* [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions
@ 2026-01-21 11:41 Shameer Kolothum
2026-01-21 11:41 ` [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 Shameer Kolothum
` (4 more replies)
0 siblings, 5 replies; 16+ messages in thread
From: Shameer Kolothum @ 2026-01-21 11:41 UTC (permalink / raw)
To: qemu-arm, qemu-devel
Cc: eric.auger, alex, clg, cohuck, mst, nicolinc, nathanc, mochs, jgg,
jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju
Hi,
Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for P2P
use cases. This adds support for vfio devices to create a dmabuf for
each mapped BAR region.
Changes from v3:
https://lore.kernel.org/qemu-devel/20260116092950.15796-1-skolothumtho@nvidia.com/
- Folded in patch #2 to linux-headers update to avoid bisect failure
due to build error.
The dmabuf support was sanity tested on an NVIDIA grace paltform.
Please take a look and let me know.
Thanks,
Shameer
Nicolin Chen (1):
hw/vfio/region: Create dmabuf for PCI BAR per region
Shameer Kolothum (2):
linux-headers: Update to Linux v6.19-rc1
hw/vfio: Add helper to retrieve device feature
hw/net/virtio-net.c | 11 +-
hw/vfio/container.c | 2 +-
hw/vfio/device.c | 9 ++
hw/vfio/listener.c | 4 +-
hw/vfio/region.c | 65 +++++++++-
hw/vfio/trace-events | 1 +
include/hw/vfio/vfio-device.h | 3 +
include/standard-headers/drm/drm_fourcc.h | 25 ++--
include/standard-headers/linux/ethtool.h | 5 +
.../linux/input-event-codes.h | 14 ++-
include/standard-headers/linux/pci_regs.h | 89 ++++++++++++++
include/standard-headers/linux/virtio_net.h | 3 +-
include/standard-headers/linux/virtio_pci.h | 2 +-
linux-headers/asm-arm64/kvm.h | 2 +-
linux-headers/asm-arm64/unistd_64.h | 1 +
linux-headers/asm-generic/unistd.h | 4 +-
linux-headers/asm-loongarch/kvm.h | 1 +
linux-headers/asm-loongarch/unistd.h | 6 +
linux-headers/asm-loongarch/unistd_64.h | 1 +
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/unistd_32.h | 1 +
linux-headers/asm-powerpc/unistd_64.h | 1 +
linux-headers/asm-riscv/kvm.h | 3 +
linux-headers/asm-riscv/unistd_32.h | 1 +
linux-headers/asm-riscv/unistd_64.h | 1 +
linux-headers/asm-s390/bitsperlong.h | 4 -
linux-headers/asm-s390/unistd.h | 4 -
linux-headers/asm-s390/unistd_64.h | 9 +-
linux-headers/asm-x86/kvm.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/iommufd.h | 10 ++
linux-headers/linux/kvm.h | 11 ++
linux-headers/linux/mshv.h | 116 +++++++++++++++++-
linux-headers/linux/psp-sev.h | 66 ++++++----
linux-headers/linux/vfio.h | 28 +++++
39 files changed, 450 insertions(+), 60 deletions(-)
--
2.43.0
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 2026-01-21 11:41 [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Shameer Kolothum @ 2026-01-21 11:41 ` Shameer Kolothum 2026-01-21 14:00 ` Cédric Le Goater 2026-01-21 11:41 ` [PATCH v4 2/3] hw/vfio: Add helper to retrieve device feature Shameer Kolothum ` (3 subsequent siblings) 4 siblings, 1 reply; 16+ messages in thread From: Shameer Kolothum @ 2026-01-21 11:41 UTC (permalink / raw) To: qemu-arm, qemu-devel Cc: eric.auger, alex, clg, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, Jason Wang Mainly for adding support for VFIO DMABUF. While at it, update all headers. The header update breaks virtio-net due to virtio_net_hdr_v1_hash changes. Include the virtio-net changes to avoid build and bisect failures. Cc: Michael S. Tsirkin <mst@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Tested-by: Nicolin Chen <nicolinc@nvidia.com> Reviewed-by: Cédric Le Goater <clg@redhat.com> Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> --- hw/net/virtio-net.c | 11 +- include/standard-headers/drm/drm_fourcc.h | 25 ++-- include/standard-headers/linux/ethtool.h | 5 + .../linux/input-event-codes.h | 14 ++- include/standard-headers/linux/pci_regs.h | 89 ++++++++++++++ include/standard-headers/linux/virtio_net.h | 3 +- include/standard-headers/linux/virtio_pci.h | 2 +- linux-headers/asm-arm64/kvm.h | 2 +- linux-headers/asm-arm64/unistd_64.h | 1 + linux-headers/asm-generic/unistd.h | 4 +- linux-headers/asm-loongarch/kvm.h | 1 + linux-headers/asm-loongarch/unistd.h | 6 + linux-headers/asm-loongarch/unistd_64.h | 1 + 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/unistd_32.h | 1 + linux-headers/asm-powerpc/unistd_64.h | 1 + linux-headers/asm-riscv/kvm.h | 3 + linux-headers/asm-riscv/unistd_32.h | 1 + linux-headers/asm-riscv/unistd_64.h | 1 + linux-headers/asm-s390/bitsperlong.h | 4 - linux-headers/asm-s390/unistd.h | 4 - linux-headers/asm-s390/unistd_64.h | 9 +- linux-headers/asm-x86/kvm.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/iommufd.h | 10 ++ linux-headers/linux/kvm.h | 11 ++ linux-headers/linux/mshv.h | 116 +++++++++++++++++- linux-headers/linux/psp-sev.h | 66 ++++++---- linux-headers/linux/vfio.h | 28 +++++ 33 files changed, 370 insertions(+), 56 deletions(-) diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index 317f1ad23b..512a7c02c9 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -1879,7 +1879,8 @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf, n->rss_data.runtime_hash_types); if (net_hash_type > NetPktRssIpV6UdpEx) { if (n->rss_data.populate_hash) { - hdr->hash_value = VIRTIO_NET_HASH_REPORT_NONE; + hdr->hash_value_lo = VIRTIO_NET_HASH_REPORT_NONE; + hdr->hash_value_hi = VIRTIO_NET_HASH_REPORT_NONE; hdr->hash_report = 0; } return n->rss_data.redirect ? n->rss_data.default_queue : -1; @@ -1888,7 +1889,8 @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf, hash = net_rx_pkt_calc_rss_hash(pkt, net_hash_type, n->rss_data.key); if (n->rss_data.populate_hash) { - hdr->hash_value = hash; + hdr->hash_value_lo = cpu_to_le16(hash & 0xffff); + hdr->hash_value_hi = cpu_to_le16((hash >> 16) & 0xffff); hdr->hash_report = reports[net_hash_type]; } @@ -1990,10 +1992,11 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, receive_header(n, sg, elem->in_num, buf, size); if (n->rss_data.populate_hash) { - offset = offsetof(typeof(extra_hdr), hash_value); + offset = offsetof(typeof(extra_hdr), hash_value_lo); iov_from_buf(sg, elem->in_num, offset, (char *)&extra_hdr + offset, - sizeof(extra_hdr.hash_value) + + sizeof(extra_hdr.hash_value_lo) + + sizeof(extra_hdr.hash_value_hi) + sizeof(extra_hdr.hash_report)); } offset = n->host_hdr_len; diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index cef077dfb3..b39e197cc7 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -978,14 +978,20 @@ extern "C" { * 2 = Gob Height 8, Turing+ Page Kind mapping * 3 = Reserved for future use. * - * 22:22 s Sector layout. On Tegra GPUs prior to Xavier, there is a further - * bit remapping step that occurs at an even lower level than the - * page kind and block linear swizzles. This causes the layout of - * surfaces mapped in those SOC's GPUs to be incompatible with the - * equivalent mapping on other GPUs in the same system. - * - * 0 = Tegra K1 - Tegra Parker/TX2 Layout. - * 1 = Desktop GPU and Tegra Xavier+ Layout + * 22:22 s Sector layout. There is a further bit remapping step that occurs + * 26:27 at an even lower level than the page kind and block linear + * swizzles. This causes the bit arrangement of surfaces in memory + * to differ subtly, and prevents direct sharing of surfaces between + * GPUs with different layouts. + * + * 0 = Tegra K1 - Tegra Parker/TX2 Layout + * 1 = Pre-GB20x, GB20x 32+ bpp, GB10, Tegra Xavier-Orin Layout + * 2 = GB20x(Blackwell 2)+ 8 bpp surface layout + * 3 = GB20x(Blackwell 2)+ 16 bpp surface layout + * 4 = Reserved for future use. + * 5 = Reserved for future use. + * 6 = Reserved for future use. + * 7 = Reserved for future use. * * 25:23 c Lossless Framebuffer Compression type. * @@ -1000,7 +1006,7 @@ extern "C" { * 6 = Reserved for future use * 7 = Reserved for future use * - * 55:25 - Reserved for future use. Must be zero. + * 55:28 - Reserved for future use. Must be zero. */ #define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \ fourcc_mod_code(NVIDIA, (0x10 | \ @@ -1008,6 +1014,7 @@ extern "C" { (((k) & 0xff) << 12) | \ (((g) & 0x3) << 20) | \ (((s) & 0x1) << 22) | \ + (((s) & 0x6) << 25) | \ (((c) & 0x7) << 23))) /* To grandfather in prior block linear format modifiers to the above layout, diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index dc24512d28..d0f7a63f10 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -2077,6 +2077,10 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT = 118, ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT = 119, ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT = 120, + ETHTOOL_LINK_MODE_1600000baseCR8_Full_BIT = 121, + ETHTOOL_LINK_MODE_1600000baseKR8_Full_BIT = 122, + ETHTOOL_LINK_MODE_1600000baseDR8_Full_BIT = 123, + ETHTOOL_LINK_MODE_1600000baseDR8_2_Full_BIT = 124, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS @@ -2190,6 +2194,7 @@ enum ethtool_link_mode_bit_indices { #define SPEED_200000 200000 #define SPEED_400000 400000 #define SPEED_800000 800000 +#define SPEED_1600000 1600000 #define SPEED_UNKNOWN -1 diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index c914ccd723..ede79c6ae4 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -27,7 +27,7 @@ #define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ #define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ #define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ -#define INPUT_PROP_HAPTIC_TOUCHPAD 0x07 /* is a haptic touchpad */ +#define INPUT_PROP_PRESSUREPAD 0x07 /* pressure triggers clicks */ #define INPUT_PROP_MAX 0x1f #define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) @@ -631,6 +631,18 @@ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ +/* + * Keycodes for hotkeys toggling the electronic privacy screen found on some + * laptops on/off. Note when the embedded-controller turns on/off the eprivacy + * screen itself then the state should be reported through drm connecter props: + * https://www.kernel.org/doc/html/latest/gpu/drm-kms.html#standard-connector-properties + * Except when implementing the drm connecter properties API is not possible + * because e.g. the firmware does not allow querying the presence and/or status + * of the eprivacy screen at boot. + */ +#define KEY_EPRIVACY_SCREEN_ON 0x252 +#define KEY_EPRIVACY_SCREEN_OFF 0x253 + #define KEY_KBDINPUTASSIST_PREV 0x260 #define KEY_KBDINPUTASSIST_NEXT 0x261 #define KEY_KBDINPUTASSIST_PREVGROUP 0x262 diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index 07e06aafec..3add74ae25 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -503,6 +503,7 @@ #define PCI_EXP_DEVCAP_PWR_VAL 0x03fc0000 /* Slot Power Limit Value */ #define PCI_EXP_DEVCAP_PWR_SCL 0x0c000000 /* Slot Power Limit Scale */ #define PCI_EXP_DEVCAP_FLR 0x10000000 /* Function Level Reset */ +#define PCI_EXP_DEVCAP_TEE 0x40000000 /* TEE I/O (TDISP) Support */ #define PCI_EXP_DEVCTL 0x08 /* Device Control */ #define PCI_EXP_DEVCTL_CERE 0x0001 /* Correctable Error Reporting En. */ #define PCI_EXP_DEVCTL_NFERE 0x0002 /* Non-Fatal Error Reporting Enable */ @@ -754,6 +755,8 @@ #define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ +#define PCI_EXT_CAP_ID_DEV3 0x2F /* Device 3 Capability/Control/Status */ +#define PCI_EXT_CAP_ID_IDE 0x30 /* Integrity and Data Encryption */ #define PCI_EXT_CAP_ID_PL_64GT 0x31 /* Physical Layer 64.0 GT/s */ #define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_64GT @@ -1244,9 +1247,95 @@ /* Deprecated old name, replaced with PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE */ #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE +/* Device 3 Extended Capability */ +#define PCI_DEV3_CAP 0x04 /* Device 3 Capabilities Register */ +#define PCI_DEV3_CTL 0x08 /* Device 3 Control Register */ +#define PCI_DEV3_STA 0x0c /* Device 3 Status Register */ +#define PCI_DEV3_STA_SEGMENT 0x8 /* Segment Captured (end-to-end flit-mode detected) */ + /* Compute Express Link (CXL r3.1, sec 8.1.5) */ #define PCI_DVSEC_CXL_PORT 3 #define PCI_DVSEC_CXL_PORT_CTL 0x0c #define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 +/* Integrity and Data Encryption Extended Capability */ +#define PCI_IDE_CAP 0x04 +#define PCI_IDE_CAP_LINK 0x1 /* Link IDE Stream Supported */ +#define PCI_IDE_CAP_SELECTIVE 0x2 /* Selective IDE Streams Supported */ +#define PCI_IDE_CAP_FLOWTHROUGH 0x4 /* Flow-Through IDE Stream Supported */ +#define PCI_IDE_CAP_PARTIAL_HEADER_ENC 0x8 /* Partial Header Encryption Supported */ +#define PCI_IDE_CAP_AGGREGATION 0x10 /* Aggregation Supported */ +#define PCI_IDE_CAP_PCRC 0x20 /* PCRC Supported */ +#define PCI_IDE_CAP_IDE_KM 0x40 /* IDE_KM Protocol Supported */ +#define PCI_IDE_CAP_SEL_CFG 0x80 /* Selective IDE for Config Request Support */ +#define PCI_IDE_CAP_ALG __GENMASK(12, 8) /* Supported Algorithms */ +#define PCI_IDE_CAP_ALG_AES_GCM_256 0 /* AES-GCM 256 key size, 96b MAC */ +#define PCI_IDE_CAP_LINK_TC_NUM __GENMASK(15, 13) /* Link IDE TCs */ +#define PCI_IDE_CAP_SEL_NUM __GENMASK(23, 16) /* Supported Selective IDE Streams */ +#define PCI_IDE_CAP_TEE_LIMITED 0x1000000 /* TEE-Limited Stream Supported */ +#define PCI_IDE_CTL 0x08 +#define PCI_IDE_CTL_FLOWTHROUGH_IDE 0x4 /* Flow-Through IDE Stream Enabled */ + +#define PCI_IDE_LINK_STREAM_0 0xc /* First Link Stream Register Block */ +#define PCI_IDE_LINK_BLOCK_SIZE 8 +/* Link IDE Stream block, up to PCI_IDE_CAP_LINK_TC_NUM */ +#define PCI_IDE_LINK_CTL_0 0x00 /* First Link Control Register Offset in block */ +#define PCI_IDE_LINK_CTL_EN 0x1 /* Link IDE Stream Enable */ +#define PCI_IDE_LINK_CTL_TX_AGGR_NPR __GENMASK(3, 2) /* Tx Aggregation Mode NPR */ +#define PCI_IDE_LINK_CTL_TX_AGGR_PR __GENMASK(5, 4) /* Tx Aggregation Mode PR */ +#define PCI_IDE_LINK_CTL_TX_AGGR_CPL __GENMASK(7, 6) /* Tx Aggregation Mode CPL */ +#define PCI_IDE_LINK_CTL_PCRC_EN 0x100 /* PCRC Enable */ +#define PCI_IDE_LINK_CTL_PART_ENC __GENMASK(13, 10) /* Partial Header Encryption Mode */ +#define PCI_IDE_LINK_CTL_ALG __GENMASK(18, 14) /* Selection from PCI_IDE_CAP_ALG */ +#define PCI_IDE_LINK_CTL_TC __GENMASK(21, 19) /* Traffic Class */ +#define PCI_IDE_LINK_CTL_ID __GENMASK(31, 24) /* Stream ID */ +#define PCI_IDE_LINK_STS_0 0x4 /* First Link Status Register Offset in block */ +#define PCI_IDE_LINK_STS_STATE __GENMASK(3, 0) /* Link IDE Stream State */ +#define PCI_IDE_LINK_STS_IDE_FAIL 0x80000000 /* IDE fail message received */ + +/* Selective IDE Stream block, up to PCI_IDE_CAP_SELECTIVE_STREAMS_NUM */ +/* Selective IDE Stream Capability Register */ +#define PCI_IDE_SEL_CAP 0x00 +#define PCI_IDE_SEL_CAP_ASSOC_NUM __GENMASK(3, 0) +/* Selective IDE Stream Control Register */ +#define PCI_IDE_SEL_CTL 0x04 +#define PCI_IDE_SEL_CTL_EN 0x1 /* Selective IDE Stream Enable */ +#define PCI_IDE_SEL_CTL_TX_AGGR_NPR __GENMASK(3, 2) /* Tx Aggregation Mode NPR */ +#define PCI_IDE_SEL_CTL_TX_AGGR_PR __GENMASK(5, 4) /* Tx Aggregation Mode PR */ +#define PCI_IDE_SEL_CTL_TX_AGGR_CPL __GENMASK(7, 6) /* Tx Aggregation Mode CPL */ +#define PCI_IDE_SEL_CTL_PCRC_EN 0x100 /* PCRC Enable */ +#define PCI_IDE_SEL_CTL_CFG_EN 0x200 /* Selective IDE for Configuration Requests */ +#define PCI_IDE_SEL_CTL_PART_ENC __GENMASK(13, 10) /* Partial Header Encryption Mode */ +#define PCI_IDE_SEL_CTL_ALG __GENMASK(18, 14) /* Selection from PCI_IDE_CAP_ALG */ +#define PCI_IDE_SEL_CTL_TC __GENMASK(21, 19) /* Traffic Class */ +#define PCI_IDE_SEL_CTL_DEFAULT 0x400000 /* Default Stream */ +#define PCI_IDE_SEL_CTL_TEE_LIMITED 0x800000 /* TEE-Limited Stream */ +#define PCI_IDE_SEL_CTL_ID __GENMASK(31, 24) /* Stream ID */ +#define PCI_IDE_SEL_CTL_ID_MAX 255 +/* Selective IDE Stream Status Register */ +#define PCI_IDE_SEL_STS 0x08 +#define PCI_IDE_SEL_STS_STATE __GENMASK(3, 0) /* Selective IDE Stream State */ +#define PCI_IDE_SEL_STS_STATE_INSECURE 0 +#define PCI_IDE_SEL_STS_STATE_SECURE 2 +#define PCI_IDE_SEL_STS_IDE_FAIL 0x80000000 /* IDE fail message received */ +/* IDE RID Association Register 1 */ +#define PCI_IDE_SEL_RID_1 0x0c +#define PCI_IDE_SEL_RID_1_LIMIT __GENMASK(23, 8) +/* IDE RID Association Register 2 */ +#define PCI_IDE_SEL_RID_2 0x10 +#define PCI_IDE_SEL_RID_2_VALID 0x1 +#define PCI_IDE_SEL_RID_2_BASE __GENMASK(23, 8) +#define PCI_IDE_SEL_RID_2_SEG __GENMASK(31, 24) +/* Selective IDE Address Association Register Block, up to PCI_IDE_SEL_CAP_ASSOC_NUM */ +#define PCI_IDE_SEL_ADDR_BLOCK_SIZE 12 +#define PCI_IDE_SEL_ADDR_1(x) (20 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) +#define PCI_IDE_SEL_ADDR_1_VALID 0x1 +#define PCI_IDE_SEL_ADDR_1_BASE_LOW __GENMASK(19, 8) +#define PCI_IDE_SEL_ADDR_1_LIMIT_LOW __GENMASK(31, 20) +/* IDE Address Association Register 2 is "Memory Limit Upper" */ +#define PCI_IDE_SEL_ADDR_2(x) (24 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) +/* IDE Address Association Register 3 is "Memory Base Upper" */ +#define PCI_IDE_SEL_ADDR_3(x) (28 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) +#define PCI_IDE_SEL_BLOCK_SIZE(nr_assoc) (20 + PCI_IDE_SEL_ADDR_BLOCK_SIZE * (nr_assoc)) + #endif /* LINUX_PCI_REGS_H */ diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h index 93abaae0b9..17a0174d6c 100644 --- a/include/standard-headers/linux/virtio_net.h +++ b/include/standard-headers/linux/virtio_net.h @@ -193,7 +193,8 @@ struct virtio_net_hdr_v1 { struct virtio_net_hdr_v1_hash { struct virtio_net_hdr_v1 hdr; - uint32_t hash_value; + uint16_t hash_value_lo; + uint16_t hash_value_hi; #define VIRTIO_NET_HASH_REPORT_NONE 0 #define VIRTIO_NET_HASH_REPORT_IPv4 1 #define VIRTIO_NET_HASH_REPORT_TCPv4 2 diff --git a/include/standard-headers/linux/virtio_pci.h b/include/standard-headers/linux/virtio_pci.h index 09e964e6ee..4c82513df2 100644 --- a/include/standard-headers/linux/virtio_pci.h +++ b/include/standard-headers/linux/virtio_pci.h @@ -40,7 +40,7 @@ #define _LINUX_VIRTIO_PCI_H #include "standard-headers/linux/types.h" -#include "standard-headers/linux/kernel.h" +#include "standard-headers/linux/const.h" #ifndef VIRTIO_PCI_NO_LEGACY diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index f4d9baafa1..46ffbddab5 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -31,7 +31,7 @@ #define KVM_SPSR_FIQ 4 #define KVM_NR_SPSR 5 -#ifndef __ASSEMBLY__ +#ifndef __ASSEMBLER__ #include <linux/psci.h> #include <linux/types.h> #include <asm/ptrace.h> diff --git a/linux-headers/asm-arm64/unistd_64.h b/linux-headers/asm-arm64/unistd_64.h index 4ae25c2b91..1ef9c40813 100644 --- a/linux-headers/asm-arm64/unistd_64.h +++ b/linux-headers/asm-arm64/unistd_64.h @@ -326,6 +326,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h index 04e0077fb4..942370b3f5 100644 --- a/linux-headers/asm-generic/unistd.h +++ b/linux-headers/asm-generic/unistd.h @@ -857,9 +857,11 @@ __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) __SYSCALL(__NR_file_getattr, sys_file_getattr) #define __NR_file_setattr 469 __SYSCALL(__NR_file_setattr, sys_file_setattr) +#define __NR_listns 470 +__SYSCALL(__NR_listns, sys_listns) #undef __NR_syscalls -#define __NR_syscalls 470 +#define __NR_syscalls 471 /* * 32 bit systems traditionally used different diff --git a/linux-headers/asm-loongarch/kvm.h b/linux-headers/asm-loongarch/kvm.h index 57ba1a563b..de6c3f18e4 100644 --- a/linux-headers/asm-loongarch/kvm.h +++ b/linux-headers/asm-loongarch/kvm.h @@ -104,6 +104,7 @@ struct kvm_fpu { #define KVM_LOONGARCH_VM_FEAT_PV_IPI 6 #define KVM_LOONGARCH_VM_FEAT_PV_STEALTIME 7 #define KVM_LOONGARCH_VM_FEAT_PTW 8 +#define KVM_LOONGARCH_VM_FEAT_MSGINT 9 /* Device Control API on vcpu fd */ #define KVM_LOONGARCH_VCPU_CPUCFG 0 diff --git a/linux-headers/asm-loongarch/unistd.h b/linux-headers/asm-loongarch/unistd.h index 1f01980f9c..e19c7f2f9f 100644 --- a/linux-headers/asm-loongarch/unistd.h +++ b/linux-headers/asm-loongarch/unistd.h @@ -1,3 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#include <asm/bitsperlong.h> + +#if __BITS_PER_LONG == 32 +#include <asm/unistd_32.h> +#else #include <asm/unistd_64.h> +#endif diff --git a/linux-headers/asm-loongarch/unistd_64.h b/linux-headers/asm-loongarch/unistd_64.h index 5033fc8f2f..aa5daac4ef 100644 --- a/linux-headers/asm-loongarch/unistd_64.h +++ b/linux-headers/asm-loongarch/unistd_64.h @@ -322,6 +322,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-mips/unistd_n32.h b/linux-headers/asm-mips/unistd_n32.h index c99c10e5bf..a33d106dca 100644 --- a/linux-headers/asm-mips/unistd_n32.h +++ b/linux-headers/asm-mips/unistd_n32.h @@ -398,5 +398,6 @@ #define __NR_open_tree_attr (__NR_Linux + 467) #define __NR_file_getattr (__NR_Linux + 468) #define __NR_file_setattr (__NR_Linux + 469) +#define __NR_listns (__NR_Linux + 470) #endif /* _ASM_UNISTD_N32_H */ diff --git a/linux-headers/asm-mips/unistd_n64.h b/linux-headers/asm-mips/unistd_n64.h index 0d975bb185..1bc251e450 100644 --- a/linux-headers/asm-mips/unistd_n64.h +++ b/linux-headers/asm-mips/unistd_n64.h @@ -374,5 +374,6 @@ #define __NR_open_tree_attr (__NR_Linux + 467) #define __NR_file_getattr (__NR_Linux + 468) #define __NR_file_setattr (__NR_Linux + 469) +#define __NR_listns (__NR_Linux + 470) #endif /* _ASM_UNISTD_N64_H */ diff --git a/linux-headers/asm-mips/unistd_o32.h b/linux-headers/asm-mips/unistd_o32.h index 86ac0ac84b..c57175d496 100644 --- a/linux-headers/asm-mips/unistd_o32.h +++ b/linux-headers/asm-mips/unistd_o32.h @@ -444,5 +444,6 @@ #define __NR_open_tree_attr (__NR_Linux + 467) #define __NR_file_getattr (__NR_Linux + 468) #define __NR_file_setattr (__NR_Linux + 469) +#define __NR_listns (__NR_Linux + 470) #endif /* _ASM_UNISTD_O32_H */ diff --git a/linux-headers/asm-powerpc/unistd_32.h b/linux-headers/asm-powerpc/unistd_32.h index d7a32c5e06..a3f4aa2fe2 100644 --- a/linux-headers/asm-powerpc/unistd_32.h +++ b/linux-headers/asm-powerpc/unistd_32.h @@ -451,6 +451,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-powerpc/unistd_64.h b/linux-headers/asm-powerpc/unistd_64.h index ff35c51fc6..d4444557f1 100644 --- a/linux-headers/asm-powerpc/unistd_64.h +++ b/linux-headers/asm-powerpc/unistd_64.h @@ -423,6 +423,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h index 759a4852c0..54f3ad7ed2 100644 --- a/linux-headers/asm-riscv/kvm.h +++ b/linux-headers/asm-riscv/kvm.h @@ -23,6 +23,8 @@ #define KVM_INTERRUPT_SET -1U #define KVM_INTERRUPT_UNSET -2U +#define KVM_EXIT_FAIL_ENTRY_NO_VSFILE (1ULL << 0) + /* for KVM_GET_REGS and KVM_SET_REGS */ struct kvm_regs { }; @@ -211,6 +213,7 @@ enum KVM_RISCV_SBI_EXT_ID { KVM_RISCV_SBI_EXT_STA, KVM_RISCV_SBI_EXT_SUSP, KVM_RISCV_SBI_EXT_FWFT, + KVM_RISCV_SBI_EXT_MPXY, KVM_RISCV_SBI_EXT_MAX, }; diff --git a/linux-headers/asm-riscv/unistd_32.h b/linux-headers/asm-riscv/unistd_32.h index 6083373e88..9f33956246 100644 --- a/linux-headers/asm-riscv/unistd_32.h +++ b/linux-headers/asm-riscv/unistd_32.h @@ -317,6 +317,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-riscv/unistd_64.h b/linux-headers/asm-riscv/unistd_64.h index f0c7585c60..c2e7258916 100644 --- a/linux-headers/asm-riscv/unistd_64.h +++ b/linux-headers/asm-riscv/unistd_64.h @@ -327,6 +327,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-s390/bitsperlong.h b/linux-headers/asm-s390/bitsperlong.h index cceaf47b02..7af27a985f 100644 --- a/linux-headers/asm-s390/bitsperlong.h +++ b/linux-headers/asm-s390/bitsperlong.h @@ -2,11 +2,7 @@ #ifndef __ASM_S390_BITSPERLONG_H #define __ASM_S390_BITSPERLONG_H -#ifndef __s390x__ -#define __BITS_PER_LONG 32 -#else #define __BITS_PER_LONG 64 -#endif #include <asm-generic/bitsperlong.h> diff --git a/linux-headers/asm-s390/unistd.h b/linux-headers/asm-s390/unistd.h index 27b8b211c8..1484618877 100644 --- a/linux-headers/asm-s390/unistd.h +++ b/linux-headers/asm-s390/unistd.h @@ -8,10 +8,6 @@ #ifndef _ASM_S390_UNISTD_H_ #define _ASM_S390_UNISTD_H_ -#ifdef __s390x__ #include <asm/unistd_64.h> -#else -#include <asm/unistd_32.h> -#endif #endif /* _ASM_S390_UNISTD_H_ */ diff --git a/linux-headers/asm-s390/unistd_64.h b/linux-headers/asm-s390/unistd_64.h index 0652ba6331..8d9e579ef5 100644 --- a/linux-headers/asm-s390/unistd_64.h +++ b/linux-headers/asm-s390/unistd_64.h @@ -1,6 +1,5 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _ASM_S390_UNISTD_64_H -#define _ASM_S390_UNISTD_64_H +#ifndef _ASM_UNISTD_64_H +#define _ASM_UNISTD_64_H #define __NR_exit 1 #define __NR_fork 2 @@ -390,5 +389,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 -#endif /* _ASM_S390_UNISTD_64_H */ + +#endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index 3bb38f6c3a..b804fd25a2 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -500,6 +500,7 @@ struct kvm_sync_regs { /* vendor-specific groups and attributes for system fd */ #define KVM_X86_GRP_SEV 1 # define KVM_X86_SEV_VMSA_FEATURES 0 +# define KVM_X86_SNP_POLICY_BITS 1 struct kvm_vmx_nested_state_data { __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; diff --git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h index 8f784a5634..34255aac64 100644 --- a/linux-headers/asm-x86/unistd_32.h +++ b/linux-headers/asm-x86/unistd_32.h @@ -460,6 +460,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_32_H */ diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h index 26c258d1a6..07f242a5fa 100644 --- a/linux-headers/asm-x86/unistd_64.h +++ b/linux-headers/asm-x86/unistd_64.h @@ -384,6 +384,7 @@ #define __NR_open_tree_attr 467 #define __NR_file_getattr 468 #define __NR_file_setattr 469 +#define __NR_listns 470 #endif /* _ASM_UNISTD_64_H */ diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h index 65c2aed946..08fc9da2fa 100644 --- a/linux-headers/asm-x86/unistd_x32.h +++ b/linux-headers/asm-x86/unistd_x32.h @@ -337,6 +337,7 @@ #define __NR_open_tree_attr (__X32_SYSCALL_BIT + 467) #define __NR_file_getattr (__X32_SYSCALL_BIT + 468) #define __NR_file_setattr (__X32_SYSCALL_BIT + 469) +#define __NR_listns (__X32_SYSCALL_BIT + 470) #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512) #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513) #define __NR_ioctl (__X32_SYSCALL_BIT + 514) diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h index 2105a03955..384183a403 100644 --- a/linux-headers/linux/iommufd.h +++ b/linux-headers/linux/iommufd.h @@ -450,6 +450,16 @@ struct iommu_hwpt_vtd_s1 { * nested domain will translate the same as the nesting parent. The S1 will * install a Context Descriptor Table pointing at userspace memory translated * by the nesting parent. + * + * It's suggested to allocate a vDEVICE object carrying vSID and then re-attach + * the nested domain, as soon as the vSID is available in the VMM level: + * + * - when Cfg=translate, a vDEVICE must be allocated prior to attaching to the + * allocated nested domain, as CD/ATS invalidations and vevents need a vSID. + * - when Cfg=bypass/abort, a vDEVICE is not enforced during the nested domain + * attachment, to support a GBPA case where VM sets CR0.SMMUEN=0. However, if + * VM sets CR0.SMMUEN=1 while missing a vDEVICE object, kernel would fail to + * report events to the VM. E.g. F_TRANSLATION when guest STE.Cfg=abort. */ struct iommu_hwpt_arm_smmuv3 { __aligned_le64 ste[2]; diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index 4ea28ef7ca..a4ab42dcba 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -179,6 +179,7 @@ struct kvm_xen_exit { #define KVM_EXIT_LOONGARCH_IOCSR 38 #define KVM_EXIT_MEMORY_FAULT 39 #define KVM_EXIT_TDX 40 +#define KVM_EXIT_ARM_SEA 41 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -465,6 +466,14 @@ struct kvm_run { } setup_event_notify; }; } tdx; + /* KVM_EXIT_ARM_SEA */ + struct { +#define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID (1ULL << 0) + __u64 flags; + __u64 esr; + __u64 gva; + __u64 gpa; + } arm_sea; /* Fix the size of the union. */ char padding[256]; }; @@ -955,6 +964,8 @@ struct kvm_enable_cap { #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 #define KVM_CAP_GUEST_MEMFD_FLAGS 244 +#define KVM_CAP_ARM_SEA_TO_USER 245 +#define KVM_CAP_S390_USER_OPEREXEC 246 struct kvm_irq_routing_irqchip { __u32 irqchip; diff --git a/linux-headers/linux/mshv.h b/linux-headers/linux/mshv.h index 5bc83db6a3..acceeddc1c 100644 --- a/linux-headers/linux/mshv.h +++ b/linux-headers/linux/mshv.h @@ -26,6 +26,7 @@ enum { MSHV_PT_BIT_LAPIC, MSHV_PT_BIT_X2APIC, MSHV_PT_BIT_GPA_SUPER_PAGES, + MSHV_PT_BIT_CPU_AND_XSAVE_FEATURES, MSHV_PT_BIT_COUNT, }; @@ -41,6 +42,8 @@ enum { * @pt_flags: Bitmask of 1 << MSHV_PT_BIT_* * @pt_isolation: MSHV_PT_ISOLATION_* * + * This is the initial/v1 version for backward compatibility. + * * Returns a file descriptor to act as a handle to a guest partition. * At this point the partition is not yet initialized in the hypervisor. * Some operations must be done with the partition in this state, e.g. setting @@ -52,6 +55,37 @@ struct mshv_create_partition { __u64 pt_isolation; }; +#define MSHV_NUM_CPU_FEATURES_BANKS 2 + +/** + * struct mshv_create_partition_v2 + * + * This is extended version of the above initial MSHV_CREATE_PARTITION + * ioctl and allows for following additional parameters: + * + * @pt_num_cpu_fbanks: Must be set to MSHV_NUM_CPU_FEATURES_BANKS. + * @pt_cpu_fbanks: Disabled processor feature banks array. + * @pt_disabled_xsave: Disabled xsave feature bits. + * + * pt_cpu_fbanks and pt_disabled_xsave are passed through as-is to the create + * partition hypercall. + * + * Returns : same as above original mshv_create_partition + */ +struct mshv_create_partition_v2 { + __u64 pt_flags; + __u64 pt_isolation; + __u16 pt_num_cpu_fbanks; + __u8 pt_rsvd[6]; /* MBZ */ + __u64 pt_cpu_fbanks[MSHV_NUM_CPU_FEATURES_BANKS]; + __u64 pt_rsvd1[2]; /* MBZ */ +#if defined(__x86_64__) + __u64 pt_disabled_xsave; +#else + __u64 pt_rsvd2; /* MBZ */ +#endif +} __attribute__((packed)); + /* /dev/mshv */ #define MSHV_CREATE_PARTITION _IOW(MSHV_IOCTL, 0x00, struct mshv_create_partition) @@ -89,7 +123,7 @@ enum { * @rsvd: MBZ * * Map or unmap a region of userspace memory to Guest Physical Addresses (GPA). - * Mappings can't overlap in GPA space or userspace. + * Mappings can't overlap in GPA space. * To unmap, these fields must match an existing mapping. */ struct mshv_user_mem_region { @@ -288,4 +322,84 @@ struct mshv_get_set_vp_state { * #define MSHV_ROOT_HVCALL _IOWR(MSHV_IOCTL, 0x07, struct mshv_root_hvcall) */ +/* Structure definitions, macros and IOCTLs for mshv_vtl */ + +#define MSHV_CAP_CORE_API_STABLE 0x0 +#define MSHV_CAP_REGISTER_PAGE 0x1 +#define MSHV_CAP_VTL_RETURN_ACTION 0x2 +#define MSHV_CAP_DR6_SHARED 0x3 +#define MSHV_MAX_RUN_MSG_SIZE 256 + +struct mshv_vp_registers { + __u32 count; /* supports only 1 register at a time */ + __u32 reserved; /* Reserved for alignment or future use */ + __u64 regs_ptr; /* pointer to struct hv_register_assoc */ +}; + +struct mshv_vtl_set_eventfd { + __s32 fd; + __u32 flag; +}; + +struct mshv_vtl_signal_event { + __u32 connection_id; + __u32 flag; +}; + +struct mshv_vtl_sint_post_msg { + __u64 message_type; + __u32 connection_id; + __u32 payload_size; /* Must not exceed HV_MESSAGE_PAYLOAD_BYTE_COUNT */ + __u64 payload_ptr; /* pointer to message payload (bytes) */ +}; + +struct mshv_vtl_ram_disposition { + __u64 start_pfn; + __u64 last_pfn; +}; + +struct mshv_vtl_set_poll_file { + __u32 cpu; + __u32 fd; +}; + +struct mshv_vtl_hvcall_setup { + __u64 bitmap_array_size; /* stores number of bytes */ + __u64 allow_bitmap_ptr; +}; + +struct mshv_vtl_hvcall { + __u64 control; /* Hypercall control code */ + __u64 input_size; /* Size of the input data */ + __u64 input_ptr; /* Pointer to the input struct */ + __u64 status; /* Status of the hypercall (output) */ + __u64 output_size; /* Size of the output data */ + __u64 output_ptr; /* Pointer to the output struct */ +}; + +struct mshv_sint_mask { + __u8 mask; + __u8 reserved[7]; +}; + +/* /dev/mshv device IOCTL */ +#define MSHV_CHECK_EXTENSION _IOW(MSHV_IOCTL, 0x00, __u32) + +/* vtl device */ +#define MSHV_CREATE_VTL _IOR(MSHV_IOCTL, 0x1D, char) +#define MSHV_ADD_VTL0_MEMORY _IOW(MSHV_IOCTL, 0x21, struct mshv_vtl_ram_disposition) +#define MSHV_SET_POLL_FILE _IOW(MSHV_IOCTL, 0x25, struct mshv_vtl_set_poll_file) +#define MSHV_RETURN_TO_LOWER_VTL _IO(MSHV_IOCTL, 0x27) +#define MSHV_GET_VP_REGISTERS _IOWR(MSHV_IOCTL, 0x05, struct mshv_vp_registers) +#define MSHV_SET_VP_REGISTERS _IOW(MSHV_IOCTL, 0x06, struct mshv_vp_registers) + +/* VMBus device IOCTLs */ +#define MSHV_SINT_SIGNAL_EVENT _IOW(MSHV_IOCTL, 0x22, struct mshv_vtl_signal_event) +#define MSHV_SINT_POST_MESSAGE _IOW(MSHV_IOCTL, 0x23, struct mshv_vtl_sint_post_msg) +#define MSHV_SINT_SET_EVENTFD _IOW(MSHV_IOCTL, 0x24, struct mshv_vtl_set_eventfd) +#define MSHV_SINT_PAUSE_MESSAGE_STREAM _IOW(MSHV_IOCTL, 0x25, struct mshv_sint_mask) + +/* hv_hvcall device */ +#define MSHV_HVCALL_SETUP _IOW(MSHV_IOCTL, 0x1E, struct mshv_vtl_hvcall_setup) +#define MSHV_HVCALL _IOWR(MSHV_IOCTL, 0x1F, struct mshv_vtl_hvcall) #endif diff --git a/linux-headers/linux/psp-sev.h b/linux-headers/linux/psp-sev.h index c525125ea8..9479928a4a 100644 --- a/linux-headers/linux/psp-sev.h +++ b/linux-headers/linux/psp-sev.h @@ -47,32 +47,32 @@ typedef enum { * with possible values from the specification. */ SEV_RET_NO_FW_CALL = -1, - SEV_RET_SUCCESS = 0, - SEV_RET_INVALID_PLATFORM_STATE, - SEV_RET_INVALID_GUEST_STATE, - SEV_RET_INAVLID_CONFIG, + SEV_RET_SUCCESS = 0, + SEV_RET_INVALID_PLATFORM_STATE = 0x0001, + SEV_RET_INVALID_GUEST_STATE = 0x0002, + SEV_RET_INAVLID_CONFIG = 0x0003, SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, - SEV_RET_INVALID_LEN, - SEV_RET_ALREADY_OWNED, - SEV_RET_INVALID_CERTIFICATE, - SEV_RET_POLICY_FAILURE, - SEV_RET_INACTIVE, - SEV_RET_INVALID_ADDRESS, - SEV_RET_BAD_SIGNATURE, - SEV_RET_BAD_MEASUREMENT, - SEV_RET_ASID_OWNED, - SEV_RET_INVALID_ASID, - SEV_RET_WBINVD_REQUIRED, - SEV_RET_DFFLUSH_REQUIRED, - SEV_RET_INVALID_GUEST, - SEV_RET_INVALID_COMMAND, - SEV_RET_ACTIVE, - SEV_RET_HWSEV_RET_PLATFORM, - SEV_RET_HWSEV_RET_UNSAFE, - SEV_RET_UNSUPPORTED, - SEV_RET_INVALID_PARAM, - SEV_RET_RESOURCE_LIMIT, - SEV_RET_SECURE_DATA_INVALID, + SEV_RET_INVALID_LEN = 0x0004, + SEV_RET_ALREADY_OWNED = 0x0005, + SEV_RET_INVALID_CERTIFICATE = 0x0006, + SEV_RET_POLICY_FAILURE = 0x0007, + SEV_RET_INACTIVE = 0x0008, + SEV_RET_INVALID_ADDRESS = 0x0009, + SEV_RET_BAD_SIGNATURE = 0x000A, + SEV_RET_BAD_MEASUREMENT = 0x000B, + SEV_RET_ASID_OWNED = 0x000C, + SEV_RET_INVALID_ASID = 0x000D, + SEV_RET_WBINVD_REQUIRED = 0x000E, + SEV_RET_DFFLUSH_REQUIRED = 0x000F, + SEV_RET_INVALID_GUEST = 0x0010, + SEV_RET_INVALID_COMMAND = 0x0011, + SEV_RET_ACTIVE = 0x0012, + SEV_RET_HWSEV_RET_PLATFORM = 0x0013, + SEV_RET_HWSEV_RET_UNSAFE = 0x0014, + SEV_RET_UNSUPPORTED = 0x0015, + SEV_RET_INVALID_PARAM = 0x0016, + SEV_RET_RESOURCE_LIMIT = 0x0017, + SEV_RET_SECURE_DATA_INVALID = 0x0018, SEV_RET_INVALID_PAGE_SIZE = 0x0019, SEV_RET_INVALID_PAGE_STATE = 0x001A, SEV_RET_INVALID_MDATA_ENTRY = 0x001B, @@ -87,6 +87,22 @@ typedef enum { SEV_RET_RESTORE_REQUIRED = 0x0025, SEV_RET_RMP_INITIALIZATION_FAILED = 0x0026, SEV_RET_INVALID_KEY = 0x0027, + SEV_RET_SHUTDOWN_INCOMPLETE = 0x0028, + SEV_RET_INCORRECT_BUFFER_LENGTH = 0x0030, + SEV_RET_EXPAND_BUFFER_LENGTH_REQUEST = 0x0031, + SEV_RET_SPDM_REQUEST = 0x0032, + SEV_RET_SPDM_ERROR = 0x0033, + SEV_RET_SEV_STATUS_ERR_IN_DEV_CONN = 0x0035, + SEV_RET_SEV_STATUS_INVALID_DEV_CTX = 0x0036, + SEV_RET_SEV_STATUS_INVALID_TDI_CTX = 0x0037, + SEV_RET_SEV_STATUS_INVALID_TDI = 0x0038, + SEV_RET_SEV_STATUS_RECLAIM_REQUIRED = 0x0039, + SEV_RET_IN_USE = 0x003A, + SEV_RET_SEV_STATUS_INVALID_DEV_STATE = 0x003B, + SEV_RET_SEV_STATUS_INVALID_TDI_STATE = 0x003C, + SEV_RET_SEV_STATUS_DEV_CERT_CHANGED = 0x003D, + SEV_RET_SEV_STATUS_RESYNC_REQ = 0x003E, + SEV_RET_SEV_STATUS_RESPONSE_TOO_LARGE = 0x003F, SEV_RET_MAX, } sev_ret_code; diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index 4d96d1fc12..720edfee7a 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -14,6 +14,7 @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <linux/stddef.h> #define VFIO_API_VERSION 0 @@ -1478,6 +1479,33 @@ struct vfio_device_feature_bus_master { }; #define VFIO_DEVICE_FEATURE_BUS_MASTER 10 +/** + * Upon VFIO_DEVICE_FEATURE_GET create a dma_buf fd for the + * regions selected. + * + * open_flags are the typical flags passed to open(2), eg O_RDWR, O_CLOEXEC, + * etc. offset/length specify a slice of the region to create the dmabuf from. + * nr_ranges is the total number of (P2P DMA) ranges that comprise the dmabuf. + * + * flags should be 0. + * + * Return: The fd number on success, -1 and errno is set on failure. + */ +#define VFIO_DEVICE_FEATURE_DMA_BUF 11 + +struct vfio_region_dma_range { + __u64 offset; + __u64 length; +}; + +struct vfio_device_feature_dma_buf { + __u32 region_index; + __u32 open_flags; + __u32 flags; + __u32 nr_ranges; + struct vfio_region_dma_range dma_ranges[] __counted_by(nr_ranges); +}; + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- 2.43.0 ^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 2026-01-21 11:41 ` [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 Shameer Kolothum @ 2026-01-21 14:00 ` Cédric Le Goater 2026-01-21 14:21 ` Peter Maydell 0 siblings, 1 reply; 16+ messages in thread From: Cédric Le Goater @ 2026-01-21 14:00 UTC (permalink / raw) To: Shameer Kolothum, qemu-arm, qemu-devel Cc: eric.auger, alex, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, Jason Wang On 1/21/26 12:41, Shameer Kolothum wrote: > Mainly for adding support for VFIO DMABUF. While at it, update all > headers. > > The header update breaks virtio-net due to virtio_net_hdr_v1_hash > changes. Include the virtio-net changes to avoid build and bisect > failures. > > Cc: Michael S. Tsirkin <mst@redhat.com> > Cc: Jason Wang <jasowang@redhat.com> > Tested-by: Nicolin Chen <nicolinc@nvidia.com> > Reviewed-by: Cédric Le Goater <clg@redhat.com> > Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> > --- > hw/net/virtio-net.c | 11 +- Recent commit 503eb470e087 ("scripts/checkpatch: more checks on files imported from Linux") added a check on the imported files and checkpatch now complains with : ERROR: headers imported from Linux should be self-contained in a patch with no other changes #101: FILE: include/standard-headers/drm/drm_fourcc.h:978: * 2 = Gob Height 8, Turing+ Page Kind mapping I suspect there is an error in the name of the file in question. Anyhow, feedbacks are welcome because I doubt this check is valid in this situation and I am ready to apply this change as is. Thanks, C. > include/standard-headers/drm/drm_fourcc.h | 25 ++-- > include/standard-headers/linux/ethtool.h | 5 + > .../linux/input-event-codes.h | 14 ++- > include/standard-headers/linux/pci_regs.h | 89 ++++++++++++++ > include/standard-headers/linux/virtio_net.h | 3 +- > include/standard-headers/linux/virtio_pci.h | 2 +- > linux-headers/asm-arm64/kvm.h | 2 +- > linux-headers/asm-arm64/unistd_64.h | 1 + > linux-headers/asm-generic/unistd.h | 4 +- > linux-headers/asm-loongarch/kvm.h | 1 + > linux-headers/asm-loongarch/unistd.h | 6 + > linux-headers/asm-loongarch/unistd_64.h | 1 + > 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/unistd_32.h | 1 + > linux-headers/asm-powerpc/unistd_64.h | 1 + > linux-headers/asm-riscv/kvm.h | 3 + > linux-headers/asm-riscv/unistd_32.h | 1 + > linux-headers/asm-riscv/unistd_64.h | 1 + > linux-headers/asm-s390/bitsperlong.h | 4 - > linux-headers/asm-s390/unistd.h | 4 - > linux-headers/asm-s390/unistd_64.h | 9 +- > linux-headers/asm-x86/kvm.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/iommufd.h | 10 ++ > linux-headers/linux/kvm.h | 11 ++ > linux-headers/linux/mshv.h | 116 +++++++++++++++++- > linux-headers/linux/psp-sev.h | 66 ++++++---- > linux-headers/linux/vfio.h | 28 +++++ > 33 files changed, 370 insertions(+), 56 deletions(-) > > diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c > index 317f1ad23b..512a7c02c9 100644 > --- a/hw/net/virtio-net.c > +++ b/hw/net/virtio-net.c > @@ -1879,7 +1879,8 @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf, > n->rss_data.runtime_hash_types); > if (net_hash_type > NetPktRssIpV6UdpEx) { > if (n->rss_data.populate_hash) { > - hdr->hash_value = VIRTIO_NET_HASH_REPORT_NONE; > + hdr->hash_value_lo = VIRTIO_NET_HASH_REPORT_NONE; > + hdr->hash_value_hi = VIRTIO_NET_HASH_REPORT_NONE; > hdr->hash_report = 0; > } > return n->rss_data.redirect ? n->rss_data.default_queue : -1; > @@ -1888,7 +1889,8 @@ static int virtio_net_process_rss(NetClientState *nc, const uint8_t *buf, > hash = net_rx_pkt_calc_rss_hash(pkt, net_hash_type, n->rss_data.key); > > if (n->rss_data.populate_hash) { > - hdr->hash_value = hash; > + hdr->hash_value_lo = cpu_to_le16(hash & 0xffff); > + hdr->hash_value_hi = cpu_to_le16((hash >> 16) & 0xffff); > hdr->hash_report = reports[net_hash_type]; > } > > @@ -1990,10 +1992,11 @@ static ssize_t virtio_net_receive_rcu(NetClientState *nc, const uint8_t *buf, > > receive_header(n, sg, elem->in_num, buf, size); > if (n->rss_data.populate_hash) { > - offset = offsetof(typeof(extra_hdr), hash_value); > + offset = offsetof(typeof(extra_hdr), hash_value_lo); > iov_from_buf(sg, elem->in_num, offset, > (char *)&extra_hdr + offset, > - sizeof(extra_hdr.hash_value) + > + sizeof(extra_hdr.hash_value_lo) + > + sizeof(extra_hdr.hash_value_hi) + > sizeof(extra_hdr.hash_report)); > } > offset = n->host_hdr_len; > diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h > index cef077dfb3..b39e197cc7 100644 > --- a/include/standard-headers/drm/drm_fourcc.h > +++ b/include/standard-headers/drm/drm_fourcc.h > @@ -978,14 +978,20 @@ extern "C" { > * 2 = Gob Height 8, Turing+ Page Kind mapping > * 3 = Reserved for future use. > * > - * 22:22 s Sector layout. On Tegra GPUs prior to Xavier, there is a further > - * bit remapping step that occurs at an even lower level than the > - * page kind and block linear swizzles. This causes the layout of > - * surfaces mapped in those SOC's GPUs to be incompatible with the > - * equivalent mapping on other GPUs in the same system. > - * > - * 0 = Tegra K1 - Tegra Parker/TX2 Layout. > - * 1 = Desktop GPU and Tegra Xavier+ Layout > + * 22:22 s Sector layout. There is a further bit remapping step that occurs > + * 26:27 at an even lower level than the page kind and block linear > + * swizzles. This causes the bit arrangement of surfaces in memory > + * to differ subtly, and prevents direct sharing of surfaces between > + * GPUs with different layouts. > + * > + * 0 = Tegra K1 - Tegra Parker/TX2 Layout > + * 1 = Pre-GB20x, GB20x 32+ bpp, GB10, Tegra Xavier-Orin Layout > + * 2 = GB20x(Blackwell 2)+ 8 bpp surface layout > + * 3 = GB20x(Blackwell 2)+ 16 bpp surface layout > + * 4 = Reserved for future use. > + * 5 = Reserved for future use. > + * 6 = Reserved for future use. > + * 7 = Reserved for future use. > * > * 25:23 c Lossless Framebuffer Compression type. > * > @@ -1000,7 +1006,7 @@ extern "C" { > * 6 = Reserved for future use > * 7 = Reserved for future use > * > - * 55:25 - Reserved for future use. Must be zero. > + * 55:28 - Reserved for future use. Must be zero. > */ > #define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \ > fourcc_mod_code(NVIDIA, (0x10 | \ > @@ -1008,6 +1014,7 @@ extern "C" { > (((k) & 0xff) << 12) | \ > (((g) & 0x3) << 20) | \ > (((s) & 0x1) << 22) | \ > + (((s) & 0x6) << 25) | \ > (((c) & 0x7) << 23))) > > /* To grandfather in prior block linear format modifiers to the above layout, > diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h > index dc24512d28..d0f7a63f10 100644 > --- a/include/standard-headers/linux/ethtool.h > +++ b/include/standard-headers/linux/ethtool.h > @@ -2077,6 +2077,10 @@ enum ethtool_link_mode_bit_indices { > ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT = 118, > ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT = 119, > ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT = 120, > + ETHTOOL_LINK_MODE_1600000baseCR8_Full_BIT = 121, > + ETHTOOL_LINK_MODE_1600000baseKR8_Full_BIT = 122, > + ETHTOOL_LINK_MODE_1600000baseDR8_Full_BIT = 123, > + ETHTOOL_LINK_MODE_1600000baseDR8_2_Full_BIT = 124, > > /* must be last entry */ > __ETHTOOL_LINK_MODE_MASK_NBITS > @@ -2190,6 +2194,7 @@ enum ethtool_link_mode_bit_indices { > #define SPEED_200000 200000 > #define SPEED_400000 400000 > #define SPEED_800000 800000 > +#define SPEED_1600000 1600000 > > #define SPEED_UNKNOWN -1 > > diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h > index c914ccd723..ede79c6ae4 100644 > --- a/include/standard-headers/linux/input-event-codes.h > +++ b/include/standard-headers/linux/input-event-codes.h > @@ -27,7 +27,7 @@ > #define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ > #define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ > #define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ > -#define INPUT_PROP_HAPTIC_TOUCHPAD 0x07 /* is a haptic touchpad */ > +#define INPUT_PROP_PRESSUREPAD 0x07 /* pressure triggers clicks */ > > #define INPUT_PROP_MAX 0x1f > #define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) > @@ -631,6 +631,18 @@ > #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ > #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ > > +/* > + * Keycodes for hotkeys toggling the electronic privacy screen found on some > + * laptops on/off. Note when the embedded-controller turns on/off the eprivacy > + * screen itself then the state should be reported through drm connecter props: > + * https://www.kernel.org/doc/html/latest/gpu/drm-kms.html#standard-connector-properties > + * Except when implementing the drm connecter properties API is not possible > + * because e.g. the firmware does not allow querying the presence and/or status > + * of the eprivacy screen at boot. > + */ > +#define KEY_EPRIVACY_SCREEN_ON 0x252 > +#define KEY_EPRIVACY_SCREEN_OFF 0x253 > + > #define KEY_KBDINPUTASSIST_PREV 0x260 > #define KEY_KBDINPUTASSIST_NEXT 0x261 > #define KEY_KBDINPUTASSIST_PREVGROUP 0x262 > diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h > index 07e06aafec..3add74ae25 100644 > --- a/include/standard-headers/linux/pci_regs.h > +++ b/include/standard-headers/linux/pci_regs.h > @@ -503,6 +503,7 @@ > #define PCI_EXP_DEVCAP_PWR_VAL 0x03fc0000 /* Slot Power Limit Value */ > #define PCI_EXP_DEVCAP_PWR_SCL 0x0c000000 /* Slot Power Limit Scale */ > #define PCI_EXP_DEVCAP_FLR 0x10000000 /* Function Level Reset */ > +#define PCI_EXP_DEVCAP_TEE 0x40000000 /* TEE I/O (TDISP) Support */ > #define PCI_EXP_DEVCTL 0x08 /* Device Control */ > #define PCI_EXP_DEVCTL_CERE 0x0001 /* Correctable Error Reporting En. */ > #define PCI_EXP_DEVCTL_NFERE 0x0002 /* Non-Fatal Error Reporting Enable */ > @@ -754,6 +755,8 @@ > #define PCI_EXT_CAP_ID_NPEM 0x29 /* Native PCIe Enclosure Management */ > #define PCI_EXT_CAP_ID_PL_32GT 0x2A /* Physical Layer 32.0 GT/s */ > #define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ > +#define PCI_EXT_CAP_ID_DEV3 0x2F /* Device 3 Capability/Control/Status */ > +#define PCI_EXT_CAP_ID_IDE 0x30 /* Integrity and Data Encryption */ > #define PCI_EXT_CAP_ID_PL_64GT 0x31 /* Physical Layer 64.0 GT/s */ > #define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_64GT > > @@ -1244,9 +1247,95 @@ > /* Deprecated old name, replaced with PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE */ > #define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL PCI_DOE_DATA_OBJECT_DISC_RSP_3_TYPE > > +/* Device 3 Extended Capability */ > +#define PCI_DEV3_CAP 0x04 /* Device 3 Capabilities Register */ > +#define PCI_DEV3_CTL 0x08 /* Device 3 Control Register */ > +#define PCI_DEV3_STA 0x0c /* Device 3 Status Register */ > +#define PCI_DEV3_STA_SEGMENT 0x8 /* Segment Captured (end-to-end flit-mode detected) */ > + > /* Compute Express Link (CXL r3.1, sec 8.1.5) */ > #define PCI_DVSEC_CXL_PORT 3 > #define PCI_DVSEC_CXL_PORT_CTL 0x0c > #define PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR 0x00000001 > > +/* Integrity and Data Encryption Extended Capability */ > +#define PCI_IDE_CAP 0x04 > +#define PCI_IDE_CAP_LINK 0x1 /* Link IDE Stream Supported */ > +#define PCI_IDE_CAP_SELECTIVE 0x2 /* Selective IDE Streams Supported */ > +#define PCI_IDE_CAP_FLOWTHROUGH 0x4 /* Flow-Through IDE Stream Supported */ > +#define PCI_IDE_CAP_PARTIAL_HEADER_ENC 0x8 /* Partial Header Encryption Supported */ > +#define PCI_IDE_CAP_AGGREGATION 0x10 /* Aggregation Supported */ > +#define PCI_IDE_CAP_PCRC 0x20 /* PCRC Supported */ > +#define PCI_IDE_CAP_IDE_KM 0x40 /* IDE_KM Protocol Supported */ > +#define PCI_IDE_CAP_SEL_CFG 0x80 /* Selective IDE for Config Request Support */ > +#define PCI_IDE_CAP_ALG __GENMASK(12, 8) /* Supported Algorithms */ > +#define PCI_IDE_CAP_ALG_AES_GCM_256 0 /* AES-GCM 256 key size, 96b MAC */ > +#define PCI_IDE_CAP_LINK_TC_NUM __GENMASK(15, 13) /* Link IDE TCs */ > +#define PCI_IDE_CAP_SEL_NUM __GENMASK(23, 16) /* Supported Selective IDE Streams */ > +#define PCI_IDE_CAP_TEE_LIMITED 0x1000000 /* TEE-Limited Stream Supported */ > +#define PCI_IDE_CTL 0x08 > +#define PCI_IDE_CTL_FLOWTHROUGH_IDE 0x4 /* Flow-Through IDE Stream Enabled */ > + > +#define PCI_IDE_LINK_STREAM_0 0xc /* First Link Stream Register Block */ > +#define PCI_IDE_LINK_BLOCK_SIZE 8 > +/* Link IDE Stream block, up to PCI_IDE_CAP_LINK_TC_NUM */ > +#define PCI_IDE_LINK_CTL_0 0x00 /* First Link Control Register Offset in block */ > +#define PCI_IDE_LINK_CTL_EN 0x1 /* Link IDE Stream Enable */ > +#define PCI_IDE_LINK_CTL_TX_AGGR_NPR __GENMASK(3, 2) /* Tx Aggregation Mode NPR */ > +#define PCI_IDE_LINK_CTL_TX_AGGR_PR __GENMASK(5, 4) /* Tx Aggregation Mode PR */ > +#define PCI_IDE_LINK_CTL_TX_AGGR_CPL __GENMASK(7, 6) /* Tx Aggregation Mode CPL */ > +#define PCI_IDE_LINK_CTL_PCRC_EN 0x100 /* PCRC Enable */ > +#define PCI_IDE_LINK_CTL_PART_ENC __GENMASK(13, 10) /* Partial Header Encryption Mode */ > +#define PCI_IDE_LINK_CTL_ALG __GENMASK(18, 14) /* Selection from PCI_IDE_CAP_ALG */ > +#define PCI_IDE_LINK_CTL_TC __GENMASK(21, 19) /* Traffic Class */ > +#define PCI_IDE_LINK_CTL_ID __GENMASK(31, 24) /* Stream ID */ > +#define PCI_IDE_LINK_STS_0 0x4 /* First Link Status Register Offset in block */ > +#define PCI_IDE_LINK_STS_STATE __GENMASK(3, 0) /* Link IDE Stream State */ > +#define PCI_IDE_LINK_STS_IDE_FAIL 0x80000000 /* IDE fail message received */ > + > +/* Selective IDE Stream block, up to PCI_IDE_CAP_SELECTIVE_STREAMS_NUM */ > +/* Selective IDE Stream Capability Register */ > +#define PCI_IDE_SEL_CAP 0x00 > +#define PCI_IDE_SEL_CAP_ASSOC_NUM __GENMASK(3, 0) > +/* Selective IDE Stream Control Register */ > +#define PCI_IDE_SEL_CTL 0x04 > +#define PCI_IDE_SEL_CTL_EN 0x1 /* Selective IDE Stream Enable */ > +#define PCI_IDE_SEL_CTL_TX_AGGR_NPR __GENMASK(3, 2) /* Tx Aggregation Mode NPR */ > +#define PCI_IDE_SEL_CTL_TX_AGGR_PR __GENMASK(5, 4) /* Tx Aggregation Mode PR */ > +#define PCI_IDE_SEL_CTL_TX_AGGR_CPL __GENMASK(7, 6) /* Tx Aggregation Mode CPL */ > +#define PCI_IDE_SEL_CTL_PCRC_EN 0x100 /* PCRC Enable */ > +#define PCI_IDE_SEL_CTL_CFG_EN 0x200 /* Selective IDE for Configuration Requests */ > +#define PCI_IDE_SEL_CTL_PART_ENC __GENMASK(13, 10) /* Partial Header Encryption Mode */ > +#define PCI_IDE_SEL_CTL_ALG __GENMASK(18, 14) /* Selection from PCI_IDE_CAP_ALG */ > +#define PCI_IDE_SEL_CTL_TC __GENMASK(21, 19) /* Traffic Class */ > +#define PCI_IDE_SEL_CTL_DEFAULT 0x400000 /* Default Stream */ > +#define PCI_IDE_SEL_CTL_TEE_LIMITED 0x800000 /* TEE-Limited Stream */ > +#define PCI_IDE_SEL_CTL_ID __GENMASK(31, 24) /* Stream ID */ > +#define PCI_IDE_SEL_CTL_ID_MAX 255 > +/* Selective IDE Stream Status Register */ > +#define PCI_IDE_SEL_STS 0x08 > +#define PCI_IDE_SEL_STS_STATE __GENMASK(3, 0) /* Selective IDE Stream State */ > +#define PCI_IDE_SEL_STS_STATE_INSECURE 0 > +#define PCI_IDE_SEL_STS_STATE_SECURE 2 > +#define PCI_IDE_SEL_STS_IDE_FAIL 0x80000000 /* IDE fail message received */ > +/* IDE RID Association Register 1 */ > +#define PCI_IDE_SEL_RID_1 0x0c > +#define PCI_IDE_SEL_RID_1_LIMIT __GENMASK(23, 8) > +/* IDE RID Association Register 2 */ > +#define PCI_IDE_SEL_RID_2 0x10 > +#define PCI_IDE_SEL_RID_2_VALID 0x1 > +#define PCI_IDE_SEL_RID_2_BASE __GENMASK(23, 8) > +#define PCI_IDE_SEL_RID_2_SEG __GENMASK(31, 24) > +/* Selective IDE Address Association Register Block, up to PCI_IDE_SEL_CAP_ASSOC_NUM */ > +#define PCI_IDE_SEL_ADDR_BLOCK_SIZE 12 > +#define PCI_IDE_SEL_ADDR_1(x) (20 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) > +#define PCI_IDE_SEL_ADDR_1_VALID 0x1 > +#define PCI_IDE_SEL_ADDR_1_BASE_LOW __GENMASK(19, 8) > +#define PCI_IDE_SEL_ADDR_1_LIMIT_LOW __GENMASK(31, 20) > +/* IDE Address Association Register 2 is "Memory Limit Upper" */ > +#define PCI_IDE_SEL_ADDR_2(x) (24 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) > +/* IDE Address Association Register 3 is "Memory Base Upper" */ > +#define PCI_IDE_SEL_ADDR_3(x) (28 + (x) * PCI_IDE_SEL_ADDR_BLOCK_SIZE) > +#define PCI_IDE_SEL_BLOCK_SIZE(nr_assoc) (20 + PCI_IDE_SEL_ADDR_BLOCK_SIZE * (nr_assoc)) > + > #endif /* LINUX_PCI_REGS_H */ > diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h > index 93abaae0b9..17a0174d6c 100644 > --- a/include/standard-headers/linux/virtio_net.h > +++ b/include/standard-headers/linux/virtio_net.h > @@ -193,7 +193,8 @@ struct virtio_net_hdr_v1 { > > struct virtio_net_hdr_v1_hash { > struct virtio_net_hdr_v1 hdr; > - uint32_t hash_value; > + uint16_t hash_value_lo; > + uint16_t hash_value_hi; > #define VIRTIO_NET_HASH_REPORT_NONE 0 > #define VIRTIO_NET_HASH_REPORT_IPv4 1 > #define VIRTIO_NET_HASH_REPORT_TCPv4 2 > diff --git a/include/standard-headers/linux/virtio_pci.h b/include/standard-headers/linux/virtio_pci.h > index 09e964e6ee..4c82513df2 100644 > --- a/include/standard-headers/linux/virtio_pci.h > +++ b/include/standard-headers/linux/virtio_pci.h > @@ -40,7 +40,7 @@ > #define _LINUX_VIRTIO_PCI_H > > #include "standard-headers/linux/types.h" > -#include "standard-headers/linux/kernel.h" > +#include "standard-headers/linux/const.h" > > #ifndef VIRTIO_PCI_NO_LEGACY > > diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h > index f4d9baafa1..46ffbddab5 100644 > --- a/linux-headers/asm-arm64/kvm.h > +++ b/linux-headers/asm-arm64/kvm.h > @@ -31,7 +31,7 @@ > #define KVM_SPSR_FIQ 4 > #define KVM_NR_SPSR 5 > > -#ifndef __ASSEMBLY__ > +#ifndef __ASSEMBLER__ > #include <linux/psci.h> > #include <linux/types.h> > #include <asm/ptrace.h> > diff --git a/linux-headers/asm-arm64/unistd_64.h b/linux-headers/asm-arm64/unistd_64.h > index 4ae25c2b91..1ef9c40813 100644 > --- a/linux-headers/asm-arm64/unistd_64.h > +++ b/linux-headers/asm-arm64/unistd_64.h > @@ -326,6 +326,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_64_H */ > diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h > index 04e0077fb4..942370b3f5 100644 > --- a/linux-headers/asm-generic/unistd.h > +++ b/linux-headers/asm-generic/unistd.h > @@ -857,9 +857,11 @@ __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) > __SYSCALL(__NR_file_getattr, sys_file_getattr) > #define __NR_file_setattr 469 > __SYSCALL(__NR_file_setattr, sys_file_setattr) > +#define __NR_listns 470 > +__SYSCALL(__NR_listns, sys_listns) > > #undef __NR_syscalls > -#define __NR_syscalls 470 > +#define __NR_syscalls 471 > > /* > * 32 bit systems traditionally used different > diff --git a/linux-headers/asm-loongarch/kvm.h b/linux-headers/asm-loongarch/kvm.h > index 57ba1a563b..de6c3f18e4 100644 > --- a/linux-headers/asm-loongarch/kvm.h > +++ b/linux-headers/asm-loongarch/kvm.h > @@ -104,6 +104,7 @@ struct kvm_fpu { > #define KVM_LOONGARCH_VM_FEAT_PV_IPI 6 > #define KVM_LOONGARCH_VM_FEAT_PV_STEALTIME 7 > #define KVM_LOONGARCH_VM_FEAT_PTW 8 > +#define KVM_LOONGARCH_VM_FEAT_MSGINT 9 > > /* Device Control API on vcpu fd */ > #define KVM_LOONGARCH_VCPU_CPUCFG 0 > diff --git a/linux-headers/asm-loongarch/unistd.h b/linux-headers/asm-loongarch/unistd.h > index 1f01980f9c..e19c7f2f9f 100644 > --- a/linux-headers/asm-loongarch/unistd.h > +++ b/linux-headers/asm-loongarch/unistd.h > @@ -1,3 +1,9 @@ > /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ > > +#include <asm/bitsperlong.h> > + > +#if __BITS_PER_LONG == 32 > +#include <asm/unistd_32.h> > +#else > #include <asm/unistd_64.h> > +#endif > diff --git a/linux-headers/asm-loongarch/unistd_64.h b/linux-headers/asm-loongarch/unistd_64.h > index 5033fc8f2f..aa5daac4ef 100644 > --- a/linux-headers/asm-loongarch/unistd_64.h > +++ b/linux-headers/asm-loongarch/unistd_64.h > @@ -322,6 +322,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_64_H */ > diff --git a/linux-headers/asm-mips/unistd_n32.h b/linux-headers/asm-mips/unistd_n32.h > index c99c10e5bf..a33d106dca 100644 > --- a/linux-headers/asm-mips/unistd_n32.h > +++ b/linux-headers/asm-mips/unistd_n32.h > @@ -398,5 +398,6 @@ > #define __NR_open_tree_attr (__NR_Linux + 467) > #define __NR_file_getattr (__NR_Linux + 468) > #define __NR_file_setattr (__NR_Linux + 469) > +#define __NR_listns (__NR_Linux + 470) > > #endif /* _ASM_UNISTD_N32_H */ > diff --git a/linux-headers/asm-mips/unistd_n64.h b/linux-headers/asm-mips/unistd_n64.h > index 0d975bb185..1bc251e450 100644 > --- a/linux-headers/asm-mips/unistd_n64.h > +++ b/linux-headers/asm-mips/unistd_n64.h > @@ -374,5 +374,6 @@ > #define __NR_open_tree_attr (__NR_Linux + 467) > #define __NR_file_getattr (__NR_Linux + 468) > #define __NR_file_setattr (__NR_Linux + 469) > +#define __NR_listns (__NR_Linux + 470) > > #endif /* _ASM_UNISTD_N64_H */ > diff --git a/linux-headers/asm-mips/unistd_o32.h b/linux-headers/asm-mips/unistd_o32.h > index 86ac0ac84b..c57175d496 100644 > --- a/linux-headers/asm-mips/unistd_o32.h > +++ b/linux-headers/asm-mips/unistd_o32.h > @@ -444,5 +444,6 @@ > #define __NR_open_tree_attr (__NR_Linux + 467) > #define __NR_file_getattr (__NR_Linux + 468) > #define __NR_file_setattr (__NR_Linux + 469) > +#define __NR_listns (__NR_Linux + 470) > > #endif /* _ASM_UNISTD_O32_H */ > diff --git a/linux-headers/asm-powerpc/unistd_32.h b/linux-headers/asm-powerpc/unistd_32.h > index d7a32c5e06..a3f4aa2fe2 100644 > --- a/linux-headers/asm-powerpc/unistd_32.h > +++ b/linux-headers/asm-powerpc/unistd_32.h > @@ -451,6 +451,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_32_H */ > diff --git a/linux-headers/asm-powerpc/unistd_64.h b/linux-headers/asm-powerpc/unistd_64.h > index ff35c51fc6..d4444557f1 100644 > --- a/linux-headers/asm-powerpc/unistd_64.h > +++ b/linux-headers/asm-powerpc/unistd_64.h > @@ -423,6 +423,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_64_H */ > diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h > index 759a4852c0..54f3ad7ed2 100644 > --- a/linux-headers/asm-riscv/kvm.h > +++ b/linux-headers/asm-riscv/kvm.h > @@ -23,6 +23,8 @@ > #define KVM_INTERRUPT_SET -1U > #define KVM_INTERRUPT_UNSET -2U > > +#define KVM_EXIT_FAIL_ENTRY_NO_VSFILE (1ULL << 0) > + > /* for KVM_GET_REGS and KVM_SET_REGS */ > struct kvm_regs { > }; > @@ -211,6 +213,7 @@ enum KVM_RISCV_SBI_EXT_ID { > KVM_RISCV_SBI_EXT_STA, > KVM_RISCV_SBI_EXT_SUSP, > KVM_RISCV_SBI_EXT_FWFT, > + KVM_RISCV_SBI_EXT_MPXY, > KVM_RISCV_SBI_EXT_MAX, > }; > > diff --git a/linux-headers/asm-riscv/unistd_32.h b/linux-headers/asm-riscv/unistd_32.h > index 6083373e88..9f33956246 100644 > --- a/linux-headers/asm-riscv/unistd_32.h > +++ b/linux-headers/asm-riscv/unistd_32.h > @@ -317,6 +317,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_32_H */ > diff --git a/linux-headers/asm-riscv/unistd_64.h b/linux-headers/asm-riscv/unistd_64.h > index f0c7585c60..c2e7258916 100644 > --- a/linux-headers/asm-riscv/unistd_64.h > +++ b/linux-headers/asm-riscv/unistd_64.h > @@ -327,6 +327,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_64_H */ > diff --git a/linux-headers/asm-s390/bitsperlong.h b/linux-headers/asm-s390/bitsperlong.h > index cceaf47b02..7af27a985f 100644 > --- a/linux-headers/asm-s390/bitsperlong.h > +++ b/linux-headers/asm-s390/bitsperlong.h > @@ -2,11 +2,7 @@ > #ifndef __ASM_S390_BITSPERLONG_H > #define __ASM_S390_BITSPERLONG_H > > -#ifndef __s390x__ > -#define __BITS_PER_LONG 32 > -#else > #define __BITS_PER_LONG 64 > -#endif > > #include <asm-generic/bitsperlong.h> > > diff --git a/linux-headers/asm-s390/unistd.h b/linux-headers/asm-s390/unistd.h > index 27b8b211c8..1484618877 100644 > --- a/linux-headers/asm-s390/unistd.h > +++ b/linux-headers/asm-s390/unistd.h > @@ -8,10 +8,6 @@ > #ifndef _ASM_S390_UNISTD_H_ > #define _ASM_S390_UNISTD_H_ > > -#ifdef __s390x__ > #include <asm/unistd_64.h> > -#else > -#include <asm/unistd_32.h> > -#endif > > #endif /* _ASM_S390_UNISTD_H_ */ > diff --git a/linux-headers/asm-s390/unistd_64.h b/linux-headers/asm-s390/unistd_64.h > index 0652ba6331..8d9e579ef5 100644 > --- a/linux-headers/asm-s390/unistd_64.h > +++ b/linux-headers/asm-s390/unistd_64.h > @@ -1,6 +1,5 @@ > -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ > -#ifndef _ASM_S390_UNISTD_64_H > -#define _ASM_S390_UNISTD_64_H > +#ifndef _ASM_UNISTD_64_H > +#define _ASM_UNISTD_64_H > > #define __NR_exit 1 > #define __NR_fork 2 > @@ -390,5 +389,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > -#endif /* _ASM_S390_UNISTD_64_H */ > + > +#endif /* _ASM_UNISTD_64_H */ > diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h > index 3bb38f6c3a..b804fd25a2 100644 > --- a/linux-headers/asm-x86/kvm.h > +++ b/linux-headers/asm-x86/kvm.h > @@ -500,6 +500,7 @@ struct kvm_sync_regs { > /* vendor-specific groups and attributes for system fd */ > #define KVM_X86_GRP_SEV 1 > # define KVM_X86_SEV_VMSA_FEATURES 0 > +# define KVM_X86_SNP_POLICY_BITS 1 > > struct kvm_vmx_nested_state_data { > __u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE]; > diff --git a/linux-headers/asm-x86/unistd_32.h b/linux-headers/asm-x86/unistd_32.h > index 8f784a5634..34255aac64 100644 > --- a/linux-headers/asm-x86/unistd_32.h > +++ b/linux-headers/asm-x86/unistd_32.h > @@ -460,6 +460,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_32_H */ > diff --git a/linux-headers/asm-x86/unistd_64.h b/linux-headers/asm-x86/unistd_64.h > index 26c258d1a6..07f242a5fa 100644 > --- a/linux-headers/asm-x86/unistd_64.h > +++ b/linux-headers/asm-x86/unistd_64.h > @@ -384,6 +384,7 @@ > #define __NR_open_tree_attr 467 > #define __NR_file_getattr 468 > #define __NR_file_setattr 469 > +#define __NR_listns 470 > > > #endif /* _ASM_UNISTD_64_H */ > diff --git a/linux-headers/asm-x86/unistd_x32.h b/linux-headers/asm-x86/unistd_x32.h > index 65c2aed946..08fc9da2fa 100644 > --- a/linux-headers/asm-x86/unistd_x32.h > +++ b/linux-headers/asm-x86/unistd_x32.h > @@ -337,6 +337,7 @@ > #define __NR_open_tree_attr (__X32_SYSCALL_BIT + 467) > #define __NR_file_getattr (__X32_SYSCALL_BIT + 468) > #define __NR_file_setattr (__X32_SYSCALL_BIT + 469) > +#define __NR_listns (__X32_SYSCALL_BIT + 470) > #define __NR_rt_sigaction (__X32_SYSCALL_BIT + 512) > #define __NR_rt_sigreturn (__X32_SYSCALL_BIT + 513) > #define __NR_ioctl (__X32_SYSCALL_BIT + 514) > diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h > index 2105a03955..384183a403 100644 > --- a/linux-headers/linux/iommufd.h > +++ b/linux-headers/linux/iommufd.h > @@ -450,6 +450,16 @@ struct iommu_hwpt_vtd_s1 { > * nested domain will translate the same as the nesting parent. The S1 will > * install a Context Descriptor Table pointing at userspace memory translated > * by the nesting parent. > + * > + * It's suggested to allocate a vDEVICE object carrying vSID and then re-attach > + * the nested domain, as soon as the vSID is available in the VMM level: > + * > + * - when Cfg=translate, a vDEVICE must be allocated prior to attaching to the > + * allocated nested domain, as CD/ATS invalidations and vevents need a vSID. > + * - when Cfg=bypass/abort, a vDEVICE is not enforced during the nested domain > + * attachment, to support a GBPA case where VM sets CR0.SMMUEN=0. However, if > + * VM sets CR0.SMMUEN=1 while missing a vDEVICE object, kernel would fail to > + * report events to the VM. E.g. F_TRANSLATION when guest STE.Cfg=abort. > */ > struct iommu_hwpt_arm_smmuv3 { > __aligned_le64 ste[2]; > diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h > index 4ea28ef7ca..a4ab42dcba 100644 > --- a/linux-headers/linux/kvm.h > +++ b/linux-headers/linux/kvm.h > @@ -179,6 +179,7 @@ struct kvm_xen_exit { > #define KVM_EXIT_LOONGARCH_IOCSR 38 > #define KVM_EXIT_MEMORY_FAULT 39 > #define KVM_EXIT_TDX 40 > +#define KVM_EXIT_ARM_SEA 41 > > /* For KVM_EXIT_INTERNAL_ERROR */ > /* Emulate instruction failed. */ > @@ -465,6 +466,14 @@ struct kvm_run { > } setup_event_notify; > }; > } tdx; > + /* KVM_EXIT_ARM_SEA */ > + struct { > +#define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID (1ULL << 0) > + __u64 flags; > + __u64 esr; > + __u64 gva; > + __u64 gpa; > + } arm_sea; > /* Fix the size of the union. */ > char padding[256]; > }; > @@ -955,6 +964,8 @@ struct kvm_enable_cap { > #define KVM_CAP_RISCV_MP_STATE_RESET 242 > #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 > #define KVM_CAP_GUEST_MEMFD_FLAGS 244 > +#define KVM_CAP_ARM_SEA_TO_USER 245 > +#define KVM_CAP_S390_USER_OPEREXEC 246 > > struct kvm_irq_routing_irqchip { > __u32 irqchip; > diff --git a/linux-headers/linux/mshv.h b/linux-headers/linux/mshv.h > index 5bc83db6a3..acceeddc1c 100644 > --- a/linux-headers/linux/mshv.h > +++ b/linux-headers/linux/mshv.h > @@ -26,6 +26,7 @@ enum { > MSHV_PT_BIT_LAPIC, > MSHV_PT_BIT_X2APIC, > MSHV_PT_BIT_GPA_SUPER_PAGES, > + MSHV_PT_BIT_CPU_AND_XSAVE_FEATURES, > MSHV_PT_BIT_COUNT, > }; > > @@ -41,6 +42,8 @@ enum { > * @pt_flags: Bitmask of 1 << MSHV_PT_BIT_* > * @pt_isolation: MSHV_PT_ISOLATION_* > * > + * This is the initial/v1 version for backward compatibility. > + * > * Returns a file descriptor to act as a handle to a guest partition. > * At this point the partition is not yet initialized in the hypervisor. > * Some operations must be done with the partition in this state, e.g. setting > @@ -52,6 +55,37 @@ struct mshv_create_partition { > __u64 pt_isolation; > }; > > +#define MSHV_NUM_CPU_FEATURES_BANKS 2 > + > +/** > + * struct mshv_create_partition_v2 > + * > + * This is extended version of the above initial MSHV_CREATE_PARTITION > + * ioctl and allows for following additional parameters: > + * > + * @pt_num_cpu_fbanks: Must be set to MSHV_NUM_CPU_FEATURES_BANKS. > + * @pt_cpu_fbanks: Disabled processor feature banks array. > + * @pt_disabled_xsave: Disabled xsave feature bits. > + * > + * pt_cpu_fbanks and pt_disabled_xsave are passed through as-is to the create > + * partition hypercall. > + * > + * Returns : same as above original mshv_create_partition > + */ > +struct mshv_create_partition_v2 { > + __u64 pt_flags; > + __u64 pt_isolation; > + __u16 pt_num_cpu_fbanks; > + __u8 pt_rsvd[6]; /* MBZ */ > + __u64 pt_cpu_fbanks[MSHV_NUM_CPU_FEATURES_BANKS]; > + __u64 pt_rsvd1[2]; /* MBZ */ > +#if defined(__x86_64__) > + __u64 pt_disabled_xsave; > +#else > + __u64 pt_rsvd2; /* MBZ */ > +#endif > +} __attribute__((packed)); > + > /* /dev/mshv */ > #define MSHV_CREATE_PARTITION _IOW(MSHV_IOCTL, 0x00, struct mshv_create_partition) > > @@ -89,7 +123,7 @@ enum { > * @rsvd: MBZ > * > * Map or unmap a region of userspace memory to Guest Physical Addresses (GPA). > - * Mappings can't overlap in GPA space or userspace. > + * Mappings can't overlap in GPA space. > * To unmap, these fields must match an existing mapping. > */ > struct mshv_user_mem_region { > @@ -288,4 +322,84 @@ struct mshv_get_set_vp_state { > * #define MSHV_ROOT_HVCALL _IOWR(MSHV_IOCTL, 0x07, struct mshv_root_hvcall) > */ > > +/* Structure definitions, macros and IOCTLs for mshv_vtl */ > + > +#define MSHV_CAP_CORE_API_STABLE 0x0 > +#define MSHV_CAP_REGISTER_PAGE 0x1 > +#define MSHV_CAP_VTL_RETURN_ACTION 0x2 > +#define MSHV_CAP_DR6_SHARED 0x3 > +#define MSHV_MAX_RUN_MSG_SIZE 256 > + > +struct mshv_vp_registers { > + __u32 count; /* supports only 1 register at a time */ > + __u32 reserved; /* Reserved for alignment or future use */ > + __u64 regs_ptr; /* pointer to struct hv_register_assoc */ > +}; > + > +struct mshv_vtl_set_eventfd { > + __s32 fd; > + __u32 flag; > +}; > + > +struct mshv_vtl_signal_event { > + __u32 connection_id; > + __u32 flag; > +}; > + > +struct mshv_vtl_sint_post_msg { > + __u64 message_type; > + __u32 connection_id; > + __u32 payload_size; /* Must not exceed HV_MESSAGE_PAYLOAD_BYTE_COUNT */ > + __u64 payload_ptr; /* pointer to message payload (bytes) */ > +}; > + > +struct mshv_vtl_ram_disposition { > + __u64 start_pfn; > + __u64 last_pfn; > +}; > + > +struct mshv_vtl_set_poll_file { > + __u32 cpu; > + __u32 fd; > +}; > + > +struct mshv_vtl_hvcall_setup { > + __u64 bitmap_array_size; /* stores number of bytes */ > + __u64 allow_bitmap_ptr; > +}; > + > +struct mshv_vtl_hvcall { > + __u64 control; /* Hypercall control code */ > + __u64 input_size; /* Size of the input data */ > + __u64 input_ptr; /* Pointer to the input struct */ > + __u64 status; /* Status of the hypercall (output) */ > + __u64 output_size; /* Size of the output data */ > + __u64 output_ptr; /* Pointer to the output struct */ > +}; > + > +struct mshv_sint_mask { > + __u8 mask; > + __u8 reserved[7]; > +}; > + > +/* /dev/mshv device IOCTL */ > +#define MSHV_CHECK_EXTENSION _IOW(MSHV_IOCTL, 0x00, __u32) > + > +/* vtl device */ > +#define MSHV_CREATE_VTL _IOR(MSHV_IOCTL, 0x1D, char) > +#define MSHV_ADD_VTL0_MEMORY _IOW(MSHV_IOCTL, 0x21, struct mshv_vtl_ram_disposition) > +#define MSHV_SET_POLL_FILE _IOW(MSHV_IOCTL, 0x25, struct mshv_vtl_set_poll_file) > +#define MSHV_RETURN_TO_LOWER_VTL _IO(MSHV_IOCTL, 0x27) > +#define MSHV_GET_VP_REGISTERS _IOWR(MSHV_IOCTL, 0x05, struct mshv_vp_registers) > +#define MSHV_SET_VP_REGISTERS _IOW(MSHV_IOCTL, 0x06, struct mshv_vp_registers) > + > +/* VMBus device IOCTLs */ > +#define MSHV_SINT_SIGNAL_EVENT _IOW(MSHV_IOCTL, 0x22, struct mshv_vtl_signal_event) > +#define MSHV_SINT_POST_MESSAGE _IOW(MSHV_IOCTL, 0x23, struct mshv_vtl_sint_post_msg) > +#define MSHV_SINT_SET_EVENTFD _IOW(MSHV_IOCTL, 0x24, struct mshv_vtl_set_eventfd) > +#define MSHV_SINT_PAUSE_MESSAGE_STREAM _IOW(MSHV_IOCTL, 0x25, struct mshv_sint_mask) > + > +/* hv_hvcall device */ > +#define MSHV_HVCALL_SETUP _IOW(MSHV_IOCTL, 0x1E, struct mshv_vtl_hvcall_setup) > +#define MSHV_HVCALL _IOWR(MSHV_IOCTL, 0x1F, struct mshv_vtl_hvcall) > #endif > diff --git a/linux-headers/linux/psp-sev.h b/linux-headers/linux/psp-sev.h > index c525125ea8..9479928a4a 100644 > --- a/linux-headers/linux/psp-sev.h > +++ b/linux-headers/linux/psp-sev.h > @@ -47,32 +47,32 @@ typedef enum { > * with possible values from the specification. > */ > SEV_RET_NO_FW_CALL = -1, > - SEV_RET_SUCCESS = 0, > - SEV_RET_INVALID_PLATFORM_STATE, > - SEV_RET_INVALID_GUEST_STATE, > - SEV_RET_INAVLID_CONFIG, > + SEV_RET_SUCCESS = 0, > + SEV_RET_INVALID_PLATFORM_STATE = 0x0001, > + SEV_RET_INVALID_GUEST_STATE = 0x0002, > + SEV_RET_INAVLID_CONFIG = 0x0003, > SEV_RET_INVALID_CONFIG = SEV_RET_INAVLID_CONFIG, > - SEV_RET_INVALID_LEN, > - SEV_RET_ALREADY_OWNED, > - SEV_RET_INVALID_CERTIFICATE, > - SEV_RET_POLICY_FAILURE, > - SEV_RET_INACTIVE, > - SEV_RET_INVALID_ADDRESS, > - SEV_RET_BAD_SIGNATURE, > - SEV_RET_BAD_MEASUREMENT, > - SEV_RET_ASID_OWNED, > - SEV_RET_INVALID_ASID, > - SEV_RET_WBINVD_REQUIRED, > - SEV_RET_DFFLUSH_REQUIRED, > - SEV_RET_INVALID_GUEST, > - SEV_RET_INVALID_COMMAND, > - SEV_RET_ACTIVE, > - SEV_RET_HWSEV_RET_PLATFORM, > - SEV_RET_HWSEV_RET_UNSAFE, > - SEV_RET_UNSUPPORTED, > - SEV_RET_INVALID_PARAM, > - SEV_RET_RESOURCE_LIMIT, > - SEV_RET_SECURE_DATA_INVALID, > + SEV_RET_INVALID_LEN = 0x0004, > + SEV_RET_ALREADY_OWNED = 0x0005, > + SEV_RET_INVALID_CERTIFICATE = 0x0006, > + SEV_RET_POLICY_FAILURE = 0x0007, > + SEV_RET_INACTIVE = 0x0008, > + SEV_RET_INVALID_ADDRESS = 0x0009, > + SEV_RET_BAD_SIGNATURE = 0x000A, > + SEV_RET_BAD_MEASUREMENT = 0x000B, > + SEV_RET_ASID_OWNED = 0x000C, > + SEV_RET_INVALID_ASID = 0x000D, > + SEV_RET_WBINVD_REQUIRED = 0x000E, > + SEV_RET_DFFLUSH_REQUIRED = 0x000F, > + SEV_RET_INVALID_GUEST = 0x0010, > + SEV_RET_INVALID_COMMAND = 0x0011, > + SEV_RET_ACTIVE = 0x0012, > + SEV_RET_HWSEV_RET_PLATFORM = 0x0013, > + SEV_RET_HWSEV_RET_UNSAFE = 0x0014, > + SEV_RET_UNSUPPORTED = 0x0015, > + SEV_RET_INVALID_PARAM = 0x0016, > + SEV_RET_RESOURCE_LIMIT = 0x0017, > + SEV_RET_SECURE_DATA_INVALID = 0x0018, > SEV_RET_INVALID_PAGE_SIZE = 0x0019, > SEV_RET_INVALID_PAGE_STATE = 0x001A, > SEV_RET_INVALID_MDATA_ENTRY = 0x001B, > @@ -87,6 +87,22 @@ typedef enum { > SEV_RET_RESTORE_REQUIRED = 0x0025, > SEV_RET_RMP_INITIALIZATION_FAILED = 0x0026, > SEV_RET_INVALID_KEY = 0x0027, > + SEV_RET_SHUTDOWN_INCOMPLETE = 0x0028, > + SEV_RET_INCORRECT_BUFFER_LENGTH = 0x0030, > + SEV_RET_EXPAND_BUFFER_LENGTH_REQUEST = 0x0031, > + SEV_RET_SPDM_REQUEST = 0x0032, > + SEV_RET_SPDM_ERROR = 0x0033, > + SEV_RET_SEV_STATUS_ERR_IN_DEV_CONN = 0x0035, > + SEV_RET_SEV_STATUS_INVALID_DEV_CTX = 0x0036, > + SEV_RET_SEV_STATUS_INVALID_TDI_CTX = 0x0037, > + SEV_RET_SEV_STATUS_INVALID_TDI = 0x0038, > + SEV_RET_SEV_STATUS_RECLAIM_REQUIRED = 0x0039, > + SEV_RET_IN_USE = 0x003A, > + SEV_RET_SEV_STATUS_INVALID_DEV_STATE = 0x003B, > + SEV_RET_SEV_STATUS_INVALID_TDI_STATE = 0x003C, > + SEV_RET_SEV_STATUS_DEV_CERT_CHANGED = 0x003D, > + SEV_RET_SEV_STATUS_RESYNC_REQ = 0x003E, > + SEV_RET_SEV_STATUS_RESPONSE_TOO_LARGE = 0x003F, > SEV_RET_MAX, > } sev_ret_code; > > diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h > index 4d96d1fc12..720edfee7a 100644 > --- a/linux-headers/linux/vfio.h > +++ b/linux-headers/linux/vfio.h > @@ -14,6 +14,7 @@ > > #include <linux/types.h> > #include <linux/ioctl.h> > +#include <linux/stddef.h> > > #define VFIO_API_VERSION 0 > > @@ -1478,6 +1479,33 @@ struct vfio_device_feature_bus_master { > }; > #define VFIO_DEVICE_FEATURE_BUS_MASTER 10 > > +/** > + * Upon VFIO_DEVICE_FEATURE_GET create a dma_buf fd for the > + * regions selected. > + * > + * open_flags are the typical flags passed to open(2), eg O_RDWR, O_CLOEXEC, > + * etc. offset/length specify a slice of the region to create the dmabuf from. > + * nr_ranges is the total number of (P2P DMA) ranges that comprise the dmabuf. > + * > + * flags should be 0. > + * > + * Return: The fd number on success, -1 and errno is set on failure. > + */ > +#define VFIO_DEVICE_FEATURE_DMA_BUF 11 > + > +struct vfio_region_dma_range { > + __u64 offset; > + __u64 length; > +}; > + > +struct vfio_device_feature_dma_buf { > + __u32 region_index; > + __u32 open_flags; > + __u32 flags; > + __u32 nr_ranges; > + struct vfio_region_dma_range dma_ranges[] __counted_by(nr_ranges); > +}; > + > /* -------- API for Type1 VFIO IOMMU -------- */ > > /** ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 2026-01-21 14:00 ` Cédric Le Goater @ 2026-01-21 14:21 ` Peter Maydell 2026-01-21 17:12 ` Jason Gunthorpe 0 siblings, 1 reply; 16+ messages in thread From: Peter Maydell @ 2026-01-21 14:21 UTC (permalink / raw) To: Cédric Le Goater Cc: Shameer Kolothum, qemu-arm, qemu-devel, eric.auger, alex, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, Jason Wang On Wed, 21 Jan 2026 at 14:02, Cédric Le Goater <clg@redhat.com> wrote: > > On 1/21/26 12:41, Shameer Kolothum wrote: > > Mainly for adding support for VFIO DMABUF. While at it, update all > > headers. > > > > The header update breaks virtio-net due to virtio_net_hdr_v1_hash > > changes. Include the virtio-net changes to avoid build and bisect > > failures. > > > > Cc: Michael S. Tsirkin <mst@redhat.com> > > Cc: Jason Wang <jasowang@redhat.com> > > Tested-by: Nicolin Chen <nicolinc@nvidia.com> > > Reviewed-by: Cédric Le Goater <clg@redhat.com> > > Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> > > --- > > hw/net/virtio-net.c | 11 +- > > Recent commit 503eb470e087 ("scripts/checkpatch: more checks on files > imported from Linux") added a check on the imported files and checkpatch > now complains with : > > ERROR: headers imported from Linux should be self-contained in a patch with no other changes > #101: FILE: include/standard-headers/drm/drm_fourcc.h:978: > * 2 = Gob Height 8, Turing+ Page Kind mapping > > > I suspect there is an error in the name of the file in question. > > Anyhow, feedbacks are welcome because I doubt this check is > valid in this situation and I am ready to apply this change > as is. The virtio-net.c change should not be in here. The change should be staged in a way that virtio-net.c gets updated first so it can cope with either the old header or the new header. But it looks to me like this is a bug in the Linux headers: they seem to have changed in a non-backwards compatible way, and possibly even in a way that makes it not possible for userspace code to use ifdefs to handle "maybe the header is the old version or the new version". Ideally the kernel headers should be fixed upstream to revert their compatibility break, I think. thanks -- PMM ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 2026-01-21 14:21 ` Peter Maydell @ 2026-01-21 17:12 ` Jason Gunthorpe 2026-01-23 14:26 ` Cédric Le Goater 0 siblings, 1 reply; 16+ messages in thread From: Jason Gunthorpe @ 2026-01-21 17:12 UTC (permalink / raw) To: Peter Maydell Cc: Cédric Le Goater, Shameer Kolothum, qemu-arm, qemu-devel, eric.auger, alex, cohuck, mst, nicolinc, nathanc, mochs, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, Jason Wang On Wed, Jan 21, 2026 at 02:21:17PM +0000, Peter Maydell wrote: > But it looks to me like this is a bug in the Linux headers: > they seem to have changed in a non-backwards compatible way, > and possibly even in a way that makes it not possible for > userspace code to use ifdefs to handle "maybe the header > is the old version or the new version". Technically Linux doesn't provide an API guarentee, just an ABI guarentee. Ie we don't guarentee all old userspace compiles with the new headers, we just guarentee that once compiled it keeps working.. You need to use something like configure and compile trial tests to figure things out. IMHO this happens rarely enough that what is proposed here as a single patch is the best option. Jason ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 2026-01-21 17:12 ` Jason Gunthorpe @ 2026-01-23 14:26 ` Cédric Le Goater 0 siblings, 0 replies; 16+ messages in thread From: Cédric Le Goater @ 2026-01-23 14:26 UTC (permalink / raw) To: Jason Gunthorpe, Peter Maydell Cc: Shameer Kolothum, qemu-arm, qemu-devel, eric.auger, alex, cohuck, mst, nicolinc, nathanc, mochs, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, Jason Wang On 1/21/26 18:12, Jason Gunthorpe wrote: > On Wed, Jan 21, 2026 at 02:21:17PM +0000, Peter Maydell wrote: >> But it looks to me like this is a bug in the Linux headers: >> they seem to have changed in a non-backwards compatible way, >> and possibly even in a way that makes it not possible for >> userspace code to use ifdefs to handle "maybe the header >> is the old version or the new version". > > Technically Linux doesn't provide an API guarentee, just an ABI > guarentee. > > Ie we don't guarentee all old userspace compiles with the new headers, > we just guarentee that once compiled it keeps working.. > > You need to use something like configure and compile trial tests to > figure things out. > > IMHO this happens rarely enough that what is proposed here as a single > patch is the best option. If no more objections, I will send a PR with these changes early next week then. Thanks, C. ^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v4 2/3] hw/vfio: Add helper to retrieve device feature 2026-01-21 11:41 [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Shameer Kolothum 2026-01-21 11:41 ` [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 Shameer Kolothum @ 2026-01-21 11:41 ` Shameer Kolothum 2026-01-21 11:41 ` [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region Shameer Kolothum ` (2 subsequent siblings) 4 siblings, 0 replies; 16+ messages in thread From: Shameer Kolothum @ 2026-01-21 11:41 UTC (permalink / raw) To: qemu-arm, qemu-devel Cc: eric.auger, alex, clg, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju Add vfio_device_get_feature() as a common helper to retrieve VFIO device features. No functional change intended. Reviewed-by: Cédric Le Goater <clg@redhat.com> Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> --- hw/vfio/container.c | 2 +- hw/vfio/device.c | 9 +++++++++ hw/vfio/listener.c | 4 ++-- include/hw/vfio/vfio-device.h | 3 +++ 4 files changed, 15 insertions(+), 3 deletions(-) diff --git a/hw/vfio/container.c b/hw/vfio/container.c index af16cd14db..4c2816b574 100644 --- a/hw/vfio/container.c +++ b/hw/vfio/container.c @@ -205,7 +205,7 @@ static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova, feature->flags = VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT; - return vbasedev->io_ops->device_feature(vbasedev, feature); + return vfio_device_get_feature(vbasedev, feature); } static int vfio_container_iommu_query_dirty_bitmap( diff --git a/hw/vfio/device.c b/hw/vfio/device.c index 086f20f676..973fc35b59 100644 --- a/hw/vfio/device.c +++ b/hw/vfio/device.c @@ -547,6 +547,15 @@ bool vfio_device_get_host_iommu_quirk_bypass_ro(VFIODevice *vbasedev, return false; } +int vfio_device_get_feature(VFIODevice *vbasedev, + struct vfio_device_feature *feature) +{ + if (!vbasedev->io_ops || !vbasedev->io_ops->device_feature) { + return -EINVAL; + } + return vbasedev->io_ops->device_feature(vbasedev, feature); +} + /* * Traditional ioctl() based io */ diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c index 8ba1cd255d..1087fdc142 100644 --- a/hw/vfio/listener.c +++ b/hw/vfio/listener.c @@ -909,7 +909,7 @@ static void vfio_devices_dma_logging_stop(VFIOContainer *bcontainer) continue; } - ret = vbasedev->io_ops->device_feature(vbasedev, feature); + ret = vfio_device_get_feature(vbasedev, feature); if (ret != 0) { warn_report("%s: Failed to stop DMA logging, err %d (%s)", @@ -1014,7 +1014,7 @@ static bool vfio_devices_dma_logging_start(VFIOContainer *bcontainer, continue; } - ret = vbasedev->io_ops->device_feature(vbasedev, feature); + ret = vfio_device_get_feature(vbasedev, feature); if (ret) { error_setg_errno(errp, -ret, "%s: Failed to start DMA logging", vbasedev->name); diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h index f6f3d0e378..35a5ec6d92 100644 --- a/include/hw/vfio/vfio-device.h +++ b/include/hw/vfio/vfio-device.h @@ -272,6 +272,9 @@ bool vfio_device_get_host_iommu_quirk_bypass_ro(VFIODevice *vbasedev, uint32_t type, void *caps, uint32_t size); +int vfio_device_get_feature(VFIODevice *vbasedev, + struct vfio_device_feature *feature); + int vfio_device_get_region_info(VFIODevice *vbasedev, int index, struct vfio_region_info **info); int vfio_device_get_region_info_type(VFIODevice *vbasedev, uint32_t type, -- 2.43.0 ^ permalink raw reply related [flat|nested] 16+ messages in thread
* [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region 2026-01-21 11:41 [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Shameer Kolothum 2026-01-21 11:41 ` [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 Shameer Kolothum 2026-01-21 11:41 ` [PATCH v4 2/3] hw/vfio: Add helper to retrieve device feature Shameer Kolothum @ 2026-01-21 11:41 ` Shameer Kolothum 2026-08-05 1:09 ` Gavin Shan 2026-01-21 12:36 ` [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Michael S. Tsirkin 2026-01-21 12:49 ` Eric Auger 4 siblings, 1 reply; 16+ messages in thread From: Shameer Kolothum @ 2026-01-21 11:41 UTC (permalink / raw) To: qemu-arm, qemu-devel Cc: eric.auger, alex, clg, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju From: Nicolin Chen <nicolinc@nvidia.com> Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for P2P use cases. Create a dmabuf for each mapped BAR region after the mmap is set up, and store the returned fd in the region’s RAMBlock. This allows QEMU to pass the fd to dma_map_file(), enabling iommufd to import the dmabuf and map the BAR correctly in the host IOMMU page table. If the kernel lacks support or dmabuf setup fails, QEMU skips the setup and continues with normal mmap handling. Tested-by: Nicolin Chen <nicolinc@nvidia.com> Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com> Reviewed-by: Cédric Le Goater <clg@redhat.com> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> --- hw/vfio/region.c | 65 +++++++++++++++++++++++++++++++++++++++++++- hw/vfio/trace-events | 1 + 2 files changed, 65 insertions(+), 1 deletion(-) diff --git a/hw/vfio/region.c b/hw/vfio/region.c index ca75ab1be4..ab39d77574 100644 --- a/hw/vfio/region.c +++ b/hw/vfio/region.c @@ -29,6 +29,7 @@ #include "qemu/error-report.h" #include "qemu/units.h" #include "monitor/monitor.h" +#include "system/ramblock.h" #include "vfio-helpers.h" /* @@ -238,13 +239,71 @@ static void vfio_subregion_unmap(VFIORegion *region, int index) region->mmaps[index].mmap = NULL; } +static bool vfio_region_create_dma_buf(VFIORegion *region, Error **errp) +{ + g_autofree struct vfio_device_feature *feature = NULL; + VFIODevice *vbasedev = region->vbasedev; + struct vfio_device_feature_dma_buf *dma_buf; + size_t total_size; + int i, ret; + + total_size = sizeof(*feature) + sizeof(*dma_buf) + + sizeof(struct vfio_region_dma_range) * region->nr_mmaps; + feature = g_malloc0(total_size); + *feature = (struct vfio_device_feature) { + .argsz = total_size, + .flags = VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_DMA_BUF, + }; + + dma_buf = (void *)feature->data; + *dma_buf = (struct vfio_device_feature_dma_buf) { + .region_index = region->nr, + .open_flags = O_RDWR, + .nr_ranges = region->nr_mmaps, + }; + + for (i = 0; i < region->nr_mmaps; i++) { + dma_buf->dma_ranges[i].offset = region->mmaps[i].offset; + dma_buf->dma_ranges[i].length = region->mmaps[i].size; + } + + ret = vfio_device_get_feature(vbasedev, feature); + if (ret < 0) { + if (ret == -ENOTTY) { + warn_report_once("VFIO dma-buf not supported in kernel: " + "PCI BAR IOMMU mappings may fail"); + return true; + } + /* P2P DMA or exposing device memory use cases are not supported. */ + error_setg_errno(errp, -ret, "%s: failed to create dma-buf: " + "PCI BAR IOMMU mappings may fail", + memory_region_name(region->mem)); + return false; + } + + /* Assign the dmabuf fd to associated RAMBlock */ + for (i = 0; i < region->nr_mmaps; i++) { + MemoryRegion *mr = ®ion->mmaps[i].mem; + RAMBlock *ram_block = mr->ram_block; + + ram_block->fd = ret; + ram_block->fd_offset = region->mmaps[i].offset; + trace_vfio_region_dmabuf(region->vbasedev->name, ret, region->nr, + memory_region_name(region->mem), + region->mmaps[i].offset, + region->mmaps[i].size); + } + return true; +} + int vfio_region_mmap(VFIORegion *region) { int i, ret, prot = 0; + Error *local_err = NULL; char *name; int fd; - if (!region->mem) { + if (!region->mem || !region->nr_mmaps) { return 0; } @@ -305,6 +364,10 @@ int vfio_region_mmap(VFIORegion *region) region->mmaps[i].size - 1); } + if (!vfio_region_create_dma_buf(region, &local_err)) { + error_report_err(local_err); + } + return 0; no_mmap: diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 180e3d526b..466695507b 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -118,6 +118,7 @@ vfio_device_put(int fd) "close vdev->fd=%d" vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)" vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64 vfio_region_setup(const char *dev, int index, const char *name, unsigned long flags, unsigned long offset, unsigned long size) "Device %s, region %d \"%s\", flags: 0x%lx, offset: 0x%lx, size: 0x%lx" +vfio_region_dmabuf(const char *dev, int fd, int index, const char *name, unsigned long offset, unsigned long size) "Device %s, dmabuf fd %d region %d \"%s\", offset: 0x%lx, size: 0x%lx" vfio_region_mmap_fault(const char *name, int index, unsigned long offset, unsigned long size, int fault) "Region %s mmaps[%d], [0x%lx - 0x%lx], fault: %d" vfio_region_mmap(const char *name, unsigned long offset, unsigned long end) "Region %s [0x%lx - 0x%lx]" vfio_region_exit(const char *name, int index) "Device %s, region %d" -- 2.43.0 ^ permalink raw reply related [flat|nested] 16+ messages in thread
* Re: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region 2026-01-21 11:41 ` [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region Shameer Kolothum @ 2026-08-05 1:09 ` Gavin Shan 2026-08-05 8:33 ` Shameer Kolothum Thodi 2026-08-05 8:49 ` Cédric Le Goater 0 siblings, 2 replies; 16+ messages in thread From: Gavin Shan @ 2026-08-05 1:09 UTC (permalink / raw) To: Shameer Kolothum, qemu-arm, qemu-devel Cc: eric.auger, alex, clg, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, meshetty Hi Nicolin and Shameer, On 1/21/26 9:41 PM, Shameer Kolothum wrote: > From: Nicolin Chen <nicolinc@nvidia.com> > > Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for P2P > use cases. Create a dmabuf for each mapped BAR region after the mmap is set > up, and store the returned fd in the region’s RAMBlock. This allows QEMU to > pass the fd to dma_map_file(), enabling iommufd to import the dmabuf and map > the BAR correctly in the host IOMMU page table. > > If the kernel lacks support or dmabuf setup fails, QEMU skips the setup > and continues with normal mmap handling. > > Tested-by: Nicolin Chen <nicolinc@nvidia.com> > Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com> > Reviewed-by: Cédric Le Goater <clg@redhat.com> > Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> > Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> > --- > hw/vfio/region.c | 65 +++++++++++++++++++++++++++++++++++++++++++- > hw/vfio/trace-events | 1 + > 2 files changed, 65 insertions(+), 1 deletion(-) > > diff --git a/hw/vfio/region.c b/hw/vfio/region.c > index ca75ab1be4..ab39d77574 100644 > --- a/hw/vfio/region.c > +++ b/hw/vfio/region.c > @@ -29,6 +29,7 @@ > #include "qemu/error-report.h" > #include "qemu/units.h" > #include "monitor/monitor.h" > +#include "system/ramblock.h" > #include "vfio-helpers.h" > > /* > @@ -238,13 +239,71 @@ static void vfio_subregion_unmap(VFIORegion *region, int index) > region->mmaps[index].mmap = NULL; > } > > +static bool vfio_region_create_dma_buf(VFIORegion *region, Error **errp) > +{ > + g_autofree struct vfio_device_feature *feature = NULL; > + VFIODevice *vbasedev = region->vbasedev; > + struct vfio_device_feature_dma_buf *dma_buf; > + size_t total_size; > + int i, ret; > + > + total_size = sizeof(*feature) + sizeof(*dma_buf) + > + sizeof(struct vfio_region_dma_range) * region->nr_mmaps; > + feature = g_malloc0(total_size); > + *feature = (struct vfio_device_feature) { > + .argsz = total_size, > + .flags = VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_DMA_BUF, > + }; > + > + dma_buf = (void *)feature->data; > + *dma_buf = (struct vfio_device_feature_dma_buf) { > + .region_index = region->nr, > + .open_flags = O_RDWR, > + .nr_ranges = region->nr_mmaps, > + }; > + > + for (i = 0; i < region->nr_mmaps; i++) { > + dma_buf->dma_ranges[i].offset = region->mmaps[i].offset; > + dma_buf->dma_ranges[i].length = region->mmaps[i].size; > + } > + Shall we check if @offset and @size is aligned to PAGE_SIZE? If they're not, I guess we need to skip populating DMA buffer instead of preventing the device from being passed through to the guest. Meghana <meshetty@redhat.com> runs into issue when passing through an NVMe card. The only memory BAR on the NVMe card is 16K, which is not aligned to 64KB (host page size). -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0 host$ sh vfio.sh QEMU 10.1.0 monitor - type 'help' for more information (qemu) qemu-kvm: -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0: \ 0004:01:00.0 BAR 0: failed to create dma-buf: PCI BAR IOMMU mappings may fail: Invalid argument host$ lspci -vvvs 0004:01:00.0 | grep Region.*Memory Region 0: Memory at 620040010000 (64-bit, non-prefetchable) [size=16K] host kernel =========== vfio_device_fops_unl_ioctl vfio_ioctl_device_feature vfio_pci_core_ioctl_feature vfio_pci_core_feature_dma_buf validate_dmabuf_input // Return -EINVAL for !PAGE_ALIGNED(len) > + ret = vfio_device_get_feature(vbasedev, feature); > + if (ret < 0) { > + if (ret == -ENOTTY) { > + warn_report_once("VFIO dma-buf not supported in kernel: " > + "PCI BAR IOMMU mappings may fail"); > + return true; > + } > + /* P2P DMA or exposing device memory use cases are not supported. */ > + error_setg_errno(errp, -ret, "%s: failed to create dma-buf: " > + "PCI BAR IOMMU mappings may fail", > + memory_region_name(region->mem)); > + return false; > + } > + > + /* Assign the dmabuf fd to associated RAMBlock */ > + for (i = 0; i < region->nr_mmaps; i++) { > + MemoryRegion *mr = ®ion->mmaps[i].mem; > + RAMBlock *ram_block = mr->ram_block; > + > + ram_block->fd = ret; > + ram_block->fd_offset = region->mmaps[i].offset; > + trace_vfio_region_dmabuf(region->vbasedev->name, ret, region->nr, > + memory_region_name(region->mem), > + region->mmaps[i].offset, > + region->mmaps[i].size); > + } > + return true; > +} > + > int vfio_region_mmap(VFIORegion *region) > { > int i, ret, prot = 0; > + Error *local_err = NULL; > char *name; > int fd; > > - if (!region->mem) { > + if (!region->mem || !region->nr_mmaps) { > return 0; > } > > @@ -305,6 +364,10 @@ int vfio_region_mmap(VFIORegion *region) > region->mmaps[i].size - 1); > } > > + if (!vfio_region_create_dma_buf(region, &local_err)) { > + error_report_err(local_err); > + } > + > return 0; > > no_mmap: > diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events > index 180e3d526b..466695507b 100644 > --- a/hw/vfio/trace-events > +++ b/hw/vfio/trace-events > @@ -118,6 +118,7 @@ vfio_device_put(int fd) "close vdev->fd=%d" > vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)" > vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64 > vfio_region_setup(const char *dev, int index, const char *name, unsigned long flags, unsigned long offset, unsigned long size) "Device %s, region %d \"%s\", flags: 0x%lx, offset: 0x%lx, size: 0x%lx" > +vfio_region_dmabuf(const char *dev, int fd, int index, const char *name, unsigned long offset, unsigned long size) "Device %s, dmabuf fd %d region %d \"%s\", offset: 0x%lx, size: 0x%lx" > vfio_region_mmap_fault(const char *name, int index, unsigned long offset, unsigned long size, int fault) "Region %s mmaps[%d], [0x%lx - 0x%lx], fault: %d" > vfio_region_mmap(const char *name, unsigned long offset, unsigned long end) "Region %s [0x%lx - 0x%lx]" > vfio_region_exit(const char *name, int index) "Device %s, region %d" Thanks, Gavin ^ permalink raw reply [flat|nested] 16+ messages in thread
* RE: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region 2026-08-05 1:09 ` Gavin Shan @ 2026-08-05 8:33 ` Shameer Kolothum Thodi 2026-08-05 9:43 ` Gavin Shan 2026-08-05 12:18 ` Jason Gunthorpe 2026-08-05 8:49 ` Cédric Le Goater 1 sibling, 2 replies; 16+ messages in thread From: Shameer Kolothum Thodi @ 2026-08-05 8:33 UTC (permalink / raw) To: Gavin Shan, qemu-arm@nongnu.org, qemu-devel@nongnu.org Cc: eric.auger@redhat.com, alex@shazbot.org, clg@redhat.com, cohuck@redhat.com, mst@redhat.com, Nicolin Chen, Nathan Chen, Matt Ochs, Jason Gunthorpe, jonathan.cameron@huawei.com, zhenzhong.duan@intel.com, vivek.kasireddy@intel.com, Krishnakant Jaju, meshetty@redhat.com Hi Gavin, > -----Original Message----- > From: Gavin Shan <gshan@redhat.com> > Sent: 05 August 2026 02:10 > To: Shameer Kolothum Thodi <skolothumtho@nvidia.com>; qemu- > arm@nongnu.org; qemu-devel@nongnu.org > Cc: eric.auger@redhat.com; alex@shazbot.org; clg@redhat.com; > cohuck@redhat.com; mst@redhat.com; Nicolin Chen <nicolinc@nvidia.com>; > Nathan Chen <nathanc@nvidia.com>; Matt Ochs <mochs@nvidia.com>; > Jason Gunthorpe <jgg@nvidia.com>; jonathan.cameron@huawei.com; > zhenzhong.duan@intel.com; vivek.kasireddy@intel.com; Krishnakant Jaju > <kjaju@nvidia.com>; meshetty@redhat.com > Subject: Re: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per > region > > External email: Use caution opening links or attachments > > > Hi Nicolin and Shameer, > > On 1/21/26 9:41 PM, Shameer Kolothum wrote: > > From: Nicolin Chen <nicolinc@nvidia.com> > > > > Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for > P2P > > use cases. Create a dmabuf for each mapped BAR region after the mmap is > set > > up, and store the returned fd in the region’s RAMBlock. This allows QEMU to > > pass the fd to dma_map_file(), enabling iommufd to import the dmabuf and > map > > the BAR correctly in the host IOMMU page table. > > > > If the kernel lacks support or dmabuf setup fails, QEMU skips the setup > > and continues with normal mmap handling. > > > > Tested-by: Nicolin Chen <nicolinc@nvidia.com> > > Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com> > > Reviewed-by: Cédric Le Goater <clg@redhat.com> > > Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> > > Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> > > --- > > hw/vfio/region.c | 65 > +++++++++++++++++++++++++++++++++++++++++++- > > hw/vfio/trace-events | 1 + > > 2 files changed, 65 insertions(+), 1 deletion(-) > > > > diff --git a/hw/vfio/region.c b/hw/vfio/region.c > > index ca75ab1be4..ab39d77574 100644 > > --- a/hw/vfio/region.c > > +++ b/hw/vfio/region.c > > @@ -29,6 +29,7 @@ > > #include "qemu/error-report.h" > > #include "qemu/units.h" > > #include "monitor/monitor.h" > > +#include "system/ramblock.h" > > #include "vfio-helpers.h" > > > > /* > > @@ -238,13 +239,71 @@ static void vfio_subregion_unmap(VFIORegion > *region, int index) > > region->mmaps[index].mmap = NULL; > > } > > > > +static bool vfio_region_create_dma_buf(VFIORegion *region, Error **errp) > > +{ > > + g_autofree struct vfio_device_feature *feature = NULL; > > + VFIODevice *vbasedev = region->vbasedev; > > + struct vfio_device_feature_dma_buf *dma_buf; > > + size_t total_size; > > + int i, ret; > > + > > + total_size = sizeof(*feature) + sizeof(*dma_buf) + > > + sizeof(struct vfio_region_dma_range) * region->nr_mmaps; > > + feature = g_malloc0(total_size); > > + *feature = (struct vfio_device_feature) { > > + .argsz = total_size, > > + .flags = VFIO_DEVICE_FEATURE_GET | > VFIO_DEVICE_FEATURE_DMA_BUF, > > + }; > > + > > + dma_buf = (void *)feature->data; > > + *dma_buf = (struct vfio_device_feature_dma_buf) { > > + .region_index = region->nr, > > + .open_flags = O_RDWR, > > + .nr_ranges = region->nr_mmaps, > > + }; > > + > > + for (i = 0; i < region->nr_mmaps; i++) { > > + dma_buf->dma_ranges[i].offset = region->mmaps[i].offset; > > + dma_buf->dma_ranges[i].length = region->mmaps[i].size; > > + } > > + > > Shall we check if @offset and @size is aligned to PAGE_SIZE? If they're not, > I guess we need to skip populating DMA buffer instead of preventing the > device from being passed through to the guest. Hmm..does it prevent passthrough in this case? The intention was not to do that. vfio_region_mmap() returns 0 irrespective of dma-buf outcome. If the concern was the usage of error_report_err() as does in patch, + if (!vfio_region_create_dma_buf(region, &local_err)) { + error_report_err(local_err); + } this is now updated to warn_report_err_once() by commit: 4b2e6505d59b: vfio/region: Clarify dma-buf failure messages Or may be I am missing your actual concern here. Please let me know. Thanks, Shameer > > Meghana <meshetty@redhat.com> runs into issue when passing through an > NVMe > card. The only memory BAR on the NVMe card is 16K, which is not aligned to > 64KB (host page size). > > -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0 > > host$ sh vfio.sh > QEMU 10.1.0 monitor - type 'help' for more information > (qemu) qemu-kvm: -device vfio- > pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0: \ > 0004:01:00.0 BAR 0: failed to create dma-buf: PCI BAR IOMMU > mappings may fail: Invalid argument > > host$ lspci -vvvs 0004:01:00.0 | grep Region.*Memory > Region 0: Memory at 620040010000 (64-bit, non-prefetchable) [size=16K] > > host kernel > =========== > vfio_device_fops_unl_ioctl > vfio_ioctl_device_feature > vfio_pci_core_ioctl_feature > vfio_pci_core_feature_dma_buf > validate_dmabuf_input // Return -EINVAL for !PAGE_ALIGNED(len) > > > > + ret = vfio_device_get_feature(vbasedev, feature); > > + if (ret < 0) { > > + if (ret == -ENOTTY) { > > + warn_report_once("VFIO dma-buf not supported in kernel: " > > + "PCI BAR IOMMU mappings may fail"); > > + return true; > > + } > > + /* P2P DMA or exposing device memory use cases are not supported. > */ > > + error_setg_errno(errp, -ret, "%s: failed to create dma-buf: " > > + "PCI BAR IOMMU mappings may fail", > > + memory_region_name(region->mem)); > > + return false; > > + } > > + > > + /* Assign the dmabuf fd to associated RAMBlock */ > > + for (i = 0; i < region->nr_mmaps; i++) { > > + MemoryRegion *mr = ®ion->mmaps[i].mem; > > + RAMBlock *ram_block = mr->ram_block; > > + > > + ram_block->fd = ret; > > + ram_block->fd_offset = region->mmaps[i].offset; > > + trace_vfio_region_dmabuf(region->vbasedev->name, ret, region->nr, > > + memory_region_name(region->mem), > > + region->mmaps[i].offset, > > + region->mmaps[i].size); > > + } > > + return true; > > +} > > + > > int vfio_region_mmap(VFIORegion *region) > > { > > int i, ret, prot = 0; > > + Error *local_err = NULL; > > char *name; > > int fd; > > > > - if (!region->mem) { > > + if (!region->mem || !region->nr_mmaps) { > > return 0; > > } > > > > @@ -305,6 +364,10 @@ int vfio_region_mmap(VFIORegion *region) > > region->mmaps[i].size - 1); > > } > > > > + if (!vfio_region_create_dma_buf(region, &local_err)) { > > + error_report_err(local_err); > > + } > > + > > return 0; > > > > no_mmap: > > diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events > > index 180e3d526b..466695507b 100644 > > --- a/hw/vfio/trace-events > > +++ b/hw/vfio/trace-events > > @@ -118,6 +118,7 @@ vfio_device_put(int fd) "close vdev->fd=%d" > > vfio_region_write(const char *name, int index, uint64_t addr, uint64_t > data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)" > > vfio_region_read(char *name, int index, uint64_t addr, unsigned size, > uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64 > > vfio_region_setup(const char *dev, int index, const char *name, unsigned > long flags, unsigned long offset, unsigned long size) "Device %s, region %d > \"%s\", flags: 0x%lx, offset: 0x%lx, size: 0x%lx" > > +vfio_region_dmabuf(const char *dev, int fd, int index, const char *name, > unsigned long offset, unsigned long size) "Device %s, dmabuf fd %d region %d > \"%s\", offset: 0x%lx, size: 0x%lx" > > vfio_region_mmap_fault(const char *name, int index, unsigned long offset, > unsigned long size, int fault) "Region %s mmaps[%d], [0x%lx - 0x%lx], fault: > %d" > > vfio_region_mmap(const char *name, unsigned long offset, unsigned long > end) "Region %s [0x%lx - 0x%lx]" > > vfio_region_exit(const char *name, int index) "Device %s, region %d" > > Thanks, > Gavin ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region 2026-08-05 8:33 ` Shameer Kolothum Thodi @ 2026-08-05 9:43 ` Gavin Shan 2026-08-05 12:18 ` Jason Gunthorpe 1 sibling, 0 replies; 16+ messages in thread From: Gavin Shan @ 2026-08-05 9:43 UTC (permalink / raw) To: Shameer Kolothum Thodi, qemu-arm@nongnu.org, qemu-devel@nongnu.org Cc: eric.auger@redhat.com, alex@shazbot.org, clg@redhat.com, cohuck@redhat.com, mst@redhat.com, Nicolin Chen, Nathan Chen, Matt Ochs, Jason Gunthorpe, jonathan.cameron@huawei.com, zhenzhong.duan@intel.com, vivek.kasireddy@intel.com, Krishnakant Jaju, meshetty@redhat.com Hi Shameer, On 8/5/26 6:33 PM, Shameer Kolothum Thodi wrote: > Hi Gavin, > >> -----Original Message----- >> From: Gavin Shan <gshan@redhat.com> >> Sent: 05 August 2026 02:10 >> To: Shameer Kolothum Thodi <skolothumtho@nvidia.com>; qemu- >> arm@nongnu.org; qemu-devel@nongnu.org >> Cc: eric.auger@redhat.com; alex@shazbot.org; clg@redhat.com; >> cohuck@redhat.com; mst@redhat.com; Nicolin Chen <nicolinc@nvidia.com>; >> Nathan Chen <nathanc@nvidia.com>; Matt Ochs <mochs@nvidia.com>; >> Jason Gunthorpe <jgg@nvidia.com>; jonathan.cameron@huawei.com; >> zhenzhong.duan@intel.com; vivek.kasireddy@intel.com; Krishnakant Jaju >> <kjaju@nvidia.com>; meshetty@redhat.com >> Subject: Re: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per >> region >> >> External email: Use caution opening links or attachments >> >> >> Hi Nicolin and Shameer, >> >> On 1/21/26 9:41 PM, Shameer Kolothum wrote: >>> From: Nicolin Chen <nicolinc@nvidia.com> >>> >>> Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for >> P2P >>> use cases. Create a dmabuf for each mapped BAR region after the mmap is >> set >>> up, and store the returned fd in the region’s RAMBlock. This allows QEMU to >>> pass the fd to dma_map_file(), enabling iommufd to import the dmabuf and >> map >>> the BAR correctly in the host IOMMU page table. >>> >>> If the kernel lacks support or dmabuf setup fails, QEMU skips the setup >>> and continues with normal mmap handling. >>> >>> Tested-by: Nicolin Chen <nicolinc@nvidia.com> >>> Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com> >>> Reviewed-by: Cédric Le Goater <clg@redhat.com> >>> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> >>> Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> >>> --- >>> hw/vfio/region.c | 65 >> +++++++++++++++++++++++++++++++++++++++++++- >>> hw/vfio/trace-events | 1 + >>> 2 files changed, 65 insertions(+), 1 deletion(-) >>> >>> diff --git a/hw/vfio/region.c b/hw/vfio/region.c >>> index ca75ab1be4..ab39d77574 100644 >>> --- a/hw/vfio/region.c >>> +++ b/hw/vfio/region.c >>> @@ -29,6 +29,7 @@ >>> #include "qemu/error-report.h" >>> #include "qemu/units.h" >>> #include "monitor/monitor.h" >>> +#include "system/ramblock.h" >>> #include "vfio-helpers.h" >>> >>> /* >>> @@ -238,13 +239,71 @@ static void vfio_subregion_unmap(VFIORegion >> *region, int index) >>> region->mmaps[index].mmap = NULL; >>> } >>> >>> +static bool vfio_region_create_dma_buf(VFIORegion *region, Error **errp) >>> +{ >>> + g_autofree struct vfio_device_feature *feature = NULL; >>> + VFIODevice *vbasedev = region->vbasedev; >>> + struct vfio_device_feature_dma_buf *dma_buf; >>> + size_t total_size; >>> + int i, ret; >>> + >>> + total_size = sizeof(*feature) + sizeof(*dma_buf) + >>> + sizeof(struct vfio_region_dma_range) * region->nr_mmaps; >>> + feature = g_malloc0(total_size); >>> + *feature = (struct vfio_device_feature) { >>> + .argsz = total_size, >>> + .flags = VFIO_DEVICE_FEATURE_GET | >> VFIO_DEVICE_FEATURE_DMA_BUF, >>> + }; >>> + >>> + dma_buf = (void *)feature->data; >>> + *dma_buf = (struct vfio_device_feature_dma_buf) { >>> + .region_index = region->nr, >>> + .open_flags = O_RDWR, >>> + .nr_ranges = region->nr_mmaps, >>> + }; >>> + >>> + for (i = 0; i < region->nr_mmaps; i++) { >>> + dma_buf->dma_ranges[i].offset = region->mmaps[i].offset; >>> + dma_buf->dma_ranges[i].length = region->mmaps[i].size; >>> + } >>> + >> >> Shall we check if @offset and @size is aligned to PAGE_SIZE? If they're not, >> I guess we need to skip populating DMA buffer instead of preventing the >> device from being passed through to the guest. > > Hmm..does it prevent passthrough in this case? The intention was not to do that. > vfio_region_mmap() returns 0 irrespective of dma-buf outcome. > > If the concern was the usage of error_report_err() as does in patch, > > + if (!vfio_region_create_dma_buf(region, &local_err)) { > + error_report_err(local_err); > + } > > this is now updated to warn_report_err_once() by commit: > > 4b2e6505d59b: vfio/region: Clarify dma-buf failure messages > > Or may be I am missing your actual concern here. Please let me know. > > Thanks, > Shameer > You're correct. I overlooked that @err returned from vfio_region_create_dma_buf() isn't propagated and stopping the NVMe card from being passed to the guest. Question: Since @err returned from vfio_region_create_dma_buf() is just used as the warning message storage, it's more reasonable to use warn_report_once(), replacing error_setg_errno() in vfio_region_create_dma_buf(). With this, the argument @errp and the boolean return value of the function can be dropped. I didn't check the history why we need the argument @errp for vfio_region_create_dma_buf(). > >> >> Meghana <meshetty@redhat.com> runs into issue when passing through an >> NVMe >> card. The only memory BAR on the NVMe card is 16K, which is not aligned to >> 64KB (host page size). >> >> -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0 >> >> host$ sh vfio.sh >> QEMU 10.1.0 monitor - type 'help' for more information >> (qemu) qemu-kvm: -device vfio- >> pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0: \ >> 0004:01:00.0 BAR 0: failed to create dma-buf: PCI BAR IOMMU >> mappings may fail: Invalid argument >> >> host$ lspci -vvvs 0004:01:00.0 | grep Region.*Memory >> Region 0: Memory at 620040010000 (64-bit, non-prefetchable) [size=16K] >> >> host kernel >> =========== >> vfio_device_fops_unl_ioctl >> vfio_ioctl_device_feature >> vfio_pci_core_ioctl_feature >> vfio_pci_core_feature_dma_buf >> validate_dmabuf_input // Return -EINVAL for !PAGE_ALIGNED(len) >> >> >>> + ret = vfio_device_get_feature(vbasedev, feature); >>> + if (ret < 0) { >>> + if (ret == -ENOTTY) { >>> + warn_report_once("VFIO dma-buf not supported in kernel: " >>> + "PCI BAR IOMMU mappings may fail"); >>> + return true; >>> + } >>> + /* P2P DMA or exposing device memory use cases are not supported. >> */ >>> + error_setg_errno(errp, -ret, "%s: failed to create dma-buf: " >>> + "PCI BAR IOMMU mappings may fail", >>> + memory_region_name(region->mem)); >>> + return false; >>> + } >>> + >>> + /* Assign the dmabuf fd to associated RAMBlock */ >>> + for (i = 0; i < region->nr_mmaps; i++) { >>> + MemoryRegion *mr = ®ion->mmaps[i].mem; >>> + RAMBlock *ram_block = mr->ram_block; >>> + >>> + ram_block->fd = ret; >>> + ram_block->fd_offset = region->mmaps[i].offset; >>> + trace_vfio_region_dmabuf(region->vbasedev->name, ret, region->nr, >>> + memory_region_name(region->mem), >>> + region->mmaps[i].offset, >>> + region->mmaps[i].size); >>> + } >>> + return true; >>> +} >>> + >>> int vfio_region_mmap(VFIORegion *region) >>> { >>> int i, ret, prot = 0; >>> + Error *local_err = NULL; >>> char *name; >>> int fd; >>> >>> - if (!region->mem) { >>> + if (!region->mem || !region->nr_mmaps) { >>> return 0; >>> } >>> >>> @@ -305,6 +364,10 @@ int vfio_region_mmap(VFIORegion *region) >>> region->mmaps[i].size - 1); >>> } >>> >>> + if (!vfio_region_create_dma_buf(region, &local_err)) { >>> + error_report_err(local_err); >>> + } >>> + >>> return 0; >>> >>> no_mmap: >>> diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events >>> index 180e3d526b..466695507b 100644 >>> --- a/hw/vfio/trace-events >>> +++ b/hw/vfio/trace-events >>> @@ -118,6 +118,7 @@ vfio_device_put(int fd) "close vdev->fd=%d" >>> vfio_region_write(const char *name, int index, uint64_t addr, uint64_t >> data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)" >>> vfio_region_read(char *name, int index, uint64_t addr, unsigned size, >> uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64 >>> vfio_region_setup(const char *dev, int index, const char *name, unsigned >> long flags, unsigned long offset, unsigned long size) "Device %s, region %d >> \"%s\", flags: 0x%lx, offset: 0x%lx, size: 0x%lx" >>> +vfio_region_dmabuf(const char *dev, int fd, int index, const char *name, >> unsigned long offset, unsigned long size) "Device %s, dmabuf fd %d region %d >> \"%s\", offset: 0x%lx, size: 0x%lx" >>> vfio_region_mmap_fault(const char *name, int index, unsigned long offset, >> unsigned long size, int fault) "Region %s mmaps[%d], [0x%lx - 0x%lx], fault: >> %d" >>> vfio_region_mmap(const char *name, unsigned long offset, unsigned long >> end) "Region %s [0x%lx - 0x%lx]" >>> vfio_region_exit(const char *name, int index) "Device %s, region %d" >> Thanks, Gavin ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region 2026-08-05 8:33 ` Shameer Kolothum Thodi 2026-08-05 9:43 ` Gavin Shan @ 2026-08-05 12:18 ` Jason Gunthorpe 1 sibling, 0 replies; 16+ messages in thread From: Jason Gunthorpe @ 2026-08-05 12:18 UTC (permalink / raw) To: Shameer Kolothum Thodi Cc: Gavin Shan, qemu-arm@nongnu.org, qemu-devel@nongnu.org, eric.auger@redhat.com, alex@shazbot.org, clg@redhat.com, cohuck@redhat.com, mst@redhat.com, Nicolin Chen, Nathan Chen, Matt Ochs, jonathan.cameron@huawei.com, zhenzhong.duan@intel.com, vivek.kasireddy@intel.com, Krishnakant Jaju, meshetty@redhat.com On Wed, Aug 05, 2026 at 08:33:06AM +0000, Shameer Kolothum Thodi wrote: > > > + dma_buf = (void *)feature->data; > > > + *dma_buf = (struct vfio_device_feature_dma_buf) { > > > + .region_index = region->nr, > > > + .open_flags = O_RDWR, > > > + .nr_ranges = region->nr_mmaps, > > > + }; > > > + > > > + for (i = 0; i < region->nr_mmaps; i++) { > > > + dma_buf->dma_ranges[i].offset = region->mmaps[i].offset; > > > + dma_buf->dma_ranges[i].length = region->mmaps[i].size; > > > + } > > > + > > > > Shall we check if @offset and @size is aligned to PAGE_SIZE? If they're not, > > I guess we need to skip populating DMA buffer instead of preventing the > > device from being passed through to the guest. > > Hmm..does it prevent passthrough in this case? The intention was not to do that. > vfio_region_mmap() returns 0 irrespective of dma-buf outcome. I think you should always be able to create a dmabuf, even with irregular offsets and sizes. The resulting dmabuf may not be mmap'able though. Jason ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region 2026-08-05 1:09 ` Gavin Shan 2026-08-05 8:33 ` Shameer Kolothum Thodi @ 2026-08-05 8:49 ` Cédric Le Goater 2026-08-05 9:45 ` Gavin Shan 1 sibling, 1 reply; 16+ messages in thread From: Cédric Le Goater @ 2026-08-05 8:49 UTC (permalink / raw) To: Gavin Shan, Shameer Kolothum, qemu-arm, qemu-devel Cc: eric.auger, alex, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, meshetty On 8/5/26 03:09, Gavin Shan wrote: > Hi Nicolin and Shameer, > > On 1/21/26 9:41 PM, Shameer Kolothum wrote: >> From: Nicolin Chen <nicolinc@nvidia.com> >> >> Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for P2P >> use cases. Create a dmabuf for each mapped BAR region after the mmap is set >> up, and store the returned fd in the region’s RAMBlock. This allows QEMU to >> pass the fd to dma_map_file(), enabling iommufd to import the dmabuf and map >> the BAR correctly in the host IOMMU page table. >> >> If the kernel lacks support or dmabuf setup fails, QEMU skips the setup >> and continues with normal mmap handling. >> >> Tested-by: Nicolin Chen <nicolinc@nvidia.com> >> Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com> >> Reviewed-by: Cédric Le Goater <clg@redhat.com> >> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> >> Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> >> --- >> hw/vfio/region.c | 65 +++++++++++++++++++++++++++++++++++++++++++- >> hw/vfio/trace-events | 1 + >> 2 files changed, 65 insertions(+), 1 deletion(-) >> >> diff --git a/hw/vfio/region.c b/hw/vfio/region.c >> index ca75ab1be4..ab39d77574 100644 >> --- a/hw/vfio/region.c >> +++ b/hw/vfio/region.c >> @@ -29,6 +29,7 @@ >> #include "qemu/error-report.h" >> #include "qemu/units.h" >> #include "monitor/monitor.h" >> +#include "system/ramblock.h" >> #include "vfio-helpers.h" >> /* >> @@ -238,13 +239,71 @@ static void vfio_subregion_unmap(VFIORegion *region, int index) >> region->mmaps[index].mmap = NULL; >> } >> +static bool vfio_region_create_dma_buf(VFIORegion *region, Error **errp) >> +{ >> + g_autofree struct vfio_device_feature *feature = NULL; >> + VFIODevice *vbasedev = region->vbasedev; >> + struct vfio_device_feature_dma_buf *dma_buf; >> + size_t total_size; >> + int i, ret; >> + >> + total_size = sizeof(*feature) + sizeof(*dma_buf) + >> + sizeof(struct vfio_region_dma_range) * region->nr_mmaps; >> + feature = g_malloc0(total_size); >> + *feature = (struct vfio_device_feature) { >> + .argsz = total_size, >> + .flags = VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_DMA_BUF, >> + }; >> + >> + dma_buf = (void *)feature->data; >> + *dma_buf = (struct vfio_device_feature_dma_buf) { >> + .region_index = region->nr, >> + .open_flags = O_RDWR, >> + .nr_ranges = region->nr_mmaps, >> + }; >> + >> + for (i = 0; i < region->nr_mmaps; i++) { >> + dma_buf->dma_ranges[i].offset = region->mmaps[i].offset; >> + dma_buf->dma_ranges[i].length = region->mmaps[i].size; >> + } >> + > > Shall we check if @offset and @size is aligned to PAGE_SIZE? If they're not, > I guess we need to skip populating DMA buffer instead of preventing the > device from being passed through to the guest. > > Meghana <meshetty@redhat.com> runs into issue when passing through an NVMe > card. The only memory BAR on the NVMe card is 16K, which is not aligned to > 64KB (host page size). > > -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0 > > host$ sh vfio.sh > QEMU 10.1.0 monitor - type 'help' for more information > (qemu) qemu-kvm: -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0: \ > 0004:01:00.0 BAR 0: failed to create dma-buf: PCI BAR IOMMU mappings may fail: Invalid argument To avoid confusion, the reported error message was slightly improved in : https://lore.kernel.org/qemu-devel/20260721170518.4160785-3-clg@redhat.com/ Thanks, C. ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region 2026-08-05 8:49 ` Cédric Le Goater @ 2026-08-05 9:45 ` Gavin Shan 0 siblings, 0 replies; 16+ messages in thread From: Gavin Shan @ 2026-08-05 9:45 UTC (permalink / raw) To: Cédric Le Goater, Shameer Kolothum, qemu-arm, qemu-devel Cc: eric.auger, alex, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju, meshetty On 8/5/26 6:49 PM, Cédric Le Goater wrote: > On 8/5/26 03:09, Gavin Shan wrote: >> Hi Nicolin and Shameer, >> >> On 1/21/26 9:41 PM, Shameer Kolothum wrote: >>> From: Nicolin Chen <nicolinc@nvidia.com> >>> >>> Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for P2P >>> use cases. Create a dmabuf for each mapped BAR region after the mmap is set >>> up, and store the returned fd in the region’s RAMBlock. This allows QEMU to >>> pass the fd to dma_map_file(), enabling iommufd to import the dmabuf and map >>> the BAR correctly in the host IOMMU page table. >>> >>> If the kernel lacks support or dmabuf setup fails, QEMU skips the setup >>> and continues with normal mmap handling. >>> >>> Tested-by: Nicolin Chen <nicolinc@nvidia.com> >>> Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com> >>> Reviewed-by: Cédric Le Goater <clg@redhat.com> >>> Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> >>> Signed-off-by: Shameer Kolothum <skolothumtho@nvidia.com> >>> --- >>> hw/vfio/region.c | 65 +++++++++++++++++++++++++++++++++++++++++++- >>> hw/vfio/trace-events | 1 + >>> 2 files changed, 65 insertions(+), 1 deletion(-) >>> >>> diff --git a/hw/vfio/region.c b/hw/vfio/region.c >>> index ca75ab1be4..ab39d77574 100644 >>> --- a/hw/vfio/region.c >>> +++ b/hw/vfio/region.c >>> @@ -29,6 +29,7 @@ >>> #include "qemu/error-report.h" >>> #include "qemu/units.h" >>> #include "monitor/monitor.h" >>> +#include "system/ramblock.h" >>> #include "vfio-helpers.h" >>> /* >>> @@ -238,13 +239,71 @@ static void vfio_subregion_unmap(VFIORegion *region, int index) >>> region->mmaps[index].mmap = NULL; >>> } >>> +static bool vfio_region_create_dma_buf(VFIORegion *region, Error **errp) >>> +{ >>> + g_autofree struct vfio_device_feature *feature = NULL; >>> + VFIODevice *vbasedev = region->vbasedev; >>> + struct vfio_device_feature_dma_buf *dma_buf; >>> + size_t total_size; >>> + int i, ret; >>> + >>> + total_size = sizeof(*feature) + sizeof(*dma_buf) + >>> + sizeof(struct vfio_region_dma_range) * region->nr_mmaps; >>> + feature = g_malloc0(total_size); >>> + *feature = (struct vfio_device_feature) { >>> + .argsz = total_size, >>> + .flags = VFIO_DEVICE_FEATURE_GET | VFIO_DEVICE_FEATURE_DMA_BUF, >>> + }; >>> + >>> + dma_buf = (void *)feature->data; >>> + *dma_buf = (struct vfio_device_feature_dma_buf) { >>> + .region_index = region->nr, >>> + .open_flags = O_RDWR, >>> + .nr_ranges = region->nr_mmaps, >>> + }; >>> + >>> + for (i = 0; i < region->nr_mmaps; i++) { >>> + dma_buf->dma_ranges[i].offset = region->mmaps[i].offset; >>> + dma_buf->dma_ranges[i].length = region->mmaps[i].size; >>> + } >>> + >> >> Shall we check if @offset and @size is aligned to PAGE_SIZE? If they're not, >> I guess we need to skip populating DMA buffer instead of preventing the >> device from being passed through to the guest. >> >> Meghana <meshetty@redhat.com> runs into issue when passing through an NVMe >> card. The only memory BAR on the NVMe card is 16K, which is not aligned to >> 64KB (host page size). >> >> -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0 >> >> host$ sh vfio.sh >> QEMU 10.1.0 monitor - type 'help' for more information >> (qemu) qemu-kvm: -device vfio-pci,id=nvme,host=0004:01:00.0,addr=0x2.0x1,bus=pcie.0: \ >> 0004:01:00.0 BAR 0: failed to create dma-buf: PCI BAR IOMMU mappings may fail: Invalid argument > > To avoid confusion, the reported error message was slightly > improved in : > > https://lore.kernel.org/qemu-devel/20260721170518.4160785-3-clg@redhat.com/ > Yeah, the warning message was reported from our downstream QEMU where this commit (for the improved messages) isn't there yet. > Thanks, > > C. > Thanks, Gavin ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions 2026-01-21 11:41 [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Shameer Kolothum ` (2 preceding siblings ...) 2026-01-21 11:41 ` [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region Shameer Kolothum @ 2026-01-21 12:36 ` Michael S. Tsirkin 2026-01-21 12:49 ` Eric Auger 4 siblings, 0 replies; 16+ messages in thread From: Michael S. Tsirkin @ 2026-01-21 12:36 UTC (permalink / raw) To: Shameer Kolothum Cc: qemu-arm, qemu-devel, eric.auger, alex, clg, cohuck, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju On Wed, Jan 21, 2026 at 11:41:08AM +0000, Shameer Kolothum wrote: > Hi, > > Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for P2P > use cases. This adds support for vfio devices to create a dmabuf for > each mapped BAR region. > > Changes from v3: > https://lore.kernel.org/qemu-devel/20260116092950.15796-1-skolothumtho@nvidia.com/ > > - Folded in patch #2 to linux-headers update to avoid bisect failure > due to build error. Reviewed-by: Michael S. Tsirkin <mst@redhat.com> > The dmabuf support was sanity tested on an NVIDIA grace paltform. > > Please take a look and let me know. > > Thanks, > Shameer > > Nicolin Chen (1): > hw/vfio/region: Create dmabuf for PCI BAR per region > > Shameer Kolothum (2): > linux-headers: Update to Linux v6.19-rc1 > hw/vfio: Add helper to retrieve device feature > > hw/net/virtio-net.c | 11 +- > hw/vfio/container.c | 2 +- > hw/vfio/device.c | 9 ++ > hw/vfio/listener.c | 4 +- > hw/vfio/region.c | 65 +++++++++- > hw/vfio/trace-events | 1 + > include/hw/vfio/vfio-device.h | 3 + > include/standard-headers/drm/drm_fourcc.h | 25 ++-- > include/standard-headers/linux/ethtool.h | 5 + > .../linux/input-event-codes.h | 14 ++- > include/standard-headers/linux/pci_regs.h | 89 ++++++++++++++ > include/standard-headers/linux/virtio_net.h | 3 +- > include/standard-headers/linux/virtio_pci.h | 2 +- > linux-headers/asm-arm64/kvm.h | 2 +- > linux-headers/asm-arm64/unistd_64.h | 1 + > linux-headers/asm-generic/unistd.h | 4 +- > linux-headers/asm-loongarch/kvm.h | 1 + > linux-headers/asm-loongarch/unistd.h | 6 + > linux-headers/asm-loongarch/unistd_64.h | 1 + > 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/unistd_32.h | 1 + > linux-headers/asm-powerpc/unistd_64.h | 1 + > linux-headers/asm-riscv/kvm.h | 3 + > linux-headers/asm-riscv/unistd_32.h | 1 + > linux-headers/asm-riscv/unistd_64.h | 1 + > linux-headers/asm-s390/bitsperlong.h | 4 - > linux-headers/asm-s390/unistd.h | 4 - > linux-headers/asm-s390/unistd_64.h | 9 +- > linux-headers/asm-x86/kvm.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/iommufd.h | 10 ++ > linux-headers/linux/kvm.h | 11 ++ > linux-headers/linux/mshv.h | 116 +++++++++++++++++- > linux-headers/linux/psp-sev.h | 66 ++++++---- > linux-headers/linux/vfio.h | 28 +++++ > 39 files changed, 450 insertions(+), 60 deletions(-) > > -- > 2.43.0 ^ permalink raw reply [flat|nested] 16+ messages in thread
* Re: [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions 2026-01-21 11:41 [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Shameer Kolothum ` (3 preceding siblings ...) 2026-01-21 12:36 ` [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Michael S. Tsirkin @ 2026-01-21 12:49 ` Eric Auger 4 siblings, 0 replies; 16+ messages in thread From: Eric Auger @ 2026-01-21 12:49 UTC (permalink / raw) To: Shameer Kolothum, qemu-arm, qemu-devel Cc: alex, clg, cohuck, mst, nicolinc, nathanc, mochs, jgg, jonathan.cameron, zhenzhong.duan, vivek.kasireddy, kjaju On 1/21/26 12:41 PM, Shameer Kolothum wrote: > Hi, > > Linux now provides a VFIO dmabuf exporter to expose PCI BAR memory for P2P > use cases. This adds support for vfio devices to create a dmabuf for > each mapped BAR region. > > Changes from v3: > https://lore.kernel.org/qemu-devel/20260116092950.15796-1-skolothumtho@nvidia.com/ > > - Folded in patch #2 to linux-headers update to avoid bisect failure > due to build error. > > The dmabuf support was sanity tested on an NVIDIA grace paltform. > > Please take a look and let me know. > > Thanks, > Shameer > > Nicolin Chen (1): > hw/vfio/region: Create dmabuf for PCI BAR per region > > Shameer Kolothum (2): > linux-headers: Update to Linux v6.19-rc1 > hw/vfio: Add helper to retrieve device feature > > hw/net/virtio-net.c | 11 +- > hw/vfio/container.c | 2 +- > hw/vfio/device.c | 9 ++ > hw/vfio/listener.c | 4 +- > hw/vfio/region.c | 65 +++++++++- > hw/vfio/trace-events | 1 + > include/hw/vfio/vfio-device.h | 3 + > include/standard-headers/drm/drm_fourcc.h | 25 ++-- > include/standard-headers/linux/ethtool.h | 5 + > .../linux/input-event-codes.h | 14 ++- > include/standard-headers/linux/pci_regs.h | 89 ++++++++++++++ > include/standard-headers/linux/virtio_net.h | 3 +- > include/standard-headers/linux/virtio_pci.h | 2 +- > linux-headers/asm-arm64/kvm.h | 2 +- > linux-headers/asm-arm64/unistd_64.h | 1 + > linux-headers/asm-generic/unistd.h | 4 +- > linux-headers/asm-loongarch/kvm.h | 1 + > linux-headers/asm-loongarch/unistd.h | 6 + > linux-headers/asm-loongarch/unistd_64.h | 1 + > 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/unistd_32.h | 1 + > linux-headers/asm-powerpc/unistd_64.h | 1 + > linux-headers/asm-riscv/kvm.h | 3 + > linux-headers/asm-riscv/unistd_32.h | 1 + > linux-headers/asm-riscv/unistd_64.h | 1 + > linux-headers/asm-s390/bitsperlong.h | 4 - > linux-headers/asm-s390/unistd.h | 4 - > linux-headers/asm-s390/unistd_64.h | 9 +- > linux-headers/asm-x86/kvm.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/iommufd.h | 10 ++ > linux-headers/linux/kvm.h | 11 ++ > linux-headers/linux/mshv.h | 116 +++++++++++++++++- > linux-headers/linux/psp-sev.h | 66 ++++++---- > linux-headers/linux/vfio.h | 28 +++++ > 39 files changed, 450 insertions(+), 60 deletions(-) > For the whole series: Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Eric Auger <eric.auger@redhat.com> Thanks Eric ^ permalink raw reply [flat|nested] 16+ messages in thread
end of thread, other threads:[~2026-08-05 12:19 UTC | newest] Thread overview: 16+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2026-01-21 11:41 [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Shameer Kolothum 2026-01-21 11:41 ` [PATCH v4 1/3] linux-headers: Update to Linux v6.19-rc1 Shameer Kolothum 2026-01-21 14:00 ` Cédric Le Goater 2026-01-21 14:21 ` Peter Maydell 2026-01-21 17:12 ` Jason Gunthorpe 2026-01-23 14:26 ` Cédric Le Goater 2026-01-21 11:41 ` [PATCH v4 2/3] hw/vfio: Add helper to retrieve device feature Shameer Kolothum 2026-01-21 11:41 ` [PATCH v4 3/3] hw/vfio/region: Create dmabuf for PCI BAR per region Shameer Kolothum 2026-08-05 1:09 ` Gavin Shan 2026-08-05 8:33 ` Shameer Kolothum Thodi 2026-08-05 9:43 ` Gavin Shan 2026-08-05 12:18 ` Jason Gunthorpe 2026-08-05 8:49 ` Cédric Le Goater 2026-08-05 9:45 ` Gavin Shan 2026-01-21 12:36 ` [PATCH v4 0/3] vfio: Add DMABUF support for PCI BAR regions Michael S. Tsirkin 2026-01-21 12:49 ` Eric Auger
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.