From 1cbcb564f5b67cee2fc2f78132b9733118a79c6d Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 5 Feb 2024 14:48:24 +0200 Subject: net/mlx5: Add the IFC related bits for query tracker Add the IFC related bits for query tracker. Signed-off-by: Yishai Hadas Reviewed-by: Kevin Tian Acked-by: Leon Romanovsky Link: https://lore.kernel.org/r/20240205124828.232701-2-yishaih@nvidia.com Signed-off-by: Alex Williamson --- include/linux/mlx5/mlx5_ifc.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c726f90ab752..0e513e372bf0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -12672,6 +12672,11 @@ struct mlx5_ifc_modify_page_track_obj_in_bits { struct mlx5_ifc_page_track_bits obj_context; }; +struct mlx5_ifc_query_page_track_obj_out_bits { + struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; + struct mlx5_ifc_page_track_bits obj_context; +}; + struct mlx5_ifc_msecq_reg_bits { u8 reserved_at_0[0x20]; -- cgit v1.3 From 4de676d494cd8fb2b4c65e58c19ebbdb36673957 Mon Sep 17 00:00:00 2001 From: Ankit Agrawal Date: Tue, 20 Feb 2024 17:20:53 +0530 Subject: vfio/pci: rename and export do_io_rw() do_io_rw() is used to read/write to the device MMIO. The grace hopper VFIO PCI variant driver require this functionality to read/write to its memory. Rename this as vfio_pci_core functions and export as GPL. Reviewed-by: Kevin Tian Reviewed-by: Yishai Hadas Signed-off-by: Ankit Agrawal Link: https://lore.kernel.org/r/20240220115055.23546-2-ankita@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_rdwr.c | 16 +++++++++------- include/linux/vfio_pci_core.h | 5 ++++- 2 files changed, 13 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c index 07fea08ea8a2..03b8f7ada1ac 100644 --- a/drivers/vfio/pci/vfio_pci_rdwr.c +++ b/drivers/vfio/pci/vfio_pci_rdwr.c @@ -96,10 +96,10 @@ VFIO_IOREAD(32) * reads with -1. This is intended for handling MSI-X vector tables and * leftover space for ROM BARs. */ -static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, - void __iomem *io, char __user *buf, - loff_t off, size_t count, size_t x_start, - size_t x_end, bool iswrite) +ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, + loff_t off, size_t count, size_t x_start, + size_t x_end, bool iswrite) { ssize_t done = 0; int ret; @@ -201,6 +201,7 @@ static ssize_t do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, return done; } +EXPORT_SYMBOL_GPL(vfio_pci_core_do_io_rw); int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar) { @@ -279,8 +280,8 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_core_device *vdev, char __user *buf, x_end = vdev->msix_offset + vdev->msix_size; } - done = do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, - count, x_start, x_end, iswrite); + done = vfio_pci_core_do_io_rw(vdev, res->flags & IORESOURCE_MEM, io, buf, pos, + count, x_start, x_end, iswrite); if (done >= 0) *ppos += done; @@ -348,7 +349,8 @@ ssize_t vfio_pci_vga_rw(struct vfio_pci_core_device *vdev, char __user *buf, * probing, so we don't currently worry about access in relation * to the memory enable bit in the command register. */ - done = do_io_rw(vdev, false, iomem, buf, off, count, 0, 0, iswrite); + done = vfio_pci_core_do_io_rw(vdev, false, iomem, buf, off, count, + 0, 0, iswrite); vga_put(vdev->pdev, rsrc); diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index 85e84b92751b..cf9480a31f3e 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -130,7 +130,10 @@ void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev); int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar); pci_ers_result_t vfio_pci_core_aer_err_detected(struct pci_dev *pdev, pci_channel_state_t state); - +ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, + void __iomem *io, char __user *buf, + loff_t off, size_t count, size_t x_start, + size_t x_end, bool iswrite); #define VFIO_IOWRITE_DECLATION(size) \ int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size val, void __iomem *io); -- cgit v1.3 From 30e920e1debb437e5aea7a4ccdab61634354297a Mon Sep 17 00:00:00 2001 From: Ankit Agrawal Date: Tue, 20 Feb 2024 17:20:54 +0530 Subject: vfio/pci: rename and export range_intersect_range range_intersect_range determines an overlap between two ranges. If an overlap, the helper function returns the overlapping offset and size. The VFIO PCI variant driver emulates the PCI config space BAR offset registers. These offset may be accessed for read/write with a variety of lengths including sub-word sizes from sub-word offsets. The driver makes use of this helper function to read/write the targeted part of the emulated register. Make this a vfio_pci_core function, rename and export as GPL. Also update references in virtio driver. Reviewed-by: Kevin Tian Reviewed-by: Yishai Hadas Signed-off-by: Ankit Agrawal Link: https://lore.kernel.org/r/20240220115055.23546-3-ankita@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/pci/vfio_pci_config.c | 42 ++++++++++++++++++++++ drivers/vfio/pci/virtio/main.c | 72 ++++++++++++++------------------------ include/linux/vfio_pci_core.h | 5 +++ 3 files changed, 73 insertions(+), 46 deletions(-) (limited to 'include') diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c index 7e2e62ab0869..97422aafaa7b 100644 --- a/drivers/vfio/pci/vfio_pci_config.c +++ b/drivers/vfio/pci/vfio_pci_config.c @@ -1966,3 +1966,45 @@ ssize_t vfio_pci_config_rw(struct vfio_pci_core_device *vdev, char __user *buf, return done; } + +/** + * vfio_pci_core_range_intersect_range() - Determine overlap between a buffer + * and register offset ranges. + * @buf_start: start offset of the buffer + * @buf_cnt: number of buffer bytes + * @reg_start: start register offset + * @reg_cnt: number of register bytes + * @buf_offset: start offset of overlap in the buffer + * @intersect_count: number of overlapping bytes + * @register_offset: start offset of overlap in register + * + * Returns: true if there is overlap, false if not. + * The overlap start and size is returned through function args. + */ +bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt, + loff_t reg_start, size_t reg_cnt, + loff_t *buf_offset, + size_t *intersect_count, + size_t *register_offset) +{ + if (buf_start <= reg_start && + buf_start + buf_cnt > reg_start) { + *buf_offset = reg_start - buf_start; + *intersect_count = min_t(size_t, reg_cnt, + buf_start + buf_cnt - reg_start); + *register_offset = 0; + return true; + } + + if (buf_start > reg_start && + buf_start < reg_start + reg_cnt) { + *buf_offset = 0; + *intersect_count = min_t(size_t, buf_cnt, + reg_start + reg_cnt - buf_start); + *register_offset = buf_start - reg_start; + return true; + } + + return false; +} +EXPORT_SYMBOL_GPL(vfio_pci_core_range_intersect_range); diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c index d5af683837d3..b5d3a8c5bbc9 100644 --- a/drivers/vfio/pci/virtio/main.c +++ b/drivers/vfio/pci/virtio/main.c @@ -132,33 +132,6 @@ end: return ret ? ret : count; } -static bool range_intersect_range(loff_t range1_start, size_t count1, - loff_t range2_start, size_t count2, - loff_t *start_offset, - size_t *intersect_count, - size_t *register_offset) -{ - if (range1_start <= range2_start && - range1_start + count1 > range2_start) { - *start_offset = range2_start - range1_start; - *intersect_count = min_t(size_t, count2, - range1_start + count1 - range2_start); - *register_offset = 0; - return true; - } - - if (range1_start > range2_start && - range1_start < range2_start + count2) { - *start_offset = 0; - *intersect_count = min_t(size_t, count1, - range2_start + count2 - range1_start); - *register_offset = range1_start - range2_start; - return true; - } - - return false; -} - static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev, char __user *buf, size_t count, loff_t *ppos) @@ -178,16 +151,18 @@ static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev, if (ret < 0) return ret; - if (range_intersect_range(pos, count, PCI_DEVICE_ID, sizeof(val16), - ©_offset, ©_count, ®ister_offset)) { + if (vfio_pci_core_range_intersect_range(pos, count, PCI_DEVICE_ID, + sizeof(val16), ©_offset, + ©_count, ®ister_offset)) { val16 = cpu_to_le16(VIRTIO_TRANS_ID_NET); if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count)) return -EFAULT; } if ((le16_to_cpu(virtvdev->pci_cmd) & PCI_COMMAND_IO) && - range_intersect_range(pos, count, PCI_COMMAND, sizeof(val16), - ©_offset, ©_count, ®ister_offset)) { + vfio_pci_core_range_intersect_range(pos, count, PCI_COMMAND, + sizeof(val16), ©_offset, + ©_count, ®ister_offset)) { if (copy_from_user((void *)&val16 + register_offset, buf + copy_offset, copy_count)) return -EFAULT; @@ -197,16 +172,18 @@ static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev, return -EFAULT; } - if (range_intersect_range(pos, count, PCI_REVISION_ID, sizeof(val8), - ©_offset, ©_count, ®ister_offset)) { + if (vfio_pci_core_range_intersect_range(pos, count, PCI_REVISION_ID, + sizeof(val8), ©_offset, + ©_count, ®ister_offset)) { /* Transional needs to have revision 0 */ val8 = 0; if (copy_to_user(buf + copy_offset, &val8, copy_count)) return -EFAULT; } - if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, sizeof(val32), - ©_offset, ©_count, ®ister_offset)) { + if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, + sizeof(val32), ©_offset, + ©_count, ®ister_offset)) { u32 bar_mask = ~(virtvdev->bar0_virtual_buf_size - 1); u32 pci_base_addr_0 = le32_to_cpu(virtvdev->pci_base_addr_0); @@ -215,8 +192,9 @@ static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev, return -EFAULT; } - if (range_intersect_range(pos, count, PCI_SUBSYSTEM_ID, sizeof(val16), - ©_offset, ©_count, ®ister_offset)) { + if (vfio_pci_core_range_intersect_range(pos, count, PCI_SUBSYSTEM_ID, + sizeof(val16), ©_offset, + ©_count, ®ister_offset)) { /* * Transitional devices use the PCI subsystem device id as * virtio device id, same as legacy driver always did. @@ -227,8 +205,9 @@ static ssize_t virtiovf_pci_read_config(struct vfio_device *core_vdev, return -EFAULT; } - if (range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID, sizeof(val16), - ©_offset, ©_count, ®ister_offset)) { + if (vfio_pci_core_range_intersect_range(pos, count, PCI_SUBSYSTEM_VENDOR_ID, + sizeof(val16), ©_offset, + ©_count, ®ister_offset)) { val16 = cpu_to_le16(PCI_VENDOR_ID_REDHAT_QUMRANET); if (copy_to_user(buf + copy_offset, (void *)&val16 + register_offset, copy_count)) @@ -270,19 +249,20 @@ static ssize_t virtiovf_pci_write_config(struct vfio_device *core_vdev, loff_t copy_offset; size_t copy_count; - if (range_intersect_range(pos, count, PCI_COMMAND, sizeof(virtvdev->pci_cmd), - ©_offset, ©_count, - ®ister_offset)) { + if (vfio_pci_core_range_intersect_range(pos, count, PCI_COMMAND, + sizeof(virtvdev->pci_cmd), + ©_offset, ©_count, + ®ister_offset)) { if (copy_from_user((void *)&virtvdev->pci_cmd + register_offset, buf + copy_offset, copy_count)) return -EFAULT; } - if (range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, - sizeof(virtvdev->pci_base_addr_0), - ©_offset, ©_count, - ®ister_offset)) { + if (vfio_pci_core_range_intersect_range(pos, count, PCI_BASE_ADDRESS_0, + sizeof(virtvdev->pci_base_addr_0), + ©_offset, ©_count, + ®ister_offset)) { if (copy_from_user((void *)&virtvdev->pci_base_addr_0 + register_offset, buf + copy_offset, copy_count)) diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h index cf9480a31f3e..a2c8b8bba711 100644 --- a/include/linux/vfio_pci_core.h +++ b/include/linux/vfio_pci_core.h @@ -134,6 +134,11 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem, void __iomem *io, char __user *buf, loff_t off, size_t count, size_t x_start, size_t x_end, bool iswrite); +bool vfio_pci_core_range_intersect_range(loff_t buf_start, size_t buf_cnt, + loff_t reg_start, size_t reg_cnt, + loff_t *buf_offset, + size_t *intersect_count, + size_t *register_offset); #define VFIO_IOWRITE_DECLATION(size) \ int vfio_pci_core_iowrite##size(struct vfio_pci_core_device *vdev, \ bool test_mem, u##size val, void __iomem *io); -- cgit v1.3 From b620ecbd17a03cacd06f014a5d3f3a11285ce053 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 8 Mar 2024 16:05:24 -0700 Subject: vfio: Introduce interface to flush virqfd inject workqueue In order to synchronize changes that can affect the thread callback, introduce an interface to force a flush of the inject workqueue. The irqfd pointer is only valid under spinlock, but the workqueue cannot be flushed under spinlock. Therefore the flush work for the irqfd is queued under spinlock. The vfio_irqfd_cleanup_wq workqueue is re-used for queuing this work such that flushing the workqueue is also ordered relative to shutdown. Reviewed-by: Kevin Tian Reviewed-by: Reinette Chatre Reviewed-by: Eric Auger Link: https://lore.kernel.org/r/20240308230557.805580-4-alex.williamson@redhat.com Signed-off-by: Alex Williamson --- drivers/vfio/virqfd.c | 21 +++++++++++++++++++++ include/linux/vfio.h | 2 ++ 2 files changed, 23 insertions(+) (limited to 'include') diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c index 29c564b7a6e1..532269133801 100644 --- a/drivers/vfio/virqfd.c +++ b/drivers/vfio/virqfd.c @@ -101,6 +101,13 @@ static void virqfd_inject(struct work_struct *work) virqfd->thread(virqfd->opaque, virqfd->data); } +static void virqfd_flush_inject(struct work_struct *work) +{ + struct virqfd *virqfd = container_of(work, struct virqfd, flush_inject); + + flush_work(&virqfd->inject); +} + int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), @@ -124,6 +131,7 @@ int vfio_virqfd_enable(void *opaque, INIT_WORK(&virqfd->shutdown, virqfd_shutdown); INIT_WORK(&virqfd->inject, virqfd_inject); + INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject); irqfd = fdget(fd); if (!irqfd.file) { @@ -213,3 +221,16 @@ void vfio_virqfd_disable(struct virqfd **pvirqfd) flush_workqueue(vfio_irqfd_cleanup_wq); } EXPORT_SYMBOL_GPL(vfio_virqfd_disable); + +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd) +{ + unsigned long flags; + + spin_lock_irqsave(&virqfd_lock, flags); + if (*pvirqfd && (*pvirqfd)->thread) + queue_work(vfio_irqfd_cleanup_wq, &(*pvirqfd)->flush_inject); + spin_unlock_irqrestore(&virqfd_lock, flags); + + flush_workqueue(vfio_irqfd_cleanup_wq); +} +EXPORT_SYMBOL_GPL(vfio_virqfd_flush_thread); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 89b265bc6ec3..8b1a29820409 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -356,6 +356,7 @@ struct virqfd { wait_queue_entry_t wait; poll_table pt; struct work_struct shutdown; + struct work_struct flush_inject; struct virqfd **pvirqfd; }; @@ -363,5 +364,6 @@ int vfio_virqfd_enable(void *opaque, int (*handler)(void *, void *), void (*thread)(void *, void *), void *data, struct virqfd **pvirqfd, int fd); void vfio_virqfd_disable(struct virqfd **pvirqfd); +void vfio_virqfd_flush_thread(struct virqfd **pvirqfd); #endif /* VFIO_H */ -- cgit v1.3