +{ +GuestPhysRDL *rdl =container_of (listener, GuestPhysRDL, listener); +MemoryRegionSection *s = rdl->section; +const hwaddr mr_start =MAX (offset, s->offset_within_region); +const hwaddr mr_end =MIN (offset + size, + s->offset_within_region +int128_get64 (s->size)); +uint8_t *host_addr; + +if (mr_start >= mr_end) { +return 0 ; + } + + host_addr =memory_region_get_ram_ptr (s->mr) + mr_start; +guest_phys_block_add (rdl->list, s->mr, + mr_start + s->offset_within_address_space, + mr_end + s->offset_within_address_space, host_addr); +return 0 ; +} +static void guest_phys_blocks_region_add (MemoryListener *listener,MemoryRegionSection *section) {
@@ -258,6 +287,22 @@ static void guest_phys_blocks_region_add(MemoryListener *listener,return ; } +/* for special sparse regions, only add populated parts */ +if (memory_region_has_ram_discard_mgr (section->mr)) { +RamDiscardMgr *rdm =memory_region_get_ram_discard_mgr (section->mr); +RamDiscardMgrClass *rdmc =RAM_DISCARD_MGR_GET_CLASS (rdm); +GuestPhysRDL rdl = { + .list = g->list, + .section = section, + }; + +ram_discard_listener_init (&rdl.listener, + guest_phys_ram_discard_notify_populate,NULL , +NULL ); + rdmc->replay_populated (rdm, section->mr, &rdl.listener); +return ; + } + target_start = section->offset_within_address_space; target_end = target_start +int128_get64 (section->size); host_addr = memory_region_get_ram_ptr(section->mr) +
Signature · 1 line
2.29.2