From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 16965733773781018.2780887200433; Thu, 5 Oct 2023 23:22:57 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCN-00058Y-My; Fri, 06 Oct 2023 02:20:31 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCJ-00056I-PY for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:29 -0400 Received: from mail.ozlabs.org ([2404:9400:2221:ea00::3] helo=gandalf.ozlabs.org) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCF-0002eR-C8 for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:27 -0400 Received: from gandalf.ozlabs.org (gandalf.ozlabs.org [150.107.74.76]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1yvw5SHnz4xPy; Fri, 6 Oct 2023 17:20:12 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yvv3FY2z4xGP; Fri, 6 Oct 2023 17:20:11 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 01/21] vfio/display: Fix missing update to set backing fields Date: Fri, 6 Oct 2023 08:19:45 +0200 Message-ID: <20231006062005.1040296-2-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2404:9400:2221:ea00::3; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -39 X-Spam_score: -4.0 X-Spam_bar: ---- X-Spam_report: (-4.0 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, RCVD_IN_DNSWL_MED=-2.3, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573378812100007 From: Alex Williamson The below referenced commit renames scanout_width/height to backing_width/height, but also promotes these fields in various portions of the egl interface. Meanwhile vfio dmabuf support has never used the previous scanout fields and is therefore missed in the update. This results in a black screen when transitioning from ramfb to dmabuf display when using Intel vGPU with these features. Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1891 Link: https://lists.gnu.org/archive/html/qemu-devel/2023-08/msg02726.html Fixes: 9ac06df8b684 ("virtio-gpu-udmabuf: correct naming of QemuDmaBuf size= properties") Signed-off-by: Alex Williamson Tested-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/display.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/vfio/display.c b/hw/vfio/display.c index bec864f482f46866bf292a5a63c31753a7c84eef..837d9e6a309e834601c125e36fa= adf81c1c5172e 100644 --- a/hw/vfio/display.c +++ b/hw/vfio/display.c @@ -243,6 +243,8 @@ static VFIODMABuf *vfio_display_get_dmabuf(VFIOPCIDevic= e *vdev, dmabuf->dmabuf_id =3D plane.dmabuf_id; dmabuf->buf.width =3D plane.width; dmabuf->buf.height =3D plane.height; + dmabuf->buf.backing_width =3D plane.width; + dmabuf->buf.backing_height =3D plane.height; dmabuf->buf.stride =3D plane.stride; dmabuf->buf.fourcc =3D plane.drm_format; dmabuf->buf.modifier =3D plane.drm_format_mod; --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573539436774.9194775428776; Thu, 5 Oct 2023 23:25:39 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCM-000573-Od; Fri, 06 Oct 2023 02:20:30 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCJ-000565-HU for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:27 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCF-0002ei-Bw for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:27 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1yvz2FvDz4xQ1; Fri, 6 Oct 2023 17:20:15 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yvx23MWz4xGP; Fri, 6 Oct 2023 17:20:13 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 02/21] vfio/pci: rename vfio_put_device to vfio_pci_put_device Date: Fri, 6 Oct 2023 08:19:46 +0200 Message-ID: <20231006062005.1040296-3-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573541451100003 From: Zhenzhong Duan vfio_put_device() is a VFIO PCI specific function, rename it with 'vfio_pci' prefix to avoid confusing. No functional change. Suggested-by: C=C3=A9dric Le Goater Signed-off-by: Zhenzhong Duan Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 3b2ca3c24ca2ed91c03b5c6bef65bb5a0fb0298a..b2d5010b9f0effbe85a3f57b43e= 282e837b6383f 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2826,7 +2826,7 @@ static void vfio_populate_device(VFIOPCIDevice *vdev,= Error **errp) } } =20 -static void vfio_put_device(VFIOPCIDevice *vdev) +static void vfio_pci_put_device(VFIOPCIDevice *vdev) { g_free(vdev->vbasedev.name); g_free(vdev->msix); @@ -3317,7 +3317,7 @@ static void vfio_instance_finalize(Object *obj) * * g_free(vdev->igd_opregion); */ - vfio_put_device(vdev); + vfio_pci_put_device(vdev); vfio_put_group(group); } =20 --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573370372854.4550404614752; Thu, 5 Oct 2023 23:22:50 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCP-00059P-0h; Fri, 06 Oct 2023 02:20:33 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCK-00056M-AV for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:29 -0400 Received: from mail.ozlabs.org ([2404:9400:2221:ea00::3] helo=gandalf.ozlabs.org) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCF-0002gc-C6 for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:28 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1yw14hDMz4xQ3; Fri, 6 Oct 2023 17:20:17 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yvz5qLKz4xGP; Fri, 6 Oct 2023 17:20:15 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Jing Liu , Reinette Chatre , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 03/21] vfio/pci: detect the support of dynamic MSI-X allocation Date: Fri, 6 Oct 2023 08:19:47 +0200 Message-ID: <20231006062005.1040296-4-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2404:9400:2221:ea00::3; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -39 X-Spam_score: -4.0 X-Spam_bar: ---- X-Spam_report: (-4.0 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, RCVD_IN_DNSWL_MED=-2.3, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573370713100001 From: Jing Liu Kernel provides the guidance of dynamic MSI-X allocation support of passthrough device, by clearing the VFIO_IRQ_INFO_NORESIZE flag to guide user space. Fetch the flags from host to determine if dynamic MSI-X allocation is supported. Originally-by: Reinette Chatre Signed-off-by: Jing Liu Reviewed-by: C=C3=A9dric Le Goater Reviewed-by: Alex Williamson Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/pci.h | 1 + hw/vfio/pci.c | 16 ++++++++++++++-- hw/vfio/trace-events | 2 +- 3 files changed, 16 insertions(+), 3 deletions(-) diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index 2d836093a83d3df5f94dc8981ee6c61cfb6d3373..0d89eb761ece426ca1df40f6346= 1b2bb1bcf1ab0 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -113,6 +113,7 @@ typedef struct VFIOMSIXInfo { uint32_t table_offset; uint32_t pba_offset; unsigned long *pending; + bool noresize; } VFIOMSIXInfo; =20 #define TYPE_VFIO_PCI "vfio-pci" diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index b2d5010b9f0effbe85a3f57b43e282e837b6383f..86c92c51a46e2d1e9856c3cbcd7= c47548daab422 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -1493,7 +1493,9 @@ static void vfio_msix_early_setup(VFIOPCIDevice *vdev= , Error **errp) uint8_t pos; uint16_t ctrl; uint32_t table, pba; - int fd =3D vdev->vbasedev.fd; + int ret, fd =3D vdev->vbasedev.fd; + struct vfio_irq_info irq_info =3D { .argsz =3D sizeof(irq_info), + .index =3D VFIO_PCI_MSIX_IRQ_INDEX }; VFIOMSIXInfo *msix; =20 pos =3D pci_find_capability(&vdev->pdev, PCI_CAP_ID_MSIX); @@ -1530,6 +1532,15 @@ static void vfio_msix_early_setup(VFIOPCIDevice *vde= v, Error **errp) msix->pba_offset =3D pba & ~PCI_MSIX_FLAGS_BIRMASK; msix->entries =3D (ctrl & PCI_MSIX_FLAGS_QSIZE) + 1; =20 + ret =3D ioctl(vdev->vbasedev.fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info); + if (ret < 0) { + error_setg_errno(errp, -ret, "failed to get MSI-X irq info"); + g_free(msix); + return; + } + + msix->noresize =3D !!(irq_info.flags & VFIO_IRQ_INFO_NORESIZE); + /* * Test the size of the pba_offset variable and catch if it extends ou= tside * of the specified BAR. If it is the case, we need to apply a hardware @@ -1562,7 +1573,8 @@ static void vfio_msix_early_setup(VFIOPCIDevice *vdev= , Error **errp) } =20 trace_vfio_msix_early_setup(vdev->vbasedev.name, pos, msix->table_bar, - msix->table_offset, msix->entries); + msix->table_offset, msix->entries, + msix->noresize); vdev->msix =3D msix; =20 vfio_pci_fixup_msix_region(vdev); diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index e64ca4a01961b34dc4b9b7d78917f1d8847d887d..0ba3c5a0e26bc82f40a0d7737e6= 8128d2c9334fe 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -27,7 +27,7 @@ vfio_vga_read(uint64_t addr, int size, uint64_t data) " (= 0x%"PRIx64", %d) =3D 0x%" vfio_pci_read_config(const char *name, int addr, int len, int val) " (%s, = @0x%x, len=3D0x%x) 0x%x" vfio_pci_write_config(const char *name, int addr, int val, int len) " (%s,= @0x%x, 0x%x, len=3D0x%x)" vfio_msi_setup(const char *name, int pos) "%s PCI MSI CAP @0x%x" -vfio_msix_early_setup(const char *name, int pos, int table_bar, int offset= , int entries) "%s PCI MSI-X CAP @0x%x, BAR %d, offset 0x%x, entries %d" +vfio_msix_early_setup(const char *name, int pos, int table_bar, int offset= , int entries, bool noresize) "%s PCI MSI-X CAP @0x%x, BAR %d, offset 0x%x,= entries %d, noresize %d" vfio_check_pcie_flr(const char *name) "%s Supports FLR via PCIe cap" vfio_check_pm_reset(const char *name) "%s Supports PM reset" vfio_check_af_flr(const char *name) "%s Supports FLR via AF cap" --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 169657328913177.11418667094927; Thu, 5 Oct 2023 23:21:29 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCM-00057B-SV; Fri, 06 Oct 2023 02:20:30 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCJ-00056H-Ot for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:29 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCF-0002hU-C9 for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:27 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1yw375dKz4xQT; Fri, 6 Oct 2023 17:20:19 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yw21Bgrz4xQM; Fri, 6 Oct 2023 17:20:17 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Jing Liu , Reinette Chatre , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 04/21] vfio/pci: enable vector on dynamic MSI-X allocation Date: Fri, 6 Oct 2023 08:19:48 +0200 Message-ID: <20231006062005.1040296-5-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573290159100007 From: Jing Liu The vector_use callback is used to enable vector that is unmasked in guest. The kernel used to only support static MSI-X allocation. When allocating a new interrupt using "static MSI-X allocation" kernels, QEMU first disables all previously allocated vectors and then re-allocates all including the new one. The nr_vectors of VFIOPCIDevice indicates that all vectors from 0 to nr_vectors are allocated (and may be enabled), which is used to loop all the possibly used vectors when e.g., disabling MSI-X interrupts. Extend the vector_use function to support dynamic MSI-X allocation when host supports the capability. QEMU therefore can individually allocate and enable a new interrupt without affecting others or causing interrupts lost during runtime. Utilize nr_vectors to calculate the upper bound of enabled vectors in dynamic MSI-X allocation mode since looping all msix_entries_nr is not efficient and unnecessary. Signed-off-by: Jing Liu Tested-by: Reinette Chatre Reviewed-by: Alex Williamson Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/pci.c | 46 ++++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 86c92c51a46e2d1e9856c3cbcd7c47548daab422..eb7627c5f9fcd67f346595ebe73= 011cc3205b58e 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -470,6 +470,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, uns= igned int nr, VFIOPCIDevice *vdev =3D VFIO_PCI(pdev); VFIOMSIVector *vector; int ret; + bool resizing =3D !!(vdev->nr_vectors < nr + 1); =20 trace_vfio_msix_vector_do_use(vdev->vbasedev.name, nr); =20 @@ -512,33 +513,42 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, u= nsigned int nr, } =20 /* - * We don't want to have the host allocate all possible MSI vectors - * for a device if they're not in use, so we shutdown and incrementally - * increase them as needed. + * When dynamic allocation is not supported, we don't want to have the + * host allocate all possible MSI vectors for a device if they're not + * in use, so we shutdown and incrementally increase them as needed. + * nr_vectors represents the total number of vectors allocated. + * + * When dynamic allocation is supported, let the host only allocate + * and enable a vector when it is in use in guest. nr_vectors represen= ts + * the upper bound of vectors being enabled (but not all of the ranges + * is allocated or enabled). */ - if (vdev->nr_vectors < nr + 1) { + if (resizing) { vdev->nr_vectors =3D nr + 1; - if (!vdev->defer_kvm_irq_routing) { + } + + if (!vdev->defer_kvm_irq_routing) { + if (vdev->msix->noresize && resizing) { vfio_disable_irqindex(&vdev->vbasedev, VFIO_PCI_MSIX_IRQ_INDEX= ); ret =3D vfio_enable_vectors(vdev, true); if (ret) { error_report("vfio: failed to enable vectors, %d", ret); } - } - } else { - Error *err =3D NULL; - int32_t fd; - - if (vector->virq >=3D 0) { - fd =3D event_notifier_get_fd(&vector->kvm_interrupt); } else { - fd =3D event_notifier_get_fd(&vector->interrupt); - } + Error *err =3D NULL; + int32_t fd; =20 - if (vfio_set_irq_signaling(&vdev->vbasedev, - VFIO_PCI_MSIX_IRQ_INDEX, nr, - VFIO_IRQ_SET_ACTION_TRIGGER, fd, &err= )) { - error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name); + if (vector->virq >=3D 0) { + fd =3D event_notifier_get_fd(&vector->kvm_interrupt); + } else { + fd =3D event_notifier_get_fd(&vector->interrupt); + } + + if (vfio_set_irq_signaling(&vdev->vbasedev, + VFIO_PCI_MSIX_IRQ_INDEX, nr, + VFIO_IRQ_SET_ACTION_TRIGGER, fd, &e= rr)) { + error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.nam= e); + } } } =20 --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573441169597.1835101471489; Thu, 5 Oct 2023 23:24:01 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCR-0005BW-6P; Fri, 06 Oct 2023 02:20:35 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCN-000587-Cy for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:31 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCL-0002pk-D2 for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:31 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1yw60dT3z4xQW; Fri, 6 Oct 2023 17:20:22 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yw43hcjz4xQV; Fri, 6 Oct 2023 17:20:20 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Jing Liu , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 05/21] vfio/pci: use an invalid fd to enable MSI-X Date: Fri, 6 Oct 2023 08:19:49 +0200 Message-ID: <20231006062005.1040296-6-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573441857100001 From: Jing Liu Guests typically enable MSI-X with all of the vectors masked in the MSI-X vector table. To match the guest state of device, QEMU enables MSI-X by enabling vector 0 with userspace triggering and immediately release. However the release function actually does not release it due to already using userspace mode. It is no need to enable triggering on host and rely on the mask bit to avoid spurious interrupts. Use an invalid fd (i.e. fd =3D -1) is enough to get MSI-X enabled. After dynamic MSI-X allocation is supported, the interrupt restoring also need use such way to enable MSI-X, therefore, create a function for that. Suggested-by: Alex Williamson Signed-off-by: Jing Liu Reviewed-by: C=C3=A9dric Le Goater Reviewed-by: Alex Williamson Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/pci.c | 44 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 36 insertions(+), 8 deletions(-) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index eb7627c5f9fcd67f346595ebe73011cc3205b58e..ad508abd6f382d5188711910178= 59c4c4c8fd4f9 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -369,6 +369,33 @@ static void vfio_msi_interrupt(void *opaque) notify(&vdev->pdev, nr); } =20 +/* + * Get MSI-X enabled, but no vector enabled, by setting vector 0 with an i= nvalid + * fd to kernel. + */ +static int vfio_enable_msix_no_vec(VFIOPCIDevice *vdev) +{ + g_autofree struct vfio_irq_set *irq_set =3D NULL; + int ret =3D 0, argsz; + int32_t *fd; + + argsz =3D sizeof(*irq_set) + sizeof(*fd); + + irq_set =3D g_malloc0(argsz); + irq_set->argsz =3D argsz; + irq_set->flags =3D VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index =3D VFIO_PCI_MSIX_IRQ_INDEX; + irq_set->start =3D 0; + irq_set->count =3D 1; + fd =3D (int32_t *)&irq_set->data; + *fd =3D -1; + + ret =3D ioctl(vdev->vbasedev.fd, VFIO_DEVICE_SET_IRQS, irq_set); + + return ret; +} + static int vfio_enable_vectors(VFIOPCIDevice *vdev, bool msix) { struct vfio_irq_set *irq_set; @@ -618,6 +645,8 @@ static void vfio_commit_kvm_msi_virq_batch(VFIOPCIDevic= e *vdev) =20 static void vfio_msix_enable(VFIOPCIDevice *vdev) { + int ret; + vfio_disable_interrupts(vdev); =20 vdev->msi_vectors =3D g_new0(VFIOMSIVector, vdev->msix->entries); @@ -640,8 +669,6 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev) vfio_commit_kvm_msi_virq_batch(vdev); =20 if (vdev->nr_vectors) { - int ret; - ret =3D vfio_enable_vectors(vdev, true); if (ret) { error_report("vfio: failed to enable vectors, %d", ret); @@ -655,13 +682,14 @@ static void vfio_msix_enable(VFIOPCIDevice *vdev) * MSI-X capability, but leaves the vector table masked. We there= fore * can't rely on a vector_use callback (from request_irq() in the = guest) * to switch the physical device into MSI-X mode because that may = come a - * long time after pci_enable_msix(). This code enables vector 0 = with - * triggering to userspace, then immediately release the vector, l= eaving - * the physical device with no vectors enabled, but MSI-X enabled,= just - * like the guest view. + * long time after pci_enable_msix(). This code sets vector 0 wit= h an + * invalid fd to make the physical device MSI-X enabled, but with = no + * vectors enabled, just like the guest view. */ - vfio_msix_vector_do_use(&vdev->pdev, 0, NULL, NULL); - vfio_msix_vector_release(&vdev->pdev, 0); + ret =3D vfio_enable_msix_no_vec(vdev); + if (ret) { + error_report("vfio: failed to enable MSI-X, %d", ret); + } } =20 trace_vfio_msix_enable(vdev->vbasedev.name); --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 169657334254810.697470287913347; Thu, 5 Oct 2023 23:22:22 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCS-0005CG-9d; Fri, 06 Oct 2023 02:20:36 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCO-00059M-Ir for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:32 -0400 Received: from mail.ozlabs.org ([2404:9400:2221:ea00::3] helo=gandalf.ozlabs.org) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCL-0002ql-QI for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:32 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1yw81HpFz4xQZ; Fri, 6 Oct 2023 17:20:24 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yw64Kb9z4xQV; Fri, 6 Oct 2023 17:20:22 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Jing Liu , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 06/21] vfio/pci: enable MSI-X in interrupt restoring on dynamic allocation Date: Fri, 6 Oct 2023 08:19:50 +0200 Message-ID: <20231006062005.1040296-7-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2404:9400:2221:ea00::3; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -39 X-Spam_score: -4.0 X-Spam_bar: ---- X-Spam_report: (-4.0 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, RCVD_IN_DNSWL_MED=-2.3, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573344204100003 From: Jing Liu During migration restoring, vfio_enable_vectors() is called to restore enabling MSI-X interrupts for assigned devices. It sets the range from 0 to nr_vectors to kernel to enable MSI-X and the vectors unmasked in guest. During the MSI-X enabling, all the vectors within the range are allocated according to the VFIO_DEVICE_SET_IRQS ioctl. When dynamic MSI-X allocation is supported, we only want the guest unmasked vectors being allocated and enabled. Use vector 0 with an invalid fd to get MSI-X enabled, after that, all the vectors can be allocated in need. Signed-off-by: Jing Liu Reviewed-by: C=C3=A9dric Le Goater Reviewed-by: Alex Williamson Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/pci.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index ad508abd6f382d518871191017859c4c4c8fd4f9..898296fd5441b07fded7e50a53b= 2927683dd4b1a 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -402,6 +402,23 @@ static int vfio_enable_vectors(VFIOPCIDevice *vdev, bo= ol msix) int ret =3D 0, i, argsz; int32_t *fds; =20 + /* + * If dynamic MSI-X allocation is supported, the vectors to be allocat= ed + * and enabled can be scattered. Before kernel enabling MSI-X, setting + * nr_vectors causes all these vectors to be allocated on host. + * + * To keep allocation as needed, use vector 0 with an invalid fd to get + * MSI-X enabled first, then set vectors with a potentially sparse set= of + * eventfds to enable interrupts only when enabled in guest. + */ + if (msix && !vdev->msix->noresize) { + ret =3D vfio_enable_msix_no_vec(vdev); + + if (ret) { + return ret; + } + } + argsz =3D sizeof(*irq_set) + (vdev->nr_vectors * sizeof(*fds)); =20 irq_set =3D g_malloc0(argsz); --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573289927900.9937845045532; Thu, 5 Oct 2023 23:21:29 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCQ-0005AL-J6; Fri, 06 Oct 2023 02:20:34 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCN-000582-8d for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:31 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCL-0002rW-IK for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:30 -0400 Received: from gandalf.ozlabs.org (gandalf.ozlabs.org [150.107.74.76]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywB5fR6z4xQb; Fri, 6 Oct 2023 17:20:26 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yw84ys8z4xQV; Fri, 6 Oct 2023 17:20:24 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Eric Auger , Yi Liu , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 07/21] scripts/update-linux-headers: Add iommufd.h Date: Fri, 6 Oct 2023 08:19:51 +0200 Message-ID: <20231006062005.1040296-8-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573291396100016 From: Eric Auger Update the script to import iommufd.h Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- scripts/update-linux-headers.sh | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers= .sh index 35a64bb501935f69e684d7a9a3d59d3f33557627..34295c0fe55b72bbf4db013c4e9= 6262fa1ebfeac 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -161,7 +161,8 @@ done rm -rf "$output/linux-headers/linux" mkdir -p "$output/linux-headers/linux" for header in const.h stddef.h kvm.h vfio.h vfio_ccw.h vfio_zdev.h vhost.h= \ - psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h v= duse.h; do + psci.h psp-sev.h userfaultfd.h memfd.h mman.h nvme_ioctl.h \ + vduse.h iommufd.h; do cp "$tmpdir/include/linux/$header" "$output/linux-headers/linux" done =20 --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573294480333.78447399849165; Thu, 5 Oct 2023 23:21:34 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCS-0005CX-NR; Fri, 06 Oct 2023 02:20:36 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCP-0005AF-TY for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:33 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCM-0002yR-TK for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:33 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywD6KsDz4xQc; Fri, 6 Oct 2023 17:20:28 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywC2G4Dz4xQV; Fri, 6 Oct 2023 17:20:27 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 08/21] linux-headers: Add iommufd.h Date: Fri, 6 Oct 2023 08:19:52 +0200 Message-ID: <20231006062005.1040296-9-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573295514100003 From: Zhenzhong Duan Since commit da3c22c74a3c ("linux-headers: Update to Linux v6.6-rc1"), linux-headers has been updated to v6.6-rc1. As previous patch added iommufd.h to update-linux-headers.sh, run the script again against TAG v6.6-rc1 to have iommufd.h included. Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- linux-headers/linux/iommufd.h | 444 ++++++++++++++++++++++++++++++++++ 1 file changed, 444 insertions(+) create mode 100644 linux-headers/linux/iommufd.h diff --git a/linux-headers/linux/iommufd.h b/linux-headers/linux/iommufd.h new file mode 100644 index 0000000000000000000000000000000000000000..218bf7ac98d07c589058af8cb11= 56582d47423db --- /dev/null +++ b/linux-headers/linux/iommufd.h @@ -0,0 +1,444 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. + */ +#ifndef _IOMMUFD_H +#define _IOMMUFD_H + +#include +#include + +#define IOMMUFD_TYPE (';') + +/** + * DOC: General ioctl format + * + * The ioctl interface follows a general format to allow for extensibility= . Each + * ioctl is passed in a structure pointer as the argument providing the si= ze of + * the structure in the first u32. The kernel checks that any structure sp= ace + * beyond what it understands is 0. This allows userspace to use the backw= ard + * compatible portion while consistently using the newer, larger, structur= es. + * + * ioctls use a standard meaning for common errnos: + * + * - ENOTTY: The IOCTL number itself is not supported at all + * - E2BIG: The IOCTL number is supported, but the provided structure has + * non-zero in a part the kernel does not understand. + * - EOPNOTSUPP: The IOCTL number is supported, and the structure is + * understood, however a known field has a value the kernel does not + * understand or support. + * - EINVAL: Everything about the IOCTL was understood, but a field is not + * correct. + * - ENOENT: An ID or IOVA provided does not exist. + * - ENOMEM: Out of memory. + * - EOVERFLOW: Mathematics overflowed. + * + * As well as additional errnos, within specific ioctls. + */ +enum { + IOMMUFD_CMD_BASE =3D 0x80, + IOMMUFD_CMD_DESTROY =3D IOMMUFD_CMD_BASE, + IOMMUFD_CMD_IOAS_ALLOC, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS, + IOMMUFD_CMD_IOAS_COPY, + IOMMUFD_CMD_IOAS_IOVA_RANGES, + IOMMUFD_CMD_IOAS_MAP, + IOMMUFD_CMD_IOAS_UNMAP, + IOMMUFD_CMD_OPTION, + IOMMUFD_CMD_VFIO_IOAS, + IOMMUFD_CMD_HWPT_ALLOC, + IOMMUFD_CMD_GET_HW_INFO, +}; + +/** + * struct iommu_destroy - ioctl(IOMMU_DESTROY) + * @size: sizeof(struct iommu_destroy) + * @id: iommufd object ID to destroy. Can be any destroyable object type. + * + * Destroy any object held within iommufd. + */ +struct iommu_destroy { + __u32 size; + __u32 id; +}; +#define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY) + +/** + * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC) + * @size: sizeof(struct iommu_ioas_alloc) + * @flags: Must be 0 + * @out_ioas_id: Output IOAS ID for the allocated object + * + * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (= IOVA) + * to memory mapping. + */ +struct iommu_ioas_alloc { + __u32 size; + __u32 flags; + __u32 out_ioas_id; +}; +#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC) + +/** + * struct iommu_iova_range - ioctl(IOMMU_IOVA_RANGE) + * @start: First IOVA + * @last: Inclusive last IOVA + * + * An interval in IOVA space. + */ +struct iommu_iova_range { + __aligned_u64 start; + __aligned_u64 last; +}; + +/** + * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES) + * @size: sizeof(struct iommu_ioas_iova_ranges) + * @ioas_id: IOAS ID to read ranges from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to the output array of struct iommu_iova_range + * @out_iova_alignment: Minimum alignment required for mapping IOVA + * + * Query an IOAS for ranges of allowed IOVAs. Mapping IOVA outside these r= anges + * is not allowed. num_iovas will be set to the total number of iovas and + * the allowed_iovas[] will be filled in as space permits. + * + * The allowed ranges are dependent on the HW path the DMA operation takes= , and + * can change during the lifetime of the IOAS. A fresh empty IOAS will hav= e a + * full range, and each attached device will narrow the ranges based on th= at + * device's HW restrictions. Detaching a device can widen the ranges. User= space + * should query ranges after every attach/detach to know what IOVAs are va= lid + * for mapping. + * + * On input num_iovas is the length of the allowed_iovas array. On output = it is + * the total number of iovas filled in. The ioctl will return -EMSGSIZE an= d set + * num_iovas to the required value if num_iovas is too small. In this case= the + * caller should allocate a larger output array and re-issue the ioctl. + * + * out_iova_alignment returns the minimum IOVA alignment that can be given + * to IOMMU_IOAS_MAP/COPY. IOVA's must satisfy:: + * + * starting_iova % out_iova_alignment =3D=3D 0 + * (starting_iova + length) % out_iova_alignment =3D=3D 0 + * + * out_iova_alignment can be 1 indicating any IOVA is allowed. It cannot + * be higher than the system PAGE_SIZE. + */ +struct iommu_ioas_iova_ranges { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; + __aligned_u64 out_iova_alignment; +}; +#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RAN= GES) + +/** + * struct iommu_ioas_allow_iovas - ioctl(IOMMU_IOAS_ALLOW_IOVAS) + * @size: sizeof(struct iommu_ioas_allow_iovas) + * @ioas_id: IOAS ID to allow IOVAs from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to array of struct iommu_iova_range + * + * Ensure a range of IOVAs are always available for allocation. If this ca= ll + * succeeds then IOMMU_IOAS_IOVA_RANGES will never return a list of IOVA r= anges + * that are narrower than the ranges provided here. This call will fail if + * IOMMU_IOAS_IOVA_RANGES is currently narrower than the given ranges. + * + * When an IOAS is first created the IOVA_RANGES will be maximally sized, = and as + * devices are attached the IOVA will narrow based on the device restricti= ons. + * When an allowed range is specified any narrowing will be refused, ie de= vice + * attachment can fail if the device requires limiting within the allowed = range. + * + * Automatic IOVA allocation is also impacted by this call. MAP will only + * allocate within the allowed IOVAs if they are present. + * + * This call replaces the entire allowed list with the given list. + */ +struct iommu_ioas_allow_iovas { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; +}; +#define IOMMU_IOAS_ALLOW_IOVAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOW_IO= VAS) + +/** + * enum iommufd_ioas_map_flags - Flags for map and copy + * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropr= iate + * IOVA to place the mapping at + * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping + * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping + */ +enum iommufd_ioas_map_flags { + IOMMU_IOAS_MAP_FIXED_IOVA =3D 1 << 0, + IOMMU_IOAS_MAP_WRITEABLE =3D 1 << 1, + IOMMU_IOAS_MAP_READABLE =3D 1 << 2, +}; + +/** + * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP) + * @size: sizeof(struct iommu_ioas_map) + * @flags: Combination of enum iommufd_ioas_map_flags + * @ioas_id: IOAS ID to change the mapping of + * @__reserved: Must be 0 + * @user_va: Userspace pointer to start mapping from + * @length: Number of bytes to map + * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is = set + * then this must be provided as input. + * + * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified the= n the + * mapping will be established at iova, otherwise a suitable location base= d on + * the reserved and allowed lists will be automatically selected and retur= ned in + * iova. + * + * If IOMMU_IOAS_MAP_FIXED_IOVA is specified then the iova range must curr= ently + * be unused, existing IOVA cannot be replaced. + */ +struct iommu_ioas_map { + __u32 size; + __u32 flags; + __u32 ioas_id; + __u32 __reserved; + __aligned_u64 user_va; + __aligned_u64 length; + __aligned_u64 iova; +}; +#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP) + +/** + * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY) + * @size: sizeof(struct iommu_ioas_copy) + * @flags: Combination of enum iommufd_ioas_map_flags + * @dst_ioas_id: IOAS ID to change the mapping of + * @src_ioas_id: IOAS ID to copy from + * @length: Number of bytes to copy and map + * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA= is + * set then this must be provided as input. + * @src_iova: IOVA to start the copy + * + * Copy an already existing mapping from src_ioas_id and establish it in + * dst_ioas_id. The src iova/length must exactly match a range used with + * IOMMU_IOAS_MAP. + * + * This may be used to efficiently clone a subset of an IOAS to another, o= r as a + * kind of 'cache' to speed up mapping. Copy has an efficiency advantage o= ver + * establishing equivalent new mappings, as internal resources are shared,= and + * the kernel will pin the user memory only once. + */ +struct iommu_ioas_copy { + __u32 size; + __u32 flags; + __u32 dst_ioas_id; + __u32 src_ioas_id; + __aligned_u64 length; + __aligned_u64 dst_iova; + __aligned_u64 src_iova; +}; +#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY) + +/** + * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP) + * @size: sizeof(struct iommu_ioas_unmap) + * @ioas_id: IOAS ID to change the mapping of + * @iova: IOVA to start the unmapping at + * @length: Number of bytes to unmap, and return back the bytes unmapped + * + * Unmap an IOVA range. The iova/length must be a superset of a previously + * mapped range used with IOMMU_IOAS_MAP or IOMMU_IOAS_COPY. Splitting or + * truncating ranges is not allowed. The values 0 to U64_MAX will unmap + * everything. + */ +struct iommu_ioas_unmap { + __u32 size; + __u32 ioas_id; + __aligned_u64 iova; + __aligned_u64 length; +}; +#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP) + +/** + * enum iommufd_option - ioctl(IOMMU_OPTION_RLIMIT_MODE) and + * ioctl(IOMMU_OPTION_HUGE_PAGES) + * @IOMMU_OPTION_RLIMIT_MODE: + * Change how RLIMIT_MEMLOCK accounting works. The caller must have pri= vilege + * to invoke this. Value 0 (default) is user based accouting, 1 uses pr= ocess + * based accounting. Global option, object_id must be 0 + * @IOMMU_OPTION_HUGE_PAGES: + * Value 1 (default) allows contiguous pages to be combined when genera= ting + * iommu mappings. Value 0 disables combining, everything is mapped to + * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS + * option, the object_id must be the IOAS ID. + */ +enum iommufd_option { + IOMMU_OPTION_RLIMIT_MODE =3D 0, + IOMMU_OPTION_HUGE_PAGES =3D 1, +}; + +/** + * enum iommufd_option_ops - ioctl(IOMMU_OPTION_OP_SET) and + * ioctl(IOMMU_OPTION_OP_GET) + * @IOMMU_OPTION_OP_SET: Set the option's value + * @IOMMU_OPTION_OP_GET: Get the option's value + */ +enum iommufd_option_ops { + IOMMU_OPTION_OP_SET =3D 0, + IOMMU_OPTION_OP_GET =3D 1, +}; + +/** + * struct iommu_option - iommu option multiplexer + * @size: sizeof(struct iommu_option) + * @option_id: One of enum iommufd_option + * @op: One of enum iommufd_option_ops + * @__reserved: Must be 0 + * @object_id: ID of the object if required + * @val64: Option value to set or value returned on get + * + * Change a simple option value. This multiplexor allows controlling optio= ns + * on objects. IOMMU_OPTION_OP_SET will load an option and IOMMU_OPTION_OP= _GET + * will return the current value. + */ +struct iommu_option { + __u32 size; + __u32 option_id; + __u16 op; + __u16 __reserved; + __u32 object_id; + __aligned_u64 val64; +}; +#define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) + +/** + * enum iommufd_vfio_ioas_op - IOMMU_VFIO_IOAS_* ioctls + * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS + * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS + * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility + */ +enum iommufd_vfio_ioas_op { + IOMMU_VFIO_IOAS_GET =3D 0, + IOMMU_VFIO_IOAS_SET =3D 1, + IOMMU_VFIO_IOAS_CLEAR =3D 2, +}; + +/** + * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS) + * @size: sizeof(struct iommu_vfio_ioas) + * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set + * For IOMMU_VFIO_IOAS_GET will output the IOAS ID + * @op: One of enum iommufd_vfio_ioas_op + * @__reserved: Must be 0 + * + * The VFIO compatibility support uses a single ioas because VFIO APIs do = not + * support the ID field. Set or Get the IOAS that VFIO compatibility will = use. + * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the + * compatibility ioas, either by taking what is already set, or auto creat= ing + * one. From then on VFIO will continue to use that ioas and is not effect= ed by + * this ioctl. SET or CLEAR does not destroy any auto-created IOAS. + */ +struct iommu_vfio_ioas { + __u32 size; + __u32 ioas_id; + __u16 op; + __u16 __reserved; +}; +#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) + +/** + * struct iommu_hwpt_alloc - ioctl(IOMMU_HWPT_ALLOC) + * @size: sizeof(struct iommu_hwpt_alloc) + * @flags: Must be 0 + * @dev_id: The device to allocate this HWPT for + * @pt_id: The IOAS to connect this HWPT to + * @out_hwpt_id: The ID of the new HWPT + * @__reserved: Must be 0 + * + * Explicitly allocate a hardware page table object. This is the same obje= ct + * type that is returned by iommufd_device_attach() and represents the + * underlying iommu driver's iommu_domain kernel object. + * + * A HWPT will be created with the IOVA mappings from the given IOAS. + */ +struct iommu_hwpt_alloc { + __u32 size; + __u32 flags; + __u32 dev_id; + __u32 pt_id; + __u32 out_hwpt_id; + __u32 __reserved; +}; +#define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC) + +/** + * struct iommu_hw_info_vtd - Intel VT-d hardware information + * + * @flags: Must be 0 + * @__reserved: Must be 0 + * + * @cap_reg: Value of Intel VT-d capability register defined in VT-d spec + * section 11.4.2 Capability Register. + * @ecap_reg: Value of Intel VT-d capability register defined in VT-d spec + * section 11.4.3 Extended Capability Register. + * + * User needs to understand the Intel VT-d specification to decode the + * register value. + */ +struct iommu_hw_info_vtd { + __u32 flags; + __u32 __reserved; + __aligned_u64 cap_reg; + __aligned_u64 ecap_reg; +}; + +/** + * enum iommu_hw_info_type - IOMMU Hardware Info Types + * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardwa= re + * info + * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type + */ +enum iommu_hw_info_type { + IOMMU_HW_INFO_TYPE_NONE, + IOMMU_HW_INFO_TYPE_INTEL_VTD, +}; + +/** + * struct iommu_hw_info - ioctl(IOMMU_GET_HW_INFO) + * @size: sizeof(struct iommu_hw_info) + * @flags: Must be 0 + * @dev_id: The device bound to the iommufd + * @data_len: Input the length of a user buffer in bytes. Output the lengt= h of + * data that kernel supports + * @data_uptr: User pointer to a user-space buffer used by the kernel to f= ill + * the iommu type specific hardware information data + * @out_data_type: Output the iommu hardware info type as defined in the e= num + * iommu_hw_info_type. + * @__reserved: Must be 0 + * + * Query an iommu type specific hardware information data from an iommu be= hind + * a given device that has been bound to iommufd. This hardware info data = will + * be used to sync capabilities between the virtual iommu and the physical + * iommu, e.g. a nested translation setup needs to check the hardware info= , so + * a guest stage-1 page table can be compatible with the physical iommu. + * + * To capture an iommu type specific hardware information data, @data_uptr= and + * its length @data_len must be provided. Trailing bytes will be zeroed if= the + * user buffer is larger than the data that kernel has. Otherwise, kernel = only + * fills the buffer using the given length in @data_len. If the ioctl succ= eeds, + * @data_len will be updated to the length that kernel actually supports, + * @out_data_type will be filled to decode the data filled in the buffer + * pointed by @data_uptr. Input @data_len =3D=3D zero is allowed. + */ +struct iommu_hw_info { + __u32 size; + __u32 flags; + __u32 dev_id; + __u32 data_len; + __aligned_u64 data_uptr; + __u32 out_data_type; + __u32 __reserved; +}; +#define IOMMU_GET_HW_INFO _IO(IOMMUFD_TYPE, IOMMUFD_CMD_GET_HW_INFO) +#endif --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573484334592.5541122360004; Thu, 5 Oct 2023 23:24:44 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCU-0005EF-3w; Fri, 06 Oct 2023 02:20:38 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCS-0005Cb-OM for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:36 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCP-0002rW-4R for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:36 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywJ3J7cz4xQf; Fri, 6 Oct 2023 17:20:32 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywF30Hhz4xQV; Fri, 6 Oct 2023 17:20:29 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Yi Liu , Eric Auger , Yi Sun , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 09/21] vfio/common: Move IOMMU agnostic helpers to a separate file Date: Fri, 6 Oct 2023 08:19:53 +0200 Message-ID: <20231006062005.1040296-10-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573484875100001 From: Yi Liu Move low-level iommu agnostic helpers to a separate helpers.c file. They relate to regions, interrupts, device/region capabilities and etc. Signed-off-by: Eric Auger Signed-off-by: Yi Sun Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 9 + hw/vfio/common.c | 588 -------------------------------- hw/vfio/helpers.c | 612 ++++++++++++++++++++++++++++++++++ hw/vfio/meson.build | 1 + 4 files changed, 622 insertions(+), 588 deletions(-) create mode 100644 hw/vfio/helpers.c diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index e9b895459534d7873445f865ef0e5f8f5c53882a..e0483893d14b536a79c372b8d02= 471255ea3da25 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -196,6 +196,12 @@ typedef struct VFIODisplay { } dmabuf; } VFIODisplay; =20 +typedef struct { + unsigned long *bitmap; + hwaddr size; + hwaddr pages; +} VFIOBitmap; + void vfio_put_base_device(VFIODevice *vbasedev); void vfio_disable_irqindex(VFIODevice *vbasedev, int index); void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); @@ -245,6 +251,8 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type1_in= fo *info, unsigned int *avail); struct vfio_info_cap_header * vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id); +struct vfio_info_cap_header * +vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id); #endif extern const MemoryListener vfio_prereg_listener; =20 @@ -257,4 +265,5 @@ int vfio_spapr_remove_window(VFIOContainer *container, bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp); void vfio_migration_exit(VFIODevice *vbasedev); =20 +int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); #endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 134649226d4333f648ca751291003316a5f3b4a9..4e122fc4e4001ee02e24c5593e4= d36b428c848e2 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -62,84 +62,6 @@ static QLIST_HEAD(, VFIOAddressSpace) vfio_address_space= s =3D static int vfio_kvm_device_fd =3D -1; #endif =20 -/* - * Common VFIO interrupt disable - */ -void vfio_disable_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set =3D { - .argsz =3D sizeof(irq_set), - .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, - .index =3D index, - .start =3D 0, - .count =3D 0, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set =3D { - .argsz =3D sizeof(irq_set), - .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, - .index =3D index, - .start =3D 0, - .count =3D 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) -{ - struct vfio_irq_set irq_set =3D { - .argsz =3D sizeof(irq_set), - .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, - .index =3D index, - .start =3D 0, - .count =3D 1, - }; - - ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); -} - -static inline const char *action_to_str(int action) -{ - switch (action) { - case VFIO_IRQ_SET_ACTION_MASK: - return "MASK"; - case VFIO_IRQ_SET_ACTION_UNMASK: - return "UNMASK"; - case VFIO_IRQ_SET_ACTION_TRIGGER: - return "TRIGGER"; - default: - return "UNKNOWN ACTION"; - } -} - -static const char *index_to_str(VFIODevice *vbasedev, int index) -{ - if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { - return NULL; - } - - switch (index) { - case VFIO_PCI_INTX_IRQ_INDEX: - return "INTX"; - case VFIO_PCI_MSI_IRQ_INDEX: - return "MSI"; - case VFIO_PCI_MSIX_IRQ_INDEX: - return "MSIX"; - case VFIO_PCI_ERR_IRQ_INDEX: - return "ERR"; - case VFIO_PCI_REQ_IRQ_INDEX: - return "REQ"; - default: - return NULL; - } -} - static int vfio_ram_block_discard_disable(VFIOContainer *container, bool s= tate) { switch (container->iommu_type) { @@ -163,183 +85,10 @@ static int vfio_ram_block_discard_disable(VFIOContain= er *container, bool state) } } =20 -int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, - int action, int fd, Error **errp) -{ - struct vfio_irq_set *irq_set; - int argsz, ret =3D 0; - const char *name; - int32_t *pfd; - - argsz =3D sizeof(*irq_set) + sizeof(*pfd); - - irq_set =3D g_malloc0(argsz); - irq_set->argsz =3D argsz; - irq_set->flags =3D VFIO_IRQ_SET_DATA_EVENTFD | action; - irq_set->index =3D index; - irq_set->start =3D subindex; - irq_set->count =3D 1; - pfd =3D (int32_t *)&irq_set->data; - *pfd =3D fd; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { - ret =3D -errno; - } - g_free(irq_set); - - if (!ret) { - return 0; - } - - error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure"); - - name =3D index_to_str(vbasedev, index); - if (name) { - error_prepend(errp, "%s-%d: ", name, subindex); - } else { - error_prepend(errp, "index %d-%d: ", index, subindex); - } - error_prepend(errp, - "Failed to %s %s eventfd signaling for interrupt ", - fd < 0 ? "tear down" : "set up", action_to_str(action)); - return ret; -} - -/* - * IO Port/MMIO - Beware of the endians, VFIO is always little endian - */ -void vfio_region_write(void *opaque, hwaddr addr, - uint64_t data, unsigned size) -{ - VFIORegion *region =3D opaque; - VFIODevice *vbasedev =3D region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - - switch (size) { - case 1: - buf.byte =3D data; - break; - case 2: - buf.word =3D cpu_to_le16(data); - break; - case 4: - buf.dword =3D cpu_to_le32(data); - break; - case 8: - buf.qword =3D cpu_to_le64(data); - break; - default: - hw_error("vfio: unsupported write size, %u bytes", size); - break; - } - - if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D si= ze) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 - ",%d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, data, size); - } - - trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); - - /* - * A read or write to a BAR always signals an INTx EOI. This will - * do nothing if not pending (including not in INTx mode). We assume - * that a BAR access is in response to an interrupt and that BAR - * accesses will service the interrupt. Unfortunately, we don't know - * which access will service the interrupt, so we're potentially - * getting quite a few host interrupts per guest interrupt. - */ - vbasedev->ops->vfio_eoi(vbasedev); -} - -uint64_t vfio_region_read(void *opaque, - hwaddr addr, unsigned size) -{ - VFIORegion *region =3D opaque; - VFIODevice *vbasedev =3D region->vbasedev; - union { - uint8_t byte; - uint16_t word; - uint32_t dword; - uint64_t qword; - } buf; - uint64_t data =3D 0; - - if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D siz= e) { - error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", - __func__, vbasedev->name, region->nr, - addr, size); - return (uint64_t)-1; - } - switch (size) { - case 1: - data =3D buf.byte; - break; - case 2: - data =3D le16_to_cpu(buf.word); - break; - case 4: - data =3D le32_to_cpu(buf.dword); - break; - case 8: - data =3D le64_to_cpu(buf.qword); - break; - default: - hw_error("vfio: unsupported read size, %u bytes", size); - break; - } - - trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); - - /* Same as write above */ - vbasedev->ops->vfio_eoi(vbasedev); - - return data; -} - -const MemoryRegionOps vfio_region_ops =3D { - .read =3D vfio_region_read, - .write =3D vfio_region_write, - .endianness =3D DEVICE_LITTLE_ENDIAN, - .valid =3D { - .min_access_size =3D 1, - .max_access_size =3D 8, - }, - .impl =3D { - .min_access_size =3D 1, - .max_access_size =3D 8, - }, -}; - /* * Device state interfaces */ =20 -typedef struct { - unsigned long *bitmap; - hwaddr size; - hwaddr pages; -} VFIOBitmap; - -static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) -{ - vbmap->pages =3D REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size= (); - vbmap->size =3D ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / - BITS_PER_BYTE; - vbmap->bitmap =3D g_try_malloc0(vbmap->size); - if (!vbmap->bitmap) { - return -ENOMEM; - } - - return 0; -} - static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, uint64_t size, ram_addr_t ram_addr); =20 @@ -1994,30 +1743,6 @@ static void vfio_listener_release(VFIOContainer *con= tainer) } } =20 -static struct vfio_info_cap_header * -vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - - for (hdr =3D ptr + cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->next) { - if (hdr->id =3D=3D id) { - return hdr; - } - } - - return NULL; -} - -struct vfio_info_cap_header * -vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - static struct vfio_info_cap_header * vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t= id) { @@ -2028,16 +1753,6 @@ vfio_get_iommu_type1_info_cap(struct vfio_iommu_type= 1_info *info, uint16_t id) return vfio_get_cap((void *)info, info->cap_offset, id); } =20 -struct vfio_info_cap_header * -vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) -{ - if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, unsigned int *avail) { @@ -2059,232 +1774,6 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type= 1_info *info, return true; } =20 -static int vfio_setup_region_sparse_mmaps(VFIORegion *region, - struct vfio_region_info *info) -{ - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_sparse_mmap *sparse; - int i, j; - - hdr =3D vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMA= P); - if (!hdr) { - return -ENODEV; - } - - sparse =3D container_of(hdr, struct vfio_region_info_cap_sparse_mmap, = header); - - trace_vfio_region_sparse_mmap_header(region->vbasedev->name, - region->nr, sparse->nr_areas); - - region->mmaps =3D g_new0(VFIOMmap, sparse->nr_areas); - - for (i =3D 0, j =3D 0; i < sparse->nr_areas; i++) { - if (sparse->areas[i].size) { - trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, - sparse->areas[i].offset + - sparse->areas[i].size - 1); - region->mmaps[j].offset =3D sparse->areas[i].offset; - region->mmaps[j].size =3D sparse->areas[i].size; - j++; - } - } - - region->nr_mmaps =3D j; - region->mmaps =3D g_realloc(region->mmaps, j * sizeof(VFIOMmap)); - - return 0; -} - -int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *regio= n, - int index, const char *name) -{ - struct vfio_region_info *info; - int ret; - - ret =3D vfio_get_region_info(vbasedev, index, &info); - if (ret) { - return ret; - } - - region->vbasedev =3D vbasedev; - region->flags =3D info->flags; - region->size =3D info->size; - region->fd_offset =3D info->offset; - region->nr =3D index; - - if (region->size) { - region->mem =3D g_new0(MemoryRegion, 1); - memory_region_init_io(region->mem, obj, &vfio_region_ops, - region, name, region->size); - - if (!vbasedev->no_mmap && - region->flags & VFIO_REGION_INFO_FLAG_MMAP) { - - ret =3D vfio_setup_region_sparse_mmaps(region, info); - - if (ret) { - region->nr_mmaps =3D 1; - region->mmaps =3D g_new0(VFIOMmap, region->nr_mmaps); - region->mmaps[0].offset =3D 0; - region->mmaps[0].size =3D region->size; - } - } - } - - g_free(info); - - trace_vfio_region_setup(vbasedev->name, index, name, - region->flags, region->fd_offset, region->size= ); - return 0; -} - -static void vfio_subregion_unmap(VFIORegion *region, int index) -{ - trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem), - region->mmaps[index].offset, - region->mmaps[index].offset + - region->mmaps[index].size - 1); - memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem); - munmap(region->mmaps[index].mmap, region->mmaps[index].size); - object_unparent(OBJECT(®ion->mmaps[index].mem)); - region->mmaps[index].mmap =3D NULL; -} - -int vfio_region_mmap(VFIORegion *region) -{ - int i, prot =3D 0; - char *name; - - if (!region->mem) { - return 0; - } - - prot |=3D region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0; - prot |=3D region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0; - - for (i =3D 0; i < region->nr_mmaps; i++) { - region->mmaps[i].mmap =3D mmap(NULL, region->mmaps[i].size, prot, - MAP_SHARED, region->vbasedev->fd, - region->fd_offset + - region->mmaps[i].offset); - if (region->mmaps[i].mmap =3D=3D MAP_FAILED) { - int ret =3D -errno; - - trace_vfio_region_mmap_fault(memory_region_name(region->mem), = i, - region->fd_offset + - region->mmaps[i].offset, - region->fd_offset + - region->mmaps[i].offset + - region->mmaps[i].size - 1, ret); - - region->mmaps[i].mmap =3D NULL; - - for (i--; i >=3D 0; i--) { - vfio_subregion_unmap(region, i); - } - - return ret; - } - - name =3D g_strdup_printf("%s mmaps[%d]", - memory_region_name(region->mem), i); - memory_region_init_ram_device_ptr(®ion->mmaps[i].mem, - memory_region_owner(region->mem), - name, region->mmaps[i].size, - region->mmaps[i].mmap); - g_free(name); - memory_region_add_subregion(region->mem, region->mmaps[i].offset, - ®ion->mmaps[i].mem); - - trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem), - region->mmaps[i].offset, - region->mmaps[i].offset + - region->mmaps[i].size - 1); - } - - return 0; -} - -void vfio_region_unmap(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - vfio_subregion_unmap(region, i); - } - } -} - -void vfio_region_exit(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem= ); - } - } - - trace_vfio_region_exit(region->vbasedev->name, region->nr); -} - -void vfio_region_finalize(VFIORegion *region) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - munmap(region->mmaps[i].mmap, region->mmaps[i].size); - object_unparent(OBJECT(®ion->mmaps[i].mem)); - } - } - - object_unparent(OBJECT(region->mem)); - - g_free(region->mem); - g_free(region->mmaps); - - trace_vfio_region_finalize(region->vbasedev->name, region->nr); - - region->mem =3D NULL; - region->mmaps =3D NULL; - region->nr_mmaps =3D 0; - region->size =3D 0; - region->flags =3D 0; - region->nr =3D 0; -} - -void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled) -{ - int i; - - if (!region->mem) { - return; - } - - for (i =3D 0; i < region->nr_mmaps; i++) { - if (region->mmaps[i].mmap) { - memory_region_set_enabled(®ion->mmaps[i].mem, enabled); - } - } - - trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem), - enabled); -} - void vfio_reset_handler(void *opaque) { VFIOGroup *group; @@ -2983,83 +2472,6 @@ void vfio_put_base_device(VFIODevice *vbasedev) close(vbasedev->fd); } =20 -int vfio_get_region_info(VFIODevice *vbasedev, int index, - struct vfio_region_info **info) -{ - size_t argsz =3D sizeof(struct vfio_region_info); - - *info =3D g_malloc0(argsz); - - (*info)->index =3D index; -retry: - (*info)->argsz =3D argsz; - - if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { - g_free(*info); - *info =3D NULL; - return -errno; - } - - if ((*info)->argsz > argsz) { - argsz =3D (*info)->argsz; - *info =3D g_realloc(*info, argsz); - - goto retry; - } - - return 0; -} - -int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, - uint32_t subtype, struct vfio_region_info **i= nfo) -{ - int i; - - for (i =3D 0; i < vbasedev->num_regions; i++) { - struct vfio_info_cap_header *hdr; - struct vfio_region_info_cap_type *cap_type; - - if (vfio_get_region_info(vbasedev, i, info)) { - continue; - } - - hdr =3D vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE); - if (!hdr) { - g_free(*info); - continue; - } - - cap_type =3D container_of(hdr, struct vfio_region_info_cap_type, h= eader); - - trace_vfio_get_dev_region(vbasedev->name, i, - cap_type->type, cap_type->subtype); - - if (cap_type->type =3D=3D type && cap_type->subtype =3D=3D subtype= ) { - return 0; - } - - g_free(*info); - } - - *info =3D NULL; - return -ENODEV; -} - -bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_ty= pe) -{ - struct vfio_region_info *info =3D NULL; - bool ret =3D false; - - if (!vfio_get_region_info(vbasedev, region, &info)) { - if (vfio_get_region_info_cap(info, cap_type)) { - ret =3D true; - } - g_free(info); - } - - return ret; -} - /* * Interfaces for IBM EEH (Enhanced Error Handling) */ diff --git a/hw/vfio/helpers.c b/hw/vfio/helpers.c new file mode 100644 index 0000000000000000000000000000000000000000..7e5da21b319120b875359aaa5ec= 26c556c1df777 --- /dev/null +++ b/hw/vfio/helpers.c @@ -0,0 +1,612 @@ +/* + * low level and IOMMU backend agnostic helpers used by VFIO devices, + * related to regions, interrupts, capabilities + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#include "qemu/osdep.h" +#include + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "hw/hw.h" +#include "trace.h" +#include "qapi/error.h" +#include "qemu/error-report.h" + +/* + * Common VFIO interrupt disable + */ +void vfio_disable_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set =3D { + .argsz =3D sizeof(irq_set), + .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_TRIGGER, + .index =3D index, + .start =3D 0, + .count =3D 0, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set =3D { + .argsz =3D sizeof(irq_set), + .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_UNMASK, + .index =3D index, + .start =3D 0, + .count =3D 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index) +{ + struct vfio_irq_set irq_set =3D { + .argsz =3D sizeof(irq_set), + .flags =3D VFIO_IRQ_SET_DATA_NONE | VFIO_IRQ_SET_ACTION_MASK, + .index =3D index, + .start =3D 0, + .count =3D 1, + }; + + ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, &irq_set); +} + +static inline const char *action_to_str(int action) +{ + switch (action) { + case VFIO_IRQ_SET_ACTION_MASK: + return "MASK"; + case VFIO_IRQ_SET_ACTION_UNMASK: + return "UNMASK"; + case VFIO_IRQ_SET_ACTION_TRIGGER: + return "TRIGGER"; + default: + return "UNKNOWN ACTION"; + } +} + +static const char *index_to_str(VFIODevice *vbasedev, int index) +{ + if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { + return NULL; + } + + switch (index) { + case VFIO_PCI_INTX_IRQ_INDEX: + return "INTX"; + case VFIO_PCI_MSI_IRQ_INDEX: + return "MSI"; + case VFIO_PCI_MSIX_IRQ_INDEX: + return "MSIX"; + case VFIO_PCI_ERR_IRQ_INDEX: + return "ERR"; + case VFIO_PCI_REQ_IRQ_INDEX: + return "REQ"; + default: + return NULL; + } +} + +int vfio_set_irq_signaling(VFIODevice *vbasedev, int index, int subindex, + int action, int fd, Error **errp) +{ + struct vfio_irq_set *irq_set; + int argsz, ret =3D 0; + const char *name; + int32_t *pfd; + + argsz =3D sizeof(*irq_set) + sizeof(*pfd); + + irq_set =3D g_malloc0(argsz); + irq_set->argsz =3D argsz; + irq_set->flags =3D VFIO_IRQ_SET_DATA_EVENTFD | action; + irq_set->index =3D index; + irq_set->start =3D subindex; + irq_set->count =3D 1; + pfd =3D (int32_t *)&irq_set->data; + *pfd =3D fd; + + if (ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set)) { + ret =3D -errno; + } + g_free(irq_set); + + if (!ret) { + return 0; + } + + error_setg_errno(errp, -ret, "VFIO_DEVICE_SET_IRQS failure"); + + name =3D index_to_str(vbasedev, index); + if (name) { + error_prepend(errp, "%s-%d: ", name, subindex); + } else { + error_prepend(errp, "index %d-%d: ", index, subindex); + } + error_prepend(errp, + "Failed to %s %s eventfd signaling for interrupt ", + fd < 0 ? "tear down" : "set up", action_to_str(action)); + return ret; +} + +/* + * IO Port/MMIO - Beware of the endians, VFIO is always little endian + */ +void vfio_region_write(void *opaque, hwaddr addr, + uint64_t data, unsigned size) +{ + VFIORegion *region =3D opaque; + VFIODevice *vbasedev =3D region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + + switch (size) { + case 1: + buf.byte =3D data; + break; + case 2: + buf.word =3D cpu_to_le16(data); + break; + case 4: + buf.dword =3D cpu_to_le32(data); + break; + case 8: + buf.qword =3D cpu_to_le64(data); + break; + default: + hw_error("vfio: unsupported write size, %u bytes", size); + break; + } + + if (pwrite(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D si= ze) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", 0x%"PRIx64 + ",%d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, data, size); + } + + trace_vfio_region_write(vbasedev->name, region->nr, addr, data, size); + + /* + * A read or write to a BAR always signals an INTx EOI. This will + * do nothing if not pending (including not in INTx mode). We assume + * that a BAR access is in response to an interrupt and that BAR + * accesses will service the interrupt. Unfortunately, we don't know + * which access will service the interrupt, so we're potentially + * getting quite a few host interrupts per guest interrupt. + */ + vbasedev->ops->vfio_eoi(vbasedev); +} + +uint64_t vfio_region_read(void *opaque, + hwaddr addr, unsigned size) +{ + VFIORegion *region =3D opaque; + VFIODevice *vbasedev =3D region->vbasedev; + union { + uint8_t byte; + uint16_t word; + uint32_t dword; + uint64_t qword; + } buf; + uint64_t data =3D 0; + + if (pread(vbasedev->fd, &buf, size, region->fd_offset + addr) !=3D siz= e) { + error_report("%s(%s:region%d+0x%"HWADDR_PRIx", %d) failed: %m", + __func__, vbasedev->name, region->nr, + addr, size); + return (uint64_t)-1; + } + switch (size) { + case 1: + data =3D buf.byte; + break; + case 2: + data =3D le16_to_cpu(buf.word); + break; + case 4: + data =3D le32_to_cpu(buf.dword); + break; + case 8: + data =3D le64_to_cpu(buf.qword); + break; + default: + hw_error("vfio: unsupported read size, %u bytes", size); + break; + } + + trace_vfio_region_read(vbasedev->name, region->nr, addr, size, data); + + /* Same as write above */ + vbasedev->ops->vfio_eoi(vbasedev); + + return data; +} + +const MemoryRegionOps vfio_region_ops =3D { + .read =3D vfio_region_read, + .write =3D vfio_region_write, + .endianness =3D DEVICE_LITTLE_ENDIAN, + .valid =3D { + .min_access_size =3D 1, + .max_access_size =3D 8, + }, + .impl =3D { + .min_access_size =3D 1, + .max_access_size =3D 8, + }, +}; + +int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) +{ + vbmap->pages =3D REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size= (); + vbmap->size =3D ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / + BITS_PER_BYTE; + vbmap->bitmap =3D g_try_malloc0(vbmap->size); + if (!vbmap->bitmap) { + return -ENOMEM; + } + + return 0; +} + +struct vfio_info_cap_header * +vfio_get_cap(void *ptr, uint32_t cap_offset, uint16_t id) +{ + struct vfio_info_cap_header *hdr; + + for (hdr =3D ptr + cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->next) { + if (hdr->id =3D=3D id) { + return hdr; + } + } + + return NULL; +} + +struct vfio_info_cap_header * +vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) +{ + if (!(info->flags & VFIO_REGION_INFO_FLAG_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +struct vfio_info_cap_header * +vfio_get_device_info_cap(struct vfio_device_info *info, uint16_t id) +{ + if (!(info->flags & VFIO_DEVICE_FLAGS_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +static int vfio_setup_region_sparse_mmaps(VFIORegion *region, + struct vfio_region_info *info) +{ + struct vfio_info_cap_header *hdr; + struct vfio_region_info_cap_sparse_mmap *sparse; + int i, j; + + hdr =3D vfio_get_region_info_cap(info, VFIO_REGION_INFO_CAP_SPARSE_MMA= P); + if (!hdr) { + return -ENODEV; + } + + sparse =3D container_of(hdr, struct vfio_region_info_cap_sparse_mmap, = header); + + trace_vfio_region_sparse_mmap_header(region->vbasedev->name, + region->nr, sparse->nr_areas); + + region->mmaps =3D g_new0(VFIOMmap, sparse->nr_areas); + + for (i =3D 0, j =3D 0; i < sparse->nr_areas; i++) { + if (sparse->areas[i].size) { + trace_vfio_region_sparse_mmap_entry(i, sparse->areas[i].offset, + sparse->areas[i].offset + + sparse->areas[i].size - 1); + region->mmaps[j].offset =3D sparse->areas[i].offset; + region->mmaps[j].size =3D sparse->areas[i].size; + j++; + } + } + + region->nr_mmaps =3D j; + region->mmaps =3D g_realloc(region->mmaps, j * sizeof(VFIOMmap)); + + return 0; +} + +int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *regio= n, + int index, const char *name) +{ + struct vfio_region_info *info; + int ret; + + ret =3D vfio_get_region_info(vbasedev, index, &info); + if (ret) { + return ret; + } + + region->vbasedev =3D vbasedev; + region->flags =3D info->flags; + region->size =3D info->size; + region->fd_offset =3D info->offset; + region->nr =3D index; + + if (region->size) { + region->mem =3D g_new0(MemoryRegion, 1); + memory_region_init_io(region->mem, obj, &vfio_region_ops, + region, name, region->size); + + if (!vbasedev->no_mmap && + region->flags & VFIO_REGION_INFO_FLAG_MMAP) { + + ret =3D vfio_setup_region_sparse_mmaps(region, info); + + if (ret) { + region->nr_mmaps =3D 1; + region->mmaps =3D g_new0(VFIOMmap, region->nr_mmaps); + region->mmaps[0].offset =3D 0; + region->mmaps[0].size =3D region->size; + } + } + } + + g_free(info); + + trace_vfio_region_setup(vbasedev->name, index, name, + region->flags, region->fd_offset, region->size= ); + return 0; +} + +static void vfio_subregion_unmap(VFIORegion *region, int index) +{ + trace_vfio_region_unmap(memory_region_name(®ion->mmaps[index].mem), + region->mmaps[index].offset, + region->mmaps[index].offset + + region->mmaps[index].size - 1); + memory_region_del_subregion(region->mem, ®ion->mmaps[index].mem); + munmap(region->mmaps[index].mmap, region->mmaps[index].size); + object_unparent(OBJECT(®ion->mmaps[index].mem)); + region->mmaps[index].mmap =3D NULL; +} + +int vfio_region_mmap(VFIORegion *region) +{ + int i, prot =3D 0; + char *name; + + if (!region->mem) { + return 0; + } + + prot |=3D region->flags & VFIO_REGION_INFO_FLAG_READ ? PROT_READ : 0; + prot |=3D region->flags & VFIO_REGION_INFO_FLAG_WRITE ? PROT_WRITE : 0; + + for (i =3D 0; i < region->nr_mmaps; i++) { + region->mmaps[i].mmap =3D mmap(NULL, region->mmaps[i].size, prot, + MAP_SHARED, region->vbasedev->fd, + region->fd_offset + + region->mmaps[i].offset); + if (region->mmaps[i].mmap =3D=3D MAP_FAILED) { + int ret =3D -errno; + + trace_vfio_region_mmap_fault(memory_region_name(region->mem), = i, + region->fd_offset + + region->mmaps[i].offset, + region->fd_offset + + region->mmaps[i].offset + + region->mmaps[i].size - 1, ret); + + region->mmaps[i].mmap =3D NULL; + + for (i--; i >=3D 0; i--) { + vfio_subregion_unmap(region, i); + } + + return ret; + } + + name =3D g_strdup_printf("%s mmaps[%d]", + memory_region_name(region->mem), i); + memory_region_init_ram_device_ptr(®ion->mmaps[i].mem, + memory_region_owner(region->mem), + name, region->mmaps[i].size, + region->mmaps[i].mmap); + g_free(name); + memory_region_add_subregion(region->mem, region->mmaps[i].offset, + ®ion->mmaps[i].mem); + + trace_vfio_region_mmap(memory_region_name(®ion->mmaps[i].mem), + region->mmaps[i].offset, + region->mmaps[i].offset + + region->mmaps[i].size - 1); + } + + return 0; +} + +void vfio_region_unmap(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + vfio_subregion_unmap(region, i); + } + } +} + +void vfio_region_exit(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + memory_region_del_subregion(region->mem, ®ion->mmaps[i].mem= ); + } + } + + trace_vfio_region_exit(region->vbasedev->name, region->nr); +} + +void vfio_region_finalize(VFIORegion *region) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + munmap(region->mmaps[i].mmap, region->mmaps[i].size); + object_unparent(OBJECT(®ion->mmaps[i].mem)); + } + } + + object_unparent(OBJECT(region->mem)); + + g_free(region->mem); + g_free(region->mmaps); + + trace_vfio_region_finalize(region->vbasedev->name, region->nr); + + region->mem =3D NULL; + region->mmaps =3D NULL; + region->nr_mmaps =3D 0; + region->size =3D 0; + region->flags =3D 0; + region->nr =3D 0; +} + +void vfio_region_mmaps_set_enabled(VFIORegion *region, bool enabled) +{ + int i; + + if (!region->mem) { + return; + } + + for (i =3D 0; i < region->nr_mmaps; i++) { + if (region->mmaps[i].mmap) { + memory_region_set_enabled(®ion->mmaps[i].mem, enabled); + } + } + + trace_vfio_region_mmaps_set_enabled(memory_region_name(region->mem), + enabled); +} + +int vfio_get_region_info(VFIODevice *vbasedev, int index, + struct vfio_region_info **info) +{ + size_t argsz =3D sizeof(struct vfio_region_info); + + *info =3D g_malloc0(argsz); + + (*info)->index =3D index; +retry: + (*info)->argsz =3D argsz; + + if (ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, *info)) { + g_free(*info); + *info =3D NULL; + return -errno; + } + + if ((*info)->argsz > argsz) { + argsz =3D (*info)->argsz; + *info =3D g_realloc(*info, argsz); + + goto retry; + } + + return 0; +} + +int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, + uint32_t subtype, struct vfio_region_info **i= nfo) +{ + int i; + + for (i =3D 0; i < vbasedev->num_regions; i++) { + struct vfio_info_cap_header *hdr; + struct vfio_region_info_cap_type *cap_type; + + if (vfio_get_region_info(vbasedev, i, info)) { + continue; + } + + hdr =3D vfio_get_region_info_cap(*info, VFIO_REGION_INFO_CAP_TYPE); + if (!hdr) { + g_free(*info); + continue; + } + + cap_type =3D container_of(hdr, struct vfio_region_info_cap_type, h= eader); + + trace_vfio_get_dev_region(vbasedev->name, i, + cap_type->type, cap_type->subtype); + + if (cap_type->type =3D=3D type && cap_type->subtype =3D=3D subtype= ) { + return 0; + } + + g_free(*info); + } + + *info =3D NULL; + return -ENODEV; +} + +bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_ty= pe) +{ + struct vfio_region_info *info =3D NULL; + bool ret =3D false; + + if (!vfio_get_region_info(vbasedev, region, &info)) { + if (vfio_get_region_info_cap(info, cap_type)) { + ret =3D true; + } + g_free(info); + } + + return ret; +} diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build index da9af297a0c5914e39be0a6f515caddd37542471..3746c9f98420b1be949443b5d57= f26a9982a37fe 100644 --- a/hw/vfio/meson.build +++ b/hw/vfio/meson.build @@ -1,5 +1,6 @@ vfio_ss =3D ss.source_set() vfio_ss.add(files( + 'helpers.c', 'common.c', 'spapr.c', 'migration.c', --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573289302694.4333676801207; Thu, 5 Oct 2023 23:21:29 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCU-0005El-Mk; Fri, 06 Oct 2023 02:20:38 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCS-0005Cv-Vw for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:36 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCR-0002yR-7u for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:36 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywL3zF8z4xQk; Fri, 6 Oct 2023 17:20:34 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywJ70hdz4xQV; Fri, 6 Oct 2023 17:20:32 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Eric Auger , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 10/21] vfio/common: Propagate KVM_SET_DEVICE_ATTR error if any Date: Fri, 6 Oct 2023 08:19:54 +0200 Message-ID: <20231006062005.1040296-11-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573291390100015 From: Eric Auger In the VFIO_SPAPR_TCE_v2_IOMMU container case, when KVM_SET_DEVICE_ATTR fails, we currently don't propagate the error as we do on the vfio_spapr_create_window() failure case. Let's align the code. Take the opportunity to reword the error message and make it more explicit. Signed-off-by: Eric Auger Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/common.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 4e122fc4e4001ee02e24c5593e4d36b428c848e2..c54a72ec803779b45803573c6c6= 33a170c5bad1f 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -878,11 +878,11 @@ static void vfio_listener_region_add(MemoryListener *= listener, QLIST_FOREACH(group, &container->group_list, container_nex= t) { param.groupfd =3D group->fd; if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &at= tr)) { - error_report("vfio: failed to setup fd %d " - "for a group with fd %d: %s", - param.tablefd, param.groupfd, - strerror(errno)); - return; + error_setg_errno(&err, errno, + "vfio: failed GROUP_SET_SPAPR_TCE= for " + "KVM VFIO device %d and group fd = %d", + param.tablefd, param.groupfd); + goto fail; } trace_vfio_spapr_group_attach(param.groupfd, param.tab= lefd); } --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 16965732890952.2064043698163687; Thu, 5 Oct 2023 23:21:29 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCc-0005HU-55; Fri, 06 Oct 2023 02:20:46 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCY-0005H3-DI for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:43 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCV-00031M-LL for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:41 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywP1DxYz4xQl; Fri, 6 Oct 2023 17:20:37 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywM0ZJqz4xQV; Fri, 6 Oct 2023 17:20:34 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Eric Auger , Yi Liu , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 11/21] vfio/common: Introduce vfio_container_add|del_section_window() Date: Fri, 6 Oct 2023 08:19:55 +0200 Message-ID: <20231006062005.1040296-12-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573290175100009 From: Eric Auger Introduce helper functions that isolate the code used for VFIO_SPAPR_TCE_v2_IOMMU. Those helpers hide implementation details beneath the container object and make the vfio_listener_region_add/del() implementations more readable. No code change intended. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/common.c | 156 +++++++++++++++++++++++++++-------------------- 1 file changed, 89 insertions(+), 67 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index c54a72ec803779b45803573c6c633a170c5bad1f..0397788aa58c8deaa8cf3ed19fa= 8eb40e91d7678 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -807,6 +807,92 @@ static bool vfio_get_section_iova_range(VFIOContainer = *container, return true; } =20 +static int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp) +{ + VFIOHostDMAWindow *hostwin; + hwaddr pgsize =3D 0; + int ret; + + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return 0; + } + + /* For now intersections are not allowed, we may relax this later */ + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (ranges_overlap(hostwin->min_iova, + hostwin->max_iova - hostwin->min_iova + 1, + section->offset_within_address_space, + int128_get64(section->size))) { + error_setg(errp, + "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" + "host DMA window [0x%"PRIx64",0x%"PRIx64"]", + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, + hostwin->min_iova, hostwin->max_iova); + return -EINVAL; + } + } + + ret =3D vfio_spapr_create_window(container, section, &pgsize); + if (ret) { + error_setg_errno(errp, -ret, "Failed to create SPAPR window"); + return ret; + } + + vfio_host_win_add(container, section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, pgsize); +#ifdef CONFIG_KVM + if (kvm_enabled()) { + VFIOGroup *group; + IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->mr); + struct kvm_vfio_spapr_tce param; + struct kvm_device_attr attr =3D { + .group =3D KVM_DEV_VFIO_GROUP, + .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, + .addr =3D (uint64_t)(unsigned long)¶m, + }; + + if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_F= D, + ¶m.tablefd)) { + QLIST_FOREACH(group, &container->group_list, container_next) { + param.groupfd =3D group->fd; + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr))= { + error_setg_errno(errp, errno, + "vfio: failed GROUP_SET_SPAPR_TCE for= " + "KVM VFIO device %d and group fd %d", + param.tablefd, param.groupfd); + return -errno; + } + trace_vfio_spapr_group_attach(param.groupfd, param.tablefd= ); + } + } + } +#endif + return 0; +} + +static void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section) +{ + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return; + } + + vfio_spapr_remove_window(container, + section->offset_within_address_space); + if (vfio_host_win_del(container, + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1) < 0) { + hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, + __func__, section->offset_within_address_space); + } +} + static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -833,62 +919,8 @@ static void vfio_listener_region_add(MemoryListener *l= istener, return; } =20 - if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - hwaddr pgsize =3D 0; - - /* For now intersections are not allowed, we may relax this later = */ - QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { - if (ranges_overlap(hostwin->min_iova, - hostwin->max_iova - hostwin->min_iova + 1, - section->offset_within_address_space, - int128_get64(section->size))) { - error_setg(&err, - "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existi= ng" - "host DMA window [0x%"PRIx64",0x%"PRIx64"]", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, - hostwin->min_iova, hostwin->max_iova); - goto fail; - } - } - - ret =3D vfio_spapr_create_window(container, section, &pgsize); - if (ret) { - error_setg_errno(&err, -ret, "Failed to create SPAPR window"); - goto fail; - } - - vfio_host_win_add(container, section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, pgsize); -#ifdef CONFIG_KVM - if (kvm_enabled()) { - VFIOGroup *group; - IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->m= r); - struct kvm_vfio_spapr_tce param; - struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, - .addr =3D (uint64_t)(unsigned long)¶m, - }; - - if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_T= CE_FD, - ¶m.tablefd)) { - QLIST_FOREACH(group, &container->group_list, container_nex= t) { - param.groupfd =3D group->fd; - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &at= tr)) { - error_setg_errno(&err, errno, - "vfio: failed GROUP_SET_SPAPR_TCE= for " - "KVM VFIO device %d and group fd = %d", - param.tablefd, param.groupfd); - goto fail; - } - trace_vfio_spapr_group_attach(param.groupfd, param.tab= lefd); - } - } - } -#endif + if (vfio_container_add_section_window(container, section, &err)) { + goto fail; } =20 hostwin =3D vfio_find_hostwin(container, iova, end); @@ -1105,17 +1137,7 @@ static void vfio_listener_region_del(MemoryListener = *listener, =20 memory_region_unref(section->mr); =20 - if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - vfio_spapr_remove_window(container, - section->offset_within_address_space); - if (vfio_host_win_del(container, - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1) < 0) { - hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, - __func__, section->offset_within_address_space); - } - } + vfio_container_del_section_window(container, section); } =20 static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool sta= rt) --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573289094801.0467044347058; Thu, 5 Oct 2023 23:21:29 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCd-0005Hs-42; Fri, 06 Oct 2023 02:20:47 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCa-0005HL-Pm for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:44 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCY-00031a-6J for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:44 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywR5b4Vz4xRj; Fri, 6 Oct 2023 17:20:39 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywP4xdJz4xQV; Fri, 6 Oct 2023 17:20:37 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Zhenzhong Duan , Yi Liu , Eric Auger , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 12/21] vfio/common: Extract out vfio_kvm_device_[add/del]_fd Date: Fri, 6 Oct 2023 08:19:56 +0200 Message-ID: <20231006062005.1040296-13-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573290160100008 From: Zhenzhong Duan Introduce two new helpers, vfio_kvm_device_[add/del]_fd which take as input a file descriptor which can be either a group fd or a cdev fd. This uses the new KVM_DEV_VFIO_FILE VFIO KVM device group, which aliases to the legacy KVM_DEV_VFIO_GROUP. vfio_kvm_device_[add/del]_group then call those new helpers. Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: Eric Auger Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 3 ++ hw/vfio/common.c | 55 +++++++++++++++++++++++++---------- 2 files changed, 42 insertions(+), 16 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index e0483893d14b536a79c372b8d02471255ea3da25..c4e7c3b4a7757087ab4bc02b634= 216bf3ae857d6 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -226,6 +226,9 @@ struct vfio_device_info *vfio_get_device_info(int fd); int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vbasedev, Error **errp); =20 +int vfio_kvm_device_add_fd(int fd, Error **errp); +int vfio_kvm_device_del_fd(int fd, Error **errp); + extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; extern VFIOGroupList vfio_group_list; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 0397788aa58c8deaa8cf3ed19fa8eb40e91d7678..d8ed432cb6d0e8e955984401cdb= be921d87636f7 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1818,17 +1818,17 @@ void vfio_reset_handler(void *opaque) } } =20 -static void vfio_kvm_device_add_group(VFIOGroup *group) +int vfio_kvm_device_add_fd(int fd, Error **errp) { #ifdef CONFIG_KVM struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_ADD, - .addr =3D (uint64_t)(unsigned long)&group->fd, + .group =3D KVM_DEV_VFIO_FILE, + .attr =3D KVM_DEV_VFIO_FILE_ADD, + .addr =3D (uint64_t)(unsigned long)&fd, }; =20 if (!kvm_enabled()) { - return; + return 0; } =20 if (vfio_kvm_device_fd < 0) { @@ -1837,38 +1837,61 @@ static void vfio_kvm_device_add_group(VFIOGroup *gr= oup) }; =20 if (kvm_vm_ioctl(kvm_state, KVM_CREATE_DEVICE, &cd)) { - error_report("Failed to create KVM VFIO device: %m"); - return; + error_setg_errno(errp, errno, "Failed to create KVM VFIO devic= e"); + return -errno; } =20 vfio_kvm_device_fd =3D cd.fd; } =20 if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to add group %d to KVM VFIO device: %m", - group->groupid); + error_setg_errno(errp, errno, "Failed to add fd %d to KVM VFIO dev= ice", + fd); + return -errno; } #endif + return 0; } =20 -static void vfio_kvm_device_del_group(VFIOGroup *group) +int vfio_kvm_device_del_fd(int fd, Error **errp) { #ifdef CONFIG_KVM struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_DEL, - .addr =3D (uint64_t)(unsigned long)&group->fd, + .group =3D KVM_DEV_VFIO_FILE, + .attr =3D KVM_DEV_VFIO_FILE_DEL, + .addr =3D (uint64_t)(unsigned long)&fd, }; =20 if (vfio_kvm_device_fd < 0) { - return; + error_setg(errp, "KVM VFIO device isn't created yet"); + return -EINVAL; } =20 if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr)) { - error_report("Failed to remove group %d from KVM VFIO device: %m", - group->groupid); + error_setg_errno(errp, errno, + "Failed to remove fd %d from KVM VFIO device", fd= ); + return -errno; } #endif + return 0; +} + +static void vfio_kvm_device_add_group(VFIOGroup *group) +{ + Error *err =3D NULL; + + if (vfio_kvm_device_add_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } +} + +static void vfio_kvm_device_del_group(VFIOGroup *group) +{ + Error *err =3D NULL; + + if (vfio_kvm_device_del_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } } =20 static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573644760393.88769259796175; Thu, 5 Oct 2023 23:27:24 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD6-0005Lj-Fw; Fri, 06 Oct 2023 02:21:16 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCm-0005Iu-Lg for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:58 -0400 Received: from mail.ozlabs.org ([2404:9400:2221:ea00::3] helo=gandalf.ozlabs.org) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCa-000322-OK for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:54 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywV2qLyz4xV1; Fri, 6 Oct 2023 17:20:42 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywS28CPz4xS5; Fri, 6 Oct 2023 17:20:40 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Eric Auger , Yi Liu , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 13/21] vfio/pci: Introduce vfio_[attach/detach]_device Date: Fri, 6 Oct 2023 08:19:57 +0200 Message-ID: <20231006062005.1040296-14-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2404:9400:2221:ea00::3; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -28 X-Spam_score: -2.9 X-Spam_bar: -- X-Spam_report: (-2.9 / 5.0 requ) BAYES_00=-1.9, FORGED_SPF_HELO=1, HEADER_FROM_DIFFERENT_DOMAINS=0.25, RCVD_IN_DNSWL_MED=-2.3, SPF_HELO_PASS=-0.001, T_SPF_TEMPERROR=0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573645451100001 From: Eric Auger We want the VFIO devices to be able to use two different IOMMU backends, the legacy VFIO one and the new iommufd one. Introduce vfio_[attach/detach]_device which aim at hiding the underlying IOMMU backend (IOCTLs, datatypes, ...). Once vfio_attach_device completes, the device is attached to a security context and its fd can be used. Conversely When vfio_detach_device completes, the device has been detached from the security context. At the moment only the implementation based on the legacy container/group exists. Let's use it from the vfio-pci device. Subsequent patches will handle other devices. We also take benefit of this patch to properly free vbasedev->name on failure. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 3 ++ hw/vfio/common.c | 74 +++++++++++++++++++++++++++++++++++ hw/vfio/pci.c | 67 +++++++------------------------ hw/vfio/trace-events | 3 +- 4 files changed, 94 insertions(+), 53 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index c4e7c3b4a7757087ab4bc02b634216bf3ae857d6..12fbfbc37d466abcd85a838f265= 67dc0add84de0 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -225,6 +225,9 @@ void vfio_put_group(VFIOGroup *group); struct vfio_device_info *vfio_get_device_info(int fd); int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vbasedev, Error **errp); +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp); +void vfio_detach_device(VFIODevice *vbasedev); =20 int vfio_kvm_device_add_fd(int fd, Error **errp); int vfio_kvm_device_del_fd(int fd, Error **errp); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index d8ed432cb6d0e8e955984401cdbbe921d87636f7..f4c33c9858f5cc2b8245a9725fd= 660e7898ee760 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -2611,3 +2611,77 @@ int vfio_eeh_as_op(AddressSpace *as, uint32_t op) } return vfio_eeh_container_op(container, op); } + +static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp) +{ + char *tmp, group_path[PATH_MAX], *group_name; + int ret, groupid; + ssize_t len; + + tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); + len =3D readlink(tmp, group_path, sizeof(group_path)); + g_free(tmp); + + if (len <=3D 0 || len >=3D sizeof(group_path)) { + ret =3D len < 0 ? -errno : -ENAMETOOLONG; + error_setg_errno(errp, -ret, "no iommu_group found"); + return ret; + } + + group_path[len] =3D 0; + + group_name =3D basename(group_path); + if (sscanf(group_name, "%d", &groupid) !=3D 1) { + error_setg_errno(errp, errno, "failed to read %s", group_path); + return -errno; + } + return groupid; +} + +/* + * vfio_attach_device: attach a device to a security context + * @name and @vbasedev->name are likely to be different depending + * on the type of the device, hence the need for passing @name + */ +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp) +{ + int groupid =3D vfio_device_groupid(vbasedev, errp); + VFIODevice *vbasedev_iter; + VFIOGroup *group; + int ret; + + if (groupid < 0) { + return groupid; + } + + trace_vfio_attach_device(vbasedev->name, groupid); + + group =3D vfio_get_group(groupid, as, errp); + if (!group) { + return -ENOENT; + } + + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { + error_setg(errp, "device is already attached"); + vfio_put_group(group); + return -EBUSY; + } + } + ret =3D vfio_get_device(group, name, vbasedev, errp); + if (ret) { + vfio_put_group(group); + } + + return ret; +} + +void vfio_detach_device(VFIODevice *vbasedev) +{ + VFIOGroup *group =3D vbasedev->group; + + trace_vfio_detach_device(vbasedev->name, group->groupid); + vfio_put_base_device(vbasedev); + vfio_put_group(group); +} diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 898296fd5441b07fded7e50a53b2927683dd4b1a..60e10d0eeedc9aaad6ac13a873e= ac5a2c215d391 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2895,10 +2895,10 @@ static void vfio_populate_device(VFIOPCIDevice *vde= v, Error **errp) =20 static void vfio_pci_put_device(VFIOPCIDevice *vdev) { + vfio_detach_device(&vdev->vbasedev); + g_free(vdev->vbasedev.name); g_free(vdev->msix); - - vfio_put_base_device(&vdev->vbasedev); } =20 static void vfio_err_notifier_handler(void *opaque) @@ -3045,13 +3045,9 @@ static void vfio_realize(PCIDevice *pdev, Error **er= rp) { VFIOPCIDevice *vdev =3D VFIO_PCI(pdev); VFIODevice *vbasedev =3D &vdev->vbasedev; - VFIODevice *vbasedev_iter; - VFIOGroup *group; - char *tmp, *subsys, group_path[PATH_MAX], *group_name; + char *tmp, *subsys; Error *err =3D NULL; - ssize_t len; struct stat st; - int groupid; int i, ret; bool is_mdev; char uuid[UUID_FMT_LEN]; @@ -3082,39 +3078,6 @@ static void vfio_realize(PCIDevice *pdev, Error **er= rp) vbasedev->type =3D VFIO_DEVICE_TYPE_PCI; vbasedev->dev =3D DEVICE(vdev); =20 - tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <=3D 0 || len >=3D sizeof(group_path)) { - error_setg_errno(errp, len < 0 ? errno : ENAMETOOLONG, - "no iommu_group found"); - goto error; - } - - group_path[len] =3D 0; - - group_name =3D basename(group_path); - if (sscanf(group_name, "%d", &groupid) !=3D 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - goto error; - } - - trace_vfio_realize(vbasedev->name, groupid); - - group =3D vfio_get_group(groupid, pci_device_iommu_address_space(pdev)= , errp); - if (!group) { - goto error; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - goto error; - } - } - /* * Mediated devices *might* operate compatibly with discarding of RAM,= but * we cannot know for certain, it depends on whether the mdev vendor d= river @@ -3132,7 +3095,6 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vbasedev->ram_block_discard_allowed && !is_mdev) { error_setg(errp, "x-balloon-allowed only potentially compatible " "with mdev devices"); - vfio_put_group(group); goto error; } =20 @@ -3143,17 +3105,17 @@ static void vfio_realize(PCIDevice *pdev, Error **e= rrp) name =3D g_strdup(vbasedev->name); } =20 - ret =3D vfio_get_device(group, name, vbasedev, errp); + ret =3D vfio_attach_device(name, vbasedev, + pci_device_iommu_address_space(pdev), errp); g_free(name); if (ret) { - vfio_put_group(group); goto error; } =20 vfio_populate_device(vdev, &err); if (err) { error_propagate(errp, err); - goto error; + goto out_detach; } =20 /* Get a copy of config space */ @@ -3163,7 +3125,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (ret < (int)MIN(pci_config_size(&vdev->pdev), vdev->config_size)) { ret =3D ret < 0 ? -errno : -EFAULT; error_setg_errno(errp, -ret, "failed to read device config space"); - goto error; + goto out_detach; } =20 /* vfio emulates a lot for us, but some bits need extra love */ @@ -3182,7 +3144,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->vendor_id !=3D PCI_ANY_ID) { if (vdev->vendor_id >=3D 0xffff) { error_setg(errp, "invalid PCI vendor ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_VENDOR_ID, vdev->vendor_id, ~0); trace_vfio_pci_emulated_vendor_id(vbasedev->name, vdev->vendor_id); @@ -3193,7 +3155,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->device_id !=3D PCI_ANY_ID) { if (vdev->device_id > 0xffff) { error_setg(errp, "invalid PCI device ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_DEVICE_ID, vdev->device_id, ~0); trace_vfio_pci_emulated_device_id(vbasedev->name, vdev->device_id); @@ -3204,7 +3166,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->sub_vendor_id !=3D PCI_ANY_ID) { if (vdev->sub_vendor_id > 0xffff) { error_setg(errp, "invalid PCI subsystem vendor ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_VENDOR_ID, vdev->sub_vendor_id, ~0); @@ -3215,7 +3177,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) if (vdev->sub_device_id !=3D PCI_ANY_ID) { if (vdev->sub_device_id > 0xffff) { error_setg(errp, "invalid PCI subsystem device ID provided"); - goto error; + goto out_detach; } vfio_add_emulated_word(vdev, PCI_SUBSYSTEM_ID, vdev->sub_device_id= , ~0); trace_vfio_pci_emulated_sub_device_id(vbasedev->name, @@ -3248,7 +3210,7 @@ static void vfio_realize(PCIDevice *pdev, Error **err= p) vfio_msix_early_setup(vdev, &err); if (err) { error_propagate(errp, err); - goto error; + goto out_detach; } =20 vfio_bars_register(vdev); @@ -3364,14 +3326,16 @@ out_deregister: out_teardown: vfio_teardown_msi(vdev); vfio_bars_exit(vdev); +out_detach: + vfio_detach_device(vbasedev); error: error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name); + g_free(vbasedev->name); } =20 static void vfio_instance_finalize(Object *obj) { VFIOPCIDevice *vdev =3D VFIO_PCI(obj); - VFIOGroup *group =3D vdev->vbasedev.group; =20 vfio_display_finalize(vdev); vfio_bars_finalize(vdev); @@ -3385,7 +3349,6 @@ static void vfio_instance_finalize(Object *obj) * g_free(vdev->igd_opregion); */ vfio_pci_put_device(vdev); - vfio_put_group(group); } =20 static void vfio_exitfn(PCIDevice *pdev) diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 0ba3c5a0e26bc82f40a0d7737e68128d2c9334fe..8ac13eb106db68c4f547b1b3819= f96272309a124 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -37,7 +37,8 @@ vfio_pci_hot_reset_dep_devices(int domain, int bus, int s= lot, int function, int vfio_pci_hot_reset_result(const char *name, const char *result) "%s hot re= set: %s" vfio_populate_device_config(const char *name, unsigned long size, unsigned= long offset, unsigned long flags) "Device %s config:\n size: 0x%lx, offse= t: 0x%lx, flags: 0x%lx" vfio_populate_device_get_irq_info_failure(const char *errstr) "VFIO_DEVICE= _GET_IRQ_INFO failure: %s" -vfio_realize(const char *name, int group_id) " (%s) group %d" +vfio_attach_device(const char *name, int group_id) " (%s) group %d" +vfio_detach_device(const char *name, int group_id) " (%s) group %d" vfio_mdev(const char *name, bool is_mdev) " (%s) is_mdev %d" vfio_add_ext_cap_dropped(const char *name, uint16_t cap, uint16_t offset) = "%s 0x%x@0x%x" vfio_pci_reset(const char *name) " (%s)" --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573562106506.00349399729384; Thu, 5 Oct 2023 23:26:02 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeCy-0005J3-Ad; Fri, 06 Oct 2023 02:21:09 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCh-0005IG-2E for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:51 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCd-00032W-19 for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:50 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywY0MHNz4xSy; Fri, 6 Oct 2023 17:20:45 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywV6XQpz4xS5; Fri, 6 Oct 2023 17:20:42 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Eric Auger , Yi Liu , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 14/21] vfio/platform: Use vfio_[attach/detach]_device Date: Fri, 6 Oct 2023 08:19:58 +0200 Message-ID: <20231006062005.1040296-15-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573563983100001 From: Eric Auger Let the vfio-platform device use vfio_attach_device() and vfio_detach_device(), hence hiding the details of the used IOMMU backend. Drop the trace event for vfio-platform as we have similar one in vfio_attach_device. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/platform.c | 43 +++---------------------------------------- hw/vfio/trace-events | 1 - 2 files changed, 3 insertions(+), 41 deletions(-) diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index 5af73f928766c16cd36010ca0d07c65ae5c5eb16..8e3d4ac45824ec69afb523f8f0e= 668327122cd02 100644 --- a/hw/vfio/platform.c +++ b/hw/vfio/platform.c @@ -529,12 +529,7 @@ static VFIODeviceOps vfio_platform_ops =3D { */ static int vfio_base_device_init(VFIODevice *vbasedev, Error **errp) { - VFIOGroup *group; - VFIODevice *vbasedev_iter; - char *tmp, group_path[PATH_MAX], *group_name; - ssize_t len; struct stat st; - int groupid; int ret; =20 /* @sysfsdev takes precedence over @host */ @@ -557,47 +552,15 @@ static int vfio_base_device_init(VFIODevice *vbasedev= , Error **errp) return -errno; } =20 - tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len < 0 || len >=3D sizeof(group_path)) { - ret =3D len < 0 ? -errno : -ENAMETOOLONG; - error_setg_errno(errp, -ret, "no iommu_group found"); - return ret; - } - - group_path[len] =3D 0; - - group_name =3D basename(group_path); - if (sscanf(group_name, "%d", &groupid) !=3D 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - return -errno; - } - - trace_vfio_platform_base_device_init(vbasedev->name, groupid); - - group =3D vfio_get_group(groupid, &address_space_memory, errp); - if (!group) { - return -ENOENT; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - return -EBUSY; - } - } - ret =3D vfio_get_device(group, vbasedev->name, vbasedev, errp); + ret =3D vfio_attach_device(vbasedev->name, vbasedev, + &address_space_memory, errp); if (ret) { - vfio_put_group(group); return ret; } =20 ret =3D vfio_populate_device(vbasedev, errp); if (ret) { - vfio_put_group(group); + vfio_detach_device(vbasedev); } =20 return ret; diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 8ac13eb106db68c4f547b1b3819f96272309a124..0eb2387cf24c920b0904ec4012b= 0fcd3f2e8b3cf 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -121,7 +121,6 @@ vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t s= ize, uint64_t bitmap_size vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu= dirty @ 0x%"PRIx64" - 0x%"PRIx64 =20 # platform.c -vfio_platform_base_device_init(char *name, int groupid) "%s belongs to gro= up #%d" vfio_platform_realize(char *name, char *compat) "vfio device %s, compat = =3D %s" vfio_platform_eoi(int pin, int fd) "EOI IRQ pin %d (fd=3D%d)" vfio_platform_intp_mmap_enable(int pin) "IRQ #%d still active, stay in slo= w path" --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573414683352.2016514190674; Thu, 5 Oct 2023 23:23:34 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD5-0005Ka-Qf; Fri, 06 Oct 2023 02:21:15 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCh-0005IL-Uv for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:52 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCf-00032w-Su for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:51 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywb6YJHz4xVK; Fri, 6 Oct 2023 17:20:47 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywY42Mvz4xS5; Fri, 6 Oct 2023 17:20:45 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Eric Auger , Yi Liu , Zhenzhong Duan , Matthew Rosato , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 15/21] vfio/ap: Use vfio_[attach/detach]_device Date: Fri, 6 Oct 2023 08:19:59 +0200 Message-ID: <20231006062005.1040296-16-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573415281100003 From: Eric Auger Let the vfio-ap device use vfio_attach_device() and vfio_detach_device(), hence hiding the details of the used IOMMU backend. We take the opportunity to use g_path_get_basename() which is prefered, as suggested by 3e015d815b ("use g_path_get_basename instead of basename") Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: Matthew Rosato Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/ap.c | 69 ++++++++++------------------------------------------ 1 file changed, 13 insertions(+), 56 deletions(-) diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c index 6e21d1da5a7090a6b9c77485d67e8eabc261438f..22e564f4f7f3ef52699a9447b5f= d7266901735cb 100644 --- a/hw/vfio/ap.c +++ b/hw/vfio/ap.c @@ -53,40 +53,6 @@ struct VFIODeviceOps vfio_ap_ops =3D { .vfio_compute_needs_reset =3D vfio_ap_compute_needs_reset, }; =20 -static void vfio_ap_put_device(VFIOAPDevice *vapdev) -{ - g_free(vapdev->vdev.name); - vfio_put_base_device(&vapdev->vdev); -} - -static VFIOGroup *vfio_ap_get_group(VFIOAPDevice *vapdev, Error **errp) -{ - GError *gerror =3D NULL; - char *symlink, *group_path; - int groupid; - - symlink =3D g_strdup_printf("%s/iommu_group", vapdev->vdev.sysfsdev); - group_path =3D g_file_read_link(symlink, &gerror); - g_free(symlink); - - if (!group_path) { - error_setg(errp, "%s: no iommu_group found for %s: %s", - TYPE_VFIO_AP_DEVICE, vapdev->vdev.sysfsdev, gerror->mes= sage); - g_error_free(gerror); - return NULL; - } - - if (sscanf(basename(group_path), "%d", &groupid) !=3D 1) { - error_setg(errp, "vfio: failed to read %s", group_path); - g_free(group_path); - return NULL; - } - - g_free(group_path); - - return vfio_get_group(groupid, &address_space_memory, errp); -} - static void vfio_ap_req_notifier_handler(void *opaque) { VFIOAPDevice *vapdev =3D opaque; @@ -189,22 +155,15 @@ static void vfio_ap_unregister_irq_notifier(VFIOAPDev= ice *vapdev, static void vfio_ap_realize(DeviceState *dev, Error **errp) { int ret; - char *mdevid; Error *err =3D NULL; - VFIOGroup *vfio_group; APDevice *apdev =3D AP_DEVICE(dev); VFIOAPDevice *vapdev =3D VFIO_AP_DEVICE(apdev); + VFIODevice *vbasedev =3D &vapdev->vdev; =20 - vfio_group =3D vfio_ap_get_group(vapdev, errp); - if (!vfio_group) { - return; - } - - vapdev->vdev.ops =3D &vfio_ap_ops; - vapdev->vdev.type =3D VFIO_DEVICE_TYPE_AP; - mdevid =3D basename(vapdev->vdev.sysfsdev); - vapdev->vdev.name =3D g_strdup_printf("%s", mdevid); - vapdev->vdev.dev =3D dev; + vbasedev->name =3D g_path_get_basename(vbasedev->sysfsdev); + vbasedev->ops =3D &vfio_ap_ops; + vbasedev->type =3D VFIO_DEVICE_TYPE_AP; + vbasedev->dev =3D dev; =20 /* * vfio-ap devices operate in a way compatible with discarding of @@ -214,9 +173,10 @@ static void vfio_ap_realize(DeviceState *dev, Error **= errp) */ vapdev->vdev.ram_block_discard_allowed =3D true; =20 - ret =3D vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp); + ret =3D vfio_attach_device(vbasedev->name, vbasedev, + &address_space_memory, errp); if (ret) { - goto out_get_dev_err; + goto error; } =20 vfio_ap_register_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX, &err); @@ -228,22 +188,19 @@ static void vfio_ap_realize(DeviceState *dev, Error *= *errp) error_report_err(err); } =20 - return; - -out_get_dev_err: - vfio_ap_put_device(vapdev); - vfio_put_group(vfio_group); +error: + error_prepend(errp, VFIO_MSG_PREFIX, vbasedev->name); + g_free(vbasedev->name); } =20 static void vfio_ap_unrealize(DeviceState *dev) { APDevice *apdev =3D AP_DEVICE(dev); VFIOAPDevice *vapdev =3D VFIO_AP_DEVICE(apdev); - VFIOGroup *group =3D vapdev->vdev.group; =20 vfio_ap_unregister_irq_notifier(vapdev, VFIO_AP_REQ_IRQ_INDEX); - vfio_ap_put_device(vapdev); - vfio_put_group(group); + vfio_detach_device(&vapdev->vdev); + g_free(vapdev->vdev.name); } =20 static Property vfio_ap_properties[] =3D { --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573630244482.873836561208; Thu, 5 Oct 2023 23:27:10 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD6-0005Lh-9t; Fri, 06 Oct 2023 02:21:16 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCo-0005J2-L6 for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:04 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCm-00033e-DS for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:20:58 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywf5gjqz4xVR; Fri, 6 Oct 2023 17:20:50 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywc39Q5z4xS5; Fri, 6 Oct 2023 17:20:48 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Eric Auger , Yi Liu , Zhenzhong Duan , Matthew Rosato , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 16/21] vfio/ccw: Use vfio_[attach/detach]_device Date: Fri, 6 Oct 2023 08:20:00 +0200 Message-ID: <20231006062005.1040296-17-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573631251100001 From: Eric Auger Let the vfio-ccw device use vfio_attach_device() and vfio_detach_device(), hence hiding the details of the used IOMMU backend. Note that the migration reduces the following trace "vfio: subchannel %s has already been attached" (featuring cssid.ssid.devid) into "device is already attached" Also now all the devices have been migrated to use the new vfio_attach_device/vfio_detach_device API, let's turn the legacy functions into static functions, local to container.c. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: Matthew Rosato Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 5 -- hw/vfio/ccw.c | 122 +++++++++------------------------- hw/vfio/common.c | 10 +-- 3 files changed, 37 insertions(+), 100 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 12fbfbc37d466abcd85a838f26567dc0add84de0..c486bdef2adfe77e02f80559005= d09426a7634bd 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -202,7 +202,6 @@ typedef struct { hwaddr pages; } VFIOBitmap; =20 -void vfio_put_base_device(VFIODevice *vbasedev); void vfio_disable_irqindex(VFIODevice *vbasedev, int index); void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index); @@ -220,11 +219,7 @@ void vfio_region_unmap(VFIORegion *region); void vfio_region_exit(VFIORegion *region); void vfio_region_finalize(VFIORegion *region); void vfio_reset_handler(void *opaque); -VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp); -void vfio_put_group(VFIOGroup *group); struct vfio_device_info *vfio_get_device_info(int fd); -int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp); int vfio_attach_device(char *name, VFIODevice *vbasedev, AddressSpace *as, Error **errp); void vfio_detach_device(VFIODevice *vbasedev); diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 1e2fce83b084675d90f42777a58eb95b47ccbbae..6ec35fedc9aea1ccde10098a725= 724faf079e4bb 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -572,88 +572,15 @@ static void vfio_ccw_put_region(VFIOCCWDevice *vcdev) g_free(vcdev->io_region); } =20 -static void vfio_ccw_put_device(VFIOCCWDevice *vcdev) -{ - g_free(vcdev->vdev.name); - vfio_put_base_device(&vcdev->vdev); -} - -static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev, - Error **errp) -{ - S390CCWDevice *cdev =3D S390_CCW_DEVICE(vcdev); - char *name =3D g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid, - cdev->hostid.ssid, - cdev->hostid.devid); - VFIODevice *vbasedev; - - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (strcmp(vbasedev->name, name) =3D=3D 0) { - error_setg(errp, "vfio: subchannel %s has already been attache= d", - name); - goto out_err; - } - } - - /* - * All vfio-ccw devices are believed to operate in a way compatible wi= th - * discarding of memory in RAM blocks, ie. pages pinned in the host are - * in the current working set of the guest driver and therefore never - * overlap e.g., with pages available to the guest balloon driver. Th= is - * needs to be set before vfio_get_device() for vfio common to handle - * ram_block_discard_disable(). - */ - vcdev->vdev.ram_block_discard_allowed =3D true; - - if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, errp)) { - goto out_err; - } - - vcdev->vdev.ops =3D &vfio_ccw_ops; - vcdev->vdev.type =3D VFIO_DEVICE_TYPE_CCW; - vcdev->vdev.name =3D name; - vcdev->vdev.dev =3D DEVICE(vcdev); - - return; - -out_err: - g_free(name); -} - -static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, Error **errp) -{ - char *tmp, group_path[PATH_MAX]; - ssize_t len; - int groupid; - - tmp =3D g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x/%s/iommu_grou= p", - cdev->hostid.cssid, cdev->hostid.ssid, - cdev->hostid.devid, cdev->mdevid); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <=3D 0 || len >=3D sizeof(group_path)) { - error_setg(errp, "vfio: no iommu_group found"); - return NULL; - } - - group_path[len] =3D 0; - - if (sscanf(basename(group_path), "%d", &groupid) !=3D 1) { - error_setg(errp, "vfio: failed to read %s", group_path); - return NULL; - } - - return vfio_get_group(groupid, &address_space_memory, errp); -} - static void vfio_ccw_realize(DeviceState *dev, Error **errp) { - VFIOGroup *group; S390CCWDevice *cdev =3D S390_CCW_DEVICE(dev); VFIOCCWDevice *vcdev =3D VFIO_CCW(cdev); S390CCWDeviceClass *cdc =3D S390_CCW_DEVICE_GET_CLASS(cdev); + VFIODevice *vbasedev =3D &vcdev->vdev; Error *err =3D NULL; + char *name; + int ret; =20 /* Call the class init function for subchannel. */ if (cdc->realize) { @@ -663,14 +590,31 @@ static void vfio_ccw_realize(DeviceState *dev, Error = **errp) } } =20 - group =3D vfio_ccw_get_group(cdev, &err); - if (!group) { - goto out_group_err; - } + name =3D g_strdup_printf("%x.%x.%04x", vcdev->cdev.hostid.cssid, + vcdev->cdev.hostid.ssid, + vcdev->cdev.hostid.devid); + vbasedev->sysfsdev =3D g_strdup_printf("/sys/bus/css/devices/%s/%s", + name, + cdev->mdevid); + vbasedev->ops =3D &vfio_ccw_ops; + vbasedev->type =3D VFIO_DEVICE_TYPE_CCW; + vbasedev->name =3D name; + vbasedev->dev =3D dev; =20 - vfio_ccw_get_device(group, vcdev, &err); - if (err) { - goto out_device_err; + /* + * All vfio-ccw devices are believed to operate in a way compatible wi= th + * discarding of memory in RAM blocks, ie. pages pinned in the host are + * in the current working set of the guest driver and therefore never + * overlap e.g., with pages available to the guest balloon driver. Th= is + * needs to be set before vfio_get_device() for vfio common to handle + * ram_block_discard_disable(). + */ + vbasedev->ram_block_discard_allowed =3D true; + + ret =3D vfio_attach_device(cdev->mdevid, vbasedev, + &address_space_memory, errp); + if (ret) { + goto out_attach_dev_err; } =20 vfio_ccw_get_region(vcdev, &err); @@ -708,10 +652,9 @@ out_irq_notifier_err: out_io_notifier_err: vfio_ccw_put_region(vcdev); out_region_err: - vfio_ccw_put_device(vcdev); -out_device_err: - vfio_put_group(group); -out_group_err: + vfio_detach_device(vbasedev); +out_attach_dev_err: + g_free(vbasedev->name); if (cdc->unrealize) { cdc->unrealize(cdev); } @@ -724,14 +667,13 @@ static void vfio_ccw_unrealize(DeviceState *dev) S390CCWDevice *cdev =3D S390_CCW_DEVICE(dev); VFIOCCWDevice *vcdev =3D VFIO_CCW(cdev); S390CCWDeviceClass *cdc =3D S390_CCW_DEVICE_GET_CLASS(cdev); - VFIOGroup *group =3D vcdev->vdev.group; =20 vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_REQ_IRQ_INDEX); vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_CRW_IRQ_INDEX); vfio_ccw_unregister_irq_notifier(vcdev, VFIO_CCW_IO_IRQ_INDEX); vfio_ccw_put_region(vcdev); - vfio_ccw_put_device(vcdev); - vfio_put_group(group); + vfio_detach_device(&vcdev->vdev); + g_free(vcdev->vdev.name); =20 if (cdc->unrealize) { cdc->unrealize(cdev); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index f4c33c9858f5cc2b8245a9725fd660e7898ee760..56cfe94d97779b539dbb15d88f2= 968c377d16bae 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -2335,7 +2335,7 @@ static void vfio_disconnect_container(VFIOGroup *grou= p) } } =20 -VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp) +static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **er= rp) { VFIOGroup *group; char path[32]; @@ -2402,7 +2402,7 @@ free_group_exit: return NULL; } =20 -void vfio_put_group(VFIOGroup *group) +static void vfio_put_group(VFIOGroup *group) { if (!group || !QLIST_EMPTY(&group->device_list)) { return; @@ -2447,8 +2447,8 @@ retry: return info; } =20 -int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp) +static int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev, Error **errp) { g_autofree struct vfio_device_info *info =3D NULL; int fd; @@ -2506,7 +2506,7 @@ int vfio_get_device(VFIOGroup *group, const char *nam= e, return 0; } =20 -void vfio_put_base_device(VFIODevice *vbasedev) +static void vfio_put_base_device(VFIODevice *vbasedev) { if (!vbasedev->group) { return; --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573375868616.0172175614748; Thu, 5 Oct 2023 23:22:55 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD9-0005O9-AQ; Fri, 06 Oct 2023 02:21:19 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCz-0005KJ-Tq for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:14 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCx-00033y-DY for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:08 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywj2w8qz4xVT; Fri, 6 Oct 2023 17:20:53 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywg2GWTz4xS5; Fri, 6 Oct 2023 17:20:51 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Zhenzhong Duan , Eric Auger , Yi Liu , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 17/21] vfio/common: Move VFIO reset handler registration to a group agnostic function Date: Fri, 6 Oct 2023 08:20:01 +0200 Message-ID: <20231006062005.1040296-18-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573376761100001 From: Zhenzhong Duan Move the reset handler registration/unregistration to a place that is not group specific. vfio_[get/put]_address_space are the best places for that purpose. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- hw/vfio/common.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 56cfe94d97779b539dbb15d88f2968c377d16bae..019da387d239cd005ab38577a68= f35a013c98587 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1909,6 +1909,10 @@ static VFIOAddressSpace *vfio_get_address_space(Addr= essSpace *as) space->as =3D as; QLIST_INIT(&space->containers); =20 + if (QLIST_EMPTY(&vfio_address_spaces)) { + qemu_register_reset(vfio_reset_handler, NULL); + } + QLIST_INSERT_HEAD(&vfio_address_spaces, space, list); =20 return space; @@ -1920,6 +1924,9 @@ static void vfio_put_address_space(VFIOAddressSpace *= space) QLIST_REMOVE(space, list); g_free(space); } + if (QLIST_EMPTY(&vfio_address_spaces)) { + qemu_unregister_reset(vfio_reset_handler, NULL); + } } =20 /* @@ -2385,10 +2392,6 @@ static VFIOGroup *vfio_get_group(int groupid, Addres= sSpace *as, Error **errp) goto close_fd_exit; } =20 - if (QLIST_EMPTY(&vfio_group_list)) { - qemu_register_reset(vfio_reset_handler, NULL); - } - QLIST_INSERT_HEAD(&vfio_group_list, group, next); =20 return group; @@ -2417,10 +2420,6 @@ static void vfio_put_group(VFIOGroup *group) trace_vfio_put_group(group->fd); close(group->fd); g_free(group); - - if (QLIST_EMPTY(&vfio_group_list)) { - qemu_unregister_reset(vfio_reset_handler, NULL); - } } =20 struct vfio_device_info *vfio_get_device_info(int fd) --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573385908794.1684137142214; Thu, 5 Oct 2023 23:23:05 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD5-0005Km-Rg; Fri, 06 Oct 2023 02:21:15 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCq-0005J4-NL for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:04 -0400 Received: from mail.ozlabs.org ([2404:9400:2221:ea00::3] helo=gandalf.ozlabs.org) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCo-00034L-AQ for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:00 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywl5QJ4z4xVV; Fri, 6 Oct 2023 17:20:55 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywj6cCQz4xS5; Fri, 6 Oct 2023 17:20:53 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Zhenzhong Duan , Eric Auger , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 18/21] vfio/common: Introduce a per container device list Date: Fri, 6 Oct 2023 08:20:02 +0200 Message-ID: <20231006062005.1040296-19-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2404:9400:2221:ea00::3; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -39 X-Spam_score: -4.0 X-Spam_bar: ---- X-Spam_report: (-4.0 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, RCVD_IN_DNSWL_MED=-2.3, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573387048100002 From: Zhenzhong Duan Several functions need to iterate over the VFIO devices attached to a given container. This is currently achieved by iterating over the groups attached to the container and then over the devices in the group. Let's introduce a per container device list that simplifies this search. Per container list is used in below functions: vfio_devices_all_dirty_tracking vfio_devices_all_device_dirty_tracking vfio_devices_all_running_and_mig_active vfio_devices_dma_logging_stop vfio_devices_dma_logging_start vfio_devices_query_dirty_bitmap This will also ease the migration of IOMMUFD by hiding the group specificity. Suggested-by: Alex Williamson Signed-off-by: Zhenzhong Duan Signed-off-by: Eric Auger Reviewed-by: C=C3=A9dric Le Goater Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 2 + hw/vfio/common.c | 141 +++++++++++++++------------------- 2 files changed, 65 insertions(+), 78 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index c486bdef2adfe77e02f80559005d09426a7634bd..8ca70dd82156e25610fe9691784= 3f334549818fe 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -98,6 +98,7 @@ typedef struct VFIOContainer { QLIST_HEAD(, VFIOGroup) group_list; QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; QLIST_ENTRY(VFIOContainer) next; + QLIST_HEAD(, VFIODevice) device_list; } VFIOContainer; =20 typedef struct VFIOGuestIOMMU { @@ -129,6 +130,7 @@ typedef struct VFIODeviceOps VFIODeviceOps; =20 typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; + QLIST_ENTRY(VFIODevice) container_next; struct VFIOGroup *group; char *sysfsdev; char *name; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 019da387d239cd005ab38577a68f35a013c98587..ef9dc7c74713f113a459db61aad= 7a017e21cf99a 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -218,7 +218,6 @@ bool vfio_device_state_is_precopy(VFIODevice *vbasedev) =20 static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) { - VFIOGroup *group; VFIODevice *vbasedev; MigrationState *ms =3D migrate_get_current(); =20 @@ -227,19 +226,17 @@ static bool vfio_devices_all_dirty_tracking(VFIOConta= iner *container) return false; } =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration =3D vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration =3D vbasedev->migration; =20 - if (!migration) { - return false; - } + if (!migration) { + return false; + } =20 - if (vbasedev->pre_copy_dirty_page_tracking =3D=3D ON_OFF_AUTO_= OFF && - (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev))) { - return false; - } + if (vbasedev->pre_copy_dirty_page_tracking =3D=3D ON_OFF_AUTO_OFF = && + (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev))) { + return false; } } return true; @@ -247,14 +244,11 @@ static bool vfio_devices_all_dirty_tracking(VFIOConta= iner *container) =20 static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *containe= r) { - VFIOGroup *group; VFIODevice *vbasedev; =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_pages_supported) { - return false; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_pages_supported) { + return false; } } =20 @@ -267,27 +261,24 @@ static bool vfio_devices_all_device_dirty_tracking(VF= IOContainer *container) */ static bool vfio_devices_all_running_and_mig_active(VFIOContainer *contain= er) { - VFIOGroup *group; VFIODevice *vbasedev; =20 if (!migration_is_active(migrate_get_current())) { return false; } =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - VFIOMigration *migration =3D vbasedev->migration; + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + VFIOMigration *migration =3D vbasedev->migration; =20 - if (!migration) { - return false; - } + if (!migration) { + return false; + } =20 - if (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev)) { - continue; - } else { - return false; - } + if (vfio_device_state_is_running(vbasedev) || + vfio_device_state_is_precopy(vbasedev)) { + continue; + } else { + return false; } } return true; @@ -1187,20 +1178,17 @@ static bool vfio_section_is_vfio_pci(MemoryRegionSe= ction *section, { VFIOPCIDevice *pcidev; VFIODevice *vbasedev; - VFIOGroup *group; Object *owner; =20 owner =3D memory_region_owner(section->mr); =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { - continue; - } - pcidev =3D container_of(vbasedev, VFIOPCIDevice, vbasedev); - if (OBJECT(pcidev) =3D=3D owner) { - return true; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->type !=3D VFIO_DEVICE_TYPE_PCI) { + continue; + } + pcidev =3D container_of(vbasedev, VFIOPCIDevice, vbasedev); + if (OBJECT(pcidev) =3D=3D owner) { + return true; } } =20 @@ -1296,24 +1284,21 @@ static void vfio_devices_dma_logging_stop(VFIOConta= iner *container) sizeof(uint64_t))] =3D {}; struct vfio_device_feature *feature =3D (struct vfio_device_feature *)= buf; VFIODevice *vbasedev; - VFIOGroup *group; =20 feature->argsz =3D sizeof(buf); feature->flags =3D VFIO_DEVICE_FEATURE_SET | VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP; =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (!vbasedev->dirty_tracking) { - continue; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (!vbasedev->dirty_tracking) { + continue; + } =20 - if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { - warn_report("%s: Failed to stop DMA logging, err %d (%s)", - vbasedev->name, -errno, strerror(errno)); - } - vbasedev->dirty_tracking =3D false; + if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { + warn_report("%s: Failed to stop DMA logging, err %d (%s)", + vbasedev->name, -errno, strerror(errno)); } + vbasedev->dirty_tracking =3D false; } } =20 @@ -1396,7 +1381,6 @@ static int vfio_devices_dma_logging_start(VFIOContain= er *container) struct vfio_device_feature *feature; VFIODirtyRanges ranges; VFIODevice *vbasedev; - VFIOGroup *group; int ret =3D 0; =20 vfio_dirty_tracking_init(container, &ranges); @@ -1406,21 +1390,19 @@ static int vfio_devices_dma_logging_start(VFIOConta= iner *container) return -errno; } =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dirty_tracking) { - continue; - } + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + if (vbasedev->dirty_tracking) { + continue; + } =20 - ret =3D ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); - if (ret) { - ret =3D -errno; - error_report("%s: Failed to start DMA logging, err %d (%s)= ", - vbasedev->name, ret, strerror(errno)); - goto out; - } - vbasedev->dirty_tracking =3D true; + ret =3D ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); + if (ret) { + ret =3D -errno; + error_report("%s: Failed to start DMA logging, err %d (%s)", + vbasedev->name, ret, strerror(errno)); + goto out; } + vbasedev->dirty_tracking =3D true; } =20 out: @@ -1500,21 +1482,18 @@ static int vfio_devices_query_dirty_bitmap(VFIOCont= ainer *container, hwaddr size) { VFIODevice *vbasedev; - VFIOGroup *group; int ret; =20 - QLIST_FOREACH(group, &container->group_list, container_next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - ret =3D vfio_device_dma_logging_report(vbasedev, iova, size, - vbmap->bitmap); - if (ret) { - error_report("%s: Failed to get DMA logging report, iova: " - "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx - ", err: %d (%s)", - vbasedev->name, iova, size, ret, strerror(-re= t)); + QLIST_FOREACH(vbasedev, &container->device_list, container_next) { + ret =3D vfio_device_dma_logging_report(vbasedev, iova, size, + vbmap->bitmap); + if (ret) { + error_report("%s: Failed to get DMA logging report, iova: " + "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx + ", err: %d (%s)", + vbasedev->name, iova, size, ret, strerror(-ret)); =20 - return ret; - } + return ret; } } =20 @@ -2648,6 +2627,7 @@ int vfio_attach_device(char *name, VFIODevice *vbased= ev, int groupid =3D vfio_device_groupid(vbasedev, errp); VFIODevice *vbasedev_iter; VFIOGroup *group; + VFIOContainer *container; int ret; =20 if (groupid < 0) { @@ -2671,8 +2651,12 @@ int vfio_attach_device(char *name, VFIODevice *vbase= dev, ret =3D vfio_get_device(group, name, vbasedev, errp); if (ret) { vfio_put_group(group); + return ret; } =20 + container =3D group->container; + QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); + return ret; } =20 @@ -2680,6 +2664,7 @@ void vfio_detach_device(VFIODevice *vbasedev) { VFIOGroup *group =3D vbasedev->group; =20 + QLIST_REMOVE(vbasedev, container_next); trace_vfio_detach_device(vbasedev->name, group->groupid); vfio_put_base_device(vbasedev); vfio_put_group(group); --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573364276510.83552089149475; Thu, 5 Oct 2023 23:22:44 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD9-0005OA-Gp; Fri, 06 Oct 2023 02:21:19 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeD5-0005Kj-IQ for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:15 -0400 Received: from gandalf.ozlabs.org ([150.107.74.76]) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeD0-00034j-3J for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:14 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywp0pQlz4xVW; Fri, 6 Oct 2023 17:20:58 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywm20vgz4xS5; Fri, 6 Oct 2023 17:20:56 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Zhenzhong Duan , Eric Auger , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 19/21] vfio/common: Store the parent container in VFIODevice Date: Fri, 6 Oct 2023 08:20:03 +0200 Message-ID: <20231006062005.1040296-20-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=150.107.74.76; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -16 X-Spam_score: -1.7 X-Spam_bar: - X-Spam_report: (-1.7 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=no autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573364474100001 From: Zhenzhong Duan let's store the parent contaienr within the VFIODevice. This simplifies the logic in vfio_viommu_preset() and brings the benefice to hide the group specificity which is useful for IOMMUFD migration. Signed-off-by: Eric Auger Signed-off-by: Zhenzhong Duan [ clg: Add test on !vbasedev->container in vfio_detach_device() ] Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 1 + hw/vfio/common.c | 8 +++++++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 8ca70dd82156e25610fe96917843f334549818fe..bf12e406676e5577ad9454152ae= c9340666241dc 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -132,6 +132,7 @@ typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; QLIST_ENTRY(VFIODevice) container_next; struct VFIOGroup *group; + VFIOContainer *container; char *sysfsdev; char *name; DeviceState *dev; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index ef9dc7c74713f113a459db61aad7a017e21cf99a..55f8a113ea82afeb9620d46286f= 04f85dd9e8b54 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -184,7 +184,7 @@ void vfio_unblock_multiple_devices_migration(void) =20 bool vfio_viommu_preset(VFIODevice *vbasedev) { - return vbasedev->group->container->space->as !=3D &address_space_memor= y; + return vbasedev->container->space->as !=3D &address_space_memory; } =20 static void vfio_set_migration_error(int err) @@ -2655,6 +2655,7 @@ int vfio_attach_device(char *name, VFIODevice *vbased= ev, } =20 container =3D group->container; + vbasedev->container =3D container; QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); =20 return ret; @@ -2664,7 +2665,12 @@ void vfio_detach_device(VFIODevice *vbasedev) { VFIOGroup *group =3D vbasedev->group; =20 + if (!vbasedev->container) { + return; + } + QLIST_REMOVE(vbasedev, container_next); + vbasedev->container =3D NULL; trace_vfio_detach_device(vbasedev->name, group->groupid); vfio_put_base_device(vbasedev); vfio_put_group(group); --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573413535626.3746915046223; Thu, 5 Oct 2023 23:23:33 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD9-0005OB-Te; Fri, 06 Oct 2023 02:21:19 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCw-0005Jk-SY for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:08 -0400 Received: from mail.ozlabs.org ([2404:9400:2221:ea00::3] helo=gandalf.ozlabs.org) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCt-000355-KR for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:06 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywr3LTRz4xVm; Fri, 6 Oct 2023 17:21:00 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1ywp4X2lz4xS5; Fri, 6 Oct 2023 17:20:58 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Zhenzhong Duan , Eric Auger , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 20/21] vfio/common: Introduce a global VFIODevice list Date: Fri, 6 Oct 2023 08:20:04 +0200 Message-ID: <20231006062005.1040296-21-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2404:9400:2221:ea00::3; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -39 X-Spam_score: -4.0 X-Spam_bar: ---- X-Spam_report: (-4.0 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, RCVD_IN_DNSWL_MED=-2.3, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573415293100004 From: Zhenzhong Duan Some functions iterate over all the VFIODevices. This is currently achieved by iterating over all groups/devices. Let's introduce a global list of VFIODevices simplifying that scan. This will also be useful while migrating to IOMMUFD by hiding the group specificity. Signed-off-by: Eric Auger Signed-off-by: Zhenzhong Duan Suggested-by: Alex Williamson Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 2 ++ hw/vfio/common.c | 45 +++++++++++++++-------------------- 2 files changed, 21 insertions(+), 26 deletions(-) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index bf12e406676e5577ad9454152aec9340666241dc..54905b9dd4bbb0b2c8bc9b3ee23= 2e539a9a46216 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -131,6 +131,7 @@ typedef struct VFIODeviceOps VFIODeviceOps; typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next; QLIST_ENTRY(VFIODevice) container_next; + QLIST_ENTRY(VFIODevice) global_next; struct VFIOGroup *group; VFIOContainer *container; char *sysfsdev; @@ -232,6 +233,7 @@ int vfio_kvm_device_del_fd(int fd, Error **errp); =20 extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; +typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; extern VFIOGroupList vfio_group_list; =20 bool vfio_mig_active(void); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 55f8a113ea82afeb9620d46286f04f85dd9e8b54..95bc50bcda4c44612cda2b0d8e9= d5782e31ea4c6 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -48,6 +48,8 @@ =20 VFIOGroupList vfio_group_list =3D QLIST_HEAD_INITIALIZER(vfio_group_list); +static VFIODeviceList vfio_device_list =3D + QLIST_HEAD_INITIALIZER(vfio_device_list); static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces =3D QLIST_HEAD_INITIALIZER(vfio_address_spaces); =20 @@ -94,18 +96,15 @@ static int vfio_get_dirty_bitmap(VFIOContainer *contain= er, uint64_t iova, =20 bool vfio_mig_active(void) { - VFIOGroup *group; VFIODevice *vbasedev; =20 - if (QLIST_EMPTY(&vfio_group_list)) { + if (QLIST_EMPTY(&vfio_device_list)) { return false; } =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration_blocker) { - return false; - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration_blocker) { + return false; } } return true; @@ -120,19 +119,16 @@ static Error *multiple_devices_migration_blocker; */ static bool vfio_multiple_devices_migration_is_supported(void) { - VFIOGroup *group; VFIODevice *vbasedev; unsigned int device_num =3D 0; bool all_support_p2p =3D true; =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->migration) { - device_num++; + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->migration) { + device_num++; =20 - if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)= ) { - all_support_p2p =3D false; - } + if (!(vbasedev->migration->mig_flags & VFIO_MIGRATION_P2P)) { + all_support_p2p =3D false; } } } @@ -1777,22 +1773,17 @@ bool vfio_get_info_dma_avail(struct vfio_iommu_type= 1_info *info, =20 void vfio_reset_handler(void *opaque) { - VFIOGroup *group; VFIODevice *vbasedev; =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized) { - vbasedev->ops->vfio_compute_needs_reset(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized) { + vbasedev->ops->vfio_compute_needs_reset(vbasedev); } } =20 - QLIST_FOREACH(group, &vfio_group_list, next) { - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (vbasedev->dev->realized && vbasedev->needs_reset) { - vbasedev->ops->vfio_hot_reset_multi(vbasedev); - } + QLIST_FOREACH(vbasedev, &vfio_device_list, next) { + if (vbasedev->dev->realized && vbasedev->needs_reset) { + vbasedev->ops->vfio_hot_reset_multi(vbasedev); } } } @@ -2657,6 +2648,7 @@ int vfio_attach_device(char *name, VFIODevice *vbased= ev, container =3D group->container; vbasedev->container =3D container; QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); + QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next); =20 return ret; } @@ -2669,6 +2661,7 @@ void vfio_detach_device(VFIODevice *vbasedev) return; } =20 + QLIST_REMOVE(vbasedev, global_next); QLIST_REMOVE(vbasedev, container_next); vbasedev->container =3D NULL; trace_vfio_detach_device(vbasedev->name, group->groupid); --=20 2.41.0 From nobody Sat May 18 18:01:55 2024 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1696573594387191.15591945393828; Thu, 5 Oct 2023 23:26:34 -0700 (PDT) Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qoeD6-0005Ll-St; Fri, 06 Oct 2023 02:21:16 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeD4-0005KS-No for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:14 -0400 Received: from mail.ozlabs.org ([2404:9400:2221:ea00::3] helo=gandalf.ozlabs.org) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qoeCx-00035P-Qc for qemu-devel@nongnu.org; Fri, 06 Oct 2023 02:21:12 -0400 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by gandalf.ozlabs.org (Postfix) with ESMTP id 4S1ywv2Yqxz4xVq; Fri, 6 Oct 2023 17:21:03 +1100 (AEDT) Received: from authenticated.ozlabs.org (localhost [127.0.0.1]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by mail.ozlabs.org (Postfix) with ESMTPSA id 4S1yws02H6z4xS5; Fri, 6 Oct 2023 17:21:00 +1100 (AEDT) From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= To: qemu-devel@nongnu.org Cc: Alex Williamson , Yi Liu , Eric Auger , Zhenzhong Duan , =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Subject: [PULL 21/21] vfio/common: Move legacy VFIO backend code into separate container.c Date: Fri, 6 Oct 2023 08:20:05 +0200 Message-ID: <20231006062005.1040296-22-clg@redhat.com> X-Mailer: git-send-email 2.41.0 In-Reply-To: <20231006062005.1040296-1-clg@redhat.com> References: <20231006062005.1040296-1-clg@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=2404:9400:2221:ea00::3; envelope-from=SRS0=cI0A=FU=redhat.com=clg@ozlabs.org; helo=gandalf.ozlabs.org X-Spam_score_int: -39 X-Spam_score: -4.0 X-Spam_bar: ---- X-Spam_report: (-4.0 / 5.0 requ) BAYES_00=-1.9, HEADER_FROM_DIFFERENT_DOMAINS=0.25, RCVD_IN_DNSWL_MED=-2.3, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: qemu-devel-bounces+importer=patchew.org@nongnu.org X-ZM-MESSAGEID: 1696573594700100001 From: Yi Liu Move all the code really dependent on the legacy VFIO container/group into a separate file: container.c. What does remain in common.c is the code related to VFIOAddressSpace, MemoryListeners, migration and all other general operations. Signed-off-by: Eric Auger Signed-off-by: Yi Liu Signed-off-by: Zhenzhong Duan Reviewed-by: C=C3=A9dric Le Goater [ clg: Add test on !vbasedev->container in vfio_detach_device() ] Signed-off-by: C=C3=A9dric Le Goater --- include/hw/vfio/vfio-common.h | 35 + hw/vfio/common.c | 1155 +------------------------------- hw/vfio/container.c | 1161 +++++++++++++++++++++++++++++++++ hw/vfio/meson.build | 1 + 4 files changed, 1213 insertions(+), 1139 deletions(-) create mode 100644 hw/vfio/container.c diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 54905b9dd4bbb0b2c8bc9b3ee232e539a9a46216..7780b9073a6c71d2aa5e2c5d157= 935c5805ba2f8 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -206,6 +206,30 @@ typedef struct { hwaddr pages; } VFIOBitmap; =20 +void vfio_host_win_add(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova, + uint64_t iova_pgsizes); +int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova); +VFIOAddressSpace *vfio_get_address_space(AddressSpace *as); +void vfio_put_address_space(VFIOAddressSpace *space); +bool vfio_devices_all_running_and_saving(VFIOContainer *container); + +/* container->fd */ +int vfio_dma_unmap(VFIOContainer *container, hwaddr iova, + ram_addr_t size, IOMMUTLBEntry *iotlb); +int vfio_dma_map(VFIOContainer *container, hwaddr iova, + ram_addr_t size, void *vaddr, bool readonly); +int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start); +int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, + hwaddr iova, hwaddr size); + +int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp); +void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section); + void vfio_disable_irqindex(VFIODevice *vbasedev, int index); void vfio_unmask_single_irqindex(VFIODevice *vbasedev, int index); void vfio_mask_single_irqindex(VFIODevice *vbasedev, int index); @@ -235,6 +259,10 @@ extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList; typedef QLIST_HEAD(VFIODeviceList, VFIODevice) VFIODeviceList; extern VFIOGroupList vfio_group_list; +extern VFIODeviceList vfio_device_list; + +extern const MemoryListener vfio_memory_listener; +extern int vfio_kvm_device_fd; =20 bool vfio_mig_active(void); int vfio_block_multiple_devices_migration(VFIODevice *vbasedev, Error **er= rp); @@ -272,4 +300,11 @@ bool vfio_migration_realize(VFIODevice *vbasedev, Erro= r **errp); void vfio_migration_exit(VFIODevice *vbasedev); =20 int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); +bool vfio_devices_all_running_and_mig_active(VFIOContainer *container); +bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container); +int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size); +int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr); #endif /* HW_VFIO_VFIO_COMMON_H */ diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 95bc50bcda4c44612cda2b0d8e9d5782e31ea4c6..9e61de03ee0ee611264ab9943d8= e5abc1320c766 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -46,9 +46,7 @@ #include "migration/qemu-file.h" #include "sysemu/tpm.h" =20 -VFIOGroupList vfio_group_list =3D - QLIST_HEAD_INITIALIZER(vfio_group_list); -static VFIODeviceList vfio_device_list =3D +VFIODeviceList vfio_device_list =3D QLIST_HEAD_INITIALIZER(vfio_device_list); static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spaces =3D QLIST_HEAD_INITIALIZER(vfio_address_spaces); @@ -61,39 +59,13 @@ static QLIST_HEAD(, VFIOAddressSpace) vfio_address_spac= es =3D * initialized, this file descriptor is only released on QEMU exit and * we'll re-use it should another vfio device be attached before then. */ -static int vfio_kvm_device_fd =3D -1; +int vfio_kvm_device_fd =3D -1; #endif =20 -static int vfio_ram_block_discard_disable(VFIOContainer *container, bool s= tate) -{ - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - /* - * We support coordinated discarding of RAM via the RamDiscardMana= ger. - */ - return ram_block_uncoordinated_discard_disable(state); - default: - /* - * VFIO_SPAPR_TCE_IOMMU most probably works just fine with - * RamDiscardManager, however, it is completely untested. - * - * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does - * completely the opposite of managing mapping/pinning dynamically= as - * required by RamDiscardManager. We would have to special-case se= ctions - * with a RamDiscardManager. - */ - return ram_block_discard_disable(state); - } -} - /* * Device state interfaces */ =20 -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr); - bool vfio_mig_active(void) { VFIODevice *vbasedev; @@ -238,7 +210,7 @@ static bool vfio_devices_all_dirty_tracking(VFIOContain= er *container) return true; } =20 -static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *containe= r) +bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) { VFIODevice *vbasedev; =20 @@ -255,7 +227,7 @@ static bool vfio_devices_all_device_dirty_tracking(VFIO= Container *container) * Check if all VFIO devices are running and migration is active, which is * essentially equivalent to the migration being in pre-copy phase. */ -static bool vfio_devices_all_running_and_mig_active(VFIOContainer *contain= er) +bool vfio_devices_all_running_and_mig_active(VFIOContainer *container) { VFIODevice *vbasedev; =20 @@ -280,150 +252,8 @@ static bool vfio_devices_all_running_and_mig_active(V= FIOContainer *container) return true; } =20 -static int vfio_dma_unmap_bitmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap *unmap; - struct vfio_bitmap *bitmap; - VFIOBitmap vbmap; - int ret; - - ret =3D vfio_bitmap_alloc(&vbmap, size); - if (ret) { - return ret; - } - - unmap =3D g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); - - unmap->argsz =3D sizeof(*unmap) + sizeof(*bitmap); - unmap->iova =3D iova; - unmap->size =3D size; - unmap->flags |=3D VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP; - bitmap =3D (struct vfio_bitmap *)&unmap->data; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsi= ze - * to qemu_real_host_page_size. - */ - bitmap->pgsize =3D qemu_real_host_page_size(); - bitmap->size =3D vbmap.size; - bitmap->data =3D (__u64 *)vbmap.bitmap; - - if (vbmap.size > container->max_dirty_bitmap_size) { - error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size= ); - ret =3D -E2BIG; - goto unmap_exit; - } - - ret =3D ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); - if (!ret) { - cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, - iotlb->translated_addr, vbmap.pages); - } else { - error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); - } - -unmap_exit: - g_free(unmap); - g_free(vbmap.bitmap); - - return ret; -} - -/* - * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 - */ -static int vfio_dma_unmap(VFIOContainer *container, - hwaddr iova, ram_addr_t size, - IOMMUTLBEntry *iotlb) -{ - struct vfio_iommu_type1_dma_unmap unmap =3D { - .argsz =3D sizeof(unmap), - .flags =3D 0, - .iova =3D iova, - .size =3D size, - }; - bool need_dirty_sync =3D false; - int ret; - - if (iotlb && vfio_devices_all_running_and_mig_active(container)) { - if (!vfio_devices_all_device_dirty_tracking(container) && - container->dirty_pages_supported) { - return vfio_dma_unmap_bitmap(container, iova, size, iotlb); - } - - need_dirty_sync =3D true; - } - - while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { - /* - * The type1 backend has an off-by-one bug in the kernel (71a7d3d7= 8e3c - * v4.15) where an overflow in its wrap-around check prevents us f= rom - * unmapping the last page of the address space. Test for the err= or - * condition and re-try the unmap excluding the last page. The - * expectation is that we've never mapped the last page anyway and= this - * unmap request comes via vIOMMU support which also makes it unli= kely - * that this page is used. This bug was introduced well after typ= e1 v2 - * support was introduced, so we shouldn't need to test for v1. A= fix - * is queued for kernel v5.0 so this workaround can be removed once - * affected kernels are sufficiently deprecated. - */ - if (errno =3D=3D EINVAL && unmap.size && !(unmap.iova + unmap.size= ) && - container->iommu_type =3D=3D VFIO_TYPE1v2_IOMMU) { - trace_vfio_dma_unmap_overflow_workaround(); - unmap.size -=3D 1ULL << ctz64(container->pgsizes); - continue; - } - error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); - return -errno; - } - - if (need_dirty_sync) { - ret =3D vfio_get_dirty_bitmap(container, iova, size, - iotlb->translated_addr); - if (ret) { - return ret; - } - } - - return 0; -} - -static int vfio_dma_map(VFIOContainer *container, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly) -{ - struct vfio_iommu_type1_dma_map map =3D { - .argsz =3D sizeof(map), - .flags =3D VFIO_DMA_MAP_FLAG_READ, - .vaddr =3D (__u64)(uintptr_t)vaddr, - .iova =3D iova, - .size =3D size, - }; - - if (!readonly) { - map.flags |=3D VFIO_DMA_MAP_FLAG_WRITE; - } - - /* - * Try the mapping, if it fails with EBUSY, unmap the region and try - * again. This shouldn't be necessary, but we sometimes see it in - * the VGA ROM space. - */ - if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0 || - (errno =3D=3D EBUSY && vfio_dma_unmap(container, iova, size, NULL)= =3D=3D 0 && - ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0)) { - return 0; - } - - error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); - return -errno; -} - -static void vfio_host_win_add(VFIOContainer *container, - hwaddr min_iova, hwaddr max_iova, - uint64_t iova_pgsizes) +void vfio_host_win_add(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova, uint64_t iova_pgsizes) { VFIOHostDMAWindow *hostwin; =20 @@ -444,8 +274,8 @@ static void vfio_host_win_add(VFIOContainer *container, QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next); } =20 -static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, - hwaddr max_iova) +int vfio_host_win_del(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova) { VFIOHostDMAWindow *hostwin; =20 @@ -794,92 +624,6 @@ static bool vfio_get_section_iova_range(VFIOContainer = *container, return true; } =20 -static int vfio_container_add_section_window(VFIOContainer *container, - MemoryRegionSection *section, - Error **errp) -{ - VFIOHostDMAWindow *hostwin; - hwaddr pgsize =3D 0; - int ret; - - if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { - return 0; - } - - /* For now intersections are not allowed, we may relax this later */ - QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { - if (ranges_overlap(hostwin->min_iova, - hostwin->max_iova - hostwin->min_iova + 1, - section->offset_within_address_space, - int128_get64(section->size))) { - error_setg(errp, - "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" - "host DMA window [0x%"PRIx64",0x%"PRIx64"]", - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, - hostwin->min_iova, hostwin->max_iova); - return -EINVAL; - } - } - - ret =3D vfio_spapr_create_window(container, section, &pgsize); - if (ret) { - error_setg_errno(errp, -ret, "Failed to create SPAPR window"); - return ret; - } - - vfio_host_win_add(container, section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1, pgsize); -#ifdef CONFIG_KVM - if (kvm_enabled()) { - VFIOGroup *group; - IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->mr); - struct kvm_vfio_spapr_tce param; - struct kvm_device_attr attr =3D { - .group =3D KVM_DEV_VFIO_GROUP, - .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, - .addr =3D (uint64_t)(unsigned long)¶m, - }; - - if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_F= D, - ¶m.tablefd)) { - QLIST_FOREACH(group, &container->group_list, container_next) { - param.groupfd =3D group->fd; - if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr))= { - error_setg_errno(errp, errno, - "vfio: failed GROUP_SET_SPAPR_TCE for= " - "KVM VFIO device %d and group fd %d", - param.tablefd, param.groupfd); - return -errno; - } - trace_vfio_spapr_group_attach(param.groupfd, param.tablefd= ); - } - } - } -#endif - return 0; -} - -static void vfio_container_del_section_window(VFIOContainer *container, - MemoryRegionSection *section) -{ - if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { - return; - } - - vfio_spapr_remove_window(container, - section->offset_within_address_space); - if (vfio_host_win_del(container, - section->offset_within_address_space, - section->offset_within_address_space + - int128_get64(section->size) - 1) < 0) { - hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, - __func__, section->offset_within_address_space); - } -} - static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -1127,33 +871,6 @@ static void vfio_listener_region_del(MemoryListener *= listener, vfio_container_del_section_window(container, section); } =20 -static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool sta= rt) -{ - int ret; - struct vfio_iommu_type1_dirty_bitmap dirty =3D { - .argsz =3D sizeof(dirty), - }; - - if (!container->dirty_pages_supported) { - return 0; - } - - if (start) { - dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_START; - } else { - dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP; - } - - ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); - if (ret) { - ret =3D -errno; - error_report("Failed to set dirty tracking flag 0x%x errno: %d", - dirty.flags, errno); - } - - return ret; -} - typedef struct VFIODirtyRanges { hwaddr min32; hwaddr max32; @@ -1473,9 +1190,9 @@ static int vfio_device_dma_logging_report(VFIODevice = *vbasedev, hwaddr iova, return 0; } =20 -static int vfio_devices_query_dirty_bitmap(VFIOContainer *container, - VFIOBitmap *vbmap, hwaddr iova, - hwaddr size) +int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size) { VFIODevice *vbasedev; int ret; @@ -1496,45 +1213,8 @@ static int vfio_devices_query_dirty_bitmap(VFIOConta= iner *container, return 0; } =20 -static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *v= bmap, - hwaddr iova, hwaddr size) -{ - struct vfio_iommu_type1_dirty_bitmap *dbitmap; - struct vfio_iommu_type1_dirty_bitmap_get *range; - int ret; - - dbitmap =3D g_malloc0(sizeof(*dbitmap) + sizeof(*range)); - - dbitmap->argsz =3D sizeof(*dbitmap) + sizeof(*range); - dbitmap->flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP; - range =3D (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data; - range->iova =3D iova; - range->size =3D size; - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pg= size - * to qemu_real_host_page_size. - */ - range->bitmap.pgsize =3D qemu_real_host_page_size(); - range->bitmap.size =3D vbmap->size; - range->bitmap.data =3D (__u64 *)vbmap->bitmap; - - ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); - if (ret) { - ret =3D -errno; - error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 - " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, - (uint64_t)range->size, errno); - } - - g_free(dbitmap); - - return ret; -} - -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr) +int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr) { bool all_device_dirty_tracking =3D vfio_devices_all_device_dirty_tracking(container); @@ -1723,7 +1403,7 @@ static void vfio_listener_log_sync(MemoryListener *li= stener, } } =20 -static const MemoryListener vfio_memory_listener =3D { +const MemoryListener vfio_memory_listener =3D { .name =3D "vfio", .region_add =3D vfio_listener_region_add, .region_del =3D vfio_listener_region_del, @@ -1732,45 +1412,6 @@ static const MemoryListener vfio_memory_listener =3D= { .log_sync =3D vfio_listener_log_sync, }; =20 -static void vfio_listener_release(VFIOContainer *container) -{ - memory_listener_unregister(&container->listener); - if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - memory_listener_unregister(&container->prereg_listener); - } -} - -static struct vfio_info_cap_header * -vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t= id) -{ - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - return vfio_get_cap((void *)info, info->cap_offset, id); -} - -bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, - unsigned int *avail) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_dma_avail *cap; - - /* If the capability cannot be found, assume no DMA limiting */ - hdr =3D vfio_get_iommu_type1_info_cap(info, - VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL); - if (hdr =3D=3D NULL) { - return false; - } - - if (avail !=3D NULL) { - cap =3D (void *) hdr; - *avail =3D cap->avail; - } - - return true; -} - void vfio_reset_handler(void *opaque) { VFIODevice *vbasedev; @@ -1846,25 +1487,7 @@ int vfio_kvm_device_del_fd(int fd, Error **errp) return 0; } =20 -static void vfio_kvm_device_add_group(VFIOGroup *group) -{ - Error *err =3D NULL; - - if (vfio_kvm_device_add_fd(group->fd, &err)) { - error_reportf_err(err, "group ID %d: ", group->groupid); - } -} - -static void vfio_kvm_device_del_group(VFIOGroup *group) -{ - Error *err =3D NULL; - - if (vfio_kvm_device_del_fd(group->fd, &err)) { - error_reportf_err(err, "group ID %d: ", group->groupid); - } -} - -static VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) +VFIOAddressSpace *vfio_get_address_space(AddressSpace *as) { VFIOAddressSpace *space; =20 @@ -1888,7 +1511,7 @@ static VFIOAddressSpace *vfio_get_address_space(Addre= ssSpace *as) return space; } =20 -static void vfio_put_address_space(VFIOAddressSpace *space) +void vfio_put_address_space(VFIOAddressSpace *space) { if (QLIST_EMPTY(&space->containers)) { QLIST_REMOVE(space, list); @@ -1899,499 +1522,6 @@ static void vfio_put_address_space(VFIOAddressSpace= *space) } } =20 -/* - * vfio_get_iommu_type - selects the richest iommu_type (v2 first) - */ -static int vfio_get_iommu_type(VFIOContainer *container, - Error **errp) -{ - int iommu_types[] =3D { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU, - VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU }; - int i; - - for (i =3D 0; i < ARRAY_SIZE(iommu_types); i++) { - if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) { - return iommu_types[i]; - } - } - error_setg(errp, "No available IOMMU models"); - return -EINVAL; -} - -static int vfio_init_container(VFIOContainer *container, int group_fd, - Error **errp) -{ - int iommu_type, ret; - - iommu_type =3D vfio_get_iommu_type(container, errp); - if (iommu_type < 0) { - return iommu_type; - } - - ret =3D ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd); - if (ret) { - error_setg_errno(errp, errno, "Failed to set group container"); - return -errno; - } - - while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) { - if (iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { - /* - * On sPAPR, despite the IOMMU subdriver always advertises v1 = and - * v2, the running platform may not support v2 and there is no - * way to guess it until an IOMMU group gets added to the cont= ainer. - * So in case it fails with v2, try v1 as a fallback. - */ - iommu_type =3D VFIO_SPAPR_TCE_IOMMU; - continue; - } - error_setg_errno(errp, errno, "Failed to set iommu for container"); - return -errno; - } - - container->iommu_type =3D iommu_type; - return 0; -} - -static int vfio_get_iommu_info(VFIOContainer *container, - struct vfio_iommu_type1_info **info) -{ - - size_t argsz =3D sizeof(struct vfio_iommu_type1_info); - - *info =3D g_new0(struct vfio_iommu_type1_info, 1); -again: - (*info)->argsz =3D argsz; - - if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) { - g_free(*info); - *info =3D NULL; - return -errno; - } - - if (((*info)->argsz > argsz)) { - argsz =3D (*info)->argsz; - *info =3D g_realloc(*info, argsz); - goto again; - } - - return 0; -} - -static struct vfio_info_cap_header * -vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) -{ - struct vfio_info_cap_header *hdr; - void *ptr =3D info; - - if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { - return NULL; - } - - for (hdr =3D ptr + info->cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->= next) { - if (hdr->id =3D=3D id) { - return hdr; - } - } - - return NULL; -} - -static void vfio_get_iommu_info_migration(VFIOContainer *container, - struct vfio_iommu_type1_info *inf= o) -{ - struct vfio_info_cap_header *hdr; - struct vfio_iommu_type1_info_cap_migration *cap_mig; - - hdr =3D vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRAT= ION); - if (!hdr) { - return; - } - - cap_mig =3D container_of(hdr, struct vfio_iommu_type1_info_cap_migrati= on, - header); - - /* - * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of - * qemu_real_host_page_size to mark those dirty. - */ - if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) { - container->dirty_pages_supported =3D true; - container->max_dirty_bitmap_size =3D cap_mig->max_dirty_bitmap_siz= e; - container->dirty_pgsizes =3D cap_mig->pgsize_bitmap; - } -} - -static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, - Error **errp) -{ - VFIOContainer *container; - int ret, fd; - VFIOAddressSpace *space; - - space =3D vfio_get_address_space(as); - - /* - * VFIO is currently incompatible with discarding of RAM insofar as the - * madvise to purge (zap) the page from QEMU's address space does not - * interact with the memory API and therefore leaves stale virtual to - * physical mappings in the IOMMU if the page was previously pinned. = We - * therefore set discarding broken for each group added to a container, - * whether the container is used individually or shared. This provides - * us with options to allow devices within a group to opt-in and allow - * discarding, so long as it is done consistently for a group (for ins= tance - * if the device is an mdev device where it is known that the host ven= dor - * driver will never pin pages outside of the working set of the guest - * driver, which would thus not be discarding candidates). - * - * The first opportunity to induce pinning occurs here where we attemp= t to - * attach the group to existing containers within the AddressSpace. I= f any - * pages are already zapped from the virtual address space, such as fr= om - * previous discards, new pinning will cause valid mappings to be - * re-established. Likewise, when the overall MemoryListener for a new - * container is registered, a replay of mappings within the AddressSpa= ce - * will occur, re-establishing any previously zapped pages as well. - * - * Especially virtio-balloon is currently only prevented from discardi= ng - * new memory, it will not yet set ram_block_discard_set_required() and - * therefore, neither stops us here or deals with the sudden memory - * consumption of inflated memory. - * - * We do support discarding of memory coordinated via the RamDiscardMa= nager - * with some IOMMU types. vfio_ram_block_discard_disable() handles the - * details once we know which type of IOMMU we are using. - */ - - QLIST_FOREACH(container, &space->containers, next) { - if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { - ret =3D vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, - "Cannot set discarding of RAM broken"); - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, - &container->fd)) { - error_report("vfio: error disconnecting group %d from" - " container", group->groupid); - } - return ret; - } - group->container =3D container; - QLIST_INSERT_HEAD(&container->group_list, group, container_nex= t); - vfio_kvm_device_add_group(group); - return 0; - } - } - - fd =3D qemu_open_old("/dev/vfio/vfio", O_RDWR); - if (fd < 0) { - error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio"); - ret =3D -errno; - goto put_space_exit; - } - - ret =3D ioctl(fd, VFIO_GET_API_VERSION); - if (ret !=3D VFIO_API_VERSION) { - error_setg(errp, "supported vfio version: %d, " - "reported version: %d", VFIO_API_VERSION, ret); - ret =3D -EINVAL; - goto close_fd_exit; - } - - container =3D g_malloc0(sizeof(*container)); - container->space =3D space; - container->fd =3D fd; - container->error =3D NULL; - container->dirty_pages_supported =3D false; - container->dma_max_mappings =3D 0; - QLIST_INIT(&container->giommu_list); - QLIST_INIT(&container->hostwin_list); - QLIST_INIT(&container->vrdl_list); - - ret =3D vfio_init_container(container, group->fd, errp); - if (ret) { - goto free_container_exit; - } - - ret =3D vfio_ram_block_discard_disable(container, true); - if (ret) { - error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"= ); - goto free_container_exit; - } - - switch (container->iommu_type) { - case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_IOMMU: - { - struct vfio_iommu_type1_info *info; - - ret =3D vfio_get_iommu_info(container, &info); - if (ret) { - error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info"); - goto enable_discards_exit; - } - - if (info->flags & VFIO_IOMMU_INFO_PGSIZES) { - container->pgsizes =3D info->iova_pgsizes; - } else { - container->pgsizes =3D qemu_real_host_page_size(); - } - - if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) { - container->dma_max_mappings =3D 65535; - } - vfio_get_iommu_info_migration(container, info); - g_free(info); - - /* - * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE - * information to get the actual window extent rather than assume - * a 64-bit IOVA address space. - */ - vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes); - - break; - } - case VFIO_SPAPR_TCE_v2_IOMMU: - case VFIO_SPAPR_TCE_IOMMU: - { - struct vfio_iommu_spapr_tce_info info; - bool v2 =3D container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU; - - /* - * The host kernel code implementing VFIO_IOMMU_DISABLE is called - * when container fd is closed so we do not call it explicitly - * in this file. - */ - if (!v2) { - ret =3D ioctl(fd, VFIO_IOMMU_ENABLE); - if (ret) { - error_setg_errno(errp, errno, "failed to enable container"= ); - ret =3D -errno; - goto enable_discards_exit; - } - } else { - container->prereg_listener =3D vfio_prereg_listener; - - memory_listener_register(&container->prereg_listener, - &address_space_memory); - if (container->error) { - memory_listener_unregister(&container->prereg_listener); - ret =3D -1; - error_propagate_prepend(errp, container->error, - "RAM memory listener initialization failed: "); - goto enable_discards_exit; - } - } - - info.argsz =3D sizeof(info); - ret =3D ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); - if (ret) { - error_setg_errno(errp, errno, - "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed"); - ret =3D -errno; - if (v2) { - memory_listener_unregister(&container->prereg_listener); - } - goto enable_discards_exit; - } - - if (v2) { - container->pgsizes =3D info.ddw.pgsizes; - /* - * There is a default window in just created container. - * To make region_add/del simpler, we better remove this - * window now and let those iommu_listener callbacks - * create/remove them when needed. - */ - ret =3D vfio_spapr_remove_window(container, info.dma32_window_= start); - if (ret) { - error_setg_errno(errp, -ret, - "failed to remove existing window"); - goto enable_discards_exit; - } - } else { - /* The default table uses 4K pages */ - container->pgsizes =3D 0x1000; - vfio_host_win_add(container, info.dma32_window_start, - info.dma32_window_start + - info.dma32_window_size - 1, - 0x1000); - } - } - } - - vfio_kvm_device_add_group(group); - - QLIST_INIT(&container->group_list); - QLIST_INSERT_HEAD(&space->containers, container, next); - - group->container =3D container; - QLIST_INSERT_HEAD(&container->group_list, group, container_next); - - container->listener =3D vfio_memory_listener; - - memory_listener_register(&container->listener, container->space->as); - - if (container->error) { - ret =3D -1; - error_propagate_prepend(errp, container->error, - "memory listener initialization failed: "); - goto listener_release_exit; - } - - container->initialized =3D true; - - return 0; -listener_release_exit: - QLIST_REMOVE(group, container_next); - QLIST_REMOVE(container, next); - vfio_kvm_device_del_group(group); - vfio_listener_release(container); - -enable_discards_exit: - vfio_ram_block_discard_disable(container, false); - -free_container_exit: - g_free(container); - -close_fd_exit: - close(fd); - -put_space_exit: - vfio_put_address_space(space); - - return ret; -} - -static void vfio_disconnect_container(VFIOGroup *group) -{ - VFIOContainer *container =3D group->container; - - QLIST_REMOVE(group, container_next); - group->container =3D NULL; - - /* - * Explicitly release the listener first before unset container, - * since unset may destroy the backend container if it's the last - * group. - */ - if (QLIST_EMPTY(&container->group_list)) { - vfio_listener_release(container); - } - - if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { - error_report("vfio: error disconnecting group %d from container", - group->groupid); - } - - if (QLIST_EMPTY(&container->group_list)) { - VFIOAddressSpace *space =3D container->space; - VFIOGuestIOMMU *giommu, *tmp; - VFIOHostDMAWindow *hostwin, *next; - - QLIST_REMOVE(container, next); - - QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, t= mp) { - memory_region_unregister_iommu_notifier( - MEMORY_REGION(giommu->iommu_mr), &giommu->n); - QLIST_REMOVE(giommu, giommu_next); - g_free(giommu); - } - - QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next, - next) { - QLIST_REMOVE(hostwin, hostwin_next); - g_free(hostwin); - } - - trace_vfio_disconnect_container(container->fd); - close(container->fd); - g_free(container); - - vfio_put_address_space(space); - } -} - -static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **er= rp) -{ - VFIOGroup *group; - char path[32]; - struct vfio_group_status status =3D { .argsz =3D sizeof(status) }; - - QLIST_FOREACH(group, &vfio_group_list, next) { - if (group->groupid =3D=3D groupid) { - /* Found it. Now is it already in the right context? */ - if (group->container->space->as =3D=3D as) { - return group; - } else { - error_setg(errp, "group %d used in multiple address spaces= ", - group->groupid); - return NULL; - } - } - } - - group =3D g_malloc0(sizeof(*group)); - - snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); - group->fd =3D qemu_open_old(path, O_RDWR); - if (group->fd < 0) { - error_setg_errno(errp, errno, "failed to open %s", path); - goto free_group_exit; - } - - if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { - error_setg_errno(errp, errno, "failed to get group %d status", gro= upid); - goto close_fd_exit; - } - - if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { - error_setg(errp, "group %d is not viable", groupid); - error_append_hint(errp, - "Please ensure all devices within the iommu_grou= p " - "are bound to their vfio bus driver.\n"); - goto close_fd_exit; - } - - group->groupid =3D groupid; - QLIST_INIT(&group->device_list); - - if (vfio_connect_container(group, as, errp)) { - error_prepend(errp, "failed to setup container for group %d: ", - groupid); - goto close_fd_exit; - } - - QLIST_INSERT_HEAD(&vfio_group_list, group, next); - - return group; - -close_fd_exit: - close(group->fd); - -free_group_exit: - g_free(group); - - return NULL; -} - -static void vfio_put_group(VFIOGroup *group) -{ - if (!group || !QLIST_EMPTY(&group->device_list)) { - return; - } - - if (!group->ram_block_discard_allowed) { - vfio_ram_block_discard_disable(group->container, false); - } - vfio_kvm_device_del_group(group); - vfio_disconnect_container(group); - QLIST_REMOVE(group, next); - trace_vfio_put_group(group->fd); - close(group->fd); - g_free(group); -} - struct vfio_device_info *vfio_get_device_info(int fd) { struct vfio_device_info *info; @@ -2415,256 +1545,3 @@ retry: =20 return info; } - -static int vfio_get_device(VFIOGroup *group, const char *name, - VFIODevice *vbasedev, Error **errp) -{ - g_autofree struct vfio_device_info *info =3D NULL; - int fd; - - fd =3D ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); - if (fd < 0) { - error_setg_errno(errp, errno, "error getting device from group %d", - group->groupid); - error_append_hint(errp, - "Verify all devices in group %d are bound to vfio- " - "or pci-stub and not already in use\n", group->group= id); - return fd; - } - - info =3D vfio_get_device_info(fd); - if (!info) { - error_setg_errno(errp, errno, "error getting device info"); - close(fd); - return -1; - } - - /* - * Set discarding of RAM as not broken for this group if the driver kn= ows - * the device operates compatibly with discarding. Setting must be - * consistent per group, but since compatibility is really only possib= le - * with mdev currently, we expect singleton groups. - */ - if (vbasedev->ram_block_discard_allowed !=3D - group->ram_block_discard_allowed) { - if (!QLIST_EMPTY(&group->device_list)) { - error_setg(errp, "Inconsistent setting of support for discardi= ng " - "RAM (e.g., balloon) within group"); - close(fd); - return -1; - } - - if (!group->ram_block_discard_allowed) { - group->ram_block_discard_allowed =3D true; - vfio_ram_block_discard_disable(group->container, false); - } - } - - vbasedev->fd =3D fd; - vbasedev->group =3D group; - QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); - - vbasedev->num_irqs =3D info->num_irqs; - vbasedev->num_regions =3D info->num_regions; - vbasedev->flags =3D info->flags; - - trace_vfio_get_device(name, info->flags, info->num_regions, info->num_= irqs); - - vbasedev->reset_works =3D !!(info->flags & VFIO_DEVICE_FLAGS_RESET); - - return 0; -} - -static void vfio_put_base_device(VFIODevice *vbasedev) -{ - if (!vbasedev->group) { - return; - } - QLIST_REMOVE(vbasedev, next); - vbasedev->group =3D NULL; - trace_vfio_put_base_device(vbasedev->fd); - close(vbasedev->fd); -} - -/* - * Interfaces for IBM EEH (Enhanced Error Handling) - */ -static bool vfio_eeh_container_ok(VFIOContainer *container) -{ - /* - * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO - * implementation is broken if there are multiple groups in a - * container. The hardware works in units of Partitionable - * Endpoints (=3D=3D IOMMU groups) and the EEH operations naively - * iterate across all groups in the container, without any logic - * to make sure the groups have their state synchronized. For - * certain operations (ENABLE) that might be ok, until an error - * occurs, but for others (GET_STATE) it's clearly broken. - */ - - /* - * XXX Once fixed kernels exist, test for them here - */ - - if (QLIST_EMPTY(&container->group_list)) { - return false; - } - - if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) { - return false; - } - - return true; -} - -static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op) -{ - struct vfio_eeh_pe_op pe_op =3D { - .argsz =3D sizeof(pe_op), - .op =3D op, - }; - int ret; - - if (!vfio_eeh_container_ok(container)) { - error_report("vfio/eeh: EEH_PE_OP 0x%x: " - "kernel requires a container with exactly one group",= op); - return -EPERM; - } - - ret =3D ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op); - if (ret < 0) { - error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op); - return -errno; - } - - return ret; -} - -static VFIOContainer *vfio_eeh_as_container(AddressSpace *as) -{ - VFIOAddressSpace *space =3D vfio_get_address_space(as); - VFIOContainer *container =3D NULL; - - if (QLIST_EMPTY(&space->containers)) { - /* No containers to act on */ - goto out; - } - - container =3D QLIST_FIRST(&space->containers); - - if (QLIST_NEXT(container, next)) { - /* We don't yet have logic to synchronize EEH state across - * multiple containers */ - container =3D NULL; - goto out; - } - -out: - vfio_put_address_space(space); - return container; -} - -bool vfio_eeh_as_ok(AddressSpace *as) -{ - VFIOContainer *container =3D vfio_eeh_as_container(as); - - return (container !=3D NULL) && vfio_eeh_container_ok(container); -} - -int vfio_eeh_as_op(AddressSpace *as, uint32_t op) -{ - VFIOContainer *container =3D vfio_eeh_as_container(as); - - if (!container) { - return -ENODEV; - } - return vfio_eeh_container_op(container, op); -} - -static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp) -{ - char *tmp, group_path[PATH_MAX], *group_name; - int ret, groupid; - ssize_t len; - - tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); - len =3D readlink(tmp, group_path, sizeof(group_path)); - g_free(tmp); - - if (len <=3D 0 || len >=3D sizeof(group_path)) { - ret =3D len < 0 ? -errno : -ENAMETOOLONG; - error_setg_errno(errp, -ret, "no iommu_group found"); - return ret; - } - - group_path[len] =3D 0; - - group_name =3D basename(group_path); - if (sscanf(group_name, "%d", &groupid) !=3D 1) { - error_setg_errno(errp, errno, "failed to read %s", group_path); - return -errno; - } - return groupid; -} - -/* - * vfio_attach_device: attach a device to a security context - * @name and @vbasedev->name are likely to be different depending - * on the type of the device, hence the need for passing @name - */ -int vfio_attach_device(char *name, VFIODevice *vbasedev, - AddressSpace *as, Error **errp) -{ - int groupid =3D vfio_device_groupid(vbasedev, errp); - VFIODevice *vbasedev_iter; - VFIOGroup *group; - VFIOContainer *container; - int ret; - - if (groupid < 0) { - return groupid; - } - - trace_vfio_attach_device(vbasedev->name, groupid); - - group =3D vfio_get_group(groupid, as, errp); - if (!group) { - return -ENOENT; - } - - QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { - if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { - error_setg(errp, "device is already attached"); - vfio_put_group(group); - return -EBUSY; - } - } - ret =3D vfio_get_device(group, name, vbasedev, errp); - if (ret) { - vfio_put_group(group); - return ret; - } - - container =3D group->container; - vbasedev->container =3D container; - QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); - QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next); - - return ret; -} - -void vfio_detach_device(VFIODevice *vbasedev) -{ - VFIOGroup *group =3D vbasedev->group; - - if (!vbasedev->container) { - return; - } - - QLIST_REMOVE(vbasedev, global_next); - QLIST_REMOVE(vbasedev, container_next); - vbasedev->container =3D NULL; - trace_vfio_detach_device(vbasedev->name, group->groupid); - vfio_put_base_device(vbasedev); - vfio_put_group(group); -} diff --git a/hw/vfio/container.c b/hw/vfio/container.c new file mode 100644 index 0000000000000000000000000000000000000000..adc467210ff73422ad2f897abfb= cf6eddbb22ad2 --- /dev/null +++ b/hw/vfio/container.c @@ -0,0 +1,1161 @@ +/* + * generic functions used by VFIO devices + * + * Copyright Red Hat, Inc. 2012 + * + * Authors: + * Alex Williamson + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Based on qemu-kvm device-assignment: + * Adapted for KVM by Qumranet. + * Copyright (c) 2007, Neocleus, Alex Novik (alex@neocleus.com) + * Copyright (c) 2007, Neocleus, Guy Zana (guy@neocleus.com) + * Copyright (C) 2008, Qumranet, Amit Shah (amit.shah@qumranet.com) + * Copyright (C) 2008, Red Hat, Amit Shah (amit.shah@redhat.com) + * Copyright (C) 2008, IBM, Muli Ben-Yehuda (muli@il.ibm.com) + */ + +#include "qemu/osdep.h" +#include +#ifdef CONFIG_KVM +#include +#endif +#include + +#include "hw/vfio/vfio-common.h" +#include "hw/vfio/vfio.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "exec/ram_addr.h" +#include "hw/hw.h" +#include "qemu/error-report.h" +#include "qemu/range.h" +#include "sysemu/kvm.h" +#include "sysemu/reset.h" +#include "trace.h" +#include "qapi/error.h" +#include "migration/migration.h" + +VFIOGroupList vfio_group_list =3D + QLIST_HEAD_INITIALIZER(vfio_group_list); + +static int vfio_ram_block_discard_disable(VFIOContainer *container, bool s= tate) +{ + switch (container->iommu_type) { + case VFIO_TYPE1v2_IOMMU: + case VFIO_TYPE1_IOMMU: + /* + * We support coordinated discarding of RAM via the RamDiscardMana= ger. + */ + return ram_block_uncoordinated_discard_disable(state); + default: + /* + * VFIO_SPAPR_TCE_IOMMU most probably works just fine with + * RamDiscardManager, however, it is completely untested. + * + * VFIO_SPAPR_TCE_v2_IOMMU with "DMA memory preregistering" does + * completely the opposite of managing mapping/pinning dynamically= as + * required by RamDiscardManager. We would have to special-case se= ctions + * with a RamDiscardManager. + */ + return ram_block_discard_disable(state); + } +} + +static int vfio_dma_unmap_bitmap(VFIOContainer *container, + hwaddr iova, ram_addr_t size, + IOMMUTLBEntry *iotlb) +{ + struct vfio_iommu_type1_dma_unmap *unmap; + struct vfio_bitmap *bitmap; + VFIOBitmap vbmap; + int ret; + + ret =3D vfio_bitmap_alloc(&vbmap, size); + if (ret) { + return ret; + } + + unmap =3D g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); + + unmap->argsz =3D sizeof(*unmap) + sizeof(*bitmap); + unmap->iova =3D iova; + unmap->size =3D size; + unmap->flags |=3D VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP; + bitmap =3D (struct vfio_bitmap *)&unmap->data; + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsi= ze + * to qemu_real_host_page_size. + */ + bitmap->pgsize =3D qemu_real_host_page_size(); + bitmap->size =3D vbmap.size; + bitmap->data =3D (__u64 *)vbmap.bitmap; + + if (vbmap.size > container->max_dirty_bitmap_size) { + error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size= ); + ret =3D -E2BIG; + goto unmap_exit; + } + + ret =3D ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); + if (!ret) { + cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, + iotlb->translated_addr, vbmap.pages); + } else { + error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); + } + +unmap_exit: + g_free(unmap); + g_free(vbmap.bitmap); + + return ret; +} + +/* + * DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86 + */ +int vfio_dma_unmap(VFIOContainer *container, hwaddr iova, + ram_addr_t size, IOMMUTLBEntry *iotlb) +{ + struct vfio_iommu_type1_dma_unmap unmap =3D { + .argsz =3D sizeof(unmap), + .flags =3D 0, + .iova =3D iova, + .size =3D size, + }; + bool need_dirty_sync =3D false; + int ret; + + if (iotlb && vfio_devices_all_running_and_mig_active(container)) { + if (!vfio_devices_all_device_dirty_tracking(container) && + container->dirty_pages_supported) { + return vfio_dma_unmap_bitmap(container, iova, size, iotlb); + } + + need_dirty_sync =3D true; + } + + while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { + /* + * The type1 backend has an off-by-one bug in the kernel (71a7d3d7= 8e3c + * v4.15) where an overflow in its wrap-around check prevents us f= rom + * unmapping the last page of the address space. Test for the err= or + * condition and re-try the unmap excluding the last page. The + * expectation is that we've never mapped the last page anyway and= this + * unmap request comes via vIOMMU support which also makes it unli= kely + * that this page is used. This bug was introduced well after typ= e1 v2 + * support was introduced, so we shouldn't need to test for v1. A= fix + * is queued for kernel v5.0 so this workaround can be removed once + * affected kernels are sufficiently deprecated. + */ + if (errno =3D=3D EINVAL && unmap.size && !(unmap.iova + unmap.size= ) && + container->iommu_type =3D=3D VFIO_TYPE1v2_IOMMU) { + trace_vfio_dma_unmap_overflow_workaround(); + unmap.size -=3D 1ULL << ctz64(container->pgsizes); + continue; + } + error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno)); + return -errno; + } + + if (need_dirty_sync) { + ret =3D vfio_get_dirty_bitmap(container, iova, size, + iotlb->translated_addr); + if (ret) { + return ret; + } + } + + return 0; +} + +int vfio_dma_map(VFIOContainer *container, hwaddr iova, + ram_addr_t size, void *vaddr, bool readonly) +{ + struct vfio_iommu_type1_dma_map map =3D { + .argsz =3D sizeof(map), + .flags =3D VFIO_DMA_MAP_FLAG_READ, + .vaddr =3D (__u64)(uintptr_t)vaddr, + .iova =3D iova, + .size =3D size, + }; + + if (!readonly) { + map.flags |=3D VFIO_DMA_MAP_FLAG_WRITE; + } + + /* + * Try the mapping, if it fails with EBUSY, unmap the region and try + * again. This shouldn't be necessary, but we sometimes see it in + * the VGA ROM space. + */ + if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0 || + (errno =3D=3D EBUSY && vfio_dma_unmap(container, iova, size, NULL)= =3D=3D 0 && + ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) =3D=3D 0)) { + return 0; + } + + error_report("VFIO_MAP_DMA failed: %s", strerror(errno)); + return -errno; +} + +int vfio_container_add_section_window(VFIOContainer *container, + MemoryRegionSection *section, + Error **errp) +{ + VFIOHostDMAWindow *hostwin; + hwaddr pgsize =3D 0; + int ret; + + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return 0; + } + + /* For now intersections are not allowed, we may relax this later */ + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (ranges_overlap(hostwin->min_iova, + hostwin->max_iova - hostwin->min_iova + 1, + section->offset_within_address_space, + int128_get64(section->size))) { + error_setg(errp, + "region [0x%"PRIx64",0x%"PRIx64"] overlaps with existing" + "host DMA window [0x%"PRIx64",0x%"PRIx64"]", + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, + hostwin->min_iova, hostwin->max_iova); + return -EINVAL; + } + } + + ret =3D vfio_spapr_create_window(container, section, &pgsize); + if (ret) { + error_setg_errno(errp, -ret, "Failed to create SPAPR window"); + return ret; + } + + vfio_host_win_add(container, section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, pgsize); +#ifdef CONFIG_KVM + if (kvm_enabled()) { + VFIOGroup *group; + IOMMUMemoryRegion *iommu_mr =3D IOMMU_MEMORY_REGION(section->mr); + struct kvm_vfio_spapr_tce param; + struct kvm_device_attr attr =3D { + .group =3D KVM_DEV_VFIO_GROUP, + .attr =3D KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE, + .addr =3D (uint64_t)(unsigned long)¶m, + }; + + if (!memory_region_iommu_get_attr(iommu_mr, IOMMU_ATTR_SPAPR_TCE_F= D, + ¶m.tablefd)) { + QLIST_FOREACH(group, &container->group_list, container_next) { + param.groupfd =3D group->fd; + if (ioctl(vfio_kvm_device_fd, KVM_SET_DEVICE_ATTR, &attr))= { + error_setg_errno(errp, errno, + "vfio: failed GROUP_SET_SPAPR_TCE for= " + "KVM VFIO device %d and group fd %d", + param.tablefd, param.groupfd); + return -errno; + } + trace_vfio_spapr_group_attach(param.groupfd, param.tablefd= ); + } + } + } +#endif + return 0; +} + +void vfio_container_del_section_window(VFIOContainer *container, + MemoryRegionSection *section) +{ + if (container->iommu_type !=3D VFIO_SPAPR_TCE_v2_IOMMU) { + return; + } + + vfio_spapr_remove_window(container, + section->offset_within_address_space); + if (vfio_host_win_del(container, + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1) < 0) { + hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, + __func__, section->offset_within_address_space); + } +} + +int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) +{ + int ret; + struct vfio_iommu_type1_dirty_bitmap dirty =3D { + .argsz =3D sizeof(dirty), + }; + + if (!container->dirty_pages_supported) { + return 0; + } + + if (start) { + dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_START; + } else { + dirty.flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP; + } + + ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); + if (ret) { + ret =3D -errno; + error_report("Failed to set dirty tracking flag 0x%x errno: %d", + dirty.flags, errno); + } + + return ret; +} + +int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, + hwaddr iova, hwaddr size) +{ + struct vfio_iommu_type1_dirty_bitmap *dbitmap; + struct vfio_iommu_type1_dirty_bitmap_get *range; + int ret; + + dbitmap =3D g_malloc0(sizeof(*dbitmap) + sizeof(*range)); + + dbitmap->argsz =3D sizeof(*dbitmap) + sizeof(*range); + dbitmap->flags =3D VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP; + range =3D (struct vfio_iommu_type1_dirty_bitmap_get *)&dbitmap->data; + range->iova =3D iova; + range->size =3D size; + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. Hence set bitmap's pg= size + * to qemu_real_host_page_size. + */ + range->bitmap.pgsize =3D qemu_real_host_page_size(); + range->bitmap.size =3D vbmap->size; + range->bitmap.data =3D (__u64 *)vbmap->bitmap; + + ret =3D ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); + if (ret) { + ret =3D -errno; + error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 + " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, + (uint64_t)range->size, errno); + } + + g_free(dbitmap); + + return ret; +} + +static void vfio_listener_release(VFIOContainer *container) +{ + memory_listener_unregister(&container->listener); + if (container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { + memory_listener_unregister(&container->prereg_listener); + } +} + +static struct vfio_info_cap_header * +vfio_get_iommu_type1_info_cap(struct vfio_iommu_type1_info *info, uint16_t= id) +{ + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { + return NULL; + } + + return vfio_get_cap((void *)info, info->cap_offset, id); +} + +bool vfio_get_info_dma_avail(struct vfio_iommu_type1_info *info, + unsigned int *avail) +{ + struct vfio_info_cap_header *hdr; + struct vfio_iommu_type1_info_dma_avail *cap; + + /* If the capability cannot be found, assume no DMA limiting */ + hdr =3D vfio_get_iommu_type1_info_cap(info, + VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL); + if (hdr =3D=3D NULL) { + return false; + } + + if (avail !=3D NULL) { + cap =3D (void *) hdr; + *avail =3D cap->avail; + } + + return true; +} + +static void vfio_kvm_device_add_group(VFIOGroup *group) +{ + Error *err =3D NULL; + + if (vfio_kvm_device_add_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } +} + +static void vfio_kvm_device_del_group(VFIOGroup *group) +{ + Error *err =3D NULL; + + if (vfio_kvm_device_del_fd(group->fd, &err)) { + error_reportf_err(err, "group ID %d: ", group->groupid); + } +} + +/* + * vfio_get_iommu_type - selects the richest iommu_type (v2 first) + */ +static int vfio_get_iommu_type(VFIOContainer *container, + Error **errp) +{ + int iommu_types[] =3D { VFIO_TYPE1v2_IOMMU, VFIO_TYPE1_IOMMU, + VFIO_SPAPR_TCE_v2_IOMMU, VFIO_SPAPR_TCE_IOMMU }; + int i; + + for (i =3D 0; i < ARRAY_SIZE(iommu_types); i++) { + if (ioctl(container->fd, VFIO_CHECK_EXTENSION, iommu_types[i])) { + return iommu_types[i]; + } + } + error_setg(errp, "No available IOMMU models"); + return -EINVAL; +} + +static int vfio_init_container(VFIOContainer *container, int group_fd, + Error **errp) +{ + int iommu_type, ret; + + iommu_type =3D vfio_get_iommu_type(container, errp); + if (iommu_type < 0) { + return iommu_type; + } + + ret =3D ioctl(group_fd, VFIO_GROUP_SET_CONTAINER, &container->fd); + if (ret) { + error_setg_errno(errp, errno, "Failed to set group container"); + return -errno; + } + + while (ioctl(container->fd, VFIO_SET_IOMMU, iommu_type)) { + if (iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU) { + /* + * On sPAPR, despite the IOMMU subdriver always advertises v1 = and + * v2, the running platform may not support v2 and there is no + * way to guess it until an IOMMU group gets added to the cont= ainer. + * So in case it fails with v2, try v1 as a fallback. + */ + iommu_type =3D VFIO_SPAPR_TCE_IOMMU; + continue; + } + error_setg_errno(errp, errno, "Failed to set iommu for container"); + return -errno; + } + + container->iommu_type =3D iommu_type; + return 0; +} + +static int vfio_get_iommu_info(VFIOContainer *container, + struct vfio_iommu_type1_info **info) +{ + + size_t argsz =3D sizeof(struct vfio_iommu_type1_info); + + *info =3D g_new0(struct vfio_iommu_type1_info, 1); +again: + (*info)->argsz =3D argsz; + + if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) { + g_free(*info); + *info =3D NULL; + return -errno; + } + + if (((*info)->argsz > argsz)) { + argsz =3D (*info)->argsz; + *info =3D g_realloc(*info, argsz); + goto again; + } + + return 0; +} + +static struct vfio_info_cap_header * +vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id) +{ + struct vfio_info_cap_header *hdr; + void *ptr =3D info; + + if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) { + return NULL; + } + + for (hdr =3D ptr + info->cap_offset; hdr !=3D ptr; hdr =3D ptr + hdr->= next) { + if (hdr->id =3D=3D id) { + return hdr; + } + } + + return NULL; +} + +static void vfio_get_iommu_info_migration(VFIOContainer *container, + struct vfio_iommu_type1_info *in= fo) +{ + struct vfio_info_cap_header *hdr; + struct vfio_iommu_type1_info_cap_migration *cap_mig; + + hdr =3D vfio_get_iommu_info_cap(info, VFIO_IOMMU_TYPE1_INFO_CAP_MIGRAT= ION); + if (!hdr) { + return; + } + + cap_mig =3D container_of(hdr, struct vfio_iommu_type1_info_cap_migrati= on, + header); + + /* + * cpu_physical_memory_set_dirty_lebitmap() supports pages in bitmap of + * qemu_real_host_page_size to mark those dirty. + */ + if (cap_mig->pgsize_bitmap & qemu_real_host_page_size()) { + container->dirty_pages_supported =3D true; + container->max_dirty_bitmap_size =3D cap_mig->max_dirty_bitmap_siz= e; + container->dirty_pgsizes =3D cap_mig->pgsize_bitmap; + } +} + +static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, + Error **errp) +{ + VFIOContainer *container; + int ret, fd; + VFIOAddressSpace *space; + + space =3D vfio_get_address_space(as); + + /* + * VFIO is currently incompatible with discarding of RAM insofar as the + * madvise to purge (zap) the page from QEMU's address space does not + * interact with the memory API and therefore leaves stale virtual to + * physical mappings in the IOMMU if the page was previously pinned. = We + * therefore set discarding broken for each group added to a container, + * whether the container is used individually or shared. This provides + * us with options to allow devices within a group to opt-in and allow + * discarding, so long as it is done consistently for a group (for ins= tance + * if the device is an mdev device where it is known that the host ven= dor + * driver will never pin pages outside of the working set of the guest + * driver, which would thus not be discarding candidates). + * + * The first opportunity to induce pinning occurs here where we attemp= t to + * attach the group to existing containers within the AddressSpace. I= f any + * pages are already zapped from the virtual address space, such as fr= om + * previous discards, new pinning will cause valid mappings to be + * re-established. Likewise, when the overall MemoryListener for a new + * container is registered, a replay of mappings within the AddressSpa= ce + * will occur, re-establishing any previously zapped pages as well. + * + * Especially virtio-balloon is currently only prevented from discardi= ng + * new memory, it will not yet set ram_block_discard_set_required() and + * therefore, neither stops us here or deals with the sudden memory + * consumption of inflated memory. + * + * We do support discarding of memory coordinated via the RamDiscardMa= nager + * with some IOMMU types. vfio_ram_block_discard_disable() handles the + * details once we know which type of IOMMU we are using. + */ + + QLIST_FOREACH(container, &space->containers, next) { + if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { + ret =3D vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, + "Cannot set discarding of RAM broken"); + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, + &container->fd)) { + error_report("vfio: error disconnecting group %d from" + " container", group->groupid); + } + return ret; + } + group->container =3D container; + QLIST_INSERT_HEAD(&container->group_list, group, container_nex= t); + vfio_kvm_device_add_group(group); + return 0; + } + } + + fd =3D qemu_open_old("/dev/vfio/vfio", O_RDWR); + if (fd < 0) { + error_setg_errno(errp, errno, "failed to open /dev/vfio/vfio"); + ret =3D -errno; + goto put_space_exit; + } + + ret =3D ioctl(fd, VFIO_GET_API_VERSION); + if (ret !=3D VFIO_API_VERSION) { + error_setg(errp, "supported vfio version: %d, " + "reported version: %d", VFIO_API_VERSION, ret); + ret =3D -EINVAL; + goto close_fd_exit; + } + + container =3D g_malloc0(sizeof(*container)); + container->space =3D space; + container->fd =3D fd; + container->error =3D NULL; + container->dirty_pages_supported =3D false; + container->dma_max_mappings =3D 0; + QLIST_INIT(&container->giommu_list); + QLIST_INIT(&container->hostwin_list); + QLIST_INIT(&container->vrdl_list); + + ret =3D vfio_init_container(container, group->fd, errp); + if (ret) { + goto free_container_exit; + } + + ret =3D vfio_ram_block_discard_disable(container, true); + if (ret) { + error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"= ); + goto free_container_exit; + } + + switch (container->iommu_type) { + case VFIO_TYPE1v2_IOMMU: + case VFIO_TYPE1_IOMMU: + { + struct vfio_iommu_type1_info *info; + + ret =3D vfio_get_iommu_info(container, &info); + if (ret) { + error_setg_errno(errp, -ret, "Failed to get VFIO IOMMU info"); + goto enable_discards_exit; + } + + if (info->flags & VFIO_IOMMU_INFO_PGSIZES) { + container->pgsizes =3D info->iova_pgsizes; + } else { + container->pgsizes =3D qemu_real_host_page_size(); + } + + if (!vfio_get_info_dma_avail(info, &container->dma_max_mappings)) { + container->dma_max_mappings =3D 65535; + } + vfio_get_iommu_info_migration(container, info); + g_free(info); + + /* + * FIXME: We should parse VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE + * information to get the actual window extent rather than assume + * a 64-bit IOVA address space. + */ + vfio_host_win_add(container, 0, (hwaddr)-1, container->pgsizes); + + break; + } + case VFIO_SPAPR_TCE_v2_IOMMU: + case VFIO_SPAPR_TCE_IOMMU: + { + struct vfio_iommu_spapr_tce_info info; + bool v2 =3D container->iommu_type =3D=3D VFIO_SPAPR_TCE_v2_IOMMU; + + /* + * The host kernel code implementing VFIO_IOMMU_DISABLE is called + * when container fd is closed so we do not call it explicitly + * in this file. + */ + if (!v2) { + ret =3D ioctl(fd, VFIO_IOMMU_ENABLE); + if (ret) { + error_setg_errno(errp, errno, "failed to enable container"= ); + ret =3D -errno; + goto enable_discards_exit; + } + } else { + container->prereg_listener =3D vfio_prereg_listener; + + memory_listener_register(&container->prereg_listener, + &address_space_memory); + if (container->error) { + memory_listener_unregister(&container->prereg_listener); + ret =3D -1; + error_propagate_prepend(errp, container->error, + "RAM memory listener initialization failed: "); + goto enable_discards_exit; + } + } + + info.argsz =3D sizeof(info); + ret =3D ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); + if (ret) { + error_setg_errno(errp, errno, + "VFIO_IOMMU_SPAPR_TCE_GET_INFO failed"); + ret =3D -errno; + if (v2) { + memory_listener_unregister(&container->prereg_listener); + } + goto enable_discards_exit; + } + + if (v2) { + container->pgsizes =3D info.ddw.pgsizes; + /* + * There is a default window in just created container. + * To make region_add/del simpler, we better remove this + * window now and let those iommu_listener callbacks + * create/remove them when needed. + */ + ret =3D vfio_spapr_remove_window(container, info.dma32_window_= start); + if (ret) { + error_setg_errno(errp, -ret, + "failed to remove existing window"); + goto enable_discards_exit; + } + } else { + /* The default table uses 4K pages */ + container->pgsizes =3D 0x1000; + vfio_host_win_add(container, info.dma32_window_start, + info.dma32_window_start + + info.dma32_window_size - 1, + 0x1000); + } + } + } + + vfio_kvm_device_add_group(group); + + QLIST_INIT(&container->group_list); + QLIST_INSERT_HEAD(&space->containers, container, next); + + group->container =3D container; + QLIST_INSERT_HEAD(&container->group_list, group, container_next); + + container->listener =3D vfio_memory_listener; + + memory_listener_register(&container->listener, container->space->as); + + if (container->error) { + ret =3D -1; + error_propagate_prepend(errp, container->error, + "memory listener initialization failed: "); + goto listener_release_exit; + } + + container->initialized =3D true; + + return 0; +listener_release_exit: + QLIST_REMOVE(group, container_next); + QLIST_REMOVE(container, next); + vfio_kvm_device_del_group(group); + vfio_listener_release(container); + +enable_discards_exit: + vfio_ram_block_discard_disable(container, false); + +free_container_exit: + g_free(container); + +close_fd_exit: + close(fd); + +put_space_exit: + vfio_put_address_space(space); + + return ret; +} + +static void vfio_disconnect_container(VFIOGroup *group) +{ + VFIOContainer *container =3D group->container; + + QLIST_REMOVE(group, container_next); + group->container =3D NULL; + + /* + * Explicitly release the listener first before unset container, + * since unset may destroy the backend container if it's the last + * group. + */ + if (QLIST_EMPTY(&container->group_list)) { + vfio_listener_release(container); + } + + if (ioctl(group->fd, VFIO_GROUP_UNSET_CONTAINER, &container->fd)) { + error_report("vfio: error disconnecting group %d from container", + group->groupid); + } + + if (QLIST_EMPTY(&container->group_list)) { + VFIOAddressSpace *space =3D container->space; + VFIOGuestIOMMU *giommu, *tmp; + VFIOHostDMAWindow *hostwin, *next; + + QLIST_REMOVE(container, next); + + QLIST_FOREACH_SAFE(giommu, &container->giommu_list, giommu_next, t= mp) { + memory_region_unregister_iommu_notifier( + MEMORY_REGION(giommu->iommu_mr), &giommu->n); + QLIST_REMOVE(giommu, giommu_next); + g_free(giommu); + } + + QLIST_FOREACH_SAFE(hostwin, &container->hostwin_list, hostwin_next, + next) { + QLIST_REMOVE(hostwin, hostwin_next); + g_free(hostwin); + } + + trace_vfio_disconnect_container(container->fd); + close(container->fd); + g_free(container); + + vfio_put_address_space(space); + } +} + +static VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **er= rp) +{ + VFIOGroup *group; + char path[32]; + struct vfio_group_status status =3D { .argsz =3D sizeof(status) }; + + QLIST_FOREACH(group, &vfio_group_list, next) { + if (group->groupid =3D=3D groupid) { + /* Found it. Now is it already in the right context? */ + if (group->container->space->as =3D=3D as) { + return group; + } else { + error_setg(errp, "group %d used in multiple address spaces= ", + group->groupid); + return NULL; + } + } + } + + group =3D g_malloc0(sizeof(*group)); + + snprintf(path, sizeof(path), "/dev/vfio/%d", groupid); + group->fd =3D qemu_open_old(path, O_RDWR); + if (group->fd < 0) { + error_setg_errno(errp, errno, "failed to open %s", path); + goto free_group_exit; + } + + if (ioctl(group->fd, VFIO_GROUP_GET_STATUS, &status)) { + error_setg_errno(errp, errno, "failed to get group %d status", gro= upid); + goto close_fd_exit; + } + + if (!(status.flags & VFIO_GROUP_FLAGS_VIABLE)) { + error_setg(errp, "group %d is not viable", groupid); + error_append_hint(errp, + "Please ensure all devices within the iommu_grou= p " + "are bound to their vfio bus driver.\n"); + goto close_fd_exit; + } + + group->groupid =3D groupid; + QLIST_INIT(&group->device_list); + + if (vfio_connect_container(group, as, errp)) { + error_prepend(errp, "failed to setup container for group %d: ", + groupid); + goto close_fd_exit; + } + + QLIST_INSERT_HEAD(&vfio_group_list, group, next); + + return group; + +close_fd_exit: + close(group->fd); + +free_group_exit: + g_free(group); + + return NULL; +} + +static void vfio_put_group(VFIOGroup *group) +{ + if (!group || !QLIST_EMPTY(&group->device_list)) { + return; + } + + if (!group->ram_block_discard_allowed) { + vfio_ram_block_discard_disable(group->container, false); + } + vfio_kvm_device_del_group(group); + vfio_disconnect_container(group); + QLIST_REMOVE(group, next); + trace_vfio_put_group(group->fd); + close(group->fd); + g_free(group); +} + +static int vfio_get_device(VFIOGroup *group, const char *name, + VFIODevice *vbasedev, Error **errp) +{ + g_autofree struct vfio_device_info *info =3D NULL; + int fd; + + fd =3D ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); + if (fd < 0) { + error_setg_errno(errp, errno, "error getting device from group %d", + group->groupid); + error_append_hint(errp, + "Verify all devices in group %d are bound to vfio- " + "or pci-stub and not already in use\n", group->group= id); + return fd; + } + + info =3D vfio_get_device_info(fd); + if (!info) { + error_setg_errno(errp, errno, "error getting device info"); + close(fd); + return -1; + } + + /* + * Set discarding of RAM as not broken for this group if the driver kn= ows + * the device operates compatibly with discarding. Setting must be + * consistent per group, but since compatibility is really only possib= le + * with mdev currently, we expect singleton groups. + */ + if (vbasedev->ram_block_discard_allowed !=3D + group->ram_block_discard_allowed) { + if (!QLIST_EMPTY(&group->device_list)) { + error_setg(errp, "Inconsistent setting of support for discardi= ng " + "RAM (e.g., balloon) within group"); + close(fd); + return -1; + } + + if (!group->ram_block_discard_allowed) { + group->ram_block_discard_allowed =3D true; + vfio_ram_block_discard_disable(group->container, false); + } + } + + vbasedev->fd =3D fd; + vbasedev->group =3D group; + QLIST_INSERT_HEAD(&group->device_list, vbasedev, next); + + vbasedev->num_irqs =3D info->num_irqs; + vbasedev->num_regions =3D info->num_regions; + vbasedev->flags =3D info->flags; + + trace_vfio_get_device(name, info->flags, info->num_regions, info->num_= irqs); + + vbasedev->reset_works =3D !!(info->flags & VFIO_DEVICE_FLAGS_RESET); + + return 0; +} + +static void vfio_put_base_device(VFIODevice *vbasedev) +{ + if (!vbasedev->group) { + return; + } + QLIST_REMOVE(vbasedev, next); + vbasedev->group =3D NULL; + trace_vfio_put_base_device(vbasedev->fd); + close(vbasedev->fd); +} + +/* + * Interfaces for IBM EEH (Enhanced Error Handling) + */ +static bool vfio_eeh_container_ok(VFIOContainer *container) +{ + /* + * As of 2016-03-04 (linux-4.5) the host kernel EEH/VFIO + * implementation is broken if there are multiple groups in a + * container. The hardware works in units of Partitionable + * Endpoints (=3D=3D IOMMU groups) and the EEH operations naively + * iterate across all groups in the container, without any logic + * to make sure the groups have their state synchronized. For + * certain operations (ENABLE) that might be ok, until an error + * occurs, but for others (GET_STATE) it's clearly broken. + */ + + /* + * XXX Once fixed kernels exist, test for them here + */ + + if (QLIST_EMPTY(&container->group_list)) { + return false; + } + + if (QLIST_NEXT(QLIST_FIRST(&container->group_list), container_next)) { + return false; + } + + return true; +} + +static int vfio_eeh_container_op(VFIOContainer *container, uint32_t op) +{ + struct vfio_eeh_pe_op pe_op =3D { + .argsz =3D sizeof(pe_op), + .op =3D op, + }; + int ret; + + if (!vfio_eeh_container_ok(container)) { + error_report("vfio/eeh: EEH_PE_OP 0x%x: " + "kernel requires a container with exactly one group",= op); + return -EPERM; + } + + ret =3D ioctl(container->fd, VFIO_EEH_PE_OP, &pe_op); + if (ret < 0) { + error_report("vfio/eeh: EEH_PE_OP 0x%x failed: %m", op); + return -errno; + } + + return ret; +} + +static VFIOContainer *vfio_eeh_as_container(AddressSpace *as) +{ + VFIOAddressSpace *space =3D vfio_get_address_space(as); + VFIOContainer *container =3D NULL; + + if (QLIST_EMPTY(&space->containers)) { + /* No containers to act on */ + goto out; + } + + container =3D QLIST_FIRST(&space->containers); + + if (QLIST_NEXT(container, next)) { + /* + * We don't yet have logic to synchronize EEH state across + * multiple containers + */ + container =3D NULL; + goto out; + } + +out: + vfio_put_address_space(space); + return container; +} + +bool vfio_eeh_as_ok(AddressSpace *as) +{ + VFIOContainer *container =3D vfio_eeh_as_container(as); + + return (container !=3D NULL) && vfio_eeh_container_ok(container); +} + +int vfio_eeh_as_op(AddressSpace *as, uint32_t op) +{ + VFIOContainer *container =3D vfio_eeh_as_container(as); + + if (!container) { + return -ENODEV; + } + return vfio_eeh_container_op(container, op); +} + +static int vfio_device_groupid(VFIODevice *vbasedev, Error **errp) +{ + char *tmp, group_path[PATH_MAX], *group_name; + int ret, groupid; + ssize_t len; + + tmp =3D g_strdup_printf("%s/iommu_group", vbasedev->sysfsdev); + len =3D readlink(tmp, group_path, sizeof(group_path)); + g_free(tmp); + + if (len <=3D 0 || len >=3D sizeof(group_path)) { + ret =3D len < 0 ? -errno : -ENAMETOOLONG; + error_setg_errno(errp, -ret, "no iommu_group found"); + return ret; + } + + group_path[len] =3D 0; + + group_name =3D basename(group_path); + if (sscanf(group_name, "%d", &groupid) !=3D 1) { + error_setg_errno(errp, errno, "failed to read %s", group_path); + return -errno; + } + return groupid; +} + +/* + * vfio_attach_device: attach a device to a security context + * @name and @vbasedev->name are likely to be different depending + * on the type of the device, hence the need for passing @name + */ +int vfio_attach_device(char *name, VFIODevice *vbasedev, + AddressSpace *as, Error **errp) +{ + int groupid =3D vfio_device_groupid(vbasedev, errp); + VFIODevice *vbasedev_iter; + VFIOGroup *group; + VFIOContainer *container; + int ret; + + if (groupid < 0) { + return groupid; + } + + trace_vfio_attach_device(vbasedev->name, groupid); + + group =3D vfio_get_group(groupid, as, errp); + if (!group) { + return -ENOENT; + } + + QLIST_FOREACH(vbasedev_iter, &group->device_list, next) { + if (strcmp(vbasedev_iter->name, vbasedev->name) =3D=3D 0) { + error_setg(errp, "device is already attached"); + vfio_put_group(group); + return -EBUSY; + } + } + ret =3D vfio_get_device(group, name, vbasedev, errp); + if (ret) { + vfio_put_group(group); + return ret; + } + + container =3D group->container; + vbasedev->container =3D container; + QLIST_INSERT_HEAD(&container->device_list, vbasedev, container_next); + QLIST_INSERT_HEAD(&vfio_device_list, vbasedev, global_next); + + return ret; +} + +void vfio_detach_device(VFIODevice *vbasedev) +{ + VFIOGroup *group =3D vbasedev->group; + + if (!vbasedev->container) { + return; + } + + QLIST_REMOVE(vbasedev, global_next); + QLIST_REMOVE(vbasedev, container_next); + vbasedev->container =3D NULL; + trace_vfio_detach_device(vbasedev->name, group->groupid); + vfio_put_base_device(vbasedev); + vfio_put_group(group); +} diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build index 3746c9f98420b1be949443b5d57f26a9982a37fe..2a6912c94027d6213144f910d64= 625a469cc2b1f 100644 --- a/hw/vfio/meson.build +++ b/hw/vfio/meson.build @@ -2,6 +2,7 @@ vfio_ss =3D ss.source_set() vfio_ss.add(files( 'helpers.c', 'common.c', + 'container.c', 'spapr.c', 'migration.c', )) --=20 2.41.0