Re: [PATCH v2] drm/cirrus: add drm_driver.release callback.
On Mon, Feb 10, 2020 at 10:53:10AM +0100, Gerd Hoffmann wrote: > Move final cleanups from cirrus_pci_remove() to the new callback. > Add drm_atomic_helper_shutdown() call to cirrus_pci_remove(). > > Set pointers to NULL after iounmap() and check them before using > them to make sure we don't touch released hardware. > > Signed-off-by: Gerd Hoffmann > --- > drivers/gpu/drm/cirrus/cirrus.c | 23 +-- > 1 file changed, 21 insertions(+), 2 deletions(-) > > diff --git a/drivers/gpu/drm/cirrus/cirrus.c b/drivers/gpu/drm/cirrus/cirrus.c > index a91fb0d7282c..128db11ed4d3 100644 > --- a/drivers/gpu/drm/cirrus/cirrus.c > +++ b/drivers/gpu/drm/cirrus/cirrus.c > @@ -154,6 +154,9 @@ static void cirrus_set_start_address(struct cirrus_device > *cirrus, u32 offset) > u32 addr; > u8 tmp; > > + if (!cirrus->mmio) > + return; Same as with the previous one, I think you're looking for drm_dev_enter/exit. And missing patch changelog. remove/release split looks good otherwise. -Daniel > + > addr = offset >> 2; > wreg_crt(cirrus, 0x0c, (u8)((addr >> 8) & 0xff)); > wreg_crt(cirrus, 0x0d, (u8)(addr & 0xff)); > @@ -179,6 +182,9 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, > int tmp; > int sr07 = 0, hdr = 0; > > + if (!cirrus->mmio) > + return -1; > + > htotal = mode->htotal / 8; > hsyncend = mode->hsync_end / 8; > hsyncstart = mode->hsync_start / 8; > @@ -301,6 +307,9 @@ static int cirrus_fb_blit_rect(struct drm_framebuffer *fb, > struct cirrus_device *cirrus = fb->dev->dev_private; > void *vmap; > > + if (!cirrus->vram) > + return -ENODEV; > + > vmap = drm_gem_shmem_vmap(fb->obj[0]); > if (!vmap) > return -ENOMEM; > @@ -502,6 +511,14 @@ static void cirrus_mode_config_init(struct cirrus_device > *cirrus) > > /* -- */ > > +static void cirrus_release(struct drm_device *dev) > +{ > + struct cirrus_device *cirrus = dev->dev_private; > + > + drm_mode_config_cleanup(dev); > + kfree(cirrus); > +} > + > DEFINE_DRM_GEM_FOPS(cirrus_fops); > > static struct drm_driver cirrus_driver = { > @@ -515,6 +532,7 @@ static struct drm_driver cirrus_driver = { > > .fops= &cirrus_fops, > DRM_GEM_SHMEM_DRIVER_OPS, > + .release = cirrus_release, > }; > > static int cirrus_pci_probe(struct pci_dev *pdev, > @@ -599,11 +617,12 @@ static void cirrus_pci_remove(struct pci_dev *pdev) > struct cirrus_device *cirrus = dev->dev_private; > > drm_dev_unregister(dev); > - drm_mode_config_cleanup(dev); > + drm_atomic_helper_shutdown(dev); > iounmap(cirrus->mmio); > + cirrus->mmio = NULL; > iounmap(cirrus->vram); > + cirrus->vram = NULL; > drm_dev_put(dev); > - kfree(cirrus); > pci_release_regions(pdev); > } > > -- > 2.18.1 > -- Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH v2] drm/virtio: add drm_driver.release callback.
On Mon, Feb 10, 2020 at 11:08:19AM +0100, Gerd Hoffmann wrote: > Split virtio_gpu_deinit(), move the drm shutdown and release to > virtio_gpu_release(). Also free vbufs in case we can't queue them. > > Signed-off-by: Gerd Hoffmann > --- > drivers/gpu/drm/virtio/virtgpu_drv.h | 1 + > drivers/gpu/drm/virtio/virtgpu_display.c | 1 - > drivers/gpu/drm/virtio/virtgpu_drv.c | 4 > drivers/gpu/drm/virtio/virtgpu_kms.c | 5 + > drivers/gpu/drm/virtio/virtgpu_vq.c | 9 - > 5 files changed, 18 insertions(+), 2 deletions(-) > > diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h > b/drivers/gpu/drm/virtio/virtgpu_drv.h > index d278c8c50f39..09a485b001e7 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_drv.h > +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h > @@ -217,6 +217,7 @@ extern struct drm_ioctl_desc > virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; > /* virtio_kms.c */ > int virtio_gpu_init(struct drm_device *dev); > void virtio_gpu_deinit(struct drm_device *dev); > +void virtio_gpu_release(struct drm_device *dev); > int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file); > void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file > *file); > > diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c > b/drivers/gpu/drm/virtio/virtgpu_display.c > index 7b0f0643bb2d..af953db4a0c9 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_display.c > +++ b/drivers/gpu/drm/virtio/virtgpu_display.c > @@ -368,6 +368,5 @@ void virtio_gpu_modeset_fini(struct virtio_gpu_device > *vgdev) > > for (i = 0 ; i < vgdev->num_scanouts; ++i) > kfree(vgdev->outputs[i].edid); > - drm_atomic_helper_shutdown(vgdev->ddev); > drm_mode_config_cleanup(vgdev->ddev); > } > diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c > b/drivers/gpu/drm/virtio/virtgpu_drv.c > index 8cf27af3ad53..664a741a3b0b 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_drv.c > +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c > @@ -31,6 +31,7 @@ > #include > > #include > +#include > #include > #include > > @@ -136,6 +137,7 @@ static void virtio_gpu_remove(struct virtio_device *vdev) > struct drm_device *dev = vdev->priv; > > drm_dev_unregister(dev); > + drm_atomic_helper_shutdown(dev); > virtio_gpu_deinit(dev); > drm_dev_put(dev); > } > @@ -214,4 +216,6 @@ static struct drm_driver driver = { > .major = DRIVER_MAJOR, > .minor = DRIVER_MINOR, > .patchlevel = DRIVER_PATCHLEVEL, > + > + .release = virtio_gpu_release, > }; > diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c > b/drivers/gpu/drm/virtio/virtgpu_kms.c > index c1086df49816..b45d12e3db2a 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_kms.c > +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c > @@ -240,6 +240,11 @@ void virtio_gpu_deinit(struct drm_device *dev) > flush_work(&vgdev->config_changed_work); > vgdev->vdev->config->reset(vgdev->vdev); > vgdev->vdev->config->del_vqs(vgdev->vdev); > +} > + > +void virtio_gpu_release(struct drm_device *dev) Split lgtm, but again I think you want drm_dev_enter/exit. And maybe a changelog. -Daniel > +{ > + struct virtio_gpu_device *vgdev = dev->dev_private; > > virtio_gpu_modeset_fini(vgdev); > virtio_gpu_free_vbufs(vgdev); > diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c > b/drivers/gpu/drm/virtio/virtgpu_vq.c > index cc02fc4bab2a..cc674b45f904 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_vq.c > +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c > @@ -330,6 +330,11 @@ static void virtio_gpu_queue_ctrl_sgs(struct > virtio_gpu_device *vgdev, > bool notify = false; > int ret; > > + if (!vgdev->vqs_ready) { > + free_vbuf(vgdev, vbuf); > + return; > + } > + > if (vgdev->has_indirect) > elemcnt = 1; > > @@ -462,8 +467,10 @@ static void virtio_gpu_queue_cursor(struct > virtio_gpu_device *vgdev, > int ret; > int outcnt; > > - if (!vgdev->vqs_ready) > + if (!vgdev->vqs_ready) { > + free_vbuf(vgdev, vbuf); > return; > + } > > sg_init_one(&ccmd, vbuf->buf, vbuf->size); > sgs[0] = &ccmd; > -- > 2.18.1 > -- Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH v3] drm/bochs: add drm_driver.release callback.
Call bochs_unload via drm_driver.release to make sure we release stuff when it is safe to do so. Use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. Tidy up here and there. Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/bochs/bochs_drv.c | 6 +++--- drivers/gpu/drm/bochs/bochs_hw.c | 24 +++- 2 files changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c index 10460878414e..addb0568c1af 100644 --- a/drivers/gpu/drm/bochs/bochs_drv.c +++ b/drivers/gpu/drm/bochs/bochs_drv.c @@ -23,7 +23,6 @@ static void bochs_unload(struct drm_device *dev) bochs_kms_fini(bochs); bochs_mm_fini(bochs); - bochs_hw_fini(dev); kfree(bochs); dev->dev_private = NULL; } @@ -69,6 +68,7 @@ static struct drm_driver bochs_driver = { .major = 1, .minor = 0, DRM_GEM_VRAM_DRIVER, + .release= bochs_unload, }; /* -- */ @@ -148,9 +148,9 @@ static void bochs_pci_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); + drm_dev_unplug(dev); drm_atomic_helper_shutdown(dev); - drm_dev_unregister(dev); - bochs_unload(dev); + bochs_hw_fini(dev); drm_dev_put(dev); } diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c index b615b7dfdd9d..952199cc0462 100644 --- a/drivers/gpu/drm/bochs/bochs_hw.c +++ b/drivers/gpu/drm/bochs/bochs_hw.c @@ -4,6 +4,7 @@ #include +#include #include #include "bochs.h" @@ -194,6 +195,8 @@ void bochs_hw_fini(struct drm_device *dev) { struct bochs_device *bochs = dev->dev_private; + /* TODO: shot down existing vram mappings */ + if (bochs->mmio) iounmap(bochs->mmio); if (bochs->ioports) @@ -207,6 +210,11 @@ void bochs_hw_fini(struct drm_device *dev) void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode *mode) { + int idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; + bochs->xres = mode->hdisplay; bochs->yres = mode->vdisplay; bochs->bpp = 32; @@ -232,11 +240,18 @@ void bochs_hw_setmode(struct bochs_device *bochs, bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED); + + drm_dev_exit(idx); } void bochs_hw_setformat(struct bochs_device *bochs, const struct drm_format_info *format) { + int idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; + DRM_DEBUG_DRIVER("format %c%c%c%c\n", (format->format >> 0) & 0xff, (format->format >> 8) & 0xff, @@ -256,13 +271,18 @@ void bochs_hw_setformat(struct bochs_device *bochs, __func__, format->format); break; } + + drm_dev_exit(idx); } void bochs_hw_setbase(struct bochs_device *bochs, int x, int y, int stride, u64 addr) { unsigned long offset; - unsigned int vx, vy, vwidth; + unsigned int vx, vy, vwidth, idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; bochs->stride = stride; offset = (unsigned long)addr + @@ -277,4 +297,6 @@ void bochs_hw_setbase(struct bochs_device *bochs, bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth); bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx); bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy); + + drm_dev_exit(idx); } -- 2.18.2 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: vhost changes (batched) in linux-next after 12/13 trigger random crashes in KVM guests after reboot
On 11.02.20 10:33, Eugenio Pérez wrote: > On Mon, 2020-02-10 at 12:01 +0100, Christian Borntraeger wrote: >> >> On 10.02.20 10:47, Eugenio Perez Martin wrote: >>> Hi Christian. >>> >>> I'm not able to reproduce the failure with >>> eccb852f1fe6bede630e2e4f1a121a81e34354ab commit. Could you add more data? >>> Your configuration (libvirt or qemu line), and host's dmesg output if any? >>> >>> Thanks! >> >> If it was not obvious, this is on s390x, a big endian system. >> > > Hi Christian. Thank you very much for the hints. > > Could we add some debug traces? Something like the inline patch should give > us some clues. attached. this time the guest crashed (and no guest moved message) [0.140906] Linux version 5.5.0+ (cborn...@m83lp52.lnxne.boe) (gcc version 9.2.1 20190827 (Red Hat 9.2.1-1) (GCC)) #18 SMP Tue Feb 11 10:51:14 CET 2020 [0.140908] setup: Linux is running natively in 64-bit mode [0.140950] setup: The maximum memory size is 131072MB [0.140955] setup: Reserving 1024MB of memory at 130048MB for crashkernel (System RAM: 130048MB) [0.140967] numa: NUMA mode: plain [0.141060] cpu: 64 configured CPUs, 0 standby CPUs [0.141107] cpu: The CPU configuration topology of the machine is: 0 0 4 2 3 10 / 4 [0.141626] Write protected kernel read-only data: 13420k [0.142408] Zone ranges: [0.142409] DMA [mem 0x-0x7fff] [0.142411] Normal [mem 0x8000-0x001f] [0.142412] Movable zone start for each node [0.142413] Early memory node ranges [0.142414] node 0: [mem 0x-0x001f] [0.142421] Initmem setup node 0 [mem 0x-0x001f] [0.142422] On node 0 totalpages: 33554432 [0.142423] DMA zone: 8192 pages used for memmap [0.142423] DMA zone: 0 pages reserved [0.142424] DMA zone: 524288 pages, LIFO batch:63 [0.159790] Normal zone: 516096 pages used for memmap [0.159791] Normal zone: 33030144 pages, LIFO batch:63 [0.175978] percpu: Embedded 33 pages/cpu s97024 r8192 d29952 u135168 [0.175986] pcpu-alloc: s97024 r8192 d29952 u135168 alloc=33*4096 [0.175987] pcpu-alloc: [0] 000 [0] 001 [0] 002 [0] 003 [0.175988] pcpu-alloc: [0] 004 [0] 005 [0] 006 [0] 007 [0.175989] pcpu-alloc: [0] 008 [0] 009 [0] 010 [0] 011 [0.175991] pcpu-alloc: [0] 012 [0] 013 [0] 014 [0] 015 [0.175992] pcpu-alloc: [0] 016 [0] 017 [0] 018 [0] 019 [0.175993] pcpu-alloc: [0] 020 [0] 021 [0] 022 [0] 023 [0.175994] pcpu-alloc: [0] 024 [0] 025 [0] 026 [0] 027 [0.175996] pcpu-alloc: [0] 028 [0] 029 [0] 030 [0] 031 [0.175997] pcpu-alloc: [0] 032 [0] 033 [0] 034 [0] 035 [0.175998] pcpu-alloc: [0] 036 [0] 037 [0] 038 [0] 039 [0.175999] pcpu-alloc: [0] 040 [0] 041 [0] 042 [0] 043 [0.176000] pcpu-alloc: [0] 044 [0] 045 [0] 046 [0] 047 [0.176001] pcpu-alloc: [0] 048 [0] 049 [0] 050 [0] 051 [0.176003] pcpu-alloc: [0] 052 [0] 053 [0] 054 [0] 055 [0.176004] pcpu-alloc: [0] 056 [0] 057 [0] 058 [0] 059 [0.176005] pcpu-alloc: [0] 060 [0] 061 [0] 062 [0] 063 [0.176006] pcpu-alloc: [0] 064 [0] 065 [0] 066 [0] 067 [0.176007] pcpu-alloc: [0] 068 [0] 069 [0] 070 [0] 071 [0.176008] pcpu-alloc: [0] 072 [0] 073 [0] 074 [0] 075 [0.176010] pcpu-alloc: [0] 076 [0] 077 [0] 078 [0] 079 [0.176011] pcpu-alloc: [0] 080 [0] 081 [0] 082 [0] 083 [0.176012] pcpu-alloc: [0] 084 [0] 085 [0] 086 [0] 087 [0.176013] pcpu-alloc: [0] 088 [0] 089 [0] 090 [0] 091 [0.176015] pcpu-alloc: [0] 092 [0] 093 [0] 094 [0] 095 [0.176016] pcpu-alloc: [0] 096 [0] 097 [0] 098 [0] 099 [0.176017] pcpu-alloc: [0] 100 [0] 101 [0] 102 [0] 103 [0.176019] pcpu-alloc: [0] 104 [0] 105 [0] 106 [0] 107 [0.176020] pcpu-alloc: [0] 108 [0] 109 [0] 110 [0] 111 [0.176021] pcpu-alloc: [0] 112 [0] 113 [0] 114 [0] 115 [0.176022] pcpu-alloc: [0] 116 [0] 117 [0] 118 [0] 119 [0.176024] pcpu-alloc: [0] 120 [0] 121 [0] 122 [0] 123 [0.176025] pcpu-alloc: [0] 124 [0] 125 [0] 126 [0] 127 [0.176026] pcpu-alloc: [0] 128 [0] 129 [0] 130 [0] 131 [0.176028] pcpu-alloc: [0] 132 [0] 133 [0] 134 [0] 135 [0.176029] pcpu-alloc: [0] 136 [0] 137 [0] 138 [0] 139 [0.176030] pcpu-alloc: [0] 140 [0] 141 [0] 142 [0] 143 [0.176031] pcpu-alloc: [0] 144 [0] 145 [0] 146 [0] 147 [0.176033] pcpu-alloc: [0] 148 [0] 149 [0] 150 [0] 151 [0.176034] pcpu-alloc: [0] 152 [0] 153 [0] 154 [0] 155 [0.176035] pcpu-alloc: [0] 156 [0] 157 [0] 158 [0] 159 [0.176036] pcpu-alloc: [0] 160 [0] 161 [0] 162 [0] 163 [0.176037] pcpu-alloc: [0] 164 [0] 165 [0] 166 [0] 167 [0.176039] pcpu-alloc: [0] 168 [0] 169 [0] 170 [0] 171 [0.176040] pcpu-alloc: [0] 172 [0] 173 [0] 174 [0] 175 [0.176041] pcpu-alloc: [0] 176 [0] 177 [0] 178 [0] 179 [0.176042] pcpu-alloc: [0] 180 [0] 181 [0] 182 [0] 183 [0.176044] pcpu-alloc: [0] 184 [0] 185 [0] 186 [0] 1
Re: vhost changes (batched) in linux-next after 12/13 trigger random crashes in KVM guests after reboot
On 11.02.20 10:56, Christian Borntraeger wrote: > > > On 11.02.20 10:33, Eugenio Pérez wrote: >> On Mon, 2020-02-10 at 12:01 +0100, Christian Borntraeger wrote: >>> >>> On 10.02.20 10:47, Eugenio Perez Martin wrote: Hi Christian. I'm not able to reproduce the failure with eccb852f1fe6bede630e2e4f1a121a81e34354ab commit. Could you add more data? Your configuration (libvirt or qemu line), and host's dmesg output if any? Thanks! >>> >>> If it was not obvious, this is on s390x, a big endian system. >>> >> >> Hi Christian. Thank you very much for the hints. >> >> Could we add some debug traces? Something like the inline patch should give >> us some clues. > > attached. this time the guest crashed (and no guest moved message) > And here with Guest moved vq after some reboots. [ 74.661450] [vq=8be108ff][vq->ndescs=0] [ 757.654136] [vq=201c16ab][vq->ndescs=0] [ 757.654142] [vq=465a3846][vq->ndescs=0] [ 758.283378] [vq=201c16ab][vq->ndescs=65] [ 758.283381] [vq=201c16ab][vq->ndescs=65][vq->first_desc=1] [ 758.283385] [vq=201c16ab][vq->ndescs=65][vq->first_desc=2] [ 758.283386] [vq=201c16ab][vq->ndescs=65][vq->first_desc=3] [ 758.283388] [vq=201c16ab][vq->ndescs=65][vq->first_desc=4] [ 758.283390] [vq=201c16ab][vq->ndescs=65][vq->first_desc=5] [ 758.283391] [vq=201c16ab][vq->ndescs=65][vq->first_desc=6] [ 758.283393] [vq=201c16ab][vq->ndescs=65][vq->first_desc=7] [ 758.283394] [vq=201c16ab][vq->ndescs=65][vq->first_desc=8] [ 758.283397] [vq=201c16ab][vq->ndescs=65][vq->first_desc=9] [ 758.283399] [vq=201c16ab][vq->ndescs=65][vq->first_desc=10] [ 758.283401] [vq=201c16ab][vq->ndescs=65][vq->first_desc=11] [ 758.283403] [vq=201c16ab][vq->ndescs=65][vq->first_desc=12] [ 758.283406] [vq=201c16ab][vq->ndescs=65][vq->first_desc=13] [ 758.283407] [vq=201c16ab][vq->ndescs=65][vq->first_desc=14] [ 758.283409] [vq=201c16ab][vq->ndescs=65][vq->first_desc=15] [ 758.283410] [vq=201c16ab][vq->ndescs=65][vq->first_desc=16] [ 758.283413] [vq=201c16ab][vq->ndescs=65][vq->first_desc=17] [ 758.283414] [vq=201c16ab][vq->ndescs=65][vq->first_desc=18] [ 758.283417] [vq=201c16ab][vq->ndescs=65][vq->first_desc=19] [ 758.283418] [vq=201c16ab][vq->ndescs=65][vq->first_desc=20] [ 758.283420] [vq=201c16ab][vq->ndescs=65][vq->first_desc=21] [ 758.283422] [vq=201c16ab][vq->ndescs=65][vq->first_desc=22] [ 758.283423] [vq=201c16ab][vq->ndescs=65][vq->first_desc=23] [ 758.283425] [vq=201c16ab][vq->ndescs=65][vq->first_desc=24] [ 758.283426] [vq=201c16ab][vq->ndescs=65][vq->first_desc=25] [ 758.283428] [vq=201c16ab][vq->ndescs=65][vq->first_desc=26] [ 758.283429] [vq=201c16ab][vq->ndescs=65][vq->first_desc=27] [ 758.283431] [vq=201c16ab][vq->ndescs=65][vq->first_desc=28] [ 758.283433] [vq=201c16ab][start=0][count=28] [ 758.344947] [vq=465a3846][vq->ndescs=1] [ 758.344948] [vq=465a3846][vq->ndescs=1][vq->first_desc=1] [ 758.344951] [vq=465a3846][vq->ndescs=0] [ 758.344962] [vq=465a3846][start=0][count=1] [ 758.366414] [vq=465a3846][vq->ndescs=1] [ 758.366415] [vq=465a3846][vq->ndescs=1][vq->first_desc=1] [ 758.366417] [vq=465a3846][vq->ndescs=0] [ 758.366420] [vq=465a3846][start=1][count=1] [ 758.366913] [vq=201c16ab][vq->ndescs=65][vq->first_desc=29] [ 758.366915] [vq=201c16ab][start=28][count=1] [ 758.366917] [vq=465a3846][vq->ndescs=1] [ 758.366918] [vq=465a3846][vq->ndescs=1][vq->first_desc=1] [ 758.366919] [vq=465a3846][vq->ndescs=0] [ 758.366924] [vq=465a3846][start=2][count=1] [ 758.366943] [vq=465a3846][vq->ndescs=2] [ 758.366944] [vq=465a3846][vq->ndescs=2][vq->first_desc=1] [ 758.366946] [vq=465a3846][vq->ndescs=2][vq->first_desc=2] [ 758.366947] [vq=465a3846][vq->ndescs=0] [ 758.366951] [vq=465a3846][start=3][count=2] [ 758.369847] [vq=201c16ab][vq->ndescs=65][vq->first_desc=30] [ 758.369852] [vq=201c16ab][start=29][count=1] [ 758.382143] [vq=201c16ab][vq->ndescs=65][vq->first_desc=31] [ 758.382145] [vq=201c16ab][start=30][count=1] [ 758.421531] [vq=201c16ab][vq->ndescs=65][vq->first_desc=32] [ 758.421534] [vq=201c16ab][vq->ndescs=65][vq->first_desc=33] [ 758.421536] [vq=201c16ab][vq->ndescs=65][vq->first_desc=34] [ 758.421537] [vq=201c16ab][start=31][count=3] [ 758.480414] [vq=201c16ab][vq->ndescs=65][vq->first_desc=35] [ 758.480418] [vq=201c16ab][start=34][count=1] [ 758.584968] [vq=465a3846][vq->ndescs=2] [ 758.584973] [vq=465a3846][vq->ndescs=2][vq->first_desc=2] [ 758.584975] [vq=465a3846][vq->ndescs=0] [ 758.584987
[PATCH v3] drm/cirrus: add drm_driver.release callback.
Move final cleanups from cirrus_pci_remove() to the new callback. Add drm_atomic_helper_shutdown() call to cirrus_pci_remove(). Use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/cirrus/cirrus.c | 43 - 1 file changed, 37 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/cirrus/cirrus.c b/drivers/gpu/drm/cirrus/cirrus.c index a91fb0d7282c..d2ff63ce8eaf 100644 --- a/drivers/gpu/drm/cirrus/cirrus.c +++ b/drivers/gpu/drm/cirrus/cirrus.c @@ -151,9 +151,13 @@ static int cirrus_pitch(struct drm_framebuffer *fb) static void cirrus_set_start_address(struct cirrus_device *cirrus, u32 offset) { + int idx; u32 addr; u8 tmp; + if (!drm_dev_enter(&cirrus->dev, &idx)) + return; + addr = offset >> 2; wreg_crt(cirrus, 0x0c, (u8)((addr >> 8) & 0xff)); wreg_crt(cirrus, 0x0d, (u8)(addr & 0xff)); @@ -168,6 +172,8 @@ static void cirrus_set_start_address(struct cirrus_device *cirrus, u32 offset) tmp &= 0x7f; tmp |= (addr >> 12) & 0x80; wreg_crt(cirrus, 0x1d, tmp); + + drm_dev_exit(idx); } static int cirrus_mode_set(struct cirrus_device *cirrus, @@ -176,9 +182,12 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, { int hsyncstart, hsyncend, htotal, hdispend; int vtotal, vdispend; - int tmp; + int tmp, idx; int sr07 = 0, hdr = 0; + if (!drm_dev_enter(&cirrus->dev, &idx)) + return -1; + htotal = mode->htotal / 8; hsyncend = mode->hsync_end / 8; hsyncstart = mode->hsync_start / 8; @@ -264,6 +273,7 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, hdr = 0xc5; break; default: + drm_dev_exit(idx); return -1; } @@ -292,6 +302,8 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, /* Unblank (needed on S3 resume, vgabios doesn't do it then) */ outb(0x20, 0x3c0); + + drm_dev_exit(idx); return 0; } @@ -300,10 +312,16 @@ static int cirrus_fb_blit_rect(struct drm_framebuffer *fb, { struct cirrus_device *cirrus = fb->dev->dev_private; void *vmap; + int idx, ret; + ret = -ENODEV; + if (!drm_dev_enter(&cirrus->dev, &idx)) + goto out; + + ret = -ENOMEM; vmap = drm_gem_shmem_vmap(fb->obj[0]); if (!vmap) - return -ENOMEM; + goto out_dev_exit; if (cirrus->cpp == fb->format->cpp[0]) drm_fb_memcpy_dstclip(cirrus->vram, @@ -323,7 +341,12 @@ static int cirrus_fb_blit_rect(struct drm_framebuffer *fb, WARN_ON_ONCE("cpp mismatch"); drm_gem_shmem_vunmap(fb->obj[0], vmap); - return 0; + ret = 0; + +out_dev_exit: + drm_dev_exit(idx); +out: + return ret; } static int cirrus_fb_blit_fullscreen(struct drm_framebuffer *fb) @@ -502,6 +525,14 @@ static void cirrus_mode_config_init(struct cirrus_device *cirrus) /* -- */ +static void cirrus_release(struct drm_device *dev) +{ + struct cirrus_device *cirrus = dev->dev_private; + + drm_mode_config_cleanup(dev); + kfree(cirrus); +} + DEFINE_DRM_GEM_FOPS(cirrus_fops); static struct drm_driver cirrus_driver = { @@ -515,6 +546,7 @@ static struct drm_driver cirrus_driver = { .fops= &cirrus_fops, DRM_GEM_SHMEM_DRIVER_OPS, + .release = cirrus_release, }; static int cirrus_pci_probe(struct pci_dev *pdev, @@ -598,12 +630,11 @@ static void cirrus_pci_remove(struct pci_dev *pdev) struct drm_device *dev = pci_get_drvdata(pdev); struct cirrus_device *cirrus = dev->dev_private; - drm_dev_unregister(dev); - drm_mode_config_cleanup(dev); + drm_dev_unplug(dev); + drm_atomic_helper_shutdown(dev); iounmap(cirrus->mmio); iounmap(cirrus->vram); drm_dev_put(dev); - kfree(cirrus); pci_release_regions(pdev); } -- 2.18.2 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH] virtio: Work around frames incorrectly marked as gso
On Tue, Feb 11, 2020 at 07:42:37AM +, Anton Ivanov wrote: > On 11/02/2020 02:51, Jason Wang wrote: > > > > On 2020/2/11 上午12:55, Anton Ivanov wrote: > > > > > > > > > On 09/12/2019 10:48, anton.iva...@cambridgegreys.com wrote: > > > > From: Anton Ivanov > > > > > > > > Some of the frames marked as GSO which arrive at > > > > virtio_net_hdr_from_skb() have no GSO_TYPE, no > > > > fragments (data_len = 0) and length significantly shorter > > > > than the MTU (752 in my experiments). > > > > > > > > This is observed on raw sockets reading off vEth interfaces > > > > in all 4.x and 5.x kernels I tested. > > > > > > > > These frames are reported as invalid while they are in fact > > > > gso-less frames. > > > > > > > > This patch marks the vnet header as no-GSO for them instead > > > > of reporting it as invalid. > > > > > > > > Signed-off-by: Anton Ivanov > > > > --- > > > > include/linux/virtio_net.h | 8 ++-- > > > > 1 file changed, 6 insertions(+), 2 deletions(-) > > > > > > > > diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h > > > > index 0d1fe9297ac6..d90d5cff1b9a 100644 > > > > --- a/include/linux/virtio_net.h > > > > +++ b/include/linux/virtio_net.h > > > > @@ -112,8 +112,12 @@ static inline int > > > > virtio_net_hdr_from_skb(const struct sk_buff *skb, > > > > hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; > > > > else if (sinfo->gso_type & SKB_GSO_TCPV6) > > > > hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; > > > > - else > > > > - return -EINVAL; > > > > + else { > > > > + if (skb->data_len == 0) > > > > + hdr->gso_type = VIRTIO_NET_HDR_GSO_NONE; > > > > + else > > > > + return -EINVAL; > > > > + } > > > > if (sinfo->gso_type & SKB_GSO_TCP_ECN) > > > > hdr->gso_type |= VIRTIO_NET_HDR_GSO_ECN; > > > > } else > > > > > > > > > > ping. > > > > > > > Do you mean gso_size is set but gso_type is not? Looks like a bug > > elsewhere. > > > > Thanks > > > > > Yes. > > I could not trace it where it is coming from. > > I see it when doing recvmmsg on raw sockets in the UML vector network > drivers. > I think we need to find the culprit and fix it there, lots of other things can break otherwise. Just printing out skb->dev->name should do the trick, no? > -- > Anton R. Ivanov > Cambridgegreys Limited. Registered in England. Company Number 10273661 > https://www.cambridgegreys.com/ ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH v3] drm/virtio: add drm_driver.release callback.
Split virtio_gpu_deinit(), move the drm shutdown and release to virtio_gpu_release(). Drop vqs_ready variable, instead use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. Tidy up here and there. Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++- drivers/gpu/drm/virtio/virtgpu_display.c | 1 - drivers/gpu/drm/virtio/virtgpu_drv.c | 6 +- drivers/gpu/drm/virtio/virtgpu_kms.c | 7 -- drivers/gpu/drm/virtio/virtgpu_vq.c | 27 +--- 5 files changed, 27 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 7fd8361e1c9e..af9403e1cf78 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -32,6 +32,7 @@ #include #include +#include #include #include #include @@ -177,7 +178,6 @@ struct virtio_gpu_device { struct virtio_gpu_queue ctrlq; struct virtio_gpu_queue cursorq; struct kmem_cache *vbufs; - bool vqs_ready; bool disable_notify; bool pending_notify; @@ -219,6 +219,7 @@ extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; /* virtio_kms.c */ int virtio_gpu_init(struct drm_device *dev); void virtio_gpu_deinit(struct drm_device *dev); +void virtio_gpu_release(struct drm_device *dev); int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file); void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file); diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 7b0f0643bb2d..af953db4a0c9 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -368,6 +368,5 @@ void virtio_gpu_modeset_fini(struct virtio_gpu_device *vgdev) for (i = 0 ; i < vgdev->num_scanouts; ++i) kfree(vgdev->outputs[i].edid); - drm_atomic_helper_shutdown(vgdev->ddev); drm_mode_config_cleanup(vgdev->ddev); } diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 8cf27af3ad53..ab4bed78e656 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -31,6 +31,7 @@ #include #include +#include #include #include @@ -135,7 +136,8 @@ static void virtio_gpu_remove(struct virtio_device *vdev) { struct drm_device *dev = vdev->priv; - drm_dev_unregister(dev); + drm_dev_unplug(dev); + drm_atomic_helper_shutdown(dev); virtio_gpu_deinit(dev); drm_dev_put(dev); } @@ -214,4 +216,6 @@ static struct drm_driver driver = { .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, + + .release = virtio_gpu_release, }; diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index c1086df49816..4009c2f97d08 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -199,7 +199,6 @@ int virtio_gpu_init(struct drm_device *dev) virtio_gpu_modeset_init(vgdev); virtio_device_ready(vgdev->vdev); - vgdev->vqs_ready = true; if (num_capsets) virtio_gpu_get_capsets(vgdev, num_capsets); @@ -234,12 +233,16 @@ void virtio_gpu_deinit(struct drm_device *dev) struct virtio_gpu_device *vgdev = dev->dev_private; flush_work(&vgdev->obj_free_work); - vgdev->vqs_ready = false; flush_work(&vgdev->ctrlq.dequeue_work); flush_work(&vgdev->cursorq.dequeue_work); flush_work(&vgdev->config_changed_work); vgdev->vdev->config->reset(vgdev->vdev); vgdev->vdev->config->del_vqs(vgdev->vdev); +} + +void virtio_gpu_release(struct drm_device *dev) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; virtio_gpu_modeset_fini(vgdev); virtio_gpu_free_vbufs(vgdev); diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index a682c2fcbe9a..cfe9c54f87a3 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -330,7 +330,14 @@ static void virtio_gpu_queue_ctrl_sgs(struct virtio_gpu_device *vgdev, { struct virtqueue *vq = vgdev->ctrlq.vq; bool notify = false; - int ret; + int ret, idx; + + if (!drm_dev_enter(vgdev->ddev, &idx)) { + if (fence && vbuf->objs) + virtio_gpu_array_unlock_resv(vbuf->objs); + free_vbuf(vgdev, vbuf); + return; + } if (vgdev->has_indirect) elemcnt = 1; @@ -338,14 +345,6 @@ static void virtio_gpu_queue_ctrl_sgs(struct virtio_gpu_device *vgdev, again: spin_lock(&vgdev->ctrlq.qlock); - if (!vgdev->vqs_ready) { - spin_unlock(&vgdev->ctrlq.qlock); - - if (fence && vbuf->objs) -
Re: [PATCH v3] drm/bochs: add drm_driver.release callback.
On Tue, Feb 11, 2020 at 10:55:29AM +0100, Gerd Hoffmann wrote: > Call bochs_unload via drm_driver.release to make sure we release stuff > when it is safe to do so. Use drm_dev_{enter,exit,unplug} to avoid > touching hardware after device removal. Tidy up here and there. > > Signed-off-by: Gerd Hoffmann Still no changelog? I mean if we'd have merge request or something I can easily check the discussions, but with mailing lists it's all over and I have 0 memory, so every time I see a patch without history I get to reconstruct the review history again and figure out where we've been. Gets old real fast. -Daniel > --- > drivers/gpu/drm/bochs/bochs_drv.c | 6 +++--- > drivers/gpu/drm/bochs/bochs_hw.c | 24 +++- > 2 files changed, 26 insertions(+), 4 deletions(-) > > diff --git a/drivers/gpu/drm/bochs/bochs_drv.c > b/drivers/gpu/drm/bochs/bochs_drv.c > index 10460878414e..addb0568c1af 100644 > --- a/drivers/gpu/drm/bochs/bochs_drv.c > +++ b/drivers/gpu/drm/bochs/bochs_drv.c > @@ -23,7 +23,6 @@ static void bochs_unload(struct drm_device *dev) > > bochs_kms_fini(bochs); > bochs_mm_fini(bochs); > - bochs_hw_fini(dev); > kfree(bochs); > dev->dev_private = NULL; > } > @@ -69,6 +68,7 @@ static struct drm_driver bochs_driver = { > .major = 1, > .minor = 0, > DRM_GEM_VRAM_DRIVER, > + .release= bochs_unload, > }; > > /* -- */ > @@ -148,9 +148,9 @@ static void bochs_pci_remove(struct pci_dev *pdev) > { > struct drm_device *dev = pci_get_drvdata(pdev); > > + drm_dev_unplug(dev); > drm_atomic_helper_shutdown(dev); > - drm_dev_unregister(dev); > - bochs_unload(dev); > + bochs_hw_fini(dev); > drm_dev_put(dev); > } > > diff --git a/drivers/gpu/drm/bochs/bochs_hw.c > b/drivers/gpu/drm/bochs/bochs_hw.c > index b615b7dfdd9d..952199cc0462 100644 > --- a/drivers/gpu/drm/bochs/bochs_hw.c > +++ b/drivers/gpu/drm/bochs/bochs_hw.c > @@ -4,6 +4,7 @@ > > #include > > +#include > #include > > #include "bochs.h" > @@ -194,6 +195,8 @@ void bochs_hw_fini(struct drm_device *dev) > { > struct bochs_device *bochs = dev->dev_private; > > + /* TODO: shot down existing vram mappings */ > + > if (bochs->mmio) > iounmap(bochs->mmio); > if (bochs->ioports) > @@ -207,6 +210,11 @@ void bochs_hw_fini(struct drm_device *dev) > void bochs_hw_setmode(struct bochs_device *bochs, > struct drm_display_mode *mode) > { > + int idx; > + > + if (!drm_dev_enter(bochs->dev, &idx)) > + return; > + > bochs->xres = mode->hdisplay; > bochs->yres = mode->vdisplay; > bochs->bpp = 32; > @@ -232,11 +240,18 @@ void bochs_hw_setmode(struct bochs_device *bochs, > > bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, > VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED); > + > + drm_dev_exit(idx); > } > > void bochs_hw_setformat(struct bochs_device *bochs, > const struct drm_format_info *format) > { > + int idx; > + > + if (!drm_dev_enter(bochs->dev, &idx)) > + return; > + > DRM_DEBUG_DRIVER("format %c%c%c%c\n", >(format->format >> 0) & 0xff, >(format->format >> 8) & 0xff, > @@ -256,13 +271,18 @@ void bochs_hw_setformat(struct bochs_device *bochs, > __func__, format->format); > break; > } > + > + drm_dev_exit(idx); > } > > void bochs_hw_setbase(struct bochs_device *bochs, > int x, int y, int stride, u64 addr) > { > unsigned long offset; > - unsigned int vx, vy, vwidth; > + unsigned int vx, vy, vwidth, idx; > + > + if (!drm_dev_enter(bochs->dev, &idx)) > + return; > > bochs->stride = stride; > offset = (unsigned long)addr + > @@ -277,4 +297,6 @@ void bochs_hw_setbase(struct bochs_device *bochs, > bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth); > bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx); > bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy); > + > + drm_dev_exit(idx); > } > -- > 2.18.2 > -- Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH] drm/virtio: rework batching
Drop the virtio_gpu_{disable,enable}_notify(). Add a new virtio_gpu_notify() call instead, which must be called whenever the driver wants make sure the host is notified needed. Drop notification from command submission. Add virtio_gpu_notify() calls everywhere instead. This results in more batching because we now notify only once for a series of commands. We already had that for page flips, now we also batch resource creation (create + attach-backing), display updates (edid + display-info) and device initialization. With this in place it is also possible to make notification optional for userspace ioctls. Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/virtio/virtgpu_drv.h | 6 ++--- drivers/gpu/drm/virtio/virtgpu_display.c | 2 ++ drivers/gpu/drm/virtio/virtgpu_ioctl.c | 4 +++ drivers/gpu/drm/virtio/virtgpu_kms.c | 3 +++ drivers/gpu/drm/virtio/virtgpu_object.c | 1 + drivers/gpu/drm/virtio/virtgpu_plane.c | 5 ++-- drivers/gpu/drm/virtio/virtgpu_vq.c | 31 +--- 7 files changed, 26 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 7fd8361e1c9e..28aeac8717e1 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -179,8 +179,7 @@ struct virtio_gpu_device { struct kmem_cache *vbufs; bool vqs_ready; - bool disable_notify; - bool pending_notify; + atomic_t pending_commands; struct ida resource_ida; @@ -334,8 +333,7 @@ void virtio_gpu_dequeue_ctrl_func(struct work_struct *work); void virtio_gpu_dequeue_cursor_func(struct work_struct *work); void virtio_gpu_dequeue_fence_func(struct work_struct *work); -void virtio_gpu_disable_notify(struct virtio_gpu_device *vgdev); -void virtio_gpu_enable_notify(struct virtio_gpu_device *vgdev); +void virtio_gpu_notify(struct virtio_gpu_device *vgdev); /* virtio_gpu_display.c */ void virtio_gpu_modeset_init(struct virtio_gpu_device *vgdev); diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 7b0f0643bb2d..e95fcfd8d20c 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -90,6 +90,7 @@ static void virtio_gpu_crtc_mode_set_nofb(struct drm_crtc *crtc) virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, crtc->mode.hdisplay, crtc->mode.vdisplay, 0, 0); + virtio_gpu_notify(vgdev); } static void virtio_gpu_crtc_atomic_enable(struct drm_crtc *crtc, @@ -108,6 +109,7 @@ static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc, struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc); virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, 0, 0, 0, 0); + virtio_gpu_notify(vgdev); output->enabled = false; } diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 205ec4abae2b..75d818d707e6 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -158,6 +158,7 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, virtio_gpu_cmd_submit(vgdev, buf, exbuf->size, vfpriv->ctx_id, buflist, out_fence); + virtio_gpu_notify(vgdev); return 0; out_memdup: @@ -314,6 +315,7 @@ static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev, (vgdev, vfpriv->ctx_id, offset, args->level, &args->box, objs, fence); dma_fence_put(&fence->f); + virtio_gpu_notify(vgdev); return 0; err_unlock: @@ -359,6 +361,7 @@ static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data, args->level, &args->box, objs, fence); dma_fence_put(&fence->f); } + virtio_gpu_notify(vgdev); return 0; err_unlock: @@ -445,6 +448,7 @@ static int virtio_gpu_get_caps_ioctl(struct drm_device *dev, /* not in cache - need to talk to hw */ virtio_gpu_cmd_get_capset(vgdev, found_valid, args->cap_set_ver, &cache_ent); + virtio_gpu_notify(vgdev); copy_exit: ret = wait_event_timeout(vgdev->resp_wq, diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index c1086df49816..44e4c07d0162 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -44,6 +44,7 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work) if (vgdev->has_edid) virtio_gpu_cmd_get_edids(vgdev); virtio_gpu_cmd_get_display_info(vgdev); + virtio_gpu_notify(vgdev); drm_helper_hpd_irq_event(vgdev->ddev); events_clear |= VIRTIO_GPU_EVENT_DISPL
Re: vhost changes (batched) in linux-next after 12/13 trigger random crashes in KVM guests after reboot
On 11.02.20 14:04, Eugenio Pérez wrote: > On Mon, 2020-02-10 at 12:01 +0100, Christian Borntraeger wrote: >> >> On 10.02.20 10:47, Eugenio Perez Martin wrote: >>> Hi Christian. >>> >>> I'm not able to reproduce the failure with >>> eccb852f1fe6bede630e2e4f1a121a81e34354ab commit. Could you add more data? >>> Your configuration (libvirt or qemu line), and host's dmesg output if any? >>> >>> Thanks! >> >> If it was not obvious, this is on s390x, a big endian system. >> > > Hi Christian. Thank you very much for your fast responses. > > Could you try this patch on top of eccb852f1fe6bede630e2e4f1a121a81e34354ab? I still get [ 43.665145] Guest moved used index from 0 to 289 after some reboots. > > Thanks! > > From 71d0f9108a18aa894cc0c0c1c7efbad39f465a27 Mon Sep 17 00:00:00 2001 > From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= < > epere...@redhat.com> > Date: Tue, 11 Feb 2020 13:19:10 +0100 > Subject: [PATCH] vhost: fix return value of vhost_get_vq_desc > > Before of the batch change, it was the chain's head. Need to keep that > way or we will not be able to free a chain of descriptors. > > Fixes: eccb852f1fe6 ("vhost: batching fetches") > --- > drivers/vhost/vhost.c | 3 +-- > 1 file changed, 1 insertion(+), 2 deletions(-) > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index b5a51b1f2e79..fc422c3e5c08 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -2409,12 +2409,11 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, > *out_num += ret; > } > > - ret = desc->id; > - > if (!(desc->flags & VRING_DESC_F_NEXT)) > break; > } > > + ret = vq->descs[vq->first_desc].id; > vq->first_desc = i + 1; > > return ret; > ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH V2 3/5] vDPA: introduce vDPA bus
On Mon, Feb 10, 2020 at 11:56:06AM +0800, Jason Wang wrote: > +/** > + * vdpa_register_device - register a vDPA device > + * Callers must have a succeed call of vdpa_init_device() before. > + * @vdev: the vdpa device to be registered to vDPA bus > + * > + * Returns an error when fail to add to vDPA bus > + */ > +int vdpa_register_device(struct vdpa_device *vdev) > +{ > + int err = device_add(&vdev->dev); > + > + if (err) { > + put_device(&vdev->dev); > + ida_simple_remove(&vdpa_index_ida, vdev->index); > + } This is a very dangerous construction, I've seen it lead to driver bugs. Better to require the driver to always do the put_device on error unwind The ida_simple_remove should probably be part of the class release function to make everything work right > +/** > + * vdpa_unregister_driver - unregister a vDPA device driver > + * @drv: the vdpa device driver to be unregistered > + */ > +void vdpa_unregister_driver(struct vdpa_driver *drv) > +{ > + driver_unregister(&drv->driver); > +} > +EXPORT_SYMBOL_GPL(vdpa_unregister_driver); > + > +static int vdpa_init(void) > +{ > + if (bus_register(&vdpa_bus) != 0) > + panic("virtio bus registration failed"); > + return 0; > +} Linus will tell you not to kill the kernel - return the error code and propagate it up to the module init function. > +/** > + * vDPA device - representation of a vDPA device > + * @dev: underlying device > + * @dma_dev: the actual device that is performing DMA > + * @config: the configuration ops for this device. > + * @index: device index > + */ > +struct vdpa_device { > + struct device dev; > + struct device *dma_dev; > + const struct vdpa_config_ops *config; > + int index; unsigned values shuld be unsigned int Jason ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 2/2] drm/virtio: fix virtio_gpu_cursor_plane_update().
Add missing virtio_gpu_array_lock_resv() call. Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/virtio/virtgpu_plane.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index ac42c84d2d7f..d1c3f5fbfee4 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -260,6 +260,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane, if (!objs) return; virtio_gpu_array_add_obj(objs, vgfb->base.obj[0]); + virtio_gpu_array_lock_resv(objs); virtio_gpu_cmd_transfer_to_host_2d (vgdev, 0, plane->state->crtc_w, -- 2.18.2 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 1/2] drm/virtio: fix virtio_gpu_execbuffer_ioctl locking
Lockdep says we can't call vmemdup() while having objects reserved because it needs the mmap semaphore. So reorder the calls reserve the objects later. Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 20 ++-- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 205ec4abae2b..0477d1250f2d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -126,22 +126,22 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, bo_handles = NULL; } - if (buflist) { - ret = virtio_gpu_array_lock_resv(buflist); - if (ret) - goto out_unused_fd; - } - buf = vmemdup_user(u64_to_user_ptr(exbuf->command), exbuf->size); if (IS_ERR(buf)) { ret = PTR_ERR(buf); - goto out_unresv; + goto out_unused_fd; + } + + if (buflist) { + ret = virtio_gpu_array_lock_resv(buflist); + if (ret) + goto out_memdup; } out_fence = virtio_gpu_fence_alloc(vgdev); if(!out_fence) { ret = -ENOMEM; - goto out_memdup; + goto out_unresv; } if (out_fence_fd >= 0) { @@ -160,11 +160,11 @@ static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, vfpriv->ctx_id, buflist, out_fence); return 0; -out_memdup: - kvfree(buf); out_unresv: if (buflist) virtio_gpu_array_unlock_resv(buflist); +out_memdup: + kvfree(buf); out_unused_fd: kvfree(bo_handles); if (buflist) -- 2.18.2 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH V2 5/5] vdpasim: vDPA device simulator
On Mon, Feb 10, 2020 at 11:56:08AM +0800, Jason Wang wrote: > + > +static struct vdpasim *vdpasim_create(void) > +{ > + struct vdpasim *vdpasim; > + struct virtio_net_config *config; > + struct vdpa_device *vdpa; > + struct device *dev; > + int ret = -ENOMEM; > + > + vdpasim = kzalloc(sizeof(*vdpasim), GFP_KERNEL); > + if (!vdpasim) > + goto err_vdpa_alloc; > + > + vdpasim->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL); > + if (!vdpasim->buffer) > + goto err_buffer_alloc; > + > + vdpasim->iommu = vhost_iotlb_alloc(2048, 0); > + if (!vdpasim->iommu) > + goto err_iotlb; > + > + config = &vdpasim->config; > + config->mtu = 1500; > + config->status = VIRTIO_NET_S_LINK_UP; > + eth_random_addr(config->mac); > + > + INIT_WORK(&vdpasim->work, vdpasim_work); > + spin_lock_init(&vdpasim->lock); > + > + vdpa = &vdpasim->vdpa; > + vdpa->dev.release = vdpasim_release_dev; The driver should not provide the release function. Again the safest model is 'vdpa_alloc_device' which combines the kzalloc and the vdpa_init_device() and returns something that is error unwound with put_device() The subsystem owns the release and does the kfree and other cleanup like releasing the IDA. > + vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu); > + vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu); > + > + dev = &vdpa->dev; > + dev->coherent_dma_mask = DMA_BIT_MASK(64); > + set_dma_ops(dev, &vdpasim_dma_ops); > + > + ret = vdpa_init_device(vdpa, &vdpasim_dev->dev, dev, > +&vdpasim_net_config_ops); > + if (ret) > + goto err_init; > + > + ret = vdpa_register_device(vdpa); > + if (ret) > + goto err_register; See? This error unwind is now all wrong: > + > + return vdpasim; > + > +err_register: > + put_device(&vdpa->dev); Double put_device > +err_init: > + vhost_iotlb_free(vdpasim->iommu); > +err_iotlb: > + kfree(vdpasim->buffer); > +err_buffer_alloc: > + kfree(vdpasim); kfree after vdpa_init_device() is incorrect, as the put_device now does kfree via release > +static int __init vdpasim_dev_init(void) > +{ > + struct device *dev; > + int ret = 0; > + > + vdpasim_dev = kzalloc(sizeof(*vdpasim_dev), GFP_KERNEL); > + if (!vdpasim_dev) > + return -ENOMEM; > + > + dev = &vdpasim_dev->dev; > + dev->release = vdpasim_device_release; > + dev_set_name(dev, "%s", VDPASIM_NAME); > + > + ret = device_register(&vdpasim_dev->dev); > + if (ret) > + goto err_register; > + > + if (!vdpasim_create()) > + goto err_register; Wrong error unwind here too > + return 0; > + > +err_register: > + kfree(vdpasim_dev); > + vdpasim_dev = NULL; > + return ret; > +} Jason ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH v4] drm/bochs: add drm_driver.release callback.
Call bochs_unload via drm_driver.release to make sure we release stuff when it is safe to do so. Use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. Tidy up here and there. v4: add changelog. v3: use drm_dev_*(). v2: move hardware deinit to pci_remove(). Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/bochs/bochs_drv.c | 6 +++--- drivers/gpu/drm/bochs/bochs_hw.c | 24 +++- 2 files changed, 26 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/bochs/bochs_drv.c b/drivers/gpu/drm/bochs/bochs_drv.c index 10460878414e..addb0568c1af 100644 --- a/drivers/gpu/drm/bochs/bochs_drv.c +++ b/drivers/gpu/drm/bochs/bochs_drv.c @@ -23,7 +23,6 @@ static void bochs_unload(struct drm_device *dev) bochs_kms_fini(bochs); bochs_mm_fini(bochs); - bochs_hw_fini(dev); kfree(bochs); dev->dev_private = NULL; } @@ -69,6 +68,7 @@ static struct drm_driver bochs_driver = { .major = 1, .minor = 0, DRM_GEM_VRAM_DRIVER, + .release= bochs_unload, }; /* -- */ @@ -148,9 +148,9 @@ static void bochs_pci_remove(struct pci_dev *pdev) { struct drm_device *dev = pci_get_drvdata(pdev); + drm_dev_unplug(dev); drm_atomic_helper_shutdown(dev); - drm_dev_unregister(dev); - bochs_unload(dev); + bochs_hw_fini(dev); drm_dev_put(dev); } diff --git a/drivers/gpu/drm/bochs/bochs_hw.c b/drivers/gpu/drm/bochs/bochs_hw.c index b615b7dfdd9d..952199cc0462 100644 --- a/drivers/gpu/drm/bochs/bochs_hw.c +++ b/drivers/gpu/drm/bochs/bochs_hw.c @@ -4,6 +4,7 @@ #include +#include #include #include "bochs.h" @@ -194,6 +195,8 @@ void bochs_hw_fini(struct drm_device *dev) { struct bochs_device *bochs = dev->dev_private; + /* TODO: shot down existing vram mappings */ + if (bochs->mmio) iounmap(bochs->mmio); if (bochs->ioports) @@ -207,6 +210,11 @@ void bochs_hw_fini(struct drm_device *dev) void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode *mode) { + int idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; + bochs->xres = mode->hdisplay; bochs->yres = mode->vdisplay; bochs->bpp = 32; @@ -232,11 +240,18 @@ void bochs_hw_setmode(struct bochs_device *bochs, bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED); + + drm_dev_exit(idx); } void bochs_hw_setformat(struct bochs_device *bochs, const struct drm_format_info *format) { + int idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; + DRM_DEBUG_DRIVER("format %c%c%c%c\n", (format->format >> 0) & 0xff, (format->format >> 8) & 0xff, @@ -256,13 +271,18 @@ void bochs_hw_setformat(struct bochs_device *bochs, __func__, format->format); break; } + + drm_dev_exit(idx); } void bochs_hw_setbase(struct bochs_device *bochs, int x, int y, int stride, u64 addr) { unsigned long offset; - unsigned int vx, vy, vwidth; + unsigned int vx, vy, vwidth, idx; + + if (!drm_dev_enter(bochs->dev, &idx)) + return; bochs->stride = stride; offset = (unsigned long)addr + @@ -277,4 +297,6 @@ void bochs_hw_setbase(struct bochs_device *bochs, bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth); bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx); bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy); + + drm_dev_exit(idx); } -- 2.18.2 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 22/62] x86/sev-es: Add handler for MMIO events
From: Tom Lendacky Add handler for VC exceptions caused by MMIO intercepts. These intercepts come along as nested page faults on pages with reserved bits set. TODO: - Add return values of helper functions - Check permissions on page-table walks - Check data segments Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/sev-es.c | 8 + arch/x86/include/uapi/asm/svm.h | 5 + arch/x86/kernel/sev-es-shared.c | 236 ++ 3 files changed, 249 insertions(+) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 270a23c05f53..55a78b42a2f2 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -67,6 +67,11 @@ static enum es_result es_read_mem(struct es_em_ctxt *ctxt, return ES_OK; } +static phys_addr_t es_slow_virt_to_phys(struct ghcb *ghcb, long vaddr) +{ + return (phys_addr_t)vaddr; +} + #undef __init #undef __pa #define __init @@ -121,6 +126,9 @@ void boot_vc_handler(struct pt_regs *regs) case SVM_EXIT_CPUID: result = handle_cpuid(boot_ghcb, &ctxt); break; + case SVM_EXIT_NPF: + result = handle_mmio(boot_ghcb, &ctxt); + break; default: result = ES_UNSUPPORTED; break; diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index c68d1618c9b0..8f36ae021a7f 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -81,6 +81,11 @@ #define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS 0x402 +/* SEV-ES software-defined VMGEXIT events */ +#define SVM_VMGEXIT_MMIO_READ 0x8001 +#define SVM_VMGEXIT_MMIO_WRITE 0x8002 +#define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000 + #define SVM_EXIT_ERR -1 #define SVM_EXIT_REASONS \ diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 0f422e3b2077..14693eff9614 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -483,3 +483,239 @@ static enum es_result handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ES_OK; } + +/* Map from x86 register index to pt_regs offset */ +static unsigned long *register_from_idx(struct pt_regs *regs, u8 reg) +{ + static int reg2pt_regs[] = { + 10, 11, 12, 5, 19, 4, 13, 14, 9, 8, 7, 6, 3, 2, 1, 0 + }; + unsigned long *regs_array = (unsigned long *)regs; + + if (WARN_ONCE(reg > 15, "register index is not valid: %#hhx\n", reg)) + return NULL; + + return ®s_array[reg2pt_regs[reg]]; +} + +static u64 insn_get_eff_addr(struct es_em_ctxt *ctxt) +{ + u64 effective_addr; + u8 mod, rm; + + if (!ctxt->insn.modrm.nbytes) + return 0; + + if (insn_rip_relative(&ctxt->insn)) + return ctxt->regs->ip + ctxt->insn.displacement.value; + + mod = X86_MODRM_MOD(ctxt->insn.modrm.value); + rm = X86_MODRM_RM(ctxt->insn.modrm.value); + + if (ctxt->insn.rex_prefix.nbytes && + X86_REX_B(ctxt->insn.rex_prefix.value)) + rm |= 0x8; + + if (mod == 3) + return *register_from_idx(ctxt->regs, rm); + + switch (mod) { + case 1: + case 2: + effective_addr = ctxt->insn.displacement.value; + break; + default: + effective_addr = 0; + } + + if (ctxt->insn.sib.nbytes) { + u8 scale, index, base; + + scale = X86_SIB_SCALE(ctxt->insn.sib.value); + index = X86_SIB_INDEX(ctxt->insn.sib.value); + base = X86_SIB_BASE(ctxt->insn.sib.value); + if (ctxt->insn.rex_prefix.nbytes && + X86_REX_X(ctxt->insn.rex_prefix.value)) + index |= 0x8; + if (ctxt->insn.rex_prefix.nbytes && + X86_REX_B(ctxt->insn.rex_prefix.value)) + base |= 0x8; + + if (index != 4) + effective_addr += (*register_from_idx(ctxt->regs, index) + << scale); + + if ((base != 5) || mod) + effective_addr += *register_from_idx(ctxt->regs, base); + else + effective_addr += ctxt->insn.displacement.value; + } else { + effective_addr += *register_from_idx(ctxt->regs, rm); + } + + return effective_addr; +} + +static unsigned long *insn_get_reg(struct es_em_ctxt *ctxt) +{ + u8 reg; + + if (!ctxt->insn.modrm.nbytes) + return NULL; + + reg = X86_MODRM_REG(ctxt->insn.modrm.value); + if (ctxt->insn.rex_prefix.nbytes &
[PATCH 16/62] x86/boot/compressed/64: Check return value of kernel_ident_mapping_init()
From: Joerg Roedel The function can fail to create an identity mapping, check for that and bail out if it happens. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/ident_map_64.c | 7 +-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 5b720736a789..feb180cced28 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -93,6 +93,8 @@ static struct x86_mapping_info mapping_info; */ static void add_identity_map(unsigned long start, unsigned long end) { + int ret; + /* Align boundary to 2M. */ start = round_down(start, PMD_SIZE); end = round_up(end, PMD_SIZE); @@ -100,8 +102,9 @@ static void add_identity_map(unsigned long start, unsigned long end) return; /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, - start, end); + ret = kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, start, end); + if (ret) + error("Error: kernel_ident_mapping_init() failed\n"); } /* Locates and clears a region for a new top level page table. */ -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 19/62] x86/sev-es: Add support for handling IOIO exceptions
From: Tom Lendacky Add support for decoding and handling #VC exceptions for IOIO events. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapted code to #VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/sev-es.c | 3 + arch/x86/kernel/sev-es-shared.c | 214 ++ 2 files changed, 217 insertions(+) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 02fb6f57128b..b2a2d068dc12 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -114,6 +114,9 @@ void boot_vc_handler(struct pt_regs *regs) goto finish; switch (exit_code) { + case SVM_EXIT_IOIO: + result = handle_ioio(boot_ghcb, &ctxt); + break; default: result = ES_UNSUPPORTED; break; diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index f83292c54ab7..bd21a79da084 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -235,3 +235,217 @@ static enum es_result insn_string_write(struct es_em_ctxt *ctxt, return ret; } + +#define IOIO_TYPE_STR BIT(2) +#define IOIO_TYPE_IN 1 +#define IOIO_TYPE_INS (IOIO_TYPE_IN | IOIO_TYPE_STR) +#define IOIO_TYPE_OUT 0 +#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR) + +#define IOIO_REP BIT(3) + +#define IOIO_ADDR_64 BIT(9) +#define IOIO_ADDR_32 BIT(8) +#define IOIO_ADDR_16 BIT(7) + +#define IOIO_DATA_32 BIT(6) +#define IOIO_DATA_16 BIT(5) +#define IOIO_DATA_8BIT(4) + +#define IOIO_SEG_ES(0 << 10) +#define IOIO_SEG_DS(3 << 10) + +static bool insn_repmode(struct insn *insn) +{ + unsigned int i; + + for (i = 0; i < insn->prefixes.nbytes; i++) { + switch (insn->prefixes.bytes[i]) { + case 0xf2: + case 0xf3: + return true; + } + } + + return false; +} + + +static enum es_result ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) +{ + struct insn *insn = &ctxt->insn; + *exitinfo = 0; + + switch (insn->opcode.bytes[0]) { + /* INS opcodes */ + case 0x6c: + case 0x6d: + *exitinfo |= IOIO_TYPE_INS; + *exitinfo |= IOIO_SEG_ES; + *exitinfo |= (ctxt->regs->dx & 0x) << 16; + break; + + /* OUTS opcodes */ + case 0x6e: + case 0x6f: + *exitinfo |= IOIO_TYPE_OUTS; + *exitinfo |= IOIO_SEG_DS; + *exitinfo |= (ctxt->regs->dx & 0x) << 16; + break; + + /* IN immediate opcodes */ + case 0xe4: + case 0xe5: + *exitinfo |= IOIO_TYPE_IN; + *exitinfo |= insn->immediate.value << 16; + break; + + /* OUT immediate opcodes */ + case 0xe6: + case 0xe7: + *exitinfo |= IOIO_TYPE_OUT; + *exitinfo |= insn->immediate.value << 16; + break; + + /* IN register opcodes */ + case 0xec: + case 0xed: + *exitinfo |= IOIO_TYPE_IN; + *exitinfo |= (ctxt->regs->dx & 0x) << 16; + break; + + /* OUT register opcodes */ + case 0xee: + case 0xef: + *exitinfo |= IOIO_TYPE_OUT; + *exitinfo |= (ctxt->regs->dx & 0x) << 16; + break; + + default: + return ES_DECODE_FAILED; + } + + switch (insn->opcode.bytes[0]) { + case 0x6c: + case 0x6e: + case 0xe4: + case 0xe6: + case 0xec: + case 0xee: + /* Single byte opcodes */ + *exitinfo |= IOIO_DATA_8; + break; + default: + /* Length determined by instruction parsing */ + *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16 +: IOIO_DATA_32; + } + switch (insn->addr_bytes) { + case 2: + *exitinfo |= IOIO_ADDR_16; + break; + case 4: + *exitinfo |= IOIO_ADDR_32; + break; + case 8: + *exitinfo |= IOIO_ADDR_64; + break; + } + + if (insn_repmode(insn)) + *exitinfo |= IOIO_REP; + + return ES_OK; +} + +static enum es_result handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + u64 exit_info_1, exit_info_2; + enum es_result ret; + + ret = ioio_exitinfo(ctxt, &exit_info_1); + if (ret != ES_OK) + return ret; + + if (exit_info_1 & IOIO_TYPE_STR) { + int df = (regs->flags & X86_EFLAGS_DF) ? -1 : 1; + unsigned int io_bytes, exit_bytes; + unsigned int ghcb_count, op_count; + u64 sw_scratc
[PATCH 33/62] x86/sev-es: Setup early #VC handler
From: Joerg Roedel Setup an early handler for #VC exceptions. There is no GHCB mapped yet, so just re-use the no_ghcb_vc_handler. It can only handle CPUID exit-codes, but that should be enough to get the kernel through verify_cpu() and __startup_64() until it runs on virtual addresses. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/desc.h | 1 + arch/x86/include/asm/processor.h | 1 + arch/x86/include/asm/sev-es.h| 2 ++ arch/x86/kernel/head64.c | 17 arch/x86/kernel/head_64.S| 35 arch/x86/kernel/idt.c| 10 + 6 files changed, 66 insertions(+) diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 8a4c642ee2b3..cc2db0325f9f 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -388,6 +388,7 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) void update_intr_gate(unsigned int n, const void *addr); void alloc_intr_gate(unsigned int n, const void *addr); +void set_early_idt_handler(gate_desc *idt, int n, void *handler); extern unsigned long system_vectors[]; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 09705ccc393c..4622427d01d4 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -768,6 +768,7 @@ extern int sysenter_setup(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; +extern struct desc_ptr early_idt_descr; extern void switch_to_new_gdt(int); extern void load_direct_gdt(int); diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index 512d3ccb9832..caa29f75ce41 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -75,4 +75,6 @@ static inline u64 copy_lower_bits(u64 out, u64 in, unsigned int bits) return out; } +extern void early_vc_handler(void); + #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index d83c62ebaa85..eab04ac260d4 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -38,6 +38,7 @@ #include #include #include +#include /* * Manage page tables very early on. @@ -516,3 +517,19 @@ void __head early_idt_setup_early_handler(unsigned long physaddr) setup_early_handlers(idt); } + +void __head early_idt_setup(unsigned long physbase) +{ + gate_desc *idt = fixup_pointer(idt_table, physbase); + void __maybe_unused *handler; + +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* VMM Communication Exception */ + handler = fixup_pointer(early_vc_handler, physbase); + set_early_idt_handler(idt, X86_TRAP_VC, handler); +#endif + + /* Initialize IDT descriptor and load IDT */ + early_idt_descr.address = (unsigned long)idt; + native_load_idt(&early_idt_descr); +} diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 81cf6c5763ef..13ebf7d3af2c 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -86,6 +86,12 @@ SYM_CODE_START_NOALIGN(startup_64) .Lon_kernel_cs: UNWIND_HINT_EMPTY + /* Setup IDT - Needed for SEV-ES */ + leaq_text(%rip), %rdi + pushq %rsi + callearly_idt_setup + popq%rsi + /* Sanitize CPU configuration */ call verify_cpu @@ -364,6 +370,32 @@ SYM_CODE_START_LOCAL(early_idt_handler_common) jmp restore_regs_and_return_to_kernel SYM_CODE_END(early_idt_handler_common) +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* + * VC Exception handler used during very early boot. The + * early_idt_handler_array can't be used because it returns via the + * paravirtualized INTERRUPT_RETURN and pv-ops don't work that early. + */ +SYM_CODE_START_NOALIGN(early_vc_handler) + UNWIND_HINT_IRET_REGS offset=8 + + /* Build pt_regs */ + PUSH_AND_CLEAR_REGS + + /* Call C handler */ + movq%rsp, %rdi + callno_ghcb_vc_handler + + /* Unwind pt_regs */ + POP_REGS + + /* Remove Error Code */ + addq$8, %rsp + + /* Pure iret required here - don't use INTERRUPT_RETURN */ + iretq +SYM_CODE_END(early_vc_handler) +#endif #define SYM_DATA_START_PAGE_ALIGNED(name) \ SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) @@ -505,6 +537,9 @@ SYM_DATA_END(level1_fixmap_pgt) SYM_DATA(early_gdt_descr, .word GDT_ENTRIES*8-1) SYM_DATA_LOCAL(early_gdt_descr_base, .quad INIT_PER_CPU_VAR(gdt_page)) +SYM_DATA(early_idt_descr, .word NUM_EXCEPTION_VECTORS * 16) +SYM_DATA_LOCAL(early_idt_descr_base, .quad 0) + .align 16 /* This must match the first entry in level2_kernel_pgt */ SYM_DATA(phys_base, .quad 0x0) diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 84250c090596..1bfee6981e9b 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -393,3 +393,13 @@ void alloc_intr_gate(unsigned int n, const
[PATCH 26/62] x86/head/64: Reload GDT after switch to virtual addresses
From: Joerg Roedel Reload the GDT after switching to virtual addresses to make sure it will not go away when the lower mappings are removed. Signed-off-by: Joerg Roedel --- arch/x86/kernel/head_64.S | 5 + 1 file changed, 5 insertions(+) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 5a3cde971cb7..a3a9383e8dd6 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -157,6 +157,11 @@ SYM_CODE_START(secondary_startup_64) 1: UNWIND_HINT_EMPTY + /* Setup boot GDT descriptor and load boot GDT */ + leaqboot_gdt(%rip), %rax + movq%rax, boot_gdt_base(%rip) + lgdtboot_gdt_descr(%rip) + /* Check if nx is implemented */ movl$0x8001, %eax cpuid -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 03/62] x86/cpufeatures: Add SEV-ES CPU feature
From: Tom Lendacky Add CPU feature detection for Secure Encrypted Virtualization with Encrypted State. This feature enhances SEV by also encrypting the guest register state, making it in-accessible to the hypervisor. Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/amd.c | 4 +++- arch/x86/kernel/cpu/scattered.c| 1 + 3 files changed, 5 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index f3327cb56edf..26e4ee209f7b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -285,6 +285,7 @@ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL(11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SEV_ES (11*32+ 6) /* AMD Secure Encrypted Virtualization - Encrypted State */ /* Intel-defined CPU features, CPUID level 0x0007:1 (EAX), word 12 */ #define X86_FEATURE_AVX512_BF16(12*32+ 5) /* AVX512 BFLOAT16 instructions */ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index ac83a0fef628..aad2223862ef 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -580,7 +580,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) *If BIOS has not enabled SME then don't advertise the *SME feature (set in scattered.c). * For SEV: If BIOS has not enabled SEV then don't advertise the -*SEV feature (set in scattered.c). +*SEV and SEV_ES feature (set in scattered.c). * * In all cases, since support for SME and SEV requires long mode, * don't advertise the feature under CONFIG_X86_32. @@ -611,6 +611,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_SME); clear_sev: setup_clear_cpu_cap(X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV); + setup_clear_cpu_cap(X86_FEATURE_SEV_ES); } } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 62b137c3c97a..30f354989cf1 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -41,6 +41,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_MBA, CPUID_EBX, 6, 0x8008, 0 }, { X86_FEATURE_SME, CPUID_EAX, 0, 0x801f, 0 }, { X86_FEATURE_SEV, CPUID_EAX, 1, 0x801f, 0 }, + { X86_FEATURE_SEV_ES, CPUID_EAX, 3, 0x801f, 0 }, { 0, 0, 0, 0, 0 } }; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 23/62] x86/idt: Move IDT to data segment
From: Joerg Roedel With SEV-ES, exception handling is needed very early, even before the kernel has cleared the bss segment. In order to prevent clearing the currently used IDT, move the IDT to the data segment. Signed-off-by: Joerg Roedel --- arch/x86/kernel/idt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 87ef69a72c52..7f81c1294847 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -166,7 +166,7 @@ static const __initconst struct idt_data dbg_idts[] = { #endif /* Must be page-aligned because the real IDT is used in a fixmap. */ -gate_desc idt_table[IDT_ENTRIES] __page_aligned_bss; +gate_desc idt_table[IDT_ENTRIES] __page_aligned_data; struct desc_ptr idt_descr __ro_after_init = { .size = (IDT_ENTRIES * 2 * sizeof(unsigned long)) - 1, -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 32/62] x86/sev-es: Compile early handler code into kernel image
From: Joerg Roedel Setup sev-es.c and include the code from the pre-decompression stage to also build it into the image of the running kernel. Temporarily add __maybe_unused annotations to avoid build warnings until the functions get used. Signed-off-by: Joerg Roedel --- arch/x86/kernel/Makefile| 1 + arch/x86/kernel/sev-es-shared.c | 24 arch/x86/kernel/sev-es.c| 98 + 3 files changed, 113 insertions(+), 10 deletions(-) create mode 100644 arch/x86/kernel/sev-es.c diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 9b294c13809a..b11bb52e2603 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -143,6 +143,7 @@ obj-$(CONFIG_UNWINDER_ORC) += unwind_orc.o obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o +obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev-es.o ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 14693eff9614..ad2a6c964217 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -9,7 +9,7 @@ * and is included directly into both code-bases. */ -static void terminate(unsigned int reason) +static void __maybe_unused terminate(unsigned int reason) { /* Request Guest Termination from Hypvervisor */ write_ghcb_msr(GHCB_SEV_TERMINATE); @@ -19,7 +19,7 @@ static void terminate(unsigned int reason) asm volatile("hlt\n" : : : "memory"); } -static bool sev_es_negotiate_protocol(void) +static bool __maybe_unused sev_es_negotiate_protocol(void) { u64 val; @@ -38,7 +38,7 @@ static bool sev_es_negotiate_protocol(void) return true; } -static void ghcb_invalidate(struct ghcb *ghcb) +static void __maybe_unused ghcb_invalidate(struct ghcb *ghcb) { memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } @@ -80,9 +80,10 @@ static bool decoding_needed(unsigned long exit_code) exit_code <= SVM_EXIT_LAST_EXCP); } -static enum es_result init_em_ctxt(struct es_em_ctxt *ctxt, - struct pt_regs *regs, - unsigned long exit_code) +static enum es_result __maybe_unused +init_em_ctxt(struct es_em_ctxt *ctxt, +struct pt_regs *regs, +unsigned long exit_code) { enum es_result ret = ES_OK; @@ -95,7 +96,7 @@ static enum es_result init_em_ctxt(struct es_em_ctxt *ctxt, return ret; } -static void finish_insn(struct es_em_ctxt *ctxt) +static void __maybe_unused finish_insn(struct es_em_ctxt *ctxt) { ctxt->regs->ip += ctxt->insn.length; } @@ -358,7 +359,8 @@ static enum es_result ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) return ES_OK; } -static enum es_result handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result __maybe_unused +handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u64 exit_info_1, exit_info_2; @@ -450,7 +452,8 @@ static enum es_result handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -static enum es_result handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result __maybe_unused +handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u32 cr4 = native_read_cr4(); @@ -656,7 +659,8 @@ static enum es_result handle_mmio_twobyte_ops(struct ghcb *ghcb, return ret; } -static enum es_result handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result __maybe_unused +handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct insn *insn = &ctxt->insn; unsigned int bytes = 0; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c new file mode 100644 index ..33ab7fe8b6a0 --- /dev/null +++ b/arch/x86/kernel/sev-es.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2019 SUSE + * + * Author: Joerg Roedel + */ + +#include +#include + +#include +#include +#include +#include +#include + +static inline u64 read_ghcb_msr(void) +{ + return native_read_msr(MSR_AMD64_SEV_ES_GHCB); +} + +static inline void write_ghcb_msr(u64 val) +{ + u32 low, high; + + low = (u32)(val); + high = (u32)(val >> 32); + + native_write_msr(MSR_AMD64_SEV_ES_GHCB, low, high); +} + +static bool check_kernel(struct pt_regs *regs) +{ + return regs->cs == __KERNEL_CS; +} + +static enum es_result es_fetch_insn_byte(struct es_em_ctxt *ctxt, +unsigned int offset, +char *buffer) +{ + char *rip = (char *)ctxt->regs->ip; + + /* More checks are needed when we boot to user-space
[PATCH 04/62] x86/traps: Move some definitions to
From: Joerg Roedel Move the definition of x86 trap vector numbers and the page-fault error code bits to the new header file asm/trap_defs.h. This makes it easier to include them into pre-decompression boot code. No functional changes. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/trap_defs.h | 49 arch/x86/include/asm/traps.h | 44 +--- 2 files changed, 50 insertions(+), 43 deletions(-) create mode 100644 arch/x86/include/asm/trap_defs.h diff --git a/arch/x86/include/asm/trap_defs.h b/arch/x86/include/asm/trap_defs.h new file mode 100644 index ..488f82ac36da --- /dev/null +++ b/arch/x86/include/asm/trap_defs.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRAP_DEFS_H +#define _ASM_X86_TRAP_DEFS_H + +/* Interrupts/Exceptions */ +enum { + X86_TRAP_DE = 0,/* 0, Divide-by-zero */ + X86_TRAP_DB,/* 1, Debug */ + X86_TRAP_NMI, /* 2, Non-maskable Interrupt */ + X86_TRAP_BP,/* 3, Breakpoint */ + X86_TRAP_OF,/* 4, Overflow */ + X86_TRAP_BR,/* 5, Bound Range Exceeded */ + X86_TRAP_UD,/* 6, Invalid Opcode */ + X86_TRAP_NM,/* 7, Device Not Available */ + X86_TRAP_DF,/* 8, Double Fault */ + X86_TRAP_OLD_MF,/* 9, Coprocessor Segment Overrun */ + X86_TRAP_TS,/* 10, Invalid TSS */ + X86_TRAP_NP,/* 11, Segment Not Present */ + X86_TRAP_SS,/* 12, Stack Segment Fault */ + X86_TRAP_GP,/* 13, General Protection Fault */ + X86_TRAP_PF,/* 14, Page Fault */ + X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */ + X86_TRAP_MF,/* 16, x87 Floating-Point Exception */ + X86_TRAP_AC,/* 17, Alignment Check */ + X86_TRAP_MC,/* 18, Machine Check */ + X86_TRAP_XF,/* 19, SIMD Floating-Point Exception */ + X86_TRAP_IRET = 32, /* 32, IRET Exception */ +}; + +/* + * Page fault error code bits: + * + * bit 0 == 0: no page found 1: protection fault + * bit 1 == 0: read access 1: write access + * bit 2 == 0: kernel-mode access 1: user-mode access + * bit 3 == 1: use of reserved bit detected + * bit 4 == 1: fault was an instruction fetch + * bit 5 == 1: protection keys block access + */ +enum x86_pf_error_code { + X86_PF_PROT = 1 << 0, + X86_PF_WRITE= 1 << 1, + X86_PF_USER = 1 << 2, + X86_PF_RSVD = 1 << 3, + X86_PF_INSTR= 1 << 4, + X86_PF_PK = 1 << 5, +}; + +#endif /* _ASM_X86_TRAP_DEFS_H */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index ffa0dc8a535e..2aa786484bb1 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -5,6 +5,7 @@ #include #include +#include #include #include/* TRAP_TRACE, ... */ @@ -132,47 +133,4 @@ void __noreturn handle_stack_overflow(const char *message, unsigned long fault_address); #endif -/* Interrupts/Exceptions */ -enum { - X86_TRAP_DE = 0,/* 0, Divide-by-zero */ - X86_TRAP_DB,/* 1, Debug */ - X86_TRAP_NMI, /* 2, Non-maskable Interrupt */ - X86_TRAP_BP,/* 3, Breakpoint */ - X86_TRAP_OF,/* 4, Overflow */ - X86_TRAP_BR,/* 5, Bound Range Exceeded */ - X86_TRAP_UD,/* 6, Invalid Opcode */ - X86_TRAP_NM,/* 7, Device Not Available */ - X86_TRAP_DF,/* 8, Double Fault */ - X86_TRAP_OLD_MF,/* 9, Coprocessor Segment Overrun */ - X86_TRAP_TS,/* 10, Invalid TSS */ - X86_TRAP_NP,/* 11, Segment Not Present */ - X86_TRAP_SS,/* 12, Stack Segment Fault */ - X86_TRAP_GP,/* 13, General Protection Fault */ - X86_TRAP_PF,/* 14, Page Fault */ - X86_TRAP_SPURIOUS, /* 15, Spurious Interrupt */ - X86_TRAP_MF,/* 16, x87 Floating-Point Exception */ - X86_TRAP_AC,/* 17, Alignment Check */ - X86_TRAP_MC,/* 18, Machine Check */ - X86_TRAP_XF,/* 19, SIMD Floating-Point Exception */ - X86_TRAP_IRET = 32, /* 32, IRET Exception */ -}; - -/* - * Page fault error code bits: - * - * bit 0 == 0: no page found 1: protection fault - * bit 1 == 0: read access 1: write access - * bit 2 == 0: kernel-mode access 1: user-mode access - * bit 3 == 1: use of reserved bit detected - * bit 4 ==
[PATCH 06/62] x86/boot/compressed: Fix debug_puthex() parameter type
From: Joerg Roedel In the CONFIG_X86_VERBOSE_BOOTUP=Y case the debug_puthex() macro just turns into __puthex, which takes 'unsigned long' as parameter. But in the CONFIG_X86_VERBOSE_BOOTUP=N case it is a function which takes 'unsigned char *', causing compile warnings when the function is used. Fix the parameter type to get rid of the warnings. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/misc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index c8181392f70d..726e264410ff 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -59,7 +59,7 @@ void __puthex(unsigned long value); static inline void debug_putstr(const char *s) { } -static inline void debug_puthex(const char *s) +static inline void debug_puthex(unsigned long value) { } #define debug_putaddr(x) /* */ -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 14/62] x86/boot/compressed/64: Add stage1 #VC handler
From: Joerg Roedel Add the first handler for #VC exceptions. At stage 1 there is no GHCB yet becaue we might still be on the EFI page table and thus can't map memory unencrypted. The stage 1 handler is limited to the MSR based protocol to talk to the hypervisor and can only support CPUID exit-codes, but that is enough to get to stage 2. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/Makefile | 1 + arch/x86/boot/compressed/idt_64.c | 4 ++ arch/x86/boot/compressed/idt_handlers_64.S | 4 ++ arch/x86/boot/compressed/misc.h| 1 + arch/x86/boot/compressed/sev-es.c | 42 ++ arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/asm/sev-es.h | 45 +++ arch/x86/include/asm/trap_defs.h | 1 + arch/x86/kernel/sev-es-shared.c| 66 ++ 9 files changed, 165 insertions(+) create mode 100644 arch/x86/boot/compressed/sev-es.c create mode 100644 arch/x86/include/asm/sev-es.h create mode 100644 arch/x86/kernel/sev-es-shared.c diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e6b3e0fc48de..583678c78e1b 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -84,6 +84,7 @@ ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 84ba57d9d436..bdd20dfd1fd0 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -31,6 +31,10 @@ void load_stage1_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; +#ifdef CONFIG_AMD_MEM_ENCRYPT + set_idt_entry(X86_TRAP_VC, boot_stage1_vc_handler); +#endif + load_boot_idt(&boot_idt_desc); } diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index f7f1ea66dcbf..330eb4e5c8b3 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -71,3 +71,7 @@ SYM_FUNC_END(\name) .code64 EXCEPTION_HANDLER boot_pf_handler do_boot_page_fault error_code=1 + +#ifdef CONFIG_AMD_MEM_ENCRYPT +EXCEPTION_HANDLER boot_stage1_vc_handler no_ghcb_vc_handler error_code=1 +#endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 4e5bc688f467..0e3508c5c15c 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -141,5 +141,6 @@ extern struct desc_ptr boot_idt_desc; /* IDT Entry Points */ void boot_pf_handler(void); +void boot_stage1_vc_handler(void); #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c new file mode 100644 index ..8d13121a8cf2 --- /dev/null +++ b/arch/x86/boot/compressed/sev-es.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + */ + +#include + +#include +#include +#include +#include + +#include "misc.h" + +static inline u64 read_ghcb_msr(void) +{ + unsigned long low, high; + + asm volatile("rdmsr\n" : "=a" (low), "=d" (high) : + "c" (MSR_AMD64_SEV_ES_GHCB)); + + return ((high << 32) | low); +} + +static inline void write_ghcb_msr(u64 val) +{ + u32 low, high; + + low = val & 0xUL; + high = val >> 32; + + asm volatile("wrmsr\n" : : "c" (MSR_AMD64_SEV_ES_GHCB), + "a"(low), "d" (high) : "memory"); +} + +#undef __init +#define __init + +/* Include code for early handlers */ +#include "../../kernel/sev-es-shared.c" diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ebe1685e92dd..b6139b70db54 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -432,6 +432,7 @@ #define MSR_AMD64_IBSBRTARGET 0xc001103b #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h new file mode 100644 index ..f524b40aef07 --- /dev/null +++ b/arch/x86/include/asm/sev-es.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + */ + +#ifndef __ASM_ENCRYPTED_STATE_H +#define __ASM_ENCRYPTED_STATE_H + +#include + +#define GHCB_SEV_CPUID_REQ 0x0
[PATCH 13/62] x86/boot/compressed/64: Change add_identity_map() to take start and end
From: Joerg Roedel Changing the function to take start and end as parameters instead of start and size simplifies the callers, which don't need to calculate the size if they already have start and end. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/ident_map_64.c | 15 +-- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index ab7a3d9705c0..ba5b88189220 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -91,10 +91,8 @@ static struct x86_mapping_info mapping_info; /* * Adds the specified range to the identity mappings. */ -static void add_identity_map(unsigned long start, unsigned long size) +static void add_identity_map(unsigned long start, unsigned long end) { - unsigned long end = start + size; - /* Align boundary to 2M. */ start = round_down(start, PMD_SIZE); end = round_up(end, PMD_SIZE); @@ -109,8 +107,6 @@ static void add_identity_map(unsigned long start, unsigned long size) /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { - unsigned long start, size; - /* If running as an SEV guest, the encryption mask is required. */ set_sev_encryption_mask(); @@ -157,9 +153,7 @@ void initialize_identity_maps(void) * New page-table is set up - map the kernel image and load it * into cr3. */ - start = (unsigned long)_head; - size = _end - _head; - add_identity_map(start, size); + add_identity_map((unsigned long)_head, (unsigned long)_end); write_cr3(top_level_pgt); } @@ -180,7 +174,8 @@ static void pf_error(unsigned long error_code, unsigned long address, void do_boot_page_fault(struct pt_regs *regs) { - unsigned long address = native_read_cr2(); + unsigned long address = native_read_cr2() & PMD_MASK; + unsigned long end = address + PMD_SIZE; unsigned long error_code = regs->orig_ax; /* @@ -196,5 +191,5 @@ void do_boot_page_fault(struct pt_regs *regs) * Error code is sane - now identity map the 2M region around * the faulting address. */ - add_identity_map(address & PMD_MASK, PMD_SIZE); + add_identity_map(address, end); } -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 15/62] x86/boot/compressed/64: Call set_sev_encryption_mask earlier
From: Joerg Roedel Call set_sev_encryption_mask() while still on the stage 1 #VC-handler, because the stage 2 handler needs our own page-tables to be set up, to which calling set_sev_encryption_mask() is a prerequisite. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/head_64.S | 8 +++- arch/x86/boot/compressed/ident_map_64.c | 3 --- 2 files changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 5164d2e8631a..5557f899b22b 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -491,9 +491,15 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) rep stosq /* - * Load stage2 IDT and switch to our own page-table + * If running as a SEV guest, the encryption mask is required in the + * page-table setup code below. When the guest also has SEV-ES enabled + * set_sev_encryption_mask() will cause #VC exceptions, but the stage2 + * handler can't map its GHCB because the page-table is not set up yet. + * So set up the encryption mask here while still on the stage1 #VC + * handler. Then load stage2 IDT and switch to our own page-table. */ pushq %rsi + callset_sev_encryption_mask callload_stage2_idt callinitialize_identity_maps popq%rsi diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index ba5b88189220..5b720736a789 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -107,9 +107,6 @@ static void add_identity_map(unsigned long start, unsigned long end) /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { - /* If running as an SEV guest, the encryption mask is required. */ - set_sev_encryption_mask(); - /* Exclude the encryption mask from __PHYSICAL_MASK */ physical_mask &= ~sme_me_mask; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 18/62] x86/boot/compressed/64: Setup GHCB Based VC Exception handler
From: Joerg Roedel Install an exception handler for #VC exception that uses a GHCB. Also add the infrastructure for handling different exit-codes by decoding the instruction that caused the exception and error handling. Signed-off-by: Joerg Roedel --- arch/x86/Kconfig | 1 + arch/x86/boot/compressed/idt_64.c | 4 + arch/x86/boot/compressed/idt_handlers_64.S | 1 + arch/x86/boot/compressed/misc.h| 1 + arch/x86/boot/compressed/sev-es.c | 91 +++ arch/x86/include/asm/sev-es.h | 33 arch/x86/include/uapi/asm/svm.h| 1 + arch/x86/kernel/sev-es-shared.c| 171 + 8 files changed, 303 insertions(+) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index beea77046f9b..c12347492589 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1526,6 +1526,7 @@ config AMD_MEM_ENCRYPT select DYNAMIC_PHYSICAL_MASK select ARCH_USE_MEMREMAP_PROT select ARCH_HAS_FORCE_DMA_UNENCRYPTED + select INSTRUCTION_DECODER ---help--- Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index bdd20dfd1fd0..eebb2f857dac 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -45,5 +45,9 @@ void load_stage2_idt(void) set_idt_entry(X86_TRAP_PF, boot_pf_handler); +#ifdef CONFIG_AMD_MEM_ENCRYPT + set_idt_entry(X86_TRAP_VC, boot_stage2_vc_handler); +#endif + load_boot_idt(&boot_idt_desc); } diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 330eb4e5c8b3..3c71a11beee0 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -74,4 +74,5 @@ EXCEPTION_HANDLER boot_pf_handler do_boot_page_fault error_code=1 #ifdef CONFIG_AMD_MEM_ENCRYPT EXCEPTION_HANDLER boot_stage1_vc_handler no_ghcb_vc_handler error_code=1 +EXCEPTION_HANDLER boot_stage2_vc_handler boot_vc_handler error_code=1 #endif diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 42f68a858a35..567d71ab5ed9 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -143,5 +143,6 @@ extern struct desc_ptr boot_idt_desc; /* IDT Entry Points */ void boot_pf_handler(void); void boot_stage1_vc_handler(void); +void boot_stage2_vc_handler(void); #endif /* BOOT_COMPRESSED_MISC_H */ diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 8d13121a8cf2..02fb6f57128b 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -8,12 +8,16 @@ #include #include +#include #include #include #include #include "misc.h" +struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); +struct ghcb *boot_ghcb; + static inline u64 read_ghcb_msr(void) { unsigned long low, high; @@ -35,8 +39,95 @@ static inline void write_ghcb_msr(u64 val) "a"(low), "d" (high) : "memory"); } +static enum es_result es_fetch_insn_byte(struct es_em_ctxt *ctxt, +unsigned int offset, +char *buffer) +{ + char *rip = (char *)ctxt->regs->ip; + + buffer[offset] = rip[offset]; + + return ES_OK; +} + +static enum es_result es_write_mem(struct es_em_ctxt *ctxt, + void *dst, char *buf, size_t size) +{ + memcpy(dst, buf, size); + + return ES_OK; +} + +static enum es_result es_read_mem(struct es_em_ctxt *ctxt, + void *src, char *buf, size_t size) +{ + memcpy(buf, src, size); + + return ES_OK; +} + #undef __init +#undef __pa #define __init +#define __pa(x)((unsigned long)(x)) + +#define __BOOT_COMPRESSED + +/* Basic instruction decoding support needed */ +#include "../../lib/inat.c" +#include "../../lib/insn.c" /* Include code for early handlers */ #include "../../kernel/sev-es-shared.c" + +static bool setup_ghcb(void) +{ + if (!sev_es_negotiate_protocol()) + terminate(GHCB_SEV_ES_REASON_PROTOCOL_UNSUPPORTED); + + if (set_page_decrypted((unsigned long)&boot_ghcb_page)) + return false; + + /* Page is now mapped decrypted, clear it */ + memset(&boot_ghcb_page, 0, sizeof(boot_ghcb_page)); + + boot_ghcb = &boot_ghcb_page; + + /* Initialize lookup tables for the instruction decoder */ + inat_init_tables(); + + return true; +} + +void boot_vc_handler(struct pt_regs *regs) +{ + unsigned long exit_code = regs->orig_ax; + struct es_em_ctxt ctxt; + enum es_result result; + + if (!boot_ghcb && !setup_ghcb()) + terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST
[PATCH 05/62] x86/insn-decoder: Make inat-tables.c suitable for pre-decompression code
From: Joerg Roedel The inat-tables.c file has some arrays in it that contain pointers to other arrays. These pointers need to be relocated when the kernel image is moved to a different location. The pre-decompression boot-code has no support for applying ELF relocations, so initialize these arrays at runtime in the pre-decompression code to make sure all pointers are correctly initialized. Signed-off-by: Joerg Roedel --- arch/x86/tools/gen-insn-attr-x86.awk | 50 +- tools/arch/x86/tools/gen-insn-attr-x86.awk | 50 +- 2 files changed, 98 insertions(+), 2 deletions(-) diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f4..af38469afd14 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -362,6 +362,9 @@ function convert_operands(count,opnd, i,j,imm,mod) END { if (awkchecked != "") exit 1 + + print "#ifndef __BOOT_COMPRESSED\n" + # print escape opcode map's array print "/* Escape opcode map array */" print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \ @@ -388,6 +391,51 @@ END { for (j = 0; j < max_lprefix; j++) if (atable[i,j]) print " ["i"]["j"] = "atable[i,j]"," - print "};" + print "};\n" + + print "#else /* !__BOOT_COMPRESSED */\n" + + print "/* Escape opcode map array */" + print "static const insn_attr_t *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* Group opcode map array */" + print "static const insn_attr_t *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* AVX opcode map array */" + print "static const insn_attr_t *inat_avx_tables[X86_VEX_M_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "static void inat_init_tables(void)" + print "{" + + # print escape opcode map's array + print "\t/* Print Escape opcode map array */" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print "\tinat_escape_tables["i"]["j"] = "etable[i,j]";" + print "" + + # print group opcode map's array + print "\t/* Print Group opcode map array */" + for (i = 0; i < ggid; i++) + for (j = 0; j < max_lprefix; j++) + if (gtable[i,j]) + print "\tinat_group_tables["i"]["j"] = "gtable[i,j]";" + print "" + # print AVX opcode map's array + print "\t/* Print AVX opcode map array */" + for (i = 0; i < gaid; i++) + for (j = 0; j < max_lprefix; j++) + if (atable[i,j]) + print "\tinat_avx_tables["i"]["j"] = "atable[i,j]";" + + print "}" + print "#endif" } diff --git a/tools/arch/x86/tools/gen-insn-attr-x86.awk b/tools/arch/x86/tools/gen-insn-attr-x86.awk index a42015b305f4..af38469afd14 100644 --- a/tools/arch/x86/tools/gen-insn-attr-x86.awk +++ b/tools/arch/x86/tools/gen-insn-attr-x86.awk @@ -362,6 +362,9 @@ function convert_operands(count,opnd, i,j,imm,mod) END { if (awkchecked != "") exit 1 + + print "#ifndef __BOOT_COMPRESSED\n" + # print escape opcode map's array print "/* Escape opcode map array */" print "const insn_attr_t * const inat_escape_tables[INAT_ESC_MAX + 1]" \ @@ -388,6 +391,51 @@ END { for (j = 0; j < max_lprefix; j++) if (atable[i,j]) print " ["i"]["j"] = "atable[i,j]"," - print "};" + print "};\n" + + print "#else /* !__BOOT_COMPRESSED */\n" + + print "/* Escape opcode map array */" + print "static const insn_attr_t *inat_escape_tables[INAT_ESC_MAX + 1]" \ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* Group opcode map array */" + print "static const insn_attr_t *inat_group_tables[INAT_GRP_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "/* AVX opcode map array */" + print "static const insn_attr_t *inat_avx_tables[X86_VEX_M_MAX + 1]"\ + "[INAT_LSTPFX_MAX + 1];" + print "" + + print "static void inat_init_tables(void)" + print "{" + + # print escape opcode map's array + print "\t/* Print Escape opcode map array */" + for (i = 0; i < geid; i++) + for (j = 0; j < max_lprefix; j++) + if (etable[i,j]) + print "\tinat_escape_tables["i"]["j"] = "etable[i,j]";" + print "" + + # print group opcode map's array + print "\t/* Print Group opcode
[PATCH 35/62] x86/sev-es: Setup per-cpu GHCBs for the runtime handler
From: Tom Lendacky The runtime handler needs a GHCB per CPU. Set them up and map them unencrypted. Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel --- arch/x86/include/asm/mem_encrypt.h | 2 ++ arch/x86/kernel/sev-es.c | 25 - arch/x86/kernel/traps.c| 3 +++ 3 files changed, 29 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 6f61bb93366a..d48e7be9bb49 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -48,6 +48,7 @@ int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); void __init mem_encrypt_init(void); void __init mem_encrypt_free_decrypted_mem(void); +void __init encrypted_state_init_ghcbs(void); bool sme_active(void); bool sev_active(void); bool sev_es_active(void); @@ -71,6 +72,7 @@ static inline void __init sme_early_init(void) { } static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } +static inline void encrypted_state_init_ghcbs(void) { } static inline bool sme_active(void) { return false; } static inline bool sev_active(void) { return false; } static inline bool sev_es_active(void) { return false; } diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0e0b28477627..9a5530857db7 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -8,8 +8,11 @@ */ #include /* For show_regs() */ -#include +#include +#include #include +#include +#include #include #include @@ -28,6 +31,9 @@ struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); */ struct ghcb __initdata *boot_ghcb; +/* Runtime GHCBs */ +static DEFINE_PER_CPU_DECRYPTED(struct ghcb, ghcb_page) __aligned(PAGE_SIZE); + /* Needed in early_forward_exception */ extern void early_exception(struct pt_regs *regs, int trapnr); @@ -133,6 +139,23 @@ static bool __init setup_ghcb(void) return true; } +void encrypted_state_init_ghcbs(void) +{ + int cpu; + + if (!sev_es_active()) + return; + + /* Initialize per-cpu GHCB pages */ + for_each_possible_cpu(cpu) { + struct ghcb *ghcb = &per_cpu(ghcb_page, cpu); + + set_memory_decrypted((unsigned long)ghcb, +sizeof(ghcb_page) >> PAGE_SHIFT); + memset(ghcb, 0, sizeof(*ghcb)); + } +} + static void __init early_forward_exception(struct es_em_ctxt *ctxt) { int trapnr = ctxt->fi.vector; diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 6ef00eb6fbb9..9c9a7fae36d3 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -918,6 +918,9 @@ void __init trap_init(void) /* Init cpu_entry_area before IST entries are set up */ setup_cpu_entry_areas(); + /* Init GHCB memory pages when running as an SEV-ES guest */ + encrypted_state_init_ghcbs(); + idt_setup_traps(); /* -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 20/62] x86/fpu: Move xgetbv()/xsetbv() into separate header
From: Joerg Roedel The xgetbv() function is needed in pre-decompression boot code, but asm/fpu/internal.h can't be included there directly. Doing so opens the door to include-hell due to various include-magic in boot/compressed/misc.h. Avoid that by moving xgetbv()/xsetbv() to a separate header file and include this instead. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/fpu/internal.h | 29 +- arch/x86/include/asm/fpu/xcr.h | 32 + 2 files changed, 33 insertions(+), 28 deletions(-) create mode 100644 arch/x86/include/asm/fpu/xcr.h diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 44c48e34d799..795fc049988e 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -19,6 +19,7 @@ #include #include #include +#include #include #include @@ -614,32 +615,4 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) } __write_pkru(pkru_val); } - -/* - * MXCSR and XCR definitions: - */ - -extern unsigned int mxcsr_feature_mask; - -#define XCR_XFEATURE_ENABLED_MASK 0x - -static inline u64 xgetbv(u32 index) -{ - u32 eax, edx; - - asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ -: "=a" (eax), "=d" (edx) -: "c" (index)); - return eax + ((u64)edx << 32); -} - -static inline void xsetbv(u32 index, u64 value) -{ - u32 eax = value; - u32 edx = value >> 32; - - asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ -: : "a" (eax), "d" (edx), "c" (index)); -} - #endif /* _ASM_X86_FPU_INTERNAL_H */ diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h new file mode 100644 index ..91ee45712737 --- /dev/null +++ b/arch/x86/include/asm/fpu/xcr.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FPU_XCR_H +#define _ASM_X86_FPU_XCR_H + +/* + * MXCSR and XCR definitions: + */ + +extern unsigned int mxcsr_feature_mask; + +#define XCR_XFEATURE_ENABLED_MASK 0x + +static inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */ +: "=a" (eax), "=d" (edx) +: "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */ +: : "a" (eax), "d" (edx), "c" (index)); +} + +#endif /* _ASM_X86_FPU_XCR_H */ -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 39/62] x86/sev-es: Harden runtime #VC handler for exceptions from user-space
From: Joerg Roedel Send SIGBUS to the user-space process that caused the #VC exception instead of killing the machine. Also ratelimit the error messages so that user-space can't flood the kernel log. Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 32 +++- 1 file changed, 23 insertions(+), 9 deletions(-) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index f5bff4219f6f..d128a9397639 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -254,16 +254,16 @@ dotraplinkage void do_vmm_communication(struct pt_regs *regs, unsigned long exit finish_insn(&ctxt); break; case ES_UNSUPPORTED: - pr_emerg("Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n", -exit_code, regs->ip); + pr_err_ratelimited("Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n", + exit_code, regs->ip); goto fail; case ES_VMM_ERROR: - pr_emerg("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n", -exit_code, regs->ip); + pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n", + exit_code, regs->ip); goto fail; case ES_DECODE_FAILED: - pr_emerg("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n", -exit_code, regs->ip); + pr_err_ratelimited("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n", + exit_code, regs->ip); goto fail; case ES_EXCEPTION: forward_exception(&ctxt); @@ -278,10 +278,24 @@ dotraplinkage void do_vmm_communication(struct pt_regs *regs, unsigned long exit return; fail: - show_regs(regs); + if (user_mode(regs)) { + /* +* Do not kill the machine if user-space triggered the +* exception. Send SIGBUS instead and let user-space deal with +* it. +*/ + force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0); + } else { + /* Show some debug info */ + show_regs(regs); - while (true) - halt(); + /* Ask hypervisor to terminate */ + terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); + + /* If that fails and we get here - just halt the machine */ + while (true) + halt(); + } } int __init boot_vc_exception(struct pt_regs *regs) -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 07/62] x86/boot/compressed/64: Disable red-zone usage
From: Joerg Roedel The x86-64 ABI defines a red-zone on the stack: The 128-byte area beyond the location pointed to by %rsp is considered to be reserved and shall not be modified by signal or interrupt handlers. 10 Therefore, functions may use this area for temporary data that is not needed across function calls. In particular, leaf functions may use this area for their entire stack frame, rather than adjusting the stack pointer in the prologue and epilogue. This area is known as the red zone. This is not compatible with exception handling, so disable it for the pre-decompression boot code. Signed-off-by: Joerg Roedel --- arch/x86/boot/Makefile| 2 +- arch/x86/boot/compressed/Makefile | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 012b82fc8617..8f55e4ce1ccc 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -65,7 +65,7 @@ clean-files += cpustr.h # --- -KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP +KBUILD_CFLAGS := $(REALMODE_CFLAGS) -D_SETUP -mno-red-zone KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__ KBUILD_CFLAGS += $(call cc-option,-fmacro-prefix-map=$(srctree)/=) GCOV_PROFILE := n diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 26050ae0b27e..e186cc0b628d 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -30,7 +30,7 @@ KBUILD_CFLAGS := -m$(BITS) -O2 KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC) KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING cflags-$(CONFIG_X86_32) := -march=i386 -cflags-$(CONFIG_X86_64) := -mcmodel=small +cflags-$(CONFIG_X86_64) := -mcmodel=small -mno-red-zone KBUILD_CFLAGS += $(cflags-y) KBUILD_CFLAGS += -mno-mmx -mno-sse KBUILD_CFLAGS += $(call cc-option,-ffreestanding) @@ -87,7 +87,7 @@ endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o -$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone +$(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o \ $(objtree)/drivers/firmware/efi/libstub/lib.a -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 36/62] x86/sev-es: Add Runtime #VC Exception Handler
From: Tom Lendacky Add the handler for #VC exceptions invoked at runtime. Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel --- arch/x86/entry/entry_64.S| 4 ++ arch/x86/include/asm/traps.h | 7 arch/x86/kernel/idt.c| 4 +- arch/x86/kernel/sev-es.c | 77 +++- 4 files changed, 90 insertions(+), 2 deletions(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f2bb91e87877..729876d368c5 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1210,6 +1210,10 @@ idtentry async_page_faultdo_async_page_fault has_error_code=1read_cr2=1 idtentry machine_check do_mce has_error_code=0 paranoid=1 #endif +#ifdef CONFIG_AMD_MEM_ENCRYPT +idtentry vmm_communication do_vmm_communicationhas_error_code=1 +#endif + /* * Save all registers in pt_regs, and switch gs if needed. * Use slow, but surefire "are we in kernel?" check. diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 2aa786484bb1..1be25c065698 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -35,6 +35,9 @@ asmlinkage void alignment_check(void); #ifdef CONFIG_X86_MCE asmlinkage void machine_check(void); #endif /* CONFIG_X86_MCE */ +#ifdef CONFIG_AMD_MEM_ENCRYPT +asmlinkage void vmm_communication(void); +#endif asmlinkage void simd_coprocessor_error(void); #if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV) @@ -93,6 +96,10 @@ dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code); dotraplinkage void do_machine_check(struct pt_regs *regs, long error_code); #endif dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code); +#ifdef CONFIG_AMD_MEM_ENCRYPT +dotraplinkage void do_vmm_communication_error(struct pt_regs *regs, + long error_code); +#endif #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code); #endif diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 1bfee6981e9b..94f6a5705e1d 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -95,8 +95,10 @@ static const __initconst struct idt_data def_idts[] = { #ifdef CONFIG_X86_MCE INTG(X86_TRAP_MC, &machine_check), #endif - SYSG(X86_TRAP_OF, overflow), +#ifdef CONFIG_AMD_MEM_ENCRYPT + INTG(X86_TRAP_VC, vmm_communication), +#endif #if defined(CONFIG_IA32_EMULATION) SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), #elif defined(CONFIG_X86_32) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 9a5530857db7..1fb7128ff386 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include /* For early boot hypervisor communication in SEV-ES enabled guests */ @@ -184,6 +184,81 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, return result; } +static void forward_exception(struct es_em_ctxt *ctxt) +{ + long error_code = ctxt->fi.error_code; + int trapnr = ctxt->fi.vector; + + ctxt->regs->orig_ax = ctxt->fi.error_code; + + switch (trapnr) { + case X86_TRAP_GP: + do_general_protection(ctxt->regs, error_code); + break; + case X86_TRAP_UD: + do_invalid_op(ctxt->regs, 0); + break; + default: + BUG(); + } +} + +dotraplinkage void do_vmm_communication(struct pt_regs *regs, unsigned long exit_code) +{ + struct es_em_ctxt ctxt; + enum es_result result; + struct ghcb *ghcb; + + /* +* This is invoked through an interrupt gate, so IRQs are disabled. The +* code below might walk page-tables for user or kernel addresses, so +* keep the IRQs disabled to protect us against concurrent TLB flushes. +*/ + + ghcb = this_cpu_ptr(&ghcb_page); + + ghcb_invalidate(ghcb); + result = init_em_ctxt(&ctxt, regs, exit_code); + + if (result == ES_OK) + result = handle_vc_exception(&ctxt, ghcb, exit_code); + + /* Done - now check the result */ + switch (result) { + case ES_OK: + finish_insn(&ctxt); + break; + case ES_UNSUPPORTED: + pr_emerg("Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n", +exit_code, regs->ip); + goto fail; + case ES_VMM_ERROR: + pr_emerg("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n", +exit_code, regs->ip); + goto fail; + case ES_DECODE_FAILED: + pr_emerg("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n", +exit_code, regs->ip); +
[PATCH 28/62] x86/head/64: Switch to initial stack earlier
From: Joerg Roedel Make sure there is a stack once the kernel runs from virual addresses. At this stage any secondary CPU which boots will have lost its stack because the kernel switched to a new page-table which does not map the real-mode stack anymore. This is also needed for handling early #VC exceptions caused by instructions like CPUID. Signed-off-by: Joerg Roedel --- arch/x86/kernel/head_64.S | 9 ++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 36f2f30ad200..eefd6838b895 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -188,6 +188,12 @@ SYM_CODE_START(secondary_startup_64) movlinitial_gs+4(%rip),%edx wrmsr + /* +* Setup a boot time stack - Any secondary CPU will have lost its stack +* by now because the cr3-switch above unmaps the real-mode stack +*/ + movq initial_stack(%rip), %rsp + /* Check if nx is implemented */ movl$0x8001, %eax cpuid @@ -208,9 +214,6 @@ SYM_CODE_START(secondary_startup_64) /* Make changes effective */ movq%rax, %cr0 - /* Setup a boot time stack */ - movq initial_stack(%rip), %rsp - /* zero EFLAGS after setting rsp */ pushq $0 popfq -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 40/62] x86/sev-es: Filter exceptions not supported from user-space
From: Joerg Roedel Currently only CPUID caused #VC exceptions are supported from user-space. Filter the others out early. Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 24 1 file changed, 24 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index d128a9397639..84b5b8f7897a 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -209,6 +209,26 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, return result; } +static enum es_result context_filter(struct pt_regs *regs, long exit_code) +{ + enum es_result r = ES_OK; + + if (user_mode(regs)) { + switch (exit_code) { + /* List of #VC exit-codes we support in user-space */ + case SVM_EXIT_EXCP_BASE ... SVM_EXIT_LAST_EXCP: + case SVM_EXIT_CPUID: + r = ES_OK; + break; + default: + r = ES_UNSUPPORTED; + break; + } + } + + return r; +} + static void forward_exception(struct es_em_ctxt *ctxt) { long error_code = ctxt->fi.error_code; @@ -245,6 +265,10 @@ dotraplinkage void do_vmm_communication(struct pt_regs *regs, unsigned long exit ghcb_invalidate(ghcb); result = init_em_ctxt(&ctxt, regs, exit_code); + /* Check if the exception is supported in the context we came from. */ + if (result == ES_OK) + result = context_filter(regs, exit_code); + if (result == ES_OK) result = handle_vc_exception(&ctxt, ghcb, exit_code); -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 12/62] x86/boot/compressed/64: Don't pre-map memory in KASLR code
From: Joerg Roedel With the page-fault handler in place the identity mapping can be built on-demand. So remove the code which manually creates the mappings and unexport/remove the functions used for it. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/ident_map_64.c | 16 ++-- arch/x86/boot/compressed/kaslr.c| 24 +--- arch/x86/boot/compressed/misc.h | 10 -- 3 files changed, 3 insertions(+), 47 deletions(-) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 6a3890caaa19..ab7a3d9705c0 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -89,11 +89,9 @@ phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; static struct x86_mapping_info mapping_info; /* - * Adds the specified range to what will become the new identity mappings. - * Once all ranges have been added, the new mapping is activated by calling - * finalize_identity_maps() below. + * Adds the specified range to the identity mappings. */ -void add_identity_map(unsigned long start, unsigned long size) +static void add_identity_map(unsigned long start, unsigned long size) { unsigned long end = start + size; @@ -165,16 +163,6 @@ void initialize_identity_maps(void) write_cr3(top_level_pgt); } -/* - * This switches the page tables to the new level4 that has been built - * via calls to add_identity_map() above. If booted via startup_32(), - * this is effectively a no-op. - */ -void finalize_identity_maps(void) -{ - write_cr3(top_level_pgt); -} - static void pf_error(unsigned long error_code, unsigned long address, struct pt_regs *regs) { diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 856dc1c9bb0d..c466fb738de0 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -399,8 +399,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, */ mem_avoid[MEM_AVOID_ZO_RANGE].start = input; mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; - add_identity_map(mem_avoid[MEM_AVOID_ZO_RANGE].start, -mem_avoid[MEM_AVOID_ZO_RANGE].size); /* Avoid initrd. */ initrd_start = (u64)boot_params->ext_ramdisk_image << 32; @@ -420,14 +418,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, ; mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line; mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size; - add_identity_map(mem_avoid[MEM_AVOID_CMDLINE].start, -mem_avoid[MEM_AVOID_CMDLINE].size); /* Avoid boot parameters. */ mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); - add_identity_map(mem_avoid[MEM_AVOID_BOOTPARAMS].start, -mem_avoid[MEM_AVOID_BOOTPARAMS].size); /* We don't need to set a mapping for setup_data. */ @@ -436,11 +430,6 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, /* Enumerate the immovable memory regions */ num_immovable_mem = count_immovable_mem_regions(); - -#ifdef CONFIG_X86_VERBOSE_BOOTUP - /* Make sure video RAM can be used. */ - add_identity_map(0, PMD_SIZE); -#endif } /* @@ -919,19 +908,8 @@ void choose_random_location(unsigned long input, warn("Physical KASLR disabled: no suitable memory region!"); } else { /* Update the new physical address location. */ - if (*output != random_addr) { - add_identity_map(random_addr, output_size); + if (*output != random_addr) *output = random_addr; - } - - /* -* This loads the identity mapping page table. -* This should only be done if a new physical address -* is found for the kernel, otherwise we should keep -* the old page table to make it be like the "nokaslr" -* case. -*/ - finalize_identity_maps(); } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index eff4ed0b1cea..4e5bc688f467 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -98,17 +98,7 @@ static inline void choose_random_location(unsigned long input, #endif #ifdef CONFIG_X86_64 -void initialize_identity_maps(void); -void add_identity_map(unsigned long start, unsigned long size); -void finalize_identity_maps(void); extern unsigned char _pgtable[]; -#else -static inline void initialize_identity_maps(void) -{ } -static inline void add_identity_map(unsigned long start, unsigned long size) -{ } -static inline void finalize_identity_m
[PATCH 37/62] x86/sev-es: Wire up existing #VC exit-code handlers
From: Joerg Roedel Re-use the handlers for CPUID and IOIO caused #VC exceptions in the early boot handler. Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es-shared.c | 9 +++-- arch/x86/kernel/sev-es.c| 9 + 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 57c29c91fe87..14693eff9614 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -358,8 +358,7 @@ static enum es_result ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) return ES_OK; } -static enum es_result __maybe_unused -handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u64 exit_info_1, exit_info_2; @@ -451,8 +450,7 @@ handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -static enum es_result __maybe_unused -handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; u32 cr4 = native_read_cr4(); @@ -658,8 +656,7 @@ static enum es_result handle_mmio_twobyte_ops(struct ghcb *ghcb, return ret; } -static enum es_result __maybe_unused -handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct insn *insn = &ctxt->insn; unsigned int bytes = 0; diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 1fb7128ff386..2a801919e7c0 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -174,6 +174,15 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, enum es_result result; switch (exit_code) { + case SVM_EXIT_CPUID: + result = handle_cpuid(ghcb, ctxt); + break; + case SVM_EXIT_IOIO: + result = handle_ioio(ghcb, ctxt); + break; + case SVM_EXIT_NPF: + result = handle_mmio(ghcb, ctxt); + break; default: /* * Unexpected #VC exception -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 08/62] x86/boot/compressed/64: Add IDT Infrastructure
From: Joerg Roedel Add code needed to setup an IDT in the early pre-decompression boot-code. The IDT is loaded first in startup_64, which is after EfiExitBootServices() has been called, and later reloaded when the kernel image has been relocated to the end of the decompression area. This allows to setup different IDT handlers before and after the relocation. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/Makefile | 1 + arch/x86/boot/compressed/head_64.S | 34 +++ arch/x86/boot/compressed/idt_64.c | 43 + arch/x86/boot/compressed/idt_handlers_64.S | 71 ++ arch/x86/boot/compressed/misc.h| 5 ++ arch/x86/include/asm/desc_defs.h | 3 + 6 files changed, 157 insertions(+) create mode 100644 arch/x86/boot/compressed/idt_64.c create mode 100644 arch/x86/boot/compressed/idt_handlers_64.S diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e186cc0b628d..54d63526e856 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -81,6 +81,7 @@ vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o + vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o endif diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 1f1f6c8139b3..d27a9ce1bcb0 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -33,6 +33,7 @@ #include #include #include +#include #include "pgtable.h" /* @@ -358,6 +359,10 @@ SYM_CODE_START(startup_64) movq%rax, gdt64+2(%rip) lgdtgdt64(%rip) + pushq %rsi + callload_stage1_idt + popq%rsi + /* * paging_prepare() sets up the trampoline and checks if we need to * enable 5-level paging. @@ -465,6 +470,16 @@ SYM_FUNC_END_ALIAS(efi_stub_entry) .text SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) +/* + * Reload GDT after relocation - The GDT at the non-relocated position + * might be overwritten soon by the in-place decompression, so reload + * GDT at the relocated address. The GDT is referenced by exception + * handling and needs to be set up correctly. + */ + leaqgdt(%rip), %rax + movq%rax, gdt64+2(%rip) + lgdtgdt64(%rip) + /* * Clear BSS (stack is currently empty) */ @@ -475,6 +490,13 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) shrq$3, %rcx rep stosq +/* + * Load stage2 IDT + */ + pushq %rsi + callload_stage2_idt + popq%rsi + /* * Do the extraction, and jump to the new kernel.. */ @@ -628,6 +650,18 @@ SYM_DATA_START_LOCAL(gdt) .quad 0x /* TS continued */ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) +SYM_DATA_START(boot_idt_desc) + .word boot_idt_end - boot_idt + .quad 0 +SYM_DATA_END(boot_idt_desc) + .balign 8 +SYM_DATA_START(boot_idt) + .rept BOOT_IDT_ENTRIES + .quad 0 + .quad 0 + .endr +SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) + #ifdef CONFIG_EFI_MIXED SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0) SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c new file mode 100644 index ..46ecea671b90 --- /dev/null +++ b/arch/x86/boot/compressed/idt_64.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include "misc.h" + +static void set_idt_entry(int vector, void (*handler)(void)) +{ + unsigned long address = (unsigned long)handler; + gate_desc entry; + + memset(&entry, 0, sizeof(entry)); + + entry.offset_low= (u16)(address & 0x); + entry.segment = __KERNEL_CS; + entry.bits.type = GATE_TRAP; + entry.bits.p= 1; + entry.offset_middle = (u16)((address >> 16) & 0x); + entry.offset_high = (u32)(address >> 32); + + memcpy(&boot_idt[vector], &entry, sizeof(entry)); +} + +/* Have this here so we don't need to include */ +static void load_boot_idt(const struct desc_ptr *dtr) +{ + asm volatile("lidt %0"::"m" (*dtr)); +} + +/* Setup IDT before kernel jumping to .Lrelocated */ +void load_stage1_idt(void) +{ + boot_idt_desc.address = (unsigned long)boot_idt; + + load_boot_idt(&boot_idt_desc); +} + +/* Setup IDT after kernel jumping to .Lrelocated */ +void load_stage2_idt(void) +{ + boot_idt_desc.address = (unsigned long)boot_idt; + + load_boot_idt(&boot_idt_desc); +} diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S new file mode 100644 index ..0
[PATCH 02/62] KVM: SVM: Add GHCB Accessor functions
From: Joerg Roedel Building a correct GHCB for the hypervisor requires setting valid bits in the GHCB. Simplify that process by providing accessor functions to set values and to update the valid bitmap. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/svm.h | 61 ++ 1 file changed, 61 insertions(+) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index f36288c659b5..e4e9f6bacfaa 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -333,4 +333,65 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) +/* GHCB Accessor functions */ + +#define DEFINE_GHCB_INDICES(field) \ + u16 idx = offsetof(struct vmcb_save_area, field) / 8; \ + u16 byte_idx = idx / 8;\ + u16 bit_idx = idx % 8;\ + BUILD_BUG_ON(byte_idx > ARRAY_SIZE(ghcb->save.valid_bitmap)); + +#define GHCB_SET_VALID(ghcb, field)\ + { \ + DEFINE_GHCB_INDICES(field) \ + (ghcb)->save.valid_bitmap[byte_idx] |= BIT(bit_idx);\ + } + +#define DEFINE_GHCB_SETTER(field) \ + static inline void \ + ghcb_set_##field(struct ghcb *ghcb, u64 value) \ + { \ + GHCB_SET_VALID(ghcb, field) \ + (ghcb)->save.field = value; \ + } + +#define DEFINE_GHCB_ACCESSORS(field) \ + static inline bool ghcb_is_valid_##field(const struct ghcb *ghcb) \ + { \ + DEFINE_GHCB_INDICES(field) \ + return !!((ghcb)->save.valid_bitmap[byte_idx] \ + & BIT(bit_idx));\ + } \ + \ + static inline void \ + ghcb_set_##field(struct ghcb *ghcb, u64 value) \ + { \ + GHCB_SET_VALID(ghcb, field) \ + (ghcb)->save.field = value; \ + } + +DEFINE_GHCB_ACCESSORS(cpl) +DEFINE_GHCB_ACCESSORS(rip) +DEFINE_GHCB_ACCESSORS(rsp) +DEFINE_GHCB_ACCESSORS(rax) +DEFINE_GHCB_ACCESSORS(rcx) +DEFINE_GHCB_ACCESSORS(rdx) +DEFINE_GHCB_ACCESSORS(rbx) +DEFINE_GHCB_ACCESSORS(rbp) +DEFINE_GHCB_ACCESSORS(rsi) +DEFINE_GHCB_ACCESSORS(rdi) +DEFINE_GHCB_ACCESSORS(r8) +DEFINE_GHCB_ACCESSORS(r9) +DEFINE_GHCB_ACCESSORS(r10) +DEFINE_GHCB_ACCESSORS(r11) +DEFINE_GHCB_ACCESSORS(r12) +DEFINE_GHCB_ACCESSORS(r13) +DEFINE_GHCB_ACCESSORS(r14) +DEFINE_GHCB_ACCESSORS(r15) +DEFINE_GHCB_ACCESSORS(sw_exit_code) +DEFINE_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_GHCB_ACCESSORS(sw_scratch) +DEFINE_GHCB_ACCESSORS(xcr0) + #endif -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 31/62] x86/sev-es: Add SEV-ES Feature Detection
From: Joerg Roedel Add the sev_es_active function for checking whether SEV-ES is enabled. Also cache the value of MSR_AMD64_SEV at boot to speed up the feature checking in the running code. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/mem_encrypt.h | 3 +++ arch/x86/include/asm/msr-index.h | 2 ++ arch/x86/mm/mem_encrypt.c | 11 ++- arch/x86/mm/mem_encrypt_identity.c | 3 +++ 4 files changed, 18 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 848ce43b9040..6f61bb93366a 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -19,6 +19,7 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT extern u64 sme_me_mask; +extern u64 sev_status; extern bool sev_enabled; void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr, @@ -49,6 +50,7 @@ void __init mem_encrypt_free_decrypted_mem(void); bool sme_active(void); bool sev_active(void); +bool sev_es_active(void); #define __bss_decrypted __attribute__((__section__(".bss..decrypted"))) @@ -71,6 +73,7 @@ static inline void __init sme_enable(struct boot_params *bp) { } static inline bool sme_active(void) { return false; } static inline bool sev_active(void) { return false; } +static inline bool sev_es_active(void) { return false; } static inline int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b6139b70db54..1411c37b6cd9 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -435,7 +435,9 @@ #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index a03614bd3e1a..a35fcba24866 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -38,7 +38,9 @@ * section is later cleared. */ u64 sme_me_mask __section(.data) = 0; +u64 sev_status __section(.data) = 0; EXPORT_SYMBOL(sme_me_mask); +EXPORT_SYMBOL(sev_status); DEFINE_STATIC_KEY_FALSE(sev_enable_key); EXPORT_SYMBOL_GPL(sev_enable_key); @@ -347,9 +349,16 @@ bool sme_active(void) bool sev_active(void) { - return sme_me_mask && sev_enabled; + return !!(sev_status & MSR_AMD64_SEV_ENABLED); } +bool sev_es_active(void) +{ + return !!(sev_status & MSR_AMD64_SEV_ES_ENABLED); +} +EXPORT_SYMBOL_GPL(sev_es_active); + + /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index e2b0e2ac07bb..68d75379e06a 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -540,6 +540,9 @@ void __init sme_enable(struct boot_params *bp) if (!(msr & MSR_AMD64_SEV_ENABLED)) return; + /* Save SEV_STATUS to avoid reading MSR again */ + sev_status = msr; + /* SEV state cannot be controlled by a command line option */ sme_me_mask = me_mask; sev_enabled = true; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[RFC PATCH 00/62] Linux as SEV-ES Guest Support
Hi, here is the first public post of the patch-set to enable Linux to run under SEV-ES enabled hypervisors. The code is mostly feature-complete, but there are still a couple of bugs to fix. Nevertheless, given the size of the patch-set, I think it is about time to ask for initial feedback of the changes that come with it. To better understand the code here is a quick explanation of SEV-ES first. This patch-set does not contain the hypervisor changes necessary to run SEV-ES enabled KVM guests. These patches will be sent separatly when they are ready to be sent out. What is SEV-ES == SEV-ES is an acronym for 'Secure Encrypted Virtualization - Encrypted State' and means a hardware feature of AMD processors which hides the register state of VCPUs to the hypervisor by encrypting it. The hypervisor can't read or make changes to the guests register state. Most intercepts set by the hypervisor do not cause a #VMEXIT of the guest anymore, but turn into a VMM Communication Exception (#VC exception, vector 29) inside the guest. The error-code of this exception is the intercept exit-code that caused the exception. The guest handles the #VC exception by communicating with the hypervisor through a shared data structure, the 'Guest-Hypervisor-Communication-Block' (GHCB). The layout of that data-structure and the protocol is specified in [1]. A description of the SEV-ES hardware interface can be found in the AMD64 Architecture Programmer's Manual Volume 2, Section 15.35 [2]. Implementation Details == SEV-ES guests will always boot via UEFI firmware and use the 64-bit EFI entry point into the kernel. This implies that only 64-bit Linux x86 guests are supported. Pre-Decompression Boot Code and Early Exception Support --- Intercepts that cause exceptions in the guest include instructions like CPUID, RDMSR/WRMSR, IOIO instructions and a couple more. Some of them are executed very early during boot, which means that exceptions need to work that early. That is the reason big parts of this patch-set enable support for early exceptions, first in the pre-decompression boot-code and later also in the early boot-code of the kernel image. As these patches add exception support to the pre-decompression boot code, it also implements a page-fault handler to create the identity-mapped page-table on-demand. One reason for this change is to make use of the exception handling code in non SEV-ES guests too, so that it is less likely to break in the future. The other reason is that for SEV-ES guests the code needs to setup its own page-table to map the GHCB unencrypted. Without these patches the pre-decompression code only uses its own page-table when KASLR is enabled and used. SIPI and INIT Handling -- The hypervisor also can't make changes to the guest register state, which implies that it can't emulate SIPI and INIT messages. This means that any CPU register state reset needs to be done inside the guest. Most of this is handled in the firmware, but the Linux kernel has to setup an AP Jump Table to boot secondary processors. CPU online/offline handling also needs special handling, where this patch-set implements a shortcut. An offlined CPU will not go back to real-mode when it is woken up again, but stays in long-mode an just jumps back to the trampoline code. NMI Special Handling The last thing that needs special handling with SEV-ES are NMIs. Hypervisors usually start to intercept IRET instructions when an NMI got injected to find out when the NMI window is re-opened. But handling IRET intercepts requires the hypervisor to access guest register state and is not possible with SEV-ES. The specification under [1] solves this problem with an NMI_COMPLETE message sent my the guest to the hypervisor, upon which the hypervisor re-opens the NMI window for the guest. This patch-set sends the NMI_COMPLETE message before the actual IRET, while the kernel is still on a valid stack and kernel cr3. This opens the NMI-window a few instructions early, but this is fine as under x86-64 Linux NMI-nesting is safe. The alternative would be to single-step over the IRET, but that requires more intrusive changes to the entry code because it does not handle entries from kernel-mode while on the entry stack. Besides the special handling above the patch-set contains the handlers for the #VC exception and all the exit-codes specified in [1]. Current State of the Patches The patch-set posted here can boot an SMP Linux guest under SEV-ES-enabled KVM and the guest survives some load-testing (kernel-compiles). The guest boots to the graphical desktop and is usable. But there are still know bugs and issues: * Putting some NMI-load on the guest will make it crash usually within a minute * The handler for MMIO events needs more security checks when walking the page-
[PATCH 11/62] x86/boot/compressed/64: Always switch to own page-table
From: Joerg Roedel When booted through startup_64 the kernel keeps running on the EFI page-table until the KASLR code sets up its own page-table. Without KASLR the pre-decompression boot code never switches off the EFI page-table. Change that by unconditionally switching to our own page-table once the kernel is relocated. This makes sure we can make changes to the mapping when necessary, for example map pages unencrypted in SEV and SEV-ES guests. Also remove the debug_putstr() calls in initialize_identity_maps() because the function now runs before console_init() is called. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/head_64.S | 3 +- arch/x86/boot/compressed/ident_map_64.c | 51 +++-- arch/x86/boot/compressed/kaslr.c| 3 -- 3 files changed, 32 insertions(+), 25 deletions(-) diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d27a9ce1bcb0..5164d2e8631a 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -491,10 +491,11 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lrelocated) rep stosq /* - * Load stage2 IDT + * Load stage2 IDT and switch to our own page-table */ pushq %rsi callload_stage2_idt + callinitialize_identity_maps popq%rsi /* diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 0865d181b85d..6a3890caaa19 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -88,9 +88,31 @@ phys_addr_t physical_mask = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; */ static struct x86_mapping_info mapping_info; +/* + * Adds the specified range to what will become the new identity mappings. + * Once all ranges have been added, the new mapping is activated by calling + * finalize_identity_maps() below. + */ +void add_identity_map(unsigned long start, unsigned long size) +{ + unsigned long end = start + size; + + /* Align boundary to 2M. */ + start = round_down(start, PMD_SIZE); + end = round_up(end, PMD_SIZE); + if (start >= end) + return; + + /* Build the mapping. */ + kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, + start, end); +} + /* Locates and clears a region for a new top level page table. */ void initialize_identity_maps(void) { + unsigned long start, size; + /* If running as an SEV guest, the encryption mask is required. */ set_sev_encryption_mask(); @@ -123,37 +145,24 @@ void initialize_identity_maps(void) */ top_level_pgt = read_cr3_pa(); if (p4d_offset((pgd_t *)top_level_pgt, 0) == (p4d_t *)_pgtable) { - debug_putstr("booted via startup_32()\n"); pgt_data.pgt_buf = _pgtable + BOOT_INIT_PGT_SIZE; pgt_data.pgt_buf_size = BOOT_PGT_SIZE - BOOT_INIT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); } else { - debug_putstr("booted via startup_64()\n"); pgt_data.pgt_buf = _pgtable; pgt_data.pgt_buf_size = BOOT_PGT_SIZE; memset(pgt_data.pgt_buf, 0, pgt_data.pgt_buf_size); top_level_pgt = (unsigned long)alloc_pgt_page(&pgt_data); } -} -/* - * Adds the specified range to what will become the new identity mappings. - * Once all ranges have been added, the new mapping is activated by calling - * finalize_identity_maps() below. - */ -void add_identity_map(unsigned long start, unsigned long size) -{ - unsigned long end = start + size; - - /* Align boundary to 2M. */ - start = round_down(start, PMD_SIZE); - end = round_up(end, PMD_SIZE); - if (start >= end) - return; - - /* Build the mapping. */ - kernel_ident_mapping_init(&mapping_info, (pgd_t *)top_level_pgt, - start, end); + /* +* New page-table is set up - map the kernel image and load it +* into cr3. +*/ + start = (unsigned long)_head; + size = _end - _head; + add_identity_map(start, size); + write_cr3(top_level_pgt); } /* diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 7c61a8c5b9cf..856dc1c9bb0d 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -903,9 +903,6 @@ void choose_random_location(unsigned long input, boot_params->hdr.loadflags |= KASLR_FLAG; - /* Prepare to add new identity pagetables on demand. */ - initialize_identity_maps(); - /* Record the various known unsafe memory ranges. */ mem_avoid_init(input, input_size, *output); -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/li
[PATCH 10/62] x86/boot/compressed/64: Add page-fault handler
From: Joerg Roedel Install a page-fault handler to add an identity mapping to addresses not yet mapped. Also do some checking whether the error code is sane. This makes non SEV-ES machines use the exception handling infrastructure in the pre-decompressions boot code too, making it less likely to break in the future. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/ident_map_64.c| 38 ++ arch/x86/boot/compressed/idt_64.c | 2 ++ arch/x86/boot/compressed/idt_handlers_64.S | 2 ++ arch/x86/boot/compressed/misc.h| 6 4 files changed, 48 insertions(+) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 3a2115582920..0865d181b85d 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -19,11 +19,13 @@ /* No PAGE_TABLE_ISOLATION support needed either: */ #undef CONFIG_PAGE_TABLE_ISOLATION +#include "error.h" #include "misc.h" /* These actually do the work of building the kernel identity maps. */ #include #include +#include /* Use the static base for this part of the boot process */ #undef __PAGE_OFFSET #define __PAGE_OFFSET __PAGE_OFFSET_BASE @@ -163,3 +165,39 @@ void finalize_identity_maps(void) { write_cr3(top_level_pgt); } + +static void pf_error(unsigned long error_code, unsigned long address, +struct pt_regs *regs) +{ + error_putstr("Unexpected page-fault:"); + error_putstr("\nError Code: "); + error_puthex(error_code); + error_putstr("\nCR2: 0x"); + error_puthex(address); + error_putstr("\nRIP relative to _head: 0x"); + error_puthex(regs->ip - (unsigned long)_head); + error_putstr("\n"); + + error("Stopping.\n"); +} + +void do_boot_page_fault(struct pt_regs *regs) +{ + unsigned long address = native_read_cr2(); + unsigned long error_code = regs->orig_ax; + + /* +* Check for unexpected error codes. Unexpected are: +* - Faults on present pages +* - User faults +* - Reserved bits set +*/ + if (error_code & (X86_PF_PROT | X86_PF_USER | X86_PF_RSVD)) + pf_error(error_code, address, regs); + + /* +* Error code is sane - now identity map the 2M region around +* the faulting address. +*/ + add_identity_map(address & PMD_MASK, PMD_SIZE); +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 46ecea671b90..84ba57d9d436 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -39,5 +39,7 @@ void load_stage2_idt(void) { boot_idt_desc.address = (unsigned long)boot_idt; + set_idt_entry(X86_TRAP_PF, boot_pf_handler); + load_boot_idt(&boot_idt_desc); } diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 0b2b6cf747d2..f7f1ea66dcbf 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -69,3 +69,5 @@ SYM_FUNC_END(\name) .text .code64 + +EXCEPTION_HANDLER boot_pf_handler do_boot_page_fault error_code=1 diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 3a030a878d53..eff4ed0b1cea 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -37,6 +37,9 @@ #define memptr unsigned #endif +/* boot/compressed/vmlinux start and end markers */ +extern char _head[], _end[]; + /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; @@ -146,4 +149,7 @@ extern pteval_t __default_kernel_pte_mask; extern gate_desc boot_idt[BOOT_IDT_ENTRIES]; extern struct desc_ptr boot_idt_desc; +/* IDT Entry Points */ +void boot_pf_handler(void); + #endif /* BOOT_COMPRESSED_MISC_H */ -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 30/62] x86/head/64: Move early exception dispatch to C code
From: Joerg Roedel Move the assembly coded dispatch between page-faults and all other exceptions to C code to make it easier to maintain and extend. Signed-off-by: Joerg Roedel --- arch/x86/kernel/head64.c | 20 arch/x86/kernel/head_64.S | 11 +-- 2 files changed, 21 insertions(+), 10 deletions(-) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 7cdfb7113811..d83c62ebaa85 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -36,6 +36,8 @@ #include #include #include +#include +#include /* * Manage page tables very early on. @@ -377,6 +379,24 @@ int __init early_make_pgtable(unsigned long address) return __early_make_pgtable(address, pmd); } +void __init early_exception(struct pt_regs *regs, int trapnr) +{ + unsigned long cr2; + int r; + + switch (trapnr) { + case X86_TRAP_PF: + cr2 = native_read_cr2(); + r = early_make_pgtable(cr2); + break; + default: + r = 1; + } + + if (r) + early_fixup_exception(regs, trapnr); +} + /* Don't add a printk in there. printk relies on the PDA which is not initialized yet. */ static void __init clear_bss(void) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 0af79f783659..81cf6c5763ef 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -357,18 +357,9 @@ SYM_CODE_START_LOCAL(early_idt_handler_common) pushq %r15 /* pt_regs->r15 */ UNWIND_HINT_REGS - cmpq $14,%rsi /* Page fault? */ - jnz 10f - GET_CR2_INTO(%rdi) /* can clobber %rax if pv */ - call early_make_pgtable - andl %eax,%eax - jz 20f /* All good */ - -10: movq %rsp,%rdi /* RDI = pt_regs; RSI is already trapnr */ - call early_fixup_exception + call early_exception -20: decl early_recursion_flag(%rip) jmp restore_regs_and_return_to_kernel SYM_CODE_END(early_idt_handler_common) -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 21/62] x86/sev-es: Add CPUID handling to #VC handler
From: Tom Lendacky Handle #VC exceptions caused by CPUID instructions. These happen in early boot code when the KASLR code checks for RDTSC. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/sev-es.c | 4 arch/x86/kernel/sev-es-shared.c | 34 +++ 2 files changed, 38 insertions(+) diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index b2a2d068dc12..270a23c05f53 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -117,6 +118,9 @@ void boot_vc_handler(struct pt_regs *regs) case SVM_EXIT_IOIO: result = handle_ioio(boot_ghcb, &ctxt); break; + case SVM_EXIT_CPUID: + result = handle_cpuid(boot_ghcb, &ctxt); + break; default: result = ES_UNSUPPORTED; break; diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index bd21a79da084..0f422e3b2077 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -449,3 +449,37 @@ static enum es_result handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } + +static enum es_result handle_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + u32 cr4 = native_read_cr4(); + enum es_result ret; + + ghcb_set_rax(ghcb, regs->ax); + ghcb_set_rcx(ghcb, regs->cx); + + if (cr4 & X86_CR4_OSXSAVE) + /* Safe to read xcr0 */ + ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK)); + else + /* xgetbv will cause #GP - use reset value for xcr0 */ + ghcb_set_xcr0(ghcb, 1); + + ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_is_valid_rax(ghcb) && + ghcb_is_valid_rbx(ghcb) && + ghcb_is_valid_rcx(ghcb) && + ghcb_is_valid_rdx(ghcb))) + return ES_VMM_ERROR; + + regs->ax = ghcb->save.rax; + regs->bx = ghcb->save.rbx; + regs->cx = ghcb->save.rcx; + regs->dx = ghcb->save.rdx; + + return ES_OK; +} -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 01/62] KVM: SVM: Add GHCB definitions
From: Tom Lendacky Extend the vmcb_safe_area with SEV-ES fields and add a new 'struct ghcb' which will be used for guest-hypervisor communication. Signed-off-by: Tom Lendacky Signed-off-by: Joerg Roedel --- arch/x86/include/asm/svm.h | 42 ++ 1 file changed, 42 insertions(+) diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 6ece8561ba66..f36288c659b5 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -201,6 +201,48 @@ struct __attribute__ ((__packed__)) vmcb_save_area { u64 br_to; u64 last_excp_from; u64 last_excp_to; + + /* +* The following part of the save area is valid only for +* SEV-ES guests when referenced through the GHCB. +*/ + u8 reserved_7[104]; + u64 reserved_8; /* rax already available at 0x01f8 */ + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_9; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_10[16]; + u64 sw_exit_code; + u64 sw_exit_info_1; + u64 sw_exit_info_2; + u64 sw_scratch; + u8 reserved_11[56]; + u64 xcr0; + u8 valid_bitmap[16]; + u64 x87_state_gpa; + u8 reserved_12[1016]; +}; + +struct __attribute__ ((__packed__)) ghcb { + struct vmcb_save_area save; + + u8 shared_buffer[2032]; + + u8 reserved_1[10]; + u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ + u32 ghcb_usage; }; struct __attribute__ ((__packed__)) vmcb { -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 27/62] x86/head/64: Load segment registers earlier
From: Joerg Roedel Make sure segments are properly set up before setting up an IDT and doing anything that might cause a #VC exception. This is later needed for early exception handling. Signed-off-by: Joerg Roedel --- arch/x86/kernel/head_64.S | 52 +++ 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index a3a9383e8dd6..36f2f30ad200 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -162,6 +162,32 @@ SYM_CODE_START(secondary_startup_64) movq%rax, boot_gdt_base(%rip) lgdtboot_gdt_descr(%rip) + /* set up data segments */ + xorl %eax,%eax + movl %eax,%ds + movl %eax,%ss + movl %eax,%es + + /* +* We don't really need to load %fs or %gs, but load them anyway +* to kill any stale realmode selectors. This allows execution +* under VT hardware. +*/ + movl %eax,%fs + movl %eax,%gs + + /* Set up %gs. +* +* The base of %gs always points to fixed_percpu_data. If the +* stack protector canary is enabled, it is located at %gs:40. +* Note that, on SMP, the boot cpu uses init data section until +* the per cpu areas are set up. +*/ + movl$MSR_GS_BASE,%ecx + movlinitial_gs(%rip),%eax + movlinitial_gs+4(%rip),%edx + wrmsr + /* Check if nx is implemented */ movl$0x8001, %eax cpuid @@ -197,32 +223,6 @@ SYM_CODE_START(secondary_startup_64) */ lgdtearly_gdt_descr(%rip) - /* set up data segments */ - xorl %eax,%eax - movl %eax,%ds - movl %eax,%ss - movl %eax,%es - - /* -* We don't really need to load %fs or %gs, but load them anyway -* to kill any stale realmode selectors. This allows execution -* under VT hardware. -*/ - movl %eax,%fs - movl %eax,%gs - - /* Set up %gs. -* -* The base of %gs always points to fixed_percpu_data. If the -* stack protector canary is enabled, it is located at %gs:40. -* Note that, on SMP, the boot cpu uses init data section until -* the per cpu areas are set up. -*/ - movl$MSR_GS_BASE,%ecx - movlinitial_gs(%rip),%eax - movlinitial_gs+4(%rip),%edx - wrmsr - /* rsi is pointer to real mode structure with interesting info. pass it to C */ movq%rsi, %rdi -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 17/62] x86/boot/compressed/64: Add function to map a page unencrypted
From: Joerg Roedel This function is needed to map the GHCB for SEV-ES guests. The GHCB is used for communication with the hypervisor, so its content must not be encrypted. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/ident_map_64.c | 125 arch/x86/boot/compressed/misc.h | 1 + 2 files changed, 126 insertions(+) diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index feb180cced28..04a5ff4bda66 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -26,6 +26,7 @@ #include #include #include +#include /* Use the static base for this part of the boot process */ #undef __PAGE_OFFSET #define __PAGE_OFFSET __PAGE_OFFSET_BASE @@ -157,6 +158,130 @@ void initialize_identity_maps(void) write_cr3(top_level_pgt); } +static pte_t *split_large_pmd(struct x86_mapping_info *info, + pmd_t *pmdp, unsigned long __address) +{ + unsigned long page_flags; + unsigned long address; + pte_t *pte; + pmd_t pmd; + int i; + + pte = (pte_t *)info->alloc_pgt_page(info->context); + if (!pte) + return NULL; + + address = __address & PMD_MASK; + /* No large page - clear PSE flag */ + page_flags = info->page_flag & ~_PAGE_PSE; + + /* Populate the PTEs */ + for (i = 0; i < PTRS_PER_PMD; i++) { + set_pte(&pte[i], __pte(address | page_flags)); + address += PAGE_SIZE; + } + + /* +* Ideally we need to clear the large PMD first and do a TLB +* flush before we write the new PMD. But the 2M range of the +* PMD might contain the code we execute and/or the stack +* we are on, so we can't do that. But that should be safe here +* because we are going from large to small mappings and we are +* also the only user of the page-table, so there is no chance +* of a TLB multihit. +*/ + pmd = __pmd((unsigned long)pte | info->kernpg_flag); + set_pmd(pmdp, pmd); + /* Flush TLB to establish the new PMD */ + write_cr3(top_level_pgt); + + return pte + pte_index(__address); +} + +static void clflush_page(unsigned long address) +{ + unsigned int flush_size; + char *cl, *start, *end; + + /* +* Hardcode cl-size to 64 - CPUID can't be used here because that might +* cause another #VC exception and the GHCB is not ready to use yet. +*/ + flush_size = 64; + start = (char *)(address & PAGE_MASK); + end= start + PAGE_SIZE; + + /* +* First make sure there are no pending writes on the cache-lines to +* flush. +*/ + asm volatile("mfence" : : : "memory"); + + for (cl = start; cl != end; cl += flush_size) + clflush(cl); +} + +static int __set_page_decrypted(struct x86_mapping_info *info, + unsigned long address) +{ + unsigned long scratch, *target; + pgd_t *pgdp = (pgd_t *)top_level_pgt; + p4d_t *p4dp; + pud_t *pudp; + pmd_t *pmdp; + pte_t *ptep, pte; + + /* +* First make sure there is a PMD mapping for 'address'. +* It should already exist, but keep things generic. +* +* To map the page just read from it and fault it in if there is no +* mapping yet. add_identity_map() can't be called here because that +* would unconditionally map the address on PMD level, destroying any +* PTE-level mappings that might already exist. Also do something +* useless with 'scratch' so the access won't be optimized away. +*/ + target = (unsigned long *)address; + scratch = *target; + arch_cmpxchg(target, scratch, scratch); + + /* +* The page is mapped at least with PMD size - so skip checks and walk +* directly to the PMD. +*/ + p4dp = p4d_offset(pgdp, address); + pudp = pud_offset(p4dp, address); + pmdp = pmd_offset(pudp, address); + + if (pmd_large(*pmdp)) + ptep = split_large_pmd(info, pmdp, address); + else + ptep = pte_offset_kernel(pmdp, address); + + if (!ptep) + return -ENOMEM; + + /* Clear encryption flag and write new pte */ + pte = pte_clear_flags(*ptep, _PAGE_ENC); + set_pte(ptep, pte); + + /* Flush TLB to map the page unencrypted */ + write_cr3(top_level_pgt); + + /* +* Changing encryption attributes of a page requires to flush it from +* the caches. +*/ + clflush_page(address); + + return 0; +} + +int set_page_decrypted(unsigned long address) +{ + return __set_page_decrypted(&mapping_info, address); +} + static void pf_error(unsigned long error_code, unsigned long address, struct pt_re
[PATCH 09/62] x86/boot/compressed/64: Rename kaslr_64.c to ident_map_64.c
From: Joerg Roedel The file contains only code related to identity mapped page-tables. Rename the file and compile it always in. Signed-off-by: Joerg Roedel --- arch/x86/boot/compressed/Makefile | 2 +- arch/x86/boot/compressed/{kaslr_64.c => ident_map_64.c} | 9 + arch/x86/boot/compressed/kaslr.c| 9 - arch/x86/boot/compressed/misc.h | 8 4 files changed, 18 insertions(+), 10 deletions(-) rename arch/x86/boot/compressed/{kaslr_64.c => ident_map_64.c} (95%) diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 54d63526e856..e6b3e0fc48de 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -80,7 +80,7 @@ vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/kernel_info.o $(obj)/head_$(BITS).o vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 - vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr_64.o + vmlinux-objs-y += $(obj)/ident_map_64.o vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o vmlinux-objs-y += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o diff --git a/arch/x86/boot/compressed/kaslr_64.c b/arch/x86/boot/compressed/ident_map_64.c similarity index 95% rename from arch/x86/boot/compressed/kaslr_64.c rename to arch/x86/boot/compressed/ident_map_64.c index 748456c365f4..3a2115582920 100644 --- a/arch/x86/boot/compressed/kaslr_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -29,6 +29,15 @@ #define __PAGE_OFFSET __PAGE_OFFSET_BASE #include "../../mm/ident_map.c" +#ifdef CONFIG_X86_5LEVEL +unsigned int __pgtable_l5_enabled; +unsigned int pgdir_shift = 39; +unsigned int ptrs_per_p4d = 1; +#endif + +/* Used by PAGE_KERN* macros: */ +pteval_t __default_kernel_pte_mask __read_mostly = ~0; + /* Used by pgtable.h asm code to force instruction serialization. */ unsigned long __force_order; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index d7408af55738..7c61a8c5b9cf 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -43,17 +43,8 @@ #define STATIC #include -#ifdef CONFIG_X86_5LEVEL -unsigned int __pgtable_l5_enabled; -unsigned int pgdir_shift __ro_after_init = 39; -unsigned int ptrs_per_p4d __ro_after_init = 1; -#endif - extern unsigned long get_cmd_line_ptr(void); -/* Used by PAGE_KERN* macros: */ -pteval_t __default_kernel_pte_mask __read_mostly = ~0; - /* Simplified build-specific string for starting entropy. */ static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION; diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 062ae3ae6930..3a030a878d53 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -134,6 +134,14 @@ int count_immovable_mem_regions(void); static inline int count_immovable_mem_regions(void) { return 0; } #endif +/* ident_map_64.c */ +#ifdef CONFIG_X86_5LEVEL +extern unsigned int __pgtable_l5_enabled, pgdir_shift, ptrs_per_p4d; +#endif + +/* Used by PAGE_KERN* macros: */ +extern pteval_t __default_kernel_pte_mask; + /* idt_64.c */ extern gate_desc boot_idt[BOOT_IDT_ENTRIES]; extern struct desc_ptr boot_idt_desc; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 25/62] x86/head/64: Install boot GDT
From: Joerg Roedel Handling exceptions during boot requires a working GDT. The kernel GDT is not yet ready for use, so install a temporary boot GDT. Signed-off-by: Joerg Roedel --- arch/x86/kernel/head_64.S | 26 ++ 1 file changed, 26 insertions(+) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 4bbc770af632..5a3cde971cb7 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -72,6 +72,20 @@ SYM_CODE_START_NOALIGN(startup_64) /* Set up the stack for verify_cpu(), similar to initial_stack below */ leaq(__end_init_task - SIZEOF_PTREGS)(%rip), %rsp + /* Setup boot GDT descriptor and load boot GDT */ + leaqboot_gdt(%rip), %rax + movq%rax, boot_gdt_base(%rip) + lgdtboot_gdt_descr(%rip) + + /* GDT loaded - switch to __KERNEL_CS so IRET works reliably */ + pushq $__KERNEL_CS + leaq.Lon_kernel_cs(%rip), %rax + pushq %rax + lretq + +.Lon_kernel_cs: + UNWIND_HINT_EMPTY + /* Sanitize CPU configuration */ call verify_cpu @@ -480,6 +494,18 @@ SYM_DATA_LOCAL(early_gdt_descr_base, .quad INIT_PER_CPU_VAR(gdt_page)) SYM_DATA(phys_base, .quad 0x0) EXPORT_SYMBOL(phys_base) +/* Boot GDT used when kernel addresses are not mapped yet */ +SYM_DATA_LOCAL(boot_gdt_descr, .word boot_gdt_end - boot_gdt) +SYM_DATA_LOCAL(boot_gdt_base, .quad 0) +SYM_DATA_START(boot_gdt) + .quad 0 + .quad 0x00cf9a00 /* __KERNEL32_CS */ + .quad 0x00af9a00 /* __KERNEL_CS */ + .quad 0x00cf9200 /* __KERNEL_DS */ + .quad 0x00808900 /* TS descriptor */ + .quad 0x /* TS continued */ +SYM_DATA_END_LABEL(boot_gdt, SYM_L_LOCAL, boot_gdt_end) + #include "../../x86/xen/xen-head.S" __PAGE_ALIGNED_BSS -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 24/62] x86/idt: Split idt_data setup out of set_intr_gate()
From: Joerg Roedel The code to setup idt_data is needed for early exception handling, but set_intr_gate() can't be used that early because it has pv-ops in its code path, which don't work that early. Split out the idt_data initialization part from set_intr_gate() so that it can be used separatly. Signed-off-by: Joerg Roedel --- arch/x86/kernel/idt.c | 22 ++ 1 file changed, 14 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 7f81c1294847..7d8fa631dca9 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -227,18 +227,24 @@ idt_setup_from_table(gate_desc *idt, const struct idt_data *t, int size, bool sy } } +static void init_idt_data(struct idt_data *data, unsigned int n, + const void *addr) +{ + BUG_ON(n > 0xFF); + + memset(data, 0, sizeof(*data)); + data->vector= n; + data->addr = addr; + data->segment = __KERNEL_CS; + data->bits.type = GATE_INTERRUPT; + data->bits.p= 1; +} + static void set_intr_gate(unsigned int n, const void *addr) { struct idt_data data; - BUG_ON(n > 0xFF); - - memset(&data, 0, sizeof(data)); - data.vector = n; - data.addr = addr; - data.segment= __KERNEL_CS; - data.bits.type = GATE_INTERRUPT; - data.bits.p = 1; + init_idt_data(&data, n, addr); idt_setup_from_table(idt_table, &data, 1, false); } -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 34/62] x86/sev-es: Setup GHCB based boot #VC handler
From: Joerg Roedel Add the infrastructure to handle #VC exceptions when the kernel runs on virtual addresses and has a GHCB mapped. This handler will be used until the runtime #VC handler takes over. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/segment.h | 2 +- arch/x86/include/asm/sev-es.h | 1 + arch/x86/kernel/head64.c| 5 ++ arch/x86/kernel/sev-es-shared.c | 15 ++--- arch/x86/kernel/sev-es.c| 116 arch/x86/mm/extable.c | 1 + 6 files changed, 131 insertions(+), 9 deletions(-) diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 6669164abadc..5b648066504c 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -230,7 +230,7 @@ #define NUM_EXCEPTION_VECTORS 32 /* Bitmask of exception vectors which push an error code on the stack: */ -#define EXCEPTION_ERRCODE_MASK 0x00027d00 +#define EXCEPTION_ERRCODE_MASK 0x20027d00 #define GDT_SIZE (GDT_ENTRIES*8) #define GDT_ENTRY_TLS_ENTRIES 3 diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index caa29f75ce41..a2d0c77dabc3 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -76,5 +76,6 @@ static inline u64 copy_lower_bits(u64 out, u64 in, unsigned int bits) } extern void early_vc_handler(void); +extern int boot_vc_exception(struct pt_regs *regs); #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index eab04ac260d4..14e0699b2692 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -390,6 +390,11 @@ void __init early_exception(struct pt_regs *regs, int trapnr) cr2 = native_read_cr2(); r = early_make_pgtable(cr2); break; +#ifdef CONFIG_AMD_MEM_ENCRYPT + case X86_TRAP_VC: + r = boot_vc_exception(regs); + break; +#endif default: r = 1; } diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index ad2a6c964217..57c29c91fe87 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -9,7 +9,7 @@ * and is included directly into both code-bases. */ -static void __maybe_unused terminate(unsigned int reason) +static void terminate(unsigned int reason) { /* Request Guest Termination from Hypvervisor */ write_ghcb_msr(GHCB_SEV_TERMINATE); @@ -19,7 +19,7 @@ static void __maybe_unused terminate(unsigned int reason) asm volatile("hlt\n" : : : "memory"); } -static bool __maybe_unused sev_es_negotiate_protocol(void) +static bool sev_es_negotiate_protocol(void) { u64 val; @@ -38,7 +38,7 @@ static bool __maybe_unused sev_es_negotiate_protocol(void) return true; } -static void __maybe_unused ghcb_invalidate(struct ghcb *ghcb) +static void ghcb_invalidate(struct ghcb *ghcb) { memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } @@ -80,10 +80,9 @@ static bool decoding_needed(unsigned long exit_code) exit_code <= SVM_EXIT_LAST_EXCP); } -static enum es_result __maybe_unused -init_em_ctxt(struct es_em_ctxt *ctxt, -struct pt_regs *regs, -unsigned long exit_code) +static enum es_result init_em_ctxt(struct es_em_ctxt *ctxt, + struct pt_regs *regs, + unsigned long exit_code) { enum es_result ret = ES_OK; @@ -96,7 +95,7 @@ init_em_ctxt(struct es_em_ctxt *ctxt, return ret; } -static void __maybe_unused finish_insn(struct es_em_ctxt *ctxt) +static void finish_insn(struct es_em_ctxt *ctxt) { ctxt->regs->ip += ctxt->insn.length; } diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 33ab7fe8b6a0..0e0b28477627 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -7,15 +7,30 @@ * Author: Joerg Roedel */ +#include /* For show_regs() */ #include +#include #include #include #include #include #include +#include #include +/* For early boot hypervisor communication in SEV-ES enabled guests */ +struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); + +/* + * Needs to be in the .data section because we need it NULL before bss is + * cleared + */ +struct ghcb __initdata *boot_ghcb; + +/* Needed in early_forward_exception */ +extern void early_exception(struct pt_regs *regs, int trapnr); + static inline u64 read_ghcb_msr(void) { return native_read_msr(MSR_AMD64_SEV_ES_GHCB); @@ -96,3 +111,104 @@ static phys_addr_t es_slow_virt_to_phys(struct ghcb *ghcb, long vaddr) /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" + +/* + * This function runs on the first #VC exception after the kernel + * switched to virtual addresses. + */ +static bool __init setup_ghcb(void) +{ + /* First make
[PATCH 29/62] x86/head/64: Load IDT earlier
From: Joerg Roedel Load the IDT right after switching to virtual addresses in head_64.S so that the kernel can handle #VC exceptions. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/desc.h | 1 + arch/x86/kernel/head64.c| 7 +++ arch/x86/kernel/head_64.S | 17 + arch/x86/kernel/idt.c | 22 ++ 4 files changed, 47 insertions(+) diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index 68a99d2a5f33..8a4c642ee2b3 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -440,6 +440,7 @@ extern void idt_setup_apic_and_irq_gates(void); extern void idt_setup_early_pf(void); extern void idt_setup_ist_traps(void); extern void idt_setup_debugidt_traps(void); +extern void setup_early_handlers(gate_desc *idt); #else static inline void idt_setup_early_pf(void) { } static inline void idt_setup_ist_traps(void) { } diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 206a4b6144c2..7cdfb7113811 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -489,3 +489,10 @@ void __init x86_64_start_reservations(char *real_mode_data) start_kernel(); } + +void __head early_idt_setup_early_handler(unsigned long physaddr) +{ + gate_desc *idt = fixup_pointer(idt_table, physaddr); + + setup_early_handlers(idt); +} diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index eefd6838b895..0af79f783659 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -98,6 +98,20 @@ SYM_CODE_START_NOALIGN(startup_64) leaq_text(%rip), %rdi pushq %rsi call__startup_64 + /* Save return value */ + pushq %rax + + /* +* Load IDT with early handlers - needed for SEV-ES +* Do this here because this must only happen on the boot CPU +* and the code below is shared with secondary CPU bringup. +*/ + leaq_text(%rip), %rdi + callearly_idt_setup_early_handler + + /* Restore __startup_64 return value*/ + popq%rax + /* Restore pointer to real_mode_data */ popq%rsi /* Form the CR3 value being sure to include the CR3 modifier */ @@ -194,6 +208,9 @@ SYM_CODE_START(secondary_startup_64) */ movq initial_stack(%rip), %rsp + /* Load IDT */ + lidtidt_descr(%rip) + /* Check if nx is implemented */ movl$0x8001, %eax cpuid diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 7d8fa631dca9..84250c090596 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -347,6 +347,28 @@ void __init idt_setup_early_handler(void) load_idt(&idt_descr); } +#ifdef CONFIG_X86_64 +/* + * This function does the same as idt_setup_early_handler(), but is + * called directly from head_64.S before the kernel switches to virtual + * addresses. PV-ops don't work at that point, so set_intr_gate() can't + * be used here. + */ +void __init setup_early_handlers(gate_desc *idt) +{ + int i; + + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) { + struct idt_data data; + gate_desc desc; + + init_idt_data(&data, i, early_idt_handler_array[i]); + idt_init_desc(&desc, &data); + native_write_idt_entry(idt, i, &desc); + } +} +#endif + /** * idt_invalidate - Invalidate interrupt descriptor table * @addr: The virtual address of the 'invalid' IDT -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH v4] drm/cirrus: add drm_driver.release callback.
Move final cleanups from cirrus_pci_remove() to the new callback. Add drm_atomic_helper_shutdown() call to cirrus_pci_remove(). Use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. v4: add changelog. v3: use drm_dev*. v2: stop touching hardware after pci_remove(). Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/cirrus/cirrus.c | 43 - 1 file changed, 37 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/cirrus/cirrus.c b/drivers/gpu/drm/cirrus/cirrus.c index a91fb0d7282c..d2ff63ce8eaf 100644 --- a/drivers/gpu/drm/cirrus/cirrus.c +++ b/drivers/gpu/drm/cirrus/cirrus.c @@ -151,9 +151,13 @@ static int cirrus_pitch(struct drm_framebuffer *fb) static void cirrus_set_start_address(struct cirrus_device *cirrus, u32 offset) { + int idx; u32 addr; u8 tmp; + if (!drm_dev_enter(&cirrus->dev, &idx)) + return; + addr = offset >> 2; wreg_crt(cirrus, 0x0c, (u8)((addr >> 8) & 0xff)); wreg_crt(cirrus, 0x0d, (u8)(addr & 0xff)); @@ -168,6 +172,8 @@ static void cirrus_set_start_address(struct cirrus_device *cirrus, u32 offset) tmp &= 0x7f; tmp |= (addr >> 12) & 0x80; wreg_crt(cirrus, 0x1d, tmp); + + drm_dev_exit(idx); } static int cirrus_mode_set(struct cirrus_device *cirrus, @@ -176,9 +182,12 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, { int hsyncstart, hsyncend, htotal, hdispend; int vtotal, vdispend; - int tmp; + int tmp, idx; int sr07 = 0, hdr = 0; + if (!drm_dev_enter(&cirrus->dev, &idx)) + return -1; + htotal = mode->htotal / 8; hsyncend = mode->hsync_end / 8; hsyncstart = mode->hsync_start / 8; @@ -264,6 +273,7 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, hdr = 0xc5; break; default: + drm_dev_exit(idx); return -1; } @@ -292,6 +302,8 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, /* Unblank (needed on S3 resume, vgabios doesn't do it then) */ outb(0x20, 0x3c0); + + drm_dev_exit(idx); return 0; } @@ -300,10 +312,16 @@ static int cirrus_fb_blit_rect(struct drm_framebuffer *fb, { struct cirrus_device *cirrus = fb->dev->dev_private; void *vmap; + int idx, ret; + ret = -ENODEV; + if (!drm_dev_enter(&cirrus->dev, &idx)) + goto out; + + ret = -ENOMEM; vmap = drm_gem_shmem_vmap(fb->obj[0]); if (!vmap) - return -ENOMEM; + goto out_dev_exit; if (cirrus->cpp == fb->format->cpp[0]) drm_fb_memcpy_dstclip(cirrus->vram, @@ -323,7 +341,12 @@ static int cirrus_fb_blit_rect(struct drm_framebuffer *fb, WARN_ON_ONCE("cpp mismatch"); drm_gem_shmem_vunmap(fb->obj[0], vmap); - return 0; + ret = 0; + +out_dev_exit: + drm_dev_exit(idx); +out: + return ret; } static int cirrus_fb_blit_fullscreen(struct drm_framebuffer *fb) @@ -502,6 +525,14 @@ static void cirrus_mode_config_init(struct cirrus_device *cirrus) /* -- */ +static void cirrus_release(struct drm_device *dev) +{ + struct cirrus_device *cirrus = dev->dev_private; + + drm_mode_config_cleanup(dev); + kfree(cirrus); +} + DEFINE_DRM_GEM_FOPS(cirrus_fops); static struct drm_driver cirrus_driver = { @@ -515,6 +546,7 @@ static struct drm_driver cirrus_driver = { .fops= &cirrus_fops, DRM_GEM_SHMEM_DRIVER_OPS, + .release = cirrus_release, }; static int cirrus_pci_probe(struct pci_dev *pdev, @@ -598,12 +630,11 @@ static void cirrus_pci_remove(struct pci_dev *pdev) struct drm_device *dev = pci_get_drvdata(pdev); struct cirrus_device *cirrus = dev->dev_private; - drm_dev_unregister(dev); - drm_mode_config_cleanup(dev); + drm_dev_unplug(dev); + drm_atomic_helper_shutdown(dev); iounmap(cirrus->mmio); iounmap(cirrus->vram); drm_dev_put(dev); - kfree(cirrus); pci_release_regions(pdev); } -- 2.18.2 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: vhost changes (batched) in linux-next after 12/13 trigger random crashes in KVM guests after reboot
On Tue, Feb 11, 2020 at 02:04:54PM +0100, Eugenio Pérez wrote: > On Mon, 2020-02-10 at 12:01 +0100, Christian Borntraeger wrote: > > > > On 10.02.20 10:47, Eugenio Perez Martin wrote: > > > Hi Christian. > > > > > > I'm not able to reproduce the failure with > > > eccb852f1fe6bede630e2e4f1a121a81e34354ab commit. Could you add more data? > > > Your configuration (libvirt or qemu line), and host's dmesg output if any? > > > > > > Thanks! > > > > If it was not obvious, this is on s390x, a big endian system. > > > > Hi Christian. Thank you very much for your fast responses. > > Could you try this patch on top of eccb852f1fe6bede630e2e4f1a121a81e34354ab? > > Thanks! > > >From 71d0f9108a18aa894cc0c0c1c7efbad39f465a27 Mon Sep 17 00:00:00 2001 > From: =?UTF-8?q?Eugenio=20P=C3=A9rez?= < > epere...@redhat.com> > Date: Tue, 11 Feb 2020 13:19:10 +0100 > Subject: [PATCH] vhost: fix return value of vhost_get_vq_desc > > Before of the batch change, it was the chain's head. Need to keep that > way or we will not be able to free a chain of descriptors. I think it's cleaner to have all descriptors in the chain have the same id. > Fixes: eccb852f1fe6 ("vhost: batching fetches") > --- > drivers/vhost/vhost.c | 3 +-- > 1 file changed, 1 insertion(+), 2 deletions(-) > > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c > index b5a51b1f2e79..fc422c3e5c08 100644 > --- a/drivers/vhost/vhost.c > +++ b/drivers/vhost/vhost.c > @@ -2409,12 +2409,11 @@ int vhost_get_vq_desc(struct vhost_virtqueue *vq, > *out_num += ret; > } > > - ret = desc->id; > - > if (!(desc->flags & VRING_DESC_F_NEXT)) > break; > } > > + ret = vq->descs[vq->first_desc].id; > vq->first_desc = i + 1; > > return ret; > -- > 2.18.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH v4] drm/virtio: add drm_driver.release callback.
Split virtio_gpu_deinit(), move the drm shutdown and release to virtio_gpu_release(). Drop vqs_ready variable, instead use drm_dev_{enter,exit,unplug} to avoid touching hardware after device removal. Tidy up here and there. v4: add changelog. v3: use drm_dev_*(). Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++- drivers/gpu/drm/virtio/virtgpu_display.c | 1 - drivers/gpu/drm/virtio/virtgpu_drv.c | 6 +- drivers/gpu/drm/virtio/virtgpu_kms.c | 7 -- drivers/gpu/drm/virtio/virtgpu_vq.c | 27 +--- 5 files changed, 27 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 7fd8361e1c9e..af9403e1cf78 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -32,6 +32,7 @@ #include #include +#include #include #include #include @@ -177,7 +178,6 @@ struct virtio_gpu_device { struct virtio_gpu_queue ctrlq; struct virtio_gpu_queue cursorq; struct kmem_cache *vbufs; - bool vqs_ready; bool disable_notify; bool pending_notify; @@ -219,6 +219,7 @@ extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; /* virtio_kms.c */ int virtio_gpu_init(struct drm_device *dev); void virtio_gpu_deinit(struct drm_device *dev); +void virtio_gpu_release(struct drm_device *dev); int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file); void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file); diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index 7b0f0643bb2d..af953db4a0c9 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -368,6 +368,5 @@ void virtio_gpu_modeset_fini(struct virtio_gpu_device *vgdev) for (i = 0 ; i < vgdev->num_scanouts; ++i) kfree(vgdev->outputs[i].edid); - drm_atomic_helper_shutdown(vgdev->ddev); drm_mode_config_cleanup(vgdev->ddev); } diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 8cf27af3ad53..ab4bed78e656 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -31,6 +31,7 @@ #include #include +#include #include #include @@ -135,7 +136,8 @@ static void virtio_gpu_remove(struct virtio_device *vdev) { struct drm_device *dev = vdev->priv; - drm_dev_unregister(dev); + drm_dev_unplug(dev); + drm_atomic_helper_shutdown(dev); virtio_gpu_deinit(dev); drm_dev_put(dev); } @@ -214,4 +216,6 @@ static struct drm_driver driver = { .major = DRIVER_MAJOR, .minor = DRIVER_MINOR, .patchlevel = DRIVER_PATCHLEVEL, + + .release = virtio_gpu_release, }; diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index c1086df49816..4009c2f97d08 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -199,7 +199,6 @@ int virtio_gpu_init(struct drm_device *dev) virtio_gpu_modeset_init(vgdev); virtio_device_ready(vgdev->vdev); - vgdev->vqs_ready = true; if (num_capsets) virtio_gpu_get_capsets(vgdev, num_capsets); @@ -234,12 +233,16 @@ void virtio_gpu_deinit(struct drm_device *dev) struct virtio_gpu_device *vgdev = dev->dev_private; flush_work(&vgdev->obj_free_work); - vgdev->vqs_ready = false; flush_work(&vgdev->ctrlq.dequeue_work); flush_work(&vgdev->cursorq.dequeue_work); flush_work(&vgdev->config_changed_work); vgdev->vdev->config->reset(vgdev->vdev); vgdev->vdev->config->del_vqs(vgdev->vdev); +} + +void virtio_gpu_release(struct drm_device *dev) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; virtio_gpu_modeset_fini(vgdev); virtio_gpu_free_vbufs(vgdev); diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index a682c2fcbe9a..cfe9c54f87a3 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -330,7 +330,14 @@ static void virtio_gpu_queue_ctrl_sgs(struct virtio_gpu_device *vgdev, { struct virtqueue *vq = vgdev->ctrlq.vq; bool notify = false; - int ret; + int ret, idx; + + if (!drm_dev_enter(vgdev->ddev, &idx)) { + if (fence && vbuf->objs) + virtio_gpu_array_unlock_resv(vbuf->objs); + free_vbuf(vgdev, vbuf); + return; + } if (vgdev->has_indirect) elemcnt = 1; @@ -338,14 +345,6 @@ static void virtio_gpu_queue_ctrl_sgs(struct virtio_gpu_device *vgdev, again: spin_lock(&vgdev->ctrlq.qlock); - if (!vgdev->vqs_ready) { - spin_unlock(&vgdev->ctrlq.qlock); - -
[PATCH 42/62] x86/sev-es: Handle DR7 read/write events
From: Tom Lendacky Add code to handle #VC exceptions on DR7 register reads and writes. This is needed early because show_regs() reads DR7 to print it out. Signed-off-by: Tom Lendacky [ jroe...@suse.de: - Adapt to #VC handling framework - Support early usage ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 69 +--- 1 file changed, 65 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index b27d5b0a8ae1..fcd67ab04d2d 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -22,6 +22,8 @@ #include #include +#define DR7_RESET_VALUE0x400 + /* For early boot hypervisor communication in SEV-ES enabled guests */ struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -30,6 +32,9 @@ struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); * cleared */ struct ghcb __initdata *boot_ghcb; +static DEFINE_PER_CPU(unsigned long, cached_dr7) = DR7_RESET_VALUE; +/* Needed before per-cpu access is set up */ +static unsigned long early_dr7 = DR7_RESET_VALUE; /* Runtime GHCBs */ static DEFINE_PER_CPU_DECRYPTED(struct ghcb, ghcb_page) __aligned(PAGE_SIZE); @@ -212,13 +217,69 @@ static void __init early_forward_exception(struct es_em_ctxt *ctxt) early_exception(ctxt->regs, trapnr); } +static enum es_result handle_dr7_write(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + bool early) +{ + u8 rm = X86_MODRM_RM(ctxt->insn.modrm.value); + unsigned long *reg; + enum es_result ret; + + if (ctxt->insn.rex_prefix.nbytes && + X86_REX_B(ctxt->insn.rex_prefix.value)) + rm |= 0x8; + + reg = register_from_idx(ctxt->regs, rm); + + /* Using a value of 0 for ExitInfo1 means RAX holds the value */ + ghcb_set_rax(ghcb, *reg); + ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0); + if (ret != ES_OK) + return ret; + + if (early) + early_dr7 = *reg; + else + this_cpu_write(cached_dr7, *reg); + + return ES_OK; +} + +static enum es_result handle_dr7_read(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + bool early) +{ + u8 rm = X86_MODRM_RM(ctxt->insn.modrm.value); + unsigned long *reg; + + if (ctxt->insn.rex_prefix.nbytes && + X86_REX_B(ctxt->insn.rex_prefix.value)) + rm |= 0x8; + + reg = register_from_idx(ctxt->regs, rm); + + if (early) + *reg = early_dr7; + else + *reg = this_cpu_read(cached_dr7); + + return ES_OK; +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, - struct ghcb *ghcb, - unsigned long exit_code) + struct ghcb *ghcb, + unsigned long exit_code, + bool early) { enum es_result result; switch (exit_code) { + case SVM_EXIT_READ_DR7: + result = handle_dr7_read(ghcb, ctxt, early); + break; + case SVM_EXIT_WRITE_DR7: + result = handle_dr7_write(ghcb, ctxt, early); + break; case SVM_EXIT_CPUID: result = handle_cpuid(ghcb, ctxt); break; @@ -302,7 +363,7 @@ dotraplinkage void do_vmm_communication(struct pt_regs *regs, unsigned long exit result = context_filter(regs, exit_code); if (result == ES_OK) - result = handle_vc_exception(&ctxt, ghcb, exit_code); + result = handle_vc_exception(&ctxt, ghcb, exit_code, false); /* Done - now check the result */ switch (result) { @@ -368,7 +429,7 @@ int __init boot_vc_exception(struct pt_regs *regs) result = init_em_ctxt(&ctxt, regs, exit_code); if (result == ES_OK) - result = handle_vc_exception(&ctxt, boot_ghcb, exit_code); + result = handle_vc_exception(&ctxt, boot_ghcb, exit_code, true); /* Done - now check the result */ switch (result) { -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 47/62] x86/sev-es: Handle RDTSCP Events
From: Joerg Roedel Extend the RDTSC handler to also handle RDTSCP events. Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 14 ++ 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 485f5a14c3b4..d5a14f277adb 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -272,19 +272,24 @@ static enum es_result handle_wbinvd(struct ghcb *ghcb, return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); } -static enum es_result handle_rdtsc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +static enum es_result handle_rdtsc(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + unsigned long exit_code) { + bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); enum es_result ret; - ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDTSC, 0, 0); + ret = ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); if (ret != ES_OK) return ret; - if (!(ghcb_is_valid_rax(ghcb) && ghcb_is_valid_rdx(ghcb))) + if (!(ghcb_is_valid_rax(ghcb) && ghcb_is_valid_rdx(ghcb) && +(!rdtscp || ghcb_is_valid_rcx(ghcb return ES_VMM_ERROR; ctxt->regs->ax = ghcb->save.rax; ctxt->regs->dx = ghcb->save.rdx; + if (rdtscp) + ctxt->regs->cx = ghcb->save.rcx; return ES_OK; } @@ -328,7 +333,8 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, result = handle_dr7_write(ghcb, ctxt, early); break; case SVM_EXIT_RDTSC: - result = handle_rdtsc(ghcb, ctxt); + case SVM_EXIT_RDTSCP: + result = handle_rdtsc(ghcb, ctxt, exit_code); break; case SVM_EXIT_RDPMC: result = handle_rdpmc(ghcb, ctxt); -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 53/62] x86/paravirt: Allow hypervisor specific VMMCALL handling under SEV-ES
From: Joerg Roedel Add two new paravirt callbacks to provide hypervisor specific processor state in the GHCB and to copy state from the hypervisor back to the processor. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/x86_init.h | 16 +++- arch/x86/kernel/sev-es.c| 12 2 files changed, 27 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 96d9cd208610..c4790ec279cc 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -4,8 +4,10 @@ #include +struct ghcb; struct mpc_bus; struct mpc_cpu; +struct pt_regs; struct mpc_table; struct cpuinfo_x86; @@ -238,10 +240,22 @@ struct x86_legacy_features { /** * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks * - * @pin_vcpu: pin current vcpu to specified physical cpu (run rarely) + * @pin_vcpu: pin current vcpu to specified physical + * cpu (run rarely) + * @sev_es_hcall_prepare: Load additional hypervisor-specific + * state into the GHCB when doing a VMMCALL under + * SEV-ES. Called from the #VC exception handler. + * @sev_es_hcall_finish: Copies state from the GHCB back into the + * processor (or pt_regs). Also runs checks on the + * state returned from the hypervisor after a + * VMMCALL under SEV-ES. Needs to return 'false' + * if the checks fail. Called from the #VC + * exception handler. */ struct x86_hyper_runtime { void (*pin_vcpu)(int cpu); + void (*sev_es_hcall_prepare)(struct ghcb *ghcb, struct pt_regs *regs); + bool (*sev_es_hcall_finish)(struct ghcb *ghcb, struct pt_regs *regs); }; /** diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 700f75fc13e7..6924bb1ad8b2 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -349,6 +349,9 @@ static enum es_result handle_vmmcall(struct ghcb *ghcb, ghcb_set_rax(ghcb, ctxt->regs->ax); ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0); + if (x86_platform.hyper.sev_es_hcall_prepare) + x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs); + ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0); if (ret != ES_OK) return ret; @@ -358,6 +361,15 @@ static enum es_result handle_vmmcall(struct ghcb *ghcb, ctxt->regs->ax = ghcb->save.rax; + /* +* Call sev_es_hcall_finish() after regs->ax is already set. +* This allows the hypervisor handler to overwrite it again if +* necessary. +*/ + if (x86_platform.hyper.sev_es_hcall_finish && + !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs)) + return ES_VMM_ERROR; + return ES_OK; } -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 58/62] x86/head/64: Don't call verify_cpu() on starting APs
From: Joerg Roedel The APs are not ready to handle exceptions when verify_cpu() is called in secondary_startup_64. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/realmode.h | 1 + arch/x86/kernel/head_64.S | 1 + arch/x86/realmode/init.c| 6 ++ 3 files changed, 8 insertions(+) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 6590394af309..5c97807c38a4 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -69,6 +69,7 @@ extern unsigned char startup_32_smp[]; extern unsigned char boot_gdt[]; #else extern unsigned char secondary_startup_64[]; +extern unsigned char secondary_startup_64_no_verify[]; #endif static inline size_t real_mode_size_needed(void) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 13ebf7d3af2c..9dd602bd6244 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -144,6 +144,7 @@ SYM_CODE_START(secondary_startup_64) /* Sanitize CPU configuration */ call verify_cpu +SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 1c5cbfd102d5..030c38268069 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -109,6 +109,12 @@ static void __init setup_real_mode(void) trampoline_header->flags |= TH_FLAGS_SME_ACTIVE; if (sev_es_active()) { + /* +* Skip the call to verify_cpu() in secondary_startup_64 as it +* will cause #VC exceptions when the AP can't handle them yet. +*/ + trampoline_header->start = (u64) secondary_startup_64_no_verify; + if (sev_es_setup_ap_jump_table(real_mode_header)) panic("Failed to update SEV-ES AP Jump Table"); } -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 43/62] x86/sev-es: Handle WBINVD Events
From: Tom Lendacky Implement a handler for #VC exceptions caused by WBINVD instructions. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling framework ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 9 + 1 file changed, 9 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index fcd67ab04d2d..491537b770fd 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -266,6 +266,12 @@ static enum es_result handle_dr7_read(struct ghcb *ghcb, return ES_OK; } +static enum es_result handle_wbinvd(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -289,6 +295,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_MSR: result = handle_msr(ghcb, ctxt); break; + case SVM_EXIT_WBINVD: + result = handle_wbinvd(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = handle_mmio(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 51/62] x86/sev-es: Handle #AC Events
From: Joerg Roedel Implement a handler for #VC exceptions caused by #AC exceptions. The #AC exception is just forwarded to do_alignment_check() and not pushed down to the hypervisor, as requested by the SEV-ES GHCB Standardization Specification. Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 4 1 file changed, 4 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 6bd2cae7eb9c..1b873d00e38f 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -375,6 +375,10 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_WRITE_DR7: result = handle_dr7_write(ghcb, ctxt, early); break; + case SVM_EXIT_EXCP_BASE + X86_TRAP_AC: + do_alignment_check(ctxt->regs, 0); + result = ES_RETRY; + break; case SVM_EXIT_RDTSC: case SVM_EXIT_RDTSCP: result = handle_rdtsc(ghcb, ctxt, exit_code); -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 61/62] x86/cpufeature: Add SEV_ES_GUEST CPU Feature
From: Joerg Roedel The feature bit will indicate whether the kernel runs as an SEV-ES guest. This can be used to apply alternatives at boot for SEV-ES guests and provides a way for user-space to detect whether it runs as an SEV-ES guest. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/amd.c | 6 +- 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 26e4ee209f7b..e864327812e2 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -234,6 +234,7 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_SEV_ES_GUEST ( 8*32+20) /* SEV-ES Guest */ /* Intel-defined CPU features, CPUID level 0x0007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index aad2223862ef..a1eb39153771 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -484,7 +484,6 @@ static void early_init_amd_mc(struct cpuinfo_x86 *c) static void bsp_init_amd(struct cpuinfo_x86 *c) { - #ifdef CONFIG_X86_64 if (c->x86 >= 0xf) { unsigned long long tseg; @@ -614,6 +613,11 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_SEV); setup_clear_cpu_cap(X86_FEATURE_SEV_ES); } + + if (!rdmsrl_safe(MSR_AMD64_SEV, &msr)) { + if (msr & MSR_AMD64_SEV_ES_ENABLED) + set_cpu_cap(c, X86_FEATURE_SEV_ES_GUEST); + } } static void early_init_amd(struct cpuinfo_x86 *c) -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 62/62] x86/sev-es: Add NMI state tracking
From: Joerg Roedel Keep NMI state in SEV-ES code so the kernel can re-enable NMIs for the vCPU when it reaches IRET. Signed-off-by: Joerg Roedel --- arch/x86/entry/entry_64.S | 48 + arch/x86/include/asm/sev-es.h | 27 +++ arch/x86/include/uapi/asm/svm.h | 1 + arch/x86/kernel/nmi.c | 8 ++ arch/x86/kernel/sev-es.c| 28 ++- 5 files changed, 111 insertions(+), 1 deletion(-) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 729876d368c5..355470b36896 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -38,6 +38,7 @@ #include #include #include +#include #include #include "calling.h" @@ -629,6 +630,13 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) ud2 1: #endif + + /* +* This code path is used by the NMI handler, so check if NMIs +* need to be re-enabled when running as an SEV-ES guest. +*/ + SEV_ES_IRET_CHECK + POP_REGS pop_rdi=0 /* @@ -1474,6 +1482,8 @@ SYM_CODE_START(nmi) movq$-1, %rsi calldo_nmi + SEV_ES_NMI_COMPLETE + /* * Return back to user mode. We must *not* do the normal exit * work, because we don't want to enable interrupts. @@ -1599,6 +1609,7 @@ nested_nmi_out: popq%rdx /* We are returning to kernel mode, so this cannot result in a fault. */ + SEV_ES_NMI_COMPLETE iretq first_nmi: @@ -1687,6 +1698,12 @@ end_repeat_nmi: movq$-1, %rsi calldo_nmi + /* +* When running as an SEV-ES guest, jump to the SEV-ES NMI IRET +* path. +*/ + SEV_ES_NMI_COMPLETE + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 @@ -1715,6 +1732,9 @@ nmi_restore: std movq$0, 5*8(%rsp) /* clear "NMI executing" */ +nmi_return: + UNWIND_HINT_IRET_REGS + /* * iretq reads the "iret" frame and exits the NMI stack in a * single instruction. We are returning to kernel mode, so this @@ -1724,6 +1744,34 @@ nmi_restore: iretq SYM_CODE_END(nmi) +#ifdef CONFIG_AMD_MEM_ENCRYPT +SYM_CODE_START(sev_es_iret_user) + UNWIND_HINT_IRET_REGS offset=8 + /* +* The kernel jumps here directly from +* swapgs_restore_regs_and_return_to_usermode. %rsp points already to +* trampoline stack, but %cr3 is still from kernel. User-regs are live +* except %rdi. Switch to user CR3, restore user %rdi and user gs_base +* and single-step over IRET +*/ + SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + popq%rdi + SWAPGS + /* +* Enable single-stepping and execute IRET. When IRET is +* finished the resulting #DB exception will cause a #VC +* exception to be raised. The #VC exception handler will send a +* NMI-complete message to the hypervisor to re-open the NMI +* window. +*/ +sev_es_iret_kernel: + pushf + btsq $X86_EFLAGS_TF_BIT, (%rsp) + popf + iretq +SYM_CODE_END(sev_es_iret_user) +#endif + #ifndef CONFIG_IA32_EMULATION /* * This handles SYSCALL from 32-bit code. There is no way to program diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index a4d7574c5c6a..22f45782149e 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -8,6 +8,8 @@ #ifndef __ASM_ENCRYPTED_STATE_H #define __ASM_ENCRYPTED_STATE_H +#ifndef __ASSEMBLY__ + #include #include @@ -82,11 +84,36 @@ struct real_mode_header; #ifdef CONFIG_AMD_MEM_ENCRYPT int sev_es_setup_ap_jump_table(struct real_mode_header *rmh); +void sev_es_nmi_enter(void); #else /* CONFIG_AMD_MEM_ENCRYPT */ static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } +static inline void sev_es_nmi_enter(void) { } +#endif /* CONFIG_AMD_MEM_ENCRYPT*/ + +#else /* !__ASSEMBLY__ */ + +#ifdef CONFIG_AMD_MEM_ENCRYPT +#define SEV_ES_NMI_COMPLETE\ + ALTERNATIVE "", "callq sev_es_nmi_complete", X86_FEATURE_SEV_ES_GUEST + +.macro SEV_ES_IRET_CHECK + ALTERNATIVE "jmp.Lend_\@", "", X86_FEATURE_SEV_ES_GUEST + movqPER_CPU_VAR(sev_es_in_nmi), %rdi + testq %rdi, %rdi + jz .Lend_\@ + callq sev_es_nmi_complete +.Lend_\@: +.endm + +#else /* CONFIG_AMD_MEM_ENCRYPT */ +#defineSEV_ES_NMI_RETURN +.macro SEV_ES_IRET_CHECK +.endm #endif /* CONFIG_AMD_MEM_ENCRYPT*/ +#endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 20a05839dd9a..0f837339db66 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -84,6 +84,7 @@ /* SEV-ES software-defined VMGEXIT events */ #define SVM
[PATCH 52/62] x86/sev-es: Handle #DB Events
From: Joerg Roedel Handle #VC exceptions caused by #DB exceptions in the guest. Do not forward them to the hypervisor and handle them with do_debug() instead. Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 12 1 file changed, 12 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 1b873d00e38f..700f75fc13e7 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -361,6 +361,15 @@ static enum es_result handle_vmmcall(struct ghcb *ghcb, return ES_OK; } +static enum es_result handle_db_exception(struct ghcb *ghcb, + struct es_em_ctxt *ctxt) +{ + do_debug(ctxt->regs, 0); + + /* Exception event, do not advance RIP */ + return ES_RETRY; +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -375,6 +384,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_WRITE_DR7: result = handle_dr7_write(ghcb, ctxt, early); break; + case SVM_EXIT_EXCP_BASE + X86_TRAP_DB: + result = handle_db_exception(ghcb, ctxt); + break; case SVM_EXIT_EXCP_BASE + X86_TRAP_AC: do_alignment_check(ctxt->regs, 0); result = ES_RETRY; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 46/62] x86/sev-es: Handle INVD Events
From: Tom Lendacky Implement a handler for #VC exceptions caused by INVD instructions. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 8 1 file changed, 8 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index e96332516c2a..485f5a14c3b4 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -308,6 +308,11 @@ static enum es_result handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ES_OK; } +static enum es_result handle_invd(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_INVD, 0, 0); +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -328,6 +333,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_RDPMC: result = handle_rdpmc(ghcb, ctxt); break; + case SVM_EXIT_INVD: + result = handle_invd(ghcb, ctxt); + break; case SVM_EXIT_CPUID: result = handle_cpuid(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 56/62] x86/realmode: Add SEV-ES specific trampoline entry point
From: Joerg Roedel The code at the trampoline entry point is executed in real-mode. In real-mode #VC exceptions can't be handled, so anything that might cause such an exception must be avoided. In the standard trampoline entry code this is the WBINVD instruction and the call to verify_cpu(), which are both not needed anyway when running as an SEV-ES guest. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/realmode.h | 3 +++ arch/x86/realmode/rm/header.S| 3 +++ arch/x86/realmode/rm/trampoline_64.S | 20 3 files changed, 26 insertions(+) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index b35030eeec36..6590394af309 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -21,6 +21,9 @@ struct real_mode_header { /* SMP trampoline */ u32 trampoline_start; u32 trampoline_header; +#ifdef CONFIG_AMD_MEM_ENCRYPT + u32 sev_es_trampoline_start; +#endif #ifdef CONFIG_X86_64 u32 trampoline_pgd; #endif diff --git a/arch/x86/realmode/rm/header.S b/arch/x86/realmode/rm/header.S index af04512c02d9..8c1db5bf5d78 100644 --- a/arch/x86/realmode/rm/header.S +++ b/arch/x86/realmode/rm/header.S @@ -20,6 +20,9 @@ SYM_DATA_START(real_mode_header) /* SMP trampoline */ .long pa_trampoline_start .long pa_trampoline_header +#ifdef CONFIG_AMD_MEM_ENCRYPT + .long pa_sev_es_trampoline_start +#endif #ifdef CONFIG_X86_64 .long pa_trampoline_pgd; #endif diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index 251758ed7443..84c5d1b33d10 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -56,6 +56,7 @@ SYM_CODE_START(trampoline_start) testl %eax, %eax # Check for return code jnz no_longmode +.Lswitch_to_protected: /* * GDT tables in non default location kernel can be beyond 16MB and * lgdt will not be able to load the address as in real mode default @@ -80,6 +81,25 @@ no_longmode: jmp no_longmode SYM_CODE_END(trampoline_start) +#ifdef CONFIG_AMD_MEM_ENCRYPT +/* SEV-ES supports non-zero IP for entry points - no alignment needed */ +SYM_CODE_START(sev_es_trampoline_start) + cli # We should be safe anyway + + LJMPW_RM(1f) +1: + mov %cs, %ax# Code and data in the same place + mov %ax, %ds + mov %ax, %es + mov %ax, %ss + + # Setup stack + movl$rm_stack_end, %esp + + jmp .Lswitch_to_protected +SYM_CODE_END(sev_es_trampoline_start) +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + #include "../kernel/verify_cpu.S" .section ".text32","ax" -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 44/62] x86/sev-es: Handle RDTSC Events
From: Tom Lendacky Implement a handler for #VC exceptions caused by RDTSC instructions. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 20 1 file changed, 20 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 491537b770fd..061557515f75 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -272,6 +272,23 @@ static enum es_result handle_wbinvd(struct ghcb *ghcb, return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0); } +static enum es_result handle_rdtsc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + enum es_result ret; + + ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDTSC, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_is_valid_rax(ghcb) && ghcb_is_valid_rdx(ghcb))) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + ctxt->regs->dx = ghcb->save.rdx; + + return ES_OK; +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -286,6 +303,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_WRITE_DR7: result = handle_dr7_write(ghcb, ctxt, early); break; + case SVM_EXIT_RDTSC: + result = handle_rdtsc(ghcb, ctxt); + break; case SVM_EXIT_CPUID: result = handle_cpuid(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 59/62] x86/head/64: Rename start_cpu0
From: Joerg Roedel For SEV-ES this entry point will be used for restarting APs after they have been offlined. Remove the '0' from the name to reflect that. Signed-off-by: Joerg Roedel --- arch/x86/include/asm/cpu.h | 2 +- arch/x86/kernel/head_32.S | 4 ++-- arch/x86/kernel/head_64.S | 6 +++--- arch/x86/kernel/smpboot.c | 4 ++-- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index adc6cc86b062..00668daf8991 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -29,7 +29,7 @@ struct x86_cpu { #ifdef CONFIG_HOTPLUG_CPU extern int arch_register_cpu(int num); extern void arch_unregister_cpu(int); -extern void start_cpu0(void); +extern void start_cpu(void); #ifdef CONFIG_DEBUG_HOTPLUG_CPU0 extern int _debug_hotplug_cpu(int cpu, int action); #endif diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 3923ab4630d7..1a280152bd10 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -180,12 +180,12 @@ SYM_CODE_END(startup_32) * up already except stack. We just set up stack here. Then call * start_secondary(). */ -SYM_FUNC_START(start_cpu0) +SYM_FUNC_START(start_cpu) movl initial_stack, %ecx movl %ecx, %esp call *(initial_code) 1: jmp 1b -SYM_FUNC_END(start_cpu0) +SYM_FUNC_END(start_cpu) #endif /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 9dd602bd6244..681f3aafd424 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -293,15 +293,15 @@ SYM_CODE_END(secondary_startup_64) #ifdef CONFIG_HOTPLUG_CPU /* - * Boot CPU0 entry point. It's called from play_dead(). Everything has been set + * CPU entry point. It's called from play_dead(). Everything has been set * up already except stack. We just set up stack here. Then call * start_secondary() via .Ljump_to_C_code. */ -SYM_CODE_START(start_cpu0) +SYM_CODE_START(start_cpu) UNWIND_HINT_EMPTY movqinitial_stack(%rip), %rsp jmp .Ljump_to_C_code -SYM_CODE_END(start_cpu0) +SYM_CODE_END(start_cpu) #endif /* Both SMP bootup and ACPI suspend change these variables */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 69881b2d446c..19aa18f1e307 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1717,7 +1717,7 @@ static inline void mwait_play_dead(void) * If NMI wants to wake up CPU0, start CPU0. */ if (wakeup_cpu0()) - start_cpu0(); + start_cpu(); } } @@ -1732,7 +1732,7 @@ void hlt_play_dead(void) * If NMI wants to wake up CPU0, start CPU0. */ if (wakeup_cpu0()) - start_cpu0(); + start_cpu(); } } -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 60/62] x86/sev-es: Support CPU offline/online
From: Joerg Roedel Add a play_dead handler when running under SEV-ES. This is needed because the hypervisor can't deliver an SIPI request to restart the AP. Instead the kernel has to issue a VMGEXIT to halt the VCPU. When the hypervisor would deliver and SIPI is wakes up the VCPU instead. Signed-off-by: Joerg Roedel --- arch/x86/include/uapi/asm/svm.h | 1 + arch/x86/kernel/sev-es.c| 46 + 2 files changed, 47 insertions(+) diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index a19ce9681ec2..20a05839dd9a 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -84,6 +84,7 @@ /* SEV-ES software-defined VMGEXIT events */ #define SVM_VMGEXIT_MMIO_READ 0x8001 #define SVM_VMGEXIT_MMIO_WRITE 0x8002 +#define SVM_VMGEXIT_AP_HLT_LOOP0x8004 #define SVM_VMGEXIT_AP_JUMP_TABLE 0x8005 #defineSVM_VMGEXIT_SET_AP_JUMP_TABLE 0 #defineSVM_VMGEXIT_GET_AP_JUMP_TABLE 1 diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index d8193d37ed2b..755708f72824 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -22,6 +22,8 @@ #include #include #include +#include +#include #define DR7_RESET_VALUE0x400 @@ -252,6 +254,48 @@ static bool __init setup_ghcb(void) return true; } +#ifdef CONFIG_HOTPLUG_CPU +static void sev_es_ap_hlt_loop(void) +{ + struct ghcb *ghcb; + + ghcb = this_cpu_ptr(&ghcb_page); + + while (true) { + ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_HLT_LOOP); + ghcb_set_sw_exit_info_1(ghcb, 0); + ghcb_set_sw_exit_info_2(ghcb, 0); + + write_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + /* Wakup Signal? */ + if (ghcb_is_valid_sw_exit_info_2(ghcb) && + ghcb->save.sw_exit_info_2 != 0) + break; + } +} + +void sev_es_play_dead(void) +{ + play_dead_common(); + + /* IRQs now disabled */ + + sev_es_ap_hlt_loop(); + + /* +* If we get here, the VCPU was woken up again. Jump to CPU +* startup code to get it back online. +*/ + + start_cpu(); +} +#else /* CONFIG_HOTPLUG_CPU */ +#define sev_es_play_dead native_play_dead +#endif /* CONFIG_HOTPLUG_CPU */ + void encrypted_state_init_ghcbs(void) { int cpu; @@ -267,6 +311,8 @@ void encrypted_state_init_ghcbs(void) sizeof(ghcb_page) >> PAGE_SHIFT); memset(ghcb, 0, sizeof(*ghcb)); } + + smp_ops.play_dead = sev_es_play_dead; } static void __init early_forward_exception(struct es_em_ctxt *ctxt) -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 45/62] x86/sev-es: Handle RDPMC Events
From: Tom Lendacky Implement a handler for #VC exceptions caused by RDPMC instructions. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 22 ++ 1 file changed, 22 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 061557515f75..e96332516c2a 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -289,6 +289,25 @@ static enum es_result handle_rdtsc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ES_OK; } +static enum es_result handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + enum es_result ret; + + ghcb_set_rcx(ghcb, ctxt->regs->cx); + + ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_is_valid_rax(ghcb) && ghcb_is_valid_rdx(ghcb))) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + ctxt->regs->dx = ghcb->save.rdx; + + return ES_OK; +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -306,6 +325,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_RDTSC: result = handle_rdtsc(ghcb, ctxt); break; + case SVM_EXIT_RDPMC: + result = handle_rdpmc(ghcb, ctxt); + break; case SVM_EXIT_CPUID: result = handle_cpuid(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 55/62] x86/vmware: Add VMware specific handling for VMMCALL under SEV-ES
From: Doug Covelli This change adds VMware specific handling for #VC faults caused by VMMCALL instructions. Signed-off-by: Doug Covelli Signed-off-by: Tom Lendacky [ jroe...@suse.de: - Adapt to different paravirt interface ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/cpu/vmware.c | 48 1 file changed, 43 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 46d732696c1c..7edab8fcf8bf 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -31,6 +31,7 @@ #include #include #include +#include #undef pr_fmt #define pr_fmt(fmt)"vmware: " fmt @@ -263,10 +264,47 @@ static bool __init vmware_legacy_x2apic_available(void) (eax & (1 << VMWARE_CMD_LEGACY_X2APIC)) != 0; } +#ifdef CONFIG_AMD_MEM_ENCRYPT +static void vmware_sev_es_hcall_prepare(struct ghcb *ghcb, + struct pt_regs *regs) +{ + /* Copy VMWARE specific Hypercall parameters to the GHCB */ + ghcb_set_rip(ghcb, regs->ip); + ghcb_set_rbx(ghcb, regs->bx); + ghcb_set_rcx(ghcb, regs->cx); + ghcb_set_rdx(ghcb, regs->dx); + ghcb_set_rsi(ghcb, regs->si); + ghcb_set_rdi(ghcb, regs->di); + ghcb_set_rbp(ghcb, regs->bp); +} + +static bool vmware_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) +{ + if (!(ghcb_is_valid_rbx(ghcb) && + ghcb_is_valid_rcx(ghcb) && + ghcb_is_valid_rdx(ghcb) && + ghcb_is_valid_rsi(ghcb) && + ghcb_is_valid_rdi(ghcb) && + ghcb_is_valid_rbp(ghcb))) + return false; + + regs->bx = ghcb->save.rbx; + regs->cx = ghcb->save.rcx; + regs->dx = ghcb->save.rdx; + regs->si = ghcb->save.rsi; + regs->di = ghcb->save.rdi; + regs->bp = ghcb->save.rbp; + + return true; +} +#endif + const __initconst struct hypervisor_x86 x86_hyper_vmware = { - .name = "VMware", - .detect = vmware_platform, - .type = X86_HYPER_VMWARE, - .init.init_platform = vmware_platform_setup, - .init.x2apic_available = vmware_legacy_x2apic_available, + .name = "VMware", + .detect = vmware_platform, + .type = X86_HYPER_VMWARE, + .init.init_platform = vmware_platform_setup, + .init.x2apic_available = vmware_legacy_x2apic_available, + .runtime.sev_es_hcall_prepare = vmware_sev_es_hcall_prepare, + .runtime.sev_es_hcall_finish= vmware_sev_es_hcall_finish, }; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 49/62] x86/sev-es: Handle MWAIT/MWAITX Events
From: Tom Lendacky Implement a handler for #VC exceptions caused by MWAIT and MWAITX instructions. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 11 +++ 1 file changed, 11 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 865f510d11ba..8f1e84da6fa6 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -333,6 +333,14 @@ static enum es_result handle_monitor(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MONITOR, 0, 0); } +static enum es_result handle_mwait(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + ghcb_set_rax(ghcb, ctxt->regs->ax); + ghcb_set_rcx(ghcb, ctxt->regs->cx); + + return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MWAIT, 0, 0); +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -372,6 +380,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_MONITOR: result = handle_monitor(ghcb, ctxt); break; + case SVM_EXIT_MWAIT: + result = handle_mwait(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = handle_mmio(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 50/62] x86/sev-es: Handle VMMCALL Events
From: Tom Lendacky Implement a handler for #VC exceptions caused by VMMCALL instructions. This patch is only a starting point, VMMCALL emulation under SEV-ES needs further hypervisor-specific changes to provide additional state. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 23 +++ 1 file changed, 23 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 8f1e84da6fa6..6bd2cae7eb9c 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -341,6 +341,26 @@ static enum es_result handle_mwait(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MWAIT, 0, 0); } +static enum es_result handle_vmmcall(struct ghcb *ghcb, +struct es_em_ctxt *ctxt) +{ + enum es_result ret; + + ghcb_set_rax(ghcb, ctxt->regs->ax); + ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0); + + ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0); + if (ret != ES_OK) + return ret; + + if (!ghcb_is_valid_rax(ghcb)) + return ES_VMM_ERROR; + + ctxt->regs->ax = ghcb->save.rax; + + return ES_OK; +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -374,6 +394,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_MSR: result = handle_msr(ghcb, ctxt); break; + case SVM_EXIT_VMMCALL: + result = handle_vmmcall(ghcb, ctxt); + break; case SVM_EXIT_WBINVD: result = handle_wbinvd(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 38/62] x86/sev-es: Handle instruction fetches from user-space
From: Joerg Roedel When a #VC exception is triggered by user-space the instruction decoder needs to read the instruction bytes from user addresses. Enhance es_fetch_insn_byte() to safely fetch kernel and user instruction bytes. Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 30 +++--- 1 file changed, 23 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 2a801919e7c0..f5bff4219f6f 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -61,13 +61,29 @@ static enum es_result es_fetch_insn_byte(struct es_em_ctxt *ctxt, unsigned int offset, char *buffer) { - char *rip = (char *)ctxt->regs->ip; - - /* More checks are needed when we boot to user-space */ - if (!check_kernel(ctxt->regs)) - return ES_UNSUPPORTED; - - buffer[offset] = rip[offset]; + if (user_mode(ctxt->regs)) { + unsigned long addr = ctxt->regs->ip + offset; + char __user *rip = (char __user *)addr; + + if (unlikely(addr >= TASK_SIZE_MAX)) + return ES_UNSUPPORTED; + + if (copy_from_user(buffer + offset, rip, 1)) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.cr2= addr; + ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER; + return ES_EXCEPTION; + } + } else { + char *rip = (char *)ctxt->regs->ip + offset; + + if (probe_kernel_read(buffer + offset, rip, 1) != 0) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.cr2= (unsigned long)rip; + ctxt->fi.error_code = X86_PF_INSTR; + return ES_EXCEPTION; + } + } return ES_OK; } -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 48/62] x86/sev-es: Handle MONITOR/MONITORX Events
From: Tom Lendacky Implement a handler for #VC exceptions caused by MONITOR and MONITORX instructions. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 18 ++ 1 file changed, 18 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index d5a14f277adb..865f510d11ba 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -318,6 +318,21 @@ static enum es_result handle_invd(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_INVD, 0, 0); } +static enum es_result handle_monitor(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + phys_addr_t monitor_pa; + pgd_t *pgd; + + pgd = __va(read_cr3_pa()); + monitor_pa = es_slow_virt_to_phys(ghcb, ctxt->regs->ax); + + ghcb_set_rax(ghcb, monitor_pa); + ghcb_set_rcx(ghcb, ctxt->regs->cx); + ghcb_set_rdx(ghcb, ctxt->regs->dx); + + return ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MONITOR, 0, 0); +} + static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code, @@ -354,6 +369,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_WBINVD: result = handle_wbinvd(ghcb, ctxt); break; + case SVM_EXIT_MONITOR: + result = handle_monitor(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = handle_mmio(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 41/62] x86/sev-es: Handle MSR events
From: Tom Lendacky Implement a handler for #VC exceptions caused by RDMSR/WRMSR instructions. Signed-off-by: Tom Lendacky [ jroe...@suse.de: Adapt to #VC handling infrastructure ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/sev-es.c | 32 1 file changed, 32 insertions(+) diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 84b5b8f7897a..b27d5b0a8ae1 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -134,6 +134,35 @@ static phys_addr_t es_slow_virt_to_phys(struct ghcb *ghcb, long vaddr) /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" +static enum es_result handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) +{ + struct pt_regs *regs = ctxt->regs; + enum es_result ret; + bool write; + u64 exit_info_1; + + write = (ctxt->insn.opcode.bytes[1] == 0x30); + + ghcb_set_rcx(ghcb, regs->cx); + if (write) { + ghcb_set_rax(ghcb, regs->ax); + ghcb_set_rdx(ghcb, regs->dx); + exit_info_1 = 1; + } else { + exit_info_1 = 0; + } + + ret = ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, exit_info_1, 0); + if (ret != ES_OK) + return ret; + else if (!write) { + regs->ax = ghcb->save.rax; + regs->dx = ghcb->save.rdx; + } + + return ret; +} + /* * This function runs on the first #VC exception after the kernel * switched to virtual addresses. @@ -196,6 +225,9 @@ static enum es_result handle_vc_exception(struct es_em_ctxt *ctxt, case SVM_EXIT_IOIO: result = handle_ioio(ghcb, ctxt); break; + case SVM_EXIT_MSR: + result = handle_msr(ghcb, ctxt); + break; case SVM_EXIT_NPF: result = handle_mmio(ghcb, ctxt); break; -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH 57/62] x86/realmode: Setup AP jump table
From: Tom Lendacky Setup the AP jump table to point to the SEV-ES trampoline code so that the APs can boot. Signed-off-by: Tom Lendacky [ jroe...@suse.de: - Adapted to different code base - Moved AP table setup from SIPI sending path to real-mode setup code ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/include/asm/sev-es.h | 11 ++ arch/x86/include/uapi/asm/svm.h | 3 ++ arch/x86/kernel/sev-es.c| 63 + arch/x86/realmode/init.c| 6 4 files changed, 83 insertions(+) diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h index a2d0c77dabc3..a4d7574c5c6a 100644 --- a/arch/x86/include/asm/sev-es.h +++ b/arch/x86/include/asm/sev-es.h @@ -78,4 +78,15 @@ static inline u64 copy_lower_bits(u64 out, u64 in, unsigned int bits) extern void early_vc_handler(void); extern int boot_vc_exception(struct pt_regs *regs); +struct real_mode_header; + +#ifdef CONFIG_AMD_MEM_ENCRYPT +int sev_es_setup_ap_jump_table(struct real_mode_header *rmh); +#else /* CONFIG_AMD_MEM_ENCRYPT */ +static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) +{ + return 0; +} +#endif /* CONFIG_AMD_MEM_ENCRYPT*/ + #endif diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index 8f36ae021a7f..a19ce9681ec2 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -84,6 +84,9 @@ /* SEV-ES software-defined VMGEXIT events */ #define SVM_VMGEXIT_MMIO_READ 0x8001 #define SVM_VMGEXIT_MMIO_WRITE 0x8002 +#define SVM_VMGEXIT_AP_JUMP_TABLE 0x8005 +#defineSVM_VMGEXIT_SET_AP_JUMP_TABLE 0 +#defineSVM_VMGEXIT_GET_AP_JUMP_TABLE 1 #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000 #define SVM_EXIT_ERR -1 diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 6924bb1ad8b2..d8193d37ed2b 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -16,6 +16,7 @@ #include #include +#include #include #include #include @@ -42,6 +43,8 @@ static DEFINE_PER_CPU_DECRYPTED(struct ghcb, ghcb_page) __aligned(PAGE_SIZE); /* Needed in early_forward_exception */ extern void early_exception(struct pt_regs *regs, int trapnr); +static inline u64 read_ghcb_msr(void); + static inline u64 read_ghcb_msr(void) { return native_read_msr(MSR_AMD64_SEV_ES_GHCB); @@ -139,6 +142,66 @@ static phys_addr_t es_slow_virt_to_phys(struct ghcb *ghcb, long vaddr) /* Include code shared with pre-decompression boot stage */ #include "sev-es-shared.c" +static u64 sev_es_get_jump_table_addr(void) +{ + unsigned long flags; + struct ghcb *ghcb; + u64 ret; + + local_irq_save(flags); + + ghcb = this_cpu_ptr(&ghcb_page); + ghcb_invalidate(ghcb); + + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE); + ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE); + ghcb_set_sw_exit_info_2(ghcb, 0); + + write_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (!ghcb_is_valid_sw_exit_info_1(ghcb) || + !ghcb_is_valid_sw_exit_info_2(ghcb)) + ret = 0; + + ret = ghcb->save.sw_exit_info_2; + + local_irq_restore(flags); + + return ret; +} + +int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) +{ + u16 startup_cs, startup_ip; + phys_addr_t jump_table_pa; + u64 jump_table_addr; + u16 *jump_table; + + jump_table_addr = sev_es_get_jump_table_addr(); + + /* Check if AP Jump Table is non-zero and page-aligned */ + if (!jump_table_addr || jump_table_addr & ~PAGE_MASK) + return 0; + + jump_table_pa = jump_table_addr & PAGE_MASK; + + startup_cs = (u16)(rmh->trampoline_start >> 4); + startup_ip = (u16)(rmh->sev_es_trampoline_start - + rmh->trampoline_start); + + jump_table = ioremap_encrypted(jump_table_pa, PAGE_SIZE); + if (!jump_table) + return -EIO; + + jump_table[0] = startup_ip; + jump_table[1] = startup_cs; + + iounmap(jump_table); + + return 0; +} + static enum es_result handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 262f83cad355..1c5cbfd102d5 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -9,6 +9,7 @@ #include #include #include +#include struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -107,6 +108,11 @@ static void __init setup_real_mode(void) if (sme_active()) trampoline_header->flags |= TH_FLAGS_SME_ACTIVE; + if (sev_es_active()) { + if (sev_es_setup_ap_jump_table(real_mode_header)) +
[PATCH 54/62] x86/kvm: Add KVM specific VMMCALL handling under SEV-ES
From: Tom Lendacky Implement the callbacks to copy the processor state required by KVM to the GHCB. Signed-off-by: Tom Lendacky [ jroe...@suse.de: - Split out of a larger patch - Adapt to different callback functions ] Co-developed-by: Joerg Roedel Signed-off-by: Joerg Roedel --- arch/x86/kernel/kvm.c | 35 +-- 1 file changed, 29 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d817f255aed8..318eb906a0b5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -34,6 +34,8 @@ #include #include #include +#include +#include static int kvmapf = 1; @@ -711,13 +713,34 @@ static void __init kvm_init_platform(void) x86_platform.apic_post_init = kvm_apic_init; } +#if defined(CONFIG_AMD_MEM_ENCRYPT) +static void kvm_sev_es_hcall_prepare(struct ghcb *ghcb, struct pt_regs *regs) +{ + /* RAX and CPL are already in the GHCB */ + ghcb_set_rbx(ghcb, regs->bx); + ghcb_set_rcx(ghcb, regs->cx); + ghcb_set_rdx(ghcb, regs->dx); + ghcb_set_rsi(ghcb, regs->si); +} + +static bool kvm_sev_es_hcall_finish(struct ghcb *ghcb, struct pt_regs *regs) +{ + /* No checking of the return state needed */ + return true; +} +#endif + const __initconst struct hypervisor_x86 x86_hyper_kvm = { - .name = "KVM", - .detect = kvm_detect, - .type = X86_HYPER_KVM, - .init.guest_late_init = kvm_guest_init, - .init.x2apic_available = kvm_para_available, - .init.init_platform = kvm_init_platform, + .name = "KVM", + .detect = kvm_detect, + .type = X86_HYPER_KVM, + .init.guest_late_init = kvm_guest_init, + .init.x2apic_available = kvm_para_available, + .init.init_platform = kvm_init_platform, +#if defined(CONFIG_AMD_MEM_ENCRYPT) + .runtime.sev_es_hcall_prepare = kvm_sev_es_hcall_prepare, + .runtime.sev_es_hcall_finish= kvm_sev_es_hcall_finish, +#endif }; static __init int activate_jump_labels(void) -- 2.17.1 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH v4] drm/bochs: add drm_driver.release callback.
On Tue, Feb 11, 2020 at 02:52:18PM +0100, Gerd Hoffmann wrote: > Call bochs_unload via drm_driver.release to make sure we release stuff > when it is safe to do so. Use drm_dev_{enter,exit,unplug} to avoid > touching hardware after device removal. Tidy up here and there. > > v4: add changelog. > v3: use drm_dev_*(). > v2: move hardware deinit to pci_remove(). > > Signed-off-by: Gerd Hoffmann Reviewed-by: Daniel Vetter Btw I checked around whether there's anything else that obviously needs a drm_dev_enter/exit, and I spotted the !bochs->mmio check in bochs_hw_load_edid. That one looks like cargo-cult, there's a single caller in the init path, so either mmio works at that point or this is dead code ... slightly confusing. -Daniel > --- > drivers/gpu/drm/bochs/bochs_drv.c | 6 +++--- > drivers/gpu/drm/bochs/bochs_hw.c | 24 +++- > 2 files changed, 26 insertions(+), 4 deletions(-) > > diff --git a/drivers/gpu/drm/bochs/bochs_drv.c > b/drivers/gpu/drm/bochs/bochs_drv.c > index 10460878414e..addb0568c1af 100644 > --- a/drivers/gpu/drm/bochs/bochs_drv.c > +++ b/drivers/gpu/drm/bochs/bochs_drv.c > @@ -23,7 +23,6 @@ static void bochs_unload(struct drm_device *dev) > > bochs_kms_fini(bochs); > bochs_mm_fini(bochs); > - bochs_hw_fini(dev); > kfree(bochs); > dev->dev_private = NULL; > } > @@ -69,6 +68,7 @@ static struct drm_driver bochs_driver = { > .major = 1, > .minor = 0, > DRM_GEM_VRAM_DRIVER, > + .release= bochs_unload, > }; > > /* -- */ > @@ -148,9 +148,9 @@ static void bochs_pci_remove(struct pci_dev *pdev) > { > struct drm_device *dev = pci_get_drvdata(pdev); > > + drm_dev_unplug(dev); > drm_atomic_helper_shutdown(dev); > - drm_dev_unregister(dev); > - bochs_unload(dev); > + bochs_hw_fini(dev); > drm_dev_put(dev); > } > > diff --git a/drivers/gpu/drm/bochs/bochs_hw.c > b/drivers/gpu/drm/bochs/bochs_hw.c > index b615b7dfdd9d..952199cc0462 100644 > --- a/drivers/gpu/drm/bochs/bochs_hw.c > +++ b/drivers/gpu/drm/bochs/bochs_hw.c > @@ -4,6 +4,7 @@ > > #include > > +#include > #include > > #include "bochs.h" > @@ -194,6 +195,8 @@ void bochs_hw_fini(struct drm_device *dev) > { > struct bochs_device *bochs = dev->dev_private; > > + /* TODO: shot down existing vram mappings */ > + > if (bochs->mmio) > iounmap(bochs->mmio); > if (bochs->ioports) > @@ -207,6 +210,11 @@ void bochs_hw_fini(struct drm_device *dev) > void bochs_hw_setmode(struct bochs_device *bochs, > struct drm_display_mode *mode) > { > + int idx; > + > + if (!drm_dev_enter(bochs->dev, &idx)) > + return; > + > bochs->xres = mode->hdisplay; > bochs->yres = mode->vdisplay; > bochs->bpp = 32; > @@ -232,11 +240,18 @@ void bochs_hw_setmode(struct bochs_device *bochs, > > bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE, > VBE_DISPI_ENABLED | VBE_DISPI_LFB_ENABLED); > + > + drm_dev_exit(idx); > } > > void bochs_hw_setformat(struct bochs_device *bochs, > const struct drm_format_info *format) > { > + int idx; > + > + if (!drm_dev_enter(bochs->dev, &idx)) > + return; > + > DRM_DEBUG_DRIVER("format %c%c%c%c\n", >(format->format >> 0) & 0xff, >(format->format >> 8) & 0xff, > @@ -256,13 +271,18 @@ void bochs_hw_setformat(struct bochs_device *bochs, > __func__, format->format); > break; > } > + > + drm_dev_exit(idx); > } > > void bochs_hw_setbase(struct bochs_device *bochs, > int x, int y, int stride, u64 addr) > { > unsigned long offset; > - unsigned int vx, vy, vwidth; > + unsigned int vx, vy, vwidth, idx; > + > + if (!drm_dev_enter(bochs->dev, &idx)) > + return; > > bochs->stride = stride; > offset = (unsigned long)addr + > @@ -277,4 +297,6 @@ void bochs_hw_setbase(struct bochs_device *bochs, > bochs_dispi_write(bochs, VBE_DISPI_INDEX_VIRT_WIDTH, vwidth); > bochs_dispi_write(bochs, VBE_DISPI_INDEX_X_OFFSET, vx); > bochs_dispi_write(bochs, VBE_DISPI_INDEX_Y_OFFSET, vy); > + > + drm_dev_exit(idx); > } > -- > 2.18.2 > -- Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH RFC] virtio_balloon: conservative balloon page shrinking
On 2020/02/10 16:27, Wang, Wei W wrote: >> Well, my comment is rather: "Do not try to reserve guest's memory. In other >> words, do not try to maintain balloons on the guest side. Since host would >> be able to cache file data on the host's cache, guests would be able to >> quickly fetch file data from host's cache via normal I/O requests." ;-) > > Didn't this one. The discussion was about guest pagecache pages v.s. guest > balloon pages. > Why is host's pagecache here? I'm expecting a mode: "Guests should try to minimize pagecache pages (and teach host to treat reclaimed pages as if POSIX_FADV_DONTNEED) instead of managing guest balloon pages". In other words, as if while :; sleep 5; echo 1 > /proc/sys/vm/drop_caches; done is running in the guest's kernel. And as if echo 2 > /proc/sys/vm/drop_caches is triggered in the guest's kernel when host requested guests to reclaim memory. No long-life balloons. Guest balloons do not need to care about NUMA. Just leave the management of pagecache pages to the host. ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH v4] drm/cirrus: add drm_driver.release callback.
On Tue, Feb 11, 2020 at 02:55:22PM +0100, Gerd Hoffmann wrote: > Move final cleanups from cirrus_pci_remove() to the new callback. > Add drm_atomic_helper_shutdown() call to cirrus_pci_remove(). > > Use drm_dev_{enter,exit,unplug} to avoid touching hardware after > device removal. > > v4: add changelog. > v3: use drm_dev*. > v2: stop touching hardware after pci_remove(). > > Signed-off-by: Gerd Hoffmann I think you got them all with drm_dev_enter/exit. Reviewed-by: Daniel Vetter Aside: everyone ignores the return value of cirrus_fb_blit_rect and cirrus_mode_set (with atomic those shouldn't be able to fail anymore), could ditch those. -Daniel > --- > drivers/gpu/drm/cirrus/cirrus.c | 43 - > 1 file changed, 37 insertions(+), 6 deletions(-) > > diff --git a/drivers/gpu/drm/cirrus/cirrus.c b/drivers/gpu/drm/cirrus/cirrus.c > index a91fb0d7282c..d2ff63ce8eaf 100644 > --- a/drivers/gpu/drm/cirrus/cirrus.c > +++ b/drivers/gpu/drm/cirrus/cirrus.c > @@ -151,9 +151,13 @@ static int cirrus_pitch(struct drm_framebuffer *fb) > > static void cirrus_set_start_address(struct cirrus_device *cirrus, u32 > offset) > { > + int idx; > u32 addr; > u8 tmp; > > + if (!drm_dev_enter(&cirrus->dev, &idx)) > + return; > + > addr = offset >> 2; > wreg_crt(cirrus, 0x0c, (u8)((addr >> 8) & 0xff)); > wreg_crt(cirrus, 0x0d, (u8)(addr & 0xff)); > @@ -168,6 +172,8 @@ static void cirrus_set_start_address(struct cirrus_device > *cirrus, u32 offset) > tmp &= 0x7f; > tmp |= (addr >> 12) & 0x80; > wreg_crt(cirrus, 0x1d, tmp); > + > + drm_dev_exit(idx); > } > > static int cirrus_mode_set(struct cirrus_device *cirrus, > @@ -176,9 +182,12 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, > { > int hsyncstart, hsyncend, htotal, hdispend; > int vtotal, vdispend; > - int tmp; > + int tmp, idx; > int sr07 = 0, hdr = 0; > > + if (!drm_dev_enter(&cirrus->dev, &idx)) > + return -1; > + > htotal = mode->htotal / 8; > hsyncend = mode->hsync_end / 8; > hsyncstart = mode->hsync_start / 8; > @@ -264,6 +273,7 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, > hdr = 0xc5; > break; > default: > + drm_dev_exit(idx); > return -1; > } > > @@ -292,6 +302,8 @@ static int cirrus_mode_set(struct cirrus_device *cirrus, > > /* Unblank (needed on S3 resume, vgabios doesn't do it then) */ > outb(0x20, 0x3c0); > + > + drm_dev_exit(idx); > return 0; > } > > @@ -300,10 +312,16 @@ static int cirrus_fb_blit_rect(struct drm_framebuffer > *fb, > { > struct cirrus_device *cirrus = fb->dev->dev_private; > void *vmap; > + int idx, ret; > > + ret = -ENODEV; > + if (!drm_dev_enter(&cirrus->dev, &idx)) > + goto out; > + > + ret = -ENOMEM; > vmap = drm_gem_shmem_vmap(fb->obj[0]); > if (!vmap) > - return -ENOMEM; > + goto out_dev_exit; > > if (cirrus->cpp == fb->format->cpp[0]) > drm_fb_memcpy_dstclip(cirrus->vram, > @@ -323,7 +341,12 @@ static int cirrus_fb_blit_rect(struct drm_framebuffer > *fb, > WARN_ON_ONCE("cpp mismatch"); > > drm_gem_shmem_vunmap(fb->obj[0], vmap); > - return 0; > + ret = 0; > + > +out_dev_exit: > + drm_dev_exit(idx); > +out: > + return ret; > } > > static int cirrus_fb_blit_fullscreen(struct drm_framebuffer *fb) > @@ -502,6 +525,14 @@ static void cirrus_mode_config_init(struct cirrus_device > *cirrus) > > /* -- */ > > +static void cirrus_release(struct drm_device *dev) > +{ > + struct cirrus_device *cirrus = dev->dev_private; > + > + drm_mode_config_cleanup(dev); > + kfree(cirrus); > +} > + > DEFINE_DRM_GEM_FOPS(cirrus_fops); > > static struct drm_driver cirrus_driver = { > @@ -515,6 +546,7 @@ static struct drm_driver cirrus_driver = { > > .fops= &cirrus_fops, > DRM_GEM_SHMEM_DRIVER_OPS, > + .release = cirrus_release, > }; > > static int cirrus_pci_probe(struct pci_dev *pdev, > @@ -598,12 +630,11 @@ static void cirrus_pci_remove(struct pci_dev *pdev) > struct drm_device *dev = pci_get_drvdata(pdev); > struct cirrus_device *cirrus = dev->dev_private; > > - drm_dev_unregister(dev); > - drm_mode_config_cleanup(dev); > + drm_dev_unplug(dev); > + drm_atomic_helper_shutdown(dev); > iounmap(cirrus->mmio); > iounmap(cirrus->vram); > drm_dev_put(dev); > - kfree(cirrus); > pci_release_regions(pdev); > } > > -- > 2.18.2 > -- Daniel Vetter Software Engineer, Intel Corporation http://blog.ffwll.ch ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.o
Re: [PATCH v4] drm/virtio: add drm_driver.release callback.
On Tue, Feb 11, 2020 at 02:58:04PM +0100, Gerd Hoffmann wrote: > Split virtio_gpu_deinit(), move the drm shutdown and release to > virtio_gpu_release(). Drop vqs_ready variable, instead use > drm_dev_{enter,exit,unplug} to avoid touching hardware after > device removal. Tidy up here and there. > > v4: add changelog. > v3: use drm_dev_*(). > > Signed-off-by: Gerd Hoffmann Looks reasonable I think. Reviewed-by: Daniel Vetter I didn't review whether you need more drm_dev_enter/exit pairs, virtio is a bit more complex for that and I have no idea how exactly it works. Maybe for these more complex drivers we need a drm_dev_assert_entered() or so that uses the right srcu lockdep annotations to make sure we do this right. Sprinkling that check into a few low-level hw functions (touching registers or whatever) should catch most issues. -Daniel > --- > drivers/gpu/drm/virtio/virtgpu_drv.h | 3 ++- > drivers/gpu/drm/virtio/virtgpu_display.c | 1 - > drivers/gpu/drm/virtio/virtgpu_drv.c | 6 +- > drivers/gpu/drm/virtio/virtgpu_kms.c | 7 -- > drivers/gpu/drm/virtio/virtgpu_vq.c | 27 +--- > 5 files changed, 27 insertions(+), 17 deletions(-) > > diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h > b/drivers/gpu/drm/virtio/virtgpu_drv.h > index 7fd8361e1c9e..af9403e1cf78 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_drv.h > +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h > @@ -32,6 +32,7 @@ > #include > > #include > +#include > #include > #include > #include > @@ -177,7 +178,6 @@ struct virtio_gpu_device { > struct virtio_gpu_queue ctrlq; > struct virtio_gpu_queue cursorq; > struct kmem_cache *vbufs; > - bool vqs_ready; > > bool disable_notify; > bool pending_notify; > @@ -219,6 +219,7 @@ extern struct drm_ioctl_desc > virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; > /* virtio_kms.c */ > int virtio_gpu_init(struct drm_device *dev); > void virtio_gpu_deinit(struct drm_device *dev); > +void virtio_gpu_release(struct drm_device *dev); > int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file); > void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file > *file); > > diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c > b/drivers/gpu/drm/virtio/virtgpu_display.c > index 7b0f0643bb2d..af953db4a0c9 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_display.c > +++ b/drivers/gpu/drm/virtio/virtgpu_display.c > @@ -368,6 +368,5 @@ void virtio_gpu_modeset_fini(struct virtio_gpu_device > *vgdev) > > for (i = 0 ; i < vgdev->num_scanouts; ++i) > kfree(vgdev->outputs[i].edid); > - drm_atomic_helper_shutdown(vgdev->ddev); > drm_mode_config_cleanup(vgdev->ddev); > } > diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c > b/drivers/gpu/drm/virtio/virtgpu_drv.c > index 8cf27af3ad53..ab4bed78e656 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_drv.c > +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c > @@ -31,6 +31,7 @@ > #include > > #include > +#include > #include > #include > > @@ -135,7 +136,8 @@ static void virtio_gpu_remove(struct virtio_device *vdev) > { > struct drm_device *dev = vdev->priv; > > - drm_dev_unregister(dev); > + drm_dev_unplug(dev); > + drm_atomic_helper_shutdown(dev); > virtio_gpu_deinit(dev); > drm_dev_put(dev); > } > @@ -214,4 +216,6 @@ static struct drm_driver driver = { > .major = DRIVER_MAJOR, > .minor = DRIVER_MINOR, > .patchlevel = DRIVER_PATCHLEVEL, > + > + .release = virtio_gpu_release, > }; > diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c > b/drivers/gpu/drm/virtio/virtgpu_kms.c > index c1086df49816..4009c2f97d08 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_kms.c > +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c > @@ -199,7 +199,6 @@ int virtio_gpu_init(struct drm_device *dev) > virtio_gpu_modeset_init(vgdev); > > virtio_device_ready(vgdev->vdev); > - vgdev->vqs_ready = true; > > if (num_capsets) > virtio_gpu_get_capsets(vgdev, num_capsets); > @@ -234,12 +233,16 @@ void virtio_gpu_deinit(struct drm_device *dev) > struct virtio_gpu_device *vgdev = dev->dev_private; > > flush_work(&vgdev->obj_free_work); > - vgdev->vqs_ready = false; > flush_work(&vgdev->ctrlq.dequeue_work); > flush_work(&vgdev->cursorq.dequeue_work); > flush_work(&vgdev->config_changed_work); > vgdev->vdev->config->reset(vgdev->vdev); > vgdev->vdev->config->del_vqs(vgdev->vdev); > +} > + > +void virtio_gpu_release(struct drm_device *dev) > +{ > + struct virtio_gpu_device *vgdev = dev->dev_private; > > virtio_gpu_modeset_fini(vgdev); > virtio_gpu_free_vbufs(vgdev); > diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c > b/drivers/gpu/drm/virtio/virtgpu_vq.c > index a682c2fcbe9a..cfe9c54f87a3 100644 > --- a/drivers/gpu/drm/virtio/virtgpu_vq.c > +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c > @@ -330,7 +330,14 @@ sta
Re: [RFC PATCH 00/62] Linux as SEV-ES Guest Support
On Tue, Feb 11, 2020 at 02:51:54PM +0100, Joerg Roedel wrote: > NMI Special Handling > > > The last thing that needs special handling with SEV-ES are NMIs. > Hypervisors usually start to intercept IRET instructions when an NMI got > injected to find out when the NMI window is re-opened. But handling IRET > intercepts requires the hypervisor to access guest register state and is > not possible with SEV-ES. The specification under [1] solves this > problem with an NMI_COMPLETE message sent my the guest to the > hypervisor, upon which the hypervisor re-opens the NMI window for the > guest. > > This patch-set sends the NMI_COMPLETE message before the actual IRET, > while the kernel is still on a valid stack and kernel cr3. This opens > the NMI-window a few instructions early, but this is fine as under > x86-64 Linux NMI-nesting is safe. The alternative would be to > single-step over the IRET, but that requires more intrusive changes to > the entry code because it does not handle entries from kernel-mode while > on the entry stack. > > Besides the special handling above the patch-set contains the handlers > for the #VC exception and all the exit-codes specified in [1]. Oh gawd; so instead of improving the whole NMI situation, AMD went and made it worse still ?!? ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [RFC PATCH 00/62] Linux as SEV-ES Guest Support
On Tue, Feb 11, 2020 at 03:50:08PM +0100, Peter Zijlstra wrote: > Oh gawd; so instead of improving the whole NMI situation, AMD went and > made it worse still ?!? Well, depends on how you want to see it. Under SEV-ES an IRET will not re-open the NMI window, but the guest has to tell the hypervisor explicitly when it is ready to receive new NMIs via the NMI_COMPLETE message. NMIs stay blocked even when an exception happens in the handler, so this could also be seen as a (slight) improvement. Regards, Joerg ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [RFC PATCH 00/62] Linux as SEV-ES Guest Support
On Tue, Feb 11, 2020 at 7:43 AM Joerg Roedel wrote: > > On Tue, Feb 11, 2020 at 03:50:08PM +0100, Peter Zijlstra wrote: > > > Oh gawd; so instead of improving the whole NMI situation, AMD went and > > made it worse still ?!? > > Well, depends on how you want to see it. Under SEV-ES an IRET will not > re-open the NMI window, but the guest has to tell the hypervisor > explicitly when it is ready to receive new NMIs via the NMI_COMPLETE > message. NMIs stay blocked even when an exception happens in the > handler, so this could also be seen as a (slight) improvement. > I don't get it. VT-x has a VMCS bit "Interruptibility state"."Blocking by NMI" that tracks the NMI masking state. Would it have killed AMD to solve the problem they same way to retain architectural behavior inside a SEV-ES VM? --Andy ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 07/62] x86/boot/compressed/64: Disable red-zone usage
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > The x86-64 ABI defines a red-zone on the stack: > > The 128-byte area beyond the location pointed to by %rsp is > considered to be reserved and shall not be modified by signal or > interrupt handlers. 10 Therefore, functions may use this area for > temporary data that is not needed across function calls. In > particular, leaf functions may use this area for their entire stack > frame, rather than adjusting the stack pointer in the prologue and > epilogue. This area is known as the red zone. > > This is not compatible with exception handling, so disable it for the > pre-decompression boot code. Acked-by: Andy Lutomirski I admit that I thought we already supported exceptions this early. At least I seem to remember writing this code. Maybe it never got upstreamed? --Andy ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 08/62] x86/boot/compressed/64: Add IDT Infrastructure
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > Add code needed to setup an IDT in the early pre-decompression > boot-code. The IDT is loaded first in startup_64, which is after > EfiExitBootServices() has been called, and later reloaded when the > kernel image has been relocated to the end of the decompression area. > > This allows to setup different IDT handlers before and after the > relocation. > > diff --git a/arch/x86/boot/compressed/idt_64.c > b/arch/x86/boot/compressed/idt_64.c > new file mode 100644 > index ..46ecea671b90 > --- /dev/null > +++ b/arch/x86/boot/compressed/idt_64.c > @@ -0,0 +1,43 @@ > +// SPDX-License-Identifier: GPL-2.0-only > +#include > +#include > +#include "misc.h" > + > +static void set_idt_entry(int vector, void (*handler)(void)) > +{ > + unsigned long address = (unsigned long)handler; > + gate_desc entry; > + > + memset(&entry, 0, sizeof(entry)); > + > + entry.offset_low= (u16)(address & 0x); > + entry.segment = __KERNEL_CS; > + entry.bits.type = GATE_TRAP; ^^^ I realize we're not running a real kernel here, but GATE_TRAP is madness. Please use GATE_INTERRUPT. > + entry.bits.p= 1; > + entry.offset_middle = (u16)((address >> 16) & 0x); > + entry.offset_high = (u32)(address >> 32); > + > + memcpy(&boot_idt[vector], &entry, sizeof(entry)); > +} > + > +/* Have this here so we don't need to include */ > +static void load_boot_idt(const struct desc_ptr *dtr) > +{ > + asm volatile("lidt %0"::"m" (*dtr)); > +} > + > +/* Setup IDT before kernel jumping to .Lrelocated */ > +void load_stage1_idt(void) > +{ > + boot_idt_desc.address = (unsigned long)boot_idt; > + > + load_boot_idt(&boot_idt_desc); > +} > + > +/* Setup IDT after kernel jumping to .Lrelocated */ > +void load_stage2_idt(void) > +{ > + boot_idt_desc.address = (unsigned long)boot_idt; > + > + load_boot_idt(&boot_idt_desc); > +} > diff --git a/arch/x86/boot/compressed/idt_handlers_64.S > b/arch/x86/boot/compressed/idt_handlers_64.S > new file mode 100644 > index ..0b2b6cf747d2 > --- /dev/null > +++ b/arch/x86/boot/compressed/idt_handlers_64.S > @@ -0,0 +1,71 @@ > +/* SPDX-License-Identifier: GPL-2.0-only */ > +/* > + * Early IDT handler entry points > + * > + * Copyright (C) 2019 SUSE > + * > + * Author: Joerg Roedel > + */ > + > +#include > + > +.macro EXCEPTION_HANDLER name function error_code=0 > +SYM_FUNC_START(\name) > + > + /* Build pt_regs */ > + .if \error_code == 0 > + pushq $0 > + .endif cld > + > + pushq %rdi > + pushq %rsi > + pushq %rdx > + pushq %rcx > + pushq %rax > + pushq %r8 > + pushq %r9 > + pushq %r10 > + pushq %r11 > + pushq %rbx > + pushq %rbp > + pushq %r12 > + pushq %r13 > + pushq %r14 > + pushq %r15 > + > + /* Call handler with pt_regs */ > + movq%rsp, %rdi > + call\function > + > + /* Restore regs */ > + popq%r15 > + popq%r14 > + popq%r13 > + popq%r12 > + popq%rbp > + popq%rbx > + popq%r11 > + popq%r10 > + popq%r9 > + popq%r8 > + popq%rax > + popq%rcx > + popq%rdx > + popq%rsi > + popq%rdi if error_code? > + > + /* Remove error code and return */ > + addq$8, %rsp > + > + /* > +* Make sure we return to __KERNEL_CS - the CS selector on > +* the IRET frame might still be from an old BIOS GDT > +*/ > + movq$__KERNEL_CS, 8(%rsp) > + If this actually happens, you have a major bug. Please sanitize all the segment registers after installing the GDT rather than hacking around it here. ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 14/62] x86/boot/compressed/64: Add stage1 #VC handler
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > Add the first handler for #VC exceptions. At stage 1 there is no GHCB > yet becaue we might still be on the EFI page table and thus can't map > memory unencrypted. > > The stage 1 handler is limited to the MSR based protocol to talk to > the hypervisor and can only support CPUID exit-codes, but that is > enough to get to stage 2. > > Signed-off-by: Joerg Roedel > --- > arch/x86/boot/compressed/Makefile | 1 + > arch/x86/boot/compressed/idt_64.c | 4 ++ > arch/x86/boot/compressed/idt_handlers_64.S | 4 ++ > arch/x86/boot/compressed/misc.h| 1 + > arch/x86/boot/compressed/sev-es.c | 42 ++ > arch/x86/include/asm/msr-index.h | 1 + > arch/x86/include/asm/sev-es.h | 45 +++ > arch/x86/include/asm/trap_defs.h | 1 + > arch/x86/kernel/sev-es-shared.c| 66 ++ > 9 files changed, 165 insertions(+) > create mode 100644 arch/x86/boot/compressed/sev-es.c > create mode 100644 arch/x86/include/asm/sev-es.h > create mode 100644 arch/x86/kernel/sev-es-shared.c > > diff --git a/arch/x86/boot/compressed/Makefile > b/arch/x86/boot/compressed/Makefile > index e6b3e0fc48de..583678c78e1b 100644 > --- a/arch/x86/boot/compressed/Makefile > +++ b/arch/x86/boot/compressed/Makefile > @@ -84,6 +84,7 @@ ifdef CONFIG_X86_64 > vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o > vmlinux-objs-y += $(obj)/mem_encrypt.o > vmlinux-objs-y += $(obj)/pgtable_64.o > + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev-es.o > endif > > vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o > diff --git a/arch/x86/boot/compressed/idt_64.c > b/arch/x86/boot/compressed/idt_64.c > index 84ba57d9d436..bdd20dfd1fd0 100644 > --- a/arch/x86/boot/compressed/idt_64.c > +++ b/arch/x86/boot/compressed/idt_64.c > @@ -31,6 +31,10 @@ void load_stage1_idt(void) > { > boot_idt_desc.address = (unsigned long)boot_idt; > > +#ifdef CONFIG_AMD_MEM_ENCRYPT > + set_idt_entry(X86_TRAP_VC, boot_stage1_vc_handler); > +#endif > + > load_boot_idt(&boot_idt_desc); > } > > diff --git a/arch/x86/boot/compressed/idt_handlers_64.S > b/arch/x86/boot/compressed/idt_handlers_64.S > index f7f1ea66dcbf..330eb4e5c8b3 100644 > --- a/arch/x86/boot/compressed/idt_handlers_64.S > +++ b/arch/x86/boot/compressed/idt_handlers_64.S > @@ -71,3 +71,7 @@ SYM_FUNC_END(\name) > .code64 > > EXCEPTION_HANDLER boot_pf_handler do_boot_page_fault error_code=1 > + > +#ifdef CONFIG_AMD_MEM_ENCRYPT > +EXCEPTION_HANDLER boot_stage1_vc_handler no_ghcb_vc_handler error_code=1 > +#endif > diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h > index 4e5bc688f467..0e3508c5c15c 100644 > --- a/arch/x86/boot/compressed/misc.h > +++ b/arch/x86/boot/compressed/misc.h > @@ -141,5 +141,6 @@ extern struct desc_ptr boot_idt_desc; > > /* IDT Entry Points */ > void boot_pf_handler(void); > +void boot_stage1_vc_handler(void); > > #endif /* BOOT_COMPRESSED_MISC_H */ > diff --git a/arch/x86/boot/compressed/sev-es.c > b/arch/x86/boot/compressed/sev-es.c > new file mode 100644 > index ..8d13121a8cf2 > --- /dev/null > +++ b/arch/x86/boot/compressed/sev-es.c > @@ -0,0 +1,42 @@ > +// SPDX-License-Identifier: GPL-2.0 > +/* > + * AMD Encrypted Register State Support > + * > + * Author: Joerg Roedel > + */ > + > +#include > + > +#include > +#include > +#include > +#include > + > +#include "misc.h" > + > +static inline u64 read_ghcb_msr(void) > +{ > + unsigned long low, high; > + > + asm volatile("rdmsr\n" : "=a" (low), "=d" (high) : > + "c" (MSR_AMD64_SEV_ES_GHCB)); > + > + return ((high << 32) | low); > +} > + > +static inline void write_ghcb_msr(u64 val) > +{ > + u32 low, high; > + > + low = val & 0xUL; > + high = val >> 32; > + > + asm volatile("wrmsr\n" : : "c" (MSR_AMD64_SEV_ES_GHCB), > + "a"(low), "d" (high) : "memory"); > +} > + > +#undef __init > +#define __init > + > +/* Include code for early handlers */ > +#include "../../kernel/sev-es-shared.c" > diff --git a/arch/x86/include/asm/msr-index.h > b/arch/x86/include/asm/msr-index.h > index ebe1685e92dd..b6139b70db54 100644 > --- a/arch/x86/include/asm/msr-index.h > +++ b/arch/x86/include/asm/msr-index.h > @@ -432,6 +432,7 @@ > #define MSR_AMD64_IBSBRTARGET 0xc001103b > #define MSR_AMD64_IBSOPDATA4 0xc001103d > #define MSR_AMD64_IBS_REG_COUNT_MAX8 /* includes MSR_AMD64_IBSBRTARGET */ > +#define MSR_AMD64_SEV_ES_GHCB 0xc0010130 > #define MSR_AMD64_SEV 0xc0010131 > #define MSR_AMD64_SEV_ENABLED_BIT 0 > #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) > diff --git a/arch/x86/include/asm/sev-es.h b/arch/x86/include/asm/sev-es.h > new file mode 100644 > index
Re: [PATCH 18/62] x86/boot/compressed/64: Setup GHCB Based VC Exception handler
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > Install an exception handler for #VC exception that uses a GHCB. Also > add the infrastructure for handling different exit-codes by decoding > the instruction that caused the exception and error handling. > > diff --git a/arch/x86/boot/compressed/sev-es.c > b/arch/x86/boot/compressed/sev-es.c > index 8d13121a8cf2..02fb6f57128b 100644 > --- a/arch/x86/boot/compressed/sev-es.c > +++ b/arch/x86/boot/compressed/sev-es.c > @@ -8,12 +8,16 @@ > #include > > #include > +#include > #include > #include > #include > > #include "misc.h" > > +struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); > +struct ghcb *boot_ghcb; > + > static inline u64 read_ghcb_msr(void) > { > unsigned long low, high; > @@ -35,8 +39,95 @@ static inline void write_ghcb_msr(u64 val) > "a"(low), "d" (high) : "memory"); > } > > +static enum es_result es_fetch_insn_byte(struct es_em_ctxt *ctxt, > +unsigned int offset, > +char *buffer) > +{ > + char *rip = (char *)ctxt->regs->ip; > + > + buffer[offset] = rip[offset]; > + > + return ES_OK; > +} > + > +static enum es_result es_write_mem(struct es_em_ctxt *ctxt, > + void *dst, char *buf, size_t size) > +{ > + memcpy(dst, buf, size); > + > + return ES_OK; > +} > + > +static enum es_result es_read_mem(struct es_em_ctxt *ctxt, > + void *src, char *buf, size_t size) > +{ > + memcpy(buf, src, size); > + > + return ES_OK; > +} What are all these abstractions for? ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 19/62] x86/sev-es: Add support for handling IOIO exceptions
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Tom Lendacky > > Add support for decoding and handling #VC exceptions for IOIO events. > > Signed-off-by: Tom Lendacky > [ jroe...@suse.de: Adapted code to #VC handling framework ] > Co-developed-by: Joerg Roedel > Signed-off-by: Joerg Roedel It would be nice if this could reuse the existing in-kernel instruction decoder. Is there some reason it can't? --Andy ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 25/62] x86/head/64: Install boot GDT
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > Handling exceptions during boot requires a working GDT. The kernel GDT > is not yet ready for use, so install a temporary boot GDT. > > Signed-off-by: Joerg Roedel > --- > arch/x86/kernel/head_64.S | 26 ++ > 1 file changed, 26 insertions(+) > > diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S > index 4bbc770af632..5a3cde971cb7 100644 > --- a/arch/x86/kernel/head_64.S > +++ b/arch/x86/kernel/head_64.S > @@ -72,6 +72,20 @@ SYM_CODE_START_NOALIGN(startup_64) > /* Set up the stack for verify_cpu(), similar to initial_stack below > */ > leaq(__end_init_task - SIZEOF_PTREGS)(%rip), %rsp > > + /* Setup boot GDT descriptor and load boot GDT */ > + leaqboot_gdt(%rip), %rax > + movq%rax, boot_gdt_base(%rip) > + lgdtboot_gdt_descr(%rip) > + > + /* GDT loaded - switch to __KERNEL_CS so IRET works reliably */ > + pushq $__KERNEL_CS > + leaq.Lon_kernel_cs(%rip), %rax > + pushq %rax > + lretq > + > +.Lon_kernel_cs: > + UNWIND_HINT_EMPTY I would suggest fixing at least SS as well. ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 23/62] x86/idt: Move IDT to data segment
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > With SEV-ES, exception handling is needed very early, even before the > kernel has cleared the bss segment. In order to prevent clearing the > currently used IDT, move the IDT to the data segment. Ugh. At the very least this needs a comment in the code. I had a patch to fix the kernel ELF loader to clear BSS, which would fix this problem once and for all, but it didn't work due to the messy way that the decompressor handles memory. I never got around to fixing this, sadly. ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 30/62] x86/head/64: Move early exception dispatch to C code
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > Move the assembly coded dispatch between page-faults and all other > exceptions to C code to make it easier to maintain and extend. > > Signed-off-by: Joerg Roedel > --- > arch/x86/kernel/head64.c | 20 > arch/x86/kernel/head_64.S | 11 +-- > 2 files changed, 21 insertions(+), 10 deletions(-) > > diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c > index 7cdfb7113811..d83c62ebaa85 100644 > --- a/arch/x86/kernel/head64.c > +++ b/arch/x86/kernel/head64.c > @@ -36,6 +36,8 @@ > #include > #include > #include > +#include > +#include > > /* > * Manage page tables very early on. > @@ -377,6 +379,24 @@ int __init early_make_pgtable(unsigned long address) > return __early_make_pgtable(address, pmd); > } > > +void __init early_exception(struct pt_regs *regs, int trapnr) > +{ > + unsigned long cr2; > + int r; How about int (or bool) handled; Or just if (!early_make_pgtable) return; This would also be nicer if you inverted the return value so that true means "I handled it". --Andy ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 35/62] x86/sev-es: Setup per-cpu GHCBs for the runtime handler
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Tom Lendacky > > The runtime handler needs a GHCB per CPU. Set them up and map them > unencrypted. > > Signed-off-by: Tom Lendacky > Signed-off-by: Joerg Roedel > --- > arch/x86/include/asm/mem_encrypt.h | 2 ++ > arch/x86/kernel/sev-es.c | 25 - > arch/x86/kernel/traps.c| 3 +++ > 3 files changed, 29 insertions(+), 1 deletion(-) > > diff --git a/arch/x86/include/asm/mem_encrypt.h > b/arch/x86/include/asm/mem_encrypt.h > index 6f61bb93366a..d48e7be9bb49 100644 > --- a/arch/x86/include/asm/mem_encrypt.h > +++ b/arch/x86/include/asm/mem_encrypt.h > @@ -48,6 +48,7 @@ int __init early_set_memory_encrypted(unsigned long vaddr, > unsigned long size); > void __init mem_encrypt_init(void); > void __init mem_encrypt_free_decrypted_mem(void); > > +void __init encrypted_state_init_ghcbs(void); > bool sme_active(void); > bool sev_active(void); > bool sev_es_active(void); > @@ -71,6 +72,7 @@ static inline void __init sme_early_init(void) { } > static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } > static inline void __init sme_enable(struct boot_params *bp) { } > > +static inline void encrypted_state_init_ghcbs(void) { } > static inline bool sme_active(void) { return false; } > static inline bool sev_active(void) { return false; } > static inline bool sev_es_active(void) { return false; } > diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c > index 0e0b28477627..9a5530857db7 100644 > --- a/arch/x86/kernel/sev-es.c > +++ b/arch/x86/kernel/sev-es.c > @@ -8,8 +8,11 @@ > */ > > #include /* For show_regs() */ > -#include > +#include > +#include > #include > +#include > +#include > #include > > #include > @@ -28,6 +31,9 @@ struct ghcb boot_ghcb_page __bss_decrypted > __aligned(PAGE_SIZE); > */ > struct ghcb __initdata *boot_ghcb; > > +/* Runtime GHCBs */ > +static DEFINE_PER_CPU_DECRYPTED(struct ghcb, ghcb_page) __aligned(PAGE_SIZE); Hmm. This is a largeish amount of memory on large non-SEV-ES systems. Maybe store a pointer instead? It would be even better if it could be DEFINE_PER_CPU like this but be discarded if we don't need it, but I don't think we have the infrastructure for that. --Andy ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
Re: [PATCH 39/62] x86/sev-es: Harden runtime #VC handler for exceptions from user-space
On Tue, Feb 11, 2020 at 5:53 AM Joerg Roedel wrote: > > From: Joerg Roedel > > Send SIGBUS to the user-space process that caused the #VC exception > instead of killing the machine. Also ratelimit the error messages so > that user-space can't flood the kernel log. What would cause this? CPUID? Something else? --Andy ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
[PATCH] char: virtio: Replace zero-length array with flexible-array member
The current codebase makes use of the zero-length array language extension to the C90 standard, but the preferred mechanism to declare variable-length types such as these ones is a flexible array member[1][2], introduced in C99: struct foo { int stuff; struct boo array[]; }; By making use of the mechanism above, we will get a compiler warning in case the flexible array does not occur last in the structure, which will help us prevent some kind of undefined behavior bugs from being inadvertenly introduced[3] to the codebase from now on. This issue was found with the help of Coccinelle. [1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html [2] https://github.com/KSPP/linux/issues/21 [3] commit 76497732932f ("cxgb3/l2t: Fix undefined behaviour") Signed-off-by: Gustavo A. R. Silva --- drivers/char/virtio_console.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index fbeb71953526..a136239e4c14 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -125,7 +125,7 @@ struct port_buffer { unsigned int sgpages; /* sg is used if spages > 0. sg must be the last in is struct */ - struct scatterlist sg[0]; + struct scatterlist sg[]; }; /* -- 2.25.0 ___ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization