s390x/pci: Accomodate vfio DMA limiting
Subsystems (2)
v3 cover s390x/pci: Accomodate vfio DMA limiting
Kernel commit 492855939bdb added a limit to the number of outstanding DMA requests for a type1 vfio container. However, lazy unmapping in s390 can in fact cause quite a large number of outstanding DMA requests to build up prior to being purged, potentially the entire guest DMA space. This results in unexpected 'VFIO_MAP_DMA failed: No space left on device' conditions seen in QEMU.
This patchset adds support to qemu to retrieve the number of allowable DMA requests via the VFIO_IOMMU_GET_INFO ioctl. The patches are separated into vfio hits which add support for reading in VFIO_IOMMU_GET_INFO capability chains and getting the per-container dma_avail value, and s390 hits to track DMA usage on a per-container basis.
Associated kernel patch:
https://marc.info/?l=kvm&m=160019703922812&w=2
Changes from v2:
- Patch 1 (new): Added a placeholder linux-headers sync
- Patch 2: Re-arranged so that this patch that adds a shared routine for finding info capabilities is first
- Patch 3: Adjusted vfio_get_info_dma_avail() logic to be able to return true when the capability exists but the caller did not provide a buffer on input.
- Patch 4 (new): Introduce hw/s390x/s390-pci-vfio.* to better-separate PCI emulation code from code that interfaces with vfio
- Patch 4: s/s390_sync_dma_avail/s390_pci_update_dma_avail/ - Since it's now moved into a different file it can't be static so I added '_pci'.
- Patch 4: Use g_autofree as suggested - drop the goto/out as a result
- Patch 4+5: Added asserts() in a few locations per suggestion
- Patch 5: lowercase inline function names
- Patch 5: fix dma_avail initialization in rpcit_service_call() and ensure we still allow unmaps to call s390_pci_update_iotlb when dma_avail == 0
Matthew Rosato (5):
linux-headers: update against 5.9-rc5
vfio: Create shared routine for scanning info capabilities
vfio: Find DMA available capability
s390x/pci: Add routine to get the vfio dma available count s390x/pci: Honor DMA limits set by vfio
hw/s390x/meson.build | 1 + hw/s390x/s390-pci-bus.c | 56 ++++++++- hw/s390x/s390-pci-bus.h | 9 ++ hw/s390x/s390-pci-inst.c | 34 ++++- hw/s390x/s390-pci-inst.h | 3 + hw/s390x/s390-pci-vfio.c | 54 ++++++++ hw/s390x/s390-pci-vfio.h | 17 +++ hw/vfio/common.c | 52 ++++++-- include/hw/vfio/vfio-common.h | 2 + include/standard-headers/drm/drm_fourcc.h | 140 +++++++++++++++++++++ include/standard-headers/linux/ethtool.h | 87 +++++++++++++ include/standard-headers/linux/input-event-codes.h | 3 +- include/standard-headers/linux/vhost_types.h | 11 ++ include/standard-headers/linux/virtio_9p.h | 4 +- include/standard-headers/linux/virtio_blk.h | 26 ++-- include/standard-headers/linux/virtio_config.h | 8 +- include/standard-headers/linux/virtio_console.h | 8 +- include/standard-headers/linux/virtio_net.h | 6 +- include/standard-headers/linux/virtio_scsi.h | 20 +-- linux-headers/asm-generic/unistd.h | 6 +- linux-headers/asm-mips/unistd_n32.h | 1 + linux-headers/asm-mips/unistd_n64.h | 1 + linux-headers/asm-mips/unistd_o32.h | 1 + linux-headers/asm-powerpc/kvm.h | 5 + linux-headers/asm-powerpc/unistd_32.h | 1 + linux-headers/asm-powerpc/unistd_64.h | 1 + linux-headers/asm-s390/kvm.h | 7 +- linux-headers/asm-s390/unistd_32.h | 1 + linux-headers/asm-s390/unistd_64.h | 1 + linux-headers/asm-x86/unistd_32.h | 1 + linux-headers/asm-x86/unistd_64.h | 1 + linux-headers/asm-x86/unistd_x32.h | 1 + linux-headers/linux/kvm.h | 10 +- linux-headers/linux/vfio.h | 18 ++- linux-headers/linux/vhost.h | 2 + 35 files changed, 537 insertions(+), 62 deletions(-) create mode 100644 hw/s390x/s390-pci-vfio.c create mode 100644 hw/s390x/s390-pci-vfio.h
Signature · 1 line
1.8.3.1
PATCH v3 1/5 linux-headers: update against 5.9-rc5
PLACEHOLDER as the kernel patch driving the need for this ("vfio iommu: Add dma available capability") is not merged yet.
--- include/standard-headers/drm/drm_fourcc.h | 140 +++++++++++++++++++++ include/standard-headers/linux/ethtool.h | 87 +++++++++++++ include/standard-headers/linux/input-event-codes.h | 3 +- include/standard-headers/linux/vhost_types.h | 11 ++ include/standard-headers/linux/virtio_9p.h | 4 +- include/standard-headers/linux/virtio_blk.h | 26 ++-- include/standard-headers/linux/virtio_config.h | 8 +- include/standard-headers/linux/virtio_console.h | 8 +- include/standard-headers/linux/virtio_net.h | 6 +- include/standard-headers/linux/virtio_scsi.h | 20 +-- linux-headers/asm-generic/unistd.h | 6 +- linux-headers/asm-mips/unistd_n32.h | 1 + linux-headers/asm-mips/unistd_n64.h | 1 + linux-headers/asm-mips/unistd_o32.h | 1 + linux-headers/asm-powerpc/kvm.h | 5 + linux-headers/asm-powerpc/unistd_32.h | 1 + linux-headers/asm-powerpc/unistd_64.h | 1 + linux-headers/asm-s390/kvm.h | 7 +- linux-headers/asm-s390/unistd_32.h | 1 + linux-headers/asm-s390/unistd_64.h | 1 + linux-headers/asm-x86/unistd_32.h | 1 + linux-headers/asm-x86/unistd_64.h | 1 + linux-headers/asm-x86/unistd_x32.h | 1 + linux-headers/linux/kvm.h | 10 +- linux-headers/linux/vfio.h | 18 ++- linux-headers/linux/vhost.h | 2 + 26 files changed, 328 insertions(+), 43 deletions(-)
include/standard-headers/drm/drm_fourcc.h +140 -0
@@ -235,6 +235,12 @@ extern "C" {#define DRM_FORMAT_NV61 fourcc_code('N', 'V', '6', '1')/* 2x1 subsampled Cb:Cr plane */ #define DRM_FORMAT_NV24 fourcc_code('N', 'V', '2', '4')/* non-subsampled Cr:Cb plane */ #define DRM_FORMAT_NV42 fourcc_code('N', 'V', '4', '2')/* non-subsampled Cb:Cr plane */ +/* +* 2 plane YCbCr +* index 0 = Y plane, [39:0] Y3:Y2:Y1:Y0 little endian +* index 1 = Cr:Cb plane, [39:0] Cr1:Cb1:Cr0:Cb0 little endian +*/ +#define DRM_FORMAT_NV15 fourcc_code('N', 'V', '1', '5')/* 2x2 subsampled Cr:Cb plane */ /* * 2 plane YCbCr MSB aligned
@@ -264,6 +270,22 @@ extern "C" {*/ #define DRM_FORMAT_P016 fourcc_code('P', '0', '1', '6')/* 2x2 subsampled Cr:Cb plane 16 bits per channel */ +/* 3 plane non-subsampled (444) YCbCr +* 16 bits per component, but only 10 bits are used and 6 bits are padded +* index 0: Y plane, [15:0] Y:x [10:6] little endian +* index 1: Cb plane, [15:0] Cb:x [10:6] little endian +* index 2: Cr plane, [15:0] Cr:x [10:6] little endian +*/ +#define DRM_FORMAT_Q410 fourcc_code('Q', '4', '1', '0') + +/* 3 plane non-subsampled (444) YCrCb +* 16 bits per component, but only 10 bits are used and 6 bits are padded +* index 0: Y plane, [15:0] Y:x [10:6] little endian +* index 1: Cr plane, [15:0] Cr:x [10:6] little endian +* index 2: Cb plane, [15:0] Cb:x [10:6] little endian +*/ +#define DRM_FORMAT_Q401 fourcc_code('Q', '4', '0', '1') +/* * 3 plane YCbCr * index 0: Y plane, [7:0] Y
@@ -308,6 +330,7 @@ extern "C" {#define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07#define DRM_FORMAT_MOD_VENDOR_ARM 0x08#define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09 +#define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a/* add more to the end as needed */
@@ -322,8 +345,33 @@ extern "C" {* When adding a new token please document the layout with a code comment, * similar to the fourcc codes above. drm_fourcc.h is considered the * authoritative source for all of these. +* +* Generic modifier names: +* +* DRM_FORMAT_MOD_GENERIC_* definitions are used to provide vendor-neutral names +* for layouts which are common across multiple vendors. To preserve +* compatibility, in cases where a vendor-specific definition already exists and +* a generic name for it is desired, the common name is a purely symbolic alias +* and must use the same numerical value as the original definition. +* +* Note that generic names should only be used for modifiers which describe +* generic layouts (such as pixel re-ordering), which may have +* independently-developed support across multiple vendors. +* +* In future cases where a generic layout is identified before merging with a +* vendor-specific modifier, a new 'GENERIC' vendor or modifier using vendor +* 'NONE' could be considered. This should only be for obvious, exceptional +* cases to avoid polluting the 'GENERIC' namespace with modifiers which only +* apply to a single vendor. +* +* Generic names should not be used for cases where multiple hardware vendors +* have implementations of the same standardised compression scheme (such as +* AFBC). In those cases, all implementations should use the same format +* modifier(s), reflecting the vendor of the standard. */ +#define DRM_FORMAT_MOD_GENERIC_16_16_TILE DRM_FORMAT_MOD_SAMSUNG_16_16_TILE +/* * Invalid Modifier *
@@ -891,6 +939,18 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier)*/ #define AFBC_FORMAT_MOD_BCH (1ULL << 11) +/* AFBC uncompressed storage mode +* +* Indicates that the buffer is using AFBC uncompressed storage mode. +* In this mode all superblock payloads in the buffer use the uncompressed +* storage mode, which is usually only used for data which cannot be compressed. +* The buffer layout is the same as for AFBC buffers without USM set, this only +* affects the storage mode of the individual superblocks. Note that even a +* buffer without USM set may use uncompressed storage mode for some or all +* superblocks, USM just guarantees it for all. +*/ +#define AFBC_FORMAT_MOD_USM (1ULL << 12) +/* * Arm 16x16 Block U-Interleaved modifier *
@@ -915,6 +975,86 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier)*/ #define DRM_FORMAT_MOD_ALLWINNER_TILED fourcc_mod_code(ALLWINNER, 1) +/* +* Amlogic Video Framebuffer Compression modifiers +* +* Amlogic uses a proprietary lossless image compression protocol and format +* for their hardware video codec accelerators, either video decoders or +* video input encoders. +* +* It considerably reduces memory bandwidth while writing and reading +* frames in memory. +* +* The underlying storage is considered to be 3 components, 8bit or 10-bit +* per component YCbCr 420, single plane : +* - DRM_FORMAT_YUV420_8BIT +* - DRM_FORMAT_YUV420_10BIT +* +* The first 8 bits of the mode defines the layout, then the following 8 bits +* defines the options changing the layout. +* +* Not all combinations are valid, and different SoCs may support different +* combinations of layout and options. +*/ +#define __fourcc_mod_amlogic_layout_mask 0xf +#define __fourcc_mod_amlogic_options_shift 8 +#define __fourcc_mod_amlogic_options_mask 0xf + +#define DRM_FORMAT_MOD_AMLOGIC_FBC (__layout, __options) \ + fourcc_mod_code(AMLOGIC, \ + ((__layout) & __fourcc_mod_amlogic_layout_mask) | \ + (((__options) & __fourcc_mod_amlogic_options_mask) \ + << __fourcc_mod_amlogic_options_shift)) + +/* Amlogic FBC Layouts */ + +/* +* Amlogic FBC Basic Layout +* +* The basic layout is composed of: +* - a body content organized in 64x32 superblocks with 4096 bytes per +* superblock in default mode. +* - a 32 bytes per 128x64 header block +* +* This layout is transferrable between Amlogic SoCs supporting this modifier. +*/ +#define AMLOGIC_FBC_LAYOUT_BASIC (1ULL) + +/* +* Amlogic FBC Scatter Memory layout +* +* Indicates the header contains IOMMU references to the compressed +* frames content to optimize memory access and layout. +* +* In this mode, only the header memory address is needed, thus the +* content memory organization is tied to the current producer +* execution and cannot be saved/dumped neither transferrable between +* Amlogic SoCs supporting this modifier. +* +* Due to the nature of the layout, these buffers are not expected to +* be accessible by the user-space clients, but only accessible by the +* hardware producers and consumers. +* +* The user-space clients should expect a failure while trying to mmap +* the DMA-BUF handle returned by the producer. +*/ +#define AMLOGIC_FBC_LAYOUT_SCATTER (2ULL) + +/* Amlogic FBC Layout Options Bit Mask */ + +/* +* Amlogic FBC Memory Saving mode +* +* Indicates the storage is packed when pixel size is multiple of word +* boudaries, i.e. 8bit should be stored in this mode to save allocation +* memory. +* +* This mode reduces body layout to 3072 bytes per 64x32 superblock with +* the basic layout and 3200 bytes per 64x32 superblock combined with +* the scatter layout. +*/ +#define AMLOGIC_FBC_OPTION_MEM_SAVING (1ULL << 0) +#if defined(__cplusplus) }#endif
include/standard-headers/linux/ethtool.h +87 -0
111 lines not on this page · raw message
include/standard-headers/linux/input-event-codes.h +2 -1
@@ -888,7 +888,8 @@#define SW_LINEIN_INSERT 0x0d/* set = inserted */ #define SW_MUTE_DEVICE 0x0e/* set = device disabled */ #define SW_PEN_INSERTED 0x0f/* set = pen inserted */ -#define SW_MAX_ 0x0f +#define SW_MACHINE_COVER 0x10/* set = cover closed */ +#define SW_MAX_ 0x10#define SW_CNT (SW_MAX_+1)/*
include/standard-headers/linux/vhost_types.h +11 -0
@@ -60,6 +60,17 @@ struct vhost_iotlb_msg {#define VHOST_IOTLB_UPDATE 2#define VHOST_IOTLB_INVALIDATE 3#define VHOST_IOTLB_ACCESS_FAIL 4 +/* +* VHOST_IOTLB_BATCH_BEGIN and VHOST_IOTLB_BATCH_END allow modifying +* multiple mappings in one go: beginning with +* VHOST_IOTLB_BATCH_BEGIN, followed by any number of +* VHOST_IOTLB_UPDATE messages, and ending with VHOST_IOTLB_BATCH_END. +* When one of these two values is used as the message type, the rest +* of the fields in the message are ignored. There's no guarantee that +* these changes take place automatically in the device. +*/ +#define VHOST_IOTLB_BATCH_BEGIN 5 +#define VHOST_IOTLB_BATCH_END 6uint8_t type; };
include/standard-headers/linux/virtio_9p.h +2 -2
@@ -25,7 +25,7 @@* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ -#include "standard-headers/linux/types.h" +#include "standard-headers/linux/virtio_types.h" #include "standard-headers/linux/virtio_ids.h" #include "standard-headers/linux/virtio_config.h"
@@ -36,7 +36,7 @@struct virtio_9p_config {/* length of the tag name */ -uint16_t tag_len; +__virtio16 tag_len;/* non-NULL terminated tag name */ uint8_t tag[0 ]; }QEMU_PACKED ;
include/standard-headers/linux/virtio_blk.h +13 -13
@@ -55,20 +55,20 @@struct virtio_blk_config {/* The capacity (in 512-byte sectors). */ -uint64_t capacity; +__virtio64 capacity;/* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */ -uint32_t size_max; +__virtio32 size_max;/* The maximum number of segments (if VIRTIO_BLK_F_SEG_MAX) */ -uint32_t seg_max; +__virtio32 seg_max;/* geometry of the device (if VIRTIO_BLK_F_GEOMETRY) */ struct virtio_blk_geometry { -uint16_t cylinders; +__virtio16 cylinders;uint8_t heads;uint8_t sectors; } geometry;/* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */ -uint32_t blk_size; +__virtio32 blk_size;/* the next 4 entries are guarded by VIRTIO_BLK_F_TOPOLOGY */ /* exponent for physical block per logical block. */
@@ -76,42 +76,42 @@ struct virtio_blk_config {/* alignment offset in logical blocks. */ uint8_t alignment_offset;/* minimum I/O size without performance penalty in logical blocks. */ -uint16_t min_io_size; +__virtio16 min_io_size;/* optimal sustained I/O size in logical blocks. */ -uint32_t opt_io_size; +__virtio32 opt_io_size;/* writeback mode (if VIRTIO_BLK_F_CONFIG_WCE) */ uint8_t wce;uint8_t unused;/* number of vqs, only available when VIRTIO_BLK_F_MQ is set */ -uint16_t num_queues; +__virtio16 num_queues;/* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */ /* * The maximum discard sectors (in 512-byte sectors) for * one segment. */ -uint32_t max_discard_sectors; +__virtio32 max_discard_sectors;/* * The maximum number of discard segments in a * discard command. */ -uint32_t max_discard_seg; +__virtio32 max_discard_seg;/* Discard commands must be aligned to this number of sectors. */ -uint32_t discard_sector_alignment; +__virtio32 discard_sector_alignment;/* the next 3 entries are guarded by VIRTIO_BLK_F_WRITE_ZEROES */ /* * The maximum number of write zeroes sectors (in 512-byte sectors) in * one segment. */ -uint32_t max_write_zeroes_sectors; +__virtio32 max_write_zeroes_sectors;/* * The maximum number of segments in a write zeroes * command. */ -uint32_t max_write_zeroes_seg; +__virtio32 max_write_zeroes_seg;/* * Set if a VIRTIO_BLK_T_WRITE_ZEROES request may result in the * deallocation of one or more of the sectors.
include/standard-headers/linux/virtio_config.h +5 -3
@@ -67,13 +67,15 @@#define VIRTIO_F_VERSION_1 32/* -* If clear - device has the IOMMU bypass quirk feature. -* If set - use platform tools to detect the IOMMU. +* If clear - device has the platform DMA (e.g. IOMMU) bypass quirk feature. +* If set - use platform DMA tools to access the memory. * * Note the reverse polarity (compared to most other features), * this is for compatibility with legacy systems. */ -#define VIRTIO_F_IOMMU_PLATFORM 33 +#define VIRTIO_F_ACCESS_PLATFORM 33 +/* Legacy name for VIRTIO_F_ACCESS_PLATFORM (for compatibility with old userspace) */ +#define VIRTIO_F_IOMMU_PLATFORM VIRTIO_F_ACCESS_PLATFORM/* This feature indicates support for the packed virtqueue layout. */ #define VIRTIO_F_RING_PACKED 34
include/standard-headers/linux/virtio_console.h +4 -4
@@ -45,13 +45,13 @@struct virtio_console_config {/* colums of the screens */ -uint16_t cols; +__virtio16 cols;/* rows of the screens */ -uint16_t rows; +__virtio16 rows;/* max. number of ports this device can hold */ -uint32_t max_nr_ports; +__virtio32 max_nr_ports;/* emergency write register */ -uint32_t emerg_wr; +__virtio32 emerg_wr; }QEMU_PACKED ;/*
include/standard-headers/linux/virtio_net.h +3 -3
@@ -87,14 +87,14 @@ struct virtio_net_config {/* The config defining mac address (if VIRTIO_NET_F_MAC) */ uint8_t mac[ETH_ALEN ];/* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */ -uint16_t status; +__virtio16 status;/* Maximum number of each of transmit and receive queues; * see VIRTIO_NET_F_MQ and VIRTIO_NET_CTRL_MQ. * Legal values are between 1 and 0x8000 */ -uint16_t max_virtqueue_pairs; +__virtio16 max_virtqueue_pairs;/* Default maximum transmit unit advice */ -uint16_t mtu; +__virtio16 mtu;/* * speed, in units of 1Mb. All values 0 to INT_MAX are legal. * Any other value stands for unknown.
include/standard-headers/linux/virtio_scsi.h +10 -10
@@ -103,16 +103,16 @@ struct virtio_scsi_event { }QEMU_PACKED ;struct virtio_scsi_config { -uint32_t num_queues; -uint32_t seg_max; -uint32_t max_sectors; -uint32_t cmd_per_lun; -uint32_t event_info_size; -uint32_t sense_size; -uint32_t cdb_size; -uint16_t max_channel; -uint16_t max_target; -uint32_t max_lun; +__virtio32 num_queues; +__virtio32 seg_max; +__virtio32 max_sectors; +__virtio32 cmd_per_lun; +__virtio32 event_info_size; +__virtio32 sense_size; +__virtio32 cdb_size; +__virtio16 max_channel; +__virtio16 max_target; +__virtio32 max_lun; }QEMU_PACKED ;/* Feature Bits */
linux-headers/asm-generic/unistd.h +4 -2
@@ -606,9 +606,9 @@ __SYSCALL(__NR_sendto, sys_sendto)#define __NR_recvfrom 207 __SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)#define __NR_setsockopt 208 -__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt) +__SC_COMP(__NR_setsockopt, sys_setsockopt, sys_setsockopt)#define __NR_getsockopt 209 -__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt) +__SC_COMP(__NR_getsockopt, sys_getsockopt, sys_getsockopt)#define __NR_shutdown 210 __SYSCALL(__NR_shutdown, sys_shutdown)#define __NR_sendmsg 211
@@ -850,6 +850,8 @@ __SYSCALL(__NR_pidfd_open, sys_pidfd_open)#define __NR_clone3 435 __SYSCALL(__NR_clone3, sys_clone3)#endif +#define __NR_close_range 436 +__SYSCALL(__NR_close_range, sys_close_range)#define __NR_openat2 437__SYSCALL (__NR_openat2, sys_openat2)
linux-headers/asm-mips/unistd_n32.h +1 -0
@@ -365,6 +365,7 @@#define __NR_fspick (__NR_Linux + 433)#define __NR_pidfd_open (__NR_Linux + 434)#define __NR_clone3 (__NR_Linux + 435) +#define __NR_close_range (__NR_Linux + 436)#define __NR_openat2 (__NR_Linux + 437)#define __NR_pidfd_getfd (__NR_Linux + 438)#define __NR_faccessat2 (__NR_Linux + 439)
linux-headers/asm-mips/unistd_n64.h +1 -0
@@ -341,6 +341,7 @@#define __NR_fspick (__NR_Linux + 433)#define __NR_pidfd_open (__NR_Linux + 434)#define __NR_clone3 (__NR_Linux + 435) +#define __NR_close_range (__NR_Linux + 436)#define __NR_openat2 (__NR_Linux + 437)#define __NR_pidfd_getfd (__NR_Linux + 438)#define __NR_faccessat2 (__NR_Linux + 439)
linux-headers/asm-mips/unistd_o32.h +1 -0
@@ -411,6 +411,7 @@#define __NR_fspick (__NR_Linux + 433)#define __NR_pidfd_open (__NR_Linux + 434)#define __NR_clone3 (__NR_Linux + 435) +#define __NR_close_range (__NR_Linux + 436)#define __NR_openat2 (__NR_Linux + 437)#define __NR_pidfd_getfd (__NR_Linux + 438)#define __NR_faccessat2 (__NR_Linux + 439)
linux-headers/asm-powerpc/kvm.h +5 -0
@@ -640,6 +640,11 @@ struct kvm_ppc_cpu_char {#define KVM_REG_PPC_ONLINE (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbf)#define KVM_REG_PPC_PTCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc0) +/* POWER10 registers */ +#define KVM_REG_PPC_MMCR3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc1) +#define KVM_REG_PPC_SIER2 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc2) +#define KVM_REG_PPC_SIER3 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xc3) +/* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */
linux-headers/asm-powerpc/unistd_32.h +1 -0
@@ -418,6 +418,7 @@#define __NR_fspick 433#define __NR_pidfd_open 434#define __NR_clone3 435 +#define __NR_close_range 436#define __NR_openat2 437#define __NR_pidfd_getfd 438#define __NR_faccessat2 439
linux-headers/asm-powerpc/unistd_64.h +1 -0
@@ -390,6 +390,7 @@#define __NR_fspick 433#define __NR_pidfd_open 434#define __NR_clone3 435 +#define __NR_close_range 436#define __NR_openat2 437#define __NR_pidfd_getfd 438#define __NR_faccessat2 439
linux-headers/asm-s390/kvm.h +5 -2
@@ -231,11 +231,13 @@ struct kvm_guest_debug_arch {#define KVM_SYNC_GSCB (1UL << 9)#define KVM_SYNC_BPBC (1UL << 10)#define KVM_SYNC_ETOKEN (1UL << 11) +#define KVM_SYNC_DIAG318 (1UL << 12)#define KVM_SYNC_S390_VALID_FIELDS \ (KVM_SYNC_PREFIX | KVM_SYNC_GPRS | KVM_SYNC_ACRS | KVM_SYNC_CRS | \ KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT | KVM_SYNC_VRS | KVM_SYNC_RICCB | \ - KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN) + KVM_SYNC_FPRS | KVM_SYNC_GSCB | KVM_SYNC_BPBC | KVM_SYNC_ETOKEN | \ + KVM_SYNC_DIAG318)/* length and alignment of the sdnx as a power of two */ #define SDNXC 8
@@ -264,7 +266,8 @@ struct kvm_sync_regs { __u8 reserved2 : 7;__u8 padding1[51 ];/* riccb needs to be 64byte aligned */ __u8 riccb[64 ];/* runtime instrumentation controls block */ -__u8 padding2[192 ];/* sdnx needs to be 256byte aligned */ +__u64 diag318;/* diagnose 0x318 info */ +__u8 padding2[184 ];/* sdnx needs to be 256byte aligned */ union {__u8 sdnx[SDNXL ];/* state description annex */ struct {
linux-headers/asm-s390/unistd_32.h +1 -0
@@ -408,6 +408,7 @@#define __NR_fspick 433#define __NR_pidfd_open 434#define __NR_clone3 435 +#define __NR_close_range 436#define __NR_openat2 437#define __NR_pidfd_getfd 438#define __NR_faccessat2 439
linux-headers/asm-s390/unistd_64.h +1 -0
@@ -356,6 +356,7 @@#define __NR_fspick 433#define __NR_pidfd_open 434#define __NR_clone3 435 +#define __NR_close_range 436#define __NR_openat2 437#define __NR_pidfd_getfd 438#define __NR_faccessat2 439
linux-headers/asm-x86/unistd_32.h +1 -0
@@ -426,6 +426,7 @@#define __NR_fspick 433#define __NR_pidfd_open 434#define __NR_clone3 435 +#define __NR_close_range 436#define __NR_openat2 437#define __NR_pidfd_getfd 438#define __NR_faccessat2 439
linux-headers/asm-x86/unistd_64.h +1 -0
@@ -348,6 +348,7 @@#define __NR_fspick 433#define __NR_pidfd_open 434#define __NR_clone3 435 +#define __NR_close_range 436#define __NR_openat2 437#define __NR_pidfd_getfd 438#define __NR_faccessat2 439
linux-headers/asm-x86/unistd_x32.h +1 -0
@@ -301,6 +301,7 @@#define __NR_fspick (__X32_SYSCALL_BIT + 433)#define __NR_pidfd_open (__X32_SYSCALL_BIT + 434)#define __NR_clone3 (__X32_SYSCALL_BIT + 435) +#define __NR_close_range (__X32_SYSCALL_BIT + 436)#define __NR_openat2 (__X32_SYSCALL_BIT + 437)#define __NR_pidfd_getfd (__X32_SYSCALL_BIT + 438)#define __NR_faccessat2 (__X32_SYSCALL_BIT + 439)
linux-headers/linux/kvm.h +8 -2
@@ -289,6 +289,7 @@ struct kvm_run {/* KVM_EXIT_FAIL_ENTRY */ struct {__u64 hardware_entry_failure_reason; +__u32 cpu; } fail_entry;/* KVM_EXIT_EXCEPTION */ struct {
@@ -789,9 +790,10 @@ struct kvm_ppc_resize_hpt {#define KVM_VM_PPC_HV 1#define KVM_VM_PPC_PR 2 -/* on MIPS, 0 forces trap & emulate, 1 forces VZ ASE */ -#define KVM_VM_MIPS_TE 0 +/* on MIPS, 0 indicates auto, 1 forces VZ ASE, 2 forces trap & emulate */ +#define KVM_VM_MIPS_AUTO 0#define KVM_VM_MIPS_VZ 1 +#define KVM_VM_MIPS_TE 2#define KVM_S390_SIE_PAGE_OFFSET 1
@@ -1031,6 +1033,10 @@ struct kvm_ppc_resize_hpt {#define KVM_CAP_PPC_SECURE_GUEST 181#define KVM_CAP_HALT_POLL 182#define KVM_CAP_ASYNC_PF_INT 183 +#define KVM_CAP_LAST_CPU 184 +#define KVM_CAP_SMALLER_MAXPHYADDR 185 +#define KVM_CAP_S390_DIAG318 186 +#define KVM_CAP_STEAL_TIME 187#ifdef KVM_CAP_IRQ_ROUTING
linux-headers/linux/vfio.h +17 -1
@@ -1030,7 +1030,7 @@ struct vfio_iommu_type1_info_cap_iova_range {* size in bytes that can be used by user applications when getting the dirty * bitmap. */ -#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 1 +#define VFIO_IOMMU_TYPE1_INFO_CAP_MIGRATION 2struct vfio_iommu_type1_info_cap_migration {struct vfio_info_cap_header header;
@@ -1039,6 +1039,22 @@ struct vfio_iommu_type1_info_cap_migration {__u64 max_dirty_bitmap_size;/* in bytes */ }; +/* +* The DMA available capability allows to report the current number of +* simultaneously outstanding DMA mappings that are allowed. +* +* The structure below defines version 1 of this capability. +* +* avail: specifies the current number of outstanding DMA mappings allowed. +*/ +#define VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL 3 + +struct vfio_iommu_type1_info_dma_avail { +struct vfio_info_cap_header header; +__u32 avail; +}; + +#define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)/**
linux-headers/linux/vhost.h +2 -0
@@ -91,6 +91,8 @@/* Use message type V2 */ #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 +/* IOTLB can accept batching hints */ +#define VHOST_BACKEND_F_IOTLB_BATCH 0x2#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64)
Signature · 1 line
1.8.3.1
PATCH v3 2/5 vfio: Create shared routine for scanning info capabilities
In reply to Matthew RosatoRather than duplicating the same loop in multiple locations, create a static function to do the work.
--- hw/vfio/common.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-)
hw/vfio/common.c +13 -8
@@ -825,17 +825,12 @@ static void vfio_listener_release(VFIOContainer *container) } } -struct vfio_info_cap_header * -vfio_get_region_info_cap (struct vfio_region_info *info,uint16_t id) +static struct vfio_info_cap_header * +vfio_get_cap (void *ptr,uint32_t cap_offset,uint16_t id) {struct vfio_info_cap_header *hdr; -void *ptr = info; - -if (!(info->flags &VFIO_REGION_INFO_FLAG_CAPS )) { -return NULL ; - } -for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) { +for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) {if (hdr->id == id) {return hdr; }
@@ -844,6 +839,16 @@ vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)return NULL ; } +struct vfio_info_cap_header * +vfio_get_region_info_cap (struct vfio_region_info *info,uint16_t id) +{ +if (!(info->flags &VFIO_REGION_INFO_FLAG_CAPS )) { +return NULL ; + } + +return vfio_get_cap ((void *)info, info->cap_offset, id); +} +static int vfio_setup_region_sparse_mmaps (VFIORegion *region,struct vfio_region_info *info) {
Signature · 1 line
1.8.3.1
Re: [PATCH v3 2/5] vfio: Create shared routine for scanning info capabilities
Quoted 4 lines · Matthew Rosato
Rather than duplicating the same loop in multiple locations, create a static function to do the work.
Signed-off-by Matthew Rosato <[email protected]>
Quoted 47 lines
--- hw/vfio/common.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-)hw/vfio/common.c +13
-8@@ -825,17 +825,12 @@ static void vfio_listener_release(VFIOContainer *container) } } -struct vfio_info_cap_header * -vfio_get_region_info_cap (struct vfio_region_info *info,uint16_t id) +static struct vfio_info_cap_header * +vfio_get_cap (void *ptr,uint32_t cap_offset,uint16_t id) {struct vfio_info_cap_header *hdr; -void *ptr = info; - -if (!(info->flags &VFIO_REGION_INFO_FLAG_CAPS )) { -return NULL ; - } -for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) { +for (hdr = ptr + cap_offset; hdr != ptr; hdr = ptr + hdr->next) {if (hdr->id == id) {return hdr; }@@ -844,6 +839,16 @@ vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)return NULL ; } +struct vfio_info_cap_header * +vfio_get_region_info_cap (struct vfio_region_info *info,uint16_t id) +{ +if (!(info->flags &VFIO_REGION_INFO_FLAG_CAPS )) { +return NULL ; + } + +return vfio_get_cap ((void *)info, info->cap_offset, id); +} +static int vfio_setup_region_sparse_mmaps (VFIORegion *region,struct vfio_region_info *info) {
Re: [PATCH v3 2/5] vfio: Create shared routine for scanning info capabilities
In reply to Matthew RosatoQuoted 7 lines · On Tue, 15 Sep 2020 15:14:40 -0400 Matthew Rosato <[email protected]>…
Rather than duplicating the same loop in multiple locations, create a static function to do the work.
Signed-off-by Matthew Rosato <[email protected]>--- hw/vfio/common.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-)
PATCH v3 3/5 vfio: Find DMA available capability
In reply to Matthew RosatoThe underlying host may be limiting the number of outstanding DMA requests for type 1 IOMMU. Add helper functions to check for the DMA available capability and retrieve the current number of DMA mappings allowed.
--- hw/vfio/common.c | 31 +++++++++++++++++++++++++++++++ include/hw/vfio/vfio-common.h | 2 ++ 2 files changed, 33 insertions(+)
hw/vfio/common.c +31 -0
@@ -849,6 +849,37 @@ vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id)return vfio_get_cap ((void *)info, info->cap_offset, id); } +static struct vfio_info_cap_header * +vfio_get_iommu_type1_info_cap (struct vfio_iommu_type1_info *info,uint16_t id) +{ +if (!(info->flags &VFIO_IOMMU_INFO_CAPS )) { +return NULL ; + } + +return vfio_get_cap ((void *)info, info->cap_offset, id); +} + +bool vfio_get_info_dma_avail (struct vfio_iommu_type1_info *info, +unsigned int *avail) +{ +struct vfio_info_cap_header *hdr; +struct vfio_iommu_type1_info_dma_avail *cap; + +/* If the capability cannot be found, assume no DMA limiting */ + hdr =vfio_get_iommu_type1_info_cap (info, +VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL ); +if (hdr ==NULL ) { +return false; + } + +if (avail !=NULL ) { + cap = (void *) hdr; + *avail = cap->avail; + } + +return true; +} +static int vfio_setup_region_sparse_mmaps (VFIORegion *region,struct vfio_region_info *info) {
include/hw/vfio/vfio-common.h +2 -0
@@ -178,6 +178,8 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp);void vfio_put_group (VFIOGroup *group);int vfio_get_device (VFIOGroup *group,const char *name,VFIODevice *vbasedev,Error **errp); +bool vfio_get_info_dma_avail (struct vfio_iommu_type1_info *info, +unsigned int *avail);extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
Signature · 1 line
1.8.3.1
Re: [PATCH v3 3/5] vfio: Find DMA available capability
Quoted 10 lines · On Tue, 15 Sep 2020 15:14:41 -0400 Matthew Rosato <[email protected]>…
The underlying host may be limiting the number of outstanding DMA requests for type 1 IOMMU. Add helper functions to check for the DMA available capability and retrieve the current number of DMA mappings allowed.
Signed-off-by Matthew Rosato <[email protected]>--- hw/vfio/common.c | 31 +++++++++++++++++++++++++++++++ include/hw/vfio/vfio-common.h | 2 ++ 2 files changed, 33 insertions(+)
PATCH v3 4/5 s390x/pci: Add routine to get the vfio dma available count
In reply to Matthew RosatoCreate new files for separating out vfio-specific work for s390 pci. Add the first such routine, which issues VFIO_IOMMU_GET_INFO ioctl to collect the current dma available count.
--- hw/s390x/meson.build | 1 + hw/s390x/s390-pci-vfio.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++ hw/s390x/s390-pci-vfio.h | 17 +++++++++++++++ 3 files changed, 72 insertions(+) create mode 100644 hw/s390x/s390-pci-vfio.c create mode 100644 hw/s390x/s390-pci-vfio.h
hw/s390x/meson.build +1 -0
@@ -10,6 +10,7 @@ s390x_ss.add(files( 's390-ccw.c', 's390-pci-bus.c', 's390-pci-inst.c', + 's390-pci-vfio.c', 's390-skeys.c', 's390-stattrib.c', 's390-virtio-hcall.c',
hw/s390x/s390-pci-vfio.c new file +54 -0
54 lines not on this page · raw message
hw/s390x/s390-pci-vfio.h new file +17 -0
@@ -0,0 +1,17 @@ +/* +* s390 vfio-pci interfaces +* +* Copyright 2020 IBM Corp. +* Author(s): Matthew Rosato <[email protected]> +* +* This work is licensed under the terms of the GNU GPL, version 2 or (at +* your option) any later version. See the COPYING file in the top-level +* directory. +*/ + +#ifndef HW_S390_PCI_VFIO_H +#define HW_S390_PCI_VFIO_H + +bool s390_pci_update_dma_avail (int fd,unsigned int *avail); + +#endif
Signature · 1 line
1.8.3.1
Re: [PATCH v3 4/5] s390x/pci: Add routine to get the vfio dma available count
Quoted 63 lines · Matthew Rosato
Create new files for separating out vfio-specific work for s390 pci. Add the first such routine, which issues
VFIO_IOMMU_GET_INFOioctl to collect the current dma available count.Signed-off-by Matthew Rosato <[email protected]>--- hw/s390x/meson.build | 1 + hw/s390x/s390-pci-vfio.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++ hw/s390x/s390-pci-vfio.h | 17 +++++++++++++++ 3 files changed, 72 insertions(+) create mode 100644 hw/s390x/s390-pci-vfio.c create mode 100644 hw/s390x/s390-pci-vfio.hhw/s390x/meson.build +1
-0@@ -10,6 +10,7 @@ s390x_ss.add(files( 's390-ccw.c', 's390-pci-bus.c', 's390-pci-inst.c', + 's390-pci-vfio.c', 's390-skeys.c', 's390-stattrib.c', 's390-virtio-hcall.c',hw/s390x/s390-pci-vfio.c new file +32
-0@@ -0,0 +1,54 @@ +/* +* s390 vfio-pci interfaces +* +* Copyright 2020 IBM Corp. +* Author(s): Matthew Rosato <[email protected]> +* +* This work is licensed under the terms of the GNU GPL, version 2 or (at +* your option) any later version. See the COPYING file in the top-level +* directory. +*/ + +#include <sys/ioctl.h> + +#include "qemu/osdep.h" +#include "s390-pci-vfio.h" +#include "hw/vfio/vfio-common.h" + +/* +* Get the current DMA available count from vfio. Returns true if vfio is +* limiting DMA requests, false otherwise. The current available count read +* from vfio is returned in avail. +*/ +bool s390_pci_update_dma_avail (int fd,unsigned int *avail) +{ + g_autofree struct vfio_iommu_type1_info *info; +uint32_t argsz; +int ret; + +assert (avail); + + argsz =sizeof (struct vfio_iommu_type1_info ); + info =g_malloc0 (argsz);
hw/s390x/s390-pci-vfio.c line 42
Quoted 10 lines
hw/s390x/s390-pci-vfio.c new file +10
-0+ info->argsz = argsz; +/* +* If the specified argsz is not large enough to contain all +* capabilities it will be updated upon return. In this case +* use the updated value to get the entire capability chain. +*/ + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); +if (argsz != info->argsz) { + argsz = info->argsz; + info =g_realloc (info, argsz);
Do we need to bzero [sizeof(struct vfio_iommu_type1_info)..argsz[?
Quoted 36 lines
hw/s390x/s390-pci-vfio.c new file +12
-0+ info->argsz = argsz; + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); + } + +if (ret) { +return false; + } + +/* If the capability exists, update with the current value */ +return vfio_get_info_dma_avail (info, avail); +} +hw/s390x/s390-pci-vfio.h new file +17
-0@@ -0,0 +1,17 @@ +/* +* s390 vfio-pci interfaces +* +* Copyright 2020 IBM Corp. +* Author(s): Matthew Rosato <[email protected]> +* +* This work is licensed under the terms of the GNU GPL, version 2 or (at +* your option) any later version. See the COPYING file in the top-level +* directory. +*/ + +#ifndef HW_S390_PCI_VFIO_H +#define HW_S390_PCI_VFIO_H + +bool s390_pci_update_dma_avail (int fd,unsigned int *avail); + +#endif
Re: [PATCH v3 4/5] s390x/pci: Add routine to get the vfio dma available count
Quoted 14 lines · On Wed, 16 Sep 2020 09:21:39 +0200 Philippe Mathieu-Daudé <[email protected]>…
Quoted 13 lines · Matthew Rosato
Create new files for separating out vfio-specific work for s390 pci. Add the first such routine, which issues
VFIO_IOMMU_GET_INFOioctl to collect the current dma available count.Signed-off-by Matthew Rosato <[email protected]>--- hw/s390x/meson.build | 1 + hw/s390x/s390-pci-vfio.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++ hw/s390x/s390-pci-vfio.h | 17 +++++++++++++++ 3 files changed, 72 insertions(+) create mode 100644 hw/s390x/s390-pci-vfio.c create mode 100644 hw/s390x/s390-pci-vfio.h
(...)
Quoted 42 lines
Quoted 42 lines
hw/s390x/s390-pci-vfio.c new file +36
-0@@ -0,0 +1,54 @@ +/* +* s390 vfio-pci interfaces +* +* Copyright 2020 IBM Corp. +* Author(s): Matthew Rosato <[email protected]> +* +* This work is licensed under the terms of the GNU GPL, version 2 or (at +* your option) any later version. See the COPYING file in the top-level +* directory. +*/ + +#include <sys/ioctl.h> + +#include "qemu/osdep.h" +#include "s390-pci-vfio.h" +#include "hw/vfio/vfio-common.h" + +/* +* Get the current DMA available count from vfio. Returns true if vfio is +* limiting DMA requests, false otherwise. The current available count read +* from vfio is returned in avail. +*/ +bool s390_pci_update_dma_avail (int fd,unsigned int *avail) +{ + g_autofree struct vfio_iommu_type1_info *info; +uint32_t argsz; +int ret; + +assert (avail); + + argsz =sizeof (struct vfio_iommu_type1_info ); + info =g_malloc0 (argsz); + info->argsz = argsz; +/* +* If the specified argsz is not large enough to contain all +* capabilities it will be updated upon return. In this case
Quoted 8 lines
hw/s390x/s390-pci-vfio.c line 42
Quoted 6 lines
hw/s390x/s390-pci-vfio.c new file +6
-0+* use the updated value to get the entire capability chain. +*/ + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); +if (argsz != info->argsz) { + argsz = info->argsz; + info =g_realloc (info, argsz);Do we need to bzero [
sizeof(struct vfio_iommu_type1_info)..argsz[?
If we do, I think we need to do the equivalent invfio_get_region_info() as well?
(Also, shouldn't we check ret before looking at info->argsz?)
Quoted 13 lines
Quoted 13 lines
hw/s390x/s390-pci-vfio.c new file +12
-0+ info->argsz = argsz; + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); + } + +if (ret) { +return false; + } + +/* If the capability exists, update with the current value */ +return vfio_get_info_dma_avail (info, avail); +} +
(...)
Re: [PATCH v3 4/5] s390x/pci: Add routine to get the vfio dma available count
Quoted 71 lines · Cornelia Huck
Quoted 14 lines · On Wed, 16 Sep 2020 09:21:39 +0200 Philippe Mathieu-Daudé <[email protected]>…
Quoted 13 lines · Matthew Rosato
Create new files for separating out vfio-specific work for s390 pci. Add the first such routine, which issues
VFIO_IOMMU_GET_INFOioctl to collect the current dma available count.Signed-off-by Matthew Rosato <[email protected]>--- hw/s390x/meson.build | 1 + hw/s390x/s390-pci-vfio.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++ hw/s390x/s390-pci-vfio.h | 17 +++++++++++++++ 3 files changed, 72 insertions(+)create mode 100644
hw/s390x/s390-pci-vfio.c
create mode 100644hw/s390x/s390-pci-vfio.h(...)
Quoted 42 lines
Quoted 42 lines
hw/s390x/s390-pci-vfio.c new file +36
-0@@ -0,0 +1,54 @@ +/* +* s390 vfio-pci interfaces +* +* Copyright 2020 IBM Corp. +* Author(s): Matthew Rosato <[email protected]> +* +* This work is licensed under the terms of the GNU GPL, version 2 or (at +* your option) any later version. See the COPYING file in the top-level +* directory. +*/ + +#include <sys/ioctl.h> + +#include "qemu/osdep.h" +#include "s390-pci-vfio.h" +#include "hw/vfio/vfio-common.h" + +/* +* Get the current DMA available count from vfio. Returns true if vfio is +* limiting DMA requests, false otherwise. The current available count read +* from vfio is returned in avail. +*/ +bool s390_pci_update_dma_avail (int fd,unsigned int *avail) +{ + g_autofree struct vfio_iommu_type1_info *info; +uint32_t argsz; +int ret; + +assert (avail); + + argsz =sizeof (struct vfio_iommu_type1_info ); + info =g_malloc0 (argsz); + info->argsz = argsz; +/* +* If the specified argsz is not large enough to contain all +* capabilities it will be updated upon return. In this case Quoted 8 lines
hw/s390x/s390-pci-vfio.c line 42
Quoted 6 lines
hw/s390x/s390-pci-vfio.c new file +6
-0+* use the updated value to get the entire capability chain. +*/ + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); +if (argsz != info->argsz) { + argsz = info->argsz; + info =g_realloc (info, argsz);Do we need to bzero [
sizeof(struct vfio_iommu_type1_info)..argsz[?
Quoted 3 lines
If we do, I think we need to do the equivalent in
vfio_get_region_info()as well?
I agree that it would need to be in both places or neither -- I would expect the re-driven ioctl to overwrite the prior contents of info (unless we get a bad ret, but in this case we don't care what is in info)?
Perhaps the fundamental difference between this code and vfio_get_region_info is that the latter checks for only a growing argsz and retries, whereas this code checks for != so it's technically possible for a smaller argsz to trigger the retry here, and we wouldn't know for sure that all bytes from the first ioctl call were overwritten.
What if I adjust this code to look like vfio_get_region_info:
retry:
info->argsz = argsz;
if (ioctl(fd, VFIO_IOMMU_GET_INFO, info)) {
// no need to g_free() bc of g_autofree
return false;
}
if (info->argsz > argsz) {
argsz = info->argsz;
info = g_realloc(info, argsz);
goto retry;
}
/* If the capability exists, update with the current value */
return vfio_get_info_dma_avail(info, avail);Now we would only trigger when we are told by the host that the buffer must be larger.
Quoted 2 lines
(Also, shouldn't we check ret before looking at
info->argsz?)
Yes, you are correct. The above proposal would fix that issue too.
Quoted 17 lines
Quoted 13 lines
Quoted 13 lines
hw/s390x/s390-pci-vfio.c new file +12
-0+ info->argsz = argsz; + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); + } + +if (ret) { +return false; + } + +/* If the capability exists, update with the current value */ +return vfio_get_info_dma_avail (info, avail); +} +(...)
Re: [PATCH v3 4/5] s390x/pci: Add routine to get the vfio dma available count
Quoted 80 lines · On Wed, 16 Sep 2020 08:55:00 -0400 Matthew Rosato <[email protected]>…
Quoted 71 lines · Cornelia Huck
Quoted 14 lines · On Wed, 16 Sep 2020 09:21:39 +0200 Philippe Mathieu-Daudé <[email protected]>…
Quoted 13 lines · Matthew Rosato
Create new files for separating out vfio-specific work for s390 pci. Add the first such routine, which issues
VFIO_IOMMU_GET_INFOioctl to collect the current dma available count.Signed-off-by Matthew Rosato <[email protected]>--- hw/s390x/meson.build | 1 + hw/s390x/s390-pci-vfio.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++ hw/s390x/s390-pci-vfio.h | 17 +++++++++++++++ 3 files changed, 72 insertions(+)create mode 100644
hw/s390x/s390-pci-vfio.c
create mode 100644hw/s390x/s390-pci-vfio.h(...)
Quoted 42 lines
Quoted 42 lines
hw/s390x/s390-pci-vfio.c new file +36
-0@@ -0,0 +1,54 @@ +/* +* s390 vfio-pci interfaces +* +* Copyright 2020 IBM Corp. +* Author(s): Matthew Rosato <[email protected]> +* +* This work is licensed under the terms of the GNU GPL, version 2 or (at +* your option) any later version. See the COPYING file in the top-level +* directory. +*/ + +#include <sys/ioctl.h> + +#include "qemu/osdep.h" +#include "s390-pci-vfio.h" +#include "hw/vfio/vfio-common.h" + +/* +* Get the current DMA available count from vfio. Returns true if vfio is +* limiting DMA requests, false otherwise. The current available count read +* from vfio is returned in avail. +*/ +bool s390_pci_update_dma_avail (int fd,unsigned int *avail) +{ + g_autofree struct vfio_iommu_type1_info *info; +uint32_t argsz; +int ret; + +assert (avail); + + argsz =sizeof (struct vfio_iommu_type1_info ); + info =g_malloc0 (argsz); + info->argsz = argsz; +/* +* If the specified argsz is not large enough to contain all +* capabilities it will be updated upon return. In this case Quoted 8 lines
hw/s390x/s390-pci-vfio.c line 42
Quoted 6 lines
hw/s390x/s390-pci-vfio.c new file +6
-0+* use the updated value to get the entire capability chain. +*/ + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); +if (argsz != info->argsz) { + argsz = info->argsz; + info =g_realloc (info, argsz);Do we need to bzero [
sizeof(struct vfio_iommu_type1_info)..argsz[?Quoted 3 lines
If we do, I think we need to do the equivalent in
vfio_get_region_info()as well?I agree that it would need to be in both places or neither -- I would expect the re-driven ioctl to overwrite the prior contents of info (unless we get a bad ret, but in this case we don't care what is in info)?
Quoted 5 lines
Perhaps the fundamental difference between this code and
vfio_get_region_infois that the latter checks for only a growing argsz and retries, whereas this code checks for != so it's technically possible for a smaller argsz to trigger the retry here, and we wouldn't know for sure that all bytes from the first ioctl call were overwritten.
Nod. Relying on overwriting should be fine.
Quoted 20 lines
What if I adjust this code to look like
vfio_get_region_info:retry:
info->argsz = argsz; if (ioctl(fd, VFIO_IOMMU_GET_INFO, info)) { // no need to g_free() bc of g_autofree return false; } if (info->argsz > argsz) { argsz = info->argsz; info = g_realloc(info, argsz); goto retry; } /* If the capability exists, update with the current value */ return vfio_get_info_dma_avail(info, avail);
Quoted 2 lines
Now we would only trigger when we are told by the host that the buffer must be larger.
I think that makes sense.
Quoted 24 lines
Quoted 3 lines
(Also, shouldn't we check ret before looking at
info->argsz?)Yes, you are correct. The above proposal would fix that issue too.
Quoted 17 lines
Quoted 13 lines
Quoted 13 lines
hw/s390x/s390-pci-vfio.c new file +12
-0+ info->argsz = argsz; + ret =ioctl (fd,VFIO_IOMMU_GET_INFO , info); + } + +if (ret) { +return false; + } + +/* If the capability exists, update with the current value */ +return vfio_get_info_dma_avail (info, avail); +} +(...)
PATCH v3 5/5 s390x/pci: Honor DMA limits set by vfio
In reply to Matthew RosatoWhen an s390 guest is using lazy unmapping, it can result in a very large number of oustanding DMA requests, far beyond the default limit configured for vfio. Let's track DMA usage similar to vfio in the host, and trigger the guest to flush their DMA mappings before vfio runs out.
--- hw/s390x/s390-pci-bus.c | 56 +++++++++++++++++++++++++++++++++++++++++++----- hw/s390x/s390-pci-bus.h | 9 ++++++++ hw/s390x/s390-pci-inst.c | 34 +++++++++++++++++++++++------ hw/s390x/s390-pci-inst.h | 3 +++ 4 files changed, 91 insertions(+), 11 deletions(-)
hw/s390x/s390-pci-bus.c +51 -5
@@ -17,6 +17,7 @@#include "cpu.h" #include "s390-pci-bus.h" #include "s390-pci-inst.h" +#include "s390-pci-vfio.h" #include "hw/pci/pci_bus.h" #include "hw/qdev-properties.h" #include "hw/pci/pci_bridge.h"
@@ -24,6 +25,8 @@#include "qemu/error-report.h" #include "qemu/module.h" +#include "hw/vfio/pci.h" +#ifndef DEBUG_S390PCI_BUS #define DEBUG_S390PCI_BUS 0#endif
@@ -737,6 +740,41 @@ static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn)object_unref (OBJECT (iommu)); } +static S390PCIDMACount *s390_start_dma_count (S390pciState *s,VFIODevice *vdev) +{ +int id = vdev->group->container->fd; +S390PCIDMACount *cnt; +uint32_t avail; + +if (!s390_pci_update_dma_avail (id, &avail)) { +return NULL ; + } + + QTAILQ_FOREACH(cnt, &s->zpci_dma_limit, link) { +if (cnt->id == id) { + cnt->users++; +return cnt; + } + } + + cnt =g_new0 (S390PCIDMACount,1 ); + cnt->id = id; + cnt->users =1 ; + cnt->avail = avail; +QTAILQ_INSERT_TAIL (&s->zpci_dma_limit, cnt, link); +return cnt; +} + +static void s390_end_dma_count (S390pciState *s,S390PCIDMACount *cnt) +{ +assert (cnt); + + cnt->users--; +if (cnt->users ==0 ) { +QTAILQ_REMOVE (&s->zpci_dma_limit, cnt, link); + } +} +static void s390_pcihost_realize (DeviceState *dev,Error **errp) {PCIBus *b;
@@ -764,6 +802,7 @@ static void s390_pcihost_realize(DeviceState *dev, Error **errp) s->bus_no =0 ;QTAILQ_INIT (&s->pending_sei);QTAILQ_INIT (&s->zpci_devs); +QTAILQ_INIT (&s->zpci_dma_limit);css_register_io_adapters (CSS_IO_ADAPTER_PCI , true, false,S390_ADAPTER_SUPPRESSIBLE , errp);
@@ -902,6 +941,7 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, {S390pciState *s =S390_PCI_HOST_BRIDGE (hotplug_dev);PCIDevice *pdev =NULL ; +VFIOPCIDevice *vpdev =NULL ;S390PCIBusDevice *pbdev =NULL ;if (object_dynamic_cast (OBJECT (dev),TYPE_PCI_BRIDGE )) {
@@ -941,17 +981,20 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, } } + pbdev->pdev = pdev; + pbdev->iommu =s390_pci_get_iommu (s,pci_get_bus (pdev), pdev->devfn); + pbdev->iommu->pbdev = pbdev; + pbdev->state =ZPCI_FS_DISABLED ; +if (object_dynamic_cast (OBJECT (dev),"vfio-pci" )) { pbdev->fh |=FH_SHM_VFIO ; + vpdev =container_of (pbdev->pdev, VFIOPCIDevice, pdev); + pbdev->iommu->dma_limit =s390_start_dma_count (s, + &vpdev->vbasedev); }else { pbdev->fh |=FH_SHM_EMUL ; } - pbdev->pdev = pdev; - pbdev->iommu =s390_pci_get_iommu (s,pci_get_bus (pdev), pdev->devfn); - pbdev->iommu->pbdev = pbdev; - pbdev->state =ZPCI_FS_DISABLED ; -if (s390_pci_msix_init (pbdev)) {error_setg (errp,"MSI-X support is mandatory " "in the S390 architecture" );
@@ -1004,6 +1047,9 @@ static void s390_pcihost_unplug(HotplugHandler *hotplug_dev, DeviceState *dev, pbdev->fid =0 ;QTAILQ_REMOVE (&s->zpci_devs, pbdev, link);g_hash_table_remove (s->zpci_table, &pbdev->idx); +if (pbdev->iommu->dma_limit) { +s390_end_dma_count (s, pbdev->iommu->dma_limit); + }qdev_unrealize (dev); } }
hw/s390x/s390-pci-bus.h +9 -0
@@ -270,6 +270,13 @@ typedef struct S390IOTLBEntry {uint64_t perm; } S390IOTLBEntry; +typedef struct S390PCIDMACount { +int id; +int users; +uint32_t avail; +QTAILQ_ENTRY (S390PCIDMACount) link; +}S390PCIDMACount ; +struct S390PCIIOMMU {Object parent_obj;S390PCIBusDevice *pbdev;
@@ -281,6 +288,7 @@ struct S390PCIIOMMU {uint64_t pba;uint64_t pal;GHashTable *iotlb; +S390PCIDMACount *dma_limit; }; typedef struct S390PCIIOMMUTable {
@@ -356,6 +364,7 @@ struct S390pciState {GHashTable *zpci_table; QTAILQ_HEAD(, SeiContainer) pending_sei; QTAILQ_HEAD(, S390PCIBusDevice) zpci_devs; + QTAILQ_HEAD(, S390PCIDMACount) zpci_dma_limit; };S390pciState *s390_get_phb (void );
hw/s390x/s390-pci-inst.c +28 -6
@@ -32,6 +32,9 @@ } \ } while (0) +#define inc_dma_avail (iommu) if (iommu->dma_limit) iommu->dma_limit->avail++; +#define dec_dma_avail (iommu) if (iommu->dma_limit) iommu->dma_limit->avail--; +static void s390_set_status_code (CPUS390XState *env,uint8_t r,uint64_t status_code) {
@@ -572,7 +575,8 @@ int pcistg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)return 0 ; } -static void s390_pci_update_iotlb (S390PCIIOMMU *iommu,S390IOTLBEntry *entry) +static uint32_t s390_pci_update_iotlb (S390PCIIOMMU *iommu, +S390IOTLBEntry *entry) {S390IOTLBEntry *cache =g_hash_table_lookup (iommu->iotlb, &entry->iova);IOMMUTLBEntry notify = {
@@ -585,14 +589,15 @@ static void s390_pci_update_iotlb(S390PCIIOMMU *iommu, S390IOTLBEntry *entry)if (entry->perm ==IOMMU_NONE ) {if (!cache) { -return ; + goto out; }g_hash_table_remove (iommu->iotlb, &entry->iova); +inc_dma_avail (iommu); }else {if (cache) {if (cache->perm == entry->perm && cache->translated_addr == entry->translated_addr) { -return ; + goto out; } notify.perm =IOMMU_NONE ;
@@ -606,9 +611,13 @@ static void s390_pci_update_iotlb(S390PCIIOMMU *iommu, S390IOTLBEntry *entry) cache->len =PAGE_SIZE ; cache->perm = entry->perm;g_hash_table_replace (iommu->iotlb, &cache->iova, cache); +dec_dma_avail (iommu); }memory_region_notify_iommu (&iommu->iommu_mr,0 , notify); + +out: +return iommu->dma_limit ? iommu->dma_limit->avail :1 ; }int rpcit_service_call (S390CPU *cpu,uint8_t r1,uint8_t r2,uintptr_t ra)
@@ -620,6 +629,7 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra)S390PCIIOMMU *iommu;S390IOTLBEntry entry;hwaddr start, end; +uint32_t dma_avail;if (env->psw.mask &PSW_MASK_PSTATE ) {s390_program_interrupt (env,PGM_PRIVILEGED , ra);
@@ -658,6 +668,11 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) } iommu = pbdev->iommu; +if (iommu->dma_limit) { + dma_avail = iommu->dma_limit->avail; + }else { + dma_avail =1 ; + }if (!iommu->g_iota) { error =ERR_EVENT_INVALAS ; goto err;
@@ -675,8 +690,9 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) } start += entry.len; -while (entry.iova < start && entry.iova < end) { -s390_pci_update_iotlb (iommu, &entry); +while (entry.iova < start && entry.iova < end && + (dma_avail >0 || entry.perm ==IOMMU_NONE )) { + dma_avail =s390_pci_update_iotlb (iommu, &entry); entry.iova +=PAGE_SIZE ; entry.translated_addr +=PAGE_SIZE ; }
@@ -689,7 +705,13 @@ err:s390_pci_generate_error_event (error, pbdev->fh, pbdev->fid, start,0 ); }else { pbdev->fmb.counter[ZPCI_FMB_CNT_RPCIT ]++; -setcc (cpu,ZPCI_PCI_LS_OK ); +if (dma_avail >0 ) { +setcc (cpu,ZPCI_PCI_LS_OK ); + }else { +/* vfio DMA mappings are exhausted, trigger a RPCIT */ +setcc (cpu,ZPCI_PCI_LS_ERR ); +s390_set_status_code (env, r1,ZPCI_RPCIT_ST_INSUFF_RES ); + } }return 0 ; }
hw/s390x/s390-pci-inst.h +3 -0
@@ -254,6 +254,9 @@ typedef struct ClpReqRspQueryPciGrp {#define ZPCI_STPCIFC_ST_INVAL_DMAAS 28#define ZPCI_STPCIFC_ST_ERROR_RECOVER 40 +/* Refresh PCI Translations status codes */ +#define ZPCI_RPCIT_ST_INSUFF_RES 16 +/* FIB function controls */ #define ZPCI_FIB_FC_ENABLED 0x80#define ZPCI_FIB_FC_ERROR 0x40
Signature · 1 line
1.8.3.1
Re: [PATCH v3 5/5] s390x/pci: Honor DMA limits set by vfio
Quoted 13 lines · On Tue, 15 Sep 2020 15:14:43 -0400 Matthew Rosato <[email protected]>…
When an s390 guest is using lazy unmapping, it can result in a very large number of oustanding DMA requests, far beyond the default limit configured for vfio. Let's track DMA usage similar to vfio in the host, and trigger the guest to flush their DMA mappings before vfio runs out.
Signed-off-by Matthew Rosato <[email protected]>--- hw/s390x/s390-pci-bus.c | 56 +++++++++++++++++++++++++++++++++++++++++++----- hw/s390x/s390-pci-bus.h | 9 ++++++++ hw/s390x/s390-pci-inst.c | 34 +++++++++++++++++++++++------ hw/s390x/s390-pci-inst.h | 3 +++ 4 files changed, 91 insertions(+), 11 deletions(-)
(...)
hw/s390x/s390-pci-bus.c static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn) · line 743
Quoted 5 lines
hw/s390x/s390-pci-bus.c +1
-0@@ -737,6 +740,41 @@ static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn)object_unref (OBJECT (iommu)); } +static S390PCIDMACount *s390_start_dma_count (S390pciState *s,VFIODevice *vdev)
Should these go into the new vfio-related file?
Quoted 57 lines
hw/s390x/s390-pci-bus.c +36
-0+{ +int id = vdev->group->container->fd; +S390PCIDMACount *cnt; +uint32_t avail; + +if (!s390_pci_update_dma_avail (id, &avail)) { +return NULL ; + } + + QTAILQ_FOREACH(cnt, &s->zpci_dma_limit, link) { +if (cnt->id == id) { + cnt->users++; +return cnt; + } + } + + cnt =g_new0 (S390PCIDMACount,1 ); + cnt->id = id; + cnt->users =1 ; + cnt->avail = avail; +QTAILQ_INSERT_TAIL (&s->zpci_dma_limit, cnt, link); +return cnt; +} + +static void s390_end_dma_count (S390pciState *s,S390PCIDMACount *cnt) +{ +assert (cnt); + + cnt->users--; +if (cnt->users ==0 ) { +QTAILQ_REMOVE (&s->zpci_dma_limit, cnt, link); + } +} +static void s390_pcihost_realize (DeviceState *dev,Error **errp) {PCIBus *b;@@ -764,6 +802,7 @@ static void s390_pcihost_realize(DeviceState *dev, Error **errp) s->bus_no =0 ;QTAILQ_INIT (&s->pending_sei);QTAILQ_INIT (&s->zpci_devs); +QTAILQ_INIT (&s->zpci_dma_limit);css_register_io_adapters (CSS_IO_ADAPTER_PCI , true, false,S390_ADAPTER_SUPPRESSIBLE , errp);@@ -902,6 +941,7 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, {S390pciState *s =S390_PCI_HOST_BRIDGE (hotplug_dev);PCIDevice *pdev =NULL ; +VFIOPCIDevice *vpdev =NULL ;S390PCIBusDevice *pbdev =NULL ;if (object_dynamic_cast (OBJECT (dev),TYPE_PCI_BRIDGE )) {@@ -941,17 +981,20 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, } }
hw/s390x/s390-pci-bus.c static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, · line 993
Quoted 10 lines
hw/s390x/s390-pci-bus.c +8
-0+ pbdev->pdev = pdev; + pbdev->iommu =s390_pci_get_iommu (s,pci_get_bus (pdev), pdev->devfn); + pbdev->iommu->pbdev = pbdev; + pbdev->state =ZPCI_FS_DISABLED ; +if (object_dynamic_cast (OBJECT (dev),"vfio-pci" )) { pbdev->fh |=FH_SHM_VFIO ; + vpdev =container_of (pbdev->pdev, VFIOPCIDevice, pdev); + pbdev->iommu->dma_limit =s390_start_dma_count (s, + &vpdev->vbasedev);
I think you can just pass s and pbdev to that function... that would move dealing with vfio specifics from this file.
Quoted 12 lines
hw/s390x/s390-pci-bus.c +0
-5}else { pbdev->fh |=FH_SHM_EMUL ; } - pbdev->pdev = pdev; - pbdev->iommu =s390_pci_get_iommu (s,pci_get_bus (pdev), pdev->devfn); - pbdev->iommu->pbdev = pbdev; - pbdev->state =ZPCI_FS_DISABLED ; -if (s390_pci_msix_init (pbdev)) {error_setg (errp,"MSI-X support is mandatory " "in the S390 architecture" );
(...)
hw/s390x/s390-pci-inst.c line 35
Quoted 9 lines
hw/s390x/s390-pci-inst.c +1
-0@@ -32,6 +32,9 @@ } \ } while (0) +#define inc_dma_avail (iommu) if (iommu->dma_limit) iommu->dma_limit->avail++;
I was thinking more of something like
static inline void inc_dma_avail(S390PCIIOMMU *iommu)
{
if (iommu->dma_limit) {
iommu->dma_limit->avail++;
}
}Quoted 5 lines
hw/s390x/s390-pci-inst.c +2
-0+#define dec_dma_avail (iommu) if (iommu->dma_limit) iommu->dma_limit->avail--; +static void s390_set_status_code (CPUS390XState *env,uint8_t r,uint64_t status_code) {
(...)
Re: [PATCH v3 5/5] s390x/pci: Honor DMA limits set by vfio
Quoted 84 lines · Cornelia Huck
Quoted 13 lines · On Tue, 15 Sep 2020 15:14:43 -0400 Matthew Rosato <[email protected]>…
When an s390 guest is using lazy unmapping, it can result in a very large number of oustanding DMA requests, far beyond the default limit configured for vfio. Let's track DMA usage similar to vfio in the host, and trigger the guest to flush their DMA mappings before vfio runs out.
Signed-off-by Matthew Rosato <[email protected]>--- hw/s390x/s390-pci-bus.c | 56 +++++++++++++++++++++++++++++++++++++++++++----- hw/s390x/s390-pci-bus.h | 9 ++++++++ hw/s390x/s390-pci-inst.c | 34 +++++++++++++++++++++++------ hw/s390x/s390-pci-inst.h | 3 +++ 4 files changed, 91 insertions(+), 11 deletions(-)(...)
hw/s390x/s390-pci-bus.c static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn) · line 743
Quoted 5 lines
hw/s390x/s390-pci-bus.c +1
-0@@ -737,6 +740,41 @@ static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn)object_unref (OBJECT (iommu)); } +static S390PCIDMACount *s390_start_dma_count (S390pciState *s,VFIODevice *vdev)Should these go into the new vfio-related file?
Quoted 57 lines
hw/s390x/s390-pci-bus.c +36
-0+{ +int id = vdev->group->container->fd; +S390PCIDMACount *cnt; +uint32_t avail; + +if (!s390_pci_update_dma_avail (id, &avail)) { +return NULL ; + } + + QTAILQ_FOREACH(cnt, &s->zpci_dma_limit, link) { +if (cnt->id == id) { + cnt->users++; +return cnt; + } + } + + cnt =g_new0 (S390PCIDMACount,1 ); + cnt->id = id; + cnt->users =1 ; + cnt->avail = avail; +QTAILQ_INSERT_TAIL (&s->zpci_dma_limit, cnt, link); +return cnt; +} + +static void s390_end_dma_count (S390pciState *s,S390PCIDMACount *cnt) +{ +assert (cnt); + + cnt->users--; +if (cnt->users ==0 ) { +QTAILQ_REMOVE (&s->zpci_dma_limit, cnt, link); + } +} +static void s390_pcihost_realize (DeviceState *dev,Error **errp) {PCIBus *b;@@ -764,6 +802,7 @@ static void s390_pcihost_realize(DeviceState *dev, Error **errp) s->bus_no =0 ;QTAILQ_INIT (&s->pending_sei);QTAILQ_INIT (&s->zpci_devs); +QTAILQ_INIT (&s->zpci_dma_limit);css_register_io_adapters (CSS_IO_ADAPTER_PCI , true, false,S390_ADAPTER_SUPPRESSIBLE , errp);@@ -902,6 +941,7 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, {S390pciState *s =S390_PCI_HOST_BRIDGE (hotplug_dev);PCIDevice *pdev =NULL ; +VFIOPCIDevice *vpdev =NULL ;S390PCIBusDevice *pbdev =NULL ;if (object_dynamic_cast (OBJECT (dev),TYPE_PCI_BRIDGE )) {@@ -941,17 +981,20 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, } }
Quoted 13 lines
hw/s390x/s390-pci-bus.c static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, · line 993
Quoted 10 lines
hw/s390x/s390-pci-bus.c +8
-0+ pbdev->pdev = pdev; + pbdev->iommu =s390_pci_get_iommu (s,pci_get_bus (pdev), pdev->devfn); + pbdev->iommu->pbdev = pbdev; + pbdev->state =ZPCI_FS_DISABLED ; +if (object_dynamic_cast (OBJECT (dev),"vfio-pci" )) { pbdev->fh |=FH_SHM_VFIO ; + vpdev =container_of (pbdev->pdev, VFIOPCIDevice, pdev); + pbdev->iommu->dma_limit =s390_start_dma_count (s, + &vpdev->vbasedev);I think you can just pass s and pbdev to that function... that would move dealing with vfio specifics from this file.
I had considered this as well, should have went with my gut -- I'll move them.
Quoted 28 lines
Quoted 13 lines
hw/s390x/s390-pci-bus.c +0
-5}else { pbdev->fh |=FH_SHM_EMUL ; } - pbdev->pdev = pdev; - pbdev->iommu =s390_pci_get_iommu (s,pci_get_bus (pdev), pdev->devfn); - pbdev->iommu->pbdev = pbdev; - pbdev->state =ZPCI_FS_DISABLED ; -if (s390_pci_msix_init (pbdev)) {error_setg (errp,"MSI-X support is mandatory " "in the S390 architecture" );(...)
hw/s390x/s390-pci-inst.c line 35
Quoted 9 lines
hw/s390x/s390-pci-inst.c +1
-0@@ -32,6 +32,9 @@ } \ } while (0) +#define inc_dma_avail (iommu) if (iommu->dma_limit) iommu->dma_limit->avail++;I was thinking more of something like
Quoted 7 lines
static inline void
inc_dma_avail(S390PCIIOMMU *iommu){ if (iommu->dma_limit) { iommu->dma_limit->avail++; } }
Ah, I read the 'lowercase' and missed the 'inline function' part of your previous comment, sorry. Will change.
Quoted 8 lines
Quoted 5 lines
hw/s390x/s390-pci-inst.c +2
-0+#define dec_dma_avail (iommu) if (iommu->dma_limit) iommu->dma_limit->avail--; +static void s390_set_status_code (CPUS390XState *env,uint8_t r,uint64_t status_code) {(...)