From b558469580f82b925d6651ac8d7a01070402dbf8 Mon Sep 17 00:00:00 2001 From: Oliver Neukum Date: Thu, 18 Jan 2024 19:36:33 +0100 Subject: USB: uapi: OTG 3.0 Add attribute bits defined in version 3.0 Signed-off-by: Oliver Neukum Link: https://lore.kernel.org/r/20240118183644.16125-1-oneukum@suse.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/ch9.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index 8a147abfc680..44d73ba8788d 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -763,6 +763,8 @@ struct usb_otg20_descriptor { #define USB_OTG_SRP (1 << 0) #define USB_OTG_HNP (1 << 1) /* swap host/device roles */ #define USB_OTG_ADP (1 << 2) /* support ADP */ +/* OTG 3.0 */ +#define USB_OTG_RSP (1 << 3) /* support RSP */ #define OTG_STS_SELECTOR 0xF000 /* OTG status selector */ /*-------------------------------------------------------------------------*/ -- cgit v1.2.3 From ace4ebf9b70a7daea12102c09ba5ef6bb73223aa Mon Sep 17 00:00:00 2001 From: "Jiri Slaby (SUSE)" Date: Mon, 22 Jan 2024 12:03:46 +0100 Subject: tty: vt: define a common enum for VESA blanking constants There are currently two places with VESA blanking constants definitions: fb.h and console.h. Extract/unify the two to a separate header (vesa.h). Given the fb's is in an uapi header, create the common header in uapi too. Note that instead of macros, an enum (vesa_blank_mode) is created. But the macros are kept too (they now expand to the enum constants), just in case someone in userspace performs some #ifdeffery. Signed-off-by: "Jiri Slaby (SUSE)" Cc: Helge Deller Cc: linux-kernel@vger.kernel.org Cc: linux-fbdev@vger.kernel.org Cc: dri-devel@lists.freedesktop.org Cc: Thomas Zimmermann Tested-by: Helge Deller # parisc STI console Link: https://lore.kernel.org/r/20240122110401.7289-33-jirislaby@kernel.org Signed-off-by: Greg Kroah-Hartman --- include/linux/console.h | 7 +------ include/uapi/linux/fb.h | 8 +------- include/uapi/linux/vesa.h | 18 ++++++++++++++++++ 3 files changed, 20 insertions(+), 13 deletions(-) create mode 100644 include/uapi/linux/vesa.h (limited to 'include/uapi') diff --git a/include/linux/console.h b/include/linux/console.h index f7c6b5fc3a36..860f82756c9c 100644 --- a/include/linux/console.h +++ b/include/linux/console.h @@ -18,6 +18,7 @@ #include #include #include +#include struct vc_data; struct console_font_op; @@ -520,12 +521,6 @@ void vcs_remove_sysfs(int index); */ extern atomic_t ignore_console_lock_warning; -/* VESA Blanking Levels */ -#define VESA_NO_BLANKING 0 -#define VESA_VSYNC_SUSPEND 1 -#define VESA_HSYNC_SUSPEND 2 -#define VESA_POWERDOWN 3 - extern void console_init(void); /* For deferred console takeover */ diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index 3a49913d006c..cde8f173f566 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -4,6 +4,7 @@ #include #include +#include /* Definitions of frame buffers */ @@ -293,13 +294,6 @@ struct fb_con2fbmap { __u32 framebuffer; }; -/* VESA Blanking Levels */ -#define VESA_NO_BLANKING 0 -#define VESA_VSYNC_SUSPEND 1 -#define VESA_HSYNC_SUSPEND 2 -#define VESA_POWERDOWN 3 - - enum { /* screen: unblanked, hsync: on, vsync: on */ FB_BLANK_UNBLANK = VESA_NO_BLANKING, diff --git a/include/uapi/linux/vesa.h b/include/uapi/linux/vesa.h new file mode 100644 index 000000000000..81947f5088cd --- /dev/null +++ b/include/uapi/linux/vesa.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_VESA_H +#define _UAPI_LINUX_VESA_H + +/* VESA Blanking Levels */ +enum vesa_blank_mode { + VESA_NO_BLANKING = 0, +#define VESA_NO_BLANKING VESA_NO_BLANKING + VESA_VSYNC_SUSPEND = 1, +#define VESA_VSYNC_SUSPEND VESA_VSYNC_SUSPEND + VESA_HSYNC_SUSPEND = 2, +#define VESA_HSYNC_SUSPEND VESA_HSYNC_SUSPEND + VESA_POWERDOWN = VESA_VSYNC_SUSPEND | VESA_HSYNC_SUSPEND, +#define VESA_POWERDOWN VESA_POWERDOWN + VESA_BLANK_MAX = VESA_POWERDOWN, +}; + +#endif -- cgit v1.2.3 From 7b07a2a7ca02a20124b552be96c5a56910795488 Mon Sep 17 00:00:00 2001 From: Paul Cercueil Date: Tue, 30 Jan 2024 13:23:39 +0100 Subject: usb: gadget: functionfs: Add DMABUF import interface MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch introduces three new ioctls. They all should be called on a data endpoint (ie. not ep0). They are: - FUNCTIONFS_DMABUF_ATTACH, which takes the file descriptor of a DMABUF object to attach to the endpoint. - FUNCTIONFS_DMABUF_DETACH, which takes the file descriptor of the DMABUF to detach from the endpoint. Note that closing the endpoint's file descriptor will automatically detach all attached DMABUFs. - FUNCTIONFS_DMABUF_TRANSFER, which requests a data transfer from / to the given DMABUF. Its argument is a structure that packs the DMABUF's file descriptor, the size in bytes to transfer (which should generally be set to the size of the DMABUF), and a 'flags' field which is unused for now. Before this ioctl can be used, the related DMABUF must be attached with FUNCTIONFS_DMABUF_ATTACH. These three ioctls enable the FunctionFS code to transfer data between the USB stack and a DMABUF object, which can be provided by a driver from a completely different subsystem, in a zero-copy fashion. Signed-off-by: Paul Cercueil Acked-by: Daniel Vetter Acked-by: Christian König Link: https://lore.kernel.org/r/20240130122340.54813-4-paul@crapouillou.net Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/Kconfig | 1 + drivers/usb/gadget/function/f_fs.c | 467 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/usb/functionfs.h | 41 ++++ 3 files changed, 509 insertions(+) (limited to 'include/uapi') diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig index b3592bcb0f96..566ff0b1282a 100644 --- a/drivers/usb/gadget/Kconfig +++ b/drivers/usb/gadget/Kconfig @@ -190,6 +190,7 @@ config USB_F_MASS_STORAGE tristate config USB_F_FS + select DMA_SHARED_BUFFER tristate config USB_F_UAC1 diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 491a1e0f4fa3..bffbc1dc651f 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -15,6 +15,9 @@ /* #define VERBOSE_DEBUG */ #include +#include +#include +#include #include #include #include @@ -43,6 +46,8 @@ #define FUNCTIONFS_MAGIC 0xa647361 /* Chosen by a honest dice roll ;) */ +MODULE_IMPORT_NS(DMA_BUF); + /* Reference counter handling */ static void ffs_data_get(struct ffs_data *ffs); static void ffs_data_put(struct ffs_data *ffs); @@ -124,6 +129,25 @@ struct ffs_ep { u8 num; }; +struct ffs_dmabuf_priv { + struct list_head entry; + struct kref ref; + struct ffs_data *ffs; + struct dma_buf_attachment *attach; + struct sg_table *sgt; + enum dma_data_direction dir; + spinlock_t lock; + u64 context; + struct usb_request *req; /* P: ffs->eps_lock */ + struct usb_ep *ep; /* P: ffs->eps_lock */ +}; + +struct ffs_dma_fence { + struct dma_fence base; + struct ffs_dmabuf_priv *priv; + struct work_struct work; +}; + struct ffs_epfile { /* Protects ep->ep and ep->req. */ struct mutex mutex; @@ -197,6 +221,11 @@ struct ffs_epfile { unsigned char isoc; /* P: ffs->eps_lock */ unsigned char _pad; + + /* Protects dmabufs */ + struct mutex dmabufs_mutex; + struct list_head dmabufs; /* P: dmabufs_mutex */ + atomic_t seqno; }; struct ffs_buffer { @@ -1271,10 +1300,58 @@ static ssize_t ffs_epfile_read_iter(struct kiocb *kiocb, struct iov_iter *to) return res; } +static void ffs_dmabuf_release(struct kref *ref) +{ + struct ffs_dmabuf_priv *priv = container_of(ref, struct ffs_dmabuf_priv, ref); + struct dma_buf_attachment *attach = priv->attach; + struct dma_buf *dmabuf = attach->dmabuf; + + pr_vdebug("FFS DMABUF release\n"); + dma_resv_lock(dmabuf->resv, NULL); + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir); + dma_resv_unlock(dmabuf->resv); + + dma_buf_detach(attach->dmabuf, attach); + dma_buf_put(dmabuf); + kfree(priv); +} + +static void ffs_dmabuf_get(struct dma_buf_attachment *attach) +{ + struct ffs_dmabuf_priv *priv = attach->importer_priv; + + kref_get(&priv->ref); +} + +static void ffs_dmabuf_put(struct dma_buf_attachment *attach) +{ + struct ffs_dmabuf_priv *priv = attach->importer_priv; + + kref_put(&priv->ref, ffs_dmabuf_release); +} + static int ffs_epfile_release(struct inode *inode, struct file *file) { struct ffs_epfile *epfile = inode->i_private; + struct ffs_dmabuf_priv *priv, *tmp; + struct ffs_data *ffs = epfile->ffs; + + mutex_lock(&epfile->dmabufs_mutex); + + /* Close all attached DMABUFs */ + list_for_each_entry_safe(priv, tmp, &epfile->dmabufs, entry) { + /* Cancel any pending transfer */ + spin_lock_irq(&ffs->eps_lock); + if (priv->ep && priv->req) + usb_ep_dequeue(priv->ep, priv->req); + spin_unlock_irq(&ffs->eps_lock); + + list_del(&priv->entry); + ffs_dmabuf_put(priv->attach); + } + + mutex_unlock(&epfile->dmabufs_mutex); __ffs_epfile_read_buffer_free(epfile); ffs_data_closed(epfile->ffs); @@ -1282,6 +1359,356 @@ ffs_epfile_release(struct inode *inode, struct file *file) return 0; } +static void ffs_dmabuf_cleanup(struct work_struct *work) +{ + struct ffs_dma_fence *dma_fence = + container_of(work, struct ffs_dma_fence, work); + struct ffs_dmabuf_priv *priv = dma_fence->priv; + struct dma_buf_attachment *attach = priv->attach; + struct dma_fence *fence = &dma_fence->base; + + ffs_dmabuf_put(attach); + dma_fence_put(fence); +} + +static void ffs_dmabuf_signal_done(struct ffs_dma_fence *dma_fence, int ret) +{ + struct ffs_dmabuf_priv *priv = dma_fence->priv; + struct dma_fence *fence = &dma_fence->base; + bool cookie = dma_fence_begin_signalling(); + + dma_fence_get(fence); + fence->error = ret; + dma_fence_signal(fence); + dma_fence_end_signalling(cookie); + + /* + * The fence will be unref'd in ffs_dmabuf_cleanup. + * It can't be done here, as the unref functions might try to lock + * the resv object, which would deadlock. + */ + INIT_WORK(&dma_fence->work, ffs_dmabuf_cleanup); + queue_work(priv->ffs->io_completion_wq, &dma_fence->work); +} + +static void ffs_epfile_dmabuf_io_complete(struct usb_ep *ep, + struct usb_request *req) +{ + pr_vdebug("FFS: DMABUF transfer complete, status=%d\n", req->status); + ffs_dmabuf_signal_done(req->context, req->status); + usb_ep_free_request(ep, req); +} + +static const char *ffs_dmabuf_get_driver_name(struct dma_fence *fence) +{ + return "functionfs"; +} + +static const char *ffs_dmabuf_get_timeline_name(struct dma_fence *fence) +{ + return ""; +} + +static void ffs_dmabuf_fence_release(struct dma_fence *fence) +{ + struct ffs_dma_fence *dma_fence = + container_of(fence, struct ffs_dma_fence, base); + + kfree(dma_fence); +} + +static const struct dma_fence_ops ffs_dmabuf_fence_ops = { + .get_driver_name = ffs_dmabuf_get_driver_name, + .get_timeline_name = ffs_dmabuf_get_timeline_name, + .release = ffs_dmabuf_fence_release, +}; + +static int ffs_dma_resv_lock(struct dma_buf *dmabuf, bool nonblock) +{ + if (!nonblock) + return dma_resv_lock_interruptible(dmabuf->resv, NULL); + + if (!dma_resv_trylock(dmabuf->resv)) + return -EBUSY; + + return 0; +} + +static struct dma_buf_attachment * +ffs_dmabuf_find_attachment(struct ffs_epfile *epfile, struct dma_buf *dmabuf) +{ + struct device *dev = epfile->ffs->gadget->dev.parent; + struct dma_buf_attachment *attach = NULL; + struct ffs_dmabuf_priv *priv; + + mutex_lock(&epfile->dmabufs_mutex); + + list_for_each_entry(priv, &epfile->dmabufs, entry) { + if (priv->attach->dev == dev + && priv->attach->dmabuf == dmabuf) { + attach = priv->attach; + break; + } + } + + if (attach) + ffs_dmabuf_get(attach); + + mutex_unlock(&epfile->dmabufs_mutex); + + return attach ?: ERR_PTR(-EPERM); +} + +static int ffs_dmabuf_attach(struct file *file, int fd) +{ + bool nonblock = file->f_flags & O_NONBLOCK; + struct ffs_epfile *epfile = file->private_data; + struct usb_gadget *gadget = epfile->ffs->gadget; + struct dma_buf_attachment *attach; + struct ffs_dmabuf_priv *priv; + enum dma_data_direction dir; + struct sg_table *sg_table; + struct dma_buf *dmabuf; + int err; + + if (!gadget || !gadget->sg_supported) + return -EPERM; + + dmabuf = dma_buf_get(fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + attach = dma_buf_attach(dmabuf, gadget->dev.parent); + if (IS_ERR(attach)) { + err = PTR_ERR(attach); + goto err_dmabuf_put; + } + + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) { + err = -ENOMEM; + goto err_dmabuf_detach; + } + + dir = epfile->in ? DMA_FROM_DEVICE : DMA_TO_DEVICE; + + err = ffs_dma_resv_lock(dmabuf, nonblock); + if (err) + goto err_free_priv; + + sg_table = dma_buf_map_attachment(attach, dir); + dma_resv_unlock(dmabuf->resv); + + if (IS_ERR(sg_table)) { + err = PTR_ERR(sg_table); + goto err_free_priv; + } + + attach->importer_priv = priv; + + priv->sgt = sg_table; + priv->dir = dir; + priv->ffs = epfile->ffs; + priv->attach = attach; + spin_lock_init(&priv->lock); + kref_init(&priv->ref); + priv->context = dma_fence_context_alloc(1); + + mutex_lock(&epfile->dmabufs_mutex); + list_add(&priv->entry, &epfile->dmabufs); + mutex_unlock(&epfile->dmabufs_mutex); + + return 0; + +err_free_priv: + kfree(priv); +err_dmabuf_detach: + dma_buf_detach(dmabuf, attach); +err_dmabuf_put: + dma_buf_put(dmabuf); + + return err; +} + +static int ffs_dmabuf_detach(struct file *file, int fd) +{ + struct ffs_epfile *epfile = file->private_data; + struct ffs_data *ffs = epfile->ffs; + struct device *dev = ffs->gadget->dev.parent; + struct ffs_dmabuf_priv *priv, *tmp; + struct dma_buf *dmabuf; + int ret = -EPERM; + + dmabuf = dma_buf_get(fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + mutex_lock(&epfile->dmabufs_mutex); + + list_for_each_entry_safe(priv, tmp, &epfile->dmabufs, entry) { + if (priv->attach->dev == dev + && priv->attach->dmabuf == dmabuf) { + /* Cancel any pending transfer */ + spin_lock_irq(&ffs->eps_lock); + if (priv->ep && priv->req) + usb_ep_dequeue(priv->ep, priv->req); + spin_unlock_irq(&ffs->eps_lock); + + list_del(&priv->entry); + + /* Unref the reference from ffs_dmabuf_attach() */ + ffs_dmabuf_put(priv->attach); + ret = 0; + break; + } + } + + mutex_unlock(&epfile->dmabufs_mutex); + dma_buf_put(dmabuf); + + return ret; +} + +static int ffs_dmabuf_transfer(struct file *file, + const struct usb_ffs_dmabuf_transfer_req *req) +{ + bool nonblock = file->f_flags & O_NONBLOCK; + struct ffs_epfile *epfile = file->private_data; + struct dma_buf_attachment *attach; + struct ffs_dmabuf_priv *priv; + struct ffs_dma_fence *fence; + struct usb_request *usb_req; + struct dma_buf *dmabuf; + struct ffs_ep *ep; + bool cookie; + u32 seqno; + int ret; + + if (req->flags & ~USB_FFS_DMABUF_TRANSFER_MASK) + return -EINVAL; + + dmabuf = dma_buf_get(req->fd); + if (IS_ERR(dmabuf)) + return PTR_ERR(dmabuf); + + if (req->length > dmabuf->size || req->length == 0) { + ret = -EINVAL; + goto err_dmabuf_put; + } + + attach = ffs_dmabuf_find_attachment(epfile, dmabuf); + if (IS_ERR(attach)) { + ret = PTR_ERR(attach); + goto err_dmabuf_put; + } + + priv = attach->importer_priv; + + ep = ffs_epfile_wait_ep(file); + if (IS_ERR(ep)) { + ret = PTR_ERR(ep); + goto err_attachment_put; + } + + ret = ffs_dma_resv_lock(dmabuf, nonblock); + if (ret) + goto err_attachment_put; + + /* Make sure we don't have writers */ + if (!dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_WRITE)) { + pr_vdebug("FFS WRITE fence is not signaled\n"); + ret = -EBUSY; + goto err_resv_unlock; + } + + /* If we're writing to the DMABUF, make sure we don't have readers */ + if (epfile->in && + !dma_resv_test_signaled(dmabuf->resv, DMA_RESV_USAGE_READ)) { + pr_vdebug("FFS READ fence is not signaled\n"); + ret = -EBUSY; + goto err_resv_unlock; + } + + ret = dma_resv_reserve_fences(dmabuf->resv, 1); + if (ret) + goto err_resv_unlock; + + fence = kmalloc(sizeof(*fence), GFP_KERNEL); + if (!fence) { + ret = -ENOMEM; + goto err_resv_unlock; + } + + fence->priv = priv; + + spin_lock_irq(&epfile->ffs->eps_lock); + + /* In the meantime, endpoint got disabled or changed. */ + if (epfile->ep != ep) { + ret = -ESHUTDOWN; + goto err_fence_put; + } + + usb_req = usb_ep_alloc_request(ep->ep, GFP_ATOMIC); + if (!usb_req) { + ret = -ENOMEM; + goto err_fence_put; + } + + /* + * usb_ep_queue() guarantees that all transfers are processed in the + * order they are enqueued, so we can use a simple incrementing + * sequence number for the dma_fence. + */ + seqno = atomic_add_return(1, &epfile->seqno); + + dma_fence_init(&fence->base, &ffs_dmabuf_fence_ops, + &priv->lock, priv->context, seqno); + + dma_resv_add_fence(dmabuf->resv, &fence->base, + dma_resv_usage_rw(epfile->in)); + dma_resv_unlock(dmabuf->resv); + + /* Now that the dma_fence is in place, queue the transfer. */ + + usb_req->length = req->length; + usb_req->buf = NULL; + usb_req->sg = priv->sgt->sgl; + usb_req->num_sgs = sg_nents_for_len(priv->sgt->sgl, req->length); + usb_req->sg_was_mapped = true; + usb_req->context = fence; + usb_req->complete = ffs_epfile_dmabuf_io_complete; + + cookie = dma_fence_begin_signalling(); + ret = usb_ep_queue(ep->ep, usb_req, GFP_ATOMIC); + dma_fence_end_signalling(cookie); + if (!ret) { + priv->req = usb_req; + priv->ep = ep->ep; + } else { + pr_warn("FFS: Failed to queue DMABUF: %d\n", ret); + ffs_dmabuf_signal_done(fence, ret); + usb_ep_free_request(ep->ep, usb_req); + } + + spin_unlock_irq(&epfile->ffs->eps_lock); + dma_buf_put(dmabuf); + + return ret; + +err_fence_put: + spin_unlock_irq(&epfile->ffs->eps_lock); + dma_fence_put(&fence->base); +err_resv_unlock: + dma_resv_unlock(dmabuf->resv); +err_attachment_put: + ffs_dmabuf_put(attach); +err_dmabuf_put: + dma_buf_put(dmabuf); + + return ret; +} + static long ffs_epfile_ioctl(struct file *file, unsigned code, unsigned long value) { @@ -1292,6 +1719,44 @@ static long ffs_epfile_ioctl(struct file *file, unsigned code, if (WARN_ON(epfile->ffs->state != FFS_ACTIVE)) return -ENODEV; + switch (code) { + case FUNCTIONFS_DMABUF_ATTACH: + { + int fd; + + if (copy_from_user(&fd, (void __user *)value, sizeof(fd))) { + ret = -EFAULT; + break; + } + + return ffs_dmabuf_attach(file, fd); + } + case FUNCTIONFS_DMABUF_DETACH: + { + int fd; + + if (copy_from_user(&fd, (void __user *)value, sizeof(fd))) { + ret = -EFAULT; + break; + } + + return ffs_dmabuf_detach(file, fd); + } + case FUNCTIONFS_DMABUF_TRANSFER: + { + struct usb_ffs_dmabuf_transfer_req req; + + if (copy_from_user(&req, (void __user *)value, sizeof(req))) { + ret = -EFAULT; + break; + } + + return ffs_dmabuf_transfer(file, &req); + } + default: + break; + } + /* Wait for endpoint to be enabled */ ep = ffs_epfile_wait_ep(file); if (IS_ERR(ep)) @@ -1869,6 +2334,8 @@ static int ffs_epfiles_create(struct ffs_data *ffs) for (i = 1; i <= count; ++i, ++epfile) { epfile->ffs = ffs; mutex_init(&epfile->mutex); + mutex_init(&epfile->dmabufs_mutex); + INIT_LIST_HEAD(&epfile->dmabufs); if (ffs->user_flags & FUNCTIONFS_VIRTUAL_ADDR) sprintf(epfile->name, "ep%02x", ffs->eps_addrmap[i]); else diff --git a/include/uapi/linux/usb/functionfs.h b/include/uapi/linux/usb/functionfs.h index 078098e73fd3..9f88de9c3d66 100644 --- a/include/uapi/linux/usb/functionfs.h +++ b/include/uapi/linux/usb/functionfs.h @@ -86,6 +86,22 @@ struct usb_ext_prop_desc { __le16 wPropertyNameLength; } __attribute__((packed)); +/* Flags for usb_ffs_dmabuf_transfer_req->flags (none for now) */ +#define USB_FFS_DMABUF_TRANSFER_MASK 0x0 + +/** + * struct usb_ffs_dmabuf_transfer_req - Transfer request for a DMABUF object + * @fd: file descriptor of the DMABUF object + * @flags: one or more USB_FFS_DMABUF_TRANSFER_* flags + * @length: number of bytes used in this DMABUF for the data transfer. + * Should generally be set to the DMABUF's size. + */ +struct usb_ffs_dmabuf_transfer_req { + int fd; + __u32 flags; + __u64 length; +} __attribute__((packed)); + #ifndef __KERNEL__ /* @@ -290,6 +306,31 @@ struct usb_functionfs_event { #define FUNCTIONFS_ENDPOINT_DESC _IOR('g', 130, \ struct usb_endpoint_descriptor) +/* + * Attach the DMABUF object, identified by its file descriptor, to the + * data endpoint. Returns zero on success, and a negative errno value + * on error. + */ +#define FUNCTIONFS_DMABUF_ATTACH _IOW('g', 131, int) + +/* + * Detach the given DMABUF object, identified by its file descriptor, + * from the data endpoint. Returns zero on success, and a negative + * errno value on error. Note that closing the endpoint's file + * descriptor will automatically detach all attached DMABUFs. + */ +#define FUNCTIONFS_DMABUF_DETACH _IOW('g', 132, int) + +/* + * Enqueue the previously attached DMABUF to the transfer queue. + * The argument is a structure that packs the DMABUF's file descriptor, + * the size in bytes to transfer (which should generally correspond to + * the size of the DMABUF), and a 'flags' field which is unused + * for now. Returns zero on success, and a negative errno value on + * error. + */ +#define FUNCTIONFS_DMABUF_TRANSFER _IOW('g', 133, \ + struct usb_ffs_dmabuf_transfer_req) #endif /* _UAPI__LINUX_FUNCTIONFS_H__ */ -- cgit v1.2.3 From 6ec429d5887a41b2dc8d92e391552f5604085cc2 Mon Sep 17 00:00:00 2001 From: Junxian Huang Date: Fri, 1 Mar 2024 18:48:45 +0800 Subject: RDMA/hns: Support userspace configuring congestion control algorithm with QP granularity Currently, congestion control algorithm is statically configured in FW, and all QPs use the same algorithm(except UD which has a fixed configuration of DCQCN). This is not flexible enough. Support userspace configuring congestion control algorithm with QP granularity while creating QPs. If the algorithm is not specified in userspace, use the default one. Signed-off-by: Junxian Huang Link: https://lore.kernel.org/r/20240301104845.1141083-1-huangjunxian6@hisilicon.com Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/hns/hns_roce_device.h | 3 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 12 +----- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 3 +- drivers/infiniband/hw/hns/hns_roce_main.c | 3 ++ drivers/infiniband/hw/hns/hns_roce_qp.c | 60 +++++++++++++++++++++++++++++ include/uapi/rdma/hns-abi.h | 16 ++++++++ 6 files changed, 85 insertions(+), 12 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 1d062c522d69..bc015901a7d3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -845,7 +845,8 @@ struct hns_roce_caps { u16 default_aeq_period; u16 default_aeq_arm_st; u16 default_ceq_arm_st; - enum hns_roce_cong_type cong_type; + u8 cong_cap; + enum hns_roce_cong_type default_cong_type; }; enum hns_roce_device_state { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 42e28586cefa..38e426f4afb5 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2209,11 +2209,12 @@ static int hns_roce_query_caps(struct hns_roce_dev *hr_dev) caps->max_wqes = 1 << le16_to_cpu(resp_c->sq_depth); caps->num_srqs = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_SRQS); - caps->cong_type = hr_reg_read(resp_d, PF_CAPS_D_CONG_TYPE); + caps->cong_cap = hr_reg_read(resp_d, PF_CAPS_D_CONG_CAP); caps->max_srq_wrs = 1 << le16_to_cpu(resp_d->srq_depth); caps->ceqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_CEQ_DEPTH); caps->num_comp_vectors = hr_reg_read(resp_d, PF_CAPS_D_NUM_CEQS); caps->aeqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_AEQ_DEPTH); + caps->default_cong_type = hr_reg_read(resp_d, PF_CAPS_D_DEFAULT_ALG); caps->reserved_pds = hr_reg_read(resp_d, PF_CAPS_D_RSV_PDS); caps->num_uars = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_UARS); caps->reserved_qps = hr_reg_read(resp_d, PF_CAPS_D_RSV_QPS); @@ -4737,14 +4738,8 @@ enum { static int check_cong_type(struct ib_qp *ibqp, struct hns_roce_congestion_algorithm *cong_alg) { - struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device); struct hns_roce_qp *hr_qp = to_hr_qp(ibqp); - if (ibqp->qp_type == IB_QPT_UD || ibqp->qp_type == IB_QPT_GSI) - hr_qp->cong_type = CONG_TYPE_DCQCN; - else - hr_qp->cong_type = hr_dev->caps.cong_type; - /* different congestion types match different configurations */ switch (hr_qp->cong_type) { case CONG_TYPE_DCQCN: @@ -4772,9 +4767,6 @@ static int check_cong_type(struct ib_qp *ibqp, cong_alg->wnd_mode_sel = WND_LIMIT; break; default: - ibdev_warn(&hr_dev->ib_dev, - "invalid type(%u) for congestion selection.\n", - hr_qp->cong_type); hr_qp->cong_type = CONG_TYPE_DCQCN; cong_alg->alg_sel = CONG_DCQCN; cong_alg->alg_sub_sel = UNSUPPORT_CONG_LEVEL; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index cd97cbee682a..359a74672ba1 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -1214,12 +1214,13 @@ struct hns_roce_query_pf_caps_d { #define PF_CAPS_D_RQWQE_HOP_NUM PF_CAPS_D_FIELD_LOC(21, 20) #define PF_CAPS_D_EX_SGE_HOP_NUM PF_CAPS_D_FIELD_LOC(23, 22) #define PF_CAPS_D_SQWQE_HOP_NUM PF_CAPS_D_FIELD_LOC(25, 24) -#define PF_CAPS_D_CONG_TYPE PF_CAPS_D_FIELD_LOC(29, 26) +#define PF_CAPS_D_CONG_CAP PF_CAPS_D_FIELD_LOC(29, 26) #define PF_CAPS_D_CEQ_DEPTH PF_CAPS_D_FIELD_LOC(85, 64) #define PF_CAPS_D_NUM_CEQS PF_CAPS_D_FIELD_LOC(95, 86) #define PF_CAPS_D_AEQ_DEPTH PF_CAPS_D_FIELD_LOC(117, 96) #define PF_CAPS_D_AEQ_ARM_ST PF_CAPS_D_FIELD_LOC(119, 118) #define PF_CAPS_D_CEQ_ARM_ST PF_CAPS_D_FIELD_LOC(121, 120) +#define PF_CAPS_D_DEFAULT_ALG PF_CAPS_D_FIELD_LOC(127, 122) #define PF_CAPS_D_RSV_PDS PF_CAPS_D_FIELD_LOC(147, 128) #define PF_CAPS_D_NUM_UARS PF_CAPS_D_FIELD_LOC(155, 148) #define PF_CAPS_D_RSV_QPS PF_CAPS_D_FIELD_LOC(179, 160) diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index b55fe6911f9f..1dc60c2b2b7a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -394,6 +394,9 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx, resp.config |= HNS_ROCE_RSP_CQE_INLINE_FLAGS; } + if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) + resp.congest_type = hr_dev->caps.cong_cap; + ret = hns_roce_uar_alloc(hr_dev, &context->uar); if (ret) goto error_out; diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 31b147210688..f35a66325d9a 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -1004,6 +1004,60 @@ static void free_kernel_wrid(struct hns_roce_qp *hr_qp) kfree(hr_qp->sq.wrid); } +static void default_congest_type(struct hns_roce_dev *hr_dev, + struct hns_roce_qp *hr_qp) +{ + if (hr_qp->ibqp.qp_type == IB_QPT_UD || + hr_qp->ibqp.qp_type == IB_QPT_GSI) + hr_qp->cong_type = CONG_TYPE_DCQCN; + else + hr_qp->cong_type = hr_dev->caps.default_cong_type; +} + +static int set_congest_type(struct hns_roce_qp *hr_qp, + struct hns_roce_ib_create_qp *ucmd) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(hr_qp->ibqp.device); + + switch (ucmd->cong_type_flags) { + case HNS_ROCE_CREATE_QP_FLAGS_DCQCN: + hr_qp->cong_type = CONG_TYPE_DCQCN; + break; + case HNS_ROCE_CREATE_QP_FLAGS_LDCP: + hr_qp->cong_type = CONG_TYPE_LDCP; + break; + case HNS_ROCE_CREATE_QP_FLAGS_HC3: + hr_qp->cong_type = CONG_TYPE_HC3; + break; + case HNS_ROCE_CREATE_QP_FLAGS_DIP: + hr_qp->cong_type = CONG_TYPE_DIP; + break; + default: + return -EINVAL; + } + + if (!test_bit(hr_qp->cong_type, (unsigned long *)&hr_dev->caps.cong_cap)) + return -EOPNOTSUPP; + + if (hr_qp->ibqp.qp_type == IB_QPT_UD && + hr_qp->cong_type != CONG_TYPE_DCQCN) + return -EOPNOTSUPP; + + return 0; +} + +static int set_congest_param(struct hns_roce_dev *hr_dev, + struct hns_roce_qp *hr_qp, + struct hns_roce_ib_create_qp *ucmd) +{ + if (ucmd->comp_mask & HNS_ROCE_CREATE_QP_MASK_CONGEST_TYPE) + return set_congest_type(hr_qp, ucmd); + + default_congest_type(hr_dev, hr_qp); + + return 0; +} + static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, struct ib_qp_init_attr *init_attr, struct ib_udata *udata, @@ -1043,6 +1097,10 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, ibdev_err(ibdev, "failed to set user SQ size, ret = %d.\n", ret); + + ret = set_congest_param(hr_dev, hr_qp, ucmd); + if (ret) + return ret; } else { if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) hr_qp->config = HNS_ROCE_EXSGE_FLAGS; @@ -1051,6 +1109,8 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, ibdev_err(ibdev, "failed to set kernel SQ size, ret = %d.\n", ret); + + default_congest_type(hr_dev, hr_qp); } return ret; diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index c996e151081e..158670da2b2a 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -73,6 +73,17 @@ struct hns_roce_ib_create_srq_resp { __u32 cap_flags; /* Use enum hns_roce_srq_cap_flags */ }; +enum hns_roce_congest_type_flags { + HNS_ROCE_CREATE_QP_FLAGS_DCQCN, + HNS_ROCE_CREATE_QP_FLAGS_LDCP, + HNS_ROCE_CREATE_QP_FLAGS_HC3, + HNS_ROCE_CREATE_QP_FLAGS_DIP, +}; + +enum hns_roce_create_qp_comp_mask { + HNS_ROCE_CREATE_QP_MASK_CONGEST_TYPE = 1 << 0, +}; + struct hns_roce_ib_create_qp { __aligned_u64 buf_addr; __aligned_u64 db_addr; @@ -81,6 +92,9 @@ struct hns_roce_ib_create_qp { __u8 sq_no_prefetch; __u8 reserved[5]; __aligned_u64 sdb_addr; + __aligned_u64 comp_mask; /* Use enum hns_roce_create_qp_comp_mask */ + __aligned_u64 create_flags; + __aligned_u64 cong_type_flags; }; enum hns_roce_qp_cap_flags { @@ -114,6 +128,8 @@ struct hns_roce_ib_alloc_ucontext_resp { __u32 reserved; __u32 config; __u32 max_inline_data; + __u8 congest_type; + __u8 reserved0[7]; }; struct hns_roce_ib_alloc_ucontext { -- cgit v1.2.3 From 64805e4039f1687b9857034123a9ec10bb9abddd Mon Sep 17 00:00:00 2001 From: Beau Belgrave Date: Thu, 22 Feb 2024 00:18:05 +0000 Subject: tracing/user_events: Introduce multi-format events Currently user_events supports 1 event with the same name and must have the exact same format when referenced by multiple programs. This opens an opportunity for malicious or poorly thought through programs to create events that others use with different formats. Another scenario is user programs wishing to use the same event name but add more fields later when the software updates. Various versions of a program may be running side-by-side, which is prevented by the current single format requirement. Add a new register flag (USER_EVENT_REG_MULTI_FORMAT) which indicates the user program wishes to use the same user_event name, but may have several different formats of the event. When this flag is used, create the underlying tracepoint backing the user_event with a unique name per-version of the format. It's important that existing ABI users do not get this logic automatically, even if one of the multi format events matches the format. This ensures existing programs that create events and assume the tracepoint name will match exactly continue to work as expected. Add logic to only check multi-format events with other multi-format events and single-format events to only check single-format events during find. Change system name of the multi-format event tracepoint to ensure that multi-format events are isolated completely from single-format events. This prevents single-format names from conflicting with multi-format events if they end with the same suffix as the multi-format events. Add a register_name (reg_name) to the user_event struct which allows for split naming of events. We now have the name that was used to register within user_events as well as the unique name for the tracepoint. Upon registering events ensure matches based on first the reg_name, followed by the fields and format of the event. This allows for multiple events with the same registered name to have different formats. The underlying tracepoint will have a unique name in the format of {reg_name}.{unique_id}. For example, if both "test u32 value" and "test u64 value" are used with the USER_EVENT_REG_MULTI_FORMAT the system would have 2 unique tracepoints. The dynamic_events file would then show the following: u:test u64 count u:test u32 count The actual tracepoint names look like this: test.0 test.1 Both would be under the new user_events_multi system name to prevent the older ABI from being used to squat on multi-formatted events and block their use. Deleting events via "!u:test u64 count" would only delete the first tracepoint that matched that format. When the delete ABI is used all events with the same name will be attempted to be deleted. If per-version deletion is required, user programs should either not use persistent events or delete them via dynamic_events. Link: https://lore.kernel.org/linux-trace-kernel/20240222001807.1463-3-beaub@linux.microsoft.com Signed-off-by: Beau Belgrave Signed-off-by: Steven Rostedt (Google) --- include/uapi/linux/user_events.h | 6 ++- kernel/trace/trace_events_user.c | 102 ++++++++++++++++++++++++++++++++++----- 2 files changed, 95 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/user_events.h b/include/uapi/linux/user_events.h index f74f3aedd49c..a03de03dccbc 100644 --- a/include/uapi/linux/user_events.h +++ b/include/uapi/linux/user_events.h @@ -12,6 +12,7 @@ #include #define USER_EVENTS_SYSTEM "user_events" +#define USER_EVENTS_MULTI_SYSTEM "user_events_multi" #define USER_EVENTS_PREFIX "u:" /* Create dynamic location entry within a 32-bit value */ @@ -22,8 +23,11 @@ enum user_reg_flag { /* Event will not delete upon last reference closing */ USER_EVENT_REG_PERSIST = 1U << 0, + /* Event will be allowed to have multiple formats */ + USER_EVENT_REG_MULTI_FORMAT = 1U << 1, + /* This value or above is currently non-ABI */ - USER_EVENT_REG_MAX = 1U << 1, + USER_EVENT_REG_MAX = 1U << 2, }; /* diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index fce5ed5fec50..70d428c394b6 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -34,7 +34,8 @@ /* Limit how long of an event name plus args within the subsystem. */ #define MAX_EVENT_DESC 512 -#define EVENT_NAME(user_event) ((user_event)->tracepoint.name) +#define EVENT_NAME(user_event) ((user_event)->reg_name) +#define EVENT_TP_NAME(user_event) ((user_event)->tracepoint.name) #define MAX_FIELD_ARRAY_SIZE 1024 /* @@ -54,10 +55,13 @@ * allows isolation for events by various means. */ struct user_event_group { - char *system_name; - struct hlist_node node; - struct mutex reg_mutex; + char *system_name; + char *system_multi_name; + struct hlist_node node; + struct mutex reg_mutex; DECLARE_HASHTABLE(register_table, 8); + /* ID that moves forward within the group for multi-event names */ + u64 multi_id; }; /* Group for init_user_ns mapping, top-most group */ @@ -78,6 +82,7 @@ static unsigned int current_user_events; */ struct user_event { struct user_event_group *group; + char *reg_name; struct tracepoint tracepoint; struct trace_event_call call; struct trace_event_class class; @@ -127,6 +132,8 @@ struct user_event_enabler { #define ENABLE_BIT(e) ((int)((e)->values & ENABLE_VAL_BIT_MASK)) +#define EVENT_MULTI_FORMAT(f) ((f) & USER_EVENT_REG_MULTI_FORMAT) + /* Used for asynchronous faulting in of pages */ struct user_event_enabler_fault { struct work_struct work; @@ -330,6 +337,7 @@ out: static void user_event_group_destroy(struct user_event_group *group) { kfree(group->system_name); + kfree(group->system_multi_name); kfree(group); } @@ -348,6 +356,11 @@ static char *user_event_group_system_name(void) return system_name; } +static char *user_event_group_system_multi_name(void) +{ + return kstrdup(USER_EVENTS_MULTI_SYSTEM, GFP_KERNEL); +} + static struct user_event_group *current_user_event_group(void) { return init_group; @@ -367,6 +380,11 @@ static struct user_event_group *user_event_group_create(void) if (!group->system_name) goto error; + group->system_multi_name = user_event_group_system_multi_name(); + + if (!group->system_multi_name) + goto error; + mutex_init(&group->reg_mutex); hash_init(group->register_table); @@ -1482,6 +1500,11 @@ static int destroy_user_event(struct user_event *user) hash_del(&user->node); user_event_destroy_validators(user); + + /* If we have different names, both must be freed */ + if (EVENT_NAME(user) != EVENT_TP_NAME(user)) + kfree(EVENT_TP_NAME(user)); + kfree(user->call.print_fmt); kfree(EVENT_NAME(user)); kfree(user); @@ -1504,12 +1527,24 @@ static struct user_event *find_user_event(struct user_event_group *group, *outkey = key; hash_for_each_possible(group->register_table, user, node, key) { + /* + * Single-format events shouldn't return multi-format + * events. Callers expect the underlying tracepoint to match + * the name exactly in these cases. Only check like-formats. + */ + if (EVENT_MULTI_FORMAT(flags) != EVENT_MULTI_FORMAT(user->reg_flags)) + continue; + if (strcmp(EVENT_NAME(user), name)) continue; if (user_fields_match(user, argc, argv)) return user_event_get(user); + /* Scan others if this is a multi-format event */ + if (EVENT_MULTI_FORMAT(flags)) + continue; + return ERR_PTR(-EADDRINUSE); } @@ -1889,8 +1924,12 @@ static bool user_event_match(const char *system, const char *event, struct user_event *user = container_of(ev, struct user_event, devent); bool match; - match = strcmp(EVENT_NAME(user), event) == 0 && - (!system || strcmp(system, USER_EVENTS_SYSTEM) == 0); + match = strcmp(EVENT_NAME(user), event) == 0; + + if (match && system) { + match = strcmp(system, user->group->system_name) == 0 || + strcmp(system, user->group->system_multi_name) == 0; + } if (match) match = user_fields_match(user, argc, argv); @@ -1923,6 +1962,33 @@ static int user_event_trace_register(struct user_event *user) return ret; } +static int user_event_set_tp_name(struct user_event *user) +{ + lockdep_assert_held(&user->group->reg_mutex); + + if (EVENT_MULTI_FORMAT(user->reg_flags)) { + char *multi_name; + + multi_name = kasprintf(GFP_KERNEL_ACCOUNT, "%s.%llx", + user->reg_name, user->group->multi_id); + + if (!multi_name) + return -ENOMEM; + + user->call.name = multi_name; + user->tracepoint.name = multi_name; + + /* Inc to ensure unique multi-event name next time */ + user->group->multi_id++; + } else { + /* Non Multi-format uses register name */ + user->call.name = user->reg_name; + user->tracepoint.name = user->reg_name; + } + + return 0; +} + /* * Parses the event name, arguments and flags then registers if successful. * The name buffer lifetime is owned by this method for success cases only. @@ -1985,7 +2051,13 @@ static int user_event_parse(struct user_event_group *group, char *name, INIT_LIST_HEAD(&user->validators); user->group = group; - user->tracepoint.name = name; + user->reg_name = name; + user->reg_flags = reg_flags; + + ret = user_event_set_tp_name(user); + + if (ret) + goto put_user; ret = user_event_parse_fields(user, args); @@ -1999,11 +2071,14 @@ static int user_event_parse(struct user_event_group *group, char *name, user->call.data = user; user->call.class = &user->class; - user->call.name = name; user->call.flags = TRACE_EVENT_FL_TRACEPOINT; user->call.tp = &user->tracepoint; user->call.event.funcs = &user_event_funcs; - user->class.system = group->system_name; + + if (EVENT_MULTI_FORMAT(user->reg_flags)) + user->class.system = group->system_multi_name; + else + user->class.system = group->system_name; user->class.fields_array = user_event_fields_array; user->class.get_fields = user_event_get_fields; @@ -2025,8 +2100,6 @@ static int user_event_parse(struct user_event_group *group, char *name, if (ret) goto put_user_lock; - user->reg_flags = reg_flags; - if (user->reg_flags & USER_EVENT_REG_PERSIST) { /* Ensure we track self ref and caller ref (2) */ refcount_set(&user->refcnt, 2); @@ -2050,6 +2123,11 @@ put_user: user_event_destroy_fields(user); user_event_destroy_validators(user); kfree(user->call.print_fmt); + + /* Caller frees reg_name on error, but not multi-name */ + if (EVENT_NAME(user) != EVENT_TP_NAME(user)) + kfree(EVENT_TP_NAME(user)); + kfree(user); return ret; } @@ -2639,7 +2717,7 @@ static int user_seq_show(struct seq_file *m, void *p) hash_for_each(group->register_table, i, user, node) { status = user->status; - seq_printf(m, "%s", EVENT_NAME(user)); + seq_printf(m, "%s", EVENT_TP_NAME(user)); if (status != 0) seq_puts(m, " #"); -- cgit v1.2.3 From ec6ecb844d14d38b7dae8beb74e3d65db9c7b3e6 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Jan 2024 23:20:39 +0000 Subject: virtio: uapi: Drop __packed attribute in linux/virtio_pci.h Commit 92792ac752aa ("virtio-pci: Introduce admin command sending function") added "__packed" structures to UAPI header linux/virtio_pci.h. This triggers build failures in the consumer userspace applications without proper "definition" of __packed (e.g., kvmtool build fails). Moreover, the structures are already packed well, and doesn't need explicit packing, similar to the rest of the structures in all virtio_* headers. Remove the __packed attribute. Fixes: 92792ac752aa ("virtio-pci: Introduce admin command sending function") Cc: Feng Liu Cc: Michael S. Tsirkin Cc: Yishai Hadas Cc: Alex Williamson Cc: Jean-Philippe Brucker Reviewed-by: Jean-Philippe Brucker Acked-by: Michael S. Tsirkin Signed-off-by: Suzuki K Poulose Message-Id: <20240125232039.913606-1-suzuki.poulose@arm.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/virtio_pci.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index ef3810dee7ef..a8208492e822 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -240,7 +240,7 @@ struct virtio_pci_cfg_cap { #define VIRTIO_ADMIN_CMD_LEGACY_DEV_CFG_READ 0x5 #define VIRTIO_ADMIN_CMD_LEGACY_NOTIFY_INFO 0x6 -struct __packed virtio_admin_cmd_hdr { +struct virtio_admin_cmd_hdr { __le16 opcode; /* * 1 - SR-IOV @@ -252,20 +252,20 @@ struct __packed virtio_admin_cmd_hdr { __le64 group_member_id; }; -struct __packed virtio_admin_cmd_status { +struct virtio_admin_cmd_status { __le16 status; __le16 status_qualifier; /* Unused, reserved for future extensions. */ __u8 reserved2[4]; }; -struct __packed virtio_admin_cmd_legacy_wr_data { +struct virtio_admin_cmd_legacy_wr_data { __u8 offset; /* Starting offset of the register(s) to write. */ __u8 reserved[7]; __u8 registers[]; }; -struct __packed virtio_admin_cmd_legacy_rd_data { +struct virtio_admin_cmd_legacy_rd_data { __u8 offset; /* Starting offset of the register(s) to read. */ }; @@ -275,7 +275,7 @@ struct __packed virtio_admin_cmd_legacy_rd_data { #define VIRTIO_ADMIN_CMD_MAX_NOTIFY_INFO 4 -struct __packed virtio_admin_cmd_notify_info_data { +struct virtio_admin_cmd_notify_info_data { __u8 flags; /* 0 = end of list, 1 = owner device, 2 = member device */ __u8 bar; /* BAR of the member or the owner device */ __u8 padding[6]; -- cgit v1.2.3 From 1496c47065f9f8413296780c63374daee9bdae20 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Sat, 3 Feb 2024 00:38:56 +0800 Subject: vhost-vdpa: uapi to support reporting per vq size The size of a virtqueue is a per vq configuration. This commit introduce a new ioctl uAPI to support this flexibility. Signed-off-by: Zhu Lingshan Message-Id: <20240202163905.8834-2-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- include/uapi/linux/vhost.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index 649560c685f1..bea697390613 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -227,4 +227,11 @@ */ #define VHOST_VDPA_GET_VRING_DESC_GROUP _IOWR(VHOST_VIRTIO, 0x7F, \ struct vhost_vring_state) + +/* Get the queue size of a specific virtqueue. + * userspace set the vring index in vhost_vring_state.index + * kernel set the queue size in vhost_vring_state.num + */ +#define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x80, \ + struct vhost_vring_state) #endif -- cgit v1.2.3 From c2475a9a789721bfdcc1b16aaf61ccfecb891914 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:55:57 +0800 Subject: vDPA: report virtio-block capacity to user space This commit allows userspace to query capacity of a virtio-block device. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-2-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 35 +++++++++++++++++++++++++++++++++++ include/linux/vdpa.h | 1 + include/uapi/linux/vdpa.h | 2 ++ 3 files changed, 38 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index c73c06102e7e..613bec31f59e 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -944,6 +944,38 @@ static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *ms return vdpa_dev_net_mq_config_fill(msg, features_device, &config); } +static int +vdpa_dev_blk_capacity_config_fill(struct sk_buff *msg, + const struct virtio_blk_config *config) +{ + u64 val_u64; + + val_u64 = __virtio64_to_cpu(true, config->capacity); + + return nla_put_u64_64bit(msg, VDPA_ATTR_DEV_BLK_CFG_CAPACITY, + val_u64, VDPA_ATTR_PAD); +} + +static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, + struct sk_buff *msg) +{ + struct virtio_blk_config config = {}; + u64 features_device; + + vdev->config->get_config(vdev, 0, &config, sizeof(config)); + + features_device = vdev->config->get_device_features(vdev); + + if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_FEATURES, features_device, + VDPA_ATTR_PAD)) + return -EMSGSIZE; + + if (vdpa_dev_blk_capacity_config_fill(msg, &config)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, int flags, struct netlink_ext_ack *extack) @@ -988,6 +1020,9 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, case VIRTIO_ID_NET: err = vdpa_dev_net_config_fill(vdev, msg); break; + case VIRTIO_ID_BLOCK: + err = vdpa_dev_blk_config_fill(vdev, msg); + break; default: err = -EOPNOTSUPP; break; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 4097e8e92860..7977ca03ac7a 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -7,6 +7,7 @@ #include #include #include +#include #include /** diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 54b649ab0f22..1bf69226cb96 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -56,6 +56,8 @@ enum vdpa_attr { /* virtio features that are provisioned to the vDPA device */ VDPA_ATTR_DEV_FEATURES, /* u64 */ + VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From 330b8aea692410fbe8f0d058e01aea2986613ff7 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:55:58 +0800 Subject: vDPA: report virtio-block max segment size to user space This commit allows reporting the max size of any single segment of virtio-block devices to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-3-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 17 +++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 18 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 613bec31f59e..db355d4683ba 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -956,6 +956,20 @@ vdpa_dev_blk_capacity_config_fill(struct sk_buff *msg, val_u64, VDPA_ATTR_PAD); } +static int +vdpa_dev_blk_seg_size_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_SIZE_MAX)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->size_max); + + return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, val_u32); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -973,6 +987,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_capacity_config_fill(msg, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_seg_size_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 1bf69226cb96..586bce3c906a 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -57,6 +57,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_FEATURES, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ + VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 3a1d33fb7e5f96471aa7bfe97dd09afc2aa03b39 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:55:59 +0800 Subject: vDPA: report virtio-block block-size to user space This commit allows reporting the block size of a virtio-block device to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-4-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 18 ++++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 19 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index db355d4683ba..d96dc2ad48aa 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -970,6 +970,21 @@ vdpa_dev_blk_seg_size_config_fill(struct sk_buff *msg, u64 features, return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, val_u32); } +/* fill the block size*/ +static int +vdpa_dev_blk_block_size_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_BLK_SIZE)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->blk_size); + + return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, val_u32); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -990,6 +1005,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_seg_size_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_block_size_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 586bce3c906a..f3baf7ea7d6d 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -58,6 +58,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 81f64e1d911550832b8065631c28c87c96ffca36 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:00 +0800 Subject: vDPA: report virtio-block max segments in a request to user space This commit allows vDPA reporting the maximum number of segments in a request of virtio-block devices to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-5-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 17 +++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 18 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index d96dc2ad48aa..3e3c84bd0337 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -985,6 +985,20 @@ vdpa_dev_blk_block_size_config_fill(struct sk_buff *msg, u64 features, return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, val_u32); } +static int +vdpa_dev_blk_seg_max_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_SEG_MAX)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->seg_max); + + return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, val_u32); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1008,6 +1022,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_block_size_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_seg_max_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index f3baf7ea7d6d..2dc92fca2052 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -59,6 +59,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_CAPACITY, /* u64 */ VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 54fb04b02efd8f56e388443d5f9e03e68eef48e6 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:01 +0800 Subject: vDPA: report virtio-block MQ info to user space This commits allows vDPA reporting virtio-block multi-queue configuration to user sapce. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-6-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 16 ++++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 3e3c84bd0337..4c348da1f2f7 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -999,6 +999,19 @@ vdpa_dev_blk_seg_max_config_fill(struct sk_buff *msg, u64 features, return nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, val_u32); } +static int vdpa_dev_blk_mq_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u16 val_u16; + + if ((features & BIT_ULL(VIRTIO_BLK_F_MQ)) == 0) + return 0; + + val_u16 = __virtio16_to_cpu(true, config->num_queues); + + return nla_put_u16(msg, VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, val_u16); +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1025,6 +1038,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_seg_max_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_mq_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 2dc92fca2052..3c8e3c87a864 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -60,6 +60,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_SEG_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, /* u16 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From c9d989b4ababe3ec7291b204f365eaadec0afa26 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:02 +0800 Subject: vDPA: report virtio-block topology info to user space This commit allows vDPA reporting topology information of virtio-blk devices to user space, includes: 1) the number of logical blocks per physical block 2) offset of first aligned logical block 3) suggested minimum I/O size in blocks 4) optimal (suggested maximum) I/O size in blocks Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-7-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 32 ++++++++++++++++++++++++++++++++ include/uapi/linux/vdpa.h | 4 ++++ 2 files changed, 36 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 4c348da1f2f7..76b2e31d6229 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1012,6 +1012,35 @@ static int vdpa_dev_blk_mq_config_fill(struct sk_buff *msg, u64 features, return nla_put_u16(msg, VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, val_u16); } +static int vdpa_dev_blk_topology_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u16 min_io_size; + u32 opt_io_size; + + if ((features & BIT_ULL(VIRTIO_BLK_F_TOPOLOGY)) == 0) + return 0; + + min_io_size = __virtio16_to_cpu(true, config->min_io_size); + opt_io_size = __virtio32_to_cpu(true, config->opt_io_size); + + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_PHY_BLK_EXP, + config->physical_block_exp)) + return -EMSGSIZE; + + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_ALIGN_OFFSET, + config->alignment_offset)) + return -EMSGSIZE; + + if (nla_put_u16(msg, VDPA_ATTR_DEV_BLK_CFG_MIN_IO_SIZE, min_io_size)) + return -EMSGSIZE; + + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_OPT_IO_SIZE, opt_io_size)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1041,6 +1070,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_mq_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_topology_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 3c8e3c87a864..5cc70614c97a 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -61,6 +61,10 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_BLK_SIZE, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_SEG_MAX, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_NUM_QUEUES, /* u16 */ + VDPA_ATTR_DEV_BLK_CFG_PHY_BLK_EXP, /* u8 */ + VDPA_ATTR_DEV_BLK_CFG_ALIGN_OFFSET, /* u8 */ + VDPA_ATTR_DEV_BLK_CFG_MIN_IO_SIZE, /* u16 */ + VDPA_ATTR_DEV_BLK_CFG_OPT_IO_SIZE, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 65848f46e1d6c01fbd0d79a1c051d978a6e6002e Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:03 +0800 Subject: vDPA: report virtio-block discarding configuration to user space This commit reports virtio-blk discarding configuration to user space,includes: 1) the maximum discard sectors 2) maximum number of discard segments for the block driver to use 3) the alignment for splitting a discarding request Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-8-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 26 ++++++++++++++++++++++++++ include/uapi/linux/vdpa.h | 3 +++ 2 files changed, 29 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 76b2e31d6229..9348818b8bf9 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1041,6 +1041,29 @@ static int vdpa_dev_blk_topology_config_fill(struct sk_buff *msg, u64 features, return 0; } +static int vdpa_dev_blk_discard_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_DISCARD)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->max_discard_sectors); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEC, val_u32)) + return -EMSGSIZE; + + val_u32 = __virtio32_to_cpu(true, config->max_discard_seg); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEG, val_u32)) + return -EMSGSIZE; + + val_u32 = __virtio32_to_cpu(true, config->discard_sector_alignment); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN, val_u32)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1073,6 +1096,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_topology_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_discard_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 5cc70614c97a..30887931a220 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -65,6 +65,9 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_ALIGN_OFFSET, /* u8 */ VDPA_ATTR_DEV_BLK_CFG_MIN_IO_SIZE, /* u16 */ VDPA_ATTR_DEV_BLK_CFG_OPT_IO_SIZE, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEC, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEG, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 6bdc7846e627ec21fc79a6d2554f69546a7b4985 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:04 +0800 Subject: vDPA: report virtio-block write zeroes configuration to user space This commits reports write zeroes configuration of virtio-block devices to user space, includes: 1)maximum write zeroes sectors size 2)maximum write zeroes segment number Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-9-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 23 +++++++++++++++++++++++ include/uapi/linux/vdpa.h | 2 ++ 2 files changed, 25 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 9348818b8bf9..bcea9f880042 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1064,6 +1064,26 @@ static int vdpa_dev_blk_discard_config_fill(struct sk_buff *msg, u64 features, return 0; } +static int +vdpa_dev_blk_write_zeroes_config_fill(struct sk_buff *msg, u64 features, + const struct virtio_blk_config *config) +{ + u32 val_u32; + + if ((features & BIT_ULL(VIRTIO_BLK_F_WRITE_ZEROES)) == 0) + return 0; + + val_u32 = __virtio32_to_cpu(true, config->max_write_zeroes_sectors); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, val_u32)) + return -EMSGSIZE; + + val_u32 = __virtio32_to_cpu(true, config->max_write_zeroes_seg); + if (nla_put_u32(msg, VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, val_u32)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1099,6 +1119,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_discard_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_write_zeroes_config_fill(msg, features_device, &config)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 30887931a220..797d5708492f 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -68,6 +68,8 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_DISCARD_SEG, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From ae1374b7f72c973631ce881a654664fd2b40c4b9 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:05 +0800 Subject: vDPA: report virtio-block read-only info to user space This commit report read-only information of virtio-blk devices to user space. Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-10-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 14 ++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index bcea9f880042..2d02ea60af0c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1084,6 +1084,17 @@ vdpa_dev_blk_write_zeroes_config_fill(struct sk_buff *msg, u64 features, return 0; } +static int vdpa_dev_blk_ro_config_fill(struct sk_buff *msg, u64 features) +{ + u8 ro; + + ro = ((features & BIT_ULL(VIRTIO_BLK_F_RO)) == 0) ? 0 : 1; + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, ro)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1122,6 +1133,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_write_zeroes_config_fill(msg, features_device, &config)) return -EMSGSIZE; + if (vdpa_dev_blk_ro_config_fill(msg, features_device)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 797d5708492f..4be8e3a15874 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -70,6 +70,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_DISCARD_SEC_ALIGN,/* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ + VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, /* u8 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 1ac61ddfee93278f87370f6c43ed669b845f9037 Mon Sep 17 00:00:00 2001 From: Zhu Lingshan Date: Mon, 19 Feb 2024 02:56:06 +0800 Subject: vDPA: report virtio-blk flush info to user space This commit reports whether a virtio-blk device support cache flush command to user space Signed-off-by: Zhu Lingshan Message-Id: <20240218185606.13509-11-lingshan.zhu@intel.com> Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 14 ++++++++++++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 15 insertions(+) (limited to 'include/uapi') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 2d02ea60af0c..b246067e074b 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1095,6 +1095,17 @@ static int vdpa_dev_blk_ro_config_fill(struct sk_buff *msg, u64 features) return 0; } +static int vdpa_dev_blk_flush_config_fill(struct sk_buff *msg, u64 features) +{ + u8 flush; + + flush = ((features & BIT_ULL(VIRTIO_BLK_F_FLUSH)) == 0) ? 0 : 1; + if (nla_put_u8(msg, VDPA_ATTR_DEV_BLK_CFG_FLUSH, flush)) + return -EMSGSIZE; + + return 0; +} + static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) { @@ -1136,6 +1147,9 @@ static int vdpa_dev_blk_config_fill(struct vdpa_device *vdev, if (vdpa_dev_blk_ro_config_fill(msg, features_device)) return -EMSGSIZE; + if (vdpa_dev_blk_flush_config_fill(msg, features_device)) + return -EMSGSIZE; + return 0; } diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 4be8e3a15874..43c51698195c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -71,6 +71,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEC, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_MAX_WRITE_ZEROES_SEG, /* u32 */ VDPA_ATTR_DEV_BLK_CFG_READ_ONLY, /* u8 */ + VDPA_ATTR_DEV_BLK_CFG_FLUSH, /* u8 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From 429846b4b6ce9853e0d803a2357bb2e55083adf0 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Sat, 23 Mar 2024 17:41:55 +0900 Subject: scsi: mpi3mr: Avoid memcpy field-spanning write WARNING When the "storcli2 show" command is executed for eHBA-9600, mpi3mr driver prints this WARNING message: memcpy: detected field-spanning write (size 128) of single field "bsg_reply_buf->reply_buf" at drivers/scsi/mpi3mr/mpi3mr_app.c:1658 (size 1) WARNING: CPU: 0 PID: 12760 at drivers/scsi/mpi3mr/mpi3mr_app.c:1658 mpi3mr_bsg_request+0x6b12/0x7f10 [mpi3mr] The cause of the WARN is 128 bytes memcpy to the 1 byte size array "__u8 replay_buf[1]" in the struct mpi3mr_bsg_in_reply_buf. The array is intended to be a flexible length array, so the WARN is a false positive. To suppress the WARN, remove the constant number '1' from the array declaration and clarify that it has flexible length. Also, adjust the memory allocation size to match the change. Suggested-by: Sathya Prakash Veerichetty Signed-off-by: Shin'ichiro Kawasaki Link: https://lore.kernel.org/r/20240323084155.166835-1-shinichiro.kawasaki@wdc.com Signed-off-by: Martin K. Petersen --- drivers/scsi/mpi3mr/mpi3mr_app.c | 2 +- include/uapi/scsi/scsi_bsg_mpi3mr.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/scsi/mpi3mr/mpi3mr_app.c b/drivers/scsi/mpi3mr/mpi3mr_app.c index 0380996b5ad2..55d590b91947 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_app.c +++ b/drivers/scsi/mpi3mr/mpi3mr_app.c @@ -1644,7 +1644,7 @@ static long mpi3mr_bsg_process_mpt_cmds(struct bsg_job *job) if ((mpirep_offset != 0xFF) && drv_bufs[mpirep_offset].bsg_buf_len) { drv_buf_iter = &drv_bufs[mpirep_offset]; - drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) - 1 + + drv_buf_iter->kern_buf_len = (sizeof(*bsg_reply_buf) + mrioc->reply_sz); bsg_reply_buf = kzalloc(drv_buf_iter->kern_buf_len, GFP_KERNEL); diff --git a/include/uapi/scsi/scsi_bsg_mpi3mr.h b/include/uapi/scsi/scsi_bsg_mpi3mr.h index c72ce387286a..30a5c1a59376 100644 --- a/include/uapi/scsi/scsi_bsg_mpi3mr.h +++ b/include/uapi/scsi/scsi_bsg_mpi3mr.h @@ -382,7 +382,7 @@ struct mpi3mr_bsg_in_reply_buf { __u8 mpi_reply_type; __u8 rsvd1; __u16 rsvd2; - __u8 reply_buf[1]; + __u8 reply_buf[]; }; /** -- cgit v1.2.3 From 0cac183b98d8a8c692c98e8dba37df15a9e9210d Mon Sep 17 00:00:00 2001 From: Jonathan Kim Date: Fri, 1 Mar 2024 12:25:17 -0500 Subject: drm/amdkfd: range check cp bad op exception interrupts Due to a CP interrupt bug, bad packet garbage exception codes are raised. Do a range check so that the debugger and runtime do not receive garbage codes. Update the user api to guard exception code type checking as well. Signed-off-by: Jonathan Kim Tested-by: Jesse Zhang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c | 3 ++- drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c | 3 ++- drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c | 3 ++- include/uapi/linux/kfd_ioctl.h | 17 ++++++++++++++--- 4 files changed, 20 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c index 9a06c6fb6605..40a21be6c07c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v10.c @@ -339,7 +339,8 @@ static void event_interrupt_wq_v10(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, context_id0 & 0x7fffff, 23); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c index 7e2859736a55..fe2ad0c0de95 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c @@ -328,7 +328,8 @@ static void event_interrupt_wq_v11(struct kfd_node *dev, /* CP */ if (source_id == SOC15_INTSRC_CP_END_OF_PIPE) kfd_signal_event_interrupt(pasid, context_id0, 32); - else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) + else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0))) kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_CTXID0_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c index 91dd5e045b51..c4c6a29052ac 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c @@ -388,7 +388,8 @@ static void event_interrupt_wq_v9(struct kfd_node *dev, break; } kfd_signal_event_interrupt(pasid, sq_int_data, 24); - } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE) { + } else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE && + KFD_DBG_EC_TYPE_IS_PACKET(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0))) { kfd_set_dbg_ev_from_interrupt(dev, pasid, KFD_DEBUG_DOORBELL_ID(context_id0), KFD_EC_MASK(KFD_DEBUG_CP_BAD_OP_ECODE(context_id0)), diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h index 9ce46edc62a5..2040a470ddb4 100644 --- a/include/uapi/linux/kfd_ioctl.h +++ b/include/uapi/linux/kfd_ioctl.h @@ -913,14 +913,25 @@ enum kfd_dbg_trap_exception_code { KFD_EC_MASK(EC_DEVICE_NEW)) #define KFD_EC_MASK_PROCESS (KFD_EC_MASK(EC_PROCESS_RUNTIME) | \ KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE)) +#define KFD_EC_MASK_PACKET (KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) | \ + KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED)) /* Checks for exception code types for KFD search */ +#define KFD_DBG_EC_IS_VALID(ecode) (ecode > EC_NONE && ecode < EC_MAX) #define KFD_DBG_EC_TYPE_IS_QUEUE(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE)) #define KFD_DBG_EC_TYPE_IS_DEVICE(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE)) #define KFD_DBG_EC_TYPE_IS_PROCESS(ecode) \ - (!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS)) +#define KFD_DBG_EC_TYPE_IS_PACKET(ecode) \ + (KFD_DBG_EC_IS_VALID(ecode) && !!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PACKET)) /* Runtime enable states */ -- cgit v1.2.3