From 88807dc8d573c0f718d0d26f592f212c5a487cf0 Mon Sep 17 00:00:00 2001 From: Oak Zeng Date: Thu, 4 Apr 2019 15:47:34 -0500 Subject: drm/amdgpu: Remap hdp coherency registers Remap HDP_MEM_COHERENCY_FLUSH_CNTL and HDP_REG_COHERENCY_FLUSH_CNTL to an empty page in mmio space. We will later map this page to process space so application can flush hdp. This can't be done properly at those registers' original location because it will expose more than desired registers to process space. v2: Use explicit register hole location v3: Moved remapped hdp registers into adev struct v4: Use more generic name for remapped page Expose register offset in kfd_ioctl.h v5: Move hdp register remap function to nbio ip function v6: Fixed operator precedence issue and other bugs Signed-off-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index dc067ed0b72d..bb1b4280f53d 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -426,6 +426,13 @@ struct kfd_ioctl_import_dmabuf_args { __u32 dmabuf_fd; /* to KFD */ }; +/* Register offset inside the remapped mmio page + */ +enum kfd_mmio_remap { + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL = 0, + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL = 4, +}; + #define AMDKFD_IOCTL_BASE 'K' #define AMDKFD_IO(nr) _IO(AMDKFD_IOCTL_BASE, nr) #define AMDKFD_IOR(nr, type) _IOR(AMDKFD_IOCTL_BASE, nr, type) -- cgit v1.2.3 From d8e408a82704c86ba87c3d58cfe69dcdb758aa07 Mon Sep 17 00:00:00 2001 From: Oak Zeng Date: Thu, 11 Apr 2019 14:43:39 -0500 Subject: drm/amdkfd: Expose HDP registers to user space Introduce a new memory type (KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP) and expose mmio page of HDP registers to user space through this new memory type. v2: moved remapped hdp regs to adev struct v3: rename the new memory type to ALLOC_MEM_FLAGS_MMIO_REMAP v4: use more generic function name v5: Fail remapped mmio allocation for asics before gfx9 Signed-off-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index bb1b4280f53d..1e7d5f3376b0 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -338,6 +338,7 @@ struct kfd_ioctl_acquire_vm_args { #define KFD_IOC_ALLOC_MEM_FLAGS_GTT (1 << 1) #define KFD_IOC_ALLOC_MEM_FLAGS_USERPTR (1 << 2) #define KFD_IOC_ALLOC_MEM_FLAGS_DOORBELL (1 << 3) +#define KFD_IOC_ALLOC_MEM_FLAGS_MMIO_REMAP (1 << 4) /* Allocation flags: attributes/access options */ #define KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE (1 << 31) #define KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE (1 << 30) -- cgit v1.2.3 From 1b4670f6983156526c286723465fdf805070b45d Mon Sep 17 00:00:00 2001 From: Oak Zeng Date: Thu, 7 Feb 2019 14:02:27 -0600 Subject: drm/amdkfd: Introduce XGMI SDMA queue type Existing QUEUE_TYPE_SDMA means PCIe optimized SDMA queues. Introduce a new QUEUE_TYPE_SDMA_XGMI, which is optimized for non-PCIe transfer such as XGMI. Signed-off-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 1e7d5f3376b0..20917c59f39c 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -35,9 +35,10 @@ struct kfd_ioctl_get_version_args { }; /* For kfd_ioctl_create_queue_args.queue_type. */ -#define KFD_IOC_QUEUE_TYPE_COMPUTE 0 -#define KFD_IOC_QUEUE_TYPE_SDMA 1 -#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL 2 +#define KFD_IOC_QUEUE_TYPE_COMPUTE 0x0 +#define KFD_IOC_QUEUE_TYPE_SDMA 0x1 +#define KFD_IOC_QUEUE_TYPE_COMPUTE_AQL 0x2 +#define KFD_IOC_QUEUE_TYPE_SDMA_XGMI 0x3 #define KFD_MAX_QUEUE_PERCENTAGE 100 #define KFD_MAX_QUEUE_PRIORITY 15 -- cgit v1.2.3 From ea8157ab2ae5e914dd427e5cfab533b6da3819cd Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 21 May 2019 07:55:45 +0100 Subject: zsfold: Convert zsfold to use the new mount API Convert the zsfold filesystem to the new internal mount API as the old one will be obsoleted and removed. This allows greater flexibility in communication of mount parameters between userspace, the VFS and the filesystem. See Documentation/filesystems/mount_api.txt for more information. Signed-off-by: David Howells --- include/uapi/linux/magic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index f8c00045d537..85c1119d0b0b 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -91,5 +91,6 @@ #define UDF_SUPER_MAGIC 0x15013346 #define BALLOON_KVM_MAGIC 0x13661366 #define ZSMALLOC_MAGIC 0x58295829 +#define Z3FOLD_MAGIC 0x33 #endif /* __LINUX_MAGIC_H__ */ -- cgit v1.2.3 From 1a058c3376765ee31d65e28cbbb9d4ff15120056 Mon Sep 17 00:00:00 2001 From: Oak Zeng Date: Mon, 6 May 2019 22:11:14 -0500 Subject: drm/amdkfd: New IOCTL to allocate queue GWS Add a new kfd ioctl to allocate queue GWS. Queue GWS is released on queue destroy. Signed-off-by: Oak Zeng Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- include/uapi/linux/kfd_ioctl.h | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 20917c59f39c..070d1bc7e725 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -410,6 +410,21 @@ struct kfd_ioctl_unmap_memory_from_gpu_args { __u32 n_success; /* to/from KFD */ }; +/* Allocate GWS for specific queue + * + * @gpu_id: device identifier + * @queue_id: queue's id that GWS is allocated for + * @num_gws: how many GWS to allocate + * @first_gws: index of the first GWS allocated. + * only support contiguous GWS allocation + */ +struct kfd_ioctl_alloc_queue_gws_args { + __u32 gpu_id; /* to KFD */ + __u32 queue_id; /* to KFD */ + __u32 num_gws; /* to KFD */ + __u32 first_gws; /* from KFD */ +}; + struct kfd_ioctl_get_dmabuf_info_args { __u64 size; /* from KFD */ __u64 metadata_ptr; /* to KFD */ @@ -529,7 +544,10 @@ enum kfd_mmio_remap { #define AMDKFD_IOC_IMPORT_DMABUF \ AMDKFD_IOWR(0x1D, struct kfd_ioctl_import_dmabuf_args) +#define AMDKFD_IOC_ALLOC_QUEUE_GWS \ + AMDKFD_IOWR(0x1E, struct kfd_ioctl_alloc_queue_gws_args) + #define AMDKFD_COMMAND_START 0x01 -#define AMDKFD_COMMAND_END 0x1E +#define AMDKFD_COMMAND_END 0x1F #endif -- cgit v1.2.3 From edcd69ab9a323b7ac7a86e1c44b6c9c46598391f Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 15 Jan 2019 12:19:57 +0000 Subject: iommu: Add virtio-iommu driver The virtio IOMMU is a para-virtualized device, allowing to send IOMMU requests such as map/unmap over virtio transport without emulating page tables. This implementation handles ATTACH, DETACH, MAP and UNMAP requests. The bulk of the code transforms calls coming from the IOMMU API into corresponding virtio requests. Mappings are kept in an interval tree instead of page tables. A little more work is required for modular and x86 support, so for the moment the driver depends on CONFIG_VIRTIO=y and CONFIG_ARM64. Tested-by: Bharat Bhushan Tested-by: Eric Auger Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_ids.h | 1 + include/uapi/linux/virtio_iommu.h | 106 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 107 insertions(+) create mode 100644 include/uapi/linux/virtio_iommu.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 6d5c3b2d4f4d..cfe47c5d9a56 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -43,5 +43,6 @@ #define VIRTIO_ID_INPUT 18 /* virtio input */ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ +#define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h new file mode 100644 index 000000000000..5e5fd62689fb --- /dev/null +++ b/include/uapi/linux/virtio_iommu.h @@ -0,0 +1,106 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Virtio-iommu definition v0.9 + * + * Copyright (C) 2018 Arm Ltd. + */ +#ifndef _UAPI_LINUX_VIRTIO_IOMMU_H +#define _UAPI_LINUX_VIRTIO_IOMMU_H + +#include + +/* Feature bits */ +#define VIRTIO_IOMMU_F_INPUT_RANGE 0 +#define VIRTIO_IOMMU_F_DOMAIN_BITS 1 +#define VIRTIO_IOMMU_F_MAP_UNMAP 2 +#define VIRTIO_IOMMU_F_BYPASS 3 + +struct virtio_iommu_range { + __u64 start; + __u64 end; +}; + +struct virtio_iommu_config { + /* Supported page sizes */ + __u64 page_size_mask; + /* Supported IOVA range */ + struct virtio_iommu_range input_range; + /* Max domain ID size */ + __u8 domain_bits; + __u8 padding[3]; + /* Probe buffer size */ + __u32 probe_size; +}; + +/* Request types */ +#define VIRTIO_IOMMU_T_ATTACH 0x01 +#define VIRTIO_IOMMU_T_DETACH 0x02 +#define VIRTIO_IOMMU_T_MAP 0x03 +#define VIRTIO_IOMMU_T_UNMAP 0x04 + +/* Status types */ +#define VIRTIO_IOMMU_S_OK 0x00 +#define VIRTIO_IOMMU_S_IOERR 0x01 +#define VIRTIO_IOMMU_S_UNSUPP 0x02 +#define VIRTIO_IOMMU_S_DEVERR 0x03 +#define VIRTIO_IOMMU_S_INVAL 0x04 +#define VIRTIO_IOMMU_S_RANGE 0x05 +#define VIRTIO_IOMMU_S_NOENT 0x06 +#define VIRTIO_IOMMU_S_FAULT 0x07 + +struct virtio_iommu_req_head { + __u8 type; + __u8 reserved[3]; +}; + +struct virtio_iommu_req_tail { + __u8 status; + __u8 reserved[3]; +}; + +struct virtio_iommu_req_attach { + struct virtio_iommu_req_head head; + __le32 domain; + __le32 endpoint; + __u8 reserved[8]; + struct virtio_iommu_req_tail tail; +}; + +struct virtio_iommu_req_detach { + struct virtio_iommu_req_head head; + __le32 domain; + __le32 endpoint; + __u8 reserved[8]; + struct virtio_iommu_req_tail tail; +}; + +#define VIRTIO_IOMMU_MAP_F_READ (1 << 0) +#define VIRTIO_IOMMU_MAP_F_WRITE (1 << 1) +#define VIRTIO_IOMMU_MAP_F_EXEC (1 << 2) +#define VIRTIO_IOMMU_MAP_F_MMIO (1 << 3) + +#define VIRTIO_IOMMU_MAP_F_MASK (VIRTIO_IOMMU_MAP_F_READ | \ + VIRTIO_IOMMU_MAP_F_WRITE | \ + VIRTIO_IOMMU_MAP_F_EXEC | \ + VIRTIO_IOMMU_MAP_F_MMIO) + +struct virtio_iommu_req_map { + struct virtio_iommu_req_head head; + __le32 domain; + __le64 virt_start; + __le64 virt_end; + __le64 phys_start; + __le32 flags; + struct virtio_iommu_req_tail tail; +}; + +struct virtio_iommu_req_unmap { + struct virtio_iommu_req_head head; + __le32 domain; + __le64 virt_start; + __le64 virt_end; + __u8 reserved[4]; + struct virtio_iommu_req_tail tail; +}; + +#endif -- cgit v1.2.3 From 2a5a314874450decec244923209ce6ba97e3ed93 Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 15 Jan 2019 12:19:58 +0000 Subject: iommu/virtio: Add probe request When the device offers the probe feature, send a probe request for each device managed by the IOMMU. Extract RESV_MEM information. When we encounter a MSI doorbell region, set it up as a IOMMU_RESV_MSI region. This will tell other subsystems that there is no need to map the MSI doorbell in the virtio-iommu, because MSIs bypass it. Tested-by: Bharat Bhushan Tested-by: Eric Auger Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_iommu.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index 5e5fd62689fb..ae6145cf5928 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -14,6 +14,7 @@ #define VIRTIO_IOMMU_F_DOMAIN_BITS 1 #define VIRTIO_IOMMU_F_MAP_UNMAP 2 #define VIRTIO_IOMMU_F_BYPASS 3 +#define VIRTIO_IOMMU_F_PROBE 4 struct virtio_iommu_range { __u64 start; @@ -37,6 +38,7 @@ struct virtio_iommu_config { #define VIRTIO_IOMMU_T_DETACH 0x02 #define VIRTIO_IOMMU_T_MAP 0x03 #define VIRTIO_IOMMU_T_UNMAP 0x04 +#define VIRTIO_IOMMU_T_PROBE 0x05 /* Status types */ #define VIRTIO_IOMMU_S_OK 0x00 @@ -103,4 +105,38 @@ struct virtio_iommu_req_unmap { struct virtio_iommu_req_tail tail; }; +#define VIRTIO_IOMMU_PROBE_T_NONE 0 +#define VIRTIO_IOMMU_PROBE_T_RESV_MEM 1 + +#define VIRTIO_IOMMU_PROBE_T_MASK 0xfff + +struct virtio_iommu_probe_property { + __le16 type; + __le16 length; +}; + +#define VIRTIO_IOMMU_RESV_MEM_T_RESERVED 0 +#define VIRTIO_IOMMU_RESV_MEM_T_MSI 1 + +struct virtio_iommu_probe_resv_mem { + struct virtio_iommu_probe_property head; + __u8 subtype; + __u8 reserved[3]; + __le64 start; + __le64 end; +}; + +struct virtio_iommu_req_probe { + struct virtio_iommu_req_head head; + __le32 endpoint; + __u8 reserved[64]; + + __u8 properties[]; + + /* + * Tail follows the variable-length properties array. No padding, + * property lengths are all aligned on 8 bytes. + */ +}; + #endif -- cgit v1.2.3 From 169a126c6e88a99578a309a9021f314b5d532c5f Mon Sep 17 00:00:00 2001 From: Jean-Philippe Brucker Date: Tue, 15 Jan 2019 12:19:59 +0000 Subject: iommu/virtio: Add event queue The event queue offers a way for the device to report access faults from endpoints. It is implemented on virtqueue #1. Whenever the host needs to signal a fault, it fills one of the buffers offered by the guest and interrupts it. Tested-by: Bharat Bhushan Tested-by: Eric Auger Reviewed-by: Eric Auger Signed-off-by: Jean-Philippe Brucker Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_iommu.h | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_iommu.h b/include/uapi/linux/virtio_iommu.h index ae6145cf5928..ba1b460c9944 100644 --- a/include/uapi/linux/virtio_iommu.h +++ b/include/uapi/linux/virtio_iommu.h @@ -139,4 +139,23 @@ struct virtio_iommu_req_probe { */ }; +/* Fault types */ +#define VIRTIO_IOMMU_FAULT_R_UNKNOWN 0 +#define VIRTIO_IOMMU_FAULT_R_DOMAIN 1 +#define VIRTIO_IOMMU_FAULT_R_MAPPING 2 + +#define VIRTIO_IOMMU_FAULT_F_READ (1 << 0) +#define VIRTIO_IOMMU_FAULT_F_WRITE (1 << 1) +#define VIRTIO_IOMMU_FAULT_F_EXEC (1 << 2) +#define VIRTIO_IOMMU_FAULT_F_ADDRESS (1 << 8) + +struct virtio_iommu_fault { + __u8 reason; + __u8 reserved[3]; + __le32 flags; + __le32 endpoint; + __u8 reserved2[4]; + __le64 address; +}; + #endif -- cgit v1.2.3 From de76cda215d56256ffcda7ffa538b70f9fb301a7 Mon Sep 17 00:00:00 2001 From: Gustavo Pimentel Date: Tue, 4 Jun 2019 18:24:43 +0200 Subject: PCI: Decode PCIe 32 GT/s link speed PCIe r5.0, sec 7.5.3.18, defines a new 32.0 GT/s bit in the Supported Link Speeds Vector of Link Capabilities 2. Decode this new speed. This does not affect the speed of the link, which should be negotiated automatically by the hardware; it only adds decoding when showing the speed to the user. Previously, reading the speed of a link operating at this speed showed "Unknown speed" instead of "32.0 GT/s". Link: https://lore.kernel.org/lkml/92365e3caf0fc559f9ab14bcd053bfc92d4f661c.1559664969.git.gustavo.pimentel@synopsys.com Signed-off-by: Gustavo Pimentel [bhelgaas: changelog] Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 27164769d184..f28e562d7ca8 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -528,6 +528,7 @@ #define PCI_EXP_LNKCAP_SLS_5_0GB 0x00000002 /* LNKCAP2 SLS Vector bit 1 */ #define PCI_EXP_LNKCAP_SLS_8_0GB 0x00000003 /* LNKCAP2 SLS Vector bit 2 */ #define PCI_EXP_LNKCAP_SLS_16_0GB 0x00000004 /* LNKCAP2 SLS Vector bit 3 */ +#define PCI_EXP_LNKCAP_SLS_32_0GB 0x00000005 /* LNKCAP2 SLS Vector bit 4 */ #define PCI_EXP_LNKCAP_MLW 0x000003f0 /* Maximum Link Width */ #define PCI_EXP_LNKCAP_ASPMS 0x00000c00 /* ASPM Support */ #define PCI_EXP_LNKCAP_L0SEL 0x00007000 /* L0s Exit Latency */ @@ -556,6 +557,7 @@ #define PCI_EXP_LNKSTA_CLS_5_0GB 0x0002 /* Current Link Speed 5.0GT/s */ #define PCI_EXP_LNKSTA_CLS_8_0GB 0x0003 /* Current Link Speed 8.0GT/s */ #define PCI_EXP_LNKSTA_CLS_16_0GB 0x0004 /* Current Link Speed 16.0GT/s */ +#define PCI_EXP_LNKSTA_CLS_32_0GB 0x0005 /* Current Link Speed 32.0GT/s */ #define PCI_EXP_LNKSTA_NLW 0x03f0 /* Negotiated Link Width */ #define PCI_EXP_LNKSTA_NLW_X1 0x0010 /* Current Link Width x1 */ #define PCI_EXP_LNKSTA_NLW_X2 0x0020 /* Current Link Width x2 */ @@ -661,6 +663,7 @@ #define PCI_EXP_LNKCAP2_SLS_5_0GB 0x00000004 /* Supported Speed 5GT/s */ #define PCI_EXP_LNKCAP2_SLS_8_0GB 0x00000008 /* Supported Speed 8GT/s */ #define PCI_EXP_LNKCAP2_SLS_16_0GB 0x00000010 /* Supported Speed 16GT/s */ +#define PCI_EXP_LNKCAP2_SLS_32_0GB 0x00000020 /* Supported Speed 32GT/s */ #define PCI_EXP_LNKCAP2_CROSSLINK 0x00000100 /* Crosslink supported */ #define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ #define PCI_EXP_LNKCTL2_TLS 0x000f @@ -668,6 +671,7 @@ #define PCI_EXP_LNKCTL2_TLS_5_0GT 0x0002 /* Supported Speed 5GT/s */ #define PCI_EXP_LNKCTL2_TLS_8_0GT 0x0003 /* Supported Speed 8GT/s */ #define PCI_EXP_LNKCTL2_TLS_16_0GT 0x0004 /* Supported Speed 16GT/s */ +#define PCI_EXP_LNKCTL2_TLS_32_0GT 0x0005 /* Supported Speed 32GT/s */ #define PCI_EXP_LNKSTA2 50 /* Link Status 2 */ #define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 52 /* v2 endpoints with link end here */ #define PCI_EXP_SLTCAP2 52 /* Slot Capabilities 2 */ -- cgit v1.2.3 From ed63bb1d1f8469586006a9ca63c42344401aa2ab Mon Sep 17 00:00:00 2001 From: Greg Hackmann Date: Thu, 13 Jun 2019 15:34:06 -0700 Subject: dma-buf: give each buffer a full-fledged inode By traversing /proc/*/fd and /proc/*/map_files, processes with CAP_ADMIN can get a lot of fine-grained data about how shmem buffers are shared among processes. stat(2) on each entry gives the caller a unique ID (st_ino), the buffer's size (st_size), and even the number of pages currently charged to the buffer (st_blocks / 512). In contrast, all dma-bufs share the same anonymous inode. So while we can count how many dma-buf fds or mappings a process has, we can't get the size of the backing buffers or tell if two entries point to the same dma-buf. On systems with debugfs, we can get a per-buffer breakdown of size and reference count, but can't tell which processes are actually holding the references to each buffer. Replace the singleton inode with full-fledged inodes allocated by alloc_anon_inode(). This involves creating and mounting a mini-pseudo-filesystem for dma-buf, following the example in fs/aio.c. Signed-off-by: Greg Hackmann Signed-off-by: Chenbo Feng Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20190613223408.139221-2-fengc@google.com --- include/uapi/linux/magic.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index f8c00045d537..665e18627f78 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -91,5 +91,6 @@ #define UDF_SUPER_MAGIC 0x15013346 #define BALLOON_KVM_MAGIC 0x13661366 #define ZSMALLOC_MAGIC 0x58295829 +#define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */ #endif /* __LINUX_MAGIC_H__ */ -- cgit v1.2.3 From bb2bb903042517b8fb17b2bc21e00512f2dcac01 Mon Sep 17 00:00:00 2001 From: Greg Hackmann Date: Thu, 13 Jun 2019 15:34:07 -0700 Subject: dma-buf: add DMA_BUF_SET_NAME ioctls This patch adds complimentary DMA_BUF_SET_NAME ioctls, which lets userspace processes attach a free-form name to each buffer. This information can be extremely helpful for tracking and accounting shared buffers. For example, on Android, we know what each buffer will be used for at allocation time: GL, multimedia, camera, etc. The userspace allocator can use DMA_BUF_SET_NAME to associate that information with the buffer, so we can later give developers a breakdown of how much memory they're allocating for graphics, camera, etc. Signed-off-by: Greg Hackmann Signed-off-by: Chenbo Feng Signed-off-by: Sumit Semwal Link: https://patchwork.freedesktop.org/patch/msgid/20190613223408.139221-3-fengc@google.com --- include/uapi/linux/dma-buf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dma-buf.h b/include/uapi/linux/dma-buf.h index d75df5210a4a..dbc7092e04b5 100644 --- a/include/uapi/linux/dma-buf.h +++ b/include/uapi/linux/dma-buf.h @@ -35,7 +35,10 @@ struct dma_buf_sync { #define DMA_BUF_SYNC_VALID_FLAGS_MASK \ (DMA_BUF_SYNC_RW | DMA_BUF_SYNC_END) +#define DMA_BUF_NAME_LEN 32 + #define DMA_BUF_BASE 'b' #define DMA_BUF_IOCTL_SYNC _IOW(DMA_BUF_BASE, 0, struct dma_buf_sync) +#define DMA_BUF_SET_NAME _IOW(DMA_BUF_BASE, 1, const char *) #endif -- cgit v1.2.3 From 9e645e1105ca60fbbc6bddf2fd5ef7e57ed3dca8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 May 2019 16:07:28 -0600 Subject: io_uring: add support for sqe links With SQE links, we can create chains of dependent SQEs. One example would be queueing an SQE that's a read from one file descriptor, with the linked SQE being a write to another with the same set of buffers. An SQE link will not stall the pipeline, it'll just ensure that dependent SQEs aren't issued before the previous link has completed. Any error at submission or completion time will break the chain of SQEs. For completions, this also includes short reads or writes, as the next SQE could depend on the previous one being fully completed. Any SQE in a chain that gets canceled due to any of the above errors, will get an CQE fill with -ECANCELED as the error value. Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a0c460025036..10b7c45f6d57 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -40,6 +40,7 @@ struct io_uring_sqe { */ #define IOSQE_FIXED_FILE (1U << 0) /* use fixed fileset */ #define IOSQE_IO_DRAIN (1U << 1) /* issue after inflight IO */ +#define IOSQE_IO_LINK (1U << 2) /* links next sqe */ /* * io_uring_setup() flags -- cgit v1.2.3 From 3ae762a09cd72a08ef620c80fbb263693c3fb204 Mon Sep 17 00:00:00 2001 From: Russell King Date: Tue, 4 Jun 2019 14:49:25 +0100 Subject: fs/adfs: correct disc record structure Fill in some padding in the disc record structure, and add GCC packed and aligned attributes to ensure that it is correctly laid out. Signed-off-by: Russell King Signed-off-by: Al Viro --- include/uapi/linux/adfs_fs.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/adfs_fs.h b/include/uapi/linux/adfs_fs.h index 151d93e27ed4..f1a7d67a7323 100644 --- a/include/uapi/linux/adfs_fs.h +++ b/include/uapi/linux/adfs_fs.h @@ -29,17 +29,17 @@ struct adfs_discrecord { __u8 log2sharesize:4; __u8 unused40:4; __u8 big_flag:1; - __u8 unused41:1; + __u8 unused41:7; __u8 nzones_high; + __u8 reserved43; __le32 format_version; __le32 root_size; __u8 unused52[60 - 52]; -}; +} __attribute__((packed, aligned(4))); #define ADFS_DISCRECORD (0xc00) #define ADFS_DR_OFFSET (0x1c0) #define ADFS_DR_SIZE 60 #define ADFS_DR_SIZE_BITS (ADFS_DR_SIZE << 3) - #endif /* _UAPI_ADFS_FS_H */ -- cgit v1.2.3 From c7369b3faea230cf6009449147ed755c45e74afd Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 31 May 2019 15:39:31 +0200 Subject: btrfs: add mask for all RAID1 types Preparatory patch for additional RAID1 profiles with more copies. The mask will contain 3-copy and 4-copy, most of the checks for plain RAID1 work the same for the other profiles. Signed-off-by: David Sterba --- include/uapi/linux/btrfs_tree.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 421239b98db2..34d5b34286fa 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -866,6 +866,8 @@ enum btrfs_raid_types { #define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \ BTRFS_BLOCK_GROUP_RAID6) +#define BTRFS_BLOCK_GROUP_RAID1_MASK (BTRFS_BLOCK_GROUP_RAID1) + /* * We need a bit for restriper to be able to tell when chunks of type * SINGLE are available. This "extended" profile format is used in -- cgit v1.2.3 From 35f2c14d2a076b063a76c5bf275c46c0743ba3a0 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 26 Jun 2019 15:38:43 -0700 Subject: platform/x86: ISST: Add common API to register and handle ioctls Encapsulate common functions which all Intel Speed Select Technology interface drivers can use. This creates API to register misc device for user kernel communication and handle all common IOCTLs. As part of the registry it allows a callback which is to handle domain specific ioctl processing. There can be multiple drivers register for services, which can be built as modules. So this driver handle contention during registry and as well as during removal. Once user space opened the misc device, the registered driver will be prevented from removal. Also once misc device is opened by the user space new client driver can't register, till the misc device is closed. There are two types of client drivers, one to handle mail box interface and the other is to allow direct read/write to some specific MMIO space. This common driver implements IOCTL ISST_IF_GET_PLATFORM_INFO. Signed-off-by: Srinivas Pandruvada Signed-off-by: Andy Shevchenko --- include/uapi/linux/isst_if.h | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 include/uapi/linux/isst_if.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h new file mode 100644 index 000000000000..fa94480b5f74 --- /dev/null +++ b/include/uapi/linux/isst_if.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel Speed Select Interface: OS to hardware Interface + * Copyright (c) 2019, Intel Corporation. + * All rights reserved. + * + * Author: Srinivas Pandruvada + */ + +#ifndef __ISST_IF_H +#define __ISST_IF_H + +#include + +/** + * struct isst_if_platform_info - Define platform information + * @api_version: Version of the firmware document, which this driver + * can communicate + * @driver_version: Driver version, which will help user to send right + * commands. Even if the firmware is capable, driver may + * not be ready + * @max_cmds_per_ioctl: Returns the maximum number of commands driver will + * accept in a single ioctl + * @mbox_supported: Support of mail box interface + * @mmio_supported: Support of mmio interface for core-power feature + * + * Used to return output of IOCTL ISST_IF_GET_PLATFORM_INFO. This + * information can be used by the user space, to get the driver, firmware + * support and also number of commands to send in a single IOCTL request. + */ +struct isst_if_platform_info { + __u16 api_version; + __u16 driver_version; + __u16 max_cmds_per_ioctl; + __u8 mbox_supported; + __u8 mmio_supported; +}; + +#define ISST_IF_MAGIC 0xFE +#define ISST_IF_GET_PLATFORM_INFO _IOR(ISST_IF_MAGIC, 0, struct isst_if_platform_info *) +#endif -- cgit v1.2.3 From fb5b36a413b9f30fba573fc2a596ab7142dfaf12 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 26 Jun 2019 15:38:45 -0700 Subject: platform/x86: ISST: Add IOCTL to Translate Linux logical CPU to PUNIT CPU number Add processing for IOCTL command ISST_IF_GET_PHY_ID. This converts from the Linux logical CPU to PUNIT CPU numbering scheme. Signed-off-by: Srinivas Pandruvada Signed-off-by: Andy Shevchenko --- include/uapi/linux/isst_if.h | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index fa94480b5f74..15d1f286a830 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -36,6 +36,34 @@ struct isst_if_platform_info { __u8 mmio_supported; }; +/** + * struct isst_if_cpu_map - CPU mapping between logical and physical CPU + * @logical_cpu: Linux logical CPU number + * @physical_cpu: PUNIT CPU number + * + * Used to convert from Linux logical CPU to PUNIT CPU numbering scheme. + * The PUNIT CPU number is different than APIC ID based CPU numbering. + */ +struct isst_if_cpu_map { + __u32 logical_cpu; + __u32 physical_cpu; +}; + +/** + * struct isst_if_cpu_maps - structure for CPU map IOCTL + * @cmd_count: Number of CPU mapping command in cpu_map[] + * @cpu_map[]: Holds one or more CPU map data structure + * + * This structure used with ioctl ISST_IF_GET_PHY_ID to send + * one or more CPU mapping commands. Here IOCTL return value indicates + * number of commands sent or error number if no commands have been sent. + */ +struct isst_if_cpu_maps { + __u32 cmd_count; + struct isst_if_cpu_map cpu_map[1]; +}; + #define ISST_IF_MAGIC 0xFE #define ISST_IF_GET_PLATFORM_INFO _IOR(ISST_IF_MAGIC, 0, struct isst_if_platform_info *) +#define ISST_IF_GET_PHY_ID _IOWR(ISST_IF_MAGIC, 1, struct isst_if_cpu_map *) #endif -- cgit v1.2.3 From d3a23584294c1f379239a3b52bac13e03fecd147 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 26 Jun 2019 15:38:46 -0700 Subject: platform/x86: ISST: Add Intel Speed Select mmio interface Added MMIO interface to read/write specific offsets in PUNIT PCI device which export core priortization. This MMIO interface can be used using ioctl interface on /dev/isst_interface using IOCTL ISST_IF_IO_CMD. This MMIO interface is used by the intel-speed-select tool under tools/x86/power to enumerate and set core priority. The MMIO offsets and semantics of the message can be checked from the source code of the tool. Signed-off-by: Srinivas Pandruvada Signed-off-by: Andy Shevchenko --- include/uapi/linux/isst_if.h | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index 15d1f286a830..fe2492ade078 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -63,7 +63,40 @@ struct isst_if_cpu_maps { struct isst_if_cpu_map cpu_map[1]; }; +/** + * struct isst_if_io_reg - Read write PUNIT IO register + * @read_write: Value 0: Read, 1: Write + * @logical_cpu: Logical CPU number to get target PCI device. + * @reg: PUNIT register offset + * @value: For write operation value to write and for + * for read placeholder read value + * + * Structure to specify read/write data to PUNIT registers. + */ +struct isst_if_io_reg { + __u32 read_write; /* Read:0, Write:1 */ + __u32 logical_cpu; + __u32 reg; + __u32 value; +}; + +/** + * struct isst_if_io_regs - structure for IO register commands + * @cmd_count: Number of io reg commands in io_reg[] + * @io_reg[]: Holds one or more io_reg command structure + * + * This structure used with ioctl ISST_IF_IO_CMD to send + * one or more read/write commands to PUNIT. Here IOCTL return value + * indicates number of requests sent or error number if no requests have + * been sent. + */ +struct isst_if_io_regs { + __u32 req_count; + struct isst_if_io_reg io_reg[1]; +}; + #define ISST_IF_MAGIC 0xFE #define ISST_IF_GET_PLATFORM_INFO _IOR(ISST_IF_MAGIC, 0, struct isst_if_platform_info *) #define ISST_IF_GET_PHY_ID _IOWR(ISST_IF_MAGIC, 1, struct isst_if_cpu_map *) +#define ISST_IF_IO_CMD _IOW(ISST_IF_MAGIC, 2, struct isst_if_io_regs *) #endif -- cgit v1.2.3 From 31a166fe9c269af17977e650846ee4ea50361c07 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 26 Jun 2019 15:38:47 -0700 Subject: platform/x86: ISST: Add Intel Speed Select mailbox interface via PCI Add an IOCTL to send mailbox commands to PUNIT using PUNIT PCI device. A limited set of mailbox commands can be sent to PUNIT. This MMIO interface is used by the intel-speed-select tool under tools/x86/power to enumerate and control Intel Speed Select features. The MBOX commands ids and semantics of the message can be checked from the source code of the tool. Signed-off-by: Srinivas Pandruvada Signed-off-by: Andy Shevchenko --- include/uapi/linux/isst_if.h | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index fe2492ade078..e4b1c2ec3279 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -95,8 +95,46 @@ struct isst_if_io_regs { struct isst_if_io_reg io_reg[1]; }; +/** + * struct isst_if_mbox_cmd - Structure to define mail box command + * @logical_cpu: Logical CPU number to get target PCI device + * @parameter: Mailbox parameter value + * @req_data: Request data for the mailbox + * @resp_data: Response data for mailbox command response + * @command: Mailbox command value + * @sub_command: Mailbox sub command value + * @reserved: Unused, set to 0 + * + * Structure to specify mailbox command to be sent to PUNIT. + */ +struct isst_if_mbox_cmd { + __u32 logical_cpu; + __u32 parameter; + __u32 req_data; + __u32 resp_data; + __u16 command; + __u16 sub_command; + __u32 reserved; +}; + +/** + * struct isst_if_mbox_cmds - structure for mailbox commands + * @cmd_count: Number of mailbox commands in mbox_cmd[] + * @mbox_cmd[]: Holds one or more mbox commands + * + * This structure used with ioctl ISST_IF_MBOX_COMMAND to send + * one or more mailbox commands to PUNIT. Here IOCTL return value + * indicates number of commands sent or error number if no commands have + * been sent. + */ +struct isst_if_mbox_cmds { + __u32 cmd_count; + struct isst_if_mbox_cmd mbox_cmd[1]; +}; + #define ISST_IF_MAGIC 0xFE #define ISST_IF_GET_PLATFORM_INFO _IOR(ISST_IF_MAGIC, 0, struct isst_if_platform_info *) #define ISST_IF_GET_PHY_ID _IOWR(ISST_IF_MAGIC, 1, struct isst_if_cpu_map *) #define ISST_IF_IO_CMD _IOW(ISST_IF_MAGIC, 2, struct isst_if_io_regs *) +#define ISST_IF_MBOX_COMMAND _IOWR(ISST_IF_MAGIC, 3, struct isst_if_mbox_cmds *) #endif -- cgit v1.2.3 From e765f37b9b8b4fa65682e9a78a2ca2b11d3d9096 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 26 Jun 2019 15:38:49 -0700 Subject: platform/x86: ISST: Add Intel Speed Select PUNIT MSR interface While using new non arhitectural features using PUNIT Mailbox and MMIO read/write interface, still there is need to operate using MSRs to control PUNIT. User space could have used user user-space MSR interface for this, but when user space MSR access is disabled, then it can't. Here only limited number of MSRs are allowed using this new interface. Signed-off-by: Srinivas Pandruvada Signed-off-by: Andy Shevchenko --- include/uapi/linux/isst_if.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index e4b1c2ec3279..d10b832c58c5 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -132,9 +132,41 @@ struct isst_if_mbox_cmds { struct isst_if_mbox_cmd mbox_cmd[1]; }; +/** + * struct isst_if_msr_cmd - Structure to define msr command + * @read_write: Value 0: Read, 1: Write + * @logical_cpu: Logical CPU number + * @msr: MSR number + * @data: For write operation, data to write, for read + * place holder + * + * Structure to specify MSR command related to PUNIT. + */ +struct isst_if_msr_cmd { + __u32 read_write; /* Read:0, Write:1 */ + __u32 logical_cpu; + __u64 msr; + __u64 data; +}; + +/** + * struct isst_if_msr_cmds - structure for msr commands + * @cmd_count: Number of mailbox commands in msr_cmd[] + * @msr_cmd[]: Holds one or more msr commands + * + * This structure used with ioctl ISST_IF_MSR_COMMAND to send + * one or more MSR commands. IOCTL return value indicates number of + * commands sent or error number if no commands have been sent. + */ +struct isst_if_msr_cmds { + __u32 cmd_count; + struct isst_if_msr_cmd msr_cmd[1]; +}; + #define ISST_IF_MAGIC 0xFE #define ISST_IF_GET_PLATFORM_INFO _IOR(ISST_IF_MAGIC, 0, struct isst_if_platform_info *) #define ISST_IF_GET_PHY_ID _IOWR(ISST_IF_MAGIC, 1, struct isst_if_cpu_map *) #define ISST_IF_IO_CMD _IOW(ISST_IF_MAGIC, 2, struct isst_if_io_regs *) #define ISST_IF_MBOX_COMMAND _IOWR(ISST_IF_MAGIC, 3, struct isst_if_mbox_cmds *) +#define ISST_IF_MSR_COMMAND _IOWR(ISST_IF_MAGIC, 4, struct isst_if_msr_cmds *) #endif -- cgit v1.2.3 From 6e84200c0a2994b991259d19450eee561029bf70 Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Fri, 5 Jul 2019 19:33:23 +0530 Subject: virtio-pmem: Add virtio pmem driver This patch adds virtio-pmem driver for KVM guest. Guest reads the persistent memory range information from Qemu over VIRTIO and registers it on nvdimm_bus. It also creates a nd_region object with the persistent memory range information so that existing 'nvdimm/pmem' driver can reserve this into system memory map. This way 'virtio-pmem' driver uses existing functionality of pmem driver to register persistent memory compatible for DAX capable filesystems. This also provides function to perform guest flush over VIRTIO from 'pmem' driver when userspace performs flush on DAX memory range. Signed-off-by: Pankaj Gupta Reviewed-by: Yuval Shaia Acked-by: Michael S. Tsirkin Acked-by: Jakub Staron Tested-by: Jakub Staron Reviewed-by: Cornelia Huck Signed-off-by: Dan Williams --- include/uapi/linux/virtio_ids.h | 1 + include/uapi/linux/virtio_pmem.h | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) create mode 100644 include/uapi/linux/virtio_pmem.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h index 6d5c3b2d4f4d..32b2f94d1f58 100644 --- a/include/uapi/linux/virtio_ids.h +++ b/include/uapi/linux/virtio_ids.h @@ -43,5 +43,6 @@ #define VIRTIO_ID_INPUT 18 /* virtio input */ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ +#define VIRTIO_ID_PMEM 27 /* virtio pmem */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h new file mode 100644 index 000000000000..efcd72f2d20d --- /dev/null +++ b/include/uapi/linux/virtio_pmem.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * Definitions for virtio-pmem devices. + * + * Copyright (C) 2019 Red Hat, Inc. + * + * Author(s): Pankaj Gupta + */ + +#ifndef _UAPI_LINUX_VIRTIO_PMEM_H +#define _UAPI_LINUX_VIRTIO_PMEM_H + +#include +#include +#include + +struct virtio_pmem_config { + __u64 start; + __u64 size; +}; + +#define VIRTIO_PMEM_REQ_TYPE_FLUSH 0 + +struct virtio_pmem_resp { + /* Host return status corresponding to flush request */ + __u32 ret; +}; + +struct virtio_pmem_req { + /* command type */ + __u32 type; +}; + +#endif -- cgit v1.2.3 From 0fa03c624d8fc9932d0f27c39a9deca6a37e0e17 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 19 Apr 2019 13:34:07 -0600 Subject: io_uring: add support for sendmsg() This is done through IORING_OP_SENDMSG. There's a new sqe->msg_flags for the flags argument, and the msghdr struct is passed in the sqe->addr field. We use MSG_DONTWAIT to force an inline fast path if sendmsg() doesn't block, and punt to async execution if it would have. Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 10b7c45f6d57..d74742d6269f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -27,6 +27,7 @@ struct io_uring_sqe { __u32 fsync_flags; __u16 poll_events; __u32 sync_range_flags; + __u32 msg_flags; }; __u64 user_data; /* data to be passed back at completion time */ union { @@ -58,6 +59,7 @@ struct io_uring_sqe { #define IORING_OP_POLL_ADD 6 #define IORING_OP_POLL_REMOVE 7 #define IORING_OP_SYNC_FILE_RANGE 8 +#define IORING_OP_SENDMSG 9 /* * sqe->fsync_flags -- cgit v1.2.3 From aa1fa28fc73ea6b740ee7b62bf3b07141883dbb8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 19 Apr 2019 13:38:09 -0600 Subject: io_uring: add support for recvmsg() This is done through IORING_OP_RECVMSG. This opcode uses the same sqe->msg_flags that IORING_OP_SENDMSG added, and we pass in the msghdr struct in the sqe->addr field as well. We use MSG_DONTWAIT to force an inline fast path if recvmsg() doesn't block, and punt to async execution if it would have. Acked-by: David S. Miller Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index d74742d6269f..1e1652f25cc1 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -60,6 +60,7 @@ struct io_uring_sqe { #define IORING_OP_POLL_REMOVE 7 #define IORING_OP_SYNC_FILE_RANGE 8 #define IORING_OP_SENDMSG 9 +#define IORING_OP_RECVMSG 10 /* * sqe->fsync_flags -- cgit v1.2.3 From da82c92f1150f66afabf78d2c85ef9ac18dc6d38 Mon Sep 17 00:00:00 2001 From: Mauro Carvalho Chehab Date: Thu, 27 Jun 2019 13:08:35 -0300 Subject: docs: cgroup-v1: add it to the admin-guide book Those files belong to the admin guide, so add them. Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6f68438aa4ed..82699845ef79 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -806,7 +806,7 @@ union bpf_attr { * based on a user-provided identifier for all traffic coming from * the tasks belonging to the related cgroup. See also the related * kernel documentation, available from the Linux sources in file - * *Documentation/cgroup-v1/net_cls.rst*. + * *Documentation/admin-guide/cgroup-v1/net_cls.rst*. * * The Linux kernel has two versions for cgroups: there are * cgroups v1 and cgroups v2. Both are available to users, who can -- cgit v1.2.3 From d4ecfeb15494ec261fef2d25d96eecba66f0b182 Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Mon, 15 Jul 2019 09:39:53 -0700 Subject: bpf: allow wide aligned loads for bpf_sock_addr user_ip6 and msg_src_ip6 Add explicit check for u64 loads of user_ip6 and msg_src_ip6 and update the comment. Cc: Yonghong Song Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6f68438aa4ed..81be929b89fc 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3248,7 +3248,7 @@ struct bpf_sock_addr { __u32 user_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 user_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 user_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __u32 user_port; /* Allows 4-byte read and write. @@ -3260,7 +3260,7 @@ struct bpf_sock_addr { __u32 msg_src_ip4; /* Allows 1,2,4-byte read and 4-byte write. * Stored in network byte order. */ - __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read and 4,8-byte write. + __u32 msg_src_ip6[4]; /* Allows 1,2,4,8-byte read and 4,8-byte write. * Stored in network byte order. */ __bpf_md_ptr(struct bpf_sock *, sk); -- cgit v1.2.3 From a5b647007e9d794956dbed9339a3354a9fc4d5c3 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Tue, 16 Jul 2019 12:52:18 -0700 Subject: fix: taprio: Change type of txtime-delay parameter to u32 During the review of the iproute2 patches for txtime-assist mode, it was pointed out that it does not make sense for the txtime-delay parameter to be negative. So, change the type of the parameter from s32 to u32. Fixes: 4cfd5779bd6e ("taprio: Add support for txtime-assist mode") Reported-by: Stephen Hemminger Signed-off-by: Vedang Patel Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 1f623252abe8..18f185299f47 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1174,7 +1174,7 @@ enum { TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME, /* s64 */ TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */ TCA_TAPRIO_ATTR_FLAGS, /* u32 */ - TCA_TAPRIO_ATTR_TXTIME_DELAY, /* s32 */ + TCA_TAPRIO_ATTR_TXTIME_DELAY, /* u32 */ __TCA_TAPRIO_ATTR_MAX, }; -- cgit v1.2.3 From 694a58e29ef27c4c26f103a9decfd053f94dd34c Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Tue, 16 Jul 2019 16:28:07 -0700 Subject: uapi linux/coda.h: use __kernel_pid_t for userspace Part of a patch by Mikko Rapeli, as Arnd Bergman commented on the original patch. pid_t might differ between libc and the kernel, so the kernel interface has to use types that the kernel defines. Link: http://lkml.kernel.org/r/f374a71f4d351bc8c8b3ac18ad7765c88d806d10.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Mikko Rapeli Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/coda.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/coda.h b/include/uapi/linux/coda.h index 695fade33c64..ed8cb263e482 100644 --- a/include/uapi/linux/coda.h +++ b/include/uapi/linux/coda.h @@ -295,8 +295,8 @@ struct coda_statfs { struct coda_in_hdr { u_int32_t opcode; u_int32_t unique; /* Keep multiple outstanding msgs distinct */ - pid_t pid; - pid_t pgid; + __kernel_pid_t pid; + __kernel_pid_t pgid; vuid_t uid; }; -- cgit v1.2.3 From f90fb3c7e2c13ae829db2274b88b845a75038b8a Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Tue, 16 Jul 2019 16:28:10 -0700 Subject: uapi linux/coda_psdev.h: move upc_req definition from uapi to kernel side headers Only users of upc_req in kernel side fs/coda/psdev.c and fs/coda/upcall.c already include linux/coda_psdev.h. Suggested by Jan Harkes in https://lore.kernel.org/lkml/20150531111913.GA23377@cs.cmu.edu/ Fixes these include/uapi/linux/coda_psdev.h compilation errors in userspace: linux/coda_psdev.h:12:19: error: field `uc_chain' has incomplete type struct list_head uc_chain; ^ linux/coda_psdev.h:13:2: error: unknown type name `caddr_t' caddr_t uc_data; ^ linux/coda_psdev.h:14:2: error: unknown type name `u_short' u_short uc_flags; ^ linux/coda_psdev.h:15:2: error: unknown type name `u_short' u_short uc_inSize; /* Size is at most 5000 bytes */ ^ linux/coda_psdev.h:16:2: error: unknown type name `u_short' u_short uc_outSize; ^ linux/coda_psdev.h:17:2: error: unknown type name `u_short' u_short uc_opcode; /* copied from data to save lookup */ ^ linux/coda_psdev.h:19:2: error: unknown type name `wait_queue_head_t' wait_queue_head_t uc_sleep; /* process' wait queue */ ^ Link: http://lkml.kernel.org/r/9f99f5ce6a0563d5266e6cf7aa9585aac2cae971.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Mikko Rapeli Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/coda_psdev.h | 13 ------------- 1 file changed, 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/coda_psdev.h b/include/uapi/linux/coda_psdev.h index aa6623efd2dd..d50d51a57fe4 100644 --- a/include/uapi/linux/coda_psdev.h +++ b/include/uapi/linux/coda_psdev.h @@ -7,19 +7,6 @@ #define CODA_PSDEV_MAJOR 67 #define MAX_CODADEVS 5 /* how many do we allow */ - -/* messages between coda filesystem in kernel and Venus */ -struct upc_req { - struct list_head uc_chain; - caddr_t uc_data; - u_short uc_flags; - u_short uc_inSize; /* Size is at most 5000 bytes */ - u_short uc_outSize; - u_short uc_opcode; /* copied from data to save lookup */ - int uc_unique; - wait_queue_head_t uc_sleep; /* process' wait queue */ -}; - #define CODA_REQ_ASYNC 0x1 #define CODA_REQ_READ 0x2 #define CODA_REQ_WRITE 0x4 -- cgit v1.2.3 From 2fe7491d219428a32f09948e88bfaf8e71b9a66b Mon Sep 17 00:00:00 2001 From: Jan Harkes Date: Tue, 16 Jul 2019 16:28:26 -0700 Subject: uapi linux/coda_psdev.h: move CODA_REQ_ from uapi to kernel side headers These constants only used internally and not exposed to userspace. Link: http://lkml.kernel.org/r/baeafc30dad70d8b422ee679420099c2d8aa7da0.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/coda_psdev.h | 5 ----- 1 file changed, 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/coda_psdev.h b/include/uapi/linux/coda_psdev.h index d50d51a57fe4..3dacb7fad66a 100644 --- a/include/uapi/linux/coda_psdev.h +++ b/include/uapi/linux/coda_psdev.h @@ -7,9 +7,4 @@ #define CODA_PSDEV_MAJOR 67 #define MAX_CODADEVS 5 /* how many do we allow */ -#define CODA_REQ_ASYNC 0x1 -#define CODA_REQ_READ 0x2 -#define CODA_REQ_WRITE 0x4 -#define CODA_REQ_ABORT 0x8 - #endif /* _UAPI__CODA_PSDEV_H */ -- cgit v1.2.3 From 6ced9aa7b56baeb241a715df4539e60d5e3118e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 16 Jul 2019 16:28:32 -0700 Subject: coda: stop using 'struct timespec' in user API We exchange file timestamps with user space using psdev device read/write operations with a fixed but architecture specific binary layout. On 32-bit systems, this uses a 'timespec' structure that is defined by the C library to contain two 32-bit values for seconds and nanoseconds. As we get ready for the year 2038 overflow of the 32-bit signed seconds, the kernel now uses 64-bit timestamps internally, and user space will do the same change by changing the 'timespec' definition in the future. Unfortunately, this breaks the layout of the coda_vattr structure, so we need to redefine that in terms of something that does not change. I'm introducing a new 'struct vtimespec' structure here that keeps the existing layout, and the same change has to be done in the coda user space copy of linux/coda.h before anyone can use that on a 32-bit architecture with 64-bit time_t. An open question is what should happen to actual times past y2038, as they are now truncated to the last valid date when sent to user space, and interpreted as pre-1970 times when a timestamp with the MSB set is read back into the kernel. Alternatively, we could change the new timespec64_to_coda()/coda_to_timespec64() functions to use a different interpretation and extend the available range further to the future by disallowing past timestamps. This would require more changes in the user space side though. Link: http://lkml.kernel.org/r/562b7324149461743e4fbe2fedbf7c242f7e274a.1558117389.git.jaharkes@cs.cmu.edu Link: https://patchwork.kernel.org/patch/10474735/ Signed-off-by: Arnd Bergmann Signed-off-by: Jan Harkes Acked-by: Jan Harkes Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/coda.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/coda.h b/include/uapi/linux/coda.h index ed8cb263e482..fc5f7874208a 100644 --- a/include/uapi/linux/coda.h +++ b/include/uapi/linux/coda.h @@ -211,6 +211,20 @@ struct CodaFid { */ enum coda_vtype { C_VNON, C_VREG, C_VDIR, C_VBLK, C_VCHR, C_VLNK, C_VSOCK, C_VFIFO, C_VBAD }; +#ifdef __linux__ +/* + * This matches the traditional Linux 'timespec' structure binary layout, + * before using 64-bit time_t everywhere. Overflows in y2038 on 32-bit + * architectures. + */ +struct vtimespec { + long tv_sec; /* seconds */ + long tv_nsec; /* nanoseconds */ +}; +#else +#define vtimespec timespec +#endif + struct coda_vattr { long va_type; /* vnode type (for create) */ u_short va_mode; /* files access mode and type */ @@ -220,9 +234,9 @@ struct coda_vattr { long va_fileid; /* file id */ u_quad_t va_size; /* file size in bytes */ long va_blocksize; /* blocksize preferred for i/o */ - struct timespec va_atime; /* time of last access */ - struct timespec va_mtime; /* time of last modification */ - struct timespec va_ctime; /* time file changed */ + struct vtimespec va_atime; /* time of last access */ + struct vtimespec va_mtime; /* time of last modification */ + struct vtimespec va_ctime; /* time file changed */ u_long va_gen; /* generation number of file */ u_long va_flags; /* flags defined for file */ cdev_t va_rdev; /* device special file represents */ -- cgit v1.2.3 From 5e7c31dfe74703f428220384b2863525957cc160 Mon Sep 17 00:00:00 2001 From: Jan Harkes Date: Tue, 16 Jul 2019 16:28:35 -0700 Subject: coda: change Coda's user api to use 64-bit time_t in timespec Move the 32-bit time_t problems to userspace. Link: http://lkml.kernel.org/r/8d089068823bfb292a4020f773922fbd82ffad39.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/coda.h | 33 +++++++-------------------------- 1 file changed, 7 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/coda.h b/include/uapi/linux/coda.h index fc5f7874208a..5dba636b6e11 100644 --- a/include/uapi/linux/coda.h +++ b/include/uapi/linux/coda.h @@ -86,10 +86,6 @@ typedef unsigned long long u_quad_t; #define inline -struct timespec { - long ts_sec; - long ts_nsec; -}; #else /* DJGPP but not KERNEL */ #include typedef unsigned long long u_quad_t; @@ -110,13 +106,6 @@ typedef unsigned long long u_quad_t; #define cdev_t dev_t #endif -#ifdef __CYGWIN32__ -struct timespec { - time_t tv_sec; /* seconds */ - long tv_nsec; /* nanoseconds */ -}; -#endif - #ifndef __BIT_TYPES_DEFINED__ #define __BIT_TYPES_DEFINED__ typedef signed char int8_t; @@ -211,19 +200,10 @@ struct CodaFid { */ enum coda_vtype { C_VNON, C_VREG, C_VDIR, C_VBLK, C_VCHR, C_VLNK, C_VSOCK, C_VFIFO, C_VBAD }; -#ifdef __linux__ -/* - * This matches the traditional Linux 'timespec' structure binary layout, - * before using 64-bit time_t everywhere. Overflows in y2038 on 32-bit - * architectures. - */ -struct vtimespec { - long tv_sec; /* seconds */ +struct coda_timespec { + int64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; -#else -#define vtimespec timespec -#endif struct coda_vattr { long va_type; /* vnode type (for create) */ @@ -234,9 +214,9 @@ struct coda_vattr { long va_fileid; /* file id */ u_quad_t va_size; /* file size in bytes */ long va_blocksize; /* blocksize preferred for i/o */ - struct vtimespec va_atime; /* time of last access */ - struct vtimespec va_mtime; /* time of last modification */ - struct vtimespec va_ctime; /* time file changed */ + struct coda_timespec va_atime; /* time of last access */ + struct coda_timespec va_mtime; /* time of last modification */ + struct coda_timespec va_ctime; /* time file changed */ u_long va_gen; /* generation number of file */ u_long va_flags; /* flags defined for file */ cdev_t va_rdev; /* device special file represents */ @@ -301,7 +281,8 @@ struct coda_statfs { #define CIOC_KERNEL_VERSION _IOWR('c', 10, size_t) -#define CODA_KERNEL_VERSION 3 /* 128-bit file identifiers */ +// CODA_KERNEL_VERSION 3 /* 128-bit file identifiers */ +#define CODA_KERNEL_VERSION 4 /* 64-bit timespec */ /* * Venus <-> Coda RPC arguments -- cgit v1.2.3 From 6dc280ebeed2c96a2fb933103dafe655a922b9c1 Mon Sep 17 00:00:00 2001 From: Jan Harkes Date: Tue, 16 Jul 2019 16:28:51 -0700 Subject: coda: remove uapi/linux/coda_psdev.h Nothing is left in this header that is used by userspace. Link: http://lkml.kernel.org/r/bb11378cef94739f2cf89425dd6d302a52c64480.1558117389.git.jaharkes@cs.cmu.edu Signed-off-by: Jan Harkes Cc: Arnd Bergmann Cc: Colin Ian King Cc: Dan Carpenter Cc: David Howells Cc: Fabian Frederick Cc: Mikko Rapeli Cc: Sam Protsenko Cc: Yann Droneaud Cc: Zhouyang Jia Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/coda_psdev.h | 10 ---------- 1 file changed, 10 deletions(-) delete mode 100644 include/uapi/linux/coda_psdev.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/coda_psdev.h b/include/uapi/linux/coda_psdev.h deleted file mode 100644 index 3dacb7fad66a..000000000000 --- a/include/uapi/linux/coda_psdev.h +++ /dev/null @@ -1,10 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _UAPI__CODA_PSDEV_H -#define _UAPI__CODA_PSDEV_H - -#include - -#define CODA_PSDEV_MAJOR 67 -#define MAX_CODADEVS 5 /* how many do we allow */ - -#endif /* _UAPI__CODA_PSDEV_H */ -- cgit v1.2.3 From a9fba24c6ac9b66c09dfc2a0e845ecace187e89c Mon Sep 17 00:00:00 2001 From: Pedro Cuadra Date: Tue, 16 Jul 2019 16:29:13 -0700 Subject: coda: add hinting support for partial file caching This adds support for partial file caching in Coda. Every read, write and mmap informs the userspace cache manager about what part of a file is about to be accessed so that the cache manager can ensure the relevant parts are available before the operation is allowed to proceed. When a read or write operation completes, this is also reported to allow the cache manager to track when partially cached content can be released. If the cache manager does not support partial file caching, or when the entire file has been fetched into the local cache, the cache manager may return an EOPNOTSUPP error to indicate that intent upcalls are no longer necessary until the file is closed. [akpm@linux-foundation.org: little whitespace fixup] Link: http://lkml.kernel.org/r/20190618181301.6960-1-jaharkes@cs.cmu.edu Signed-off-by: Pedro Cuadra Signed-off-by: Jan Harkes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/coda.h | 29 +++++++++++++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/coda.h b/include/uapi/linux/coda.h index 5dba636b6e11..aa34c2dcae8d 100644 --- a/include/uapi/linux/coda.h +++ b/include/uapi/linux/coda.h @@ -271,7 +271,8 @@ struct coda_statfs { #define CODA_STATFS 34 #define CODA_STORE 35 #define CODA_RELEASE 36 -#define CODA_NCALLS 37 +#define CODA_ACCESS_INTENT 37 +#define CODA_NCALLS 38 #define DOWNCALL(opcode) (opcode >= CODA_REPLACE && opcode <= CODA_PURGEFID) @@ -281,8 +282,12 @@ struct coda_statfs { #define CIOC_KERNEL_VERSION _IOWR('c', 10, size_t) +// CODA_KERNEL_VERSION 0 /* don't care about kernel version number */ +// CODA_KERNEL_VERSION 1 /* The old venus 4.6 compatible interface */ +// CODA_KERNEL_VERSION 2 /* venus_lookup gets an extra parameter */ // CODA_KERNEL_VERSION 3 /* 128-bit file identifiers */ -#define CODA_KERNEL_VERSION 4 /* 64-bit timespec */ +// CODA_KERNEL_VERSION 4 /* 64-bit timespec */ +#define CODA_KERNEL_VERSION 5 /* access intent support */ /* * Venus <-> Coda RPC arguments @@ -637,6 +642,25 @@ struct coda_statfs_out { struct coda_statfs stat; }; +#define CODA_ACCESS_TYPE_READ 1 +#define CODA_ACCESS_TYPE_WRITE 2 +#define CODA_ACCESS_TYPE_MMAP 3 +#define CODA_ACCESS_TYPE_READ_FINISH 4 +#define CODA_ACCESS_TYPE_WRITE_FINISH 5 + +/* coda_access_intent: NO_OUT */ +struct coda_access_intent_in { + struct coda_in_hdr ih; + struct CodaFid VFid; + int count; + int pos; + int type; +}; + +struct coda_access_intent_out { + struct coda_out_hdr out; +}; + /* * Occasionally, we don't cache the fid returned by CODA_LOOKUP. * For instance, if the fid is inconsistent. @@ -668,6 +692,7 @@ union inputArgs { struct coda_open_by_fd_in coda_open_by_fd; struct coda_open_by_path_in coda_open_by_path; struct coda_statfs_in coda_statfs; + struct coda_access_intent_in coda_access_intent; }; union outputArgs { -- cgit v1.2.3 From 201766a20e30f982ccfe36bebfad9602c3ff574a Mon Sep 17 00:00:00 2001 From: Elvira Khabirova Date: Tue, 16 Jul 2019 16:29:42 -0700 Subject: ptrace: add PTRACE_GET_SYSCALL_INFO request PTRACE_GET_SYSCALL_INFO is a generic ptrace API that lets ptracer obtain details of the syscall the tracee is blocked in. There are two reasons for a special syscall-related ptrace request. Firstly, with the current ptrace API there are cases when ptracer cannot retrieve necessary information about syscalls. Some examples include: * The notorious int-0x80-from-64-bit-task issue. See [1] for details. In short, if a 64-bit task performs a syscall through int 0x80, its tracer has no reliable means to find out that the syscall was, in fact, a compat syscall, and misidentifies it. * Syscall-enter-stop and syscall-exit-stop look the same for the tracer. Common practice is to keep track of the sequence of ptrace-stops in order not to mix the two syscall-stops up. But it is not as simple as it looks; for example, strace had a (just recently fixed) long-standing bug where attaching strace to a tracee that is performing the execve system call led to the tracer identifying the following syscall-exit-stop as syscall-enter-stop, which messed up all the state tracking. * Since the introduction of commit 84d77d3f06e7 ("ptrace: Don't allow accessing an undumpable mm"), both PTRACE_PEEKDATA and process_vm_readv become unavailable when the process dumpable flag is cleared. On such architectures as ia64 this results in all syscall arguments being unavailable for the tracer. Secondly, ptracers also have to support a lot of arch-specific code for obtaining information about the tracee. For some architectures, this requires a ptrace(PTRACE_PEEKUSER, ...) invocation for every syscall argument and return value. ptrace(2) man page: long ptrace(enum __ptrace_request request, pid_t pid, void *addr, void *data); ... PTRACE_GET_SYSCALL_INFO Retrieve information about the syscall that caused the stop. The information is placed into the buffer pointed by "data" argument, which should be a pointer to a buffer of type "struct ptrace_syscall_info". The "addr" argument contains the size of the buffer pointed to by "data" argument (i.e., sizeof(struct ptrace_syscall_info)). The return value contains the number of bytes available to be written by the kernel. If the size of data to be written by the kernel exceeds the size specified by "addr" argument, the output is truncated. [ldv@altlinux.org: selftests/seccomp/seccomp_bpf: update for PTRACE_GET_SYSCALL_INFO] Link: http://lkml.kernel.org/r/20190708182904.GA12332@altlinux.org Link: http://lkml.kernel.org/r/20190510152842.GF28558@altlinux.org Signed-off-by: Elvira Khabirova Co-developed-by: Dmitry V. Levin Signed-off-by: Dmitry V. Levin Reviewed-by: Oleg Nesterov Reviewed-by: Kees Cook Reviewed-by: Andy Lutomirski Cc: Eugene Syromyatnikov Cc: Benjamin Herrenschmidt Cc: Greentime Hu Cc: Helge Deller [parisc] Cc: James E.J. Bottomley Cc: James Hogan Cc: kbuild test robot Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Ralf Baechle Cc: Richard Kuo Cc: Shuah Khan Cc: Vincent Chen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/ptrace.h | 35 +++++++++++++++++++++++++++++++++++ 1 file changed, 35 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index d5a1b8a492b9..a71b6e3b03eb 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -73,6 +73,41 @@ struct seccomp_metadata { __u64 flags; /* Output: filter's flags */ }; +#define PTRACE_GET_SYSCALL_INFO 0x420e +#define PTRACE_SYSCALL_INFO_NONE 0 +#define PTRACE_SYSCALL_INFO_ENTRY 1 +#define PTRACE_SYSCALL_INFO_EXIT 2 +#define PTRACE_SYSCALL_INFO_SECCOMP 3 + +struct ptrace_syscall_info { + __u8 op; /* PTRACE_SYSCALL_INFO_* */ + __u32 arch __attribute__((__aligned__(sizeof(__u32)))); + __u64 instruction_pointer; + __u64 stack_pointer; + union { + struct { + __u64 nr; + __u64 args[6]; + } entry; + struct { + __s64 rval; + __u8 is_error; + } exit; + struct { + __u64 nr; + __u64 args[6]; + __u32 ret_data; + } seccomp; + }; +}; + +/* + * These values are stored in task->ptrace_message + * by tracehook_report_syscall_* to describe the current syscall-stop. + */ +#define PTRACE_EVENTMSG_SYSCALL_ENTRY 1 +#define PTRACE_EVENTMSG_SYSCALL_EXIT 2 + /* Read signals from a shared (process wide) queue */ #define PTRACE_PEEKSIGINFO_SHARED (1 << 0) -- cgit v1.2.3 From 8c2e408e73f735d2e6e8b43f9b038c9abb082939 Mon Sep 17 00:00:00 2001 From: Pankaj Gupta Date: Fri, 12 Jul 2019 10:46:10 +0530 Subject: virtio_pmem: fix sparse warning This patch fixes below sparse warning related to __virtio type in virtio pmem driver. This is reported by Intel test bot on linux-next tree. nd_virtio.c:56:28: warning: incorrect type in assignment (different base types) nd_virtio.c:56:28: expected unsigned int [unsigned] [usertype] type nd_virtio.c:56:28: got restricted __virtio32 nd_virtio.c:93:59: warning: incorrect type in argument 2 (different base types) nd_virtio.c:93:59: expected restricted __virtio32 [usertype] val nd_virtio.c:93:59: got unsigned int [unsigned] [usertype] ret Reported-by: kbuild test robot Signed-off-by: Pankaj Gupta Acked-by: Michael S. Tsirkin Signed-off-by: Dan Williams --- include/uapi/linux/virtio_pmem.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_pmem.h b/include/uapi/linux/virtio_pmem.h index efcd72f2d20d..9a63ed6d062f 100644 --- a/include/uapi/linux/virtio_pmem.h +++ b/include/uapi/linux/virtio_pmem.h @@ -23,12 +23,12 @@ struct virtio_pmem_config { struct virtio_pmem_resp { /* Host return status corresponding to flush request */ - __u32 ret; + __le32 ret; }; struct virtio_pmem_req { /* command type */ - __u32 type; + __le32 type; }; #endif -- cgit v1.2.3