On Mon, 31 Oct 2022 00:45:38 +0800
Cindy Lu <l...@redhat.com> wrote:
> - Move the function vfio_get_xlat_addr to softmmu/memory.c, and
> change the name to memory_get_xlat_addr(). So we can use this
> function on other devices, such as vDPA device.
> - Add a new bool arg in this function, which shows whether the memory is
> backed by a discard manager. So the device can have its own warning.
>
> Signed-off-by: Cindy Lu <l...@redhat.com>
> ---
> hw/vfio/common.c | 107 +++++++++++-------------------------------
> include/exec/memory.h | 4 ++
> softmmu/memory.c | 72 ++++++++++++++++++++++++++++
> 3 files changed, 104 insertions(+), 79 deletions(-)
>
> diff --git a/hw/vfio/common.c b/hw/vfio/common.c
> index ace9562a9b..a934262f39 100644
> --- a/hw/vfio/common.c
> +++ b/hw/vfio/common.c
> @@ -573,61 +573,20 @@ static bool
> vfio_listener_skipped_section(MemoryRegionSection *section)
> */
> section->offset_within_address_space & (1ULL << 63);
> }
> -
> -/* Called with rcu_read_lock held. */
> -static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
> - ram_addr_t *ram_addr, bool *read_only)
> +static inline void vfio_mr_discard_manager_warn(bool mr_has_discard_manager)
> {
> - MemoryRegion *mr;
> - hwaddr xlat;
> - hwaddr len = iotlb->addr_mask + 1;
> - bool writable = iotlb->perm & IOMMU_WO;
> -
> - /*
> - * The IOMMU TLB entry we have just covers translation through
> - * this IOMMU to its immediate target. We need to translate
> - * it the rest of the way through to memory.
> - */
> - mr = address_space_translate(&address_space_memory,
> - iotlb->translated_addr,
> - &xlat, &len, writable,
> - MEMTXATTRS_UNSPECIFIED);
> - if (!memory_region_is_ram(mr)) {
> - error_report("iommu map to non memory area %"HWADDR_PRIx"",
> - xlat);
> - return false;
> - } else if (memory_region_has_ram_discard_manager(mr)) {
> - RamDiscardManager *rdm = memory_region_get_ram_discard_manager(mr);
> - MemoryRegionSection tmp = {
> - .mr = mr,
> - .offset_within_region = xlat,
> - .size = int128_make64(len),
> - };
> -
> - /*
> - * Malicious VMs can map memory into the IOMMU, which is expected
> - * to remain discarded. vfio will pin all pages, populating memory.
> - * Disallow that. vmstate priorities make sure any RamDiscardManager
> - * were already restored before IOMMUs are restored.
> - */
> - if (!ram_discard_manager_is_populated(rdm, &tmp)) {
> - error_report("iommu map to discarded memory (e.g., unplugged via"
> - " virtio-mem): %"HWADDR_PRIx"",
> - iotlb->translated_addr);
> - return false;
> - }
> -
> + if (mr_has_discard_manager) {
> /*
> - * Malicious VMs might trigger discarding of IOMMU-mapped memory. The
> - * pages will remain pinned inside vfio until unmapped, resulting in
> a
> - * higher memory consumption than expected. If memory would get
> - * populated again later, there would be an inconsistency between
> pages
> - * pinned by vfio and pages seen by QEMU. This is the case until
> - * unmapped from the IOMMU (e.g., during device reset).
> + * Malicious VMs might trigger discarding of IOMMU-mapped memory.
> + * The pages will remain pinned inside vfio until unmapped,
> + * resulting in a higher memory consumption than expected. If memory
> + * would get populated again later, there would be an inconsistency
> + * between pages pinned by vfio and pages seen by QEMU. This is the
> + * case until unmapped from the IOMMU (e.g., during device reset).
> *
> - * With malicious guests, we really only care about pinning more
> memory
> - * than expected. RLIMIT_MEMLOCK set for the user/process can never
> be
> - * exceeded and can be used to mitigate this problem.
> + * With malicious guests, we really only care about pinning more
> + * memory than expected. RLIMIT_MEMLOCK set for the user/process can
> + * never be exceeded and can be used to mitigate this problem.
> */
> warn_report_once("Using vfio with vIOMMUs and coordinated discarding
> of"
> " RAM (e.g., virtio-mem) works, however, malicious"
> @@ -635,31 +594,7 @@ static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb,
> void **vaddr,
> " intended via an IOMMU. It's possible to mitigate "
> " by setting/adjusting RLIMIT_MEMLOCK.");
> }
> -
> - /*
> - * Translation truncates length to the IOMMU page size,
> - * check that it did not truncate too much.
> - */
> - if (len & iotlb->addr_mask) {
> - error_report("iommu has granularity incompatible with target AS");
> - return false;
> - }
> -
> - if (vaddr) {
> - *vaddr = memory_region_get_ram_ptr(mr) + xlat;
> - }
> -
> - if (ram_addr) {
> - *ram_addr = memory_region_get_ram_addr(mr) + xlat;
> - }
> -
> - if (read_only) {
> - *read_only = !writable || mr->readonly;
> - }
> -
> - return true;
> }
> -
> static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
> {
> VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
> @@ -681,10 +616,17 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n,
> IOMMUTLBEntry *iotlb)
>
> if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) {
> bool read_only;
> + bool mr_has_discard_manager;
>
> - if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only)) {
> + if (!memory_get_xlat_addr(iotlb, &vaddr, NULL, &read_only,
> + &mr_has_discard_manager)) {
> goto out;
> }
> + /*
> + * if the mr has the discard_manager and the return value of
> + * memory_get_xlat_addr() is ture then we need to warn
> + */
> + vfio_mr_discard_manager_warn(mr_has_discard_manager);
The wrapper should be around the memory_get_xlat_addr() function, not
a separate helper whose only purpose is to trigger the error report,
ie. extract all but the warn_report_once() into a shared
function, keep vfio_get_xlat_addr(). The vfio call sites should not
change. Thanks,
Alex
> /*
> * vaddr is only valid until rcu_read_unlock(). But after
> * vfio_dma_map has set up the mapping the pages will be
> @@ -1349,6 +1291,7 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier
> *n, IOMMUTLBEntry *iotlb)
> VFIOContainer *container = giommu->container;
> hwaddr iova = iotlb->iova + giommu->iommu_offset;
> ram_addr_t translated_addr;
> + bool mr_has_discard_manager;
>
> trace_vfio_iommu_map_dirty_notify(iova, iova + iotlb->addr_mask);
>
> @@ -1359,9 +1302,9 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier
> *n, IOMMUTLBEntry *iotlb)
> }
>
> rcu_read_lock();
> - if (vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL)) {
> + if (memory_get_xlat_addr(iotlb, NULL, &translated_addr, NULL,
> + &mr_has_discard_manager)) {
> int ret;
> -
> ret = vfio_get_dirty_bitmap(container, iova, iotlb->addr_mask + 1,
> translated_addr);
> if (ret) {
> @@ -1370,6 +1313,12 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier
> *n, IOMMUTLBEntry *iotlb)
> container, iova,
> iotlb->addr_mask + 1, ret);
> }
> +
> + /*
> + * if the mr has the discard_manager and the return value of
> + * memory_get_xlat_addr() is ture then we need to warn
> + */
> + vfio_mr_discard_manager_warn(mr_has_discard_manager);
> }
> rcu_read_unlock();
> }
> diff --git a/include/exec/memory.h b/include/exec/memory.h
> index bfb1de8eea..d1e79c39dc 100644
> --- a/include/exec/memory.h
> +++ b/include/exec/memory.h
> @@ -713,6 +713,10 @@ void
> ram_discard_manager_register_listener(RamDiscardManager *rdm,
> void ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
> RamDiscardListener *rdl);
>
> +bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
> + ram_addr_t *ram_addr, bool *read_only,
> + bool *mr_has_discard_manager);
> +
> typedef struct CoalescedMemoryRange CoalescedMemoryRange;
> typedef struct MemoryRegionIoeventfd MemoryRegionIoeventfd;
>
> diff --git a/softmmu/memory.c b/softmmu/memory.c
> index 7ba2048836..bc0be3f62c 100644
> --- a/softmmu/memory.c
> +++ b/softmmu/memory.c
> @@ -33,6 +33,7 @@
> #include "qemu/accel.h"
> #include "hw/boards.h"
> #include "migration/vmstate.h"
> +#include "exec/address-spaces.h"
>
> //#define DEBUG_UNASSIGNED
>
> @@ -2121,6 +2122,77 @@ void
> ram_discard_manager_unregister_listener(RamDiscardManager *rdm,
> rdmc->unregister_listener(rdm, rdl);
> }
>
> +/* Called with rcu_read_lock held. */
> +bool memory_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr,
> + ram_addr_t *ram_addr, bool *read_only,
> + bool *mr_has_discard_manager)
> +{
> + MemoryRegion *mr;
> + hwaddr xlat;
> + hwaddr len = iotlb->addr_mask + 1;
> + bool writable = iotlb->perm & IOMMU_WO;
> +
> + if (mr_has_discard_manager) {
> + *mr_has_discard_manager = false;
> + }
> + /*
> + * The IOMMU TLB entry we have just covers translation through
> + * this IOMMU to its immediate target. We need to translate
> + * it the rest of the way through to memory.
> + */
> + mr = address_space_translate(&address_space_memory,
> iotlb->translated_addr,
> + &xlat, &len, writable,
> MEMTXATTRS_UNSPECIFIED);
> + if (!memory_region_is_ram(mr)) {
> + error_report("iommu map to non memory area %" HWADDR_PRIx "", xlat);
> + return false;
> + } else if (memory_region_has_ram_discard_manager(mr)) {
> + RamDiscardManager *rdm = memory_region_get_ram_discard_manager(mr);
> + MemoryRegionSection tmp = {
> + .mr = mr,
> + .offset_within_region = xlat,
> + .size = int128_make64(len),
> + };
> + if (mr_has_discard_manager) {
> + *mr_has_discard_manager = true;
> + }
> + /*
> + * Malicious VMs can map memory into the IOMMU, which is expected
> + * to remain discarded. vfio will pin all pages, populating memory.
> + * Disallow that. vmstate priorities make sure any RamDiscardManager
> + * were already restored before IOMMUs are restored.
> + */
> + if (!ram_discard_manager_is_populated(rdm, &tmp)) {
> + error_report("iommu map to discarded memory (e.g., unplugged via"
> + " virtio-mem): %" HWADDR_PRIx "",
> + iotlb->translated_addr);
> + return false;
> + }
> + }
> +
> + /*
> + * Translation truncates length to the IOMMU page size,
> + * check that it did not truncate too much.
> + */
> + if (len & iotlb->addr_mask) {
> + error_report("iommu has granularity incompatible with target AS");
> + return false;
> + }
> +
> + if (vaddr) {
> + *vaddr = memory_region_get_ram_ptr(mr) + xlat;
> + }
> +
> + if (ram_addr) {
> + *ram_addr = memory_region_get_ram_addr(mr) + xlat;
> + }
> +
> + if (read_only) {
> + *read_only = !writable || mr->readonly;
> + }
> +
> + return true;
> +}
> +
> void memory_region_set_log(MemoryRegion *mr, bool log, unsigned client)
> {
> uint8_t mask = 1 << client;
