diff --git a/debian/changelog b/debian/changelog index eddf1b8..9e214e0 100644 --- a/debian/changelog +++ b/debian/changelog @@ -1,3 +1,13 @@ +qemu (1:2.11+dfsg-1ubuntu7.20) bionic; urgency=medium + + * d/p/lp-1842774-s390x-cpumodel-Add-the-z15-name-to-the-description-o.patch: + update the z15 model name (LP: #1842774) + * d/p/u/lp-1847948-*: allow MSIX BAR mapping on VFIO in general and use that + instead of emulation on ppc64 increasing performance of e.g. NVME + passthrough (LP: #1847948) + + -- Christian Ehrhardt Tue, 15 Oct 2019 11:23:23 +0200 + qemu (1:2.11+dfsg-1ubuntu7.19) bionic; urgency=medium * d/p/ubuntu/lp-1837869-block-Fix-flags-in-reopen-queue.patch: avoid diff --git a/debian/patches/lp-1847948-vfio-Use-a-trace-point-when-a-RAM-section-cannot-be-.patch b/debian/patches/lp-1847948-vfio-Use-a-trace-point-when-a-RAM-section-cannot-be-.patch new file mode 100644 index 0000000..ee036ab --- /dev/null +++ b/debian/patches/lp-1847948-vfio-Use-a-trace-point-when-a-RAM-section-cannot-be-.patch @@ -0,0 +1,81 @@ +From 5c08600547c059e3fd072995f9f367cdaf3c7d9d Mon Sep 17 00:00:00 2001 +From: Eric Auger +Date: Wed, 4 Apr 2018 22:30:50 +0200 +Subject: [PATCH] vfio: Use a trace point when a RAM section cannot be DMA + mapped +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +Commit 567b5b309abe ("vfio/pci: Relax DMA map errors for MMIO regions") +added an error message if a passed memory section address or size +is not aligned to the page size and thus cannot be DMA mapped. + +This patch fixes the trace by printing the region name and the +memory region section offset within the address space (instead of +offset_within_region). + +We also turn the error_report into a trace event. Indeed, In some +cases, the traces can be confusing to non expert end-users and +let think the use case does not work (whereas it works as before). + +This is the case where a BAR is successively mapped at different +GPAs and its sections are not compatible with dma map. The listener +is called several times and traces are issued for each intermediate +mapping. The end-user cannot easily match those GPAs against the +final GPA output by lscpi. So let's keep those information to +informed users. In mid term, the plan is to advise the user about +BAR relocation relevance. + +Fixes: 567b5b309abe ("vfio/pci: Relax DMA map errors for MMIO regions") +Signed-off-by: Eric Auger +Reviewed-by: Philippe Mathieu-Daudé +Reviewed-by: Alexey Kardashevskiy +Signed-off-by: Alex Williamson + +Origin: upstream, https://git.qemu.org/?p=qemu.git;a=commit;h=5c08600547c05 +Bug-Ubuntu: https://bugs.launchpad.net/bugs/1847948 +Last-Update: 2019-10-16 + +--- + hw/vfio/common.c | 11 +++++------ + hw/vfio/trace-events | 1 + + 2 files changed, 6 insertions(+), 6 deletions(-) + +diff --git a/hw/vfio/common.c b/hw/vfio/common.c +index 5e84716218..07ffa0ba10 100644 +--- a/hw/vfio/common.c ++++ b/hw/vfio/common.c +@@ -548,12 +548,11 @@ static void vfio_listener_region_add(MemoryListener *listener, + hwaddr pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1; + + if ((iova & pgmask) || (int128_get64(llsize) & pgmask)) { +- error_report("Region 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx +- " is not aligned to 0x%"HWADDR_PRIx +- " and cannot be mapped for DMA", +- section->offset_within_region, +- int128_getlo(section->size), +- pgmask + 1); ++ trace_vfio_listener_region_add_no_dma_map( ++ memory_region_name(section->mr), ++ section->offset_within_address_space, ++ int128_getlo(section->size), ++ pgmask + 1); + return; + } + } +diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events +index 79f63a2ff6..20109cb758 100644 +--- a/hw/vfio/trace-events ++++ b/hw/vfio/trace-events +@@ -90,6 +90,7 @@ vfio_iommu_map_notify(const char *op, uint64_t iova_start, uint64_t iova_end) "i + vfio_listener_region_add_skip(uint64_t start, uint64_t end) "SKIPPING region_add 0x%"PRIx64" - 0x%"PRIx64 + vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64 + vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]" ++vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" + vfio_listener_region_del_skip(uint64_t start, uint64_t end) "SKIPPING region_del 0x%"PRIx64" - 0x%"PRIx64 + vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 + vfio_disconnect_container(int fd) "close container->fd=%d" +-- +2.23.0 + diff --git a/debian/patches/lp-1847948-vfio-pci-Relax-DMA-map-errors-for-MMIO-regions.patch b/debian/patches/lp-1847948-vfio-pci-Relax-DMA-map-errors-for-MMIO-regions.patch new file mode 100644 index 0000000..7994041 --- /dev/null +++ b/debian/patches/lp-1847948-vfio-pci-Relax-DMA-map-errors-for-MMIO-regions.patch @@ -0,0 +1,137 @@ +From 567b5b309abe744b1098018a2eb157e7109c9f30 Mon Sep 17 00:00:00 2001 +From: Alexey Kardashevskiy +Date: Tue, 13 Mar 2018 11:17:30 -0600 +Subject: [PATCH] vfio/pci: Relax DMA map errors for MMIO regions + +At the moment if vfio_memory_listener is registered in the system memory +address space, it maps/unmaps every RAM memory region for DMA. +It expects system page size aligned memory sections so vfio_dma_map +would not fail and so far this has been the case. A mapping failure +would be fatal. A side effect of such behavior is that some MMIO pages +would not be mapped silently. + +However we are going to change MSIX BAR handling so we will end having +non-aligned sections in vfio_memory_listener (more details is in +the next patch) and vfio_dma_map will exit QEMU. + +In order to avoid fatal failures on what previously was not a failure and +was just silently ignored, this checks the section alignment to +the smallest supported IOMMU page size and prints an error if not aligned; +it also prints an error if vfio_dma_map failed despite the page size check. +Both errors are not fatal; only MMIO RAM regions are checked +(aka "RAM device" regions). + +If the amount of errors printed is overwhelming, the MSIX relocation +could be used to avoid excessive error output. + +This is unlikely to cause any behavioral change. + +Signed-off-by: Alexey Kardashevskiy +[aw: Fix Int128 bit ops] +Signed-off-by: Alex Williamson + +Origin: upstream, https://git.qemu.org/?p=qemu.git;a=commit;h=567b5b309abe7 +Bug-Ubuntu: https://bugs.launchpad.net/bugs/1847948 +Last-Update: 2019-10-16 + +--- + hw/vfio/common.c | 55 ++++++++++++++++++++++++++++++++++++++++++------ + 1 file changed, 49 insertions(+), 6 deletions(-) + +diff --git a/hw/vfio/common.c b/hw/vfio/common.c +index 6a8203a532..07c03d78b6 100644 +--- a/hw/vfio/common.c ++++ b/hw/vfio/common.c +@@ -544,18 +544,40 @@ static void vfio_listener_region_add(MemoryListener *listener, + + llsize = int128_sub(llend, int128_make64(iova)); + ++ if (memory_region_is_ram_device(section->mr)) { ++ hwaddr pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1; ++ ++ if ((iova & pgmask) || (int128_get64(llsize) & pgmask)) { ++ error_report("Region 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx ++ " is not aligned to 0x%"HWADDR_PRIx ++ " and cannot be mapped for DMA", ++ section->offset_within_region, ++ int128_getlo(section->size), ++ pgmask + 1); ++ return; ++ } ++ } ++ + ret = vfio_dma_map(container, iova, int128_get64(llsize), + vaddr, section->readonly); + if (ret) { + error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " + "0x%"HWADDR_PRIx", %p) = %d (%m)", + container, iova, int128_get64(llsize), vaddr, ret); ++ if (memory_region_is_ram_device(section->mr)) { ++ /* Allow unexpected mappings not to be fatal for RAM devices */ ++ return; ++ } + goto fail; + } + + return; + + fail: ++ if (memory_region_is_ram_device(section->mr)) { ++ error_report("failed to vfio_dma_map. pci p2p may not work"); ++ return; ++ } + /* + * On the initfn path, store the first error in the container so we + * can gracefully fail. Runtime, there's not much we can do other +@@ -577,6 +599,7 @@ static void vfio_listener_region_del(MemoryListener *listener, + hwaddr iova, end; + Int128 llend, llsize; + int ret; ++ bool try_unmap = true; + + if (vfio_listener_skipped_section(section)) { + trace_vfio_listener_region_del_skip( +@@ -629,14 +652,34 @@ static void vfio_listener_region_del(MemoryListener *listener, + + trace_vfio_listener_region_del(iova, end); + +- ret = vfio_dma_unmap(container, iova, int128_get64(llsize)); +- memory_region_unref(section->mr); +- if (ret) { +- error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " +- "0x%"HWADDR_PRIx") = %d (%m)", +- container, iova, int128_get64(llsize), ret); ++ if (memory_region_is_ram_device(section->mr)) { ++ hwaddr pgmask; ++ VFIOHostDMAWindow *hostwin; ++ bool hostwin_found = false; ++ ++ QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { ++ if (hostwin->min_iova <= iova && end <= hostwin->max_iova) { ++ hostwin_found = true; ++ break; ++ } ++ } ++ assert(hostwin_found); /* or region_add() would have failed */ ++ ++ pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1; ++ try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask)); ++ } ++ ++ if (try_unmap) { ++ ret = vfio_dma_unmap(container, iova, int128_get64(llsize)); ++ if (ret) { ++ error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " ++ "0x%"HWADDR_PRIx") = %d (%m)", ++ container, iova, int128_get64(llsize), ret); ++ } + } + ++ memory_region_unref(section->mr); ++ + if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { + vfio_spapr_remove_window(container, + section->offset_within_address_space); +-- +2.23.0 + diff --git a/debian/patches/series b/debian/patches/series index d6a690a..b2015aa 100644 --- a/debian/patches/series +++ b/debian/patches/series @@ -123,3 +123,8 @@ ubuntu/lp-1836154-09-s390-cpumodel-fix-description-for-the-new-vector-fac.patch ubuntu/lp-1836154-s390x-cpumodel-remove-esort-from-the-default-model.patch ubuntu/lp-1836154-s390x-cpumodel-also-change-name-of-vxbeh.patch ubuntu/lp-1837869-block-Fix-flags-in-reopen-queue.patch +ubuntu/lp-1842774-s390x-cpumodel-Add-the-z15-name-to-the-description-o.patch +ubuntu/lp-1847948-vfio-pci-Allow-mmap-of-MSIX-BAR.patch +ubuntu/lp-1847948-ppc-spapr-vfio-Turn-off-MSIX-emulation-for-VFIO-devi.patch +lp-1847948-vfio-pci-Relax-DMA-map-errors-for-MMIO-regions.patch +lp-1847948-vfio-Use-a-trace-point-when-a-RAM-section-cannot-be-.patch diff --git a/debian/patches/ubuntu/lp-1842774-s390x-cpumodel-Add-the-z15-name-to-the-description-o.patch b/debian/patches/ubuntu/lp-1842774-s390x-cpumodel-Add-the-z15-name-to-the-description-o.patch new file mode 100644 index 0000000..e888e41 --- /dev/null +++ b/debian/patches/ubuntu/lp-1842774-s390x-cpumodel-Add-the-z15-name-to-the-description-o.patch @@ -0,0 +1,30 @@ +From 7505deca0bfa859136ec6419dbafc504f22fcac2 Mon Sep 17 00:00:00 2001 +From: Christian Borntraeger +Date: Wed, 18 Sep 2019 16:42:14 +0200 +Subject: [PATCH] s390x/cpumodel: Add the z15 name to the description of gen15a + +We now know that gen15a is called z15. + +Reviewed-by: David Hildenbrand +Signed-off-by: Christian Borntraeger + +Backport-Note: context slightly changed for z14.2 +Origin: backport, https://git.qemu.org/?p=qemu.git;a=commit;h=7505deca +Bug-Ubuntu: https://bugs.launchpad.net/bugs/1842774 +Last-Update: 2019-09-24 + +--- + target/s390x/cpu_models.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/target/s390x/cpu_models.c ++++ b/target/s390x/cpu_models.c +@@ -79,7 +79,7 @@ static S390CPUDef s390_cpu_defs[] = { + CPUDEF_INIT(0x2965, 13, 2, 47, 0x08000000U, "z13s", "IBM z13s GA1"), + CPUDEF_INIT(0x3906, 14, 1, 47, 0x08000000U, "z14", "IBM z14 GA1"), + CPUDEF_INIT(0x3907, 14, 1, 47, 0x08000000U, "z14ZR1", "IBM z14 Model ZR1 GA1"), +- CPUDEF_INIT(0x8561, 15, 1, 47, 0x08000000U, "gen15a", "IBM 8561 GA1"), ++ CPUDEF_INIT(0x8561, 15, 1, 47, 0x08000000U, "gen15a", "IBM z15 GA1"), + CPUDEF_INIT(0x8562, 15, 1, 47, 0x08000000U, "gen15b", "IBM 8562 GA1"), + }; + diff --git a/debian/patches/ubuntu/lp-1847948-ppc-spapr-vfio-Turn-off-MSIX-emulation-for-VFIO-devi.patch b/debian/patches/ubuntu/lp-1847948-ppc-spapr-vfio-Turn-off-MSIX-emulation-for-VFIO-devi.patch new file mode 100644 index 0000000..8d3f8b0 --- /dev/null +++ b/debian/patches/ubuntu/lp-1847948-ppc-spapr-vfio-Turn-off-MSIX-emulation-for-VFIO-devi.patch @@ -0,0 +1,82 @@ +From fcad0d2121976df4b422b4007a5eb7fcaac01134 Mon Sep 17 00:00:00 2001 +From: Alexey Kardashevskiy +Date: Tue, 13 Mar 2018 11:17:31 -0600 +Subject: [PATCH] ppc/spapr, vfio: Turn off MSIX emulation for VFIO devices + +This adds a possibility for the platform to tell VFIO not to emulate MSIX +so MMIO memory regions do not get split into chunks in flatview and +the entire page can be registered as a KVM memory slot and make direct +MMIO access possible for the guest. + +This enables the entire MSIX BAR mapping to the guest for the pseries +platform in order to achieve the maximum MMIO preformance for certain +devices. + +Tested on: +LSI Logic / Symbios Logic SAS3008 PCI-Express Fusion-MPT SAS-3 (rev 02) + +Signed-off-by: Alexey Kardashevskiy +Reviewed-by: David Gibson +Signed-off-by: Alex Williamson + +Origin: upstream, https://git.qemu.org/?p=qemu.git;a=commit;h=fcad0d2121976df4b422b4007a5e +Bug-Ubuntu: https://bugs.launchpad.net/bugs/1847948 +Last-Update: 2019-10-15 + +--- + hw/ppc/spapr.c | 7 +++++++ + hw/vfio/pci.c | 13 +++++++++++++ + 2 files changed, 20 insertions(+) + +diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c +index 7e1c858566..032d03423f 100644 +--- a/hw/ppc/spapr.c ++++ b/hw/ppc/spapr.c +@@ -2855,6 +2855,11 @@ static void spapr_set_modern_hotplug_events(Object *obj, bool value, + spapr->use_hotplug_event_source = value; + } + ++static bool spapr_get_msix_emulation(Object *obj, Error **errp) ++{ ++ return true; ++} ++ + static char *spapr_get_resize_hpt(Object *obj, Error **errp) + { + sPAPRMachineState *spapr = SPAPR_MACHINE(obj); +@@ -2936,6 +2941,8 @@ static void spapr_instance_init(Object *obj) + object_property_set_description(obj, "vsmt", + "Virtual SMT: KVM behaves as if this were" + " the host's SMT mode", &error_abort); ++ object_property_add_bool(obj, "vfio-no-msix-emulation", ++ spapr_get_msix_emulation, NULL, NULL); + } + + static void spapr_machine_finalizefn(Object *obj) +diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c +index 02974f4eb9..b9bc6cd310 100644 +--- a/hw/vfio/pci.c ++++ b/hw/vfio/pci.c +@@ -1581,6 +1581,19 @@ static int vfio_msix_setup(VFIOPCIDevice *vdev, int pos, Error **errp) + */ + memory_region_set_enabled(&vdev->pdev.msix_pba_mmio, false); + ++ /* ++ * The emulated machine may provide a paravirt interface for MSIX setup ++ * so it is not strictly necessary to emulate MSIX here. This becomes ++ * helpful when frequently accessed MMIO registers are located in ++ * subpages adjacent to the MSIX table but the MSIX data containing page ++ * cannot be mapped because of a host page size bigger than the MSIX table ++ * alignment. ++ */ ++ if (object_property_get_bool(OBJECT(qdev_get_machine()), ++ "vfio-no-msix-emulation", NULL)) { ++ memory_region_set_enabled(&vdev->pdev.msix_table_mmio, false); ++ } ++ + return 0; + } + +-- +2.23.0 + diff --git a/debian/patches/ubuntu/lp-1847948-vfio-pci-Allow-mmap-of-MSIX-BAR.patch b/debian/patches/ubuntu/lp-1847948-vfio-pci-Allow-mmap-of-MSIX-BAR.patch new file mode 100644 index 0000000..b0c1550 --- /dev/null +++ b/debian/patches/ubuntu/lp-1847948-vfio-pci-Allow-mmap-of-MSIX-BAR.patch @@ -0,0 +1,95 @@ +From ae0215b2bb56a9d5321a185dde133bfdd306a4c0 Mon Sep 17 00:00:00 2001 +From: Alexey Kardashevskiy +Date: Tue, 13 Mar 2018 11:17:31 -0600 +Subject: [PATCH] vfio-pci: Allow mmap of MSIX BAR + +At the moment we unconditionally avoid mapping MSIX data of a BAR and +emulate MSIX table in QEMU. However it is 1) not always necessary as +a platform may provide a paravirt interface for MSIX configuration; +2) can affect the speed of MMIO access by emulating them in QEMU when +frequently accessed registers share same system page with MSIX data, +this is particularly a problem for systems with the page size bigger +than 4KB. + +A new capability - VFIO_REGION_INFO_CAP_MSIX_MAPPABLE - has been added +to the kernel [1] which tells the userspace that mapping of the MSIX data +is possible now. This makes use of it so from now on QEMU tries mapping +the entire BAR as a whole and emulate MSIX on top of that. + +[1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=a32295c612c57990d17fb0f41e7134394b2f35f6 + +Signed-off-by: Alexey Kardashevskiy +Reviewed-by: David Gibson +Signed-off-by: Alex Williamson + +Origin: upstream, https://git.qemu.org/?p=qemu.git;a=commit;h=ae0215b2bb56a9d5321a185dde13 +Bug-Ubuntu: https://bugs.launchpad.net/bugs/1847948 +Last-Update: 2019-10-15 + +--- + hw/vfio/common.c | 15 +++++++++++++++ + hw/vfio/pci.c | 9 +++++++++ + include/hw/vfio/vfio-common.h | 1 + + 3 files changed, 25 insertions(+) + +diff --git a/hw/vfio/common.c b/hw/vfio/common.c +index 07c03d78b6..5e84716218 100644 +--- a/hw/vfio/common.c ++++ b/hw/vfio/common.c +@@ -1471,6 +1471,21 @@ int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, + return -ENODEV; + } + ++bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type) ++{ ++ struct vfio_region_info *info = NULL; ++ bool ret = false; ++ ++ if (!vfio_get_region_info(vbasedev, region, &info)) { ++ if (vfio_get_region_info_cap(info, cap_type)) { ++ ret = true; ++ } ++ g_free(info); ++ } ++ ++ return ret; ++} ++ + /* + * Interfaces for IBM EEH (Enhanced Error Handling) + */ +diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c +index b9d2c12b82..02974f4eb9 100644 +--- a/hw/vfio/pci.c ++++ b/hw/vfio/pci.c +@@ -1294,6 +1294,15 @@ static void vfio_pci_fixup_msix_region(VFIOPCIDevice *vdev) + off_t start, end; + VFIORegion *region = &vdev->bars[vdev->msix->table_bar].region; + ++ /* ++ * If the host driver allows mapping of a MSIX data, we are going to ++ * do map the entire BAR and emulate MSIX table on top of that. ++ */ ++ if (vfio_has_region_cap(&vdev->vbasedev, region->nr, ++ VFIO_REGION_INFO_CAP_MSIX_MAPPABLE)) { ++ return; ++ } ++ + /* + * We expect to find a single mmap covering the whole BAR, anything else + * means it's either unsupported or already setup. +diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h +index c5efa32750..d9360148e6 100644 +--- a/include/hw/vfio/vfio-common.h ++++ b/include/hw/vfio/vfio-common.h +@@ -193,6 +193,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index, + struct vfio_region_info **info); + int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, + uint32_t subtype, struct vfio_region_info **info); ++bool vfio_has_region_cap(VFIODevice *vbasedev, int region, uint16_t cap_type); + #endif + extern const MemoryListener vfio_prereg_listener; + +-- +2.23.0 +